gcc: mitigate the Straight-line Speculation attack

Straight-line Speculation is a SPECTRE-like attack on Armv8-A, further
details can be found in the white paper here:

https://developer.arm.com/support/arm-security-updates/speculative-processor-vulnerability/downloads/straight-line-speculation

Backport the GCC patches to mitigate the attack.

CVE: CVE-2020-13844
Signed-off-by: Ross Burton <ross.burton@arm.com>
Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

4 files changed, 1470 insertions, 0 deletions

diff --git a/meta/recipes-devtools/gcc/gcc-10.1.inc b/meta/recipes-devtools/gcc/gcc-10.1.inc
index a3de91a2c6..7c1201a2e3 100644
--- a/meta/recipes-devtools/gcc/gcc-10.1.inc
+++ b/meta/recipes-devtools/gcc/gcc-10.1.inc
@@ -66,6 +66,9 @@ SRC_URI = "\
            file://0036-Enable-CET-in-cross-compiler-if-possible.patch \
            file://0037-mingw32-Enable-operation_not_supported.patch \
            file://0038-libatomic-Do-not-enforce-march-on-aarch64.patch \
+           file://0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch \
+           file://0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch \
+           file://0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch \
 "
 SRC_URI[sha256sum] = "b6898a23844b656f1b68691c5c012036c2e694ac4b53a8918d4712ad876e7ea2"
 
diff --git a/meta/recipes-devtools/gcc/gcc-10.1/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch b/meta/recipes-devtools/gcc/gcc-10.1/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch
new file mode 100644
index 0000000000..73de4c7590
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc-10.1/0001-aarch64-New-Straight-Line-Speculation-SLS-mitigation.patch
@@ -0,0 +1,202 @@
+CVE: CVE-2020-13844
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@arm.com>
+
+From 1ff243934ac443b5f58cd02a5012ce58ecc31fb2 Mon Sep 17 00:00:00 2001
+From: Matthew Malcomson <matthew.malcomson@arm.com>
+Date: Thu, 9 Jul 2020 09:11:58 +0100
+Subject: [PATCH 1/3] aarch64: New Straight Line Speculation (SLS) mitigation
+ flags
+
+Here we introduce the flags that will be used for straight line speculation.
+
+The new flag introduced is `-mharden-sls=`.
+This flag can take arguments of `none`, `all`, or a comma seperated list of one
+or more of `retbr` or `blr`.
+`none` indicates no special mitigation of the straight line speculation
+vulnerability.
+`all` requests all mitigations currently implemented.
+`retbr` requests that the RET and BR instructions have a speculation barrier
+inserted after them.
+`blr` requests that BLR instructions are replaced by a BL to a function stub
+using a BR with a speculation barrier after it.
+
+Setting this on a per-function basis using attributes or the like is not
+enabled, but may be in the future.
+
+gcc/ChangeLog:
+
+2020-06-02  Matthew Malcomson  <matthew.malcomson@arm.com>
+
+	* config/aarch64/aarch64-protos.h (aarch64_harden_sls_retbr_p):
+	New.
+	(aarch64_harden_sls_blr_p): New.
+	* config/aarch64/aarch64.c (enum aarch64_sls_hardening_type):
+	New.
+	(aarch64_harden_sls_retbr_p): New.
+	(aarch64_harden_sls_blr_p): New.
+	(aarch64_validate_sls_mitigation): New.
+	(aarch64_override_options): Parse options for SLS mitigation.
+	* config/aarch64/aarch64.opt (-mharden-sls): New option.
+	* doc/invoke.texi: Document new option.
+---
+ gcc/config/aarch64/aarch64-protos.h |  3 ++
+ gcc/config/aarch64/aarch64.c        | 76 +++++++++++++++++++++++++++++++++++++
+ gcc/config/aarch64/aarch64.opt      |  4 ++
+ gcc/doc/invoke.texi                 | 12 ++++++
+ 4 files changed, 95 insertions(+)
+
+diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
+index 723d9ba..eb5f4b4 100644
+--- a/gcc/config/aarch64/aarch64-protos.h
++++ b/gcc/config/aarch64/aarch64-protos.h
+@@ -781,4 +781,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names;
+ 
+ tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *);
+ 
++extern bool aarch64_harden_sls_retbr_p (void);
++extern bool aarch64_harden_sls_blr_p (void);
++
+ #endif /* GCC_AARCH64_PROTOS_H */
+diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
+index b86434a..437a9cf 100644
+--- a/gcc/config/aarch64/aarch64.c
++++ b/gcc/config/aarch64/aarch64.c
+@@ -14494,6 +14494,79 @@ aarch64_validate_mcpu (const char *str, const struct processor **res,
+   return false;
+ }
+ 
++/* Straight line speculation indicators.  */
++enum aarch64_sls_hardening_type
++{
++  SLS_NONE = 0,
++  SLS_RETBR = 1,
++  SLS_BLR = 2,
++  SLS_ALL = 3,
++};
++static enum aarch64_sls_hardening_type aarch64_sls_hardening;
++
++/* Return whether we should mitigatate Straight Line Speculation for the RET
++   and BR instructions.  */
++bool
++aarch64_harden_sls_retbr_p (void)
++{
++  return aarch64_sls_hardening & SLS_RETBR;
++}
++
++/* Return whether we should mitigatate Straight Line Speculation for the BLR
++   instruction.  */
++bool
++aarch64_harden_sls_blr_p (void)
++{
++  return aarch64_sls_hardening & SLS_BLR;
++}
++
++/* As of yet we only allow setting these options globally, in the future we may
++   allow setting them per function.  */
++static void
++aarch64_validate_sls_mitigation (const char *const_str)
++{
++  char *token_save = NULL;
++  char *str = NULL;
++
++  if (strcmp (const_str, "none") == 0)
++    {
++      aarch64_sls_hardening = SLS_NONE;
++      return;
++    }
++  if (strcmp (const_str, "all") == 0)
++    {
++      aarch64_sls_hardening = SLS_ALL;
++      return;
++    }
++
++  char *str_root = xstrdup (const_str);
++  str = strtok_r (str_root, ",", &token_save);
++  if (!str)
++    error ("invalid argument given to %<-mharden-sls=%>");
++
++  int temp = SLS_NONE;
++  while (str)
++    {
++      if (strcmp (str, "blr") == 0)
++	temp |= SLS_BLR;
++      else if (strcmp (str, "retbr") == 0)
++	temp |= SLS_RETBR;
++      else if (strcmp (str, "none") == 0 || strcmp (str, "all") == 0)
++	{
++	  error ("%<%s%> must be by itself for %<-mharden-sls=%>", str);
++	  break;
++	}
++      else
++	{
++	  error ("invalid argument %<%s%> for %<-mharden-sls=%>", str);
++	  break;
++	}
++      str = strtok_r (NULL, ",", &token_save);
++    }
++  aarch64_sls_hardening = (aarch64_sls_hardening_type) temp;
++  free (str_root);
++}
++
+ /* Parses CONST_STR for branch protection features specified in
+    aarch64_branch_protect_types, and set any global variables required.  Returns
+    the parsing result and assigns LAST_STR to the last processed token from
+@@ -14738,6 +14811,9 @@ aarch64_override_options (void)
+   selected_arch = NULL;
+   selected_tune = NULL;
+ 
++  if (aarch64_harden_sls_string)
++    aarch64_validate_sls_mitigation (aarch64_harden_sls_string);
++
+   if (aarch64_branch_protection_string)
+     aarch64_validate_mbranch_protection (aarch64_branch_protection_string);
+ 
+diff --git a/gcc/config/aarch64/aarch64.opt b/gcc/config/aarch64/aarch64.opt
+index d99d14c..5170361 100644
+--- a/gcc/config/aarch64/aarch64.opt
++++ b/gcc/config/aarch64/aarch64.opt
+@@ -71,6 +71,10 @@ mgeneral-regs-only
+ Target Report RejectNegative Mask(GENERAL_REGS_ONLY) Save
+ Generate code which uses only the general registers.
+ 
++mharden-sls=
++Target RejectNegative Joined Var(aarch64_harden_sls_string)
++Generate code to mitigate against straight line speculation.
++
+ mfix-cortex-a53-835769
+ Target Report Var(aarch64_fix_a53_err835769) Init(2) Save
+ Workaround for ARM Cortex-A53 Erratum number 835769.
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+index a2794a6..bd5b77a 100644
+--- a/gcc/doc/invoke.texi
++++ b/gcc/doc/invoke.texi
+@@ -696,6 +696,7 @@ Objective-C and Objective-C++ Dialects}.
+ -msign-return-address=@var{scope} @gol
+ -mbranch-protection=@var{none}|@var{standard}|@var{pac-ret}[+@var{leaf}
+ +@var{b-key}]|@var{bti} @gol
++-mharden-sls=@var{opts} @gol
+ -march=@var{name}  -mcpu=@var{name}  -mtune=@var{name}  @gol
+ -moverride=@var{string}  -mverbose-cost-dump @gol
+ -mstack-protector-guard=@var{guard} -mstack-protector-guard-reg=@var{sysreg} @gol
+@@ -17065,6 +17066,17 @@ functions.  The optional argument @samp{b-key} can be used to sign the functions
+ with the B-key instead of the A-key.
+ @samp{bti} turns on branch target identification mechanism.
+ 
++@item -mharden-sls=@var{opts}
++@opindex mharden-sls
++Enable compiler hardening against straight line speculation (SLS).
++@var{opts} is a comma-separated list of the following options:
++@table @samp
++@item retbr
++@item blr
++@end table
++In addition, @samp{-mharden-sls=all} enables all SLS hardening while
++@samp{-mharden-sls=none} disables all SLS hardening.
++
+ @item -msve-vector-bits=@var{bits}
+ @opindex msve-vector-bits
+ Specify the number of bits in an SVE vector register.  This option only has
+-- 
+2.7.4
+
diff --git a/meta/recipes-devtools/gcc/gcc-10.1/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch b/meta/recipes-devtools/gcc/gcc-10.1/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch
new file mode 100644
index 0000000000..823cc8b668
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc-10.1/0002-aarch64-Introduce-SLS-mitigation-for-RET-and-BR-inst.patch
@@ -0,0 +1,607 @@
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@arm.com>
+
+From b1204d16e1ec96a4aa89e44de8990e2499ffdb22 Mon Sep 17 00:00:00 2001
+From: Matthew Malcomson <matthew.malcomson@arm.com>
+Date: Thu, 9 Jul 2020 09:11:59 +0100
+Subject: [PATCH 2/3] aarch64: Introduce SLS mitigation for RET and BR
+ instructions
+
+Instructions following RET or BR are not necessarily executed.  In order
+to avoid speculation past RET and BR we can simply append a speculation
+barrier.
+
+Since these speculation barriers will not be architecturally executed,
+they are not expected to add a high performance penalty.
+
+The speculation barrier is to be SB when targeting architectures which
+have this enabled, and DSB SY + ISB otherwise.
+
+We add tests for each of the cases where such an instruction was seen.
+
+This is implemented by modifying each machine description pattern that
+emits either a RET or a BR instruction.  We choose not to use something
+like `TARGET_ASM_FUNCTION_EPILOGUE` since it does not affect the
+`indirect_jump`, `jump`, `sibcall_insn` and `sibcall_value_insn`
+patterns and we find it preferable to implement the functionality in the
+same way for every pattern.
+
+There is one particular case which is slightly tricky.  The
+implementation of TARGET_ASM_TRAMPOLINE_TEMPLATE uses a BR which needs
+to be mitigated against.  The trampoline template is used *once* per
+compilation unit, and the TRAMPOLINE_SIZE is exposed to the user via the
+builtin macro __LIBGCC_TRAMPOLINE_SIZE__.
+In the future we may implement function specific attributes to turn on
+and off hardening on a per-function basis.
+The fixed nature of the trampoline described above implies it will be
+safer to ensure this speculation barrier is always used.
+
+Testing:
+  Bootstrap and regtest done on aarch64-none-linux
+  Used a temporary hack(1) to use these options on every test in the
+  testsuite and a script to check that the output never emitted an
+  unmitigated RET or BR.
+
+1) Temporary hack was a change to the testsuite to always use
+`-save-temps` and run a script on the assembly output of those
+compilations which produced one to ensure every RET or BR is immediately
+followed by a speculation barrier.
+
+gcc/ChangeLog:
+
+	* config/aarch64/aarch64-protos.h (aarch64_sls_barrier): New.
+	* config/aarch64/aarch64.c (aarch64_output_casesi): Emit
+	speculation barrier after BR instruction if needs be.
+	(aarch64_trampoline_init): Handle ptr_mode value & adjust size
+	of code copied.
+	(aarch64_sls_barrier): New.
+	(aarch64_asm_trampoline_template): Add needed barriers.
+	* config/aarch64/aarch64.h (AARCH64_ISA_SB): New.
+	(TARGET_SB): New.
+	(TRAMPOLINE_SIZE): Account for barrier.
+	* config/aarch64/aarch64.md (indirect_jump, *casesi_dispatch,
+	simple_return, *do_return, *sibcall_insn, *sibcall_value_insn):
+	Emit barrier if needs be, also account for possible barrier using
+	"sls_length" attribute.
+	(sls_length): New attribute.
+	(length): Determine default using any non-default sls_length
+	value.
+
+gcc/testsuite/ChangeLog:
+
+	* gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c: New test.
+	* gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c:
+	New test.
+	* gcc.target/aarch64/sls-mitigation/sls-mitigation.exp: New file.
+	* lib/target-supports.exp (check_effective_target_aarch64_asm_sb_ok):
+	New proc.
+---
+ gcc/config/aarch64/aarch64-protos.h                |   1 +
+ gcc/config/aarch64/aarch64.c                       |  41 ++++++-
+ gcc/config/aarch64/aarch64.h                       |  10 +-
+ gcc/config/aarch64/aarch64.md                      |  76 +++++++++----
+ .../aarch64/sls-mitigation/sls-miti-retbr-pacret.c |  21 ++++
+ .../aarch64/sls-mitigation/sls-miti-retbr.c        | 119 +++++++++++++++++++++
+ .../aarch64/sls-mitigation/sls-mitigation.exp      |  73 +++++++++++++
+ gcc/testsuite/lib/target-supports.exp              |   2 +-
+ 8 files changed, 318 insertions(+), 25 deletions(-)
+ create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c
+ create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c
+ create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp
+
+diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
+index eb5f4b4..ee0ffde 100644
+--- a/gcc/config/aarch64/aarch64-protos.h
++++ b/gcc/config/aarch64/aarch64-protos.h
+@@ -781,6 +781,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names;
+ 
+ tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *);
+ 
++const char *aarch64_sls_barrier (int);
+ extern bool aarch64_harden_sls_retbr_p (void);
+ extern bool aarch64_harden_sls_blr_p (void);
+ 
+diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
+index 437a9cf..44e3d1f 100644
+--- a/gcc/config/aarch64/aarch64.c
++++ b/gcc/config/aarch64/aarch64.c
+@@ -10852,8 +10852,8 @@ aarch64_return_addr (int count, rtx frame ATTRIBUTE_UNUSED)
+ static void
+ aarch64_asm_trampoline_template (FILE *f)
+ {
+-  int offset1 = 16;
+-  int offset2 = 20;
++  int offset1 = 24;
++  int offset2 = 28;
+ 
+   if (aarch64_bti_enabled ())
+     {
+@@ -10876,6 +10876,17 @@ aarch64_asm_trampoline_template (FILE *f)
+     }
+   asm_fprintf (f, "\tbr\t%s\n", reg_names [IP1_REGNUM]);
+ 
++  /* We always emit a speculation barrier.
++     This is because the same trampoline template is used for every nested
++     function.  Since nested functions are not particularly common or
++     performant we don't worry too much about the extra instructions to copy
++     around.
++     This is not yet a problem, since we have not yet implemented function
++     specific attributes to choose between hardening against straight line
++     speculation or not, but such function specific attributes are likely to
++     happen in the future.  */
++  asm_fprintf (f, "\tdsb\tsy\n\tisb\n");
++
+   /* The trampoline needs an extra padding instruction.  In case if BTI is
+      enabled the padding instruction is replaced by the BTI instruction at
+      the beginning.  */
+@@ -10890,10 +10901,14 @@ static void
+ aarch64_trampoline_init (rtx m_tramp, tree fndecl, rtx chain_value)
+ {
+   rtx fnaddr, mem, a_tramp;
+-  const int tramp_code_sz = 16;
++  const int tramp_code_sz = 24;
+ 
+   /* Don't need to copy the trailing D-words, we fill those in below.  */
+-  emit_block_move (m_tramp, assemble_trampoline_template (),
++  /* We create our own memory address in Pmode so that `emit_block_move` can
++     use parts of the backend which expect Pmode addresses.  */
++  rtx temp = convert_memory_address (Pmode, XEXP (m_tramp, 0));
++  emit_block_move (gen_rtx_MEM (BLKmode, temp),
++		   assemble_trampoline_template (),
+ 		   GEN_INT (tramp_code_sz), BLOCK_OP_NORMAL);
+   mem = adjust_address (m_tramp, ptr_mode, tramp_code_sz);
+   fnaddr = XEXP (DECL_RTL (fndecl), 0);
+@@ -11084,6 +11099,8 @@ aarch64_output_casesi (rtx *operands)
+   output_asm_insn (buf, operands);
+   output_asm_insn (patterns[index][1], operands);
+   output_asm_insn ("br\t%3", operands);
++  output_asm_insn (aarch64_sls_barrier (aarch64_harden_sls_retbr_p ()),
++		   operands);
+   assemble_label (asm_out_file, label);
+   return "";
+ }
+@@ -22924,6 +22941,22 @@ aarch64_file_end_indicate_exec_stack ()
+ #undef GNU_PROPERTY_AARCH64_FEATURE_1_BTI
+ #undef GNU_PROPERTY_AARCH64_FEATURE_1_AND
+ 
++/* Helper function for straight line speculation.
++   Return what barrier should be emitted for straight line speculation
++   mitigation.
++   When not mitigating against straight line speculation this function returns
++   an empty string.
++   When mitigating against straight line speculation, use:
++   * SB when the v8.5-A SB extension is enabled.
++   * DSB+ISB otherwise.  */
++const char *
++aarch64_sls_barrier (int mitigation_required)
++{
++  return mitigation_required
++    ? (TARGET_SB ? "sb" : "dsb\tsy\n\tisb")
++    : "";
++}
++
+ /* Target-specific selftests.  */
+ 
+ #if CHECKING_P
+diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
+index 1ce23c6..c21015f 100644
+--- a/gcc/config/aarch64/aarch64.h
++++ b/gcc/config/aarch64/aarch64.h
+@@ -281,6 +281,7 @@ extern unsigned aarch64_architecture_version;
+ #define AARCH64_ISA_F32MM	   (aarch64_isa_flags & AARCH64_FL_F32MM)
+ #define AARCH64_ISA_F64MM	   (aarch64_isa_flags & AARCH64_FL_F64MM)
+ #define AARCH64_ISA_BF16	   (aarch64_isa_flags & AARCH64_FL_BF16)
++#define AARCH64_ISA_SB  	   (aarch64_isa_flags & AARCH64_FL_SB)
+ 
+ /* Crypto is an optional extension to AdvSIMD.  */
+ #define TARGET_CRYPTO (TARGET_SIMD && AARCH64_ISA_CRYPTO)
+@@ -378,6 +379,9 @@ extern unsigned aarch64_architecture_version;
+ #define TARGET_FIX_ERR_A53_835769_DEFAULT 1
+ #endif
+ 
++/* SB instruction is enabled through +sb.  */
++#define TARGET_SB (AARCH64_ISA_SB)
++
+ /* Apply the workaround for Cortex-A53 erratum 835769.  */
+ #define TARGET_FIX_ERR_A53_835769	\
+   ((aarch64_fix_a53_err835769 == 2)	\
+@@ -1058,8 +1062,10 @@ typedef struct
+ 
+ #define RETURN_ADDR_RTX aarch64_return_addr
+ 
+-/* BTI c + 3 insns + 2 pointer-sized entries.  */
+-#define TRAMPOLINE_SIZE	(TARGET_ILP32 ? 24 : 32)
++/* BTI c + 3 insns
++   + sls barrier of DSB + ISB.
++   + 2 pointer-sized entries.  */
++#define TRAMPOLINE_SIZE	(24 + (TARGET_ILP32 ? 8 : 16))
+ 
+ /* Trampolines contain dwords, so must be dword aligned.  */
+ #define TRAMPOLINE_ALIGNMENT 64
+diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
+index 8c8be3c..dda04ee 100644
+--- a/gcc/config/aarch64/aarch64.md
++++ b/gcc/config/aarch64/aarch64.md
+@@ -407,10 +407,25 @@
+ ;; Attribute that specifies whether the alternative uses MOVPRFX.
+ (define_attr "movprfx" "no,yes" (const_string "no"))
+ 
++;; Attribute to specify that an alternative has the length of a single
++;; instruction plus a speculation barrier.
++(define_attr "sls_length" "none,retbr,casesi" (const_string "none"))
++
+ (define_attr "length" ""
+   (cond [(eq_attr "movprfx" "yes")
+            (const_int 8)
+-        ] (const_int 4)))
++
++	 (eq_attr "sls_length" "retbr")
++	   (cond [(match_test "!aarch64_harden_sls_retbr_p ()") (const_int 4)
++		  (match_test "TARGET_SB") (const_int 8)]
++		 (const_int 12))
++
++	 (eq_attr "sls_length" "casesi")
++	   (cond [(match_test "!aarch64_harden_sls_retbr_p ()") (const_int 16)
++		  (match_test "TARGET_SB") (const_int 20)]
++		 (const_int 24))
++	]
++	  (const_int 4)))
+ 
+ ;; Strictly for compatibility with AArch32 in pipeline models, since AArch64 has
+ ;; no predicated insns.
+@@ -447,8 +462,12 @@
+ (define_insn "indirect_jump"
+   [(set (pc) (match_operand:DI 0 "register_operand" "r"))]
+   ""
+-  "br\\t%0"
+-  [(set_attr "type" "branch")]
++  {
++    output_asm_insn ("br\\t%0", operands);
++    return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ());
++  }
++  [(set_attr "type" "branch")
++   (set_attr "sls_length" "retbr")]
+ )
+ 
+ (define_insn "jump"
+@@ -765,7 +784,7 @@
+   "*
+   return aarch64_output_casesi (operands);
+   "
+-  [(set_attr "length" "16")
++  [(set_attr "sls_length" "casesi")
+    (set_attr "type" "branch")]
+ )
+ 
+@@ -844,18 +863,23 @@
+   [(return)]
+   ""
+   {
++    const char *ret = NULL;
+     if (aarch64_return_address_signing_enabled ()
+ 	&& TARGET_ARMV8_3
+ 	&& !crtl->calls_eh_return)
+       {
+ 	if (aarch64_ra_sign_key == AARCH64_KEY_B)
+-	  return "retab";
++	  ret = "retab";
+ 	else
+-	  return "retaa";
++	  ret = "retaa";
+       }
+-    return "ret";
++    else
++      ret = "ret";
++    output_asm_insn (ret, operands);
++    return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ());
+   }
+-  [(set_attr "type" "branch")]
++  [(set_attr "type" "branch")
++   (set_attr "sls_length" "retbr")]
+ )
+ 
+ (define_expand "return"
+@@ -867,8 +891,12 @@
+ (define_insn "simple_return"
+   [(simple_return)]
+   ""
+-  "ret"
+-  [(set_attr "type" "branch")]
++  {
++    output_asm_insn ("ret", operands);
++    return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ());
++  }
++  [(set_attr "type" "branch")
++   (set_attr "sls_length" "retbr")]
+ )
+ 
+ (define_insn "*cb<optab><mode>1"
+@@ -1066,10 +1094,16 @@
+    (unspec:DI [(match_operand:DI 2 "const_int_operand")] UNSPEC_CALLEE_ABI)
+    (return)]
+   "SIBLING_CALL_P (insn)"
+-  "@
+-   br\\t%0
+-   b\\t%c0"
+-  [(set_attr "type" "branch, branch")]
++  {
++    if (which_alternative == 0)
++      {
++	output_asm_insn ("br\\t%0", operands);
++	return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ());
++      }
++    return "b\\t%c0";
++  }
++  [(set_attr "type" "branch, branch")
++   (set_attr "sls_length" "retbr,none")]
+ )
+ 
+ (define_insn "*sibcall_value_insn"
+@@ -1080,10 +1114,16 @@
+    (unspec:DI [(match_operand:DI 3 "const_int_operand")] UNSPEC_CALLEE_ABI)
+    (return)]
+   "SIBLING_CALL_P (insn)"
+-  "@
+-   br\\t%1
+-   b\\t%c1"
+-  [(set_attr "type" "branch, branch")]
++  {
++    if (which_alternative == 0)
++      {
++	output_asm_insn ("br\\t%1", operands);
++	return aarch64_sls_barrier (aarch64_harden_sls_retbr_p ());
++      }
++    return "b\\t%c1";
++  }
++  [(set_attr "type" "branch, branch")
++   (set_attr "sls_length" "retbr,none")]
+ )
+ 
+ ;; Call subroutine returning any type.
+diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c
+new file mode 100644
+index 0000000..fa1887a
+--- /dev/null
++++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr-pacret.c
+@@ -0,0 +1,21 @@
++/* Avoid ILP32 since pacret is only available for LP64 */
++/* { dg-do compile { target { ! ilp32 } } } */
++/* { dg-additional-options "-mharden-sls=retbr -mbranch-protection=pac-ret -march=armv8.3-a" } */
++
++/* Testing the do_return pattern for retaa and retab.  */
++long retbr_subcall(void);
++long retbr_do_return_retaa(void)
++{
++    return retbr_subcall()+1;
++}
++
++__attribute__((target("branch-protection=pac-ret+b-key")))
++long retbr_do_return_retab(void)
++{
++    return retbr_subcall()+1;
++}
++
++/* Ensure there are no BR or RET instructions which are not directly followed
++   by a speculation barrier.  */
++/* { dg-final { scan-assembler-not {\t(br|ret|retaa|retab)\tx[0-9][0-9]?\n\t(?!dsb\tsy\n\tisb)} } } */
++/* { dg-final { scan-assembler-not {ret\t} } } */
+diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c
+new file mode 100644
+index 0000000..76b8d03
+--- /dev/null
++++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-retbr.c
+@@ -0,0 +1,119 @@
++/* We ensure that -Wpedantic is off since it complains about the trampolines
++   we explicitly want to test.  */
++/* { dg-additional-options "-mharden-sls=retbr -Wno-pedantic " } */
++/*
++   Ensure that the SLS hardening of RET and BR leaves no unprotected RET/BR
++   instructions.
++  */
++typedef int (foo) (int, int);
++typedef void (bar) (int, int);
++struct sls_testclass {
++    foo *x;
++    bar *y;
++    int left;
++    int right;
++};
++
++int
++retbr_sibcall_value_insn (struct sls_testclass x)
++{
++  return x.x(x.left, x.right);
++}
++
++void
++retbr_sibcall_insn (struct sls_testclass x)
++{
++  x.y(x.left, x.right);
++}
++
++/* Aim to test two different returns.
++   One that introduces a tail call in the middle of the function, and one that
++   has a normal return.  */
++int
++retbr_multiple_returns (struct sls_testclass x)
++{
++  int temp;
++  if (x.left % 10)
++    return x.x(x.left, 100);
++  else if (x.right % 20)
++    {
++      return x.x(x.left * x.right, 100);
++    }
++  temp = x.left % x.right;
++  temp *= 100;
++  temp /= 2;
++  return temp % 3;
++}
++
++void
++retbr_multiple_returns_void (struct sls_testclass x)
++{
++  if (x.left % 10)
++    {
++      x.y(x.left, 100);
++    }
++  else if (x.right % 20)
++    {
++      x.y(x.left * x.right, 100);
++    }
++  return;
++}
++
++/* Testing the casesi jump via register.  */
++__attribute__ ((optimize ("Os")))
++int
++retbr_casesi_dispatch (struct sls_testclass x)
++{
++  switch (x.left)
++    {
++    case -5:
++      return -2;
++    case -3:
++      return -1;
++    case 0:
++      return 0;
++    case 3:
++      return 1;
++    case 5:
++      break;
++    default:
++      __builtin_unreachable ();
++    }
++  return x.right;
++}
++
++/* Testing the BR in trampolines is mitigated against.  */
++void f1 (void *);
++void f3 (void *, void (*)(void *));
++void f2 (void *);
++
++int
++retbr_trampolines (void *a, int b)
++{
++  if (!b)
++    {
++      f1 (a);
++      return 1;
++    }
++  if (b)
++    {
++      void retbr_tramp_internal (void *c)
++      {
++	if (c == a)
++	  f2 (c);
++      }
++      f3 (a, retbr_tramp_internal);
++    }
++  return 0;
++}
++
++/* Testing the indirect_jump pattern.  */
++void
++retbr_indirect_jump (int *buf)
++{
++  __builtin_longjmp(buf, 1);
++}
++
++/* Ensure there are no BR or RET instructions which are not directly followed
++   by a speculation barrier.  */
++/* { dg-final { scan-assembler-not {\t(br|ret|retaa|retab)\tx[0-9][0-9]?\n\t(?!dsb\tsy\n\tisb|sb)} } } */
+diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp
+new file mode 100644
+index 0000000..8122503
+--- /dev/null
++++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-mitigation.exp
+@@ -0,0 +1,73 @@
++#  Regression driver for SLS mitigation on AArch64.
++#  Copyright (C) 2020 Free Software Foundation, Inc.
++#  Contributed by ARM Ltd.
++#
++#  This file is part of GCC.
++#
++#  GCC is free software; you can redistribute it and/or modify it
++#  under the terms of the GNU General Public License as published by
++#  the Free Software Foundation; either version 3, or (at your option)
++#  any later version.
++#
++#  GCC is distributed in the hope that it will be useful, but
++#  WITHOUT ANY WARRANTY; without even the implied warranty of
++#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
++#  General Public License for more details.
++#
++#  You should have received a copy of the GNU General Public License
++#  along with GCC; see the file COPYING3.  If not see
++#  <http://www.gnu.org/licenses/>.  */
++
++# Exit immediately if this isn't an AArch64 target.
++if {![istarget aarch64*-*-*] } then {
++  return
++}
++
++# Load support procs.
++load_lib gcc-dg.exp
++load_lib torture-options.exp
++
++# If a testcase doesn't have special options, use these.
++global DEFAULT_CFLAGS
++if ![info exists DEFAULT_CFLAGS] then {
++    set DEFAULT_CFLAGS " "
++}
++
++# Initialize `dg'.
++dg-init
++torture-init
++
++# Use different architectures as well as the normal optimisation options.
++# (i.e. use both SB and DSB+ISB barriers).
++
++set save-dg-do-what-default ${dg-do-what-default}
++# Main loop.
++# Run with torture tests (i.e. a bunch of different optimisation levels) just
++# to increase test coverage.
++set dg-do-what-default assemble
++gcc-dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*.\[cCS\]]] \
++	"-save-temps" $DEFAULT_CFLAGS
++
++# Run the same tests but this time with SB extension.
++# Since not all supported assemblers will support that extension we decide
++# whether to assemble or just compile based on whether the extension is
++# supported for the available assembler.
++
++set templist {}
++foreach x $DG_TORTURE_OPTIONS {
++  lappend templist "$x -march=armv8.3-a+sb "
++  lappend templist "$x -march=armv8-a+sb "
++}
++set-torture-options $templist
++if { [check_effective_target_aarch64_asm_sb_ok] } {
++    set dg-do-what-default assemble
++} else {
++    set dg-do-what-default compile
++}
++gcc-dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/*.\[cCS\]]] \
++	"-save-temps" $DEFAULT_CFLAGS
++set dg-do-what-default ${save-dg-do-what-default}
++
++# All done.
++torture-finish
++dg-finish
+diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
+index 8a186dd..9d2e093 100644
+--- a/gcc/testsuite/lib/target-supports.exp
++++ b/gcc/testsuite/lib/target-supports.exp
+@@ -9432,7 +9432,7 @@ proc check_effective_target_aarch64_tiny { } {
+ # various architecture extensions via the .arch_extension pseudo-op.
+ 
+ foreach { aarch64_ext } { "fp" "simd" "crypto" "crc" "lse" "dotprod" "sve"
+-			  "i8mm" "f32mm" "f64mm" "bf16" } {
++			  "i8mm" "f32mm" "f64mm" "bf16" "sb" } {
+     eval [string map [list FUNC $aarch64_ext] {
+ 	proc check_effective_target_aarch64_asm_FUNC_ok { } {
+ 	  if { [istarget aarch64*-*-*] } {
+-- 
+2.7.4
+
diff --git a/meta/recipes-devtools/gcc/gcc-10.1/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch b/meta/recipes-devtools/gcc/gcc-10.1/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch
new file mode 100644
index 0000000000..716a367172
--- /dev/null
+++ b/meta/recipes-devtools/gcc/gcc-10.1/0003-aarch64-Mitigate-SLS-for-BLR-instruction.patch
@@ -0,0 +1,658 @@
+Upstream-Status: Backport
+Signed-off-by: Ross Burton <ross.burton@arm.com>
+
+From a5e7efc40ed841934c1d913f39476afa17d8e5f7 Mon Sep 17 00:00:00 2001
+From: Matthew Malcomson <matthew.malcomson@arm.com>
+Date: Thu, 9 Jul 2020 09:11:59 +0100
+Subject: [PATCH 3/3] aarch64: Mitigate SLS for BLR instruction
+
+This patch introduces the mitigation for Straight Line Speculation past
+the BLR instruction.
+
+This mitigation replaces BLR instructions with a BL to a stub which uses
+a BR to jump to the original value.  These function stubs are then
+appended with a speculation barrier to ensure no straight line
+speculation happens after these jumps.
+
+When optimising for speed we use a set of stubs for each function since
+this should help the branch predictor make more accurate predictions
+about where a stub should branch.
+
+When optimising for size we use one set of stubs for all functions.
+This set of stubs can have human readable names, and we are using
+`__call_indirect_x<N>` for register x<N>.
+
+When BTI branch protection is enabled the BLR instruction can jump to a
+`BTI c` instruction using any register, while the BR instruction can
+only jump to a `BTI c` instruction using the x16 or x17 registers.
+Hence, in order to ensure this transformation is safe we mov the value
+of the original register into x16 and use x16 for the BR.
+
+As an example when optimising for size:
+a
+    BLR x0
+instruction would get transformed to something like
+    BL __call_indirect_x0
+where __call_indirect_x0 labels a thunk that contains
+__call_indirect_x0:
+    MOV X16, X0
+    BR X16
+    <speculation barrier>
+
+The first version of this patch used local symbols specific to a
+compilation unit to try and avoid relocations.
+This was mistaken since functions coming from the same compilation unit
+can still be in different sections, and the assembler will insert
+relocations at jumps between sections.
+
+On any relocation the linker is permitted to emit a veneer to handle
+jumps between symbols that are very far apart.  The registers x16 and
+x17 may be clobbered by these veneers.
+Hence the function stubs cannot rely on the values of x16 and x17 being
+the same as just before the function stub is called.
+
+Similar can be said for the hot/cold partitioning of single functions,
+so function-local stubs have the same restriction.
+
+This updated version of the patch never emits function stubs for x16 and
+x17, and instead forces other registers to be used.
+
+Given the above, there is now no benefit to local symbols (since they
+are not enough to avoid dealing with linker intricacies).  This patch
+now uses global symbols with hidden visibility each stored in their own
+COMDAT section.  This means stubs can be shared between compilation
+units while still avoiding the PLT indirection.
+
+This patch also removes the `__call_indirect_x30` stub (and
+function-local equivalent) which would simply jump back to the original
+location.
+
+The function-local stubs are emitted to the assembly output file in one
+chunk, which means we need not add the speculation barrier directly
+after each one.
+This is because we know for certain that the instructions directly after
+the BR in all but the last function stub will be from another one of
+these stubs and hence will not contain a speculation gadget.
+Instead we add a speculation barrier at the end of the sequence of
+stubs.
+
+The global stubs are emitted in COMDAT/.linkonce sections by
+themselves so that the linker can remove duplicates from multiple object
+files.  This means they are not emitted in one chunk, and each one must
+include the speculation barrier.
+
+Another difference is that since the global stubs are shared across
+compilation units we do not know that all functions will be targeting an
+architecture supporting the SB instruction.
+Rather than provide multiple stubs for each architecture, we provide a
+stub that will work for all architectures -- using the DSB+ISB barrier.
+
+This mitigation does not apply for BLR instructions in the following
+places:
+- Some accesses to thread-local variables use a code sequence with a BLR
+  instruction.  This code sequence is part of the binary interface between
+  compiler and linker. If this BLR instruction needs to be mitigated, it'd
+  probably be best to do so in the linker. It seems that the code sequence
+  for thread-local variable access is unlikely to lead to a Spectre Revalation
+  Gadget.
+- PLT stubs are produced by the linker and each contain a BLR instruction.
+  It seems that at most only after the last PLT stub a Spectre Revalation
+  Gadget might appear.
+
+Testing:
+  Bootstrap and regtest on AArch64
+    (with BOOT_CFLAGS="-mharden-sls=retbr,blr")
+  Used a temporary hack(1) in gcc-dg.exp to use these options on every
+  test in the testsuite, a slight modification to emit the speculation
+  barrier after every function stub, and a script to check that the
+  output never emitted a BLR, or unmitigated BR or RET instruction.
+  Similar on an aarch64-none-elf cross-compiler.
+
+1) Temporary hack emitted a speculation barrier at the end of every stub
+function, and used a script to ensure that:
+  a) Every RET or BR is immediately followed by a speculation barrier.
+  b) No BLR instruction is emitted by compiler.
+
+gcc/ChangeLog:
+
+	* config/aarch64/aarch64-protos.h (aarch64_indirect_call_asm):
+	New declaration.
+	* config/aarch64/aarch64.c (aarch64_regno_regclass): Handle new
+	stub registers class.
+	(aarch64_class_max_nregs): Likewise.
+	(aarch64_register_move_cost): Likewise.
+	(aarch64_sls_shared_thunks): Global array to store stub labels.
+	(aarch64_sls_emit_function_stub): New.
+	(aarch64_create_blr_label): New.
+	(aarch64_sls_emit_blr_function_thunks): New.
+	(aarch64_sls_emit_shared_blr_thunks): New.
+	(aarch64_asm_file_end): New.
+	(aarch64_indirect_call_asm): New.
+	(TARGET_ASM_FILE_END): Use aarch64_asm_file_end.
+	(TARGET_ASM_FUNCTION_EPILOGUE): Use
+	aarch64_sls_emit_blr_function_thunks.
+	* config/aarch64/aarch64.h (STB_REGNUM_P): New.
+	(enum reg_class): Add STUB_REGS class.
+	(machine_function): Introduce `call_via` array for
+	function-local stub labels.
+	* config/aarch64/aarch64.md (*call_insn, *call_value_insn): Use
+	aarch64_indirect_call_asm to emit code when hardening BLR
+	instructions.
+	* config/aarch64/constraints.md (Ucr): New constraint
+	representing registers for indirect calls.  Is GENERAL_REGS
+	usually, and STUB_REGS when hardening BLR instruction against
+	SLS.
+	* config/aarch64/predicates.md (aarch64_general_reg): STUB_REGS class
+	is also a general register.
+
+gcc/testsuite/ChangeLog:
+
+	* gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c: New test.
+	* gcc.target/aarch64/sls-mitigation/sls-miti-blr.c: New test.
+---
+ gcc/config/aarch64/aarch64-protos.h                |   1 +
+ gcc/config/aarch64/aarch64.c                       | 225 ++++++++++++++++++++-
+ gcc/config/aarch64/aarch64.h                       |  15 ++
+ gcc/config/aarch64/aarch64.md                      |  11 +-
+ gcc/config/aarch64/constraints.md                  |   9 +
+ gcc/config/aarch64/predicates.md                   |   3 +-
+ .../aarch64/sls-mitigation/sls-miti-blr-bti.c      |  40 ++++
+ .../aarch64/sls-mitigation/sls-miti-blr.c          |  33 +++
+ 8 files changed, 328 insertions(+), 9 deletions(-)
+ create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c
+ create mode 100644 gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c
+
+diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
+index ee0ffde..839f801 100644
+--- a/gcc/config/aarch64/aarch64-protos.h
++++ b/gcc/config/aarch64/aarch64-protos.h
+@@ -782,6 +782,7 @@ extern const atomic_ool_names aarch64_ool_ldeor_names;
+ tree aarch64_resolve_overloaded_builtin_general (location_t, tree, void *);
+ 
+ const char *aarch64_sls_barrier (int);
++const char *aarch64_indirect_call_asm (rtx);
+ extern bool aarch64_harden_sls_retbr_p (void);
+ extern bool aarch64_harden_sls_blr_p (void);
+ 
+diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
+index 2389d49..0f7bba3 100644
+--- a/gcc/config/aarch64/aarch64.c
++++ b/gcc/config/aarch64/aarch64.c
+@@ -10605,6 +10605,9 @@ aarch64_label_mentioned_p (rtx x)
+ enum reg_class
+ aarch64_regno_regclass (unsigned regno)
+ {
++  if (STUB_REGNUM_P (regno))
++    return STUB_REGS;
++
+   if (GP_REGNUM_P (regno))
+     return GENERAL_REGS;
+ 
+@@ -10939,6 +10942,7 @@ aarch64_class_max_nregs (reg_class_t regclass, machine_mode mode)
+   unsigned int nregs, vec_flags;
+   switch (regclass)
+     {
++    case STUB_REGS:
+     case TAILCALL_ADDR_REGS:
+     case POINTER_REGS:
+     case GENERAL_REGS:
+@@ -13155,10 +13159,12 @@ aarch64_register_move_cost (machine_mode mode,
+     = aarch64_tune_params.regmove_cost;
+ 
+   /* Caller save and pointer regs are equivalent to GENERAL_REGS.  */
+-  if (to == TAILCALL_ADDR_REGS || to == POINTER_REGS)
++  if (to == TAILCALL_ADDR_REGS || to == POINTER_REGS
++      || to == STUB_REGS)
+     to = GENERAL_REGS;
+ 
+-  if (from == TAILCALL_ADDR_REGS || from == POINTER_REGS)
++  if (from == TAILCALL_ADDR_REGS || from == POINTER_REGS
++      || from == STUB_REGS)
+     from = GENERAL_REGS;
+ 
+   /* Make RDFFR very expensive.  In particular, if we know that the FFR
+@@ -22957,6 +22963,215 @@ aarch64_sls_barrier (int mitigation_required)
+     : "";
+ }
+ 
++static GTY (()) tree aarch64_sls_shared_thunks[30];
++static GTY (()) bool aarch64_sls_shared_thunks_needed = false;
++const char *indirect_symbol_names[30] = {
++    "__call_indirect_x0",
++    "__call_indirect_x1",
++    "__call_indirect_x2",
++    "__call_indirect_x3",
++    "__call_indirect_x4",
++    "__call_indirect_x5",
++    "__call_indirect_x6",
++    "__call_indirect_x7",
++    "__call_indirect_x8",
++    "__call_indirect_x9",
++    "__call_indirect_x10",
++    "__call_indirect_x11",
++    "__call_indirect_x12",
++    "__call_indirect_x13",
++    "__call_indirect_x14",
++    "__call_indirect_x15",
++    "", /* "__call_indirect_x16",  */
++    "", /* "__call_indirect_x17",  */
++    "__call_indirect_x18",
++    "__call_indirect_x19",
++    "__call_indirect_x20",
++    "__call_indirect_x21",
++    "__call_indirect_x22",
++    "__call_indirect_x23",
++    "__call_indirect_x24",
++    "__call_indirect_x25",
++    "__call_indirect_x26",
++    "__call_indirect_x27",
++    "__call_indirect_x28",
++    "__call_indirect_x29",
++};
++
++/* Function to create a BLR thunk.  This thunk is used to mitigate straight
++   line speculation.  Instead of a simple BLR that can be speculated past,
++   we emit a BL to this thunk, and this thunk contains a BR to the relevant
++   register.  These thunks have the relevant speculation barries put after
++   their indirect branch so that speculation is blocked.
++
++   We use such a thunk so the speculation barriers are kept off the
++   architecturally executed path in order to reduce the performance overhead.
++
++   When optimizing for size we use stubs shared by the linked object.
++   When optimizing for performance we emit stubs for each function in the hope
++   that the branch predictor can better train on jumps specific for a given
++   function.  */
++rtx
++aarch64_sls_create_blr_label (int regnum)
++{
++  gcc_assert (STUB_REGNUM_P (regnum));
++  if (optimize_function_for_size_p (cfun))
++    {
++      /* For the thunks shared between different functions in this compilation
++	 unit we use a named symbol -- this is just for users to more easily
++	 understand the generated assembly.  */
++      aarch64_sls_shared_thunks_needed = true;
++      const char *thunk_name = indirect_symbol_names[regnum];
++      if (aarch64_sls_shared_thunks[regnum] == NULL)
++	{
++	  /* Build a decl representing this function stub and record it for
++	     later.  We build a decl here so we can use the GCC machinery for
++	     handling sections automatically (through `get_named_section` and
++	     `make_decl_one_only`).  That saves us a lot of trouble handling
++	     the specifics of different output file formats.  */
++	  tree decl = build_decl (BUILTINS_LOCATION, FUNCTION_DECL,
++				  get_identifier (thunk_name),
++				  build_function_type_list (void_type_node,
++							    NULL_TREE));
++	  DECL_RESULT (decl) = build_decl (BUILTINS_LOCATION, RESULT_DECL,
++					   NULL_TREE, void_type_node);
++	  TREE_PUBLIC (decl) = 1;
++	  TREE_STATIC (decl) = 1;
++	  DECL_IGNORED_P (decl) = 1;
++	  DECL_ARTIFICIAL (decl) = 1;
++	  make_decl_one_only (decl, DECL_ASSEMBLER_NAME (decl));
++	  resolve_unique_section (decl, 0, false);
++	  aarch64_sls_shared_thunks[regnum] = decl;
++	}
++
++      return gen_rtx_SYMBOL_REF (Pmode, thunk_name);
++    }
++
++  if (cfun->machine->call_via[regnum] == NULL)
++    cfun->machine->call_via[regnum]
++      = gen_rtx_LABEL_REF (Pmode, gen_label_rtx ());
++  return cfun->machine->call_via[regnum];
++}
++
++/* Helper function for aarch64_sls_emit_blr_function_thunks and
++   aarch64_sls_emit_shared_blr_thunks below.  */
++static void
++aarch64_sls_emit_function_stub (FILE *out_file, int regnum)
++{
++  /* Save in x16 and branch to that function so this transformation does
++     not prevent jumping to `BTI c` instructions.  */
++  asm_fprintf (out_file, "\tmov\tx16, x%d\n", regnum);
++  asm_fprintf (out_file, "\tbr\tx16\n");
++}
++
++/* Emit all BLR stubs for this particular function.
++   Here we emit all the BLR stubs needed for the current function.  Since we
++   emit these stubs in a consecutive block we know there will be no speculation
++   gadgets between each stub, and hence we only emit a speculation barrier at
++   the end of the stub sequences.
++
++   This is called in the TARGET_ASM_FUNCTION_EPILOGUE hook.  */
++void
++aarch64_sls_emit_blr_function_thunks (FILE *out_file)
++{
++  if (! aarch64_harden_sls_blr_p ())
++    return;
++
++  bool any_functions_emitted = false;
++  /* We must save and restore the current function section since this assembly
++     is emitted at the end of the function.  This means it can be emitted *just
++     after* the cold section of a function.  That cold part would be emitted in
++     a different section.  That switch would trigger a `.cfi_endproc` directive
++     to be emitted in the original section and a `.cfi_startproc` directive to
++     be emitted in the new section.  Switching to the original section without
++     restoring would mean that the `.cfi_endproc` emitted as a function ends
++     would happen in a different section -- leaving an unmatched
++     `.cfi_startproc` in the cold text section and an unmatched `.cfi_endproc`
++     in the standard text section.  */
++  section *save_text_section = in_section;
++  switch_to_section (function_section (current_function_decl));
++  for (int regnum = 0; regnum < 30; ++regnum)
++    {
++      rtx specu_label = cfun->machine->call_via[regnum];
++      if (specu_label == NULL)
++	continue;
++
++      targetm.asm_out.print_operand (out_file, specu_label, 0);
++      asm_fprintf (out_file, ":\n");
++      aarch64_sls_emit_function_stub (out_file, regnum);
++      any_functions_emitted = true;
++    }
++  if (any_functions_emitted)
++    /* Can use the SB if needs be here, since this stub will only be used
++      by the current function, and hence for the current target.  */
++    asm_fprintf (out_file, "\t%s\n", aarch64_sls_barrier (true));
++  switch_to_section (save_text_section);
++}
++
++/* Emit shared BLR stubs for the current compilation unit.
++   Over the course of compiling this unit we may have converted some BLR
++   instructions to a BL to a shared stub function.  This is where we emit those
++   stub functions.
++   This function is for the stubs shared between different functions in this
++   compilation unit.  We share when optimizing for size instead of speed.
++
++   This function is called through the TARGET_ASM_FILE_END hook.  */
++void
++aarch64_sls_emit_shared_blr_thunks (FILE *out_file)
++{
++  if (! aarch64_sls_shared_thunks_needed)
++    return;
++
++  for (int regnum = 0; regnum < 30; ++regnum)
++    {
++      tree decl = aarch64_sls_shared_thunks[regnum];
++      if (!decl)
++	continue;
++
++      const char *name = indirect_symbol_names[regnum];
++      switch_to_section (get_named_section (decl, NULL, 0));
++      ASM_OUTPUT_ALIGN (out_file, 2);
++      targetm.asm_out.globalize_label (out_file, name);
++      /* Only emits if the compiler is configured for an assembler that can
++	 handle visibility directives.  */
++      targetm.asm_out.assemble_visibility (decl, VISIBILITY_HIDDEN);
++      ASM_OUTPUT_TYPE_DIRECTIVE (out_file, name, "function");
++      ASM_OUTPUT_LABEL (out_file, name);
++      aarch64_sls_emit_function_stub (out_file, regnum);
++      /* Use the most conservative target to ensure it can always be used by any
++	 function in the translation unit.  */
++      asm_fprintf (out_file, "\tdsb\tsy\n\tisb\n");
++      ASM_DECLARE_FUNCTION_SIZE (out_file, name, decl);
++    }
++}
++
++/* Implement TARGET_ASM_FILE_END.  */
++void
++aarch64_asm_file_end ()
++{
++  aarch64_sls_emit_shared_blr_thunks (asm_out_file);
++  /* Since this function will be called for the ASM_FILE_END hook, we ensure
++     that what would be called otherwise (e.g. `file_end_indicate_exec_stack`
++     for FreeBSD) still gets called.  */
++#ifdef TARGET_ASM_FILE_END
++  TARGET_ASM_FILE_END ();
++#endif
++}
++
++const char *
++aarch64_indirect_call_asm (rtx addr)
++{
++  gcc_assert (REG_P (addr));
++  if (aarch64_harden_sls_blr_p ())
++    {
++      rtx stub_label = aarch64_sls_create_blr_label (REGNO (addr));
++      output_asm_insn ("bl\t%0", &stub_label);
++    }
++  else
++   output_asm_insn ("blr\t%0", &addr);
++  return "";
++}
++
+ /* Target-specific selftests.  */
+ 
+ #if CHECKING_P
+@@ -23507,6 +23722,12 @@ aarch64_libgcc_floating_mode_supported_p
+ #undef TARGET_MD_ASM_ADJUST
+ #define TARGET_MD_ASM_ADJUST arm_md_asm_adjust
+ 
++#undef TARGET_ASM_FILE_END
++#define TARGET_ASM_FILE_END aarch64_asm_file_end
++
++#undef TARGET_ASM_FUNCTION_EPILOGUE
++#define TARGET_ASM_FUNCTION_EPILOGUE aarch64_sls_emit_blr_function_thunks
++
+ struct gcc_target targetm = TARGET_INITIALIZER;
+ 
+ #include "gt-aarch64.h"
+diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
+index 8e0fc37..7331450 100644
+--- a/gcc/config/aarch64/aarch64.h
++++ b/gcc/config/aarch64/aarch64.h
+@@ -643,6 +643,16 @@ extern unsigned aarch64_architecture_version;
+ #define GP_REGNUM_P(REGNO)						\
+   (((unsigned) (REGNO - R0_REGNUM)) <= (R30_REGNUM - R0_REGNUM))
+ 
++/* Registers known to be preserved over a BL instruction.  This consists of the
++   GENERAL_REGS without x16, x17, and x30.  The x30 register is changed by the
++   BL instruction itself, while the x16 and x17 registers may be used by
++   veneers which can be inserted by the linker.  */
++#define STUB_REGNUM_P(REGNO) \
++  (GP_REGNUM_P (REGNO) \
++   && (REGNO) != R16_REGNUM \
++   && (REGNO) != R17_REGNUM \
++   && (REGNO) != R30_REGNUM) \
++
+ #define FP_REGNUM_P(REGNO)			\
+   (((unsigned) (REGNO - V0_REGNUM)) <= (V31_REGNUM - V0_REGNUM))
+ 
+@@ -667,6 +677,7 @@ enum reg_class
+ {
+   NO_REGS,
+   TAILCALL_ADDR_REGS,
++  STUB_REGS,
+   GENERAL_REGS,
+   STACK_REG,
+   POINTER_REGS,
+@@ -689,6 +700,7 @@ enum reg_class
+ {						\
+   "NO_REGS",					\
+   "TAILCALL_ADDR_REGS",				\
++  "STUB_REGS",					\
+   "GENERAL_REGS",				\
+   "STACK_REG",					\
+   "POINTER_REGS",				\
+@@ -708,6 +720,7 @@ enum reg_class
+ {									\
+   { 0x00000000, 0x00000000, 0x00000000 },	/* NO_REGS */		\
+   { 0x00030000, 0x00000000, 0x00000000 },	/* TAILCALL_ADDR_REGS */\
++  { 0x3ffcffff, 0x00000000, 0x00000000 },	/* STUB_REGS */		\
+   { 0x7fffffff, 0x00000000, 0x00000003 },	/* GENERAL_REGS */	\
+   { 0x80000000, 0x00000000, 0x00000000 },	/* STACK_REG */		\
+   { 0xffffffff, 0x00000000, 0x00000003 },	/* POINTER_REGS */	\
+@@ -862,6 +875,8 @@ typedef struct GTY (()) machine_function
+   struct aarch64_frame frame;
+   /* One entry for each hard register.  */
+   bool reg_is_wrapped_separately[LAST_SAVED_REGNUM];
++  /* One entry for each general purpose register.  */
++  rtx call_via[SP_REGNUM];
+   bool label_is_assembled;
+ } machine_function;
+ #endif
+diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
+index dda04ee..43da754 100644
+--- a/gcc/config/aarch64/aarch64.md
++++ b/gcc/config/aarch64/aarch64.md
+@@ -1022,16 +1022,15 @@
+ )
+ 
+ (define_insn "*call_insn"
+-  [(call (mem:DI (match_operand:DI 0 "aarch64_call_insn_operand" "r, Usf"))
++  [(call (mem:DI (match_operand:DI 0 "aarch64_call_insn_operand" "Ucr, Usf"))
+ 	 (match_operand 1 "" ""))
+    (unspec:DI [(match_operand:DI 2 "const_int_operand")] UNSPEC_CALLEE_ABI)
+    (clobber (reg:DI LR_REGNUM))]
+   ""
+   "@
+-  blr\\t%0
++  * return aarch64_indirect_call_asm (operands[0]);
+   bl\\t%c0"
+-  [(set_attr "type" "call, call")]
+-)
++  [(set_attr "type" "call, call")])
+ 
+ (define_expand "call_value"
+   [(parallel
+@@ -1050,13 +1049,13 @@
+ 
+ (define_insn "*call_value_insn"
+   [(set (match_operand 0 "" "")
+-	(call (mem:DI (match_operand:DI 1 "aarch64_call_insn_operand" "r, Usf"))
++	(call (mem:DI (match_operand:DI 1 "aarch64_call_insn_operand" "Ucr, Usf"))
+ 		      (match_operand 2 "" "")))
+    (unspec:DI [(match_operand:DI 3 "const_int_operand")] UNSPEC_CALLEE_ABI)
+    (clobber (reg:DI LR_REGNUM))]
+   ""
+   "@
+-  blr\\t%1
++  * return aarch64_indirect_call_asm (operands[1]);
+   bl\\t%c1"
+   [(set_attr "type" "call, call")]
+ )
+diff --git a/gcc/config/aarch64/constraints.md b/gcc/config/aarch64/constraints.md
+index d993268..8cc6f50 100644
+--- a/gcc/config/aarch64/constraints.md
++++ b/gcc/config/aarch64/constraints.md
+@@ -24,6 +24,15 @@
+ (define_register_constraint "Ucs" "TAILCALL_ADDR_REGS"
+   "@internal Registers suitable for an indirect tail call")
+ 
++(define_register_constraint "Ucr"
++    "aarch64_harden_sls_blr_p () ? STUB_REGS : GENERAL_REGS"
++  "@internal Registers to be used for an indirect call.
++   This is usually the general registers, but when we are hardening against
++   Straight Line Speculation we disallow x16, x17, and x30 so we can use
++   indirection stubs.  These indirection stubs cannot use the above registers
++   since they will be reached by a BL that may have to go through a linker
++   veneer.")
++
+ (define_register_constraint "w" "FP_REGS"
+   "Floating point and SIMD vector registers.")
+ 
+diff --git a/gcc/config/aarch64/predicates.md b/gcc/config/aarch64/predicates.md
+index 215fcec..1754b1e 100644
+--- a/gcc/config/aarch64/predicates.md
++++ b/gcc/config/aarch64/predicates.md
+@@ -32,7 +32,8 @@
+ 
+ (define_predicate "aarch64_general_reg"
+   (and (match_operand 0 "register_operand")
+-       (match_test "REGNO_REG_CLASS (REGNO (op)) == GENERAL_REGS")))
++       (match_test "REGNO_REG_CLASS (REGNO (op)) == STUB_REGS
++		    || REGNO_REG_CLASS (REGNO (op)) == GENERAL_REGS")))
+ 
+ ;; Return true if OP a (const_int 0) operand.
+ (define_predicate "const0_operand"
+diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c
+new file mode 100644
+index 0000000..b1fb754
+--- /dev/null
++++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr-bti.c
+@@ -0,0 +1,40 @@
++/* { dg-do compile } */
++/* { dg-additional-options "-mharden-sls=blr -mbranch-protection=bti" } */
++/*
++   Ensure that the SLS hardening of BLR leaves no BLR instructions.
++   Here we also check that there are no BR instructions with anything except an
++   x16 or x17 register.  This is because a `BTI c` instruction can be branched
++   to using a BLR instruction using any register, but can only be branched to
++   with a BR using an x16 or x17 register.
++  */
++typedef int (foo) (int, int);
++typedef void (bar) (int, int);
++struct sls_testclass {
++    foo *x;
++    bar *y;
++    int left;
++    int right;
++};
++
++/* We test both RTL patterns for a call which returns a value and a call which
++   does not.  */
++int blr_call_value (struct sls_testclass x)
++{
++  int retval = x.x(x.left, x.right);
++  if (retval % 10)
++    return 100;
++  return 9;
++}
++
++int blr_call (struct sls_testclass x)
++{
++  x.y(x.left, x.right);
++  if (x.left % 10)
++    return 100;
++  return 9;
++}
++
++/* { dg-final { scan-assembler-not {\tblr\t} } } */
++/* { dg-final { scan-assembler-not {\tbr\tx(?!16|17)} } } */
++/* { dg-final { scan-assembler {\tbr\tx(16|17)} } } */
++
+diff --git a/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c
+new file mode 100644
+index 0000000..88bafff
+--- /dev/null
++++ b/gcc/testsuite/gcc.target/aarch64/sls-mitigation/sls-miti-blr.c
+@@ -0,0 +1,33 @@
++/* { dg-additional-options "-mharden-sls=blr -save-temps" } */
++/* Ensure that the SLS hardening of BLR leaves no BLR instructions.
++   We only test that all BLR instructions have been removed, not that the
++   resulting code makes sense.  */
++typedef int (foo) (int, int);
++typedef void (bar) (int, int);
++struct sls_testclass {
++    foo *x;
++    bar *y;
++    int left;
++    int right;
++};
++
++/* We test both RTL patterns for a call which returns a value and a call which
++   does not.  */
++int blr_call_value (struct sls_testclass x)
++{
++  int retval = x.x(x.left, x.right);
++  if (retval % 10)
++    return 100;
++  return 9;
++}
++
++int blr_call (struct sls_testclass x)
++{
++  x.y(x.left, x.right);
++  if (x.left % 10)
++    return 100;
++  return 9;
++}
++
++/* { dg-final { scan-assembler-not {\tblr\t} } } */
++/* { dg-final { scan-assembler {\tbr\tx[0-9][0-9]?} } } */
+-- 
+2.7.4
+