diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-02-08 10:44:25 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-02-08 10:44:25 -0800 |
commit | c0136321924dd338bb8fc5661c4b0e27441a8d04 (patch) | |
tree | 099cc60dfe6793309b21474a00e4d10087a7cae8 /arch/arm64 | |
parent | 846ade7dd2e630a309a8c57302046e8c4037b8df (diff) | |
parent | 3a0a397ff5ff8b56ca9f7908b75dee6bf0b5fabb (diff) | |
download | op-kernel-dev-c0136321924dd338bb8fc5661c4b0e27441a8d04.zip op-kernel-dev-c0136321924dd338bb8fc5661c4b0e27441a8d04.tar.gz |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull more arm64 updates from Catalin Marinas:
"As I mentioned in the last pull request, there's a second batch of
security updates for arm64 with mitigations for Spectre/v1 and an
improved one for Spectre/v2 (via a newly defined firmware interface
API).
Spectre v1 mitigation:
- back-end version of array_index_mask_nospec()
- masking of the syscall number to restrict speculation through the
syscall table
- masking of __user pointers prior to deference in uaccess routines
Spectre v2 mitigation update:
- using the new firmware SMC calling convention specification update
- removing the current PSCI GET_VERSION firmware call mitigation as
vendors are deploying new SMCCC-capable firmware
- additional branch predictor hardening for synchronous exceptions
and interrupts while in user mode
Meltdown v3 mitigation update:
- Cavium Thunder X is unaffected but a hardware erratum gets in the
way. The kernel now starts with the page tables mapped as global
and switches to non-global if kpti needs to be enabled.
Other:
- Theoretical trylock bug fixed"
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (38 commits)
arm64: Kill PSCI_GET_VERSION as a variant-2 workaround
arm64: Add ARM_SMCCC_ARCH_WORKAROUND_1 BP hardening support
arm/arm64: smccc: Implement SMCCC v1.1 inline primitive
arm/arm64: smccc: Make function identifiers an unsigned quantity
firmware/psci: Expose SMCCC version through psci_ops
firmware/psci: Expose PSCI conduit
arm64: KVM: Add SMCCC_ARCH_WORKAROUND_1 fast handling
arm64: KVM: Report SMCCC_ARCH_WORKAROUND_1 BP hardening support
arm/arm64: KVM: Turn kvm_psci_version into a static inline
arm/arm64: KVM: Advertise SMCCC v1.1
arm/arm64: KVM: Implement PSCI 1.0 support
arm/arm64: KVM: Add smccc accessors to PSCI code
arm/arm64: KVM: Add PSCI_VERSION helper
arm/arm64: KVM: Consolidate the PSCI include files
arm64: KVM: Increment PC after handling an SMC trap
arm: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls
arm64: KVM: Fix SMCCC handling of unimplemented SMC/HVC calls
arm64: entry: Apply BP hardening for suspicious interrupts from EL0
arm64: entry: Apply BP hardening for high-priority synchronous exceptions
arm64: futex: Mask __user pointers prior to dereference
...
Diffstat (limited to 'arch/arm64')
28 files changed, 612 insertions, 229 deletions
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3873dd7..1241fb2 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -116,6 +116,24 @@ .endm /* + * Value prediction barrier + */ + .macro csdb + hint #20 + .endm + +/* + * Sanitise a 64-bit bounded index wrt speculation, returning zero if out + * of bounds. + */ + .macro mask_nospec64, idx, limit, tmp + sub \tmp, \idx, \limit + bic \tmp, \tmp, \idx + and \idx, \idx, \tmp, asr #63 + csdb + .endm + +/* * NOP sequence */ .macro nops, num @@ -514,7 +532,7 @@ alternative_endif * phys: physical address, preserved * ttbr: returns the TTBR value */ - .macro phys_to_ttbr, phys, ttbr + .macro phys_to_ttbr, ttbr, phys #ifdef CONFIG_ARM64_PA_BITS_52 orr \ttbr, \phys, \phys, lsr #46 and \ttbr, \ttbr, #TTBR_BADDR_MASK_52 @@ -523,6 +541,29 @@ alternative_endif #endif .endm + .macro phys_to_pte, pte, phys +#ifdef CONFIG_ARM64_PA_BITS_52 + /* + * We assume \phys is 64K aligned and this is guaranteed by only + * supporting this configuration with 64K pages. + */ + orr \pte, \phys, \phys, lsr #36 + and \pte, \pte, #PTE_ADDR_MASK +#else + mov \pte, \phys +#endif + .endm + + .macro pte_to_phys, phys, pte +#ifdef CONFIG_ARM64_PA_BITS_52 + ubfiz \phys, \pte, #(48 - 16 - 12), #16 + bfxil \phys, \pte, #16, #32 + lsl \phys, \phys, #16 +#else + and \phys, \pte, #PTE_ADDR_MASK +#endif + .endm + /** * Errata workaround prior to disable MMU. Insert an ISB immediately prior * to executing the MSR that will change SCTLR_ELn[M] from a value of 1 to 0. diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 77651c4..f11518a 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -32,6 +32,7 @@ #define dsb(opt) asm volatile("dsb " #opt : : : "memory") #define psb_csync() asm volatile("hint #17" : : : "memory") +#define csdb() asm volatile("hint #20" : : : "memory") #define mb() dsb(sy) #define rmb() dsb(ld) @@ -40,6 +41,27 @@ #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) +/* + * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz + * and 0 otherwise. + */ +#define array_index_mask_nospec array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long idx, + unsigned long sz) +{ + unsigned long mask; + + asm volatile( + " cmp %1, %2\n" + " sbc %0, xzr, xzr\n" + : "=r" (mask) + : "r" (idx), "Ir" (sz) + : "cc"); + + csdb(); + return mask; +} + #define __smp_mb() dmb(ish) #define __smp_rmb() dmb(ishld) #define __smp_wmb() dmb(ishst) diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 5bb2fd4..07fe247 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -48,9 +48,10 @@ do { \ } while (0) static inline int -arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr) { int oldval = 0, ret, tmp; + u32 __user *uaddr = __uaccess_mask_ptr(_uaddr); pagefault_disable(); @@ -88,15 +89,17 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) } static inline int -futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, u32 oldval, u32 newval) { int ret = 0; u32 val, tmp; + u32 __user *uaddr; - if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) + if (!access_ok(VERIFY_WRITE, _uaddr, sizeof(u32))) return -EFAULT; + uaddr = __uaccess_mask_ptr(_uaddr); uaccess_enable(); asm volatile("// futex_atomic_cmpxchg_inatomic\n" " prfm pstl1strm, %2\n" diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 82386e8..a780f67 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -123,16 +123,8 @@ /* * Initial memory map attributes. */ -#define _SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) -#define _SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) - -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define SWAPPER_PTE_FLAGS (_SWAPPER_PTE_FLAGS | PTE_NG) -#define SWAPPER_PMD_FLAGS (_SWAPPER_PMD_FLAGS | PMD_SECT_NG) -#else -#define SWAPPER_PTE_FLAGS _SWAPPER_PTE_FLAGS -#define SWAPPER_PMD_FLAGS _SWAPPER_PMD_FLAGS -#endif +#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) +#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) #if ARM64_SWAPPER_USES_SECTION_MAPS #define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 4485ae8..a73f63a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -415,4 +415,10 @@ static inline void kvm_arm_vhe_guest_exit(void) { local_daif_restore(DAIF_PROCCTX_NOIRQ); } + +static inline bool kvm_arm_harden_branch_predictor(void) +{ + return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); +} + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_psci.h b/arch/arm64/include/asm/kvm_psci.h deleted file mode 100644 index bc39e55..0000000 --- a/arch/arm64/include/asm/kvm_psci.h +++ /dev/null @@ -1,27 +0,0 @@ -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program 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 this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#ifndef __ARM64_KVM_PSCI_H__ -#define __ARM64_KVM_PSCI_H__ - -#define KVM_ARM_PSCI_0_1 1 -#define KVM_ARM_PSCI_0_2 2 - -int kvm_psci_version(struct kvm_vcpu *vcpu); -int kvm_psci_call(struct kvm_vcpu *vcpu); - -#endif /* __ARM64_KVM_PSCI_H__ */ diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 22a9268..2db84df 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -37,13 +37,11 @@ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define PROT_DEFAULT (_PROT_DEFAULT | PTE_NG) -#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_SECT_NG) -#else -#define PROT_DEFAULT _PROT_DEFAULT -#define PROT_SECT_DEFAULT _PROT_SECT_DEFAULT -#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ +#define PTE_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PTE_NG : 0) +#define PMD_MAYBE_NG (arm64_kernel_unmapped_at_el0() ? PMD_SECT_NG : 0) + +#define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) +#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) @@ -55,22 +53,22 @@ #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) #define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) -#define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) -#define _HYP_PAGE_DEFAULT (_PAGE_DEFAULT & ~PTE_NG) +#define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) +#define _HYP_PAGE_DEFAULT _PAGE_DEFAULT -#define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) -#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) -#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) +#define PAGE_KERNEL __pgprot(PROT_NORMAL) +#define PAGE_KERNEL_RO __pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY) +#define PAGE_KERNEL_EXEC __pgprot(PROT_NORMAL & ~PTE_PXN) +#define PAGE_KERNEL_EXEC_CONT __pgprot((PROT_NORMAL & ~PTE_PXN) | PTE_CONT) #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) #define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) -#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) -#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) +#define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) +#define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 6db43eb..fce604e 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -21,6 +21,9 @@ #define TASK_SIZE_64 (UL(1) << VA_BITS) +#define KERNEL_DS UL(-1) +#define USER_DS (TASK_SIZE_64 - 1) + #ifndef __ASSEMBLY__ /* diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index fdb827c..ebdae15 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -87,8 +87,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) " cbnz %w1, 1f\n" " add %w1, %w0, %3\n" " casa %w0, %w1, %2\n" - " and %w1, %w1, #0xffff\n" - " eor %w1, %w1, %w0, lsr #16\n" + " sub %w1, %w1, %3\n" + " eor %w1, %w1, %w0\n" "1:") : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) : "I" (1 << TICKET_SHIFT) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 59fda52..543e11f 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -35,16 +35,20 @@ #include <asm/compiler.h> #include <asm/extable.h> -#define KERNEL_DS (-1UL) #define get_ds() (KERNEL_DS) - -#define USER_DS TASK_SIZE_64 #define get_fs() (current_thread_info()->addr_limit) static inline void set_fs(mm_segment_t fs) { current_thread_info()->addr_limit = fs; + /* + * Prevent a mispredicted conditional call to set_fs from forwarding + * the wrong address limit to access_ok under speculation. + */ + dsb(nsh); + isb(); + /* On user-mode return, check fs is correct */ set_thread_flag(TIF_FSCHECK); @@ -66,22 +70,32 @@ static inline void set_fs(mm_segment_t fs) * Returns 1 if the range is valid, 0 otherwise. * * This is equivalent to the following test: - * (u65)addr + (u65)size <= current->addr_limit - * - * This needs 65-bit arithmetic. + * (u65)addr + (u65)size <= (u65)current->addr_limit + 1 */ -#define __range_ok(addr, size) \ -({ \ - unsigned long __addr = (unsigned long)(addr); \ - unsigned long flag, roksum; \ - __chk_user_ptr(addr); \ - asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls" \ - : "=&r" (flag), "=&r" (roksum) \ - : "1" (__addr), "Ir" (size), \ - "r" (current_thread_info()->addr_limit) \ - : "cc"); \ - flag; \ -}) +static inline unsigned long __range_ok(unsigned long addr, unsigned long size) +{ + unsigned long limit = current_thread_info()->addr_limit; + + __chk_user_ptr(addr); + asm volatile( + // A + B <= C + 1 for all A,B,C, in four easy steps: + // 1: X = A + B; X' = X % 2^64 + " adds %0, %0, %2\n" + // 2: Set C = 0 if X > 2^64, to guarantee X' > C in step 4 + " csel %1, xzr, %1, hi\n" + // 3: Set X' = ~0 if X >= 2^64. For X == 2^64, this decrements X' + // to compensate for the carry flag being set in step 4. For + // X > 2^64, X' merely has to remain nonzero, which it does. + " csinv %0, %0, xzr, cc\n" + // 4: For X < 2^64, this gives us X' - C - 1 <= 0, where the -1 + // comes from the carry in being clear. Otherwise, we are + // testing X' - C == 0, subject to the previous adjustments. + " sbcs xzr, %0, %1\n" + " cset %0, ls\n" + : "+r" (addr), "+r" (limit) : "Ir" (size) : "cc"); + + return addr; +} /* * When dealing with data aborts, watchpoints, or instruction traps we may end @@ -90,7 +104,7 @@ static inline void set_fs(mm_segment_t fs) */ #define untagged_addr(addr) sign_extend64(addr, 55) -#define access_ok(type, addr, size) __range_ok(addr, size) +#define access_ok(type, addr, size) __range_ok((unsigned long)(addr), size) #define user_addr_max get_fs #define _ASM_EXTABLE(from, to) \ @@ -221,6 +235,26 @@ static inline void uaccess_enable_not_uao(void) } /* + * Sanitise a uaccess pointer such that it becomes NULL if above the + * current addr_limit. + */ +#define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) +static inline void __user *__uaccess_mask_ptr(const void __user *ptr) +{ + void __user *safe_ptr; + + asm volatile( + " bics xzr, %1, %2\n" + " csel %0, %1, xzr, eq\n" + : "=&r" (safe_ptr) + : "r" (ptr), "r" (current_thread_info()->addr_limit) + : "cc"); + + csdb(); + return safe_ptr; +} + +/* * The "__xxx" versions of the user access functions do not verify the address * space - it must have been done previously with a separate "access_ok()" * call. @@ -272,28 +306,33 @@ do { \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user(x, ptr) \ +#define __get_user_check(x, ptr, err) \ ({ \ - int __gu_err = 0; \ - __get_user_err((x), (ptr), __gu_err); \ - __gu_err; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \ + __p = uaccess_mask_ptr(__p); \ + __get_user_err((x), __p, (err)); \ + } else { \ + (x) = 0; (err) = -EFAULT; \ + } \ }) #define __get_user_error(x, ptr, err) \ ({ \ - __get_user_err((x), (ptr), (err)); \ + __get_user_check((x), (ptr), (err)); \ (void)0; \ }) -#define get_user(x, ptr) \ +#define __get_user(x, ptr) \ ({ \ - __typeof__(*(ptr)) __user *__p = (ptr); \ - might_fault(); \ - access_ok(VERIFY_READ, __p, sizeof(*__p)) ? \ - __get_user((x), __p) : \ - ((x) = 0, -EFAULT); \ + int __gu_err = 0; \ + __get_user_check((x), (ptr), __gu_err); \ + __gu_err; \ }) +#define get_user __get_user + #define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature) \ asm volatile( \ "1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \ @@ -336,43 +375,63 @@ do { \ uaccess_disable_not_uao(); \ } while (0) -#define __put_user(x, ptr) \ +#define __put_user_check(x, ptr, err) \ ({ \ - int __pu_err = 0; \ - __put_user_err((x), (ptr), __pu_err); \ - __pu_err; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \ + __p = uaccess_mask_ptr(__p); \ + __put_user_err((x), __p, (err)); \ + } else { \ + (err) = -EFAULT; \ + } \ }) #define __put_user_error(x, ptr, err) \ ({ \ - __put_user_err((x), (ptr), (err)); \ + __put_user_check((x), (ptr), (err)); \ (void)0; \ }) -#define put_user(x, ptr) \ +#define __put_user(x, ptr) \ ({ \ - __typeof__(*(ptr)) __user *__p = (ptr); \ - might_fault(); \ - access_ok(VERIFY_WRITE, __p, sizeof(*__p)) ? \ - __put_user((x), __p) : \ - -EFAULT; \ + int __pu_err = 0; \ + __put_user_check((x), (ptr), __pu_err); \ + __pu_err; \ }) +#define put_user __put_user + extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); -#define raw_copy_from_user __arch_copy_from_user +#define raw_copy_from_user(to, from, n) \ +({ \ + __arch_copy_from_user((to), __uaccess_mask_ptr(from), (n)); \ +}) + extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); -#define raw_copy_to_user __arch_copy_to_user -extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n); -extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n); +#define raw_copy_to_user(to, from, n) \ +({ \ + __arch_copy_to_user(__uaccess_mask_ptr(to), (from), (n)); \ +}) + +extern unsigned long __must_check __arch_copy_in_user(void __user *to, const void __user *from, unsigned long n); +#define raw_copy_in_user(to, from, n) \ +({ \ + __arch_copy_in_user(__uaccess_mask_ptr(to), \ + __uaccess_mask_ptr(from), (n)); \ +}) + #define INLINE_COPY_TO_USER #define INLINE_COPY_FROM_USER -static inline unsigned long __must_check clear_user(void __user *to, unsigned long n) +extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned long n); +static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { if (access_ok(VERIFY_WRITE, to, n)) - n = __clear_user(to, n); + n = __arch_clear_user(__uaccess_mask_ptr(to), n); return n; } +#define clear_user __clear_user extern long strncpy_from_user(char *dest, const char __user *src, long count); @@ -386,7 +445,7 @@ extern unsigned long __must_check __copy_user_flushcache(void *to, const void __ static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) { kasan_check_write(dst, size); - return __copy_user_flushcache(dst, src, size); + return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size); } #endif diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 67368c7..66be504 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -37,8 +37,8 @@ EXPORT_SYMBOL(clear_page); /* user mem (segment) */ EXPORT_SYMBOL(__arch_copy_from_user); EXPORT_SYMBOL(__arch_copy_to_user); -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(raw_copy_in_user); +EXPORT_SYMBOL(__arch_clear_user); +EXPORT_SYMBOL(__arch_copy_in_user); /* physical memory */ EXPORT_SYMBOL(memstart_addr); diff --git a/arch/arm64/kernel/bpi.S b/arch/arm64/kernel/bpi.S index 76225c2..e5de335 100644 --- a/arch/arm64/kernel/bpi.S +++ b/arch/arm64/kernel/bpi.S @@ -17,6 +17,7 @@ */ #include <linux/linkage.h> +#include <linux/arm-smccc.h> .macro ventry target .rept 31 @@ -53,30 +54,6 @@ ENTRY(__bp_harden_hyp_vecs_start) vectors __kvm_hyp_vector .endr ENTRY(__bp_harden_hyp_vecs_end) -ENTRY(__psci_hyp_bp_inval_start) - sub sp, sp, #(8 * 18) - stp x16, x17, [sp, #(16 * 0)] - stp x14, x15, [sp, #(16 * 1)] - stp x12, x13, [sp, #(16 * 2)] - stp x10, x11, [sp, #(16 * 3)] - stp x8, x9, [sp, #(16 * 4)] - stp x6, x7, [sp, #(16 * 5)] - stp x4, x5, [sp, #(16 * 6)] - stp x2, x3, [sp, #(16 * 7)] - stp x0, x1, [sp, #(16 * 8)] - mov x0, #0x84000000 - smc #0 - ldp x16, x17, [sp, #(16 * 0)] - ldp x14, x15, [sp, #(16 * 1)] - ldp x12, x13, [sp, #(16 * 2)] - ldp x10, x11, [sp, #(16 * 3)] - ldp x8, x9, [sp, #(16 * 4)] - ldp x6, x7, [sp, #(16 * 5)] - ldp x4, x5, [sp, #(16 * 6)] - ldp x2, x3, [sp, #(16 * 7)] - ldp x0, x1, [sp, #(16 * 8)] - add sp, sp, #(8 * 18) -ENTRY(__psci_hyp_bp_inval_end) ENTRY(__qcom_hyp_sanitize_link_stack_start) stp x29, x30, [sp, #-16]! @@ -85,3 +62,22 @@ ENTRY(__qcom_hyp_sanitize_link_stack_start) .endr ldp x29, x30, [sp], #16 ENTRY(__qcom_hyp_sanitize_link_stack_end) + +.macro smccc_workaround_1 inst + sub sp, sp, #(8 * 4) + stp x2, x3, [sp, #(8 * 0)] + stp x0, x1, [sp, #(8 * 2)] + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + \inst #0 + ldp x2, x3, [sp, #(8 * 0)] + ldp x0, x1, [sp, #(8 * 2)] + add sp, sp, #(8 * 4) +.endm + +ENTRY(__smccc_workaround_1_smc_start) + smccc_workaround_1 smc +ENTRY(__smccc_workaround_1_smc_end) + +ENTRY(__smccc_workaround_1_hvc_start) + smccc_workaround_1 hvc +ENTRY(__smccc_workaround_1_hvc_end) diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 2a752cb..8021b46 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -16,7 +16,7 @@ #include <asm/virt.h> .text -.pushsection .idmap.text, "ax" +.pushsection .idmap.text, "awx" /* * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ed68818..0782359 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -67,9 +67,12 @@ static int cpu_enable_trap_ctr_access(void *__unused) DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); #ifdef CONFIG_KVM -extern char __psci_hyp_bp_inval_start[], __psci_hyp_bp_inval_end[]; extern char __qcom_hyp_sanitize_link_stack_start[]; extern char __qcom_hyp_sanitize_link_stack_end[]; +extern char __smccc_workaround_1_smc_start[]; +extern char __smccc_workaround_1_smc_end[]; +extern char __smccc_workaround_1_hvc_start[]; +extern char __smccc_workaround_1_hvc_end[]; static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, const char *hyp_vecs_end) @@ -112,10 +115,12 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, spin_unlock(&bp_lock); } #else -#define __psci_hyp_bp_inval_start NULL -#define __psci_hyp_bp_inval_end NULL #define __qcom_hyp_sanitize_link_stack_start NULL #define __qcom_hyp_sanitize_link_stack_end NULL +#define __smccc_workaround_1_smc_start NULL +#define __smccc_workaround_1_smc_end NULL +#define __smccc_workaround_1_hvc_start NULL +#define __smccc_workaround_1_hvc_end NULL static void __install_bp_hardening_cb(bp_hardening_cb_t fn, const char *hyp_vecs_start, @@ -142,17 +147,59 @@ static void install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry, __install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end); } +#include <uapi/linux/psci.h> +#include <linux/arm-smccc.h> #include <linux/psci.h> -static int enable_psci_bp_hardening(void *data) +static void call_smc_arch_workaround_1(void) +{ + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); +} + +static void call_hvc_arch_workaround_1(void) +{ + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); +} + +static int enable_smccc_arch_workaround_1(void *data) { const struct arm64_cpu_capabilities *entry = data; + bp_hardening_cb_t cb; + void *smccc_start, *smccc_end; + struct arm_smccc_res res; + + if (!entry->matches(entry, SCOPE_LOCAL_CPU)) + return 0; + + if (psci_ops.smccc_version == SMCCC_VERSION_1_0) + return 0; + + switch (psci_ops.conduit) { + case PSCI_CONDUIT_HVC: + arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + if (res.a0) + return 0; + cb = call_hvc_arch_workaround_1; + smccc_start = __smccc_workaround_1_hvc_start; + smccc_end = __smccc_workaround_1_hvc_end; + break; + + case PSCI_CONDUIT_SMC: + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + if (res.a0) + return 0; + cb = call_smc_arch_workaround_1; + smccc_start = __smccc_workaround_1_smc_start; + smccc_end = __smccc_workaround_1_smc_end; + break; + + default: + return 0; + } - if (psci_ops.get_version) - install_bp_hardening_cb(entry, - (bp_hardening_cb_t)psci_ops.get_version, - __psci_hyp_bp_inval_start, - __psci_hyp_bp_inval_end); + install_bp_hardening_cb(entry, cb, smccc_start, smccc_end); return 0; } @@ -333,22 +380,22 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CORTEX_A75), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, @@ -362,12 +409,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, { .capability = ARM64_HARDEN_BRANCH_PREDICTOR, MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), - .enable = enable_psci_bp_hardening, + .enable = enable_smccc_arch_workaround_1, }, #endif { diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0fb6a31..29b1f87 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -856,12 +856,23 @@ static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, int __unused) { + char const *str = "command line option"; u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); - /* Forced on command line? */ + /* + * For reasons that aren't entirely clear, enabling KPTI on Cavium + * ThunderX leads to apparent I-cache corruption of kernel text, which + * ends as well as you might imagine. Don't even try. + */ + if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_27456)) { + str = "ARM64_WORKAROUND_CAVIUM_27456"; + __kpti_forced = -1; + } + + /* Forced? */ if (__kpti_forced) { - pr_info_once("kernel page table isolation forced %s by command line option\n", - __kpti_forced > 0 ? "ON" : "OFF"); + pr_info_once("kernel page table isolation forced %s by %s\n", + __kpti_forced > 0 ? "ON" : "OFF", str); return __kpti_forced > 0; } @@ -881,6 +892,30 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, ID_AA64PFR0_CSV3_SHIFT); } +static int kpti_install_ng_mappings(void *__unused) +{ + typedef void (kpti_remap_fn)(int, int, phys_addr_t); + extern kpti_remap_fn idmap_kpti_install_ng_mappings; + kpti_remap_fn *remap_fn; + + static bool kpti_applied = false; + int cpu = smp_processor_id(); + + if (kpti_applied) + return 0; + + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); + + cpu_install_idmap(); + remap_fn(cpu, num_online_cpus(), __pa_symbol(swapper_pg_dir)); + cpu_uninstall_idmap(); + + if (!cpu) + kpti_applied = true; + + return 0; +} + static int __init parse_kpti(char *str) { bool enabled; @@ -1004,6 +1039,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_UNMAP_KERNEL_AT_EL0, .def_scope = SCOPE_SYSTEM, .matches = unmap_kernel_at_el0, + .enable = kpti_install_ng_mappings, }, #endif { diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index cccd278..ec2ee72 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -167,10 +167,10 @@ alternative_else_nop_endif .else add x21, sp, #S_FRAME_SIZE get_thread_info tsk - /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + /* Save the task's original addr_limit and set USER_DS */ ldr x20, [tsk, #TSK_TI_ADDR_LIMIT] str x20, [sp, #S_ORIG_ADDR_LIMIT] - mov x20, #TASK_SIZE_64 + mov x20, #USER_DS str x20, [tsk, #TSK_TI_ADDR_LIMIT] /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */ .endif /* \el == 0 */ @@ -382,6 +382,7 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 * x7 is reserved for the system call number in 32-bit mode. */ wsc_nr .req w25 // number of system calls +xsc_nr .req x25 // number of system calls (zero-extended) wscno .req w26 // syscall number xscno .req x26 // syscall number (zero-extended) stbl .req x27 // syscall table pointer @@ -770,7 +771,10 @@ el0_sp_pc: * Stack or PC alignment exception handling */ mrs x26, far_el1 - enable_daif + enable_da_f +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif ct_user_exit mov x0, x26 mov x1, x25 @@ -828,6 +832,11 @@ el0_irq_naked: #endif ct_user_exit +#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR + tbz x22, #55, 1f + bl do_el0_irq_bp_hardening +1: +#endif irq_handler #ifdef CONFIG_TRACE_IRQFLAGS @@ -939,6 +948,7 @@ el0_svc_naked: // compat entry point b.ne __sys_trace cmp wscno, wsc_nr // check upper syscall limit b.hs ni_sys + mask_nospec64 xscno, xsc_nr, x19 // enforce bounds for syscall number ldr x16, [stbl, xscno, lsl #3] // address in the syscall table blr x16 // call sys_* routine b ret_fast_syscall @@ -1017,16 +1027,9 @@ alternative_else_nop_endif orr \tmp, \tmp, #USER_ASID_FLAG msr ttbr1_el1, \tmp /* - * We avoid running the post_ttbr_update_workaround here because the - * user and kernel ASIDs don't have conflicting mappings, so any - * "blessing" as described in: - * - * http://lkml.kernel.org/r/56BB848A.6060603@caviumnetworks.com - * - * will not hurt correctness. Whilst this may partially defeat the - * point of using split ASIDs in the first place, it avoids - * the hit of invalidating the entire I-cache on every return to - * userspace. + * We avoid running the post_ttbr_update_workaround here because + * it's only needed by Cavium ThunderX, which requires KPTI to be + * disabled. */ .endm diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ba3ab047..2b6b8b2 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -148,26 +148,6 @@ preserve_boot_args: ENDPROC(preserve_boot_args) /* - * Macro to arrange a physical address in a page table entry, taking care of - * 52-bit addresses. - * - * Preserves: phys - * Returns: pte - */ - .macro phys_to_pte, phys, pte -#ifdef CONFIG_ARM64_PA_BITS_52 - /* - * We assume \phys is 64K aligned and this is guaranteed by only - * supporting this configuration with 64K pages. - */ - orr \pte, \phys, \phys, lsr #36 - and \pte, \pte, #PTE_ADDR_MASK -#else - mov \pte, \phys -#endif - .endm - -/* * Macro to create a table entry to the next page. * * tbl: page table address @@ -181,7 +161,7 @@ ENDPROC(preserve_boot_args) */ .macro create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2 add \tmp1, \tbl, #PAGE_SIZE - phys_to_pte \tmp1, \tmp2 + phys_to_pte \tmp2, \tmp1 orr \tmp2, \tmp2, #PMD_TYPE_TABLE // address of next table and entry type lsr \tmp1, \virt, #\shift sub \ptrs, \ptrs, #1 @@ -207,7 +187,7 @@ ENDPROC(preserve_boot_args) * Returns: rtbl */ .macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1 -.Lpe\@: phys_to_pte \rtbl, \tmp1 +.Lpe\@: phys_to_pte \tmp1, \rtbl orr \tmp1, \tmp1, \flags // tmp1 = table entry str \tmp1, [\tbl, \index, lsl #3] add \rtbl, \rtbl, \inc // rtbl = pa next level @@ -475,7 +455,7 @@ ENDPROC(__primary_switched) * end early head section, begin head code that is also used for * hotplug and needs to have the same protections as the text region */ - .section ".idmap.text","ax" + .section ".idmap.text","awx" ENTRY(kimage_vaddr) .quad _text - TEXT_OFFSET @@ -776,8 +756,8 @@ ENTRY(__enable_mmu) update_early_cpu_boot_status 0, x1, x2 adrp x1, idmap_pg_dir adrp x2, swapper_pg_dir - phys_to_ttbr x1, x3 - phys_to_ttbr x2, x4 + phys_to_ttbr x3, x1 + phys_to_ttbr x4, x2 msr ttbr0_el1, x3 // load TTBR0 msr ttbr1_el1, x4 // load TTBR1 isb diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 84f5d52..dd14ab8 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -34,12 +34,12 @@ * each stage of the walk. */ .macro break_before_make_ttbr_switch zero_page, page_table, tmp - phys_to_ttbr \zero_page, \tmp + phys_to_ttbr \tmp, \zero_page msr ttbr1_el1, \tmp isb tlbi vmalle1 dsb nsh - phys_to_ttbr \page_table, \tmp + phys_to_ttbr \tmp, \page_table msr ttbr1_el1, \tmp isb .endm diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 10dd16d..bebec8e 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -96,7 +96,7 @@ ENTRY(__cpu_suspend_enter) ret ENDPROC(__cpu_suspend_enter) - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly bl __cpu_setup diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 520b0da..e5e741b 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -22,13 +22,14 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <kvm/arm_psci.h> + #include <asm/esr.h> #include <asm/exception.h> #include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> -#include <asm/kvm_psci.h> #include <asm/debug-monitors.h> #include <asm/traps.h> @@ -51,7 +52,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vcpu_hvc_get_imm(vcpu)); vcpu->stat.hvc_exit_stat++; - ret = kvm_psci_call(vcpu); + ret = kvm_hvc_call_handler(vcpu); if (ret < 0) { vcpu_set_reg(vcpu, 0, ~0UL); return 1; @@ -62,7 +63,16 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) { + /* + * "If an SMC instruction executed at Non-secure EL1 is + * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a + * Trap exception, not a Secure Monitor Call exception [...]" + * + * We need to advance the PC after the trap, as it would + * otherwise return to the same address... + */ vcpu_set_reg(vcpu, 0, ~0UL); + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); return 1; } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index e086c6e..5aa9ccf 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -63,7 +63,7 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc - phys_to_ttbr x0, x4 + phys_to_ttbr x4, x0 msr ttbr0_el2, x4 mrs x4, tcr_el1 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index e4f37b9..f36464b 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -15,6 +15,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/arm-smccc.h> #include <linux/linkage.h> #include <asm/alternative.h> @@ -64,10 +65,11 @@ alternative_endif lsr x0, x1, #ESR_ELx_EC_SHIFT cmp x0, #ESR_ELx_EC_HVC64 + ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap - mrs x1, vttbr_el2 // If vttbr is valid, the 64bit guest - cbnz x1, el1_trap // called HVC + mrs x1, vttbr_el2 // If vttbr is valid, the guest + cbnz x1, el1_hvc_guest // called HVC /* Here, we're pretty sure the host called HVC. */ ldp x0, x1, [sp], #16 @@ -100,6 +102,20 @@ alternative_endif eret +el1_hvc_guest: + /* + * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1. + * The workaround has already been applied on the host, + * so let's quickly get back to the guest. We don't bother + * restoring x1, as it can be clobbered anyway. + */ + ldr x1, [sp] // Guest's x0 + eor w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1 + cbnz w1, el1_trap + mov x0, x1 + add sp, sp, #16 + eret + el1_trap: /* * x0: ESR_EC diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 036e1f3..cac6a05 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -19,6 +19,8 @@ #include <linux/jump_label.h> #include <uapi/linux/psci.h> +#include <kvm/arm_psci.h> + #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> @@ -348,18 +350,6 @@ again: if (exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu)) goto again; - if (exit_code == ARM_EXCEPTION_TRAP && - (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC64 || - kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_HVC32) && - vcpu_get_reg(vcpu, 0) == PSCI_0_2_FN_PSCI_VERSION) { - u64 val = PSCI_RET_NOT_SUPPORTED; - if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) - val = 2; - - vcpu_set_reg(vcpu, 0, val); - goto again; - } - if (static_branch_unlikely(&vgic_v2_cpuif_trap) && exit_code == ARM_EXCEPTION_TRAP) { bool valid; diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 3d69a8d..21ba0b2 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -21,7 +21,7 @@ .text -/* Prototype: int __clear_user(void *addr, size_t sz) +/* Prototype: int __arch_clear_user(void *addr, size_t sz) * Purpose : clear some user memory * Params : addr - user memory address to clear * : sz - number of bytes to clear @@ -29,7 +29,7 @@ * * Alignment fixed up by hardware. */ -ENTRY(__clear_user) +ENTRY(__arch_clear_user) uaccess_enable_not_uao x2, x3, x4 mov x2, x1 // save the size for fixup return subs x1, x1, #8 @@ -52,7 +52,7 @@ uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 5: mov x0, #0 uaccess_disable_not_uao x2, x3 ret -ENDPROC(__clear_user) +ENDPROC(__arch_clear_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index fbb090f..54b75de 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -64,14 +64,15 @@ .endm end .req x5 -ENTRY(raw_copy_in_user) + +ENTRY(__arch_copy_in_user) uaccess_enable_not_uao x3, x4, x5 add end, x0, x2 #include "copy_template.S" uaccess_disable_not_uao x3, x4 mov x0, #0 ret -ENDPROC(raw_copy_in_user) +ENDPROC(__arch_copy_in_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index ce441d2..f76bb2c 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -240,7 +240,7 @@ static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs, if (fsc_type == ESR_ELx_FSC_PERM) return true; - if (addr < USER_DS && system_uses_ttbr0_pan()) + if (addr < TASK_SIZE && system_uses_ttbr0_pan()) return fsc_type == ESR_ELx_FSC_FAULT && (regs->pstate & PSR_PAN_BIT); @@ -414,7 +414,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } - if (addr < USER_DS && is_permission_fault(esr, regs, addr)) { + if (addr < TASK_SIZE && is_permission_fault(esr, regs, addr)) { /* regs->orig_addr_limit may be 0 if we entered from EL0 */ if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); @@ -707,6 +707,12 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr, arm64_notify_die("", regs, &info, esr); } +asmlinkage void __exception do_el0_irq_bp_hardening(void) +{ + /* PC has already been checked in entry.S */ + arm64_apply_bp_hardening(); +} + asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, unsigned int esr, struct pt_regs *regs) @@ -731,6 +737,12 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr, struct siginfo info; struct task_struct *tsk = current; + if (user_mode(regs)) { + if (instruction_pointer(regs) > TASK_SIZE) + arm64_apply_bp_hardening(); + local_irq_enable(); + } + if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS)) pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n", tsk->comm, task_pid_nr(tsk), @@ -790,6 +802,9 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, if (interrupts_enabled(regs)) trace_hardirqs_off(); + if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE) + arm64_apply_bp_hardening(); + if (!inf->fn(addr, esr, regs)) { rv = 1; } else { diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 4e369df..4694cda 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -118,6 +118,10 @@ static bool pgattr_change_is_safe(u64 old, u64 new) if ((old | new) & PTE_CONT) return false; + /* Transitioning from Global to Non-Global is safe */ + if (((old ^ new) == PTE_NG) && (new & PTE_NG)) + return true; + return ((old ^ new) & ~mask) == 0; } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 9f177aa..71baed7 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -90,7 +90,7 @@ ENDPROC(cpu_do_suspend) * * x0: Address of context pointer */ - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" ENTRY(cpu_do_resume) ldp x2, x3, [x0] ldp x4, x5, [x0, #16] @@ -153,7 +153,7 @@ ENDPROC(cpu_do_resume) ENTRY(cpu_do_switch_mm) mrs x2, ttbr1_el1 mmid x1, x1 // get mm->context.id - phys_to_ttbr x0, x3 + phys_to_ttbr x3, x0 #ifdef CONFIG_ARM64_SW_TTBR0_PAN bfi x3, x1, #48, #16 // set the ASID field in TTBR0 #endif @@ -165,7 +165,18 @@ ENTRY(cpu_do_switch_mm) b post_ttbr_update_workaround // Back to C code... ENDPROC(cpu_do_switch_mm) - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" + +.macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 + adrp \tmp1, empty_zero_page + phys_to_ttbr \tmp2, \tmp1 + msr ttbr1_el1, \tmp2 + isb + tlbi vmalle1 + dsb nsh + isb +.endm + /* * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd) * @@ -175,24 +186,201 @@ ENDPROC(cpu_do_switch_mm) ENTRY(idmap_cpu_replace_ttbr1) save_and_disable_daif flags=x2 - adrp x1, empty_zero_page - phys_to_ttbr x1, x3 + __idmap_cpu_set_reserved_ttbr1 x1, x3 + + phys_to_ttbr x3, x0 msr ttbr1_el1, x3 isb - tlbi vmalle1 - dsb nsh + restore_daif x2 + + ret +ENDPROC(idmap_cpu_replace_ttbr1) + .popsection + +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + .pushsection ".idmap.text", "awx" + + .macro __idmap_kpti_get_pgtable_ent, type + dc cvac, cur_\()\type\()p // Ensure any existing dirty + dmb sy // lines are written back before + ldr \type, [cur_\()\type\()p] // loading the entry + tbz \type, #0, next_\()\type // Skip invalid entries + .endm + + .macro __idmap_kpti_put_pgtable_ent_ng, type + orr \type, \type, #PTE_NG // Same bit for blocks and pages + str \type, [cur_\()\type\()p] // Update the entry and ensure it + dc civac, cur_\()\type\()p // is visible to all CPUs. + .endm + +/* + * void __kpti_install_ng_mappings(int cpu, int num_cpus, phys_addr_t swapper) + * + * Called exactly once from stop_machine context by each CPU found during boot. + */ +__idmap_kpti_flag: + .long 1 +ENTRY(idmap_kpti_install_ng_mappings) + cpu .req w0 + num_cpus .req w1 + swapper_pa .req x2 + swapper_ttb .req x3 + flag_ptr .req x4 + cur_pgdp .req x5 + end_pgdp .req x6 + pgd .req x7 + cur_pudp .req x8 + end_pudp .req x9 + pud .req x10 + cur_pmdp .req x11 + end_pmdp .req x12 + pmd .req x13 + cur_ptep .req x14 + end_ptep .req x15 + pte .req x16 + + mrs swapper_ttb, ttbr1_el1 + adr flag_ptr, __idmap_kpti_flag + + cbnz cpu, __idmap_kpti_secondary + + /* We're the boot CPU. Wait for the others to catch up */ + sevl +1: wfe + ldaxr w18, [flag_ptr] + eor w18, w18, num_cpus + cbnz w18, 1b + + /* We need to walk swapper, so turn off the MMU. */ + pre_disable_mmu_workaround + mrs x18, sctlr_el1 + bic x18, x18, #SCTLR_ELx_M + msr sctlr_el1, x18 isb - phys_to_ttbr x0, x3 - msr ttbr1_el1, x3 + /* Everybody is enjoying the idmap, so we can rewrite swapper. */ + /* PGD */ + mov cur_pgdp, swapper_pa + add end_pgdp, cur_pgdp, #(PTRS_PER_PGD * 8) +do_pgd: __idmap_kpti_get_pgtable_ent pgd + tbnz pgd, #1, walk_puds + __idmap_kpti_put_pgtable_ent_ng pgd +next_pgd: + add cur_pgdp, cur_pgdp, #8 + cmp cur_pgdp, end_pgdp + b.ne do_pgd + + /* Publish the updated tables and nuke all the TLBs */ + dsb sy + tlbi vmalle1is + dsb ish isb - restore_daif x2 + /* We're done: fire up the MMU again */ + mrs x18, sctlr_el1 + orr x18, x18, #SCTLR_ELx_M + msr sctlr_el1, x18 + isb + /* Set the flag to zero to indicate that we're all done */ + str wzr, [flag_ptr] ret -ENDPROC(idmap_cpu_replace_ttbr1) + + /* PUD */ +walk_puds: + .if CONFIG_PGTABLE_LEVELS > 3 + pte_to_phys cur_pudp, pgd + add end_pudp, cur_pudp, #(PTRS_PER_PUD * 8) +do_pud: __idmap_kpti_get_pgtable_ent pud + tbnz pud, #1, walk_pmds + __idmap_kpti_put_pgtable_ent_ng pud +next_pud: + add cur_pudp, cur_pudp, 8 + cmp cur_pudp, end_pudp + b.ne do_pud + b next_pgd + .else /* CONFIG_PGTABLE_LEVELS <= 3 */ + mov pud, pgd + b walk_pmds +next_pud: + b next_pgd + .endif + + /* PMD */ +walk_pmds: + .if CONFIG_PGTABLE_LEVELS > 2 + pte_to_phys cur_pmdp, pud + add end_pmdp, cur_pmdp, #(PTRS_PER_PMD * 8) +do_pmd: __idmap_kpti_get_pgtable_ent pmd + tbnz pmd, #1, walk_ptes + __idmap_kpti_put_pgtable_ent_ng pmd +next_pmd: + add cur_pmdp, cur_pmdp, #8 + cmp cur_pmdp, end_pmdp + b.ne do_pmd + b next_pud + .else /* CONFIG_PGTABLE_LEVELS <= 2 */ + mov pmd, pud + b walk_ptes +next_pmd: + b next_pud + .endif + + /* PTE */ +walk_ptes: + pte_to_phys cur_ptep, pmd + add end_ptep, cur_ptep, #(PTRS_PER_PTE * 8) +do_pte: __idmap_kpti_get_pgtable_ent pte + __idmap_kpti_put_pgtable_ent_ng pte +next_pte: + add cur_ptep, cur_ptep, #8 + cmp cur_ptep, end_ptep + b.ne do_pte + b next_pmd + + /* Secondary CPUs end up here */ +__idmap_kpti_secondary: + /* Uninstall swapper before surgery begins */ + __idmap_cpu_set_reserved_ttbr1 x18, x17 + + /* Increment the flag to let the boot CPU we're ready */ +1: ldxr w18, [flag_ptr] + add w18, w18, #1 + stxr w17, w18, [flag_ptr] + cbnz w17, 1b + + /* Wait for the boot CPU to finish messing around with swapper */ + sevl +1: wfe + ldxr w18, [flag_ptr] + cbnz w18, 1b + + /* All done, act like nothing happened */ + msr ttbr1_el1, swapper_ttb + isb + ret + + .unreq cpu + .unreq num_cpus + .unreq swapper_pa + .unreq swapper_ttb + .unreq flag_ptr + .unreq cur_pgdp + .unreq end_pgdp + .unreq pgd + .unreq cur_pudp + .unreq end_pudp + .unreq pud + .unreq cur_pmdp + .unreq end_pmdp + .unreq pmd + .unreq cur_ptep + .unreq end_ptep + .unreq pte +ENDPROC(idmap_kpti_install_ng_mappings) .popsection +#endif /* * __cpu_setup @@ -200,7 +388,7 @@ ENDPROC(idmap_cpu_replace_ttbr1) * Initialise the processor for turning the MMU on. Return in x0 the * value of the SCTLR_EL1 register. */ - .pushsection ".idmap.text", "ax" + .pushsection ".idmap.text", "awx" ENTRY(__cpu_setup) tlbi vmalle1 // Invalidate local TLB dsb nsh |