diff options
Diffstat (limited to 'arch/x86/kernel')
| -rw-r--r-- | arch/x86/kernel/Makefile | 5 | ||||
| -rw-r--r-- | arch/x86/kernel/cet.c | 131 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/common.c | 35 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/cpuid-deps.c | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/proc.c | 23 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/core.c | 54 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/regset.c | 81 | ||||
| -rw-r--r-- | arch/x86/kernel/fpu/xstate.c | 90 | ||||
| -rw-r--r-- | arch/x86/kernel/ibt_selftest.S | 17 | ||||
| -rw-r--r-- | arch/x86/kernel/idt.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/process.c | 21 | ||||
| -rw-r--r-- | arch/x86/kernel/process_64.c | 8 | ||||
| -rw-r--r-- | arch/x86/kernel/ptrace.c | 12 | ||||
| -rw-r--r-- | arch/x86/kernel/shstk.c | 550 | ||||
| -rw-r--r-- | arch/x86/kernel/signal.c | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/signal_32.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/signal_64.c | 8 | ||||
| -rw-r--r-- | arch/x86/kernel/sys_x86_64.c | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/traps.c | 87 |
19 files changed, 986 insertions, 148 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 00df34c263cc..3269a0e23d3a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -48,6 +48,7 @@ obj-y += process_$(BITS).o signal.o signal_$(BITS).o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o +obj-$(CONFIG_X86_KERNEL_IBT) += ibt_selftest.o obj-y += setup.o x86_init.o i8259.o irqinit.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o @@ -144,6 +145,10 @@ obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_CALL_THUNKS) += callthunks.o +obj-$(CONFIG_X86_CET) += cet.o + +obj-$(CONFIG_X86_USER_SHADOW_STACK) += shstk.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c new file mode 100644 index 000000000000..d2c732a34e5d --- /dev/null +++ b/arch/x86/kernel/cet.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/ptrace.h> +#include <asm/bugs.h> +#include <asm/traps.h> + +enum cp_error_code { + CP_EC = (1 << 15) - 1, + + CP_RET = 1, + CP_IRET = 2, + CP_ENDBR = 3, + CP_RSTRORSSP = 4, + CP_SETSSBSY = 5, + + CP_ENCL = 1 << 15, +}; + +static const char cp_err[][10] = { + [0] = "unknown", + [1] = "near ret", + [2] = "far/iret", + [3] = "endbranch", + [4] = "rstorssp", + [5] = "setssbsy", +}; + +static const char *cp_err_string(unsigned long error_code) +{ + unsigned int cpec = error_code & CP_EC; + + if (cpec >= ARRAY_SIZE(cp_err)) + cpec = 0; + return cp_err[cpec]; +} + +static void do_unexpected_cp(struct pt_regs *regs, unsigned long error_code) +{ + WARN_ONCE(1, "Unexpected %s #CP, error_code: %s\n", + user_mode(regs) ? "user mode" : "kernel mode", + cp_err_string(error_code)); +} + +static DEFINE_RATELIMIT_STATE(cpf_rate, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + +static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) +{ + struct task_struct *tsk; + unsigned long ssp; + + /* + * An exception was just taken from userspace. Since interrupts are disabled + * here, no scheduling should have messed with the registers yet and they + * will be whatever is live in userspace. So read the SSP before enabling + * interrupts so locking the fpregs to do it later is not required. + */ + rdmsrl(MSR_IA32_PL3_SSP, ssp); + + cond_local_irq_enable(regs); + + tsk = current; + tsk->thread.error_code = error_code; + tsk->thread.trap_nr = X86_TRAP_CP; + + /* Ratelimit to prevent log spamming. */ + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + __ratelimit(&cpf_rate)) { + pr_emerg("%s[%d] control protection ip:%lx sp:%lx ssp:%lx error:%lx(%s)%s", + tsk->comm, task_pid_nr(tsk), + regs->ip, regs->sp, ssp, error_code, + cp_err_string(error_code), + error_code & CP_ENCL ? " in enclave" : ""); + print_vma_addr(KERN_CONT " in ", regs->ip); + pr_cont("\n"); + } + + force_sig_fault(SIGSEGV, SEGV_CPERR, (void __user *)0); + cond_local_irq_disable(regs); +} + +static __ro_after_init bool ibt_fatal = true; + +static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) +{ + if ((error_code & CP_EC) != CP_ENDBR) { + do_unexpected_cp(regs, error_code); + return; + } + + if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { + regs->ax = 0; + return; + } + + pr_err("Missing ENDBR: %pS\n", (void *)instruction_pointer(regs)); + if (!ibt_fatal) { + printk(KERN_DEFAULT CUT_HERE); + __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + return; + } + BUG(); +} + +static int __init ibt_setup(char *str) +{ + if (!strcmp(str, "off")) + setup_clear_cpu_cap(X86_FEATURE_IBT); + + if (!strcmp(str, "warn")) + ibt_fatal = false; + + return 1; +} + +__setup("ibt=", ibt_setup); + +DEFINE_IDTENTRY_ERRORCODE(exc_control_protection) +{ + if (user_mode(regs)) { + if (cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + do_user_cp_fault(regs, error_code); + else + do_unexpected_cp(regs, error_code); + } else { + if (cpu_feature_enabled(X86_FEATURE_IBT)) + do_kernel_cp_fault(regs, error_code); + else + do_unexpected_cp(regs, error_code); + } +} diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 90b8c5ea25aa..6d75fab10161 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -587,27 +587,43 @@ __noendbr void ibt_restore(u64 save) static __always_inline void setup_cet(struct cpuinfo_x86 *c) { - u64 msr = CET_ENDBR_EN; + bool user_shstk, kernel_ibt; - if (!HAS_KERNEL_IBT || - !cpu_feature_enabled(X86_FEATURE_IBT)) + if (!IS_ENABLED(CONFIG_X86_CET)) return; - wrmsrl(MSR_IA32_S_CET, msr); + kernel_ibt = HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT); + user_shstk = cpu_feature_enabled(X86_FEATURE_SHSTK) && + IS_ENABLED(CONFIG_X86_USER_SHADOW_STACK); + + if (!kernel_ibt && !user_shstk) + return; + + if (user_shstk) + set_cpu_cap(c, X86_FEATURE_USER_SHSTK); + + if (kernel_ibt) + wrmsrl(MSR_IA32_S_CET, CET_ENDBR_EN); + else + wrmsrl(MSR_IA32_S_CET, 0); + cr4_set_bits(X86_CR4_CET); - if (!ibt_selftest()) { + if (kernel_ibt && ibt_selftest()) { pr_err("IBT selftest: Failed!\n"); wrmsrl(MSR_IA32_S_CET, 0); setup_clear_cpu_cap(X86_FEATURE_IBT); - return; } } __noendbr void cet_disable(void) { - if (cpu_feature_enabled(X86_FEATURE_IBT)) - wrmsrl(MSR_IA32_S_CET, 0); + if (!(cpu_feature_enabled(X86_FEATURE_IBT) || + cpu_feature_enabled(X86_FEATURE_SHSTK))) + return; + + wrmsrl(MSR_IA32_S_CET, 0); + wrmsrl(MSR_IA32_U_CET, 0); } /* @@ -1491,6 +1507,9 @@ static void __init cpu_parse_early_param(void) if (cmdline_find_option_bool(boot_command_line, "noxsaves")) setup_clear_cpu_cap(X86_FEATURE_XSAVES); + if (cmdline_find_option_bool(boot_command_line, "nousershstk")) + setup_clear_cpu_cap(X86_FEATURE_USER_SHSTK); + arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg)); if (arglen <= 0) return; diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index f6748c8bd647..e462c1d3800a 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -81,6 +81,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XFD, X86_FEATURE_XSAVES }, { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, + { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES }, {} }; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 099b6f0d96bd..31c0e68f6227 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -4,6 +4,8 @@ #include <linux/string.h> #include <linux/seq_file.h> #include <linux/cpufreq.h> +#include <asm/prctl.h> +#include <linux/proc_fs.h> #include "cpu.h" @@ -175,3 +177,24 @@ const struct seq_operations cpuinfo_op = { .stop = c_stop, .show = show_cpuinfo, }; + +#ifdef CONFIG_X86_USER_SHADOW_STACK +static void dump_x86_features(struct seq_file *m, unsigned long features) +{ + if (features & ARCH_SHSTK_SHSTK) + seq_puts(m, "shstk "); + if (features & ARCH_SHSTK_WRSS) + seq_puts(m, "wrss "); +} + +void arch_proc_pid_thread_features(struct seq_file *m, struct task_struct *task) +{ + seq_puts(m, "x86_Thread_features:\t"); + dump_x86_features(m, task->thread.features); + seq_putc(m, '\n'); + + seq_puts(m, "x86_Thread_features_locked:\t"); + dump_x86_features(m, task->thread.features_locked); + seq_putc(m, '\n'); +} +#endif /* CONFIG_X86_USER_SHADOW_STACK */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 98e507cc7d34..a86d37052a64 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -552,8 +552,36 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu) } } +/* A passed ssp of zero will not cause any update */ +static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp) +{ +#ifdef CONFIG_X86_USER_SHADOW_STACK + struct cet_user_state *xstate; + + /* If ssp update is not needed. */ + if (!ssp) + return 0; + + xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave, + XFEATURE_CET_USER); + + /* + * If there is a non-zero ssp, then 'dst' must be configured with a shadow + * stack and the fpu state should be up to date since it was just copied + * from the parent in fpu_clone(). So there must be a valid non-init CET + * state location in the buffer. + */ + if (WARN_ON_ONCE(!xstate)) + return 1; + + xstate->user_ssp = (u64)ssp; +#endif + return 0; +} + /* Clone current's FPU state on fork */ -int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) +int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal, + unsigned long ssp) { struct fpu *src_fpu = ¤t->thread.fpu; struct fpu *dst_fpu = &dst->thread.fpu; @@ -613,6 +641,12 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal) if (use_xsave()) dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID; + /* + * Update shadow stack pointer, in case it changed during clone. + */ + if (update_fpu_shstk(dst, ssp)) + return 1; + trace_x86_fpu_copy_src(src_fpu); trace_x86_fpu_copy_dst(dst_fpu); @@ -753,6 +787,24 @@ void switch_fpu_return(void) } EXPORT_SYMBOL_GPL(switch_fpu_return); +void fpregs_lock_and_load(void) +{ + /* + * fpregs_lock() only disables preemption (mostly). So modifying state + * in an interrupt could screw up some in progress fpregs operation. + * Warn about it. + */ + WARN_ON_ONCE(!irq_fpu_usable()); + WARN_ON_ONCE(current->flags & PF_KTHREAD); + + fpregs_lock(); + + fpregs_assert_state_consistent(); + + if (test_thread_flag(TIF_NEED_FPU_LOAD)) + fpregs_restore_userregs(); +} + #ifdef CONFIG_X86_DEBUG_FPU /* * If current FPU state according to its tracking (loaded FPU context on this diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6d056b68f4ed..6bc1eb2a21bd 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -8,6 +8,7 @@ #include <asm/fpu/api.h> #include <asm/fpu/signal.h> #include <asm/fpu/regset.h> +#include <asm/prctl.h> #include "context.h" #include "internal.h" @@ -174,6 +175,86 @@ out: return ret; } +#ifdef CONFIG_X86_USER_SHADOW_STACK +int ssp_active(struct task_struct *target, const struct user_regset *regset) +{ + if (target->thread.features & ARCH_SHSTK_SHSTK) + return regset->n; + + return 0; +} + +int ssp_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + struct fpu *fpu = &target->thread.fpu; + struct cet_user_state *cetregs; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + return -ENODEV; + + sync_fpstate(fpu); + cetregs = get_xsave_addr(&fpu->fpstate->regs.xsave, XFEATURE_CET_USER); + if (WARN_ON(!cetregs)) { + /* + * This shouldn't ever be NULL because shadow stack was + * verified to be enabled above. This means + * MSR_IA32_U_CET.CET_SHSTK_EN should be 1 and so + * XFEATURE_CET_USER should not be in the init state. + */ + return -ENODEV; + } + + return membuf_write(&to, (unsigned long *)&cetregs->user_ssp, + sizeof(cetregs->user_ssp)); +} + +int ssp_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave = &fpu->fpstate->regs.xsave; + struct cet_user_state *cetregs; + unsigned long user_ssp; + int r; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) + return -ENODEV; + + if (pos != 0 || count != sizeof(user_ssp)) + return -EINVAL; + + r = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_ssp, 0, -1); + if (r) + return r; + + /* + * Some kernel instructions (IRET, etc) can cause exceptions in the case + * of disallowed CET register values. Just prevent invalid values. + */ + if (user_ssp >= TASK_SIZE_MAX || !IS_ALIGNED(user_ssp, 8)) + return -EINVAL; + + fpu_force_restore(fpu); + + cetregs = get_xsave_addr(xsave, XFEATURE_CET_USER); + if (WARN_ON(!cetregs)) { + /* + * This shouldn't ever be NULL because shadow stack was + * verified to be enabled above. This means + * MSR_IA32_U_CET.CET_SHSTK_EN should be 1 and so + * XFEATURE_CET_USER should not be in the init state. + */ + return -ENODEV; + } + + cetregs->user_ssp = user_ssp; + return 0; +} +#endif /* CONFIG_X86_USER_SHADOW_STACK */ + #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1afbc4866b10..41dac93b8ea4 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -39,26 +39,26 @@ */ static const char *xfeature_names[] = { - "x87 floating point registers" , - "SSE registers" , - "AVX registers" , - "MPX bounds registers" , - "MPX CSR" , - "AVX-512 opmask" , - "AVX-512 Hi256" , - "AVX-512 ZMM_Hi256" , - "Processor Trace (unused)" , + "x87 floating point registers", + "SSE registers", + "AVX registers", + "MPX bounds registers", + "MPX CSR", + "AVX-512 opmask", + "AVX-512 Hi256", + "AVX-512 ZMM_Hi256", + "Processor Trace (unused)", "Protection Keys User registers", "PASID state", - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "unknown xstate feature" , - "AMX Tile config" , - "AMX Tile data" , - "unknown xstate feature" , + "Control-flow User registers", + "Control-flow Kernel registers (unused)", + "unknown xstate feature", + "unknown xstate feature", + "unknown xstate feature", + "unknown xstate feature", + "AMX Tile config", + "AMX Tile data", + "unknown xstate feature", }; static unsigned short xsave_cpuid_features[] __initdata = { @@ -73,6 +73,7 @@ static unsigned short xsave_cpuid_features[] __initdata = { [XFEATURE_PT_UNIMPLEMENTED_SO_FAR] = X86_FEATURE_INTEL_PT, [XFEATURE_PKRU] = X86_FEATURE_PKU, [XFEATURE_PASID] = X86_FEATURE_ENQCMD, + [XFEATURE_CET_USER] = X86_FEATURE_SHSTK, [XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE, [XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE, }; @@ -276,6 +277,7 @@ static void __init print_xstate_features(void) print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); print_xstate_feature(XFEATURE_MASK_PKRU); print_xstate_feature(XFEATURE_MASK_PASID); + print_xstate_feature(XFEATURE_MASK_CET_USER); print_xstate_feature(XFEATURE_MASK_XTILE_CFG); print_xstate_feature(XFEATURE_MASK_XTILE_DATA); } @@ -344,6 +346,7 @@ static __init void os_xrstor_booting(struct xregs_state *xstate) XFEATURE_MASK_BNDREGS | \ XFEATURE_MASK_BNDCSR | \ XFEATURE_MASK_PASID | \ + XFEATURE_MASK_CET_USER | \ XFEATURE_MASK_XTILE) /* @@ -446,14 +449,15 @@ static void __init __xstate_dump_leaves(void) } \ } while (0) -#define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \ - if ((nr == nr_macro) && \ - WARN_ONCE(sz != sizeof(__struct), \ - "%s: struct is %zu bytes, cpu state %d bytes\n", \ - __stringify(nr_macro), sizeof(__struct), sz)) { \ +#define XCHECK_SZ(sz, nr, __struct) ({ \ + if (WARN_ONCE(sz != sizeof(__struct), \ + "[%s]: struct is %zu bytes, cpu state %d bytes\n", \ + xfeature_names[nr], sizeof(__struct), sz)) { \ __xstate_dump_leaves(); \ } \ -} while (0) + true; \ +}) + /** * check_xtile_data_against_struct - Check tile data state size. @@ -527,36 +531,28 @@ static bool __init check_xstate_against_struct(int nr) * Ask the CPU for the size of the state. */ int sz = xfeature_size(nr); + /* * Match each CPU state with the corresponding software * structure. */ - XCHECK_SZ(sz, nr, XFEATURE_YMM, struct ymmh_struct); - XCHECK_SZ(sz, nr, XFEATURE_BNDREGS, struct mpx_bndreg_state); - XCHECK_SZ(sz, nr, XFEATURE_BNDCSR, struct mpx_bndcsr_state); - XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state); - XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); - XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); - XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state); - XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state); - XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg); - - /* The tile data size varies between implementations. */ - if (nr == XFEATURE_XTILE_DATA) - check_xtile_data_against_struct(sz); - - /* - * Make *SURE* to add any feature numbers in below if - * there are "holes" in the xsave state component - * numbers. - */ - if ((nr < XFEATURE_YMM) || - (nr >= XFEATURE_MAX) || - (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) || - ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) { + switch (nr) { + case XFEATURE_YMM: return XCHECK_SZ(sz, nr, struct ymmh_struct); + case XFEATURE_BNDREGS: return XCHECK_SZ(sz, nr, struct mpx_bndreg_state); + case XFEATURE_BNDCSR: return XCHECK_SZ(sz, nr, struct mpx_bndcsr_state); + case XFEATURE_OPMASK: return XCHECK_SZ(sz, nr, struct avx_512_opmask_state); + case XFEATURE_ZMM_Hi256: return XCHECK_SZ(sz, nr, struct avx_512_zmm_uppers_state); + case XFEATURE_Hi16_ZMM: return XCHECK_SZ(sz, nr, struct avx_512_hi16_state); + case XFEATURE_PKRU: return XCHECK_SZ(sz, nr, struct pkru_state); + case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state); + case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg); + case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state); + case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true; + default: XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr); return false; } + return true; } diff --git a/arch/x86/kernel/ibt_selftest.S b/arch/x86/kernel/ibt_selftest.S new file mode 100644 index 000000000000..c43c4ed28a9c --- /dev/null +++ b/arch/x86/kernel/ibt_selftest.S @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <linux/objtool.h> +#include <asm/nospec-branch.h> + +SYM_CODE_START(ibt_selftest_noendbr) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + /* #CP handler sets %ax to 0 */ + RET +SYM_CODE_END(ibt_selftest_noendbr) + +SYM_FUNC_START(ibt_selftest) + lea ibt_selftest_noendbr(%rip), %rax + ANNOTATE_RETPOLINE_SAFE + jmp *%rax +SYM_FUNC_END(ibt_selftest) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index f3958262c725..b786d48f5a0f 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -107,7 +107,7 @@ static const __initconst struct idt_data def_idts[] = { ISTG(X86_TRAP_MC, asm_exc_machine_check, IST_INDEX_MCE), #endif -#ifdef CONFIG_X86_KERNEL_IBT +#ifdef CONFIG_X86_CET INTG(X86_TRAP_CP, asm_exc_control_protection), #endif diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 72015dba72ab..9f0909142a0a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -51,6 +51,7 @@ #include <asm/unwind.h> #include <asm/tdx.h> #include <asm/mmu_context.h> +#include <asm/shstk.h> #include "process.h" @@ -122,6 +123,7 @@ void exit_thread(struct task_struct *tsk) free_vm86(t); + shstk_free(tsk); fpu__drop(fpu); } @@ -162,6 +164,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) struct inactive_task_frame *frame; struct fork_frame *fork_frame; struct pt_regs *childregs; + unsigned long new_ssp; int ret = 0; childregs = task_pt_regs(p); @@ -199,7 +202,16 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame->flags = X86_EFLAGS_FIXED; #endif - fpu_clone(p, clone_flags, args->fn); + /* + * Allocate a new shadow stack for thread if needed. If shadow stack, + * is disabled, new_ssp will remain 0, and fpu_clone() will know not to + * update it. + */ + new_ssp = shstk_alloc_thread_stack(p, clone_flags, args->stack_size); + if (IS_ERR_VALUE(new_ssp)) + return PTR_ERR((void *)new_ssp); + + fpu_clone(p, clone_flags, args->fn, new_ssp); /* Kernel thread ? */ if (unlikely(p->flags & PF_KTHREAD)) { @@ -245,6 +257,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP))) io_bitmap_share(p); + /* + * If copy_thread() if failing, don't leak the shadow stack possibly + * allocated in shstk_alloc_thread_stack() above. + */ + if (ret) + shstk_free(p); + return ret; } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3d181c16a2f6..33b268747bb7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -515,6 +515,8 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, load_gs_index(__USER_DS); } + reset_thread_features(); + loadsegment(fs, 0); loadsegment(es, _ds); loadsegment(ds, _ds); @@ -894,6 +896,12 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2) else return put_user(LAM_U57_BITS, (unsigned long __user *)arg2); #endif + case ARCH_SHSTK_ENABLE: + case ARCH_SHSTK_DISABLE: + case ARCH_SHSTK_LOCK: + case ARCH_SHSTK_UNLOCK: + case ARCH_SHSTK_STATUS: + return shstk_prctl(task, option, arg2); default: ret = -EINVAL; break; diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index dfaa270a7cc9..095f04bdabdc 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -58,6 +58,7 @@ enum x86_regset_64 { REGSET64_FP, REGSET64_IOPERM, REGSET64_XSTATE, + REGSET64_SSP, }; #define REGSET_GENERAL \ @@ -1267,6 +1268,17 @@ static struct user_regset x86_64_regsets[] __ro_after_init = { .active = ioperm_active, .regset_get = ioperm_get }, +#ifdef CONFIG_X86_USER_SHADOW_STACK + [REGSET64_SSP] = { + .core_note_type = NT_X86_SHSTK, + .n = 1, + .size = sizeof(u64), + .align = sizeof(u64), + .active = ssp_active, + .regset_get = ssp_get, + .set = ssp_set + }, +#endif }; static const struct user_regset_view user_x86_64_view = { diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c new file mode 100644 index 000000000000..fd689921a1db --- /dev/null +++ b/arch/x86/kernel/shstk.c @@ -0,0 +1,550 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * shstk.c - Intel shadow stack support + * + * Copyright (c) 2021, Intel Corporation. + * Yu-cheng Yu <yu-cheng.yu@intel.com> + */ + +#include <linux/sched.h> +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/sched/signal.h> +#include <linux/compat.h> +#include <linux/sizes.h> +#include <linux/user.h> +#include <linux/syscalls.h> +#include <asm/msr.h> +#include <asm/fpu/xstate.h> +#include <asm/fpu/types.h> +#include <asm/shstk.h> +#include <asm/special_insns.h> +#include <asm/fpu/api.h> +#include <asm/prctl.h> + +#define SS_FRAME_SIZE 8 + +static bool features_enabled(unsigned long features) +{ + return current->thread.features & features; +} + +static void features_set(unsigned long features) +{ + current->thread.features |= features; +} + +static void features_clr(unsigned long features) +{ + current->thread.features &= ~features; +} + +/* + * Create a restore token on the shadow stack. A token is always 8-byte + * and aligned to 8. + */ +static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) +{ + unsigned long addr; + + /* Token must be aligned */ + if (!IS_ALIGNED(ssp, 8)) + return -EINVAL; + + addr = ssp - SS_FRAME_SIZE; + + /* + * SSP is aligned, so reserved bits and mode bit are a zero, just mark + * the token 64-bit. + */ + ssp |= BIT(0); + + if (write_user_shstk_64((u64 __user *)addr, (u64)ssp)) + return -EFAULT; + + if (token_addr) + *token_addr = addr; + + return 0; +} + +/* + * VM_SHADOW_STACK will have a guard page. This helps userspace protect + * itself from attacks. The reasoning is as follows: + * + * The shadow stack pointer(SSP) is moved by CALL, RET, and INCSSPQ. The + * INCSSP instruction can increment the shadow stack pointer. It is the + * shadow stack analog of an instruction like: + * + * addq $0x80, %rsp + * + * However, there is one important difference between an ADD on %rsp + * and INCSSP. In addition to modifying SSP, INCSSP also reads from the + * memory of the first and last elements that were "popped". It can be + * thought of as acting like this: + * + * READ_ONCE(ssp); // read+discard top element on stack + * ssp += nr_to_pop * 8; // move the shadow stack + * READ_ONCE(ssp-8); // read+discard last popped stack element + * + * The maximum distance INCSSP can move the SSP is 2040 bytes, before + * it would read the memory. Therefore a single page gap will be enough + * to prevent any operation from shifting the SSP to an adjacent stack, + * since it would have to land in the gap at least once, causing a + * fault. + */ +static unsigned long alloc_shstk(unsigned long addr, unsigned long size, + unsigned long token_offset, bool set_res_tok) +{ + int flags = MAP_ANONYMOUS | MAP_PRIVATE | MAP_ABOVE4G; + struct mm_struct *mm = current->mm; + unsigned long mapped_addr, unused; + + if (addr) + flags |= MAP_FIXED_NOREPLACE; + + mmap_write_lock(mm); + mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags, + VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL); + mmap_write_unlock(mm); + + if (!set_res_tok || IS_ERR_VALUE(mapped_addr)) + goto out; + + if (create_rstor_token(mapped_addr + token_offset, NULL)) { + vm_munmap(mapped_addr, size); + return -EINVAL; + } + +out: + return mapped_addr; +} + +static unsigned long adjust_shstk_size(unsigned long size) +{ + if (size) + return PAGE_ALIGN(size); + + return PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G)); +} + +static void unmap_shadow_stack(u64 base, u64 size) +{ + int r; + + r = vm_munmap(base, size); + + /* + * mmap_write_lock_killable() failed with -EINTR. This means + * the process is about to die and have it's MM cleaned up. + * This task shouldn't ever make it back to userspace. In this + * case it is ok to leak a shadow stack, so just exit out. + */ + if (r == -EINTR) + return; + + /* + * For all other types of vm_munmap() failure, either the + * system is out of memory or there is bug. + */ + WARN_ON_ONCE(r); +} + +static int shstk_setup(void) +{ + struct thread_shstk *shstk = ¤t->thread.shstk; + unsigned long addr, size; + + /* Already enabled */ + if (features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + /* Also not supported for 32 bit and x32 */ + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_32bit_syscall()) + return -EOPNOTSUPP; + + size = adjust_shstk_size(0); + addr = alloc_shstk(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return PTR_ERR((void *)addr); + + fpregs_lock_and_load(); + wrmsrl(MSR_IA32_PL3_SSP, addr + size); + wrmsrl(MSR_IA32_U_CET, CET_SHSTK_EN); + fpregs_unlock(); + + shstk->base = addr; + shstk->size = size; + features_set(ARCH_SHSTK_SHSTK); + + return 0; +} + +void reset_thread_features(void) +{ + memset(¤t->thread.shstk, 0, sizeof(struct thread_shstk)); + current->thread.features = 0; + current->thread.features_locked = 0; +} + +unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long clone_flags, + unsigned long stack_size) +{ + struct thread_shstk *shstk = &tsk->thread.shstk; + unsigned long addr, size; + + /* + * If shadow stack is not enabled on the new thread, skip any + * switch to a new shadow stack. + */ + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + /* + * For CLONE_VM, except vfork, the child needs a separate shadow + * stack. + */ + if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) + return 0; + + size = adjust_shstk_size(stack_size); + addr = alloc_shstk(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return addr; + + shstk->base = addr; + shstk->size = size; + + return addr + size; +} + +static unsigned long get_user_shstk_addr(void) +{ + unsigned long long ssp; + + fpregs_lock_and_load(); + + rdmsrl(MSR_IA32_PL3_SSP, ssp); + + fpregs_unlock(); + + return ssp; +} + +#define SHSTK_DATA_BIT BIT(63) + +static int put_shstk_data(u64 __user *addr, u64 data) +{ + if (WARN_ON_ONCE(data & SHSTK_DATA_BIT)) + return -EINVAL; + + /* + * Mark the high bit so that the sigframe can't be processed as a + * return address. + */ + if (write_user_shstk_64(addr, data | SHSTK_DATA_BIT)) + return -EFAULT; + return 0; +} + +static int get_shstk_data(unsigned long *data, unsigned long __user *addr) +{ + unsigned long ldata; + + if (unlikely(get_user(ldata, addr))) + return -EFAULT; + + if (!(ldata & SHSTK_DATA_BIT)) + return -EINVAL; + + *data = ldata & ~SHSTK_DATA_BIT; + + return 0; +} + +static int shstk_push_sigframe(unsigned long *ssp) +{ + unsigned long target_ssp = *ssp; + + /* Token must be aligned */ + if (!IS_ALIGNED(target_ssp, 8)) + return -EINVAL; + + *ssp -= SS_FRAME_SIZE; + if (put_shstk_data((void __user *)*ssp, target_ssp)) + return -EFAULT; + + return 0; +} + +static int shstk_pop_sigframe(unsigned long *ssp) +{ + struct vm_area_struct *vma; + unsigned long token_addr; + bool need_to_check_vma; + int err = 1; + + /* + * It is possible for the SSP to be off the end of a shadow stack by 4 + * or 8 bytes. If the shadow stack is at the start of a page or 4 bytes + * before it, it might be this case, so check that the address being + * read is actually shadow stack. + */ + if (!IS_ALIGNED(*ssp, 8)) + return -EINVAL; + + need_to_check_vma = PAGE_ALIGN(*ssp) == *ssp; + + if (need_to_check_vma) + mmap_read_lock_killable(current->mm); + + err = get_shstk_data(&token_addr, (unsigned long __user *)*ssp); + if (unlikely(err)) + goto out_err; + + if (need_to_check_vma) { + vma = find_vma(current->mm, *ssp); + if (!vma || !(vma->vm_flags & VM_SHADOW_STACK)) { + err = -EFAULT; + goto out_err; + } + + mmap_read_unlock(current->mm); + } + + /* Restore SSP aligned? */ + if (unlikely(!IS_ALIGNED(token_addr, 8))) + return -EINVAL; + + /* SSP in userspace? */ + if (unlikely(token_addr >= TASK_SIZE_MAX)) + return -EINVAL; + + *ssp = token_addr; + + return 0; +out_err: + if (need_to_check_vma) + mmap_read_unlock(current->mm); + return err; +} + +int setup_signal_shadow_stack(struct ksignal *ksig) +{ + void __user *restorer = ksig->ka.sa.sa_restorer; + unsigned long ssp; + int err; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + if (!restorer) + return -EINVAL; + + ssp = get_user_shstk_addr(); + if (unlikely(!ssp)) + return -EINVAL; + + err = shstk_push_sigframe(&ssp); + if (unlikely(err)) + return err; + + /* Push restorer address */ + ssp -= SS_FRAME_SIZE; + err = write_user_shstk_64((u64 __user *)ssp, (u64)restorer); + if (unlikely(err)) + return -EFAULT; + + fpregs_lock_and_load(); + wrmsrl(MSR_IA32_PL3_SSP, ssp); + fpregs_unlock(); + + return 0; +} + +int restore_signal_shadow_stack(void) +{ + unsigned long ssp; + int err; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + ssp = get_user_shstk_addr(); + if (unlikely(!ssp)) + return -EINVAL; + + err = shstk_pop_sigframe(&ssp); + if (unlikely(err)) + return err; + + fpregs_lock_and_load(); + wrmsrl(MSR_IA32_PL3_SSP, ssp); + fpregs_unlock(); + + return 0; +} + +void shstk_free(struct task_struct *tsk) +{ + struct thread_shstk *shstk = &tsk->thread.shstk; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !features_enabled(ARCH_SHSTK_SHSTK)) + return; + + /* + * When fork() with CLONE_VM fails, the child (tsk) already has a + * shadow stack allocated, and exit_thread() calls this function to + * free it. In this case the parent (current) and the child share + * the same mm struct. + */ + if (!tsk->mm || tsk->mm != current->mm) + return; + + unmap_shadow_stack(shstk->base, shstk->size); +} + +static int wrss_control(bool enable) +{ + u64 msrval; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + return -EOPNOTSUPP; + + /* + * Only enable WRSS if shadow stack is enabled. If shadow stack is not + * enabled, WRSS will already be disabled, so don't bother clearing it + * when disabling. + */ + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return -EPERM; + + /* Already enabled/disabled? */ + if (features_enabled(ARCH_SHSTK_WRSS) == enable) + return 0; + + fpregs_lock_and_load(); + rdmsrl(MSR_IA32_U_CET, msrval); + + if (enable) { + features_set(ARCH_SHSTK_WRSS); + msrval |= CET_WRSS_EN; + } else { + features_clr(ARCH_SHSTK_WRSS); + if (!(msrval & CET_WRSS_EN)) + goto unlock; + + msrval &= ~CET_WRSS_EN; + } + + wrmsrl(MSR_IA32_U_CET, msrval); + +unlock: + fpregs_unlock(); + + return 0; +} + +static int shstk_disable(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + return -EOPNOTSUPP; + + /* Already disabled? */ + if (!features_enabled(ARCH_SHSTK_SHSTK)) + return 0; + + fpregs_lock_and_load(); + /* Disable WRSS too when disabling shadow stack */ + wrmsrl(MSR_IA32_U_CET, 0); + wrmsrl(MSR_IA32_PL3_SSP, 0); + fpregs_unlock(); + + shstk_free(current); + features_clr(ARCH_SHSTK_SHSTK | ARCH_SHSTK_WRSS); + + return 0; +} + +SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) +{ + bool set_tok = flags & SHADOW_STACK_SET_TOKEN; + unsigned long aligned_size; + + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + return -EOPNOTSUPP; + + if (flags & ~SHADOW_STACK_SET_TOKEN) + return -EINVAL; + + /* If there isn't space for a token */ + if (set_tok && size < 8) + return -ENOSPC; + + if (addr && addr < SZ_4G) + return -ERANGE; + + /* + * An overflow would result in attempting to write the restore token + * to the wrong location. Not catastrophic, but just return the right + * error code and block it. + */ + aligned_size = PAGE_ALIGN(size); + if (aligned_size < size) + return -EOVERFLOW; + + return alloc_shstk(addr, aligned_size, size, set_tok); +} + +long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) +{ + unsigned long features = arg2; + + if (option == ARCH_SHSTK_STATUS) { + return put_user(task->thread.features, (unsigned long __user *)arg2); + } + + if (option == ARCH_SHSTK_LOCK) { + task->thread.features_locked |= features; + return 0; + } + + /* Only allow via ptrace */ + if (task != current) { + if (option == ARCH_SHSTK_UNLOCK && IS_ENABLED(CONFIG_CHECKPOINT_RESTORE)) { + task->thread.features_locked &= ~features; + return 0; + } + return -EINVAL; + } + + /* Do not allow to change locked features */ + if (features & task->thread.features_locked) + return -EPERM; + + /* Only support enabling/disabling one feature at a time. */ + if (hweight_long(features) > 1) + return -EINVAL; + + if (option == ARCH_SHSTK_DISABLE) { + if (features & ARCH_SHSTK_WRSS) + return wrss_control(false); + if (features & ARCH_SHSTK_SHSTK) + return shstk_disable(); + return -EINVAL; + } + + /* Handle ARCH_SHSTK_ENABLE */ + if (features & ARCH_SHSTK_SHSTK) + return shstk_setup(); + if (features & ARCH_SHSTK_WRSS) + return wrss_control(true); + return -EINVAL; +} diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index cfeec3ee877e..65fe2094da59 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -40,6 +40,7 @@ #include <asm/syscall.h> #include <asm/sigframe.h> #include <asm/signal.h> +#include <asm/shstk.h> static inline int is_ia32_compat_frame(struct ksignal *ksig) { diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index 9027fc088f97..c12624bc82a3 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -402,7 +402,7 @@ Efault: */ static_assert(NSIGILL == 11); static_assert(NSIGFPE == 15); -static_assert(NSIGSEGV == 9); +static_assert(NSIGSEGV == 10); static_assert(NSIGBUS == 5); static_assert(NSIGTRAP == 6); static_assert(NSIGCHLD == 6); diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 13a1e6083837..cacf2ede6217 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -175,6 +175,9 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); uc_flags = frame_uc_flags(regs); + if (setup_signal_shadow_stack(ksig)) + return -EFAULT; + if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; @@ -260,6 +263,9 @@ SYSCALL_DEFINE0(rt_sigreturn) if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) goto badframe; + if (restore_signal_shadow_stack()) + goto badframe; + if (restore_altstack(&frame->uc.uc_stack)) goto badframe; @@ -403,7 +409,7 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) */ static_assert(NSIGILL == 11); static_assert(NSIGFPE == 15); -static_assert(NSIGSEGV == 9); +static_assert(NSIGSEGV == 10); static_assert(NSIGBUS == 5); static_assert(NSIGTRAP == 6); static_assert(NSIGCHLD == 6); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 8cc653ffdccd..c783aeb37dce 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -193,7 +193,11 @@ get_unmapped_area: info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; - info.low_limit = PAGE_SIZE; + if (!in_32bit_syscall() && (flags & MAP_ABOVE4G)) + info.low_limit = SZ_4G; + else + info.low_limit = PAGE_SIZE; + info.high_limit = get_mmap_base(0); /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4a817d20ce3b..c876f1d36a81 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -77,18 +77,6 @@ DECLARE_BITMAP(system_vectors, NR_VECTORS); -static inline void cond_local_irq_enable(struct pt_regs *regs) -{ - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); -} - -static inline void cond_local_irq_disable(struct pt_regs *regs) -{ - if (regs->flags & X86_EFLAGS_IF) - local_irq_disable(); -} - __always_inline int is_valid_bugaddr(unsigned long addr) { if (addr < TASK_SIZE_MAX) @@ -213,81 +201,6 @@ DEFINE_IDTENTRY(exc_overflow) do_error_trap(regs, 0, "overflow", X86_TRAP_OF, SIGSEGV, 0, NULL); } -#ifdef CONFIG_X86_KERNEL_IBT - -static __ro_after_init bool ibt_fatal = true; - -extern void ibt_selftest_ip(void); /* code label defined in asm below */ - -enum cp_error_code { - CP_EC = (1 << 15) - 1, - - CP_RET = 1, - CP_IRET = 2, - CP_ENDBR = 3, - CP_RSTRORSSP = 4, - CP_SETSSBSY = 5, - - CP_ENCL = 1 << 15, -}; - -DEFINE_IDTENTRY_ERRORCODE(exc_control_protection) -{ - if (!cpu_feature_enabled(X86_FEATURE_IBT)) { - pr_err("Unexpected #CP\n"); - BUG(); - } - - if (WARN_ON_ONCE(user_mode(regs) || (error_code & CP_EC) != CP_ENDBR)) - return; - - if (unlikely(regs->ip == (unsigned long)&ibt_selftest_ip)) { - regs->ax = 0; - return; - } - - pr_err("Missing ENDBR: %pS\n", (void *)instruction_pointer(regs)); - if (!ibt_fatal) { - printk(KERN_DEFAULT CUT_HERE); - __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); - return; - } - BUG(); -} - -/* Must be noinline to ensure uniqueness of ibt_selftest_ip. */ -noinline bool ibt_selftest(void) -{ - unsigned long ret; - - asm (" lea ibt_selftest_ip(%%rip), %%rax\n\t" - ANNOTATE_RETPOLINE_SAFE - " jmp *%%rax\n\t" - "ibt_selftest_ip:\n\t" - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - " nop\n\t" - - : "=a" (ret) : : "memory"); - - return !ret; -} - -static int __init ibt_setup(char *str) -{ - if (!strcmp(str, "off")) - setup_clear_cpu_cap(X86_FEATURE_IBT); - - if (!strcmp(str, "warn")) - ibt_fatal = false; - - return 1; -} - -__setup("ibt=", ibt_setup); - -#endif /* CONFIG_X86_KERNEL_IBT */ - #ifdef CONFIG_X86_F00F_BUG void handle_invalid_op(struct pt_regs *regs) #else |