[RFC PATCH 00/29] arm64: Scalable Vector Extension core support

@@ -19,9 +19,11 @@
 
 #include <linux/compat.h>
 #include <linux/errno.h>
+#include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/freezer.h>
+#include <linux/stddef.h>
 #include <linux/uaccess.h>
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>

@@ -45,6 +47,10 @@ struct rt_sigframe {
 	u64 lr;
 };
 
+struct rt_sigframe_user_layout {
+	struct rt_sigframe __user *sigframe;
+};
+
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 {
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;

@@ -92,12 +98,86 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
 	return err ? -EFAULT : 0;
 }
 
+struct user_ctxs {
+	struct fpsimd_context __user *fpsimd;
+};
+
+static int parse_user_sigframe(struct user_ctxs *user,
+			       struct rt_sigframe __user *sf)
+{
+	struct sigcontext __user *sc = &sf->uc.uc_mcontext;
+	struct _aarch64_ctx __user *head =
+		(struct _aarch64_ctx __user *)&sc->__reserved;
+	size_t offset = 0;
+
+	user->fpsimd = NULL;
+
+	while (1) {
+		int err;
+		u32 magic, size;
+
+		head = (struct _aarch64_ctx __user *)&sc->__reserved[offset];
+		if (!IS_ALIGNED((unsigned long)head, 16))
+			goto invalid;
+
+		err = 0;
+		__get_user_error(magic, &head->magic, err);
+		__get_user_error(size, &head->size, err);
+		if (err)
+			return err;
+
+		switch (magic) {
+		case 0:
+			if (size)
+				goto invalid;
+
+			goto done;
+
+		case FPSIMD_MAGIC:
+			if (user->fpsimd)
+				goto invalid;
+
+			if (offset > sizeof(sc->__reserved) -
+					sizeof(*user->fpsimd) ||
+			    size < sizeof(*user->fpsimd))
+				goto invalid;
+
+			user->fpsimd = (struct fpsimd_context __user *)head;
+			break;
+
+		case ESR_MAGIC:
+			/* ignore */
+			break;
+
+		default:
+			goto invalid;
+		}
+
+		if (size < sizeof(*head))
+			goto invalid;
+
+		if (size > sizeof(sc->__reserved) - (sizeof(*head) + offset))
+			goto invalid;
+
+		offset += size;
+	}
+
+done:
+	if (!user->fpsimd)
+		goto invalid;
+
+	return 0;
+
+invalid:
+	return -EINVAL;
+}
+
 static int restore_sigframe(struct pt_regs *regs,
 			    struct rt_sigframe __user *sf)
 {
 	sigset_t set;
 	int i, err;
-	void *aux = sf->uc.uc_mcontext.__reserved;
+	struct user_ctxs user;
 
 	err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set));
 	if (err == 0)

@@ -116,12 +196,11 @@ static int restore_sigframe(struct pt_regs *regs,
 	regs->syscallno = ~0UL;
 
 	err |= !valid_user_regs(&regs->user_regs, current);
+	if (err == 0)
+		err = parse_user_sigframe(&user, sf);
 
-	if (err == 0) {
-		struct fpsimd_context *fpsimd_ctx =
-			container_of(aux, struct fpsimd_context, head);
-		err |= restore_fpsimd_context(fpsimd_ctx);
-	}
+	if (err == 0)
+		err = restore_fpsimd_context(user.fpsimd);
 
 	return err;
 }

@@ -162,10 +241,11 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	return 0;
 }
 
-static int setup_sigframe(struct rt_sigframe __user *sf,
+static int setup_sigframe(struct rt_sigframe_user_layout *user,
 			  struct pt_regs *regs, sigset_t *set)
 {
 	int i, err = 0;
+	struct rt_sigframe __user *sf = user->sigframe;
 	void *aux = sf->uc.uc_mcontext.__reserved;
 	struct _aarch64_ctx *end;
 

@@ -209,33 +289,32 @@ static int setup_sigframe(struct rt_sigframe __user *sf,
 	return err;
 }
 
-static struct rt_sigframe __user *get_sigframe(struct ksignal *ksig,
-					       struct pt_regs *regs)
+static int get_sigframe(struct rt_sigframe_user_layout *user,
+			 struct ksignal *ksig, struct pt_regs *regs)
 {
 	unsigned long sp, sp_top;
-	struct rt_sigframe __user *frame;
 
 	sp = sp_top = sigsp(regs->sp, ksig);
 
 	sp = (sp - sizeof(struct rt_sigframe)) & ~15;
-	frame = (struct rt_sigframe __user *)sp;
+	user->sigframe = (struct rt_sigframe __user *)sp;
 
 	/*
 	 * Check that we can actually write to the signal frame.
 	 */
-	if (!access_ok(VERIFY_WRITE, frame, sp_top - sp))
-		frame = NULL;
+	if (!access_ok(VERIFY_WRITE, user->sigframe, sp_top - sp))
+		return -EFAULT;
 
-	return frame;
+	return 0;
 }
 
 static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
-			 void __user *frame, int usig)
+			 struct rt_sigframe_user_layout *user, int usig)
 {
 	__sigrestore_t sigtramp;
 
 	regs->regs[0] = usig;
-	regs->sp = (unsigned long)frame;
+	regs->sp = (unsigned long)user->sigframe;
 	regs->regs[29] = regs->sp + offsetof(struct rt_sigframe, fp);
 	regs->pc = (unsigned long)ka->sa.sa_handler;
 

@@ -250,20 +329,22 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
 			  struct pt_regs *regs)
 {
+	struct rt_sigframe_user_layout user;
 	struct rt_sigframe __user *frame;
 	int err = 0;
 
-	frame = get_sigframe(ksig, regs);
-	if (!frame)
+	if (get_sigframe(&user, ksig, regs))
 		return 1;
 
+	frame = user.sigframe;
+
 	__put_user_error(0, &frame->uc.uc_flags, err);
 	__put_user_error(NULL, &frame->uc.uc_link, err);
 
 	err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
-	err |= setup_sigframe(frame, regs, set);
+	err |= setup_sigframe(&user, regs, set);
 	if (err == 0) {
-		setup_return(regs, &ksig->ka, frame, usig);
+		setup_return(regs, &ksig->ka, &user, usig);
 		if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
 			err |= copy_siginfo_to_user(&frame->info, &ksig->info);
 			regs->regs[1] = (unsigned long)&frame->info;

@@ -25,6 +25,7 @@
 #include <linux/freezer.h>
 #include <linux/stddef.h>
 #include <linux/uaccess.h>
+#include <linux/string.h>
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>
 

@@ -49,8 +50,39 @@ struct rt_sigframe {
 
 struct rt_sigframe_user_layout {
 	struct rt_sigframe __user *sigframe;
+
+	unsigned long size;	/* size of allocated sigframe data */
+	unsigned long limit;	/* largest allowed size */
+
+	unsigned long fpsimd_offset;
+	unsigned long esr_offset;
+	unsigned long end_offset;
 };
 
+static void init_user_layout(struct rt_sigframe_user_layout *user)
+{
+	memset(user, 0, sizeof(*user));
+	user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved);
+
+	user->limit = user->size +
+		sizeof(user->sigframe->uc.uc_mcontext.__reserved) -
+		round_up(sizeof(struct _aarch64_ctx), 16);
+		/* ^ reserve space for terminator */
+}
+
+static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
+{
+	return round_up(max(user->size, sizeof(struct rt_sigframe)), 16);
+}
+
+static void __user *apply_user_offset(
+	struct rt_sigframe_user_layout const *user, unsigned long offset)
+{
+	char __user *base = (char __user *)user->sigframe;
+
+	return base + offset;
+}
+
 static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
 {
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;

@@ -106,26 +138,35 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			       struct rt_sigframe __user *sf)
 {
 	struct sigcontext __user *sc = &sf->uc.uc_mcontext;
-	struct _aarch64_ctx __user *head =
-		(struct _aarch64_ctx __user *)&sc->__reserved;
+	struct _aarch64_ctx __user *head;
+	char __user *base = (char __user *)&sc->__reserved;
 	size_t offset = 0;
+	size_t limit = sizeof(sc->__reserved);
 
 	user->fpsimd = NULL;
 
+	if (!IS_ALIGNED((unsigned long)base, 16))
+		goto invalid;
+
 	while (1) {
-		int err;
+		int err = 0;
 		u32 magic, size;
 
-		head = (struct _aarch64_ctx __user *)&sc->__reserved[offset];
-		if (!IS_ALIGNED((unsigned long)head, 16))
+		if (limit - offset < sizeof(*head))
 			goto invalid;
 
-		err = 0;
+		if (!IS_ALIGNED(offset, 16))
+			goto invalid;
+
+		head = (struct _aarch64_ctx __user *)(base + offset);
 		__get_user_error(magic, &head->magic, err);
 		__get_user_error(size, &head->size, err);
 		if (err)
 			return err;
 
+		if (limit - offset < size)
+			goto invalid;
+
 		switch (magic) {
 		case 0:
 			if (size)

@@ -137,9 +178,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			if (user->fpsimd)
 				goto invalid;
 
-			if (offset > sizeof(sc->__reserved) -
-					sizeof(*user->fpsimd) ||
-			    size < sizeof(*user->fpsimd))
+			if (size < sizeof(*user->fpsimd))
 				goto invalid;
 
 			user->fpsimd = (struct fpsimd_context __user *)head;

@@ -156,7 +195,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 		if (size < sizeof(*head))
 			goto invalid;
 
-		if (size > sizeof(sc->__reserved) - (sizeof(*head) + offset))
+		if (limit - offset < size)
 			goto invalid;
 
 		offset += size;

@@ -241,13 +280,30 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 	return 0;
 }
 
+/* Determine the layout of optional records in the signal frame */
+static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
+{
+	user->fpsimd_offset = user->size;
+	user->size += round_up(sizeof(struct fpsimd_context), 16);
+
+	/* fault information, if valid */
+	if (current->thread.fault_code) {
+		user->esr_offset = user->size;
+		user->size += round_up(sizeof(struct esr_context), 16);
+	}
+
+	/* set the "end" magic */
+	user->end_offset = user->size;
+
+	return 0;
+}
+
+
 static int setup_sigframe(struct rt_sigframe_user_layout *user,
 			  struct pt_regs *regs, sigset_t *set)
 {
 	int i, err = 0;
 	struct rt_sigframe __user *sf = user->sigframe;
-	void *aux = sf->uc.uc_mcontext.__reserved;
-	struct _aarch64_ctx *end;
 
 	/* set up the stack frame for unwinding */
 	__put_user_error(regs->regs[29], &sf->fp, err);

@@ -265,26 +321,29 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 	err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set));
 
 	if (err == 0) {
-		struct fpsimd_context *fpsimd_ctx =
-			container_of(aux, struct fpsimd_context, head);
+		struct fpsimd_context __user *fpsimd_ctx =
+			apply_user_offset(user, user->fpsimd_offset);
 		err |= preserve_fpsimd_context(fpsimd_ctx);
-		aux += sizeof(*fpsimd_ctx);
 	}
 
 	/* fault information, if valid */
-	if (current->thread.fault_code) {
-		struct esr_context *esr_ctx =
-			container_of(aux, struct esr_context, head);
+	if (err == 0 && user->esr_offset) {
+		struct esr_context __user *esr_ctx =
+			apply_user_offset(user, user->esr_offset);
+
 		__put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err);
 		__put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err);
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
-		aux += sizeof(*esr_ctx);
 	}
 
 	/* set the "end" magic */
-	end = aux;
-	__put_user_error(0, &end->magic, err);
-	__put_user_error(0, &end->size, err);
+	if (err == 0) {
+		struct _aarch64_ctx __user *end =
+			apply_user_offset(user, user->end_offset);
+
+		__put_user_error(0, &end->magic, err);
+		__put_user_error(0, &end->size, err);
+	}
 
 	return err;
 }

@@ -293,10 +352,15 @@ static int get_sigframe(struct rt_sigframe_user_layout *user,
 			 struct ksignal *ksig, struct pt_regs *regs)
 {
 	unsigned long sp, sp_top;
+	int err;
 
-	sp = sp_top = sigsp(regs->sp, ksig);
+	init_user_layout(user);
+	err = setup_sigframe_layout(user);
+	if (err)
+		return err;
 
-	sp = (sp - sizeof(struct rt_sigframe)) & ~15;
+	sp = sp_top = sigsp(regs->sp, ksig);
+	sp = (sp & ~15) - sigframe_size(user);
 	user->sigframe = (struct rt_sigframe __user *)sp;
 
 	/*

@@ -75,6 +75,22 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
 	return round_up(max(user->size, sizeof(struct rt_sigframe)), 16);
 }
 
+/*
+ * Allocate space for an optional record of <size> bytes in the user
+ * signal frame.  The offset from the signal frame base address to the
+ * allocated block is assigned to *offset.
+ */
+static int sigframe_alloc(struct rt_sigframe_user_layout *user,
+			  unsigned long *offset, size_t size)
+{
+	size_t padded_size = round_up(size, 16);
+
+	*offset = user->size;
+	user->size += padded_size;
+
+	return 0;
+}
+
 static void __user *apply_user_offset(
 	struct rt_sigframe_user_layout const *user, unsigned long offset)
 {

@@ -283,19 +299,32 @@ asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
 /* Determine the layout of optional records in the signal frame */
 static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 {
-	user->fpsimd_offset = user->size;
-	user->size += round_up(sizeof(struct fpsimd_context), 16);
+	int err;
+
+	err = sigframe_alloc(user, &user->fpsimd_offset,
+			     sizeof(struct fpsimd_context));
+	if (err)
+		return err;
 
 	/* fault information, if valid */
 	if (current->thread.fault_code) {
-		user->esr_offset = user->size;
-		user->size += round_up(sizeof(struct esr_context), 16);
+		err = sigframe_alloc(user, &user->esr_offset,
+				     sizeof(struct esr_context));
+		if (err)
+			return err;
 	}
 
-	/* set the "end" magic */
-	user->end_offset = user->size;
+	/*
+	 * Allocate space for the terminator record.
+	 * HACK: here we undo the reservation of space for the end record.
+	 * This bodge should be replaced with a cleaner approach later on.
+	 */
+	user->limit = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved) +
+		sizeof(user->sigframe->uc.uc_mcontext.__reserved);
 
-	return 0;
+	err = sigframe_alloc(user, &user->end_offset,
+			     sizeof(struct _aarch64_ctx));
+	return err;
 }
 
 

@@ -61,4 +61,31 @@ struct esr_context {
 	__u64 esr;
 };
 
+/*
+ * Pointer to extra space for additional structures that don't fit in
+ * sigcontext.__reserved[].  Note:
+ *
+ * 1) fpsimd_context, esr_context and extra_context must be placed in
+ * sigcontext.__reserved[] if present.  They cannot be placed in the
+ * extra space.  Any other record can be placed either in the extra
+ * space or in sigcontext.__reserved[].
+ *
+ * 2) There must not be more than one extra_context.
+ *
+ * 3) If extra_context is present, it must be followed immediately in
+ * sigcontext.__reserved[] by the terminating null _aarch64_ctx (i.e.,
+ * extra_context must be the last record in sigcontext.__reserved[]
+ * except for the terminator).
+ *
+ * 4) The extra space must itself be terminated with a null
+ * _aarch64_ctx.
+ */
+#define EXTRA_MAGIC	0x45585401
+
+struct extra_context {
+	struct _aarch64_ctx head;
+	void *data;	/* 16-byte aligned pointer to the extra space */
+	__u32 size;	/* size in bytes of the extra space */
+};
+
 #endif /* _UAPI__ASM_SIGCONTEXT_H */

@@ -25,6 +25,7 @@
 #include <linux/freezer.h>
 #include <linux/stddef.h>
 #include <linux/uaccess.h>
+#include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/tracehook.h>
 #include <linux/ratelimit.h>

@@ -56,18 +57,22 @@ struct rt_sigframe_user_layout {
 
 	unsigned long fpsimd_offset;
 	unsigned long esr_offset;
+	unsigned long extra_offset;
 	unsigned long end_offset;
 };
 
 static void init_user_layout(struct rt_sigframe_user_layout *user)
 {
+	const size_t __reserved_size =
+		sizeof(user->sigframe->uc.uc_mcontext.__reserved);
+	const size_t terminator_size =
+		round_up(sizeof(struct _aarch64_ctx), 16);
+
 	memset(user, 0, sizeof(*user));
 	user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved);
-
-	user->limit = user->size +
-		sizeof(user->sigframe->uc.uc_mcontext.__reserved) -
-		round_up(sizeof(struct _aarch64_ctx), 16);
-		/* ^ reserve space for terminator */
+	user->limit = user->size + (__reserved_size - terminator_size -
+				    sizeof(struct extra_context));
+	/* Reserve space for extension and terminator ^ */
 }
 
 static size_t sigframe_size(struct rt_sigframe_user_layout const *user)

@@ -75,6 +80,49 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
 	return round_up(max(user->size, sizeof(struct rt_sigframe)), 16);
 }
 
+/* Sanity limit on the maximum size of signal frame we'll try to generate. */
+/* This is NOT ABI. */
+#define SIGFRAME_MAXSZ SZ_64K
+
+static int __sigframe_alloc(struct rt_sigframe_user_layout *user,
+			    unsigned long *offset, size_t size, bool extend)
+{
+	size_t padded_size = round_up(size, 16);
+
+	if (padded_size > user->limit - user->size &&
+	    !user->extra_offset &&
+	    extend) {
+		int ret;
+
+		ret = __sigframe_alloc(user, &user->extra_offset,
+				       sizeof(struct extra_context), false);
+		if (ret)
+			return ret;
+
+		/*
+		 * Further allocations must go after the fixed-size
+		 * part of the signal frame:
+		 */
+		user->size = round_up(sizeof(struct rt_sigframe), 16);
+
+		/*
+		 * Allow expansion up to SIGFRAME_MAXSZ, ensuring space for
+		 * the terminator:
+		 */
+		user->limit = SIGFRAME_MAXSZ -
+			round_up(sizeof(struct _aarch64_ctx), 16);
+	}
+
+	/* Still not enough space?  Bad luck! */
+	if (padded_size > user->limit - user->size)
+		return -ENOMEM;
+
+	*offset = user->size;
+	user->size += padded_size;
+
+	return 0;
+}
+
 /*
  * Allocate space for an optional record of <size> bytes in the user
  * signal frame.  The offset from the signal frame base address to the

@@ -83,11 +131,26 @@ static size_t sigframe_size(struct rt_sigframe_user_layout const *user)
 static int sigframe_alloc(struct rt_sigframe_user_layout *user,
 			  unsigned long *offset, size_t size)
 {
-	size_t padded_size = round_up(size, 16);
+	return __sigframe_alloc(user, offset, size, true);
+}
 
-	*offset = user->size;
-	user->size += padded_size;
+/* Allocate the null terminator record and prevent further allocations */
+static int sigframe_alloc_end(struct rt_sigframe_user_layout *user)
+{
+	int ret;
+	const size_t terminator_size =
+		round_up(sizeof(struct _aarch64_ctx), 16);
+
+	/* Un-reserve the space reserved for the terminator: */
+	user->limit += terminator_size;
+
+	ret = sigframe_alloc(user, &user->end_offset,
+			     sizeof(struct _aarch64_ctx));
+	if (ret)
+		return ret;
 
+	/* Prevent further allocation: */
+	user->limit = user->size;
 	return 0;
 }
 

@@ -314,17 +377,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user)
 			return err;
 	}
 
-	/*
-	 * Allocate space for the terminator record.
-	 * HACK: here we undo the reservation of space for the end record.
-	 * This bodge should be replaced with a cleaner approach later on.
-	 */
-	user->limit = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved) +
-		sizeof(user->sigframe->uc.uc_mcontext.__reserved);
-
-	err = sigframe_alloc(user, &user->end_offset,
-			     sizeof(struct _aarch64_ctx));
-	return err;
+	return sigframe_alloc_end(user);
 }
 
 

@@ -365,6 +418,27 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
 		__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
 	}
 
+	if (err == 0 && user->extra_offset) {
+		struct extra_context __user *extra =
+			apply_user_offset(user, user->extra_offset);
+		struct _aarch64_ctx __user *end =
+			(struct _aarch64_ctx __user *)((char __user *)extra +
+				round_up(sizeof(*extra), 16));
+		void __user *extra_data = apply_user_offset(user,
+			round_up(sizeof(struct rt_sigframe), 16));
+		u32 extra_size = round_up(user->size, 16) -
+			round_up(sizeof(struct rt_sigframe), 16);
+
+		__put_user_error(EXTRA_MAGIC, &extra->head.magic, err);
+		__put_user_error(sizeof(*extra), &extra->head.size, err);
+		__put_user_error(extra_data, &extra->data, err);
+		__put_user_error(extra_size, &extra->size, err);
+
+		/* Add the terminator */
+		__put_user_error(0, &end->magic, err);
+		__put_user_error(0, &end->size, err);
+	}
+
 	/* set the "end" magic */
 	if (err == 0) {
 		struct _aarch64_ctx __user *end =

@@ -221,6 +221,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	char __user *base = (char __user *)&sc->__reserved;
 	size_t offset = 0;
 	size_t limit = sizeof(sc->__reserved);
+	bool have_extra_context = false;
 
 	user->fpsimd = NULL;
 

@@ -230,6 +231,9 @@ static int parse_user_sigframe(struct user_ctxs *user,
 	while (1) {
 		int err = 0;
 		u32 magic, size;
+		struct extra_context const __user *extra;
+		void __user *extra_data;
+		u32 extra_size;
 
 		if (limit - offset < sizeof(*head))
 			goto invalid;

@@ -267,6 +271,42 @@ static int parse_user_sigframe(struct user_ctxs *user,
 			/* ignore */
 			break;
 
+		case EXTRA_MAGIC:
+			if (have_extra_context)
+				goto invalid;
+
+			if (size < sizeof(*extra))
+				goto invalid;
+
+			extra = (struct extra_context const __user *)head;
+			__get_user_error(extra_data, &extra->data, err);
+			__get_user_error(extra_size, &extra->size, err);
+			if (err)
+				return err;
+
+			/* Prevent looping/repeated parsing of extra_conext */
+			have_extra_context = true;
+
+			/*
+			 * Rely on the __user accessors to reject bogus
+			 * pointers.
+			 */
+			base = extra_data;
+			if (!IS_ALIGNED((unsigned long)base, 16))
+				goto invalid;
+
+			/* Reject "unreasonably large" frames: */
+			limit = extra_size;
+			if (limit > SIGFRAME_MAXSZ - sizeof(sc->__reserved))
+				goto invalid;
+
+			/*
+			 * Ignore trailing terminator in __reserved[]
+			 * and start parsing extra_data:
+			 */
+			offset = 0;
+			continue;
+
 		default:
 			goto invalid;
 		}

@@ -963,6 +963,7 @@ config EFI_STUB
 config EFI
 	bool "UEFI runtime support"
 	depends on OF && !CPU_BIG_ENDIAN
+	depends on KERNEL_MODE_NEON
 	select LIBFDT
 	select UCS2_STRING
 	select EFI_PARAMS_FROM_FDT

@@ -223,9 +223,6 @@ config SWIOTLB
 config IOMMU_HELPER
 	def_bool SWIOTLB
 
-config KERNEL_MODE_NEON
-	def_bool y
-
 config FIX_EARLYCON_MEM
 	def_bool y
 

@@ -268,6 +265,10 @@ endmenu
 
 menu "Kernel Features"
 
+config KERNEL_MODE_NEON
+	bool "Support NEON/FPSIMD code in the kernel"
+	default y
+
 menu "ARM errata workarounds via the alternatives framework"
 
 config ARM64_ERRATUM_826319

@@ -876,6 +876,18 @@ config ARM64_UAO
 
 endmenu
 
+config ARM64_SVE
+	bool "ARM Scalable Vector Extension support"
+	default y
+	depends on !KERNEL_MODE_NEON	# until it works with SVE
+	help
+	  The Scalable Vector Extension (SVE) is an extension to the AArch64
+	  execution state which complements and extends the SIMD functionality
+	  of the base architecture to support much larger vectors and to enable
+	  additional vectorisation opportunities.
+
+	  To enable use of this extension on CPUs that implement it, say Y.
+
 config ARM64_MODULE_CMODEL_LARGE
 	bool
 

@@ -81,6 +81,9 @@ extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
 				      u32 num_regs);
 extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
 
+extern void sve_save_state(void *state, u32 *pfpsr);
+extern void sve_load_state(void const *state, u32 const *pfpsr);
+
 #endif
 
 #endif

@@ -131,3 +131,148 @@
 	ldp	q0, q1, [\state, #-16 * 0 - 16]
 0:
 .endm
+
+.macro _check_reg nr
+	.if (\nr) < 0 || (\nr) > 31
+		.error "Bad register number \nr."
+	.endif
+.endm
+
+.macro _check_zreg znr
+	.if (\znr) < 0 || (\znr) > 31
+		.error "Bad Scalable Vector Extension vector register number \znr."
+	.endif
+.endm
+
+.macro _check_preg pnr
+	.if (\pnr) < 0 || (\pnr) > 15
+		.error "Bad Scalable Vector Extension predicate register number \pnr."
+	.endif
+.endm
+
+.macro _check_num n, min, max
+	.if (\n) < (\min) || (\n) > (\max)
+		.error "Number \n out of range [\min,\max]"
+	.endif
+.endm
+
+.macro _zstrv znt, nspb, ioff=0
+	_check_zreg \znt
+	_check_reg \nspb
+	_check_num (\ioff), -0x100, 0xff
+	.inst	0xe5804000			\
+		| (\znt)			\
+		| ((\nspb) << 5)		\
+		| (((\ioff) & 7) << 10)		\
+		| (((\ioff) & 0x1f8) << 13)
+.endm
+
+.macro _zldrv znt, nspb, ioff=0
+	_check_zreg \znt
+	_check_reg \nspb
+	_check_num (\ioff), -0x100, 0xff
+	.inst	0x85804000			\
+		| (\znt)			\
+		| ((\nspb) << 5)		\
+		| (((\ioff) & 7) << 10)		\
+		| (((\ioff) & 0x1f8) << 13)
+.endm
+
+.macro _zstrp pnt, nspb, ioff=0
+	_check_preg \pnt
+	_check_reg \nspb
+	_check_num (\ioff), -0x100, 0xff
+	.inst	0xe5800000			\
+		| (\pnt)			\
+		| ((\nspb) << 5)		\
+		| (((\ioff) & 7) << 10)		\
+		| (((\ioff) & 0x1f8) << 13)
+.endm
+
+.macro _zldrp pnt, nspb, ioff=0
+	_check_preg \pnt
+	_check_reg \nspb
+	_check_num (\ioff), -0x100, 0xff
+	.inst	0x85800000			\
+		| (\pnt)			\
+		| ((\nspb) << 5)		\
+		| (((\ioff) & 7) << 10)		\
+		| (((\ioff) & 0x1f8) << 13)
+.endm
+
+.macro _zrdvl nspd, is1
+	_check_reg \nspd
+	_check_num (\is1), -0x20, 0x1f
+	.inst	0x04bf5000			\
+		| (\nspd)			\
+		| (((\is1) & 0x3f) << 5)
+.endm
+
+.macro _zrdffr pnd
+	_check_preg \pnd
+	.inst	0x2519f000			\
+		| (\pnd)
+.endm
+
+.macro _zwrffr pnd
+	_check_preg \pnd
+	.inst	0x25289000			\
+		| ((\pnd) << 5)
+.endm
+
+.macro for from, to, insn
+	.if (\from) >= (\to)
+		\insn	(\from)
+		.exitm
+	.endif
+
+	for \from, ((\from) + (\to)) / 2, \insn
+	for ((\from) + (\to)) / 2 + 1, \to, \insn
+.endm
+
+.macro sve_save nb, xpfpsr, ntmp
+	.macro savez n
+		_zstrv	\n, \nb, (\n) - 34
+	.endm
+
+	.macro savep n
+		_zstrp	\n, \nb, (\n) - 16
+	.endm
+
+	for	0, 31, savez
+	for	0, 15, savep
+	_zrdffr	0
+	_zstrp	0, \nb
+	_zldrp	0, \nb, -16
+
+	mrs	x\ntmp, fpsr
+	str	w\ntmp, [\xpfpsr]
+	mrs	x\ntmp, fpcr
+	str	w\ntmp, [\xpfpsr, #4]
+
+	.purgem savez
+	.purgem savep
+.endm
+
+.macro sve_load nb, xpfpsr, ntmp
+	.macro loadz n
+		_zldrv	\n, \nb, (\n) - 34
+	.endm
+
+	.macro loadp n
+		_zldrp	\n, \nb, (\n) - 16
+	.endm
+
+	for	0, 31, loadz
+	_zldrp	0, \nb
+	_zwrffr	0
+	for	0, 15, loadp
+
+	ldr	w\ntmp, [\xpfpsr]
+	msr	fpsr, x\ntmp
+	ldr	w\ntmp, [\xpfpsr, #4]
+	msr	fpcr, x\ntmp
+
+	.purgem loadz
+	.purgem loadp
+.endm