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

Pull arm64 updates from Will Deacon:
 "A sizeable pile of arm64 updates for 5.8.

  Summary below, but the big two features are support for Branch Target
  Identification and Clang's Shadow Call stack. The latter is currently
  arm64-only, but the high-level parts are all in core code so it could
  easily be adopted by other architectures pending toolchain support

  Branch Target Identification (BTI):

   - Support for ARMv8.5-BTI in both user- and kernel-space. This allows
     branch targets to limit the types of branch from which they can be
     called and additionally prevents branching to arbitrary code,
     although kernel support requires a very recent toolchain.

   - Function annotation via SYM_FUNC_START() so that assembly functions
     are wrapped with the relevant "landing pad" instructions.

   - BPF and vDSO updates to use the new instructions.

   - Addition of a new HWCAP and exposure of BTI capability to userspace
     via ID register emulation, along with ELF loader support for the
     BTI feature in .note.gnu.property.

   - Non-critical fixes to CFI unwind annotations in the sigreturn
     trampoline.

  Shadow Call Stack (SCS):

   - Support for Clang's Shadow Call Stack feature, which reserves
     platform register x18 to point at a separate stack for each task
     that holds only return addresses. This protects function return
     control flow from buffer overruns on the main stack.

   - Save/restore of x18 across problematic boundaries (user-mode,
     hypervisor, EFI, suspend, etc).

   - Core support for SCS, should other architectures want to use it
     too.

   - SCS overflow checking on context-switch as part of the existing
     stack limit check if CONFIG_SCHED_STACK_END_CHECK=y.

  CPU feature detection:

   - Removed numerous "SANITY CHECK" errors when running on a system
     with mismatched AArch32 support at EL1. This is primarily a concern
     for KVM, which disabled support for 32-bit guests on such a system.

   - Addition of new ID registers and fields as the architecture has
     been extended.

  Perf and PMU drivers:

   - Minor fixes and cleanups to system PMU drivers.

  Hardware errata:

   - Unify KVM workarounds for VHE and nVHE configurations.

   - Sort vendor errata entries in Kconfig.

  Secure Monitor Call Calling Convention (SMCCC):

   - Update to the latest specification from Arm (v1.2).

   - Allow PSCI code to query the SMCCC version.

  Software Delegated Exception Interface (SDEI):

   - Unexport a bunch of unused symbols.

   - Minor fixes to handling of firmware data.

  Pointer authentication:

   - Add support for dumping the kernel PAC mask in vmcoreinfo so that
     the stack can be unwound by tools such as kdump.

   - Simplification of key initialisation during CPU bringup.

  BPF backend:

   - Improve immediate generation for logical and add/sub instructions.

  vDSO:

   - Minor fixes to the linker flags for consistency with other
     architectures and support for LLVM's unwinder.

   - Clean up logic to initialise and map the vDSO into userspace.

  ACPI:

   - Work around for an ambiguity in the IORT specification relating to
     the "num_ids" field.

   - Support _DMA method for all named components rather than only PCIe
     root complexes.

   - Minor other IORT-related fixes.

  Miscellaneous:

   - Initialise debug traps early for KGDB and fix KDB cacheflushing
     deadlock.

   - Minor tweaks to early boot state (documentation update, set
     TEXT_OFFSET to 0x0, increase alignment of PE/COFF sections).

   - Refactoring and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (148 commits)
  KVM: arm64: Move __load_guest_stage2 to kvm_mmu.h
  KVM: arm64: Check advertised Stage-2 page size capability
  arm64/cpufeature: Add get_arm64_ftr_reg_nowarn()
  ACPI/IORT: Remove the unused __get_pci_rid()
  arm64/cpuinfo: Add ID_MMFR4_EL1 into the cpuinfo_arm64 context
  arm64/cpufeature: Add remaining feature bits in ID_AA64PFR1 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64PFR0 register
  arm64/cpufeature: Add remaining feature bits in ID_AA64ISAR0 register
  arm64/cpufeature: Add remaining feature bits in ID_MMFR4 register
  arm64/cpufeature: Add remaining feature bits in ID_PFR0 register
  arm64/cpufeature: Introduce ID_MMFR5 CPU register
  arm64/cpufeature: Introduce ID_DFR1 CPU register
  arm64/cpufeature: Introduce ID_PFR2 CPU register
  arm64/cpufeature: Make doublelock a signed feature in ID_AA64DFR0
  arm64/cpufeature: Drop TraceFilt feature exposure from ID_DFR0 register
  arm64/cpufeature: Add explicit ftr_id_isar0[] for ID_ISAR0 register
  arm64: mm: Add asid_gen_match() helper
  firmware: smccc: Fix missing prototype warning for arm_smccc_version_init
  arm64: vdso: Fix CFI directives in sigreturn trampoline
  arm64: vdso: Don't prefix sigreturn trampoline with a BTI C instruction
  ...

1 files changed, 72 insertions, 61 deletions

diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c728f163f329..d332590f5978 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -272,6 +272,61 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 	}
 }
 
+#ifdef CONFIG_COMPAT
+#define PSTATE_IT_1_0_SHIFT	25
+#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
+#define PSTATE_IT_7_2_SHIFT	10
+#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
+
+static u32 compat_get_it_state(struct pt_regs *regs)
+{
+	u32 it, pstate = regs->pstate;
+
+	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
+	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
+
+	return it;
+}
+
+static void compat_set_it_state(struct pt_regs *regs, u32 it)
+{
+	u32 pstate_it;
+
+	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
+	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
+
+	regs->pstate &= ~PSR_AA32_IT_MASK;
+	regs->pstate |= pstate_it;
+}
+
+static void advance_itstate(struct pt_regs *regs)
+{
+	u32 it;
+
+	/* ARM mode */
+	if (!(regs->pstate & PSR_AA32_T_BIT) ||
+	    !(regs->pstate & PSR_AA32_IT_MASK))
+		return;
+
+	it  = compat_get_it_state(regs);
+
+	/*
+	 * If this is the last instruction of the block, wipe the IT
+	 * state. Otherwise advance it.
+	 */
+	if (!(it & 7))
+		it = 0;
+	else
+		it = (it & 0xe0) | ((it << 1) & 0x1f);
+
+	compat_set_it_state(regs, it);
+}
+#else
+static void advance_itstate(struct pt_regs *regs)
+{
+}
+#endif
+
 void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 {
 	regs->pc += size;
@@ -282,6 +337,11 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
 	 */
 	if (user_mode(regs))
 		user_fastforward_single_step(current);
+
+	if (compat_user_mode(regs))
+		advance_itstate(regs);
+	else
+		regs->pstate &= ~PSR_BTYPE_MASK;
 }
 
 static LIST_HEAD(undef_hook);
@@ -411,6 +471,13 @@ void do_undefinstr(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(do_undefinstr);
 
+void do_bti(struct pt_regs *regs)
+{
+	BUG_ON(!user_mode(regs));
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+}
+NOKPROBE_SYMBOL(do_bti);
+
 #define __user_cache_maint(insn, address, res)			\
 	if (address >= user_addr_max()) {			\
 		res = -EFAULT;					\
@@ -566,34 +633,7 @@ static const struct sys64_hook sys64_hooks[] = {
 	{},
 };
 
-
 #ifdef CONFIG_COMPAT
-#define PSTATE_IT_1_0_SHIFT	25
-#define PSTATE_IT_1_0_MASK	(0x3 << PSTATE_IT_1_0_SHIFT)
-#define PSTATE_IT_7_2_SHIFT	10
-#define PSTATE_IT_7_2_MASK	(0x3f << PSTATE_IT_7_2_SHIFT)
-
-static u32 compat_get_it_state(struct pt_regs *regs)
-{
-	u32 it, pstate = regs->pstate;
-
-	it  = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
-	it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
-
-	return it;
-}
-
-static void compat_set_it_state(struct pt_regs *regs, u32 it)
-{
-	u32 pstate_it;
-
-	pstate_it  = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
-	pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
-
-	regs->pstate &= ~PSR_AA32_IT_MASK;
-	regs->pstate |= pstate_it;
-}
-
 static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
 {
 	int cond;
@@ -614,42 +654,12 @@ static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
 	return aarch32_opcode_cond_checks[cond](regs->pstate);
 }
 
-static void advance_itstate(struct pt_regs *regs)
-{
-	u32 it;
-
-	/* ARM mode */
-	if (!(regs->pstate & PSR_AA32_T_BIT) ||
-	    !(regs->pstate & PSR_AA32_IT_MASK))
-		return;
-
-	it  = compat_get_it_state(regs);
-
-	/*
-	 * If this is the last instruction of the block, wipe the IT
-	 * state. Otherwise advance it.
-	 */
-	if (!(it & 7))
-		it = 0;
-	else
-		it = (it & 0xe0) | ((it << 1) & 0x1f);
-
-	compat_set_it_state(regs, it);
-}
-
-static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs,
-						   unsigned int sz)
-{
-	advance_itstate(regs);
-	arm64_skip_faulting_instruction(regs, sz);
-}
-
 static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
 
 	pt_regs_write_reg(regs, reg, arch_timer_get_rate());
-	arm64_compat_skip_faulting_instruction(regs, 4);
+	arm64_skip_faulting_instruction(regs, 4);
 }
 
 static const struct sys64_hook cp15_32_hooks[] = {
@@ -669,7 +679,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 
 	pt_regs_write_reg(regs, rt, lower_32_bits(val));
 	pt_regs_write_reg(regs, rt2, upper_32_bits(val));
-	arm64_compat_skip_faulting_instruction(regs, 4);
+	arm64_skip_faulting_instruction(regs, 4);
 }
 
 static const struct sys64_hook cp15_64_hooks[] = {
@@ -690,7 +700,7 @@ void do_cp15instr(unsigned int esr, struct pt_regs *regs)
 		 * There is no T16 variant of a CP access, so we
 		 * always advance PC by 4 bytes.
 		 */
-		arm64_compat_skip_faulting_instruction(regs, 4);
+		arm64_skip_faulting_instruction(regs, 4);
 		return;
 	}
 
@@ -753,6 +763,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_CP10_ID]		= "CP10 MRC/VMRS",
 	[ESR_ELx_EC_PAC]		= "PAC",
 	[ESR_ELx_EC_CP14_64]		= "CP14 MCRR/MRRC",
+	[ESR_ELx_EC_BTI]		= "BTI",
 	[ESR_ELx_EC_ILL]		= "PSTATE.IL",
 	[ESR_ELx_EC_SVC32]		= "SVC (AArch32)",
 	[ESR_ELx_EC_HVC32]		= "HVC (AArch32)",
@@ -1043,11 +1054,11 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
 }
 
-/* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
 	register_kernel_break_hook(&bug_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
 	register_kernel_break_hook(&kasan_break_hook);
 #endif
+	debug_traps_init();
 }