1 files changed, 171 insertions, 48 deletions

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9eb448c7859d..0e0b4288a4b2 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -54,15 +54,14 @@
 #include <asm/vdso.h>
 #include <asm/intel_rdt_sched.h>
 #include <asm/unistd.h>
+#include <asm/fsgsbase.h>
 #ifdef CONFIG_IA32_EMULATION
 /* Not included via unistd.h */
 #include <asm/unistd_32_ia32.h>
 #endif
 
-__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
-
 /* Prints also some state that isn't saved in the pt_regs */
-void __show_regs(struct pt_regs *regs, int all)
+void __show_regs(struct pt_regs *regs, enum show_regs_mode mode)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
 	unsigned long d0, d1, d2, d3, d6, d7;
@@ -87,9 +86,17 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
 	       regs->r13, regs->r14, regs->r15);
 
-	if (!all)
+	if (mode == SHOW_REGS_SHORT)
 		return;
 
+	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);
+		return;
+	}
+
 	asm("movl %%ds,%0" : "=r" (ds));
 	asm("movl %%cs,%0" : "=r" (cs));
 	asm("movl %%es,%0" : "=r" (es));
@@ -205,6 +212,20 @@ static __always_inline void save_fsgs(struct task_struct *task)
 	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.
+ */
+void save_fsgs_for_kvm(void)
+{
+	save_fsgs(current);
+}
+EXPORT_SYMBOL_GPL(save_fsgs_for_kvm);
+#endif
+
 static __always_inline void loadseg(enum which_selector which,
 				    unsigned short sel)
 {
@@ -264,6 +285,138 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
 	}
 }
 
+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);
+}
+
+static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
+					    unsigned short selector)
+{
+	unsigned short idx = selector >> 3;
+	unsigned long base;
+
+	if (likely((selector & SEGMENT_TI_MASK) == 0)) {
+		if (unlikely(idx >= GDT_ENTRIES))
+			return 0;
+
+		/*
+		 * There are no user segments in the GDT with nonzero bases
+		 * other than the TLS segments.
+		 */
+		if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
+			return 0;
+
+		idx -= GDT_ENTRY_TLS_MIN;
+		base = get_desc_base(&task->thread.tls_array[idx]);
+	} else {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+		struct ldt_struct *ldt;
+
+		/*
+		 * If performance here mattered, we could protect the LDT
+		 * with RCU.  This is a slow path, though, so we can just
+		 * take the mutex.
+		 */
+		mutex_lock(&task->mm->context.lock);
+		ldt = task->mm->context.ldt;
+		if (unlikely(idx >= ldt->nr_entries))
+			base = 0;
+		else
+			base = get_desc_base(ldt->entries + idx);
+		mutex_unlock(&task->mm->context.lock);
+#else
+		base = 0;
+#endif
+	}
+
+	return base;
+}
+
+void x86_fsbase_write_cpu(unsigned long fsbase)
+{
+	/*
+	 * Set the selector to 0 as a notion, that the segment base is
+	 * overwritten, which will be checked for skipping the segment load
+	 * during context switch.
+	 */
+	loadseg(FS, 0);
+	wrmsrl(MSR_FS_BASE, fsbase);
+}
+
+void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
+{
+	/* Set the selector to 0 for the same reason as %fs above. */
+	loadseg(GS, 0);
+	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)
+		fsbase = task->thread.fsbase;
+	else
+		fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex);
+
+	return fsbase;
+}
+
+unsigned long x86_gsbase_read_task(struct task_struct *task)
+{
+	unsigned long gsbase;
+
+	if (task == current)
+		gsbase = x86_gsbase_read_cpu_inactive();
+	else if (task->thread.gsindex == 0)
+		gsbase = task->thread.gsbase;
+	else
+		gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex);
+
+	return gsbase;
+}
+
+int x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase)
+{
+	/*
+	 * Not strictly needed for %fs, but do it for symmetry
+	 * with %gs
+	 */
+	if (unlikely(fsbase >= TASK_SIZE_MAX))
+		return -EPERM;
+
+	preempt_disable();
+	task->thread.fsbase = fsbase;
+	if (task == current)
+		x86_fsbase_write_cpu(fsbase);
+	task->thread.fsindex = 0;
+	preempt_enable();
+
+	return 0;
+}
+
+int x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase)
+{
+	if (unlikely(gsbase >= TASK_SIZE_MAX))
+		return -EPERM;
+
+	preempt_disable();
+	task->thread.gsbase = gsbase;
+	if (task == current)
+		x86_gsbase_write_cpu_inactive(gsbase);
+	task->thread.gsindex = 0;
+	preempt_enable();
+
+	return 0;
+}
+
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
@@ -370,6 +523,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 	start_thread_common(regs, new_ip, new_sp,
 			    __USER_CS, __USER_DS, 0);
 }
+EXPORT_SYMBOL_GPL(start_thread);
 
 #ifdef CONFIG_COMPAT
 void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
@@ -450,10 +604,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (unlikely(next->ds | prev->ds))
 		loadsegment(ds, next->ds);
 
-	load_seg_legacy(prev->fsindex, prev->fsbase,
-			next->fsindex, next->fsbase, FS);
-	load_seg_legacy(prev->gsindex, prev->gsbase,
-			next->gsindex, next->gsbase, GS);
+	x86_fsgsbase_load(prev, next);
 
 	switch_fpu_finish(next_fpu, cpu);
 
@@ -464,7 +615,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
@@ -528,6 +679,7 @@ void set_personality_64bit(void)
 	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)
@@ -549,10 +701,10 @@ static void __set_personality_x32(void)
 		current->mm->context.ia32_compat = TIF_X32;
 	current->personality &= ~READ_IMPLIES_EXEC;
 	/*
-	 * in_compat_syscall() uses the presence of the x32 syscall bit
+	 * in_32bit_syscall() uses the presence of the x32 syscall bit
 	 * flag to determine compat status.  The x86 mmap() code relies on
 	 * the syscall bitness so set x32 syscall bit right here to make
-	 * in_compat_syscall() work during exec().
+	 * in_32bit_syscall() work during exec().
 	 *
 	 * Pretend to come from a x32 execve.
 	 */
@@ -603,54 +755,25 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 {
 	int ret = 0;
-	int doit = task == current;
-	int cpu;
 
 	switch (option) {
-	case ARCH_SET_GS:
-		if (arg2 >= TASK_SIZE_MAX)
-			return -EPERM;
-		cpu = get_cpu();
-		task->thread.gsindex = 0;
-		task->thread.gsbase = arg2;
-		if (doit) {
-			load_gs_index(0);
-			ret = wrmsrl_safe(MSR_KERNEL_GS_BASE, arg2);
-		}
-		put_cpu();
+	case ARCH_SET_GS: {
+		ret = x86_gsbase_write_task(task, arg2);
 		break;
-	case ARCH_SET_FS:
-		/* Not strictly needed for fs, but do it for symmetry
-		   with gs */
-		if (arg2 >= TASK_SIZE_MAX)
-			return -EPERM;
-		cpu = get_cpu();
-		task->thread.fsindex = 0;
-		task->thread.fsbase = arg2;
-		if (doit) {
-			/* set the selector to 0 to not confuse __switch_to */
-			loadsegment(fs, 0);
-			ret = wrmsrl_safe(MSR_FS_BASE, arg2);
-		}
-		put_cpu();
+	}
+	case ARCH_SET_FS: {
+		ret = x86_fsbase_write_task(task, arg2);
 		break;
+	}
 	case ARCH_GET_FS: {
-		unsigned long base;
+		unsigned long base = x86_fsbase_read_task(task);
 
-		if (doit)
-			rdmsrl(MSR_FS_BASE, base);
-		else
-			base = task->thread.fsbase;
 		ret = put_user(base, (unsigned long __user *)arg2);
 		break;
 	}
 	case ARCH_GET_GS: {
-		unsigned long base;
+		unsigned long base = x86_gsbase_read_task(task);
 
-		if (doit)
-			rdmsrl(MSR_KERNEL_GS_BASE, base);
-		else
-			base = task->thread.gsbase;
 		ret = put_user(base, (unsigned long __user *)arg2);
 		break;
 	}