Merge branch 'for-next/bti-user' into for-next/bti

Merge in user support for Branch Target Identification, which narrowly
missed the cut for 5.7 after a late ABI concern.

* for-next/bti-user:
  arm64: bti: Document behaviour for dynamically linked binaries
  arm64: elf: Fix allnoconfig kernel build with !ARCH_USE_GNU_PROPERTY
  arm64: BTI: Add Kconfig entry for userspace BTI
  mm: smaps: Report arm64 guarded pages in smaps
  arm64: mm: Display guarded pages in ptdump
  KVM: arm64: BTI: Reset BTYPE when skipping emulated instructions
  arm64: BTI: Reset BTYPE when skipping emulated instructions
  arm64: traps: Shuffle code to eliminate forward declarations
  arm64: unify native/compat instruction skipping
  arm64: BTI: Decode BYTPE bits when printing PSTATE
  arm64: elf: Enable BTI at exec based on ELF program properties
  elf: Allow arch to tweak initial mmap prot flags
  arm64: Basic Branch Target Identification support
  ELF: Add ELF program property parsing support
  ELF: UAPI and Kconfig additions for ELF program properties

Author: willdeacon

Documentation/arm64/cpu-feature-registers.rst

@@ -176,6 +176,8 @@ infrastructure:
      +------------------------------+---------+---------+
      | SSBS                         | [7-4]   |    y    |
      +------------------------------+---------+---------+
+     | BT                           | [3-0]   |    y    |
+     +------------------------------+---------+---------+
 
 
   4) MIDR_EL1 - Main ID Register

Documentation/arm64/elf_hwcaps.rst

@@ -236,6 +236,11 @@ HWCAP2_RNG
 
     Functionality implied by ID_AA64ISAR0_EL1.RNDR == 0b0001.
 
+HWCAP2_BTI
+
+    Functionality implied by ID_AA64PFR0_EL1.BT == 0b0001.
+
+
 4. Unused AT_HWCAP bits
 -----------------------
 

Documentation/filesystems/proc.rst

@@ -543,6 +543,7 @@ encoded manner. The codes are the following:
     hg    huge page advise flag
     nh    no huge page advise flag
     mg    mergable advise flag
+    bt  - arm64 BTI guarded page
     ==    =======================================
 
 Note that there is no guarantee that every flag and associated mnemonic will

arch/arm64/Kconfig

@@ -9,6 +9,7 @@ config ARM64
 	select ACPI_MCFG if (ACPI && PCI)
 	select ACPI_SPCR_TABLE if ACPI
 	select ACPI_PPTT if ACPI
+	select ARCH_BINFMT_ELF_STATE
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_DMA_PREP_COHERENT
@@ -32,6 +33,7 @@ config ARM64
 	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_ELF_PROT
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
 	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
@@ -61,6 +63,7 @@ config ARM64
 	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
+	select ARCH_USE_GNU_PROPERTY
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
@@ -1584,6 +1587,28 @@ endmenu
 
 menu "ARMv8.5 architectural features"
 
+config ARM64_BTI
+	bool "Branch Target Identification support"
+	default y
+	help
+	  Branch Target Identification (part of the ARMv8.5 Extensions)
+	  provides a mechanism to limit the set of locations to which computed
+	  branch instructions such as BR or BLR can jump.
+
+	  To make use of BTI on CPUs that support it, say Y.
+
+	  BTI is intended to provide complementary protection to other control
+	  flow integrity protection mechanisms, such as the Pointer
+	  authentication mechanism provided as part of the ARMv8.3 Extensions.
+	  For this reason, it does not make sense to enable this option without
+	  also enabling support for pointer authentication.  Thus, when
+	  enabling this option you should also select ARM64_PTR_AUTH=y.
+
+	  Userspace binaries must also be specifically compiled to make use of
+	  this mechanism.  If you say N here or the hardware does not support
+	  BTI, such binaries can still run, but you get no additional
+	  enforcement of branch destinations.
+
 config ARM64_E0PD
 	bool "Enable support for E0PD"
 	default y

arch/arm64/include/asm/cpucaps.h

@@ -61,7 +61,8 @@
 #define ARM64_HAS_AMU_EXTN			51
 #define ARM64_HAS_ADDRESS_AUTH			52
 #define ARM64_HAS_GENERIC_AUTH			53
+#define ARM64_BTI				54
 
-#define ARM64_NCAPS				54
+#define ARM64_NCAPS				55
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -680,6 +680,11 @@ static inline bool system_has_prio_mask_debugging(void)
 	       system_uses_irq_prio_masking();
 }
 
+static inline bool system_supports_bti(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1

arch/arm64/include/asm/elf.h

@@ -114,7 +114,11 @@
 
 #ifndef __ASSEMBLY__
 
+#include <uapi/linux/elf.h>
 #include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/types.h>
 #include <asm/processor.h> /* for signal_minsigstksz, used by ARCH_DLINFO */
 
 typedef unsigned long elf_greg_t;
@@ -224,6 +228,52 @@ extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
 
 #endif /* CONFIG_COMPAT */
 
+struct arch_elf_state {
+	int flags;
+};
+
+#define ARM64_ELF_BTI		(1 << 0)
+
+#define INIT_ARCH_ELF_STATE {			\
+	.flags = 0,				\
+}
+
+static inline int arch_parse_elf_property(u32 type, const void *data,
+					  size_t datasz, bool compat,
+					  struct arch_elf_state *arch)
+{
+	/* No known properties for AArch32 yet */
+	if (IS_ENABLED(CONFIG_COMPAT) && compat)
+		return 0;
+
+	if (type == GNU_PROPERTY_AARCH64_FEATURE_1_AND) {
+		const u32 *p = data;
+
+		if (datasz != sizeof(*p))
+			return -ENOEXEC;
+
+		if (system_supports_bti() &&
+		    (*p & GNU_PROPERTY_AARCH64_FEATURE_1_BTI))
+			arch->flags |= ARM64_ELF_BTI;
+	}
+
+	return 0;
+}
+
+static inline int arch_elf_pt_proc(void *ehdr, void *phdr,
+				   struct file *f, bool is_interp,
+				   struct arch_elf_state *state)
+{
+	return 0;
+}
+
+static inline int arch_check_elf(void *ehdr, bool has_interp,
+				 void *interp_ehdr,
+				 struct arch_elf_state *state)
+{
+	return 0;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif

arch/arm64/include/asm/esr.h

@@ -22,7 +22,7 @@
 #define ESR_ELx_EC_PAC		(0x09)	/* EL2 and above */
 /* Unallocated EC: 0x0A - 0x0B */
 #define ESR_ELx_EC_CP14_64	(0x0C)
-/* Unallocated EC: 0x0d */
+#define ESR_ELx_EC_BTI		(0x0D)
 #define ESR_ELx_EC_ILL		(0x0E)
 /* Unallocated EC: 0x0F - 0x10 */
 #define ESR_ELx_EC_SVC32	(0x11)

arch/arm64/include/asm/exception.h

@@ -34,6 +34,7 @@ static inline u32 disr_to_esr(u64 disr)
 asmlinkage void enter_from_user_mode(void);
 void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 void do_undefinstr(struct pt_regs *regs);
+void do_bti(struct pt_regs *regs);
 asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr);
 void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
 			struct pt_regs *regs);

arch/arm64/include/asm/hwcap.h

@@ -94,6 +94,7 @@
 #define KERNEL_HWCAP_BF16		__khwcap2_feature(BF16)
 #define KERNEL_HWCAP_DGH		__khwcap2_feature(DGH)
 #define KERNEL_HWCAP_RNG		__khwcap2_feature(RNG)
+#define KERNEL_HWCAP_BTI		__khwcap2_feature(BTI)
 
 /*
  * This yields a mask that user programs can use to figure out what

arch/arm64/include/asm/kvm_emulate.h

@@ -507,10 +507,12 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 
 static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
-	if (vcpu_mode_is_32bit(vcpu))
+	if (vcpu_mode_is_32bit(vcpu)) {
 		kvm_skip_instr32(vcpu, is_wide_instr);
-	else
+	} else {
 		*vcpu_pc(vcpu) += 4;
+		*vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK;
+	}
 
 	/* advance the singlestep state machine */
 	*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;

arch/arm64/include/asm/mman.h

@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMAN_H__
+#define __ASM_MMAN_H__
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <uapi/asm/mman.h>
+
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+	unsigned long pkey __always_unused)
+{
+	if (system_supports_bti() && (prot & PROT_BTI))
+		return VM_ARM64_BTI;
+
+	return 0;
+}
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
+{
+	return (vm_flags & VM_ARM64_BTI) ? __pgprot(PTE_GP) : __pgprot(0);
+}
+#define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
+
+static inline bool arch_validate_prot(unsigned long prot,
+	unsigned long addr __always_unused)
+{
+	unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
+
+	if (system_supports_bti())
+		supported |= PROT_BTI;
+
+	return (prot & ~supported) == 0;
+}
+#define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr)
+
+#endif /* ! __ASM_MMAN_H__ */

arch/arm64/include/asm/pgtable-hwdef.h

@@ -151,6 +151,7 @@
 #define PTE_SHARED		(_AT(pteval_t, 3) << 8)		/* SH[1:0], inner shareable */
 #define PTE_AF			(_AT(pteval_t, 1) << 10)	/* Access Flag */
 #define PTE_NG			(_AT(pteval_t, 1) << 11)	/* nG */
+#define PTE_GP			(_AT(pteval_t, 1) << 50)	/* BTI guarded */
 #define PTE_DBM			(_AT(pteval_t, 1) << 51)	/* Dirty Bit Management */
 #define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */

arch/arm64/include/asm/pgtable.h

@@ -660,7 +660,7 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY |
-			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE;
+			      PTE_PROT_NONE | PTE_VALID | PTE_WRITE | PTE_GP;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
 		pte = pte_mkdirty(pte);

arch/arm64/include/asm/ptrace.h

@@ -35,6 +35,7 @@
 #define GIC_PRIO_PSR_I_SET		(1 << 4)
 
 /* Additional SPSR bits not exposed in the UABI */
+
 #define PSR_IL_BIT		(1 << 20)
 
 /* AArch32-specific ptrace requests */

arch/arm64/include/asm/sysreg.h

@@ -552,6 +552,8 @@
 #endif
 
 /* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_BT1		(BIT(36))
+#define SCTLR_EL1_BT0		(BIT(35))
 #define SCTLR_EL1_UCI		(BIT(26))
 #define SCTLR_EL1_E0E		(BIT(24))
 #define SCTLR_EL1_SPAN		(BIT(23))
@@ -660,10 +662,12 @@
 
 /* id_aa64pfr1 */
 #define ID_AA64PFR1_SSBS_SHIFT		4
+#define ID_AA64PFR1_BT_SHIFT		0
 
 #define ID_AA64PFR1_SSBS_PSTATE_NI	0
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
+#define ID_AA64PFR1_BT_BTI		0x1
 
 /* id_aa64zfr0 */
 #define ID_AA64ZFR0_F64MM_SHIFT		56

arch/arm64/include/uapi/asm/hwcap.h

@@ -73,5 +73,6 @@
 #define HWCAP2_BF16		(1 << 14)
 #define HWCAP2_DGH		(1 << 15)
 #define HWCAP2_RNG		(1 << 16)
+#define HWCAP2_BTI		(1 << 17)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/include/uapi/asm/mman.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI__ASM_MMAN_H
+#define _UAPI__ASM_MMAN_H
+
+#include <asm-generic/mman.h>
+
+#define PROT_BTI	0x10		/* BTI guarded page */
+
+#endif /* ! _UAPI__ASM_MMAN_H */

arch/arm64/include/uapi/asm/ptrace.h

@@ -46,6 +46,7 @@
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
 #define PSR_D_BIT	0x00000200
+#define PSR_BTYPE_MASK	0x00000c00
 #define PSR_SSBS_BIT	0x00001000
 #define PSR_PAN_BIT	0x00400000
 #define PSR_UAO_BIT	0x00800000
@@ -55,6 +56,8 @@
 #define PSR_Z_BIT	0x40000000
 #define PSR_N_BIT	0x80000000
 
+#define PSR_BTYPE_SHIFT		10
+
 /*
  * Groups of PSR bits
  */
@@ -63,6 +66,12 @@
 #define PSR_x		0x0000ff00	/* Extension		*/
 #define PSR_c		0x000000ff	/* Control		*/
 
+/* Convenience names for the values of PSTATE.BTYPE */
+#define PSR_BTYPE_NONE		(0b00 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_JC		(0b01 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_C		(0b10 << PSR_BTYPE_SHIFT)
+#define PSR_BTYPE_J		(0b11 << PSR_BTYPE_SHIFT)
+
 /* syscall emulation path in ptrace */
 #define PTRACE_SYSEMU		  31
 #define PTRACE_SYSEMU_SINGLESTEP  32