Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 pti updates from Thomas Gleixner:
 "This contains:

   - a PTI bugfix to avoid setting reserved CR3 bits when PCID is
     disabled. This seems to cause issues on a virtual machine at least
     and is incorrect according to the AMD manual.

   - a PTI bugfix which disables the perf BTS facility if PTI is
     enabled. The BTS AUX buffer is not globally visible and causes the
     CPU to fault when the mapping disappears on switching CR3 to user
     space. A full fix which restores BTS on PTI is non trivial and will
     be worked on.

   - PTI bugfixes for EFI and trusted boot which make sure that the user
     space visible page table entries have the NX bit cleared

   - removal of dead code in the PTI pagetable setup functions

   - add PTI documentation

   - add a selftest for vsyscall to verify that the kernel actually
     implements what it advertises.

   - a sysfs interface to expose vulnerability and mitigation
     information so there is a coherent way for users to retrieve the
     status.

   - the initial spectre_v2 mitigations, aka retpoline:

      + The necessary ASM thunk and compiler support

      + The ASM variants of retpoline and the conversion of affected ASM
        code

      + Make LFENCE serializing on AMD so it can be used as speculation
        trap

      + The RSB fill after vmexit

   - initial objtool support for retpoline

  As I said in the status mail this is the most of the set of patches
  which should go into 4.15 except two straight forward patches still on
  hold:

   - the retpoline add on of LFENCE which waits for ACKs

   - the RSB fill after context switch

  Both should be ready to go early next week and with that we'll have
  covered the major holes of spectre_v2 and go back to normality"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
  x86,perf: Disable intel_bts when PTI
  security/Kconfig: Correct the Documentation reference for PTI
  x86/pti: Fix !PCID and sanitize defines
  selftests/x86: Add test_vsyscall
  x86/retpoline: Fill return stack buffer on vmexit
  x86/retpoline/irq32: Convert assembler indirect jumps
  x86/retpoline/checksum32: Convert assembler indirect jumps
  x86/retpoline/xen: Convert Xen hypercall indirect jumps
  x86/retpoline/hyperv: Convert assembler indirect jumps
  x86/retpoline/ftrace: Convert ftrace assembler indirect jumps
  x86/retpoline/entry: Convert entry assembler indirect jumps
  x86/retpoline/crypto: Convert crypto assembler indirect jumps
  x86/spectre: Add boot time option to select Spectre v2 mitigation
  x86/retpoline: Add initial retpoline support
  objtool: Allow alternatives to be ignored
  objtool: Detect jumps to retpoline thunks
  x86/pti: Make unpoison of pgd for trusted boot work for real
  x86/alternatives: Fix optimize_nops() checking
  sysfs/cpu: Fix typos in vulnerability documentation
  x86/cpu/AMD: Use LFENCE_RDTSC in preference to MFENCE_RDTSC
  ...

8 files changed, 243 insertions, 14 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index dbaf14d69ebd..4817d743c263 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -344,9 +344,12 @@ done:
 static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
 {
 	unsigned long flags;
+	int i;
 
-	if (instr[0] != 0x90)
-		return;
+	for (i = 0; i < a->padlen; i++) {
+		if (instr[i] != 0x90)
+			return;
+	}
 
 	local_irq_save(flags);
 	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bcb75dc97d44..ea831c858195 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -829,8 +829,32 @@ static void init_amd(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_K8);
 
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
-		/* MFENCE stops RDTSC speculation */
-		set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		unsigned long long val;
+		int ret;
+
+		/*
+		 * A serializing LFENCE has less overhead than MFENCE, so
+		 * use it for execution serialization.  On families which
+		 * don't have that MSR, LFENCE is already serializing.
+		 * msr_set_bit() uses the safe accessors, too, even if the MSR
+		 * is not present.
+		 */
+		msr_set_bit(MSR_F10H_DECFG,
+			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+
+		/*
+		 * Verify that the MSR write was successful (could be running
+		 * under a hypervisor) and only then assume that LFENCE is
+		 * serializing.
+		 */
+		ret = rdmsrl_safe(MSR_F10H_DECFG, &val);
+		if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) {
+			/* A serializing LFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
+		} else {
+			/* MFENCE stops RDTSC speculation */
+			set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
+		}
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ba0b2424c9b0..e4dc26185aa7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -10,6 +10,10 @@
  */
 #include <linux/init.h>
 #include <linux/utsname.h>
+#include <linux/cpu.h>
+
+#include <asm/nospec-branch.h>
+#include <asm/cmdline.h>
 #include <asm/bugs.h>
 #include <asm/processor.h>
 #include <asm/processor-flags.h>
@@ -20,6 +24,8 @@
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 
+static void __init spectre_v2_select_mitigation(void);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -29,6 +35,9 @@ void __init check_bugs(void)
 		print_cpu_info(&boot_cpu_data);
 	}
 
+	/* Select the proper spectre mitigation before patching alternatives */
+	spectre_v2_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -60,3 +69,179 @@ void __init check_bugs(void)
 		set_memory_4k((unsigned long)__va(0), 1);
 #endif
 }
+
+/* The kernel command line selection */
+enum spectre_v2_mitigation_cmd {
+	SPECTRE_V2_CMD_NONE,
+	SPECTRE_V2_CMD_AUTO,
+	SPECTRE_V2_CMD_FORCE,
+	SPECTRE_V2_CMD_RETPOLINE,
+	SPECTRE_V2_CMD_RETPOLINE_GENERIC,
+	SPECTRE_V2_CMD_RETPOLINE_AMD,
+};
+
+static const char *spectre_v2_strings[] = {
+	[SPECTRE_V2_NONE]			= "Vulnerable",
+	[SPECTRE_V2_RETPOLINE_MINIMAL]		= "Vulnerable: Minimal generic ASM retpoline",
+	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
+	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
+	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+};
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 mitigation: " fmt
+
+static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE;
+
+static void __init spec2_print_if_insecure(const char *reason)
+{
+	if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s\n", reason);
+}
+
+static void __init spec2_print_if_secure(const char *reason)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		pr_info("%s\n", reason);
+}
+
+static inline bool retp_compiler(void)
+{
+	return __is_defined(RETPOLINE);
+}
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+	int len = strlen(opt);
+
+	return len == arglen && !strncmp(arg, opt, len);
+}
+
+static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
+{
+	char arg[20];
+	int ret;
+
+	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg,
+				  sizeof(arg));
+	if (ret > 0)  {
+		if (match_option(arg, ret, "off")) {
+			goto disable;
+		} else if (match_option(arg, ret, "on")) {
+			spec2_print_if_secure("force enabled on command line.");
+			return SPECTRE_V2_CMD_FORCE;
+		} else if (match_option(arg, ret, "retpoline")) {
+			spec2_print_if_insecure("retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE;
+		} else if (match_option(arg, ret, "retpoline,amd")) {
+			if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
+				pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n");
+				return SPECTRE_V2_CMD_AUTO;
+			}
+			spec2_print_if_insecure("AMD retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE_AMD;
+		} else if (match_option(arg, ret, "retpoline,generic")) {
+			spec2_print_if_insecure("generic retpoline selected on command line.");
+			return SPECTRE_V2_CMD_RETPOLINE_GENERIC;
+		} else if (match_option(arg, ret, "auto")) {
+			return SPECTRE_V2_CMD_AUTO;
+		}
+	}
+
+	if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+		return SPECTRE_V2_CMD_AUTO;
+disable:
+	spec2_print_if_insecure("disabled on command line.");
+	return SPECTRE_V2_CMD_NONE;
+}
+
+static void __init spectre_v2_select_mitigation(void)
+{
+	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
+	enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+
+	/*
+	 * If the CPU is not affected and the command line mode is NONE or AUTO
+	 * then nothing to do.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+	    (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+		return;
+
+	switch (cmd) {
+	case SPECTRE_V2_CMD_NONE:
+		return;
+
+	case SPECTRE_V2_CMD_FORCE:
+		/* FALLTRHU */
+	case SPECTRE_V2_CMD_AUTO:
+		goto retpoline_auto;
+
+	case SPECTRE_V2_CMD_RETPOLINE_AMD:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_amd;
+		break;
+	case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_generic;
+		break;
+	case SPECTRE_V2_CMD_RETPOLINE:
+		if (IS_ENABLED(CONFIG_RETPOLINE))
+			goto retpoline_auto;
+		break;
+	}
+	pr_err("kernel not compiled with retpoline; no mitigation available!");
+	return;
+
+retpoline_auto:
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+	retpoline_amd:
+		if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) {
+			pr_err("LFENCE not serializing. Switching to generic retpoline\n");
+			goto retpoline_generic;
+		}
+		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD :
+					 SPECTRE_V2_RETPOLINE_MINIMAL_AMD;
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD);
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+	} else {
+	retpoline_generic:
+		mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC :
+					 SPECTRE_V2_RETPOLINE_MINIMAL;
+		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
+	}
+
+	spectre_v2_enabled = mode;
+	pr_info("%s\n", spectre_v2_strings[mode]);
+}
+
+#undef pr_fmt
+
+#ifdef CONFIG_SYSFS
+ssize_t cpu_show_meltdown(struct device *dev,
+			  struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+		return sprintf(buf, "Not affected\n");
+	if (boot_cpu_has(X86_FEATURE_PTI))
+		return sprintf(buf, "Mitigation: PTI\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
+		return sprintf(buf, "Not affected\n");
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+		return sprintf(buf, "Not affected\n");
+
+	return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]);
+}
+#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 39d7ea865207..ef29ad001991 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -926,6 +926,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	if (c->x86_vendor != X86_VENDOR_AMD)
 		setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+	setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+
 	fpu__init_system(c);
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index b6c6468e10bc..4c8440de3355 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -8,6 +8,7 @@
 #include <asm/segment.h>
 #include <asm/export.h>
 #include <asm/ftrace.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CC_USING_FENTRY
 # define function_hook	__fentry__
@@ -197,7 +198,8 @@ ftrace_stub:
 	movl	0x4(%ebp), %edx
 	subl	$MCOUNT_INSN_SIZE, %eax
 
-	call	*ftrace_trace_function
+	movl	ftrace_trace_function, %ecx
+	CALL_NOSPEC %ecx
 
 	popl	%edx
 	popl	%ecx
@@ -241,5 +243,5 @@ return_to_handler:
 	movl	%eax, %ecx
 	popl	%edx
 	popl	%eax
-	jmp	*%ecx
+	JMP_NOSPEC %ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index c832291d948a..7cb8ba08beb9 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -7,7 +7,7 @@
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
-
+#include <asm/nospec-branch.h>
 
 	.code64
 	.section .entry.text, "ax"
@@ -286,8 +286,8 @@ trace:
 	 * ip and parent ip are used and the list function is called when
 	 * function tracing is enabled.
 	 */
-	call   *ftrace_trace_function
-
+	movq ftrace_trace_function, %r8
+	CALL_NOSPEC %r8
 	restore_mcount_regs
 
 	jmp fgraph_trace
@@ -329,5 +329,5 @@ GLOBAL(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 	addq $24, %rsp
-	jmp *%rdi
+	JMP_NOSPEC %rdi
 #endif
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index a83b3346a0e1..c1bdbd3d3232 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 
 #include <asm/apic.h>
+#include <asm/nospec-branch.h>
 
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 
@@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 static void call_on_stack(void *func, void *stack)
 {
 	asm volatile("xchgl	%%ebx,%%esp	\n"
-		     "call	*%%edi		\n"
+		     CALL_NOSPEC
 		     "movl	%%ebx,%%esp	\n"
 		     : "=b" (stack)
 		     : "0" (stack),
-		       "D"(func)
+		       [thunk_target] "D"(func)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
@@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 		call_on_stack(print_stack_overflow, isp);
 
 	asm volatile("xchgl	%%ebx,%%esp	\n"
-		     "call	*%%edi		\n"
+		     CALL_NOSPEC
 		     "movl	%%ebx,%%esp	\n"
 		     : "=a" (arg1), "=b" (isp)
 		     :  "0" (desc),   "1" (isp),
-			"D" (desc->handle_irq)
+			[thunk_target] "D" (desc->handle_irq)
 		     : "memory", "cc", "ecx");
 	return 1;
 }
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index a4eb27918ceb..a2486f444073 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -138,6 +138,17 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
 		return -1;
 	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
 	pte_unmap(pte);
+
+	/*
+	 * PTI poisons low addresses in the kernel page tables in the
+	 * name of making them unusable for userspace.  To execute
+	 * code at such a low address, the poison must be cleared.
+	 *
+	 * Note: 'pgd' actually gets set in p4d_alloc() _or_
+	 * pud_alloc() depending on 4/5-level paging.
+	 */
+	pgd->pgd &= ~_PAGE_NX;
+
 	return 0;
 }