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

Pull x86 asm changes from Ingo Molnar:
 "The biggest changes in this cycle were:

   - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC)
     primitives.  (Andy Lutomirski)

   - Add new, comprehensible entry and exit handlers written in C.
     (Andy Lutomirski)

   - vm86 mode cleanups and fixes.  (Brian Gerst)

   - 32-bit compat code cleanups.  (Brian Gerst)

  The amount of simplification in low level assembly code is already
  palpable:

     arch/x86/entry/entry_32.S                          | 130 +----
     arch/x86/entry/entry_64.S                          | 197 ++-----

  but more simplifications are planned.

  There's also the usual laudry mix of low level changes - see the
  changelog for details"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits)
  x86/asm: Drop repeated macro of X86_EFLAGS_AC definition
  x86/asm/msr: Make wrmsrl() a function
  x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer
  x86/asm: Add MONITORX/MWAITX instruction support
  x86/traps: Weaken context tracking entry assertions
  x86/asm/tsc: Add rdtscll() merge helper
  selftests/x86: Add syscall_nt selftest
  selftests/x86: Disable sigreturn_64
  x86/vdso: Emit a GNU hash
  x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks
  x86/entry/32: Migrate to C exit path
  x86/entry/32: Remove 32-bit syscall audit optimizations
  x86/vm86: Rename vm86->v86flags and v86mask
  x86/vm86: Rename vm86->vm86_info to user_vm86
  x86/vm86: Clean up vm86.h includes
  x86/vm86: Move the vm86 IRQ definitions to vm86.h
  x86/vm86: Use the normal pt_regs area for vm86
  x86/vm86: Eliminate 'struct kernel_vm86_struct'
  x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86'
  x86/vm86: Move vm86 fields out of 'thread_struct'
  ...

6 files changed, 893 insertions, 14 deletions

diff --git a/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c b/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
index 5224ee5..6ff8383 100644
--- a/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
+++ b/tools/power/cpupower/debug/kernel/cpufreq-test_tsc.c
@@ -81,11 +81,11 @@ static int __init cpufreq_test_tsc(void)
 
 	printk(KERN_DEBUG "start--> \n");
 	then = read_pmtmr();
-        rdtscll(then_tsc);
+	then_tsc = rdtsc();
 	for (i=0;i<20;i++) {
 		mdelay(100);
 		now = read_pmtmr();
-		rdtscll(now_tsc);
+		now_tsc = rdtsc();
 		diff = (now - then) & 0xFFFFFF;
 		diff_tsc = now_tsc - then_tsc;
 		printk(KERN_DEBUG "t1: %08u t2: %08u diff_pmtmr: %08u diff_tsc: %016llu\n", then, now, diff, diff_tsc);
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index caa60d5..29089b2 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,8 +4,8 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs
-TARGETS_C_32BIT_ONLY := entry_from_vm86
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c
index 5c38a18..9a43a59 100644
--- a/tools/testing/selftests/x86/entry_from_vm86.c
+++ b/tools/testing/selftests/x86/entry_from_vm86.c
@@ -28,6 +28,55 @@
 static unsigned long load_addr = 0x10000;
 static int nerrs = 0;
 
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static sig_atomic_t got_signal;
+
+static void sighandler(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_VM ||
+	    (ctx->uc_mcontext.gregs[REG_CS] & 3) != 3) {
+		printf("[FAIL]\tSignal frame should not reflect vm86 mode\n");
+		nerrs++;
+	}
+
+	const char *signame;
+	if (sig == SIGSEGV)
+		signame = "SIGSEGV";
+	else if (sig == SIGILL)
+		signame = "SIGILL";
+	else
+		signame = "unexpected signal";
+
+	printf("[INFO]\t%s: FLAGS = 0x%lx, CS = 0x%hx\n", signame,
+	       (unsigned long)ctx->uc_mcontext.gregs[REG_EFL],
+	       (unsigned short)ctx->uc_mcontext.gregs[REG_CS]);
+
+	got_signal = 1;
+}
+
 asm (
 	".pushsection .rodata\n\t"
 	".type vmcode_bound, @object\n\t"
@@ -38,6 +87,14 @@ asm (
 	"int3\n\t"
 	"vmcode_sysenter:\n\t"
 	"sysenter\n\t"
+	"vmcode_syscall:\n\t"
+	"syscall\n\t"
+	"vmcode_sti:\n\t"
+	"sti\n\t"
+	"vmcode_int3:\n\t"
+	"int3\n\t"
+	"vmcode_int80:\n\t"
+	"int $0x80\n\t"
 	".size vmcode, . - vmcode\n\t"
 	"end_vmcode:\n\t"
 	".code32\n\t"
@@ -45,9 +102,12 @@ asm (
 	);
 
 extern unsigned char vmcode[], end_vmcode[];
-extern unsigned char vmcode_bound[], vmcode_sysenter[];
+extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[],
+	vmcode_sti[], vmcode_int3[], vmcode_int80[];
 
-static void do_test(struct vm86plus_struct *v86, unsigned long eip,
+/* Returns false if the test was skipped. */
+static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
+		    unsigned int rettype, unsigned int retarg,
 		    const char *text)
 {
 	long ret;
@@ -58,7 +118,7 @@ static void do_test(struct vm86plus_struct *v86, unsigned long eip,
 
 	if (ret == -1 && errno == ENOSYS) {
 		printf("[SKIP]\tvm86 not supported\n");
-		return;
+		return false;
 	}
 
 	if (VM86_TYPE(ret) == VM86_INTx) {
@@ -73,13 +133,30 @@ static void do_test(struct vm86plus_struct *v86, unsigned long eip,
 		else
 			sprintf(trapname, "%d", trapno);
 
-		printf("[OK]\tExited vm86 mode due to #%s\n", trapname);
+		printf("[INFO]\tExited vm86 mode due to #%s\n", trapname);
 	} else if (VM86_TYPE(ret) == VM86_UNKNOWN) {
-		printf("[OK]\tExited vm86 mode due to unhandled GP fault\n");
+		printf("[INFO]\tExited vm86 mode due to unhandled GP fault\n");
+	} else if (VM86_TYPE(ret) == VM86_TRAP) {
+		printf("[INFO]\tExited vm86 mode due to a trap (arg=%ld)\n",
+		       VM86_ARG(ret));
+	} else if (VM86_TYPE(ret) == VM86_SIGNAL) {
+		printf("[INFO]\tExited vm86 mode due to a signal\n");
+	} else if (VM86_TYPE(ret) == VM86_STI) {
+		printf("[INFO]\tExited vm86 mode due to STI\n");
 	} else {
-		printf("[OK]\tExited vm86 mode due to type %ld, arg %ld\n",
+		printf("[INFO]\tExited vm86 mode due to type %ld, arg %ld\n",
 		       VM86_TYPE(ret), VM86_ARG(ret));
 	}
+
+	if (rettype == -1 ||
+	    (VM86_TYPE(ret) == rettype && VM86_ARG(ret) == retarg)) {
+		printf("[OK]\tReturned correctly\n");
+	} else {
+		printf("[FAIL]\tIncorrect return reason\n");
+		nerrs++;
+	}
+
+	return true;
 }
 
 int main(void)
@@ -105,10 +182,52 @@ int main(void)
 	assert((v86.regs.cs & 3) == 0);	/* Looks like RPL = 0 */
 
 	/* #BR -- should deliver SIG??? */
-	do_test(&v86, vmcode_bound - vmcode, "#BR");
-
-	/* SYSENTER -- should cause #GP or #UD depending on CPU */
-	do_test(&v86, vmcode_sysenter - vmcode, "SYSENTER");
+	do_test(&v86, vmcode_bound - vmcode, VM86_INTx, 5, "#BR");
+
+	/*
+	 * SYSENTER -- should cause #GP or #UD depending on CPU.
+	 * Expected return type -1 means that we shouldn't validate
+	 * the vm86 return value.  This will avoid problems on non-SEP
+	 * CPUs.
+	 */
+	sethandler(SIGILL, sighandler, 0);
+	do_test(&v86, vmcode_sysenter - vmcode, -1, 0, "SYSENTER");
+	clearhandler(SIGILL);
+
+	/*
+	 * SYSCALL would be a disaster in VM86 mode.  Fortunately,
+	 * there is no kernel that both enables SYSCALL and sets
+	 * EFER.SCE, so it's #UD on all systems.  But vm86 is
+	 * buggy (or has a "feature"), so the SIGILL will actually
+	 * be delivered.
+	 */
+	sethandler(SIGILL, sighandler, 0);
+	do_test(&v86, vmcode_syscall - vmcode, VM86_SIGNAL, 0, "SYSCALL");
+	clearhandler(SIGILL);
+
+	/* STI with VIP set */
+	v86.regs.eflags |= X86_EFLAGS_VIP;
+	v86.regs.eflags &= ~X86_EFLAGS_IF;
+	do_test(&v86, vmcode_sti - vmcode, VM86_STI, 0, "STI with VIP set");
+
+	/* INT3 -- should cause #BP */
+	do_test(&v86, vmcode_int3 - vmcode, VM86_TRAP, 3, "INT3");
+
+	/* INT80 -- should exit with "INTx 0x80" */
+	v86.regs.eax = (unsigned int)-1;
+	do_test(&v86, vmcode_int80 - vmcode, VM86_INTx, 0x80, "int80");
+
+	/* Execute a null pointer */
+	v86.regs.cs = 0;
+	v86.regs.ss = 0;
+	sethandler(SIGSEGV, sighandler, 0);
+	got_signal = 0;
+	if (do_test(&v86, 0, VM86_SIGNAL, 0, "Execute null pointer") &&
+	    !got_signal) {
+		printf("[FAIL]\tDid not receive SIGSEGV\n");
+		nerrs++;
+	}
+	clearhandler(SIGSEGV);
 
 	return (nerrs == 0 ? 0 : 1);
 }
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
new file mode 100644
index 0000000..31a3035
--- /dev/null
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -0,0 +1,576 @@
+/*
+ * ldt_gdt.c - Test cases for LDT and GDT access
+ * Copyright (c) 2015 Andrew Lutomirski
+ */
+
+#define _GNU_SOURCE
+#include <err.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <signal.h>
+#include <setjmp.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <asm/ldt.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sched.h>
+#include <linux/futex.h>
+
+#define AR_ACCESSED		(1<<8)
+
+#define AR_TYPE_RODATA		(0 * (1<<9))
+#define AR_TYPE_RWDATA		(1 * (1<<9))
+#define AR_TYPE_RODATA_EXPDOWN	(2 * (1<<9))
+#define AR_TYPE_RWDATA_EXPDOWN	(3 * (1<<9))
+#define AR_TYPE_XOCODE		(4 * (1<<9))
+#define AR_TYPE_XRCODE		(5 * (1<<9))
+#define AR_TYPE_XOCODE_CONF	(6 * (1<<9))
+#define AR_TYPE_XRCODE_CONF	(7 * (1<<9))
+
+#define AR_DPL3			(3 * (1<<13))
+
+#define AR_S			(1 << 12)
+#define AR_P			(1 << 15)
+#define AR_AVL			(1 << 20)
+#define AR_L			(1 << 21)
+#define AR_DB			(1 << 22)
+#define AR_G			(1 << 23)
+
+static int nerrs;
+
+static void check_invalid_segment(uint16_t index, int ldt)
+{
+	uint32_t has_limit = 0, has_ar = 0, limit, ar;
+	uint32_t selector = (index << 3) | (ldt << 2) | 3;
+
+	asm ("lsl %[selector], %[limit]\n\t"
+	     "jnz 1f\n\t"
+	     "movl $1, %[has_limit]\n\t"
+	     "1:"
+	     : [limit] "=r" (limit), [has_limit] "+rm" (has_limit)
+	     : [selector] "r" (selector));
+	asm ("larl %[selector], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "movl $1, %[has_ar]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [has_ar] "+rm" (has_ar)
+	     : [selector] "r" (selector));
+
+	if (has_limit || has_ar) {
+		printf("[FAIL]\t%s entry %hu is valid but should be invalid\n",
+		       (ldt ? "LDT" : "GDT"), index);
+		nerrs++;
+	} else {
+		printf("[OK]\t%s entry %hu is invalid\n",
+		       (ldt ? "LDT" : "GDT"), index);
+	}
+}
+
+static void check_valid_segment(uint16_t index, int ldt,
+				uint32_t expected_ar, uint32_t expected_limit,
+				bool verbose)
+{
+	uint32_t has_limit = 0, has_ar = 0, limit, ar;
+	uint32_t selector = (index << 3) | (ldt << 2) | 3;
+
+	asm ("lsl %[selector], %[limit]\n\t"
+	     "jnz 1f\n\t"
+	     "movl $1, %[has_limit]\n\t"
+	     "1:"
+	     : [limit] "=r" (limit), [has_limit] "+rm" (has_limit)
+	     : [selector] "r" (selector));
+	asm ("larl %[selector], %[ar]\n\t"
+	     "jnz 1f\n\t"
+	     "movl $1, %[has_ar]\n\t"
+	     "1:"
+	     : [ar] "=r" (ar), [has_ar] "+rm" (has_ar)
+	     : [selector] "r" (selector));
+
+	if (!has_limit || !has_ar) {
+		printf("[FAIL]\t%s entry %hu is invalid but should be valid\n",
+		       (ldt ? "LDT" : "GDT"), index);
+		nerrs++;
+		return;
+	}
+
+	if (ar != expected_ar) {
+		printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n",
+		       (ldt ? "LDT" : "GDT"), index, ar, expected_ar);
+		nerrs++;
+	} else if (limit != expected_limit) {
+		printf("[FAIL]\t%s entry %hu has limit 0x%08X but expected 0x%08X\n",
+		       (ldt ? "LDT" : "GDT"), index, limit, expected_limit);
+		nerrs++;
+	} else if (verbose) {
+		printf("[OK]\t%s entry %hu has AR 0x%08X and limit 0x%08X\n",
+		       (ldt ? "LDT" : "GDT"), index, ar, limit);
+	}
+}
+
+static bool install_valid_mode(const struct user_desc *desc, uint32_t ar,
+			       bool oldmode)
+{
+	int ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11,
+			  desc, sizeof(*desc));
+	if (ret < -1)
+		errno = -ret;
+	if (ret == 0) {
+		uint32_t limit = desc->limit;
+		if (desc->limit_in_pages)
+			limit = (limit << 12) + 4095;
+		check_valid_segment(desc->entry_number, 1, ar, limit, true);
+		return true;
+	} else if (errno == ENOSYS) {
+		printf("[OK]\tmodify_ldt returned -ENOSYS\n");
+		return false;
+	} else {
+		if (desc->seg_32bit) {
+			printf("[FAIL]\tUnexpected modify_ldt failure %d\n",
+			       errno);
+			nerrs++;
+			return false;
+		} else {
+			printf("[OK]\tmodify_ldt rejected 16 bit segment\n");
+			return false;
+		}
+	}
+}
+
+static bool install_valid(const struct user_desc *desc, uint32_t ar)
+{
+	return install_valid_mode(desc, ar, false);
+}
+
+static void install_invalid(const struct user_desc *desc, bool oldmode)
+{
+	int ret = syscall(SYS_modify_ldt, oldmode ? 1 : 0x11,
+			  desc, sizeof(*desc));
+	if (ret < -1)
+		errno = -ret;
+	if (ret == 0) {
+		check_invalid_segment(desc->entry_number, 1);
+	} else if (errno == ENOSYS) {
+		printf("[OK]\tmodify_ldt returned -ENOSYS\n");
+	} else {
+		if (desc->seg_32bit) {
+			printf("[FAIL]\tUnexpected modify_ldt failure %d\n",
+			       errno);
+			nerrs++;
+		} else {
+			printf("[OK]\tmodify_ldt rejected 16 bit segment\n");
+		}
+	}
+}
+
+static int safe_modify_ldt(int func, struct user_desc *ptr,
+			   unsigned long bytecount)
+{
+	int ret = syscall(SYS_modify_ldt, 0x11, ptr, bytecount);
+	if (ret < -1)
+		errno = -ret;
+	return ret;
+}
+
+static void fail_install(struct user_desc *desc)
+{
+	if (safe_modify_ldt(0x11, desc, sizeof(*desc)) == 0) {
+		printf("[FAIL]\tmodify_ldt accepted a bad descriptor\n");
+		nerrs++;
+	} else if (errno == ENOSYS) {
+		printf("[OK]\tmodify_ldt returned -ENOSYS\n");
+	} else {
+		printf("[OK]\tmodify_ldt failure %d\n", errno);
+	}
+}
+
+static void do_simple_tests(void)
+{
+	struct user_desc desc = {
+		.entry_number    = 0,
+		.base_addr       = 0,
+		.limit           = 10,
+		.seg_32bit       = 1,
+		.contents        = 2, /* Code, not conforming */
+		.read_exec_only  = 0,
+		.limit_in_pages  = 0,
+		.seg_not_present = 0,
+		.useable         = 0
+	};
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB);
+
+	desc.limit_in_pages = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_P | AR_DB | AR_G);
+
+	check_invalid_segment(1, 1);
+
+	desc.entry_number = 2;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_P | AR_DB | AR_G);
+
+	check_invalid_segment(1, 1);
+
+	desc.base_addr = 0xf0000000;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_P | AR_DB | AR_G);
+
+	desc.useable = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_P | AR_DB | AR_G | AR_AVL);
+
+	desc.seg_not_present = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_DB | AR_G | AR_AVL);
+
+	desc.seg_32bit = 0;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_G | AR_AVL);
+
+	desc.seg_32bit = 1;
+	desc.contents = 0;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA |
+		      AR_S | AR_DB | AR_G | AR_AVL);
+
+	desc.read_exec_only = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA |
+		      AR_S | AR_DB | AR_G | AR_AVL);
+
+	desc.contents = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA_EXPDOWN |
+		      AR_S | AR_DB | AR_G | AR_AVL);
+
+	desc.read_exec_only = 0;
+	desc.limit_in_pages = 0;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA_EXPDOWN |
+		      AR_S | AR_DB | AR_AVL);
+
+	desc.contents = 3;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE_CONF |
+		      AR_S | AR_DB | AR_AVL);
+
+	desc.read_exec_only = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XOCODE_CONF |
+		      AR_S | AR_DB | AR_AVL);
+
+	desc.read_exec_only = 0;
+	desc.contents = 2;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE |
+		      AR_S | AR_DB | AR_AVL);
+
+	desc.read_exec_only = 1;
+
+#ifdef __x86_64__
+	desc.lm = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XOCODE |
+		      AR_S | AR_DB | AR_AVL);
+	desc.lm = 0;
+#endif
+
+	bool entry1_okay = install_valid(&desc, AR_DPL3 | AR_TYPE_XOCODE |
+					 AR_S | AR_DB | AR_AVL);
+
+	if (entry1_okay) {
+		printf("[RUN]\tTest fork\n");
+		pid_t child = fork();
+		if (child == 0) {
+			nerrs = 0;
+			check_valid_segment(desc.entry_number, 1,
+					    AR_DPL3 | AR_TYPE_XOCODE |
+					    AR_S | AR_DB | AR_AVL, desc.limit,
+					    true);
+			check_invalid_segment(1, 1);
+			exit(nerrs ? 1 : 0);
+		} else {
+			int status;
+			if (waitpid(child, &status, 0) != child ||
+			    !WIFEXITED(status)) {
+				printf("[FAIL]\tChild died\n");
+				nerrs++;
+			} else if (WEXITSTATUS(status) != 0) {
+				printf("[FAIL]\tChild failed\n");
+				nerrs++;
+			} else {
+				printf("[OK]\tChild succeeded\n");
+			}
+		}
+
+		printf("[RUN]\tTest size\n");
+		int i;
+		for (i = 0; i < 8192; i++) {
+			desc.entry_number = i;
+			desc.limit = i;
+			if (safe_modify_ldt(0x11, &desc, sizeof(desc)) != 0) {
+				printf("[FAIL]\tFailed to install entry %d\n", i);
+				nerrs++;
+				break;
+			}
+		}
+		for (int j = 0; j < i; j++) {
+			check_valid_segment(j, 1, AR_DPL3 | AR_TYPE_XOCODE |
+					    AR_S | AR_DB | AR_AVL, j, false);
+		}
+		printf("[DONE]\tSize test\n");
+	} else {
+		printf("[SKIP]\tSkipping fork and size tests because we have no LDT\n");
+	}
+
+	/* Test entry_number too high. */
+	desc.entry_number = 8192;
+	fail_install(&desc);
+
+	/* Test deletion and actions mistakeable for deletion. */
+	memset(&desc, 0, sizeof(desc));
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P);
+
+	desc.seg_not_present = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S);
+
+	desc.seg_not_present = 0;
+	desc.read_exec_only = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S | AR_P);
+
+	desc.read_exec_only = 0;
+	desc.seg_not_present = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S);
+
+	desc.read_exec_only = 1;
+	desc.limit = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S);
+
+	desc.limit = 0;
+	desc.base_addr = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RODATA | AR_S);
+
+	desc.base_addr = 0;
+	install_invalid(&desc, false);
+
+	desc.seg_not_present = 0;
+	desc.read_exec_only = 0;
+	desc.seg_32bit = 1;
+	install_valid(&desc, AR_DPL3 | AR_TYPE_RWDATA | AR_S | AR_P | AR_DB);
+	install_invalid(&desc, true);
+}
+
+/*
+ * 0: thread is idle
+ * 1: thread armed
+ * 2: thread should clear LDT entry 0
+ * 3: thread should exit
+ */
+static volatile unsigned int ftx;
+
+static void *threadproc(void *ctx)
+{
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(1, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		err(1, "sched_setaffinity to CPU 1");	/* should never fail */
+
+	while (1) {
+		syscall(SYS_futex, &ftx, FUTEX_WAIT, 0, NULL, NULL, 0);
+		while (ftx != 2) {
+			if (ftx >= 3)
+				return NULL;
+		}
+
+		/* clear LDT entry 0 */
+		const struct user_desc desc = {};
+		if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) != 0)
+			err(1, "modify_ldt");
+
+		/* If ftx == 2, set it to zero.  If ftx == 100, quit. */
+		unsigned int x = -2;
+		asm volatile ("lock xaddl %[x], %[ftx]" :
+			      [x] "+r" (x), [ftx] "+m" (ftx));
+		if (x != 2)
+			return NULL;
+	}
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
+{
+	siglongjmp(jmpbuf, 1);
+}
+
+static void do_multicpu_tests(void)
+{
+	cpu_set_t cpuset;
+	pthread_t thread;
+	int failures = 0, iters = 5, i;
+	unsigned short orig_ss;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(1, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) {
+		printf("[SKIP]\tCannot set affinity to CPU 1\n");
+		return;
+	}
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) {
+		printf("[SKIP]\tCannot set affinity to CPU 0\n");
+		return;
+	}
+
+	sethandler(SIGSEGV, sigsegv, 0);
+#ifdef __i386__
+	/* True 32-bit kernels send SIGILL instead of SIGSEGV on IRET faults. */
+	sethandler(SIGILL, sigsegv, 0);
+#endif
+
+	printf("[RUN]\tCross-CPU LDT invalidation\n");
+
+	if (pthread_create(&thread, 0, threadproc, 0) != 0)
+		err(1, "pthread_create");
+
+	asm volatile ("mov %%ss, %0" : "=rm" (orig_ss));
+
+	for (i = 0; i < 5; i++) {
+		if (sigsetjmp(jmpbuf, 1) != 0)
+			continue;
+
+		/* Make sure the thread is ready after the last test. */
+		while (ftx != 0)
+			;
+
+		struct user_desc desc = {
+			.entry_number    = 0,
+			.base_addr       = 0,
+			.limit           = 0xfffff,
+			.seg_32bit       = 1,
+			.contents        = 0, /* Data */
+			.read_exec_only  = 0,
+			.limit_in_pages  = 1,
+			.seg_not_present = 0,
+			.useable         = 0
+		};
+
+		if (safe_modify_ldt(0x11, &desc, sizeof(desc)) != 0) {
+			if (errno != ENOSYS)
+				err(1, "modify_ldt");
+			printf("[SKIP]\tmodify_ldt unavailable\n");
+			break;
+		}
+
+		/* Arm the thread. */
+		ftx = 1;
+		syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+
+		asm volatile ("mov %0, %%ss" : : "r" (0x7));
+
+		/* Go! */
+		ftx = 2;
+
+		while (ftx != 0)
+			;
+
+		/*
+		 * On success, modify_ldt will segfault us synchronously,
+		 * and we'll escape via siglongjmp.
+		 */
+
+		failures++;
+		asm volatile ("mov %0, %%ss" : : "rm" (orig_ss));
+	};
+
+	ftx = 100;  /* Kill the thread. */
+	syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+
+	if (pthread_join(thread, NULL) != 0)
+		err(1, "pthread_join");
+
+	if (failures) {
+		printf("[FAIL]\t%d of %d iterations failed\n", failures, iters);
+		nerrs++;
+	} else {
+		printf("[OK]\tAll %d iterations succeeded\n", iters);
+	}
+}
+
+static int finish_exec_test(void)
+{
+	/*
+	 * In a sensible world, this would be check_invalid_segment(0, 1);
+	 * For better or for worse, though, the LDT is inherited across exec.
+	 * We can probably change this safely, but for now we test it.
+	 */
+	check_valid_segment(0, 1,
+			    AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB,
+			    42, true);
+
+	return nerrs ? 1 : 0;
+}
+
+static void do_exec_test(void)
+{
+	printf("[RUN]\tTest exec\n");
+
+	struct user_desc desc = {
+		.entry_number    = 0,
+		.base_addr       = 0,
+		.limit           = 42,
+		.seg_32bit       = 1,
+		.contents        = 2, /* Code, not conforming */
+		.read_exec_only  = 0,
+		.limit_in_pages  = 0,
+		.seg_not_present = 0,
+		.useable         = 0
+	};
+	install_valid(&desc, AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB);
+
+	pid_t child = fork();
+	if (child == 0) {
+		execl("/proc/self/exe", "ldt_gdt_test_exec", NULL);
+		printf("[FAIL]\tCould not exec self\n");
+		exit(1);	/* exec failed */
+	} else {
+		int status;
+		if (waitpid(child, &status, 0) != child ||
+		    !WIFEXITED(status)) {
+			printf("[FAIL]\tChild died\n");
+			nerrs++;
+		} else if (WEXITSTATUS(status) != 0) {
+			printf("[FAIL]\tChild failed\n");
+			nerrs++;
+		} else {
+			printf("[OK]\tChild succeeded\n");
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	if (argc == 1 && !strcmp(argv[0], "ldt_gdt_test_exec"))
+		return finish_exec_test();
+
+	do_simple_tests();
+
+	do_multicpu_tests();
+
+	do_exec_test();
+
+	return nerrs ? 1 : 0;
+}
diff --git a/tools/testing/selftests/x86/syscall_arg_fault.c b/tools/testing/selftests/x86/syscall_arg_fault.c
new file mode 100644
index 0000000..7db4fc9
--- /dev/null
+++ b/tools/testing/selftests/x86/syscall_arg_fault.c
@@ -0,0 +1,130 @@
+/*
+ * syscall_arg_fault.c - tests faults 32-bit fast syscall stack args
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/signal.h>
+#include <sys/ucontext.h>
+#include <err.h>
+#include <setjmp.h>
+#include <errno.h>
+
+/* Our sigaltstack scratch space. */
+static unsigned char altstack_data[SIGSTKSZ];
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static volatile sig_atomic_t sig_traps;
+static sigjmp_buf jmpbuf;
+
+static volatile sig_atomic_t n_errs;
+
+static void sigsegv(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (ctx->uc_mcontext.gregs[REG_EAX] != -EFAULT) {
+		printf("[FAIL]\tAX had the wrong value: 0x%x\n",
+		       ctx->uc_mcontext.gregs[REG_EAX]);
+		n_errs++;
+	} else {
+		printf("[OK]\tSeems okay\n");
+	}
+
+	siglongjmp(jmpbuf, 1);
+}
+
+static void sigill(int sig, siginfo_t *info, void *ctx_void)
+{
+	printf("[SKIP]\tIllegal instruction\n");
+	siglongjmp(jmpbuf, 1);
+}
+
+int main()
+{
+	stack_t stack = {
+		.ss_sp = altstack_data,
+		.ss_size = SIGSTKSZ,
+	};
+	if (sigaltstack(&stack, NULL) != 0)
+		err(1, "sigaltstack");
+
+	sethandler(SIGSEGV, sigsegv, SA_ONSTACK);
+	sethandler(SIGILL, sigill, SA_ONSTACK);
+
+	/*
+	 * Exercise another nasty special case.  The 32-bit SYSCALL
+	 * and SYSENTER instructions (even in compat mode) each
+	 * clobber one register.  A Linux system call has a syscall
+	 * number and six arguments, and the user stack pointer
+	 * needs to live in some register on return.  That means
+	 * that we need eight registers, but SYSCALL and SYSENTER
+	 * only preserve seven registers.  As a result, one argument
+	 * ends up on the stack.  The stack is user memory, which
+	 * means that the kernel can fail to read it.
+	 *
+	 * The 32-bit fast system calls don't have a defined ABI:
+	 * we're supposed to invoke them through the vDSO.  So we'll
+	 * fudge it: we set all regs to invalid pointer values and
+	 * invoke the entry instruction.  The return will fail no
+	 * matter what, and we completely lose our program state,
+	 * but we can fix it up with a signal handler.
+	 */
+
+	printf("[RUN]\tSYSENTER with invalid state\n");
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		asm volatile (
+			"movl $-1, %%eax\n\t"
+			"movl $-1, %%ebx\n\t"
+			"movl $-1, %%ecx\n\t"
+			"movl $-1, %%edx\n\t"
+			"movl $-1, %%esi\n\t"
+			"movl $-1, %%edi\n\t"
+			"movl $-1, %%ebp\n\t"
+			"movl $-1, %%esp\n\t"
+			"sysenter"
+			: : : "memory", "flags");
+	}
+
+	printf("[RUN]\tSYSCALL with invalid state\n");
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		asm volatile (
+			"movl $-1, %%eax\n\t"
+			"movl $-1, %%ebx\n\t"
+			"movl $-1, %%ecx\n\t"
+			"movl $-1, %%edx\n\t"
+			"movl $-1, %%esi\n\t"
+			"movl $-1, %%edi\n\t"
+			"movl $-1, %%ebp\n\t"
+			"movl $-1, %%esp\n\t"
+			"syscall\n\t"
+			"pushl $0"	/* make sure we segfault cleanly */
+			: : : "memory", "flags");
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
new file mode 100644
index 0000000..60c06af4
--- /dev/null
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -0,0 +1,54 @@
+/*
+ * syscall_nt.c - checks syscalls with NT set
+ * Copyright (c) 2014-2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Some obscure user-space code requires the ability to make system calls
+ * with FLAGS.NT set.  Make sure it works.
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <asm/processor-flags.h>
+
+#ifdef __x86_64__
+# define WIDTH "q"
+#else
+# define WIDTH "l"
+#endif
+
+static unsigned long get_eflags(void)
+{
+	unsigned long eflags;
+	asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags));
+	return eflags;
+}
+
+static void set_eflags(unsigned long eflags)
+{
+	asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH
+		      : : "rm" (eflags) : "flags");
+}
+
+int main()
+{
+	printf("[RUN]\tSet NT and issue a syscall\n");
+	set_eflags(get_eflags() | X86_EFLAGS_NT);
+	syscall(SYS_getpid);
+	if (get_eflags() & X86_EFLAGS_NT) {
+		printf("[OK]\tThe syscall worked and NT is still set\n");
+		return 0;
+	} else {
+		printf("[FAIL]\tThe syscall worked but NT was cleared\n");
+		return 1;
+	}
+}