Merge tag 'x86-fsgsbase-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fsgsbase from Thomas Gleixner:
 "Support for FSGSBASE. Almost 5 years after the first RFC to support
  it, this has been brought into a shape which is maintainable and
  actually works.

  This final version was done by Sasha Levin who took it up after Intel
  dropped the ball. Sasha discovered that the SGX (sic!) offerings out
  there ship rogue kernel modules enabling FSGSBASE behind the kernels
  back which opens an instantanious unpriviledged root hole.

  The FSGSBASE instructions provide a considerable speedup of the
  context switch path and enable user space to write GSBASE without
  kernel interaction. This enablement requires careful handling of the
  exception entries which go through the paranoid entry path as they
  can no longer rely on the assumption that user GSBASE is positive (as
  enforced via prctl() on non FSGSBASE enabled systemn).

  All other entries (syscalls, interrupts and exceptions) can still just
  utilize SWAPGS unconditionally when the entry comes from user space.
  Converting these entries to use FSGSBASE has no benefit as SWAPGS is
  only marginally slower than WRGSBASE and locating and retrieving the
  kernel GSBASE value is not a free operation either. The real benefit
  of RD/WRGSBASE is the avoidance of the MSR reads and writes.

  The changes come with appropriate selftests and have held up in field
  testing against the (sanitized) Graphene-SGX driver"

* tag 'x86-fsgsbase-2020-08-04' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  x86/fsgsbase: Fix Xen PV support
  x86/ptrace: Fix 32-bit PTRACE_SETREGS vs fsbase and gsbase
  selftests/x86/fsgsbase: Add a missing memory constraint
  selftests/x86/fsgsbase: Fix a comment in the ptrace_write_gsbase test
  selftests/x86: Add a syscall_arg_fault_64 test for negative GSBASE
  selftests/x86/fsgsbase: Test ptracer-induced GS base write with FSGSBASE
  selftests/x86/fsgsbase: Test GS selector on ptracer-induced GS base write
  Documentation/x86/64: Add documentation for GS/FS addressing mode
  x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2
  x86/cpu: Enable FSGSBASE on 64bit by default and add a chicken bit
  x86/entry/64: Handle FSGSBASE enabled paranoid entry/exit
  x86/entry/64: Introduce the FIND_PERCPU_BASE macro
  x86/entry/64: Switch CR3 before SWAPGS in paranoid entry
  x86/speculation/swapgs: Check FSGSBASE in enabling SWAPGS mitigation
  x86/process/64: Use FSGSBASE instructions on thread copy and ptrace
  x86/process/64: Use FSBSBASE in switch_to() if available
  x86/process/64: Make save_fsgs_for_kvm() ready for FSGSBASE
  x86/fsgsbase/64: Enable FSGSBASE instructions in helper functions
  x86/fsgsbase/64: Add intrinsics for FSGSBASE instructions
  x86/cpu: Add 'unsafe_fsgsbase' to enable CR4.FSGSBASE
  ...

1 files changed, 123 insertions, 16 deletions

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 04d201ad3a1e..d6f946707270 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -151,6 +151,56 @@ 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
@@ -199,22 +249,35 @@ 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,
@@ -279,14 +342,26 @@ 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);
+	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;
@@ -328,13 +403,44 @@ 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 (static_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 (static_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 (static_cpu_has(X86_FEATURE_FSGSBASE) ||
+		 (task->thread.fsindex == 0))
 		fsbase = task->thread.fsbase;
 	else
 		fsbase = x86_fsgsbase_read_task(task, task->thread.fsindex);
@@ -348,7 +454,8 @@ 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 (static_cpu_has(X86_FEATURE_FSGSBASE) ||
+		 (task->thread.gsindex == 0))
 		gsbase = task->thread.gsbase;
 	else
 		gsbase = x86_fsgsbase_read_task(task, task->thread.gsindex);