diff options
Diffstat (limited to 'arch/x86/kernel/process_64.c')
-rw-r--r-- | arch/x86/kernel/process_64.c | 266 |
1 files changed, 198 insertions, 68 deletions
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ffd497804dbc..6b3418bff326 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -40,20 +40,19 @@ #include <linux/ftrace.h> #include <linux/syscalls.h> -#include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/fpu/internal.h> +#include <asm/pkru.h> +#include <asm/fpu/sched.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> #include <asm/proto.h> #include <asm/ia32.h> -#include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> -#include <asm/resctrl_sched.h> +#include <asm/resctrl.h> #include <asm/unistd.h> #include <asm/fsgsbase.h> #ifdef CONFIG_IA32_EMULATION @@ -64,30 +63,31 @@ #include "process.h" /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, + const char *log_lvl) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; unsigned int fsindex, gsindex; unsigned int ds, es; - show_iret_regs(regs); + show_iret_regs(regs, log_lvl); if (regs->orig_ax != -1) pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax); else pr_cont("\n"); - printk(KERN_DEFAULT "RAX: %016lx RBX: %016lx RCX: %016lx\n", - regs->ax, regs->bx, regs->cx); - printk(KERN_DEFAULT "RDX: %016lx RSI: %016lx RDI: %016lx\n", - regs->dx, regs->si, regs->di); - printk(KERN_DEFAULT "RBP: %016lx R08: %016lx R09: %016lx\n", - regs->bp, regs->r8, regs->r9); - printk(KERN_DEFAULT "R10: %016lx R11: %016lx R12: %016lx\n", - regs->r10, regs->r11, regs->r12); - printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", - regs->r13, regs->r14, regs->r15); + printk("%sRAX: %016lx RBX: %016lx RCX: %016lx\n", + log_lvl, regs->ax, regs->bx, regs->cx); + printk("%sRDX: %016lx RSI: %016lx RDI: %016lx\n", + log_lvl, regs->dx, regs->si, regs->di); + printk("%sRBP: %016lx R08: %016lx R09: %016lx\n", + log_lvl, regs->bp, regs->r8, regs->r9); + printk("%sR10: %016lx R11: %016lx R12: %016lx\n", + log_lvl, regs->r10, regs->r11, regs->r12); + printk("%sR13: %016lx R14: %016lx R15: %016lx\n", + log_lvl, regs->r13, regs->r14, regs->r15); if (mode == SHOW_REGS_SHORT) return; @@ -95,8 +95,8 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) if (mode == SHOW_REGS_USER) { rdmsrl(MSR_FS_BASE, fs); rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); - printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", - fs, shadowgs); + printk("%sFS: %016lx GS: %016lx\n", + log_lvl, fs, shadowgs); return; } @@ -114,12 +114,12 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) cr3 = __read_cr3(); cr4 = __read_cr4(); - printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", - fs, fsindex, gs, gsindex, shadowgs); - printk(KERN_DEFAULT "CS: %04lx DS: %04x ES: %04x CR0: %016lx\n", regs->cs, ds, - es, cr0); - printk(KERN_DEFAULT "CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, - cr4); + printk("%sFS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", + log_lvl, fs, fsindex, gs, gsindex, shadowgs); + printk("%sCS: %04lx DS: %04x ES: %04x CR0: %016lx\n", + log_lvl, regs->cs, ds, es, cr0); + printk("%sCR2: %016lx CR3: %016lx CR4: %016lx\n", + log_lvl, cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); @@ -131,14 +131,14 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) /* Only print out debug registers if they are in their non-default state. */ if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && (d6 == DR6_RESERVED) && (d7 == 0x400))) { - printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", - d0, d1, d2); - printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", - d3, d6, d7); + printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n", + log_lvl, d0, d1, d2); + printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n", + log_lvl, d3, d6, d7); } - if (boot_cpu_has(X86_FEATURE_OSPKE)) - printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru()); + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } void release_thread(struct task_struct *dead_task) @@ -152,6 +152,56 @@ enum which_selector { }; /* + * Out of line to be protected from kprobes and tracing. If this would be + * traced or probed than any access to a per CPU variable happens with + * the wrong GS. + * + * It is not used on Xen paravirt. When paravirt support is needed, it + * needs to be renamed with native_ prefix. + */ +static noinstr unsigned long __rdgsbase_inactive(void) +{ + unsigned long gsbase; + + lockdep_assert_irqs_disabled(); + + if (!static_cpu_has(X86_FEATURE_XENPV)) { + native_swapgs(); + gsbase = rdgsbase(); + native_swapgs(); + } else { + instrumentation_begin(); + rdmsrl(MSR_KERNEL_GS_BASE, gsbase); + instrumentation_end(); + } + + return gsbase; +} + +/* + * Out of line to be protected from kprobes and tracing. If this would be + * traced or probed than any access to a per CPU variable happens with + * the wrong GS. + * + * It is not used on Xen paravirt. When paravirt support is needed, it + * needs to be renamed with native_ prefix. + */ +static noinstr void __wrgsbase_inactive(unsigned long gsbase) +{ + lockdep_assert_irqs_disabled(); + + if (!static_cpu_has(X86_FEATURE_XENPV)) { + native_swapgs(); + wrgsbase(gsbase); + native_swapgs(); + } else { + instrumentation_begin(); + wrmsrl(MSR_KERNEL_GS_BASE, gsbase); + instrumentation_end(); + } +} + +/* * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are * not available. The goal is to be reasonably fast on non-FSGSBASE systems. * It's forcibly inlined because it'll generate better code and this function @@ -200,22 +250,35 @@ static __always_inline void save_fsgs(struct task_struct *task) { savesegment(fs, task->thread.fsindex); savesegment(gs, task->thread.gsindex); - save_base_legacy(task, task->thread.fsindex, FS); - save_base_legacy(task, task->thread.gsindex, GS); + if (static_cpu_has(X86_FEATURE_FSGSBASE)) { + /* + * If FSGSBASE is enabled, we can't make any useful guesses + * about the base, and user code expects us to save the current + * value. Fortunately, reading the base directly is efficient. + */ + task->thread.fsbase = rdfsbase(); + task->thread.gsbase = __rdgsbase_inactive(); + } else { + save_base_legacy(task, task->thread.fsindex, FS); + save_base_legacy(task, task->thread.gsindex, GS); + } } -#if IS_ENABLED(CONFIG_KVM) /* * While a process is running,current->thread.fsbase and current->thread.gsbase - * may not match the corresponding CPU registers (see save_base_legacy()). KVM - * wants an efficient way to save and restore FSBASE and GSBASE. - * When FSGSBASE extensions are enabled, this will have to use RD{FS,GS}BASE. + * may not match the corresponding CPU registers (see save_base_legacy()). */ -void save_fsgs_for_kvm(void) +void current_save_fsgs(void) { + unsigned long flags; + + /* Interrupts need to be off for FSGSBASE */ + local_irq_save(flags); save_fsgs(current); + local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(save_fsgs_for_kvm); +#if IS_ENABLED(CONFIG_KVM) +EXPORT_SYMBOL_GPL(current_save_fsgs); #endif static __always_inline void loadseg(enum which_selector which, @@ -277,17 +340,52 @@ static __always_inline void load_seg_legacy(unsigned short prev_index, } } +/* + * Store prev's PKRU value and load next's PKRU value if they differ. PKRU + * is not XSTATE managed on context switch because that would require a + * lookup in the task's FPU xsave buffer and require to keep that updated + * in various places. + */ +static __always_inline void x86_pkru_load(struct thread_struct *prev, + struct thread_struct *next) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Stash the prev task's value: */ + prev->pkru = rdpkru(); + + /* + * PKRU writes are slightly expensive. Avoid them when not + * strictly necessary: + */ + if (prev->pkru != next->pkru) + wrpkru(next->pkru); +} + static __always_inline void x86_fsgsbase_load(struct thread_struct *prev, struct thread_struct *next) { - load_seg_legacy(prev->fsindex, prev->fsbase, - next->fsindex, next->fsbase, FS); - load_seg_legacy(prev->gsindex, prev->gsbase, - next->gsindex, next->gsbase, GS); + if (static_cpu_has(X86_FEATURE_FSGSBASE)) { + /* Update the FS and GS selectors if they could have changed. */ + if (unlikely(prev->fsindex || next->fsindex)) + loadseg(FS, next->fsindex); + if (unlikely(prev->gsindex || next->gsindex)) + loadseg(GS, next->gsindex); + + /* Update the bases. */ + wrfsbase(next->fsbase); + __wrgsbase_inactive(next->gsbase); + } else { + load_seg_legacy(prev->fsindex, prev->fsbase, + next->fsindex, next->fsbase, FS); + load_seg_legacy(prev->gsindex, prev->gsbase, + next->gsindex, next->gsbase, GS); + } } -static unsigned long x86_fsgsbase_read_task(struct task_struct *task, - unsigned short selector) +unsigned long x86_fsgsbase_read_task(struct task_struct *task, + unsigned short selector) { unsigned short idx = selector >> 3; unsigned long base; @@ -316,7 +414,7 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task, */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; - if (unlikely(idx >= ldt->nr_entries)) + if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); @@ -329,13 +427,44 @@ static unsigned long x86_fsgsbase_read_task(struct task_struct *task, return base; } +unsigned long x86_gsbase_read_cpu_inactive(void) +{ + unsigned long gsbase; + + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) { + unsigned long flags; + + local_irq_save(flags); + gsbase = __rdgsbase_inactive(); + local_irq_restore(flags); + } else { + rdmsrl(MSR_KERNEL_GS_BASE, gsbase); + } + + return gsbase; +} + +void x86_gsbase_write_cpu_inactive(unsigned long gsbase) +{ + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) { + unsigned long flags; + + local_irq_save(flags); + __wrgsbase_inactive(gsbase); + local_irq_restore(flags); + } else { + wrmsrl(MSR_KERNEL_GS_BASE, gsbase); + } +} + unsigned long x86_fsbase_read_task(struct task_struct *task) { unsigned long fsbase; if (task == current) fsbase = x86_fsbase_read_cpu(); - else if (task->thread.fsindex == 0) + else if (boot_cpu_has(X86_FEATURE_FSGSBASE) || + (task->thread.fsindex == 0)) fsbase = task->thread.fsbase; else fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex); @@ -349,7 +478,8 @@ unsigned long x86_gsbase_read_task(struct task_struct *task) if (task == current) gsbase = x86_gsbase_read_cpu_inactive(); - else if (task->thread.gsindex == 0) + else if (boot_cpu_has(X86_FEATURE_FSGSBASE) || + (task->thread.gsindex == 0)) gsbase = task->thread.gsbase; else gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex); @@ -405,11 +535,10 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) EXPORT_SYMBOL_GPL(start_thread); #ifdef CONFIG_COMPAT -void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp) +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32) { start_thread_common(regs, new_ip, new_sp, - test_thread_flag(TIF_X32) - ? __USER_CS : __USER32_CS, + x32 ? __USER_CS : __USER32_CS, __USER_DS, __USER_DS); } #endif @@ -424,17 +553,17 @@ void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp) * Kprobes not supported here. Set the probe on schedule instead. * Function graph tracer not supported too. */ +__no_kmsan_checks __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; struct fpu *prev_fpu = &prev->fpu; - struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && - this_cpu_read(irq_count) != -1); + this_cpu_read(hardirq_stack_inuse)); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_prepare(prev_fpu, cpu); @@ -483,13 +612,15 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) x86_fsgsbase_load(prev, next); + x86_pkru_load(prev, next); + /* * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); - switch_fpu_finish(next_fpu); + switch_fpu_finish(); /* Reload sp0. */ update_task_stack(next_p); @@ -535,16 +666,12 @@ void set_personality_64bit(void) /* inherit personality from parent */ /* Make sure to be in 64bit mode */ - clear_thread_flag(TIF_IA32); clear_thread_flag(TIF_ADDR32); - clear_thread_flag(TIF_X32); /* Pretend that this comes from a 64bit execve */ task_pt_regs(current)->orig_ax = __NR_execve; current_thread_info()->status &= ~TS_COMPAT; - - /* Ensure the corresponding mm is not marked. */ if (current->mm) - current->mm->context.ia32_compat = 0; + current->mm->context.flags = MM_CONTEXT_HAS_VSYSCALL; /* TBD: overwrites user setup. Should have two bits. But 64bit processes have always behaved this way, @@ -555,11 +682,10 @@ void set_personality_64bit(void) static void __set_personality_x32(void) { -#ifdef CONFIG_X86_X32 - clear_thread_flag(TIF_IA32); - set_thread_flag(TIF_X32); +#ifdef CONFIG_X86_X32_ABI if (current->mm) - current->mm->context.ia32_compat = TIF_X32; + current->mm->context.flags = 0; + current->personality &= ~READ_IMPLIES_EXEC; /* * in_32bit_syscall() uses the presence of the x32 syscall bit @@ -577,10 +703,14 @@ static void __set_personality_x32(void) static void __set_personality_ia32(void) { #ifdef CONFIG_IA32_EMULATION - set_thread_flag(TIF_IA32); - clear_thread_flag(TIF_X32); - if (current->mm) - current->mm->context.ia32_compat = TIF_IA32; + if (current->mm) { + /* + * uprobes applied to this MM need to know this and + * cannot use user_64bit_mode() at that time. + */ + current->mm->context.flags = MM_CONTEXT_UPROBE_IA32; + } + current->personality |= force_personality32; /* Prepare the first "return" to user space */ task_pt_regs(current)->orig_ax = __NR_ia32_execve; @@ -715,7 +845,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) ret = do_arch_prctl_64(current, option, arg2); if (ret == -EINVAL) - ret = do_arch_prctl_common(current, option, arg2); + ret = do_arch_prctl_common(option, arg2); return ret; } @@ -723,7 +853,7 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) #ifdef CONFIG_IA32_EMULATION COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) { - return do_arch_prctl_common(current, option, arg2); + return do_arch_prctl_common(option, arg2); } #endif |