aboutsummaryrefslogtreecommitdiff
path: root/tools/testing/selftests/kcmp/kcmp_test.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing/selftests/kcmp/kcmp_test.c')
-rw-r--r--tools/testing/selftests/kcmp/kcmp_test.c96
1 files changed, 96 insertions, 0 deletions
diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c
new file mode 100644
index 00000000000..fa4f1b37e04
--- /dev/null
+++ b/tools/testing/selftests/kcmp/kcmp_test.c
@@ -0,0 +1,96 @@
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <limits.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <fcntl.h>
+
+#include <linux/unistd.h>
+#include <linux/kcmp.h>
+
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/wait.h>
+
+static long sys_kcmp(int pid1, int pid2, int type, int fd1, int fd2)
+{
+ return syscall(__NR_kcmp, pid1, pid2, type, fd1, fd2);
+}
+
+int main(int argc, char **argv)
+{
+ const char kpath[] = "kcmp-test-file";
+ int pid1, pid2;
+ int fd1, fd2;
+ int status;
+
+ fd1 = open(kpath, O_RDWR | O_CREAT | O_TRUNC, 0644);
+ pid1 = getpid();
+
+ if (fd1 < 0) {
+ perror("Can't create file");
+ exit(1);
+ }
+
+ pid2 = fork();
+ if (pid2 < 0) {
+ perror("fork failed");
+ exit(1);
+ }
+
+ if (!pid2) {
+ int pid2 = getpid();
+ int ret;
+
+ fd2 = open(kpath, O_RDWR, 0644);
+ if (fd2 < 0) {
+ perror("Can't open file");
+ exit(1);
+ }
+
+ /* An example of output and arguments */
+ printf("pid1: %6d pid2: %6d FD: %2ld FILES: %2ld VM: %2ld "
+ "FS: %2ld SIGHAND: %2ld IO: %2ld SYSVSEM: %2ld "
+ "INV: %2ld\n",
+ pid1, pid2,
+ sys_kcmp(pid1, pid2, KCMP_FILE, fd1, fd2),
+ sys_kcmp(pid1, pid2, KCMP_FILES, 0, 0),
+ sys_kcmp(pid1, pid2, KCMP_VM, 0, 0),
+ sys_kcmp(pid1, pid2, KCMP_FS, 0, 0),
+ sys_kcmp(pid1, pid2, KCMP_SIGHAND, 0, 0),
+ sys_kcmp(pid1, pid2, KCMP_IO, 0, 0),
+ sys_kcmp(pid1, pid2, KCMP_SYSVSEM, 0, 0),
+
+ /* This one should fail */
+ sys_kcmp(pid1, pid2, KCMP_TYPES + 1, 0, 0));
+
+ /* This one should return same fd */
+ ret = sys_kcmp(pid1, pid2, KCMP_FILE, fd1, fd1);
+ if (ret) {
+ printf("FAIL: 0 expected but %d returned (%s)\n",
+ ret, strerror(errno));
+ ret = -1;
+ } else
+ printf("PASS: 0 returned as expected\n");
+
+ /* Compare with self */
+ ret = sys_kcmp(pid1, pid1, KCMP_VM, 0, 0);
+ if (ret) {
+ printf("FAIL: 0 expected but %li returned (%s)\n",
+ ret, strerror(errno));
+ ret = -1;
+ } else
+ printf("PASS: 0 returned as expected\n");
+
+ exit(ret);
+ }
+
+ waitpid(pid2, &status, P_ALL);
+
+ return 0;
+}
/include/asm/archrandom.h136
-rw-r--r--arch/x86/include/asm/asm.h56
-rw-r--r--arch/x86/include/asm/atomic.h252
-rw-r--r--arch/x86/include/asm/atomic64_32.h316
-rw-r--r--arch/x86/include/asm/atomic64_64.h223
-rw-r--r--arch/x86/include/asm/atomic_32.h415
-rw-r--r--arch/x86/include/asm/atomic_64.h485
-rw-r--r--arch/x86/include/asm/barrier.h157
-rw-r--r--arch/x86/include/asm/bios_ebda.h28
-rw-r--r--arch/x86/include/asm/bitops.h174
-rw-r--r--arch/x86/include/asm/boot.h19
-rw-r--r--arch/x86/include/asm/bootparam_utils.h54
-rw-r--r--arch/x86/include/asm/bug.h4
-rw-r--r--arch/x86/include/asm/cache.h2
-rw-r--r--arch/x86/include/asm/cacheflush.h91
-rw-r--r--arch/x86/include/asm/calgary.h4
-rw-r--r--arch/x86/include/asm/calling.h184
-rw-r--r--arch/x86/include/asm/ce4100.h6
-rw-r--r--arch/x86/include/asm/checksum.h4
-rw-r--r--arch/x86/include/asm/checksum_32.h22
-rw-r--r--arch/x86/include/asm/checksum_64.h11
-rw-r--r--arch/x86/include/asm/clocksource.h15
-rw-r--r--arch/x86/include/asm/cmdline.h6
-rw-r--r--arch/x86/include/asm/cmpxchg.h232
-rw-r--r--arch/x86/include/asm/cmpxchg_32.h294
-rw-r--r--arch/x86/include/asm/cmpxchg_64.h114
-rw-r--r--arch/x86/include/asm/compat.h122
-rw-r--r--arch/x86/include/asm/context_tracking.h10
-rw-r--r--arch/x86/include/asm/cpu.h6
-rw-r--r--arch/x86/include/asm/cpu_device_id.h13
-rw-r--r--arch/x86/include/asm/cpufeature.h308
-rw-r--r--arch/x86/include/asm/cputime.h1
-rw-r--r--arch/x86/include/asm/crypto/aes.h (renamed from arch/x86/include/asm/aes.h)0
-rw-r--r--arch/x86/include/asm/crypto/camellia.h101
-rw-r--r--arch/x86/include/asm/crypto/glue_helper.h145
-rw-r--r--arch/x86/include/asm/crypto/serpent-avx.h48
-rw-r--r--arch/x86/include/asm/crypto/serpent-sse2.h63
-rw-r--r--arch/x86/include/asm/crypto/twofish.h46
-rw-r--r--arch/x86/include/asm/current.h2
-rw-r--r--arch/x86/include/asm/debugreg.h157
-rw-r--r--arch/x86/include/asm/delay.h25
-rw-r--r--arch/x86/include/asm/desc.h287
-rw-r--r--arch/x86/include/asm/device.h9
-rw-r--r--arch/x86/include/asm/div64.h22
-rw-r--r--arch/x86/include/asm/dma-contiguous.h12
-rw-r--r--arch/x86/include/asm/dma-mapping.h51
-rw-r--r--arch/x86/include/asm/dma.h19
-rw-r--r--arch/x86/include/asm/dmi.h6
-rw-r--r--arch/x86/include/asm/ds.h302
-rw-r--r--arch/x86/include/asm/dwarf2.h34
-rw-r--r--arch/x86/include/asm/e820.h91
-rw-r--r--arch/x86/include/asm/efi.h205
-rw-r--r--arch/x86/include/asm/elf.h88
-rw-r--r--arch/x86/include/asm/emergency-restart.h14
-rw-r--r--arch/x86/include/asm/entry_arch.h35
-rw-r--r--arch/x86/include/asm/espfix.h16
-rw-r--r--arch/x86/include/asm/exec.h1
-rw-r--r--arch/x86/include/asm/fb.h4
-rw-r--r--arch/x86/include/asm/fixmap.h108
-rw-r--r--arch/x86/include/asm/floppy.h6
-rw-r--r--arch/x86/include/asm/fpu-internal.h619
-rw-r--r--arch/x86/include/asm/frame.h13
-rw-r--r--arch/x86/include/asm/ftrace.h89
-rw-r--r--arch/x86/include/asm/futex.h51
-rw-r--r--arch/x86/include/asm/gart.h42
-rw-r--r--arch/x86/include/asm/gpio.h60
-rw-r--r--arch/x86/include/asm/hardirq.h23
-rw-r--r--arch/x86/include/asm/hash.h7
-rw-r--r--arch/x86/include/asm/highmem.h15
-rw-r--r--arch/x86/include/asm/hpet.h18
-rw-r--r--arch/x86/include/asm/hugetlb.h6
-rw-r--r--arch/x86/include/asm/hw_breakpoint.h18
-rw-r--r--arch/x86/include/asm/hw_irq.h158
-rw-r--r--arch/x86/include/asm/hypervisor.h46
-rw-r--r--arch/x86/include/asm/i387.h377
-rw-r--r--arch/x86/include/asm/i8253.h18
-rw-r--r--arch/x86/include/asm/i8259.h23
-rw-r--r--arch/x86/include/asm/ia32.h84
-rw-r--r--arch/x86/include/asm/ia32_unistd.h13
-rw-r--r--arch/x86/include/asm/idle.h3
-rw-r--r--arch/x86/include/asm/inat.h5
-rw-r--r--arch/x86/include/asm/init.h26
-rw-r--r--arch/x86/include/asm/insn.h27
-rw-r--r--arch/x86/include/asm/inst.h166
-rw-r--r--arch/x86/include/asm/intel-mid.h157
-rw-r--r--arch/x86/include/asm/intel_mid_vrtc.h9
-rw-r--r--arch/x86/include/asm/intel_scu_ipc.h73
-rw-r--r--arch/x86/include/asm/io.h213
-rw-r--r--arch/x86/include/asm/io_32.h196
-rw-r--r--arch/x86/include/asm/io_64.h181
-rw-r--r--arch/x86/include/asm/io_apic.h137
-rw-r--r--arch/x86/include/asm/iomap.h6
-rw-r--r--arch/x86/include/asm/iommu_table.h100
-rw-r--r--arch/x86/include/asm/iosf_mbi.h145
-rw-r--r--arch/x86/include/asm/ipi.h8
-rw-r--r--arch/x86/include/asm/irq.h24
-rw-r--r--arch/x86/include/asm/irq_regs.h4
-rw-r--r--arch/x86/include/asm/irq_remapping.h111
-rw-r--r--arch/x86/include/asm/irq_vectors.h85
-rw-r--r--arch/x86/include/asm/irqflags.h35
-rw-r--r--arch/x86/include/asm/ist.h17
-rw-r--r--arch/x86/include/asm/jump_label.h47
-rw-r--r--arch/x86/include/asm/k8.h31
-rw-r--r--arch/x86/include/asm/kbdleds.h17
-rw-r--r--arch/x86/include/asm/kdebug.h12
-rw-r--r--arch/x86/include/asm/kexec.h9
-rw-r--r--arch/x86/include/asm/kgdb.h28
-rw-r--r--arch/x86/include/asm/kprobes.h39
-rw-r--r--arch/x86/include/asm/kvm_emulate.h333
-rw-r--r--arch/x86/include/asm/kvm_guest.h6
-rw-r--r--arch/x86/include/asm/kvm_host.h792
-rw-r--r--arch/x86/include/asm/kvm_para.h104
-rw-r--r--arch/x86/include/asm/lguest.h17
-rw-r--r--arch/x86/include/asm/lguest_hcall.h30
-rw-r--r--arch/x86/include/asm/linkage.h23
-rw-r--r--arch/x86/include/asm/local.h86
-rw-r--r--arch/x86/include/asm/local64.h1
-rw-r--r--arch/x86/include/asm/mach_timer.h2
-rw-r--r--arch/x86/include/asm/mach_traps.h14
-rw-r--r--arch/x86/include/asm/mc146818rtc.h9
-rw-r--r--arch/x86/include/asm/mca.h43
-rw-r--r--arch/x86/include/asm/mca_dma.h201
-rw-r--r--arch/x86/include/asm/mce.h173
-rw-r--r--arch/x86/include/asm/microcode.h36
-rw-r--r--arch/x86/include/asm/microcode_amd.h77
-rw-r--r--arch/x86/include/asm/microcode_intel.h87
-rw-r--r--arch/x86/include/asm/misc.h6
-rw-r--r--arch/x86/include/asm/mmconfig.h4
-rw-r--r--arch/x86/include/asm/mmu.h8
-rw-r--r--arch/x86/include/asm/mmu_context.h37
-rw-r--r--arch/x86/include/asm/mmzone.h4
-rw-r--r--arch/x86/include/asm/mmzone_32.h54
-rw-r--r--arch/x86/include/asm/mmzone_64.h32
-rw-r--r--arch/x86/include/asm/module.h11
-rw-r--r--arch/x86/include/asm/mpspec.h55
-rw-r--r--arch/x86/include/asm/mpspec_def.h10
-rw-r--r--arch/x86/include/asm/mshyperv.h23
-rw-r--r--arch/x86/include/asm/msr.h95
-rw-r--r--arch/x86/include/asm/mtrr.h95
-rw-r--r--arch/x86/include/asm/mutex.h4
-rw-r--r--arch/x86/include/asm/mutex_32.h11
-rw-r--r--arch/x86/include/asm/mutex_64.h41
-rw-r--r--arch/x86/include/asm/mwait.h59
-rw-r--r--arch/x86/include/asm/nmi.h93
-rw-r--r--arch/x86/include/asm/nops.h152
-rw-r--r--arch/x86/include/asm/numa.h84
-rw-r--r--arch/x86/include/asm/numa_32.h3
-rw-r--r--arch/x86/include/asm/numa_64.h47
-rw-r--r--arch/x86/include/asm/numachip/numachip.h19
-rw-r--r--arch/x86/include/asm/numachip/numachip_csr.h167
-rw-r--r--arch/x86/include/asm/numaq.h171
-rw-r--r--arch/x86/include/asm/olpc.h68
-rw-r--r--arch/x86/include/asm/olpc_ofw.h37
-rw-r--r--arch/x86/include/asm/page.h15
-rw-r--r--arch/x86/include/asm/page_32.h5
-rw-r--r--arch/x86/include/asm/page_32_types.h10
-rw-r--r--arch/x86/include/asm/page_64.h36
-rw-r--r--arch/x86/include/asm/page_64_types.h45
-rw-r--r--arch/x86/include/asm/page_types.h20
-rw-r--r--arch/x86/include/asm/paravirt.h159
-rw-r--r--arch/x86/include/asm/paravirt_types.h49
-rw-r--r--arch/x86/include/asm/parport.h4
-rw-r--r--arch/x86/include/asm/pci.h83
-rw-r--r--arch/x86/include/asm/pci_64.h2
-rw-r--r--arch/x86/include/asm/pci_x86.h52
-rw-r--r--arch/x86/include/asm/percpu.h462
-rw-r--r--arch/x86/include/asm/perf_event.h239
-rw-r--r--arch/x86/include/asm/perf_event_p4.h876
-rw-r--r--arch/x86/include/asm/pgalloc.h18
-rw-r--r--arch/x86/include/asm/pgtable-2level.h72
-rw-r--r--arch/x86/include/asm/pgtable-3level.h97
-rw-r--r--arch/x86/include/asm/pgtable.h295
-rw-r--r--arch/x86/include/asm/pgtable_32.h22
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h2
-rw-r--r--arch/x86/include/asm/pgtable_64.h57
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h8
-rw-r--r--arch/x86/include/asm/pgtable_types.h105
-rw-r--r--arch/x86/include/asm/posix_types.h12
-rw-r--r--arch/x86/include/asm/posix_types_32.h85
-rw-r--r--arch/x86/include/asm/posix_types_64.h119
-rw-r--r--arch/x86/include/asm/preempt.h111
-rw-r--r--arch/x86/include/asm/probe_roms.h8
-rw-r--r--arch/x86/include/asm/processor-flags.h91
-rw-r--r--arch/x86/include/asm/processor.h387
-rw-r--r--arch/x86/include/asm/prom.h43
-rw-r--r--arch/x86/include/asm/proto.h14
-rw-r--r--arch/x86/include/asm/ptrace-abi.h142
-rw-r--r--arch/x86/include/asm/ptrace.h174
-rw-r--r--arch/x86/include/asm/pvclock-abi.h5
-rw-r--r--arch/x86/include/asm/pvclock.h93
-rw-r--r--arch/x86/include/asm/qrwlock.h17
-rw-r--r--arch/x86/include/asm/rdc321x_defs.h12
-rw-r--r--arch/x86/include/asm/realmode.h64
-rw-r--r--arch/x86/include/asm/reboot.h7
-rw-r--r--arch/x86/include/asm/required-features.h10
-rw-r--r--arch/x86/include/asm/rmwcc.h41
-rw-r--r--arch/x86/include/asm/rwlock.h43
-rw-r--r--arch/x86/include/asm/rwsem.h174
-rw-r--r--arch/x86/include/asm/scatterlist.h4
-rw-r--r--arch/x86/include/asm/seccomp.h4
-rw-r--r--arch/x86/include/asm/segment.h109
-rw-r--r--arch/x86/include/asm/setup.h45
-rw-r--r--arch/x86/include/asm/sigcontext.h213
-rw-r--r--arch/x86/include/asm/sigframe.h13
-rw-r--r--arch/x86/include/asm/sighandling.h22
-rw-r--r--arch/x86/include/asm/siginfo.h10
-rw-r--r--arch/x86/include/asm/signal.h170
-rw-r--r--arch/x86/include/asm/simd.h11
-rw-r--r--arch/x86/include/asm/smap.h91
-rw-r--r--arch/x86/include/asm/smp.h81
-rw-r--r--arch/x86/include/asm/smpboot_hooks.h11
-rw-r--r--arch/x86/include/asm/special_insns.h207
-rw-r--r--arch/x86/include/asm/spinlock.h283
-rw-r--r--arch/x86/include/asm/spinlock_types.h41
-rw-r--r--arch/x86/include/asm/srat.h39
-rw-r--r--arch/x86/include/asm/sta2x11.h12
-rw-r--r--arch/x86/include/asm/stackprotector.h5
-rw-r--r--arch/x86/include/asm/stacktrace.h81
-rw-r--r--arch/x86/include/asm/string.h4
-rw-r--r--arch/x86/include/asm/suspend.h4
-rw-r--r--arch/x86/include/asm/suspend_32.h6
-rw-r--r--arch/x86/include/asm/suspend_64.h12
-rw-r--r--arch/x86/include/asm/svm.h141
-rw-r--r--arch/x86/include/asm/swiotlb.h20
-rw-r--r--arch/x86/include/asm/switch_to.h129
-rw-r--r--arch/x86/include/asm/sync_bitops.h26
-rw-r--r--arch/x86/include/asm/sys_ia32.h63
-rw-r--r--arch/x86/include/asm/syscall.h30
-rw-r--r--arch/x86/include/asm/syscalls.h45
-rw-r--r--arch/x86/include/asm/sysfb.h98
-rw-r--r--arch/x86/include/asm/system.h460
-rw-r--r--arch/x86/include/asm/system_64.h22
-rw-r--r--arch/x86/include/asm/thread_info.h162
-rw-r--r--arch/x86/include/asm/time.h6
-rw-r--r--arch/x86/include/asm/timer.h67
-rw-r--r--arch/x86/include/asm/tlb.h9
-rw-r--r--arch/x86/include/asm/tlbflush.h121
-rw-r--r--arch/x86/include/asm/topology.h113
-rw-r--r--arch/x86/include/asm/trace/exceptions.h52
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h115
-rw-r--r--arch/x86/include/asm/trace_clock.h20
-rw-r--r--arch/x86/include/asm/trampoline.h28
-rw-r--r--arch/x86/include/asm/traps.h62
-rw-r--r--arch/x86/include/asm/tsc.h10
-rw-r--r--arch/x86/include/asm/types.h22
-rw-r--r--arch/x86/include/asm/uaccess.h391
-rw-r--r--arch/x86/include/asm/uaccess_32.h55
-rw-r--r--arch/x86/include/asm/uaccess_64.h89
-rw-r--r--arch/x86/include/asm/unistd.h60
-rw-r--r--arch/x86/include/asm/unistd_32.h386
-rw-r--r--arch/x86/include/asm/unistd_64.h708
-rw-r--r--arch/x86/include/asm/uprobes.h67
-rw-r--r--arch/x86/include/asm/user.h62
-rw-r--r--arch/x86/include/asm/uv/bios.h11
-rw-r--r--arch/x86/include/asm/uv/uv.h6
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h743
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h207
-rw-r--r--arch/x86/include/asm/uv/uv_mmrs.h3711
-rw-r--r--arch/x86/include/asm/vdso.h79
-rw-r--r--arch/x86/include/asm/vga.h6
-rw-r--r--arch/x86/include/asm/vgtod.h79
-rw-r--r--arch/x86/include/asm/virtext.h1
-rw-r--r--arch/x86/include/asm/visws/cobalt.h125
-rw-r--r--arch/x86/include/asm/visws/lithium.h53
-rw-r--r--arch/x86/include/asm/visws/piix4.h107
-rw-r--r--arch/x86/include/asm/visws/sgivw.h5
-rw-r--r--arch/x86/include/asm/vm86.h128
-rw-r--r--arch/x86/include/asm/vmi.h269
-rw-r--r--arch/x86/include/asm/vmi_time.h98
-rw-r--r--arch/x86/include/asm/vmware.h27
-rw-r--r--arch/x86/include/asm/vmx.h180
-rw-r--r--arch/x86/include/asm/vsyscall.h56
-rw-r--r--arch/x86/include/asm/vvar.h53
-rw-r--r--arch/x86/include/asm/word-at-a-time.h105
-rw-r--r--arch/x86/include/asm/x2apic.h49
-rw-r--r--arch/x86/include/asm/x86_init.h88
-rw-r--r--arch/x86/include/asm/xen/events.h5
-rw-r--r--arch/x86/include/asm/xen/grant_table.h7
-rw-r--r--arch/x86/include/asm/xen/hypercall.h106
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h22
-rw-r--r--arch/x86/include/asm/xen/interface.h30
-rw-r--r--arch/x86/include/asm/xen/interface_32.h5
-rw-r--r--arch/x86/include/asm/xen/interface_64.h13
-rw-r--r--arch/x86/include/asm/xen/page-coherent.h38
-rw-r--r--arch/x86/include/asm/xen/page.h101
-rw-r--r--arch/x86/include/asm/xen/pci.h82
-rw-r--r--arch/x86/include/asm/xen/swiotlb-xen.h16
-rw-r--r--arch/x86/include/asm/xen/trace_types.h18
-rw-r--r--arch/x86/include/asm/xor.h495
-rw-r--r--arch/x86/include/asm/xor_32.h353
-rw-r--r--arch/x86/include/asm/xor_64.h352
-rw-r--r--arch/x86/include/asm/xor_avx.h184
-rw-r--r--arch/x86/include/asm/xsave.h96
-rw-r--r--arch/x86/include/uapi/asm/Kbuild64
-rw-r--r--arch/x86/include/uapi/asm/a.out.h (renamed from arch/x86/include/asm/a.out.h)0
-rw-r--r--arch/x86/include/uapi/asm/auxvec.h (renamed from arch/x86/include/asm/auxvec.h)7
-rw-r--r--arch/x86/include/uapi/asm/bitsperlong.h (renamed from arch/x86/include/asm/bitsperlong.h)0
-rw-r--r--arch/x86/include/uapi/asm/boot.h10
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h (renamed from arch/x86/include/asm/bootparam.h)79
-rw-r--r--arch/x86/include/uapi/asm/byteorder.h (renamed from arch/x86/include/asm/byteorder.h)0
-rw-r--r--arch/x86/include/uapi/asm/debugreg.h80
-rw-r--r--arch/x86/include/uapi/asm/e820.h75
-rw-r--r--arch/x86/include/uapi/asm/errno.h (renamed from arch/x86/include/asm/errno.h)0
-rw-r--r--arch/x86/include/uapi/asm/fcntl.h (renamed from arch/x86/include/asm/fcntl.h)0
-rw-r--r--arch/x86/include/uapi/asm/hw_breakpoint.h1
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h226
-rw-r--r--arch/x86/include/uapi/asm/ioctl.h (renamed from arch/x86/include/asm/ioctl.h)0
-rw-r--r--arch/x86/include/uapi/asm/ioctls.h (renamed from arch/x86/include/asm/ioctls.h)0
-rw-r--r--arch/x86/include/uapi/asm/ipcbuf.h (renamed from arch/x86/include/asm/ipcbuf.h)0
-rw-r--r--arch/x86/include/uapi/asm/ist.h29
-rw-r--r--arch/x86/include/uapi/asm/kvm.h (renamed from arch/x86/include/asm/kvm.h)68
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h101
-rw-r--r--arch/x86/include/uapi/asm/ldt.h (renamed from arch/x86/include/asm/ldt.h)0
-rw-r--r--arch/x86/include/uapi/asm/mce.h34
-rw-r--r--arch/x86/include/uapi/asm/mman.h (renamed from arch/x86/include/asm/mman.h)3
-rw-r--r--arch/x86/include/uapi/asm/msgbuf.h (renamed from arch/x86/include/asm/msgbuf.h)0
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h (renamed from arch/x86/include/asm/msr-index.h)263
-rw-r--r--arch/x86/include/uapi/asm/msr.h15
-rw-r--r--arch/x86/include/uapi/asm/mtrr.h117
-rw-r--r--arch/x86/include/uapi/asm/param.h (renamed from arch/x86/include/asm/param.h)0
-rw-r--r--arch/x86/include/uapi/asm/perf_regs.h33
-rw-r--r--arch/x86/include/uapi/asm/poll.h (renamed from arch/x86/include/asm/poll.h)0
-rw-r--r--arch/x86/include/uapi/asm/posix_types.h9
-rw-r--r--arch/x86/include/uapi/asm/posix_types_32.h25
-rw-r--r--arch/x86/include/uapi/asm/posix_types_64.h19
-rw-r--r--arch/x86/include/uapi/asm/posix_types_x32.h19
-rw-r--r--arch/x86/include/uapi/asm/prctl.h (renamed from arch/x86/include/asm/prctl.h)0
-rw-r--r--arch/x86/include/uapi/asm/processor-flags.h153
-rw-r--r--arch/x86/include/uapi/asm/ptrace-abi.h87
-rw-r--r--arch/x86/include/uapi/asm/ptrace.h78
-rw-r--r--arch/x86/include/uapi/asm/resource.h (renamed from arch/x86/include/asm/resource.h)0
-rw-r--r--arch/x86/include/uapi/asm/sembuf.h (renamed from arch/x86/include/asm/sembuf.h)10
-rw-r--r--arch/x86/include/uapi/asm/setup.h1
-rw-r--r--arch/x86/include/uapi/asm/shmbuf.h (renamed from arch/x86/include/asm/shmbuf.h)0
-rw-r--r--arch/x86/include/uapi/asm/sigcontext.h221
-rw-r--r--arch/x86/include/uapi/asm/sigcontext32.h (renamed from arch/x86/include/asm/sigcontext32.h)0
-rw-r--r--arch/x86/include/uapi/asm/siginfo.h16
-rw-r--r--arch/x86/include/uapi/asm/signal.h135
-rw-r--r--arch/x86/include/uapi/asm/socket.h (renamed from arch/x86/include/asm/socket.h)0
-rw-r--r--arch/x86/include/uapi/asm/sockios.h (renamed from arch/x86/include/asm/sockios.h)0
-rw-r--r--arch/x86/include/uapi/asm/stat.h (renamed from arch/x86/include/asm/stat.h)61
-rw-r--r--arch/x86/include/uapi/asm/statfs.h (renamed from arch/x86/include/asm/statfs.h)0
-rw-r--r--arch/x86/include/uapi/asm/svm.h132
-rw-r--r--arch/x86/include/uapi/asm/swab.h (renamed from arch/x86/include/asm/swab.h)29
-rw-r--r--arch/x86/include/uapi/asm/termbits.h (renamed from arch/x86/include/asm/termbits.h)0
-rw-r--r--arch/x86/include/uapi/asm/termios.h (renamed from arch/x86/include/asm/termios.h)0
-rw-r--r--arch/x86/include/uapi/asm/types.h6
-rw-r--r--arch/x86/include/uapi/asm/ucontext.h (renamed from arch/x86/include/asm/ucontext.h)0
-rw-r--r--arch/x86/include/uapi/asm/unistd.h17
-rw-r--r--arch/x86/include/uapi/asm/vm86.h129
-rw-r--r--arch/x86/include/uapi/asm/vmx.h119
-rw-r--r--arch/x86/include/uapi/asm/vsyscall.h12
366 files changed, 20646 insertions, 13524 deletions
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 9f828f87ca3..3ca9762e164 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -1,25 +1,10 @@
-include include/asm-generic/Kbuild.asm
-header-y += boot.h
-header-y += bootparam.h
-header-y += debugreg.h
-header-y += ldt.h
-header-y += msr-index.h
-header-y += prctl.h
-header-y += ptrace-abi.h
-header-y += sigcontext32.h
-header-y += ucontext.h
-header-y += processor-flags.h
-header-y += hw_breakpoint.h
-unifdef-y += e820.h
-unifdef-y += ist.h
-unifdef-y += mce.h
-unifdef-y += msr.h
-unifdef-y += mtrr.h
-unifdef-y += posix_types_32.h
-unifdef-y += posix_types_64.h
-unifdef-y += unistd_32.h
-unifdef-y += unistd_64.h
-unifdef-y += vm86.h
-unifdef-y += vsyscall.h
+genhdr-y += unistd_32.h
+genhdr-y += unistd_64.h
+genhdr-y += unistd_x32.h
+
+generic-y += clkdev.h
+generic-y += early_ioremap.h
+generic-y += cputime.h
+generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h
new file mode 100644
index 00000000000..66873297e9f
--- /dev/null
+++ b/arch/x86/include/asm/acenv.h
@@ -0,0 +1,49 @@
+/*
+ * X86 specific ACPICA environments and implementation
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Author: Lv Zheng <lv.zheng@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ASM_X86_ACENV_H
+#define _ASM_X86_ACENV_H
+
+#include <asm/special_insns.h>
+
+/* Asm macros */
+
+#define ACPI_FLUSH_CPU_CACHE() wbinvd()
+
+#ifdef CONFIG_ACPI
+
+int __acpi_acquire_global_lock(unsigned int *lock);
+int __acpi_release_global_lock(unsigned int *lock);
+
+#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
+ ((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
+
+#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
+ ((Acq) = __acpi_release_global_lock(&facs->global_lock))
+
+/*
+ * Math helper asm macros
+ */
+#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
+ asm("divl %2;" \
+ : "=a"(q32), "=d"(r32) \
+ : "r"(d32), \
+ "0"(n_lo), "1"(n_hi))
+
+#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
+ asm("shrl $1,%2 ;" \
+ "rcrl $1,%3;" \
+ : "=r"(n_hi), "=r"(n_lo) \
+ : "0"(n_hi), "1"(n_lo))
+
+#endif
+
+#endif /* _ASM_X86_ACENV_H */
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 56f462cf22d..e06225eda63 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -26,58 +26,11 @@
#include <acpi/pdc_intel.h>
#include <asm/numa.h>
+#include <asm/fixmap.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mpspec.h>
-
-#define COMPILER_DEPENDENT_INT64 long long
-#define COMPILER_DEPENDENT_UINT64 unsigned long long
-
-/*
- * Calling conventions:
- *
- * ACPI_SYSTEM_XFACE - Interfaces to host OS (handlers, threads)
- * ACPI_EXTERNAL_XFACE - External ACPI interfaces
- * ACPI_INTERNAL_XFACE - Internal ACPI interfaces
- * ACPI_INTERNAL_VAR_XFACE - Internal variable-parameter list interfaces
- */
-#define ACPI_SYSTEM_XFACE
-#define ACPI_EXTERNAL_XFACE
-#define ACPI_INTERNAL_XFACE
-#define ACPI_INTERNAL_VAR_XFACE
-
-/* Asm macros */
-
-#define ACPI_ASM_MACROS
-#define BREAKPOINT3
-#define ACPI_DISABLE_IRQS() local_irq_disable()
-#define ACPI_ENABLE_IRQS() local_irq_enable()
-#define ACPI_FLUSH_CPU_CACHE() wbinvd()
-
-int __acpi_acquire_global_lock(unsigned int *lock);
-int __acpi_release_global_lock(unsigned int *lock);
-
-#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
- ((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
-
-#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
- ((Acq) = __acpi_release_global_lock(&facs->global_lock))
-
-/*
- * Math helper asm macros
- */
-#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
- asm("divl %2;" \
- : "=a"(q32), "=d"(r32) \
- : "r"(d32), \
- "0"(n_lo), "1"(n_hi))
-
-
-#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
- asm("shrl $1,%2 ;" \
- "rcrl $1,%3;" \
- : "=r"(n_hi), "=r"(n_lo) \
- : "0"(n_hi), "1"(n_lo))
+#include <asm/realmode.h>
#ifdef CONFIG_ACPI
extern int acpi_lapic;
@@ -85,19 +38,22 @@ extern int acpi_ioapic;
extern int acpi_noirq;
extern int acpi_strict;
extern int acpi_disabled;
-extern int acpi_ht;
extern int acpi_pci_disabled;
extern int acpi_skip_timer_override;
extern int acpi_use_timer_override;
+extern int acpi_fix_pin2_polarity;
+extern int acpi_disable_cmcff;
extern u8 acpi_sci_flags;
extern int acpi_sci_override_gsi;
void acpi_pic_sci_set_trigger(unsigned int, u16);
+extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
+ int trigger, int polarity);
+
static inline void disable_acpi(void)
{
acpi_disabled = 1;
- acpi_ht = 0;
acpi_pci_disabled = 1;
acpi_noirq = 1;
}
@@ -111,14 +67,11 @@ static inline void acpi_disable_pci(void)
acpi_noirq_set();
}
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-extern void acpi_restore_state_mem(void);
-
-extern unsigned long acpi_wakeup_address;
+/* Low-level suspend routine. */
+extern int (*acpi_suspend_lowlevel)(void);
-/* early initialization routine */
-extern void acpi_reserve_wakeup_memory(void);
+/* Physical address to resume after wakeup */
+#define acpi_wakeup_address ((unsigned long)(real_mode_header->wakeup_start))
/*
* Check if the CPU can handle C2 and deeper
@@ -136,7 +89,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
boot_cpu_data.x86_model <= 0x05 &&
boot_cpu_data.x86_mask < 0x0A)
return 1;
- else if (boot_cpu_has(X86_FEATURE_AMDC1E))
+ else if (amd_e400_c1e_detected)
return 1;
else
return max_cstate;
@@ -172,6 +125,7 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
#define acpi_lapic 0
#define acpi_ioapic 0
+#define acpi_disable_cmcff 0
static inline void acpi_noirq_set(void) { }
static inline void acpi_disable_pci(void) { }
static inline void disable_acpi(void) { }
@@ -180,21 +134,10 @@ static inline void disable_acpi(void) { }
#define ARCH_HAS_POWER_INIT 1
-struct bootnode;
-
#ifdef CONFIG_ACPI_NUMA
extern int acpi_numa;
-extern int acpi_get_nodes(struct bootnode *physnodes);
-extern int acpi_scan_nodes(unsigned long start, unsigned long end);
-#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
- int num_nodes);
-#else
-static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
- int num_nodes)
-{
-}
-#endif
+extern int x86_acpi_numa_init(void);
+#endif /* CONFIG_ACPI_NUMA */
#define acpi_unlazy_tlb(x) leave_mm(x)
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index b97f786a48d..372231c22a4 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -1,18 +1,31 @@
+#ifndef _ASM_X86_ALTERNATIVE_ASM_H
+#define _ASM_X86_ALTERNATIVE_ASM_H
+
#ifdef __ASSEMBLY__
#include <asm/asm.h>
#ifdef CONFIG_SMP
.macro LOCK_PREFIX
-1: lock
- .section .smp_locks,"a"
- _ASM_ALIGN
- _ASM_PTR 1b
- .previous
+672: lock
+ .pushsection .smp_locks,"a"
+ .balign 4
+ .long 672b - .
+ .popsection
.endm
#else
.macro LOCK_PREFIX
.endm
#endif
+.macro altinstruction_entry orig alt feature orig_len alt_len
+ .long \orig - .
+ .long \alt - .
+ .word \feature
+ .byte \orig_len
+ .byte \alt_len
+.endm
+
#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 69b74a7b877..0a3f9c9f98d 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -5,6 +5,7 @@
#include <linux/stddef.h>
#include <linux/stringify.h>
#include <asm/asm.h>
+#include <asm/ptrace.h>
/*
* Alternative inline assembly for SMP.
@@ -28,30 +29,26 @@
*/
#ifdef CONFIG_SMP
-#define LOCK_PREFIX \
- ".section .smp_locks,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR "661f\n" /* address */ \
- ".previous\n" \
- "661:\n\tlock; "
+#define LOCK_PREFIX_HERE \
+ ".pushsection .smp_locks,\"a\"\n" \
+ ".balign 4\n" \
+ ".long 671f - .\n" /* offset */ \
+ ".popsection\n" \
+ "671:"
+
+#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
#else /* ! CONFIG_SMP */
+#define LOCK_PREFIX_HERE ""
#define LOCK_PREFIX ""
#endif
-/* This must be included *after* the definition of LOCK_PREFIX */
-#include <asm/cpufeature.h>
-
struct alt_instr {
- u8 *instr; /* original instruction */
- u8 *replacement;
- u8 cpuid; /* cpuid bit set for replacement */
+ s32 instr_offset; /* original instruction */
+ s32 repl_offset; /* offset to replacement instruction */
+ u16 cpuid; /* cpuid bit set for replacement */
u8 instrlen; /* length of original instruction */
u8 replacementlen; /* length of new instruction, <= instrlen */
- u8 pad1;
-#ifdef CONFIG_X86_64
- u32 pad2;
-#endif
};
extern void alternative_instructions(void);
@@ -64,31 +61,75 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end);
extern void alternatives_smp_module_del(struct module *mod);
-extern void alternatives_smp_switch(int smp);
+extern void alternatives_enable_smp(void);
+extern int alternatives_text_reserved(void *start, void *end);
+extern bool skip_smp_alternatives;
#else
static inline void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end) {}
static inline void alternatives_smp_module_del(struct module *mod) {}
-static inline void alternatives_smp_switch(int smp) {}
+static inline void alternatives_enable_smp(void) {}
+static inline int alternatives_text_reserved(void *start, void *end)
+{
+ return 0;
+}
#endif /* CONFIG_SMP */
+#define OLDINSTR(oldinstr) "661:\n\t" oldinstr "\n662:\n"
+
+#define b_replacement(number) "663"#number
+#define e_replacement(number) "664"#number
+
+#define alt_slen "662b-661b"
+#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f"
+
+#define ALTINSTR_ENTRY(feature, number) \
+ " .long 661b - .\n" /* label */ \
+ " .long " b_replacement(number)"f - .\n" /* new instruction */ \
+ " .word " __stringify(feature) "\n" /* feature bit */ \
+ " .byte " alt_slen "\n" /* source len */ \
+ " .byte " alt_rlen(number) "\n" /* replacement len */
+
+#define DISCARD_ENTRY(number) /* rlen <= slen */ \
+ " .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n"
+
+#define ALTINSTR_REPLACEMENT(newinstr, feature, number) /* replacement */ \
+ b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t"
+
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
- \
- "661:\n\t" oldinstr "\n662:\n" \
- ".section .altinstructions,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR "661b\n" /* label */ \
- _ASM_PTR "663f\n" /* new instruction */ \
- " .byte " __stringify(feature) "\n" /* feature bit */ \
- " .byte 662b-661b\n" /* sourcelen */ \
- " .byte 664f-663f\n" /* replacementlen */ \
- " .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \
- ".previous\n" \
- ".section .altinstr_replacement, \"ax\"\n" \
- "663:\n\t" newinstr "\n664:\n" /* replacement */ \
- ".previous"
+ OLDINSTR(oldinstr) \
+ ".pushsection .altinstructions,\"a\"\n" \
+ ALTINSTR_ENTRY(feature, 1) \
+ ".popsection\n" \
+ ".pushsection .discard,\"aw\",@progbits\n" \
+ DISCARD_ENTRY(1) \
+ ".popsection\n" \
+ ".pushsection .altinstr_replacement, \"ax\"\n" \
+ ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
+ ".popsection"
+
+#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
+ OLDINSTR(oldinstr) \
+ ".pushsection .altinstructions,\"a\"\n" \
+ ALTINSTR_ENTRY(feature1, 1) \
+ ALTINSTR_ENTRY(feature2, 2) \
+ ".popsection\n" \
+ ".pushsection .discard,\"aw\",@progbits\n" \
+ DISCARD_ENTRY(1) \
+ DISCARD_ENTRY(2) \
+ ".popsection\n" \
+ ".pushsection .altinstr_replacement, \"ax\"\n" \
+ ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
+ ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
+ ".popsection"
+
+/*
+ * This must be included *after* the definition of ALTERNATIVE due to
+ * <asm/arch_hweight.h>
+ */
+#include <asm/cpufeature.h>
/*
* Alternative instructions for different CPU types or capabilities.
@@ -125,11 +166,35 @@ static inline void alternatives_smp_switch(int smp) {}
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
: output : "i" (0), ## input)
+/* Like alternative_io, but for replacing a direct call with another one. */
+#define alternative_call(oldfunc, newfunc, feature, output, input...) \
+ asm volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \
+ : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+
+/*
+ * Like alternative_call, but there are two features and respective functions.
+ * If CPU has feature2, function2 is used.
+ * Otherwise, if CPU has feature1, function1 is used.
+ * Otherwise, old function is used.
+ */
+#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
+ output, input...) \
+ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
+ "call %P[new2]", feature2) \
+ : output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
+ [new2] "i" (newfunc2), ## input)
+
/*
* use this macro(s) if you need more than one output parameter
* in alternative_io
*/
-#define ASM_OUTPUT2(a, b) a, b
+#define ASM_OUTPUT2(a...) a
+
+/*
+ * use this macro if you need clobbers but no inputs in
+ * alternative_{input,io,call}()
+ */
+#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
struct paravirt_patch_site;
#ifdef CONFIG_PARAVIRT
@@ -143,6 +208,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
#define __parainstructions_end NULL
#endif
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
/*
* Clear and restore the kernel write-protection flag on the local CPU.
* Allows the kernel to edit read-only pages.
@@ -154,11 +221,11 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
* no thread can be preempted in the instructions being modified (no iret to an
* invalid instruction possible) or if the instructions are changed from a
* consistent state to another consistent state atomically.
- * More care must be taken when modifying code in the SMP case because of
- * Intel's errata.
* On the local CPU you need to be protected again NMI or MCE handlers seeing an
* inconsistent instruction while you patch.
*/
extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern int poke_int3_handler(struct pt_regs *regs);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
#endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
deleted file mode 100644
index 5af2982133b..00000000000
--- a/arch/x86/include/asm/amd_iommu.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- * Leo Duran <leo.duran@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _ASM_X86_AMD_IOMMU_H
-#define _ASM_X86_AMD_IOMMU_H
-
-#include <linux/irqreturn.h>
-
-#ifdef CONFIG_AMD_IOMMU
-
-extern void amd_iommu_detect(void);
-
-#else
-
-static inline void amd_iommu_detect(void) { }
-
-#endif
-
-#endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
deleted file mode 100644
index d2544f1d705..00000000000
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/*
- * Copyright (C) 2009 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _ASM_X86_AMD_IOMMU_PROTO_H
-#define _ASM_X86_AMD_IOMMU_PROTO_H
-
-struct amd_iommu;
-
-extern int amd_iommu_init_dma_ops(void);
-extern int amd_iommu_init_passthrough(void);
-extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_flush_all_domains(void);
-extern void amd_iommu_flush_all_devices(void);
-extern void amd_iommu_apply_erratum_63(u16 devid);
-extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
-extern int amd_iommu_init_devices(void);
-extern void amd_iommu_uninit_devices(void);
-extern void amd_iommu_init_notifier(void);
-extern void amd_iommu_init_api(void);
-#ifndef CONFIG_AMD_IOMMU_STATS
-
-static inline void amd_iommu_stats_init(void) { }
-
-#endif /* !CONFIG_AMD_IOMMU_STATS */
-
-#endif /* _ASM_X86_AMD_IOMMU_PROTO_H */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
deleted file mode 100644
index ba19ad4c47d..00000000000
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ /dev/null
@@ -1,502 +0,0 @@
-/*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- * Leo Duran <leo.duran@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-#ifndef _ASM_X86_AMD_IOMMU_TYPES_H
-#define _ASM_X86_AMD_IOMMU_TYPES_H
-
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-/*
- * Maximum number of IOMMUs supported
- */
-#define MAX_IOMMUS 32
-
-/*
- * some size calculation constants
- */
-#define DEV_TABLE_ENTRY_SIZE 32
-#define ALIAS_TABLE_ENTRY_SIZE 2
-#define RLOOKUP_TABLE_ENTRY_SIZE (sizeof(void *))
-
-/* Length of the MMIO region for the AMD IOMMU */
-#define MMIO_REGION_LENGTH 0x4000
-
-/* Capability offsets used by the driver */
-#define MMIO_CAP_HDR_OFFSET 0x00
-#define MMIO_RANGE_OFFSET 0x0c
-#define MMIO_MISC_OFFSET 0x10
-
-/* Masks, shifts and macros to parse the device range capability */
-#define MMIO_RANGE_LD_MASK 0xff000000
-#define MMIO_RANGE_FD_MASK 0x00ff0000
-#define MMIO_RANGE_BUS_MASK 0x0000ff00
-#define MMIO_RANGE_LD_SHIFT 24
-#define MMIO_RANGE_FD_SHIFT 16
-#define MMIO_RANGE_BUS_SHIFT 8
-#define MMIO_GET_LD(x) (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT)
-#define MMIO_GET_FD(x) (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT)
-#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT)
-#define MMIO_MSI_NUM(x) ((x) & 0x1f)
-
-/* Flag masks for the AMD IOMMU exclusion range */
-#define MMIO_EXCL_ENABLE_MASK 0x01ULL
-#define MMIO_EXCL_ALLOW_MASK 0x02ULL
-
-/* Used offsets into the MMIO space */
-#define MMIO_DEV_TABLE_OFFSET 0x0000
-#define MMIO_CMD_BUF_OFFSET 0x0008
-#define MMIO_EVT_BUF_OFFSET 0x0010
-#define MMIO_CONTROL_OFFSET 0x0018
-#define MMIO_EXCL_BASE_OFFSET 0x0020
-#define MMIO_EXCL_LIMIT_OFFSET 0x0028
-#define MMIO_CMD_HEAD_OFFSET 0x2000
-#define MMIO_CMD_TAIL_OFFSET 0x2008
-#define MMIO_EVT_HEAD_OFFSET 0x2010
-#define MMIO_EVT_TAIL_OFFSET 0x2018
-#define MMIO_STATUS_OFFSET 0x2020
-
-/* MMIO status bits */
-#define MMIO_STATUS_COM_WAIT_INT_MASK 0x04
-
-/* event logging constants */
-#define EVENT_ENTRY_SIZE 0x10
-#define EVENT_TYPE_SHIFT 28
-#define EVENT_TYPE_MASK 0xf
-#define EVENT_TYPE_ILL_DEV 0x1
-#define EVENT_TYPE_IO_FAULT 0x2
-#define EVENT_TYPE_DEV_TAB_ERR 0x3
-#define EVENT_TYPE_PAGE_TAB_ERR 0x4
-#define EVENT_TYPE_ILL_CMD 0x5
-#define EVENT_TYPE_CMD_HARD_ERR 0x6
-#define EVENT_TYPE_IOTLB_INV_TO 0x7
-#define EVENT_TYPE_INV_DEV_REQ 0x8
-#define EVENT_DEVID_MASK 0xffff
-#define EVENT_DEVID_SHIFT 0
-#define EVENT_DOMID_MASK 0xffff
-#define EVENT_DOMID_SHIFT 0
-#define EVENT_FLAGS_MASK 0xfff
-#define EVENT_FLAGS_SHIFT 0x10
-
-/* feature control bits */
-#define CONTROL_IOMMU_EN 0x00ULL
-#define CONTROL_HT_TUN_EN 0x01ULL
-#define CONTROL_EVT_LOG_EN 0x02ULL
-#define CONTROL_EVT_INT_EN 0x03ULL
-#define CONTROL_COMWAIT_EN 0x04ULL
-#define CONTROL_PASSPW_EN 0x08ULL
-#define CONTROL_RESPASSPW_EN 0x09ULL
-#define CONTROL_COHERENT_EN 0x0aULL
-#define CONTROL_ISOC_EN 0x0bULL
-#define CONTROL_CMDBUF_EN 0x0cULL
-#define CONTROL_PPFLOG_EN 0x0dULL
-#define CONTROL_PPFINT_EN 0x0eULL
-
-/* command specific defines */
-#define CMD_COMPL_WAIT 0x01
-#define CMD_INV_DEV_ENTRY 0x02
-#define CMD_INV_IOMMU_PAGES 0x03
-
-#define CMD_COMPL_WAIT_STORE_MASK 0x01
-#define CMD_COMPL_WAIT_INT_MASK 0x02
-#define CMD_INV_IOMMU_PAGES_SIZE_MASK 0x01
-#define CMD_INV_IOMMU_PAGES_PDE_MASK 0x02
-
-#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS 0x7fffffffffffffffULL
-
-/* macros and definitions for device table entries */
-#define DEV_ENTRY_VALID 0x00
-#define DEV_ENTRY_TRANSLATION 0x01
-#define DEV_ENTRY_IR 0x3d
-#define DEV_ENTRY_IW 0x3e
-#define DEV_ENTRY_NO_PAGE_FAULT 0x62
-#define DEV_ENTRY_EX 0x67
-#define DEV_ENTRY_SYSMGT1 0x68
-#define DEV_ENTRY_SYSMGT2 0x69
-#define DEV_ENTRY_INIT_PASS 0xb8
-#define DEV_ENTRY_EINT_PASS 0xb9
-#define DEV_ENTRY_NMI_PASS 0xba
-#define DEV_ENTRY_LINT0_PASS 0xbe
-#define DEV_ENTRY_LINT1_PASS 0xbf
-#define DEV_ENTRY_MODE_MASK 0x07
-#define DEV_ENTRY_MODE_SHIFT 0x09
-
-/* constants to configure the command buffer */
-#define CMD_BUFFER_SIZE 8192
-#define CMD_BUFFER_ENTRIES 512
-#define MMIO_CMD_SIZE_SHIFT 56
-#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
-
-/* constants for event buffer handling */
-#define EVT_BUFFER_SIZE 8192 /* 512 entries */
-#define EVT_LEN_MASK (0x9ULL << 56)
-
-#define PAGE_MODE_NONE 0x00
-#define PAGE_MODE_1_LEVEL 0x01
-#define PAGE_MODE_2_LEVEL 0x02
-#define PAGE_MODE_3_LEVEL 0x03
-#define PAGE_MODE_4_LEVEL 0x04
-#define PAGE_MODE_5_LEVEL 0x05
-#define PAGE_MODE_6_LEVEL 0x06
-
-#define PM_LEVEL_SHIFT(x) (12 + ((x) * 9))
-#define PM_LEVEL_SIZE(x) (((x) < 6) ? \
- ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \
- (0xffffffffffffffffULL))
-#define PM_LEVEL_INDEX(x, a) (((a) >> PM_LEVEL_SHIFT((x))) & 0x1ffULL)
-#define PM_LEVEL_ENC(x) (((x) << 9) & 0xe00ULL)
-#define PM_LEVEL_PDE(x, a) ((a) | PM_LEVEL_ENC((x)) | \
- IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-#define PM_PTE_LEVEL(pte) (((pte) >> 9) & 0x7ULL)
-
-#define PM_MAP_4k 0
-#define PM_ADDR_MASK 0x000ffffffffff000ULL
-#define PM_MAP_MASK(lvl) (PM_ADDR_MASK & \
- (~((1ULL << (12 + ((lvl) * 9))) - 1)))
-#define PM_ALIGNED(lvl, addr) ((PM_MAP_MASK(lvl) & (addr)) == (addr))
-
-#define IOMMU_PTE_P (1ULL << 0)
-#define IOMMU_PTE_TV (1ULL << 1)
-#define IOMMU_PTE_U (1ULL << 59)
-#define IOMMU_PTE_FC (1ULL << 60)
-#define IOMMU_PTE_IR (1ULL << 61)
-#define IOMMU_PTE_IW (1ULL << 62)
-
-#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
-#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
-#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
-#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07)
-
-#define IOMMU_PROT_MASK 0x03
-#define IOMMU_PROT_IR 0x01
-#define IOMMU_PROT_IW 0x02
-
-/* IOMMU capabilities */
-#define IOMMU_CAP_IOTLB 24
-#define IOMMU_CAP_NPCACHE 26
-
-#define MAX_DOMAIN_ID 65536
-
-/* FIXME: move this macro to <linux/pci.h> */
-#define PCI_BUS(x) (((x) >> 8) & 0xff)
-
-/* Protection domain flags */
-#define PD_DMA_OPS_MASK (1UL << 0) /* domain used for dma_ops */
-#define PD_DEFAULT_MASK (1UL << 1) /* domain is a default dma_ops
- domain for an IOMMU */
-#define PD_PASSTHROUGH_MASK (1UL << 2) /* domain has no page
- translation */
-
-extern bool amd_iommu_dump;
-#define DUMP_printk(format, arg...) \
- do { \
- if (amd_iommu_dump) \
- printk(KERN_INFO "AMD-Vi: " format, ## arg); \
- } while(0);
-
-/* global flag if IOMMUs cache non-present entries */
-extern bool amd_iommu_np_cache;
-
-/*
- * Make iterating over all IOMMUs easier
- */
-#define for_each_iommu(iommu) \
- list_for_each_entry((iommu), &amd_iommu_list, list)
-#define for_each_iommu_safe(iommu, next) \
- list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
-
-#define APERTURE_RANGE_SHIFT 27 /* 128 MB */
-#define APERTURE_RANGE_SIZE (1ULL << APERTURE_RANGE_SHIFT)
-#define APERTURE_RANGE_PAGES (APERTURE_RANGE_SIZE >> PAGE_SHIFT)
-#define APERTURE_MAX_RANGES 32 /* allows 4GB of DMA address space */
-#define APERTURE_RANGE_INDEX(a) ((a) >> APERTURE_RANGE_SHIFT)
-#define APERTURE_PAGE_INDEX(a) (((a) >> 21) & 0x3fULL)
-
-/*
- * This structure contains generic data for IOMMU protection domains
- * independent of their use.
- */
-struct protection_domain {
- struct list_head list; /* for list of all protection domains */
- struct list_head dev_list; /* List of all devices in this domain */
- spinlock_t lock; /* mostly used to lock the page table*/
- u16 id; /* the domain id written to the device table */
- int mode; /* paging mode (0-6 levels) */
- u64 *pt_root; /* page table root pointer */
- unsigned long flags; /* flags to find out type of domain */
- bool updated; /* complete domain flush required */
- unsigned dev_cnt; /* devices assigned to this domain */
- unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */
- void *priv; /* private data */
-
-};
-
-/*
- * This struct contains device specific data for the IOMMU
- */
-struct iommu_dev_data {
- struct list_head list; /* For domain->dev_list */
- struct device *dev; /* Device this data belong to */
- struct device *alias; /* The Alias Device */
- struct protection_domain *domain; /* Domain the device is bound to */
- atomic_t bind; /* Domain attach reverent count */
-};
-
-/*
- * For dynamic growth the aperture size is split into ranges of 128MB of
- * DMA address space each. This struct represents one such range.
- */
-struct aperture_range {
-
- /* address allocation bitmap */
- unsigned long *bitmap;
-
- /*
- * Array of PTE pages for the aperture. In this array we save all the
- * leaf pages of the domain page table used for the aperture. This way
- * we don't need to walk the page table to find a specific PTE. We can
- * just calculate its address in constant time.
- */
- u64 *pte_pages[64];
-
- unsigned long offset;
-};
-
-/*
- * Data container for a dma_ops specific protection domain
- */
-struct dma_ops_domain {
- struct list_head list;
-
- /* generic protection domain information */
- struct protection_domain domain;
-
- /* size of the aperture for the mappings */
- unsigned long aperture_size;
-
- /* address we start to search for free addresses */
- unsigned long next_address;
-
- /* address space relevant data */
- struct aperture_range *aperture[APERTURE_MAX_RANGES];
-
- /* This will be set to true when TLB needs to be flushed */
- bool need_flush;
-
- /*
- * if this is a preallocated domain, keep the device for which it was
- * preallocated in this variable
- */
- u16 target_dev;
-};
-
-/*
- * Structure where we save information about one hardware AMD IOMMU in the
- * system.
- */
-struct amd_iommu {
- struct list_head list;
-
- /* Index within the IOMMU array */
- int index;
-
- /* locks the accesses to the hardware */
- spinlock_t lock;
-
- /* Pointer to PCI device of this IOMMU */
- struct pci_dev *dev;
-
- /* physical address of MMIO space */
- u64 mmio_phys;
- /* virtual address of MMIO space */
- u8 *mmio_base;
-
- /* capabilities of that IOMMU read from ACPI */
- u32 cap;
-
- /*
- * Capability pointer. There could be more than one IOMMU per PCI
- * device function if there are more than one AMD IOMMU capability
- * pointers.
- */
- u16 cap_ptr;
-
- /* pci domain of this IOMMU */
- u16 pci_seg;
-
- /* first device this IOMMU handles. read from PCI */
- u16 first_device;
- /* last device this IOMMU handles. read from PCI */
- u16 last_device;
-
- /* start of exclusion range of that IOMMU */
- u64 exclusion_start;
- /* length of exclusion range of that IOMMU */
- u64 exclusion_length;
-
- /* command buffer virtual address */
- u8 *cmd_buf;
- /* size of command buffer */
- u32 cmd_buf_size;
-
- /* size of event buffer */
- u32 evt_buf_size;
- /* event buffer virtual address */
- u8 *evt_buf;
- /* MSI number for event interrupt */
- u16 evt_msi_num;
-
- /* true if interrupts for this IOMMU are already enabled */
- bool int_enabled;
-
- /* if one, we need to send a completion wait command */
- bool need_sync;
-
- /* becomes true if a command buffer reset is running */
- bool reset_in_progress;
-
- /* default dma_ops domain for that IOMMU */
- struct dma_ops_domain *default_dom;
-};
-
-/*
- * List with all IOMMUs in the system. This list is not locked because it is
- * only written and read at driver initialization or suspend time
- */
-extern struct list_head amd_iommu_list;
-
-/*
- * Array with pointers to each IOMMU struct
- * The indices are referenced in the protection domains
- */
-extern struct amd_iommu *amd_iommus[MAX_IOMMUS];
-
-/* Number of IOMMUs present in the system */
-extern int amd_iommus_present;
-
-/*
- * Declarations for the global list of all protection domains
- */
-extern spinlock_t amd_iommu_pd_lock;
-extern struct list_head amd_iommu_pd_list;
-
-/*
- * Structure defining one entry in the device table
- */
-struct dev_table_entry {
- u32 data[8];
-};
-
-/*
- * One entry for unity mappings parsed out of the ACPI table.
- */
-struct unity_map_entry {
- struct list_head list;
-
- /* starting device id this entry is used for (including) */
- u16 devid_start;
- /* end device id this entry is used for (including) */
- u16 devid_end;
-
- /* start address to unity map (including) */
- u64 address_start;
- /* end address to unity map (including) */
- u64 address_end;
-
- /* required protection */
- int prot;
-};
-
-/*
- * List of all unity mappings. It is not locked because as runtime it is only
- * read. It is created at ACPI table parsing time.
- */
-extern struct list_head amd_iommu_unity_map;
-
-/*
- * Data structures for device handling
- */
-
-/*
- * Device table used by hardware. Read and write accesses by software are
- * locked with the amd_iommu_pd_table lock.
- */
-extern struct dev_table_entry *amd_iommu_dev_table;
-
-/*
- * Alias table to find requestor ids to device ids. Not locked because only
- * read on runtime.
- */
-extern u16 *amd_iommu_alias_table;
-
-/*
- * Reverse lookup table to find the IOMMU which translates a specific device.
- */
-extern struct amd_iommu **amd_iommu_rlookup_table;
-
-/* size of the dma_ops aperture as power of 2 */
-extern unsigned amd_iommu_aperture_order;
-
-/* largest PCI device id we expect translation requests for */
-extern u16 amd_iommu_last_bdf;
-
-/* allocation bitmap for domain ids */
-extern unsigned long *amd_iommu_pd_alloc_bitmap;
-
-/*
- * If true, the addresses will be flushed on unmap time, not when
- * they are reused
- */
-extern bool amd_iommu_unmap_flush;
-
-/* takes bus and device/function and returns the device id
- * FIXME: should that be in generic PCI code? */
-static inline u16 calc_devid(u8 bus, u8 devfn)
-{
- return (((u16)bus) << 8) | devfn;
-}
-
-#ifdef CONFIG_AMD_IOMMU_STATS
-
-struct __iommu_counter {
- char *name;
- struct dentry *dent;
- u64 value;
-};
-
-#define DECLARE_STATS_COUNTER(nm) \
- static struct __iommu_counter nm = { \
- .name = #nm, \
- }
-
-#define INC_STATS_COUNTER(name) name.value += 1
-#define ADD_STATS_COUNTER(name, x) name.value += (x)
-#define SUB_STATS_COUNTER(name, x) name.value -= (x)
-
-#else /* CONFIG_AMD_IOMMU_STATS */
-
-#define DECLARE_STATS_COUNTER(name)
-#define INC_STATS_COUNTER(name)
-#define ADD_STATS_COUNTER(name, x)
-#define SUB_STATS_COUNTER(name, x)
-
-#endif /* CONFIG_AMD_IOMMU_STATS */
-
-#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
new file mode 100644
index 00000000000..aaac3b2fb74
--- /dev/null
+++ b/arch/x86/include/asm/amd_nb.h
@@ -0,0 +1,110 @@
+#ifndef _ASM_X86_AMD_NB_H
+#define _ASM_X86_AMD_NB_H
+
+#include <linux/ioport.h>
+#include <linux/pci.h>
+
+struct amd_nb_bus_dev_range {
+ u8 bus;
+ u8 dev_base;
+ u8 dev_limit;
+};
+
+extern const struct pci_device_id amd_nb_misc_ids[];
+extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[];
+
+extern bool early_is_amd_nb(u32 value);
+extern struct resource *amd_get_mmconfig_range(struct resource *res);
+extern int amd_cache_northbridges(void);
+extern void amd_flush_garts(void);
+extern int amd_numa_init(void);
+extern int amd_get_subcaches(int);
+extern int amd_set_subcaches(int, unsigned long);
+
+struct amd_l3_cache {
+ unsigned indices;
+ u8 subcaches[4];
+};
+
+struct threshold_block {
+ unsigned int block;
+ unsigned int bank;
+ unsigned int cpu;
+ u32 address;
+ u16 interrupt_enable;
+ bool interrupt_capable;
+ u16 threshold_limit;
+ struct kobject kobj;
+ struct list_head miscj;
+};
+
+struct threshold_bank {
+ struct kobject *kobj;
+ struct threshold_block *blocks;
+
+ /* initialized to the number of CPUs on the node sharing this bank */
+ atomic_t cpus;
+};
+
+struct amd_northbridge {
+ struct pci_dev *misc;
+ struct pci_dev *link;
+ struct amd_l3_cache l3_cache;
+ struct threshold_bank *bank4;
+};
+
+struct amd_northbridge_info {
+ u16 num;
+ u64 flags;
+ struct amd_northbridge *nb;
+};
+extern struct amd_northbridge_info amd_northbridges;
+
+#define AMD_NB_GART BIT(0)
+#define AMD_NB_L3_INDEX_DISABLE BIT(1)
+#define AMD_NB_L3_PARTITIONING BIT(2)
+
+#ifdef CONFIG_AMD_NB
+
+static inline u16 amd_nb_num(void)
+{
+ return amd_northbridges.num;
+}
+
+static inline bool amd_nb_has_feature(unsigned feature)
+{
+ return ((amd_northbridges.flags & feature) == feature);
+}
+
+static inline struct amd_northbridge *node_to_amd_nb(int node)
+{
+ return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
+}
+
+static inline u16 amd_get_node_id(struct pci_dev *pdev)
+{
+ struct pci_dev *misc;
+ int i;
+
+ for (i = 0; i != amd_nb_num(); i++) {
+ misc = node_to_amd_nb(i)->misc;
+
+ if (pci_domain_nr(misc->bus) == pci_domain_nr(pdev->bus) &&
+ PCI_SLOT(misc->devfn) == PCI_SLOT(pdev->devfn))
+ return i;
+ }
+
+ WARN(1, "Unable to find AMD Northbridge id for %s\n", pci_name(pdev));
+ return 0;
+}
+
+#else
+
+#define amd_nb_num(x) 0
+#define amd_nb_has_feature(x) false
+#define node_to_amd_nb(x) NULL
+
+#endif
+
+
+#endif /* _ASM_X86_AMD_NB_H */
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
new file mode 100644
index 00000000000..0acbac299e4
--- /dev/null
+++ b/arch/x86/include/asm/apb_timer.h
@@ -0,0 +1,49 @@
+/*
+ * apb_timer.h: Driver for Langwell APB timer based on Synopsis DesignWare
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Note:
+ */
+
+#ifndef ASM_X86_APBT_H
+#define ASM_X86_APBT_H
+#include <linux/sfi.h>
+
+#ifdef CONFIG_APB_TIMER
+
+/* default memory mapped register base */
+#define LNW_SCU_ADDR 0xFF100000
+#define LNW_EXT_TIMER_OFFSET 0x1B800
+#define APBT_DEFAULT_BASE (LNW_SCU_ADDR+LNW_EXT_TIMER_OFFSET)
+#define LNW_EXT_TIMER_PGOFFSET 0x800
+
+/* APBT clock speed range from PCLK to fabric base, 25-100MHz */
+#define APBT_MAX_FREQ 50000000
+#define APBT_MIN_FREQ 1000000
+#define APBT_MMAP_SIZE 1024
+
+#define APBT_DEV_USED 1
+
+extern void apbt_time_init(void);
+extern unsigned long apbt_quick_calibrate(void);
+extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
+extern void apbt_setup_secondary_clock(void);
+
+extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
+extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
+extern int sfi_mtimer_num;
+
+#else /* CONFIG_APB_TIMER */
+
+static inline unsigned long apbt_quick_calibrate(void) {return 0; }
+static inline void apbt_time_init(void) { }
+
+#endif
+#endif /* ASM_X86_APBT_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index b4ac2cdcb64..19b0ebafcd3 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -2,18 +2,17 @@
#define _ASM_X86_APIC_H
#include <linux/cpumask.h>
-#include <linux/delay.h>
#include <linux/pm.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/processor.h>
#include <asm/apicdef.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/fixmap.h>
#include <asm/mpspec.h>
-#include <asm/system.h>
#include <asm/msr.h>
+#include <asm/idle.h>
#define ARCH_APICTIMER_STOPS_ON_C3 1
@@ -50,6 +49,7 @@ extern unsigned int apic_verbosity;
extern int local_apic_timer_c2_ok;
extern int disable_apic;
+extern unsigned int lapic_timer_frequency;
#ifdef CONFIG_SMP
extern void __inquire_remote_apic(int apicid);
@@ -93,9 +93,6 @@ static inline int is_vsmp_box(void)
return 0;
}
#endif
-extern void xapic_wait_icr_idle(void);
-extern u32 safe_xapic_wait_icr_idle(void);
-extern void xapic_icr_write(u32, u32);
extern int setup_profiling_timer(unsigned int);
static inline void native_apic_mem_write(u32 reg, u32 v)
@@ -139,15 +136,20 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
}
+static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
+{
+ wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+}
+
static inline u32 native_apic_msr_read(u32 reg)
{
- u32 low, high;
+ u64 msr;
if (reg == APIC_DFR)
return -1;
- rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
- return low;
+ rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+ return (u32)msr;
}
static inline void native_x2apic_wait_icr_idle(void)
@@ -176,17 +178,17 @@ static inline u64 native_x2apic_icr_read(void)
}
extern int x2apic_phys;
+extern int x2apic_preenabled;
extern void check_x2apic(void);
extern void enable_x2apic(void);
-extern void x2apic_icr_write(u32 low, u32 id);
static inline int x2apic_enabled(void)
{
- int msr, msr2;
+ u64 msr;
if (!cpu_has_x2apic)
return 0;
- rdmsr(MSR_IA32_APICBASE, msr, msr2);
+ rdmsrl(MSR_IA32_APICBASE, msr);
if (msr & X2APIC_ENABLE)
return 1;
return 0;
@@ -198,6 +200,9 @@ static inline void x2apic_force_phys(void)
x2apic_phys = 1;
}
#else
+static inline void disable_x2apic(void)
+{
+}
static inline void check_x2apic(void)
{
}
@@ -220,7 +225,6 @@ extern void enable_IR_x2apic(void);
extern int get_physical_broadcast(void);
-extern void apic_disable(void);
extern int lapic_get_maxlvt(void);
extern void clear_local_APIC(void);
extern void connect_bsp_APIC(void);
@@ -228,22 +232,22 @@ extern void disconnect_bsp_APIC(int virt_wire_setup);
extern void disable_local_APIC(void);
extern void lapic_shutdown(void);
extern int verify_local_APIC(void);
-extern void cache_APIC_registers(void);
extern void sync_Arb_IDs(void);
extern void init_bsp_APIC(void);
extern void setup_local_APIC(void);
extern void end_local_APIC_setup(void);
+extern void bsp_end_local_APIC_setup(void);
extern void init_apic_mappings(void);
+void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
extern void setup_secondary_APIC_clock(void);
extern int APIC_init_uniprocessor(void);
-extern void enable_NMI_through_LVT0(void);
+extern int apic_force_enable(unsigned long addr);
/*
* On 32bit this is mach-xxx local
*/
#ifdef CONFIG_X86_64
-extern void early_init_lapic_mapping(void);
extern int apic_is_clustered_box(void);
#else
static inline int apic_is_clustered_box(void)
@@ -252,16 +256,13 @@ static inline int apic_is_clustered_box(void)
}
#endif
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
#else /* !CONFIG_X86_LOCAL_APIC */
static inline void lapic_shutdown(void) { }
#define local_apic_timer_c2_ok 1
static inline void init_apic_mappings(void) { }
static inline void disable_local_APIC(void) { }
-static inline void apic_disable(void) { }
# define setup_boot_APIC_clock x86_init_noop
# define setup_secondary_APIC_clock x86_init_noop
#endif /* !CONFIG_X86_LOCAL_APIC */
@@ -287,6 +288,7 @@ struct apic {
int (*probe)(void);
int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+ int (*apic_id_valid)(int apicid);
int (*apic_id_registered)(void);
u32 irq_delivery_mode;
@@ -300,15 +302,14 @@ struct apic {
unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid);
unsigned long (*check_apicid_present)(int apicid);
- void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+ void (*vector_allocation_domain)(int cpu, struct cpumask *retmask,
+ const struct cpumask *mask);
void (*init_apic_ldr)(void);
void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
void (*setup_apic_routing)(void);
int (*multi_timer_check)(int apic, int irq);
- int (*apicid_to_node)(int logical_apicid);
- int (*cpu_to_logical_apicid)(int cpu);
int (*cpu_present_to_apicid)(int mps_cpu);
void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
void (*setup_portio_remap)(void);
@@ -327,9 +328,9 @@ struct apic {
unsigned long (*set_apic_id)(unsigned int id);
unsigned long apic_id_mask;
- unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
- unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
- const struct cpumask *andmask);
+ int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+ const struct cpumask *andmask,
+ unsigned int *apicid);
/* ipi */
void (*send_IPI_mask)(const struct cpumask *mask, int vector);
@@ -345,17 +346,47 @@ struct apic {
int trampoline_phys_low;
int trampoline_phys_high;
- void (*wait_for_init_deassert)(atomic_t *deassert);
+ bool wait_for_init_deassert;
void (*smp_callin_clear_local_apic)(void);
void (*inquire_remote_apic)(int apicid);
/* apic ops */
u32 (*read)(u32 reg);
void (*write)(u32 reg, u32 v);
+ /*
+ * ->eoi_write() has the same signature as ->write().
+ *
+ * Drivers can support both ->eoi_write() and ->write() by passing the same
+ * callback value. Kernel can override ->eoi_write() and fall back
+ * on write for EOI.
+ */
+ void (*eoi_write)(u32 reg, u32 v);
u64 (*icr_read)(void);
void (*icr_write)(u32 low, u32 high);
void (*wait_icr_idle)(void);
u32 (*safe_wait_icr_idle)(void);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Called very early during boot from get_smp_config(). It should
+ * return the logical apicid. x86_[bios]_cpu_to_apicid is
+ * initialized before this function is called.
+ *
+ * If logical apicid can't be determined that early, the function
+ * may return BAD_APICID. Logical apicid will be configured after
+ * init_apic_ldr() while bringing up CPUs. Note that NUMA affinity
+ * won't be applied properly during early boot in this case.
+ */
+ int (*x86_32_early_logical_apicid)(int cpu);
+
+ /*
+ * Optional method called from setup_local_APIC() after logical
+ * apicid is guaranteed to be known to initialize apicid -> node
+ * mapping if NUMA initialization hasn't done so already. Don't
+ * add new users.
+ */
+ int (*x86_32_numa_cpu_node)(int cpu);
+#endif
};
/*
@@ -366,6 +397,26 @@ struct apic {
extern struct apic *apic;
/*
+ * APIC drivers are probed based on how they are listed in the .apicdrivers
+ * section. So the order is important and enforced by the ordering
+ * of different apic driver files in the Makefile.
+ *
+ * For the files having two apic drivers, we use apic_drivers()
+ * to enforce the order with in them.
+ */
+#define apic_driver(sym) \
+ static const struct apic *__apicdrivers_##sym __used \
+ __aligned(sizeof(struct apic *)) \
+ __section(.apicdrivers) = { &sym }
+
+#define apic_drivers(sym1, sym2) \
+ static struct apic *__apicdrivers_##sym1##sym2[2] __used \
+ __aligned(sizeof(struct apic *)) \
+ __section(.apicdrivers) = { &sym1, &sym2 }
+
+extern struct apic *__apicdrivers[], *__apicdrivers_end[];
+
+/*
* APIC functionality to boot other CPUs - only used on SMP:
*/
#ifdef CONFIG_SMP
@@ -373,6 +424,8 @@ extern atomic_t init_deasserted;
extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
#endif
+#ifdef CONFIG_X86_LOCAL_APIC
+
static inline u32 apic_read(u32 reg)
{
return apic->read(reg);
@@ -383,6 +436,11 @@ static inline void apic_write(u32 reg, u32 val)
apic->write(reg, val);
}
+static inline void apic_eoi(void)
+{
+ apic->eoi_write(APIC_EOI, APIC_EOI_ACK);
+}
+
static inline u64 apic_icr_read(void)
{
return apic->icr_read();
@@ -403,18 +461,28 @@ static inline u32 safe_apic_wait_icr_idle(void)
return apic->safe_wait_icr_idle();
}
+extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v));
+
+#else /* CONFIG_X86_LOCAL_APIC */
+
+static inline u32 apic_read(u32 reg) { return 0; }
+static inline void apic_write(u32 reg, u32 val) { }
+static inline void apic_eoi(void) { }
+static inline u64 apic_icr_read(void) { return 0; }
+static inline void apic_icr_write(u32 low, u32 high) { }
+static inline void apic_wait_icr_idle(void) { }
+static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {}
+
+#endif /* CONFIG_X86_LOCAL_APIC */
static inline void ack_APIC_irq(void)
{
-#ifdef CONFIG_X86_LOCAL_APIC
/*
* ack_APIC_irq() actually gets compiled as a single instruction
* ... yummie.
*/
-
- /* Docs say use 0 for future compatibility */
- apic_write(APIC_EOI, 0);
-#endif
+ apic_eoi();
}
static inline unsigned default_get_apic_id(unsigned long x)
@@ -434,28 +502,16 @@ static inline unsigned default_get_apic_id(unsigned long x)
#define DEFAULT_TRAMPOLINE_PHYS_HIGH 0x469
#ifdef CONFIG_X86_64
-extern struct apic apic_flat;
-extern struct apic apic_physflat;
-extern struct apic apic_x2apic_cluster;
-extern struct apic apic_x2apic_phys;
extern int default_acpi_madt_oem_check(char *, char *);
extern void apic_send_IPI_self(int vector);
-extern struct apic apic_x2apic_uv_x;
DECLARE_PER_CPU(int, x2apic_extra_bits);
extern int default_cpu_present_to_apicid(int mps_cpu);
extern int default_check_phys_apicid_present(int phys_apicid);
#endif
-static inline void default_wait_for_init_deassert(atomic_t *deassert)
-{
- while (!atomic_read(deassert))
- cpu_relax();
- return;
-}
-
extern void generic_bigsmp_probe(void);
@@ -474,7 +530,12 @@ static inline const struct cpumask *default_target_cpus(void)
#endif
}
-DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+static inline const struct cpumask *online_target_cpus(void)
+{
+ return cpu_online_mask;
+}
+
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
static inline unsigned int read_apic_id(void)
@@ -486,13 +547,21 @@ static inline unsigned int read_apic_id(void)
return apic->get_apic_id(reg);
}
+static inline int default_apic_id_valid(int apicid)
+{
+ return (apicid < 255);
+}
+
extern void default_setup_apic_routing(void);
extern struct apic apic_noop;
#ifdef CONFIG_X86_32
-extern struct apic apic_default;
+static inline int noop_x86_32_early_logical_apicid(int cpu)
+{
+ return BAD_APICID;
+}
/*
* Set up the logical destination ID.
@@ -513,25 +582,52 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
return cpuid_apic >> index_msb;
}
-extern int default_apicid_to_node(int logical_apicid);
-
#endif
-static inline unsigned int
-default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+static inline int
+flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+ const struct cpumask *andmask,
+ unsigned int *apicid)
{
- return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+ unsigned long cpu_mask = cpumask_bits(cpumask)[0] &
+ cpumask_bits(andmask)[0] &
+ cpumask_bits(cpu_online_mask)[0] &
+ APIC_ALL_CPUS;
+
+ if (likely(cpu_mask)) {
+ *apicid = (unsigned int)cpu_mask;
+ return 0;
+ } else {
+ return -EINVAL;
+ }
}
-static inline unsigned int
+extern int
default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
- const struct cpumask *andmask)
-{
- unsigned long mask1 = cpumask_bits(cpumask)[0];
- unsigned long mask2 = cpumask_bits(andmask)[0];
- unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+ const struct cpumask *andmask,
+ unsigned int *apicid);
+
+static inline void
+flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
+ const struct cpumask *mask)
+{
+ /* Careful. Some cpus do not strictly honor the set of cpus
+ * specified in the interrupt destination when using lowest
+ * priority interrupt delivery mode.
+ *
+ * In particular there was a hyperthreading cpu observed to
+ * deliver interrupts to the wrong hyperthread when only one
+ * hyperthread was specified in the interrupt desitination.
+ */
+ cpumask_clear(retmask);
+ cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
+}
- return (unsigned int)(mask1 & mask2 & mask3);
+static inline void
+default_vector_allocation_domain(int cpu, struct cpumask *retmask,
+ const struct cpumask *mask)
+{
+ cpumask_copy(retmask, cpumask_of(cpu));
}
static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid)
@@ -549,12 +645,6 @@ static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_ma
*retmap = *phys_map;
}
-/* Mapping from cpu number to logical apicid */
-static inline int default_cpu_to_logical_apicid(int cpu)
-{
- return 1 << cpu;
-}
-
static inline int __default_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
@@ -586,9 +676,33 @@ extern int default_check_phys_apicid_present(int phys_apicid);
#endif
#endif /* CONFIG_X86_LOCAL_APIC */
+extern void irq_enter(void);
+extern void irq_exit(void);
-#ifdef CONFIG_X86_32
-extern u8 cpu_2_logical_apicid[NR_CPUS];
-#endif
+static inline void entering_irq(void)
+{
+ irq_enter();
+ exit_idle();
+}
+
+static inline void entering_ack_irq(void)
+{
+ ack_APIC_irq();
+ entering_irq();
+}
+
+static inline void exiting_irq(void)
+{
+ irq_exit();
+}
+
+static inline void exiting_ack_irq(void)
+{
+ irq_exit();
+ /* Ack only at the end to avoid potential reentry */
+ ack_APIC_irq();
+}
+
+extern void ioapic_zap_locks(void);
#endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/apic_flat_64.h b/arch/x86/include/asm/apic_flat_64.h
new file mode 100644
index 00000000000..a2d31279644
--- /dev/null
+++ b/arch/x86/include/asm/apic_flat_64.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_APIC_FLAT_64_H
+#define _ASM_X86_APIC_FLAT_64_H
+
+extern void flat_init_apic_ldr(void);
+
+#endif
+
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 7fe3b3060f0..c46bb99d5fb 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -37,7 +37,7 @@
#define APIC_ARBPRI_MASK 0xFFu
#define APIC_PROCPRI 0xA0
#define APIC_EOI 0xB0
-#define APIC_EIO_ACK 0x0
+#define APIC_EOI_ACK 0x0 /* Docs say 0 for future compat. */
#define APIC_RRR 0xC0
#define APIC_LDR 0xD0
#define APIC_LDR_MASK (0xFFu << 24)
@@ -78,6 +78,7 @@
#define APIC_DEST_LOGICAL 0x00800
#define APIC_DEST_PHYSICAL 0x00000
#define APIC_DM_FIXED 0x00000
+#define APIC_DM_FIXED_MASK 0x00700
#define APIC_DM_LOWEST 0x00100
#define APIC_DM_SMI 0x00200
#define APIC_DM_REMRD 0x00300
@@ -99,7 +100,9 @@
#define APIC_TIMER_BASE_CLKIN 0x0
#define APIC_TIMER_BASE_TMBASE 0x1
#define APIC_TIMER_BASE_DIV 0x2
+#define APIC_LVT_TIMER_ONESHOT (0 << 17)
#define APIC_LVT_TIMER_PERIODIC (1 << 17)
+#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17)
#define APIC_LVT_MASKED (1 << 16)
#define APIC_LVT_LEVEL_TRIGGER (1 << 15)
#define APIC_LVT_REMOTE_IRR (1 << 14)
@@ -131,6 +134,7 @@
#define APIC_EILVTn(n) (0x500 + 0x10 * n)
#define APIC_EILVT_NR_AMD_K8 1 /* # of extended interrupts */
#define APIC_EILVT_NR_AMD_10H 4
+#define APIC_EILVT_NR_MAX APIC_EILVT_NR_AMD_10H
#define APIC_EILVT_LVTOFF(x) (((x) >> 4) & 0xF)
#define APIC_EILVT_MSG_FIX 0x0
#define APIC_EILVT_MSG_SMI 0x2
@@ -140,10 +144,12 @@
#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
#define APIC_BASE_MSR 0x800
+#define XAPIC_ENABLE (1UL << 11)
#define X2APIC_ENABLE (1UL << 10)
#ifdef CONFIG_X86_32
# define MAX_IO_APICS 64
+# define MAX_LOCAL_APIC 256
#else
# define MAX_IO_APICS 128
# define MAX_LOCAL_APIC 32768
@@ -424,4 +430,16 @@ struct local_apic {
#else
#define BAD_APICID 0xFFFFu
#endif
+
+enum ioapic_irq_destination_types {
+ dest_Fixed = 0,
+ dest_LowestPrio = 1,
+ dest_SMI = 2,
+ dest__reserved_1 = 3,
+ dest_NMI = 4,
+ dest_INIT = 5,
+ dest__reserved_2 = 6,
+ dest_ExtINT = 7
+};
+
#endif /* _ASM_X86_APICDEF_H */
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
new file mode 100644
index 00000000000..9686c3d9ff7
--- /dev/null
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -0,0 +1,61 @@
+#ifndef _ASM_X86_HWEIGHT_H
+#define _ASM_X86_HWEIGHT_H
+
+#ifdef CONFIG_64BIT
+/* popcnt %edi, %eax -- redundant REX prefix for alignment */
+#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"
+/* popcnt %rdi, %rax */
+#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
+#define REG_IN "D"
+#define REG_OUT "a"
+#else
+/* popcnt %eax, %eax */
+#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0"
+#define REG_IN "a"
+#define REG_OUT "a"
+#endif
+
+/*
+ * __sw_hweightXX are called from within the alternatives below
+ * and callee-clobbered registers need to be taken care of. See
+ * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
+ * compiler switches.
+ */
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+ unsigned int res = 0;
+
+ asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
+ : "="REG_OUT (res)
+ : REG_IN (w));
+
+ return res;
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+ return __arch_hweight32(w & 0xffff);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+ return __arch_hweight32(w & 0xff);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+ unsigned long res = 0;
+
+#ifdef CONFIG_X86_32
+ return __arch_hweight32((u32)w) +
+ __arch_hweight32((u32)(w >> 32));
+#else
+ asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
+ : "="REG_OUT (res)
+ : REG_IN (w));
+#endif /* CONFIG_X86_32 */
+
+ return res;
+}
+
+#endif
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
new file mode 100644
index 00000000000..69f1366f1aa
--- /dev/null
+++ b/arch/x86/include/asm/archrandom.h
@@ -0,0 +1,136 @@
+/*
+ * This file is part of the Linux kernel.
+ *
+ * Copyright (c) 2011-2014, Intel Corporation
+ * Authors: Fenghua Yu <fenghua.yu@intel.com>,
+ * H. Peter Anvin <hpa@linux.intel.com>
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#ifndef ASM_X86_ARCHRANDOM_H
+#define ASM_X86_ARCHRANDOM_H
+
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative.h>
+#include <asm/nops.h>
+
+#define RDRAND_RETRY_LOOPS 10
+
+#define RDRAND_INT ".byte 0x0f,0xc7,0xf0"
+#define RDSEED_INT ".byte 0x0f,0xc7,0xf8"
+#ifdef CONFIG_X86_64
+# define RDRAND_LONG ".byte 0x48,0x0f,0xc7,0xf0"
+# define RDSEED_LONG ".byte 0x48,0x0f,0xc7,0xf8"
+#else
+# define RDRAND_LONG RDRAND_INT
+# define RDSEED_LONG RDSEED_INT
+#endif
+
+#ifdef CONFIG_ARCH_RANDOM
+
+/* Instead of arch_get_random_long() when alternatives haven't run. */
+static inline int rdrand_long(unsigned long *v)
+{
+ int ok;
+ asm volatile("1: " RDRAND_LONG "\n\t"
+ "jc 2f\n\t"
+ "decl %0\n\t"
+ "jnz 1b\n\t"
+ "2:"
+ : "=r" (ok), "=a" (*v)
+ : "0" (RDRAND_RETRY_LOOPS));
+ return ok;
+}
+
+/* A single attempt at RDSEED */
+static inline bool rdseed_long(unsigned long *v)
+{
+ unsigned char ok;
+ asm volatile(RDSEED_LONG "\n\t"
+ "setc %0"
+ : "=qm" (ok), "=a" (*v));
+ return ok;
+}
+
+#define GET_RANDOM(name, type, rdrand, nop) \
+static inline int name(type *v) \
+{ \
+ int ok; \
+ alternative_io("movl $0, %0\n\t" \
+ nop, \
+ "\n1: " rdrand "\n\t" \
+ "jc 2f\n\t" \
+ "decl %0\n\t" \
+ "jnz 1b\n\t" \
+ "2:", \
+ X86_FEATURE_RDRAND, \
+ ASM_OUTPUT2("=r" (ok), "=a" (*v)), \
+ "0" (RDRAND_RETRY_LOOPS)); \
+ return ok; \
+}
+
+#define GET_SEED(name, type, rdseed, nop) \
+static inline int name(type *v) \
+{ \
+ unsigned char ok; \
+ alternative_io("movb $0, %0\n\t" \
+ nop, \
+ rdseed "\n\t" \
+ "setc %0", \
+ X86_FEATURE_RDSEED, \
+ ASM_OUTPUT2("=q" (ok), "=a" (*v))); \
+ return ok; \
+}
+
+#ifdef CONFIG_X86_64
+
+GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5);
+GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4);
+
+GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP5);
+GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
+
+#else
+
+GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3);
+GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
+
+GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP4);
+GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
+
+#endif /* CONFIG_X86_64 */
+
+#define arch_has_random() static_cpu_has(X86_FEATURE_RDRAND)
+#define arch_has_random_seed() static_cpu_has(X86_FEATURE_RDSEED)
+
+#else
+
+static inline int rdrand_long(unsigned long *v)
+{
+ return 0;
+}
+
+static inline bool rdseed_long(unsigned long *v)
+{
+ return 0;
+}
+
+#endif /* CONFIG_ARCH_RANDOM */
+
+extern void x86_init_rdrand(struct cpuinfo_x86 *c);
+
+#endif /* ASM_X86_ARCHRANDOM_H */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index b3ed1e1460f..7730c1c5c83 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -3,20 +3,25 @@
#ifdef __ASSEMBLY__
# define __ASM_FORM(x) x
-# define __ASM_EX_SEC .section __ex_table, "a"
+# define __ASM_FORM_RAW(x) x
+# define __ASM_FORM_COMMA(x) x,
#else
# define __ASM_FORM(x) " " #x " "
-# define __ASM_EX_SEC " .section __ex_table,\"a\"\n"
+# define __ASM_FORM_RAW(x) #x
+# define __ASM_FORM_COMMA(x) " " #x ","
#endif
#ifdef CONFIG_X86_32
# define __ASM_SEL(a,b) __ASM_FORM(a)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
#else
# define __ASM_SEL(a,b) __ASM_FORM(b)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
#endif
-#define __ASM_SIZE(inst) __ASM_SEL(inst##l, inst##q)
-#define __ASM_REG(reg) __ASM_SEL(e##reg, r##reg)
+#define __ASM_SIZE(inst, ...) __ASM_SEL(inst##l##__VA_ARGS__, \
+ inst##q##__VA_ARGS__)
+#define __ASM_REG(reg) __ASM_SEL_RAW(e##reg, r##reg)
#define _ASM_PTR __ASM_SEL(.long, .quad)
#define _ASM_ALIGN __ASM_SEL(.balign 4, .balign 8)
@@ -39,17 +44,40 @@
/* Exception table entry */
#ifdef __ASSEMBLY__
-# define _ASM_EXTABLE(from,to) \
- __ASM_EX_SEC ; \
- _ASM_ALIGN ; \
- _ASM_PTR from , to ; \
- .previous
+# define _ASM_EXTABLE(from,to) \
+ .pushsection "__ex_table","a" ; \
+ .balign 8 ; \
+ .long (from) - . ; \
+ .long (to) - . ; \
+ .popsection
+
+# define _ASM_EXTABLE_EX(from,to) \
+ .pushsection "__ex_table","a" ; \
+ .balign 8 ; \
+ .long (from) - . ; \
+ .long (to) - . + 0x7ffffff0 ; \
+ .popsection
+
+# define _ASM_NOKPROBE(entry) \
+ .pushsection "_kprobe_blacklist","aw" ; \
+ _ASM_ALIGN ; \
+ _ASM_PTR (entry); \
+ .popsection
#else
-# define _ASM_EXTABLE(from,to) \
- __ASM_EX_SEC \
- _ASM_ALIGN "\n" \
- _ASM_PTR #from "," #to "\n" \
- " .previous\n"
+# define _ASM_EXTABLE(from,to) \
+ " .pushsection \"__ex_table\",\"a\"\n" \
+ " .balign 8\n" \
+ " .long (" #from ") - .\n" \
+ " .long (" #to ") - .\n" \
+ " .popsection\n"
+
+# define _ASM_EXTABLE_EX(from,to) \
+ " .pushsection \"__ex_table\",\"a\"\n" \
+ " .balign 8\n" \
+ " .long (" #from ") - .\n" \
+ " .long (" #to ") - . + 0x7ffffff0\n" \
+ " .popsection\n"
+/* For C file, we already have NOKPROBE_SYMBOL macro */
#endif
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 4e1b8873c47..6dd1c7dd047 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -1,5 +1,253 @@
+#ifndef _ASM_X86_ATOMIC_H
+#define _ASM_X86_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+#include <asm/rmwcc.h>
+#include <asm/barrier.h>
+
+/*
+ * Atomic operations that C can't guarantee us. Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i) { (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+ return (*(volatile int *)&(v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+ asm volatile(LOCK_PREFIX "addl %1,%0"
+ : "+m" (v->counter)
+ : "ir" (i));
+}
+
+/**
+ * atomic_sub - subtract integer from atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic_sub(int i, atomic_t *v)
+{
+ asm volatile(LOCK_PREFIX "subl %1,%0"
+ : "+m" (v->counter)
+ : "ir" (i));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_sub_and_test(int i, atomic_t *v)
+{
+ GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+ asm volatile(LOCK_PREFIX "incl %0"
+ : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic_dec(atomic_t *v)
+{
+ asm volatile(LOCK_PREFIX "decl %0"
+ : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+ GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+}
+
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_inc_and_test(atomic_t *v)
+{
+ GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic_add_negative(int i, atomic_t *v)
+{
+ GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
+}
+
+/**
+ * atomic_add_return - add integer and return
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+ return i + xadd(&v->counter, i);
+}
+
+/**
+ * atomic_sub_return - subtract integer and return
+ * @v: pointer of type atomic_t
+ * @i: integer value to subtract
+ *
+ * Atomically subtracts @i from @v and returns @v - @i
+ */
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+ return atomic_add_return(-i, v);
+}
+
+#define atomic_inc_return(v) (atomic_add_return(1, v))
+#define atomic_dec_return(v) (atomic_sub_return(1, v))
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+ return cmpxchg(&v->counter, old, new);
+}
+
+static inline int atomic_xchg(atomic_t *v, int new)
+{
+ return xchg(&v->counter, new);
+}
+
+/**
+ * __atomic_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as @v was not already @u.
+ * Returns the old value of @v.
+ */
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+ int c, old;
+ c = atomic_read(v);
+ for (;;) {
+ if (unlikely(c == (u)))
+ break;
+ old = atomic_cmpxchg((v), c, c + (a));
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return c;
+}
+
+/**
+ * atomic_inc_short - increment of a short integer
+ * @v: pointer to type int
+ *
+ * Atomically adds 1 to @v
+ * Returns the new value of @u
+ */
+static inline short int atomic_inc_short(short int *v)
+{
+ asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
+ return *v;
+}
+
+#ifdef CONFIG_X86_64
+/**
+ * atomic_or_long - OR of two long integers
+ * @v1: pointer to type unsigned long
+ * @v2: pointer to type unsigned long
+ *
+ * Atomically ORs @v1 and @v2
+ * Returns the result of the OR
+ */
+static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
+{
+ asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
+}
+#endif
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr) \
+ asm volatile(LOCK_PREFIX "andl %0,%1" \
+ : : "r" (~(mask)), "m" (*(addr)) : "memory")
+
+#define atomic_set_mask(mask, addr) \
+ asm volatile(LOCK_PREFIX "orl %0,%1" \
+ : : "r" ((unsigned)(mask)), "m" (*(addr)) \
+ : "memory")
+
#ifdef CONFIG_X86_32
-# include "atomic_32.h"
+# include <asm/atomic64_32.h>
#else
-# include "atomic_64.h"
+# include <asm/atomic64_64.h>
#endif
+
+#endif /* _ASM_X86_ATOMIC_H */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
new file mode 100644
index 00000000000..b154de75c90
--- /dev/null
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -0,0 +1,316 @@
+#ifndef _ASM_X86_ATOMIC64_32_H
+#define _ASM_X86_ATOMIC64_32_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/processor.h>
+//#include <asm/cmpxchg.h>
+
+/* An 64bit atomic type */
+
+typedef struct {
+ u64 __aligned(8) counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(val) { (val) }
+
+#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
+#ifndef ATOMIC64_EXPORT
+#define ATOMIC64_DECL_ONE __ATOMIC64_DECL
+#else
+#define ATOMIC64_DECL_ONE(sym) __ATOMIC64_DECL(sym); \
+ ATOMIC64_EXPORT(atomic64_##sym)
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+#define __alternative_atomic64(f, g, out, in...) \
+ asm volatile("call %P[func]" \
+ : out : [func] "i" (atomic64_##g##_cx8), ## in)
+
+#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
+#else
+#define __alternative_atomic64(f, g, out, in...) \
+ alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
+ X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+
+#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
+ ATOMIC64_DECL_ONE(sym##_386)
+
+ATOMIC64_DECL_ONE(add_386);
+ATOMIC64_DECL_ONE(sub_386);
+ATOMIC64_DECL_ONE(inc_386);
+ATOMIC64_DECL_ONE(dec_386);
+#endif
+
+#define alternative_atomic64(f, out, in...) \
+ __alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+
+ATOMIC64_DECL(read);
+ATOMIC64_DECL(set);
+ATOMIC64_DECL(xchg);
+ATOMIC64_DECL(add_return);
+ATOMIC64_DECL(sub_return);
+ATOMIC64_DECL(inc_return);
+ATOMIC64_DECL(dec_return);
+ATOMIC64_DECL(dec_if_positive);
+ATOMIC64_DECL(inc_not_zero);
+ATOMIC64_DECL(add_unless);
+
+#undef ATOMIC64_DECL
+#undef ATOMIC64_DECL_ONE
+#undef __ATOMIC64_DECL
+#undef ATOMIC64_EXPORT
+
+/**
+ * atomic64_cmpxchg - cmpxchg atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @o: expected value
+ * @n: new value
+ *
+ * Atomically sets @v to @n if it was equal to @o and returns
+ * the old value.
+ */
+
+static inline long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+{
+ return cmpxchg64(&v->counter, o, n);
+}
+
+/**
+ * atomic64_xchg - xchg atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @n: value to assign
+ *
+ * Atomically xchgs the value of @v to @n and returns
+ * the old value.
+ */
+static inline long long atomic64_xchg(atomic64_t *v, long long n)
+{
+ long long o;
+ unsigned high = (unsigned)(n >> 32);
+ unsigned low = (unsigned)n;
+ alternative_atomic64(xchg, "=&A" (o),
+ "S" (v), "b" (low), "c" (high)
+ : "memory");
+ return o;
+}
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @i: value to assign
+ *
+ * Atomically sets the value of @v to @n.
+ */
+static inline void atomic64_set(atomic64_t *v, long long i)
+{
+ unsigned high = (unsigned)(i >> 32);
+ unsigned low = (unsigned)i;
+ alternative_atomic64(set, /* no output */,
+ "S" (v), "b" (low), "c" (high)
+ : "eax", "edx", "memory");
+}
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically reads the value of @v and returns it.
+ */
+static inline long long atomic64_read(const atomic64_t *v)
+{
+ long long r;
+ alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
+ return r;
+ }
+
+/**
+ * atomic64_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns @i + *@v
+ */
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
+{
+ alternative_atomic64(add_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
+ return i;
+}
+
+/*
+ * Other variants with different arithmetic operators:
+ */
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
+{
+ alternative_atomic64(sub_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
+ return i;
+}
+
+static inline long long atomic64_inc_return(atomic64_t *v)
+{
+ long long a;
+ alternative_atomic64(inc_return, "=&A" (a),
+ "S" (v) : "memory", "ecx");
+ return a;
+}
+
+static inline long long atomic64_dec_return(atomic64_t *v)
+{
+ long long a;
+ alternative_atomic64(dec_return, "=&A" (a),
+ "S" (v) : "memory", "ecx");
+ return a;
+}
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline long long atomic64_add(long long i, atomic64_t *v)
+{
+ __alternative_atomic64(add, add_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
+ return i;
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline long long atomic64_sub(long long i, atomic64_t *v)
+{
+ __alternative_atomic64(sub, sub_return,
+ ASM_OUTPUT2("+A" (i), "+c" (v)),
+ ASM_NO_INPUT_CLOBBER("memory"));
+ return i;
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+ return atomic64_sub_return(i, v) == 0;
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic64_inc(atomic64_t *v)
+{
+ __alternative_atomic64(inc, inc_return, /* no output */,
+ "S" (v) : "memory", "eax", "ecx", "edx");
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic64_dec(atomic64_t *v)
+{
+ __alternative_atomic64(dec, dec_return, /* no output */,
+ "S" (v) : "memory", "eax", "ecx", "edx");
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic64_dec_and_test(atomic64_t *v)
+{
+ return atomic64_dec_return(v) == 0;
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_inc_and_test(atomic64_t *v)
+{
+ return atomic64_inc_return(v) == 0;
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic64_add_negative(long long i, atomic64_t *v)
+{
+ return atomic64_add_return(i, v) < 0;
+}
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if the add was done, zero otherwise.
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+ unsigned low = (unsigned)u;
+ unsigned high = (unsigned)(u >> 32);
+ alternative_atomic64(add_unless,
+ ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
+ "S" (v) : "memory");
+ return (int)a;
+}
+
+
+static inline int atomic64_inc_not_zero(atomic64_t *v)
+{
+ int r;
+ alternative_atomic64(inc_not_zero, "=&a" (r),
+ "S" (v) : "ecx", "edx", "memory");
+ return r;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+ long long r;
+ alternative_atomic64(dec_if_positive, "=&A" (r),
+ "S" (v) : "ecx", "memory");
+ return r;
+}
+
+#undef alternative_atomic64
+#undef __alternative_atomic64
+
+#endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
new file mode 100644
index 00000000000..46e9052bbd2
--- /dev/null
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -0,0 +1,223 @@
+#ifndef _ASM_X86_ATOMIC64_64_H
+#define _ASM_X86_ATOMIC64_64_H
+
+#include <linux/types.h>
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+
+/* The 64-bit atomic type */
+
+#define ATOMIC64_INIT(i) { (i) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+static inline long atomic64_read(const atomic64_t *v)
+{
+ return (*(volatile long *)&(v)->counter);
+}
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic64_set(atomic64_t *v, long i)
+{
+ v->counter = i;
+}
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic64_add(long i, atomic64_t *v)
+{
+ asm volatile(LOCK_PREFIX "addq %1,%0"
+ : "=m" (v->counter)
+ : "er" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic64_sub(long i, atomic64_t *v)
+{
+ asm volatile(LOCK_PREFIX "subq %1,%0"
+ : "=m" (v->counter)
+ : "er" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_sub_and_test(long i, atomic64_t *v)
+{
+ GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", "e");
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic64_inc(atomic64_t *v)
+{
+ asm volatile(LOCK_PREFIX "incq %0"
+ : "=m" (v->counter)
+ : "m" (v->counter));
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic64_dec(atomic64_t *v)
+{
+ asm volatile(LOCK_PREFIX "decq %0"
+ : "=m" (v->counter)
+ : "m" (v->counter));
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic64_dec_and_test(atomic64_t *v)
+{
+ GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_inc_and_test(atomic64_t *v)
+{
+ GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic64_add_negative(long i, atomic64_t *v)
+{
+ GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", "s");
+}
+
+/**
+ * atomic64_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline long atomic64_add_return(long i, atomic64_t *v)
+{
+ return i + xadd(&v->counter, i);
+}
+
+static inline long atomic64_sub_return(long i, atomic64_t *v)
+{
+ return atomic64_add_return(-i, v);
+}
+
+#define atomic64_inc_return(v) (atomic64_add_return(1, (v)))
+#define atomic64_dec_return(v) (atomic64_sub_return(1, (v)))
+
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+{
+ return cmpxchg(&v->counter, old, new);
+}
+
+static inline long atomic64_xchg(atomic64_t *v, long new)
+{
+ return xchg(&v->counter, new);
+}
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns the old value of @v.
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+ long c, old;
+ c = atomic64_read(v);
+ for (;;) {
+ if (unlikely(c == (u)))
+ break;
+ old = atomic64_cmpxchg((v), c, c + (a));
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return c != (u);
+}
+
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+static inline long atomic64_dec_if_positive(atomic64_t *v)
+{
+ long c, old, dec;
+ c = atomic64_read(v);
+ for (;;) {
+ dec = c - 1;
+ if (unlikely(dec < 0))
+ break;
+ old = atomic64_cmpxchg((v), c, dec);
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+ return dec;
+}
+
+#endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
deleted file mode 100644
index dc5a667ff79..00000000000
--- a/arch/x86/include/asm/atomic_32.h
+++ /dev/null
@@ -1,415 +0,0 @@
-#ifndef _ASM_X86_ATOMIC_32_H
-#define _ASM_X86_ATOMIC_32_H
-
-#include <linux/compiler.h>
-#include <linux/types.h>
-#include <asm/processor.h>
-#include <asm/cmpxchg.h>
-
-/*
- * Atomic operations that C can't guarantee us. Useful for
- * resource counting etc..
- */
-
-#define ATOMIC_INIT(i) { (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-static inline int atomic_read(const atomic_t *v)
-{
- return v->counter;
-}
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-static inline void atomic_set(atomic_t *v, int i)
-{
- v->counter = i;
-}
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "addl %1,%0"
- : "+m" (v->counter)
- : "ir" (i));
-}
-
-/**
- * atomic_sub - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "subl %1,%0"
- : "+m" (v->counter)
- : "ir" (i));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
- : "+m" (v->counter), "=qm" (c)
- : "ir" (i) : "memory");
- return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic_inc(atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "incl %0"
- : "+m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic_dec(atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "decl %0"
- : "+m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic_dec_and_test(atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "decl %0; sete %1"
- : "+m" (v->counter), "=qm" (c)
- : : "memory");
- return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_inc_and_test(atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "incl %0; sete %1"
- : "+m" (v->counter), "=qm" (c)
- : : "memory");
- return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
- : "+m" (v->counter), "=qm" (c)
- : "ir" (i) : "memory");
- return c;
-}
-
-/**
- * atomic_add_return - add integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
- int __i;
-#ifdef CONFIG_M386
- unsigned long flags;
- if (unlikely(boot_cpu_data.x86 <= 3))
- goto no_xadd;
-#endif
- /* Modern 486+ processor */
- __i = i;
- asm volatile(LOCK_PREFIX "xaddl %0, %1"
- : "+r" (i), "+m" (v->counter)
- : : "memory");
- return i + __i;
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
- local_irq_save(flags);
- __i = atomic_read(v);
- atomic_set(v, i + __i);
- local_irq_restore(flags);
- return i + __i;
-#endif
-}
-
-/**
- * atomic_sub_return - subtract integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to subtract
- *
- * Atomically subtracts @i from @v and returns @v - @i
- */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
- return atomic_add_return(-i, v);
-}
-
-static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
-{
- return cmpxchg(&v->counter, old, new);
-}
-
-static inline int atomic_xchg(atomic_t *v, int new)
-{
- return xchg(&v->counter, new);
-}
-
-/**
- * atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr) \
- asm volatile(LOCK_PREFIX "andl %0,%1" \
- : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr) \
- asm volatile(LOCK_PREFIX "orl %0,%1" \
- : : "r" (mask), "m" (*(addr)) : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
-/* An 64bit atomic type */
-
-typedef struct {
- u64 __aligned(8) counter;
-} atomic64_t;
-
-#define ATOMIC64_INIT(val) { (val) }
-
-extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
-
-/**
- * atomic64_xchg - xchg atomic64 variable
- * @ptr: pointer to type atomic64_t
- * @new_val: value to assign
- *
- * Atomically xchgs the value of @ptr to @new_val and returns
- * the old value.
- */
-extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
-
-/**
- * atomic64_set - set atomic64 variable
- * @ptr: pointer to type atomic64_t
- * @new_val: value to assign
- *
- * Atomically sets the value of @ptr to @new_val.
- */
-extern void atomic64_set(atomic64_t *ptr, u64 new_val);
-
-/**
- * atomic64_read - read atomic64 variable
- * @ptr: pointer to type atomic64_t
- *
- * Atomically reads the value of @ptr and returns it.
- */
-static inline u64 atomic64_read(atomic64_t *ptr)
-{
- u64 res;
-
- /*
- * Note, we inline this atomic64_t primitive because
- * it only clobbers EAX/EDX and leaves the others
- * untouched. We also (somewhat subtly) rely on the
- * fact that cmpxchg8b returns the current 64-bit value
- * of the memory location we are touching:
- */
- asm volatile(
- "mov %%ebx, %%eax\n\t"
- "mov %%ecx, %%edx\n\t"
- LOCK_PREFIX "cmpxchg8b %1\n"
- : "=&A" (res)
- : "m" (*ptr)
- );
-
- return res;
-}
-
-extern u64 atomic64_read(atomic64_t *ptr);
-
-/**
- * atomic64_add_return - add and return
- * @delta: integer value to add
- * @ptr: pointer to type atomic64_t
- *
- * Atomically adds @delta to @ptr and returns @delta + *@ptr
- */
-extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
-
-/*
- * Other variants with different arithmetic operators:
- */
-extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
-extern u64 atomic64_inc_return(atomic64_t *ptr);
-extern u64 atomic64_dec_return(atomic64_t *ptr);
-
-/**
- * atomic64_add - add integer to atomic64 variable
- * @delta: integer value to add
- * @ptr: pointer to type atomic64_t
- *
- * Atomically adds @delta to @ptr.
- */
-extern void atomic64_add(u64 delta, atomic64_t *ptr);
-
-/**
- * atomic64_sub - subtract the atomic64 variable
- * @delta: integer value to subtract
- * @ptr: pointer to type atomic64_t
- *
- * Atomically subtracts @delta from @ptr.
- */
-extern void atomic64_sub(u64 delta, atomic64_t *ptr);
-
-/**
- * atomic64_sub_and_test - subtract value from variable and test result
- * @delta: integer value to subtract
- * @ptr: pointer to type atomic64_t
- *
- * Atomically subtracts @delta from @ptr and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
-
-/**
- * atomic64_inc - increment atomic64 variable
- * @ptr: pointer to type atomic64_t
- *
- * Atomically increments @ptr by 1.
- */
-extern void atomic64_inc(atomic64_t *ptr);
-
-/**
- * atomic64_dec - decrement atomic64 variable
- * @ptr: pointer to type atomic64_t
- *
- * Atomically decrements @ptr by 1.
- */
-extern void atomic64_dec(atomic64_t *ptr);
-
-/**
- * atomic64_dec_and_test - decrement and test
- * @ptr: pointer to type atomic64_t
- *
- * Atomically decrements @ptr by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-extern int atomic64_dec_and_test(atomic64_t *ptr);
-
-/**
- * atomic64_inc_and_test - increment and test
- * @ptr: pointer to type atomic64_t
- *
- * Atomically increments @ptr by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-extern int atomic64_inc_and_test(atomic64_t *ptr);
-
-/**
- * atomic64_add_negative - add and test if negative
- * @delta: integer value to add
- * @ptr: pointer to type atomic64_t
- *
- * Atomically adds @delta to @ptr and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
-
-#include <asm-generic/atomic-long.h>
-#endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
deleted file mode 100644
index d605dc268e7..00000000000
--- a/arch/x86/include/asm/atomic_64.h
+++ /dev/null
@@ -1,485 +0,0 @@
-#ifndef _ASM_X86_ATOMIC_64_H
-#define _ASM_X86_ATOMIC_64_H
-
-#include <linux/types.h>
-#include <asm/alternative.h>
-#include <asm/cmpxchg.h>
-
-/*
- * Atomic operations that C can't guarantee us. Useful for
- * resource counting etc..
- */
-
-#define ATOMIC_INIT(i) { (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-static inline int atomic_read(const atomic_t *v)
-{
- return v->counter;
-}
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-static inline void atomic_set(atomic_t *v, int i)
-{
- v->counter = i;
-}
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "addl %1,%0"
- : "=m" (v->counter)
- : "ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "subl %1,%0"
- : "=m" (v->counter)
- : "ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "ir" (i), "m" (v->counter) : "memory");
- return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic_inc(atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "incl %0"
- : "=m" (v->counter)
- : "m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic_dec(atomic_t *v)
-{
- asm volatile(LOCK_PREFIX "decl %0"
- : "=m" (v->counter)
- : "m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic_dec_and_test(atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "decl %0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "m" (v->counter) : "memory");
- return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_inc_and_test(atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "incl %0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "m" (v->counter) : "memory");
- return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
- : "=m" (v->counter), "=qm" (c)
- : "ir" (i), "m" (v->counter) : "memory");
- return c;
-}
-
-/**
- * atomic_add_return - add and return
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
- int __i = i;
- asm volatile(LOCK_PREFIX "xaddl %0, %1"
- : "+r" (i), "+m" (v->counter)
- : : "memory");
- return i + __i;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
- return atomic_add_return(-i, v);
-}
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
-
-/* The 64-bit atomic type */
-
-#define ATOMIC64_INIT(i) { (i) }
-
-/**
- * atomic64_read - read atomic64 variable
- * @v: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
-static inline long atomic64_read(const atomic64_t *v)
-{
- return v->counter;
-}
-
-/**
- * atomic64_set - set atomic64 variable
- * @v: pointer to type atomic64_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-static inline void atomic64_set(atomic64_t *v, long i)
-{
- v->counter = i;
-}
-
-/**
- * atomic64_add - add integer to atomic64 variable
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic64_add(long i, atomic64_t *v)
-{
- asm volatile(LOCK_PREFIX "addq %1,%0"
- : "=m" (v->counter)
- : "er" (i), "m" (v->counter));
-}
-
-/**
- * atomic64_sub - subtract the atomic64 variable
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic64_sub(long i, atomic64_t *v)
-{
- asm volatile(LOCK_PREFIX "subq %1,%0"
- : "=m" (v->counter)
- : "er" (i), "m" (v->counter));
-}
-
-/**
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic64_sub_and_test(long i, atomic64_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "er" (i), "m" (v->counter) : "memory");
- return c;
-}
-
-/**
- * atomic64_inc - increment atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic64_inc(atomic64_t *v)
-{
- asm volatile(LOCK_PREFIX "incq %0"
- : "=m" (v->counter)
- : "m" (v->counter));
-}
-
-/**
- * atomic64_dec - decrement atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic64_dec(atomic64_t *v)
-{
- asm volatile(LOCK_PREFIX "decq %0"
- : "=m" (v->counter)
- : "m" (v->counter));
-}
-
-/**
- * atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic64_dec_and_test(atomic64_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "decq %0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "m" (v->counter) : "memory");
- return c != 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic64_inc_and_test(atomic64_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "incq %0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "m" (v->counter) : "memory");
- return c != 0;
-}
-
-/**
- * atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic64_add_negative(long i, atomic64_t *v)
-{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
- : "=m" (v->counter), "=qm" (c)
- : "er" (i), "m" (v->counter) : "memory");
- return c;
-}
-
-/**
- * atomic64_add_return - add and return
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
- long __i = i;
- asm volatile(LOCK_PREFIX "xaddq %0, %1;"
- : "+r" (i), "+m" (v->counter)
- : : "memory");
- return i + __i;
-}
-
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
- return atomic64_add_return(-i, v);
-}
-
-#define atomic64_inc_return(v) (atomic64_add_return(1, (v)))
-#define atomic64_dec_return(v) (atomic64_sub_return(1, (v)))
-
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
-{
- return cmpxchg(&v->counter, old, new);
-}
-
-static inline long atomic64_xchg(atomic64_t *v, long new)
-{
- return xchg(&v->counter, new);
-}
-
-static inline long atomic_cmpxchg(atomic_t *v, int old, int new)
-{
- return cmpxchg(&v->counter, old, new);
-}
-
-static inline long atomic_xchg(atomic_t *v, int new)
-{
- return xchg(&v->counter, new);
-}
-
-/**
- * atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
- int c, old;
- c = atomic_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
- long c, old;
- c = atomic64_read(v);
- for (;;) {
- if (unlikely(c == (u)))
- break;
- old = atomic64_cmpxchg((v), c, c + (a));
- if (likely(old == c))
- break;
- c = old;
- }
- return c != (u);
-}
-
-/**
- * atomic_inc_short - increment of a short integer
- * @v: pointer to type int
- *
- * Atomically adds 1 to @v
- * Returns the new value of @u
- */
-static inline short int atomic_inc_short(short int *v)
-{
- asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
- return *v;
-}
-
-/**
- * atomic_or_long - OR of two long integers
- * @v1: pointer to type unsigned long
- * @v2: pointer to type unsigned long
- *
- * Atomically ORs @v1 and @v2
- * Returns the result of the OR
- */
-static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
-{
- asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr) \
- asm volatile(LOCK_PREFIX "andl %0,%1" \
- : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr) \
- asm volatile(LOCK_PREFIX "orl %0,%1" \
- : : "r" ((unsigned)(mask)), "m" (*(addr)) \
- : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
-#include <asm-generic/atomic-long.h>
-#endif /* _ASM_X86_ATOMIC_64_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
new file mode 100644
index 00000000000..5c7198cca5e
--- /dev/null
+++ b/arch/x86/include/asm/barrier.h
@@ -0,0 +1,157 @@
+#ifndef _ASM_X86_BARRIER_H
+#define _ASM_X86_BARRIER_H
+
+#include <asm/alternative.h>
+#include <asm/nops.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_X86_32
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define mb() asm volatile("mfence":::"memory")
+#define rmb() asm volatile("lfence":::"memory")
+#define wmb() asm volatile("sfence" ::: "memory")
+#endif
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier. All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads. This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies. See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ * CPU 0 CPU 1
+ *
+ * b = 2;
+ * memory_barrier();
+ * p = &b; q = p;
+ * read_barrier_depends();
+ * d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends(). However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ * CPU 0 CPU 1
+ *
+ * a = 2;
+ * memory_barrier();
+ * b = 3; y = b;
+ * read_barrier_depends();
+ * x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b". Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends() do { } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+# define smp_rmb() rmb()
+#else
+# define smp_rmb() barrier()
+#endif
+#define smp_wmb() barrier()
+#define smp_read_barrier_depends() read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#else /* !SMP */
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_read_barrier_depends() do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif /* SMP */
+
+#if defined(CONFIG_X86_PPRO_FENCE)
+
+/*
+ * For either of these options x86 doesn't have a strong TSO memory
+ * model and we should fall back to full barriers.
+ */
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ smp_mb(); \
+ ___p1; \
+})
+
+#else /* regular x86 TSO memory ordering */
+
+#define smp_store_release(p, v) \
+do { \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ACCESS_ONCE(*p) = (v); \
+} while (0)
+
+#define smp_load_acquire(p) \
+({ \
+ typeof(*p) ___p1 = ACCESS_ONCE(*p); \
+ compiletime_assert_atomic_type(*p); \
+ barrier(); \
+ ___p1; \
+})
+
+#endif
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic() barrier()
+#define smp_mb__after_atomic() barrier()
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static __always_inline void rdtsc_barrier(void)
+{
+ alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+ alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
index 3c7521063d3..aa6a3170ab5 100644
--- a/arch/x86/include/asm/bios_ebda.h
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -4,16 +4,40 @@
#include <asm/io.h>
/*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E.
+ * Returns physical address of EBDA. Returns 0 if there is no EBDA.
*/
static inline unsigned int get_bios_ebda(void)
{
+ /*
+ * There is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E.
+ */
unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
address <<= 4;
return address; /* 0 means none */
}
+/*
+ * Return the sanitized length of the EBDA in bytes, if it exists.
+ */
+static inline unsigned int get_bios_ebda_length(void)
+{
+ unsigned int address;
+ unsigned int length;
+
+ address = get_bios_ebda();
+ if (!address)
+ return 0;
+
+ /* EBDA length is byte 0 of the EBDA (stored in KiB) */
+ length = *(unsigned char *)phys_to_virt(address);
+ length <<= 10;
+
+ /* Trim the length if it extends beyond 640KiB */
+ length = min_t(unsigned int, (640 * 1024) - address, length);
+ return length;
+}
+
void reserve_ebda_region(void);
#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 02b47a603fc..afcd35d331d 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -14,6 +14,18 @@
#include <linux/compiler.h>
#include <asm/alternative.h>
+#include <asm/rmwcc.h>
+#include <asm/barrier.h>
+
+#if BITS_PER_LONG == 32
+# define _BITOPS_LONG_SHIFT 5
+#elif BITS_PER_LONG == 64
+# define _BITOPS_LONG_SHIFT 6
+#else
+# error "Unexpected BITS_PER_LONG"
+#endif
+
+#define BIT_64(n) (U64_C(1) << (n))
/*
* These have to be done with inline assembly: that way the bit-setting
@@ -57,7 +69,7 @@
* restricted to acting on a single-word quantity.
*/
static __always_inline void
-set_bit(unsigned int nr, volatile unsigned long *addr)
+set_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -79,7 +91,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr)
* If it's called on the same region of memory simultaneously, the effect
* may be that only one operation succeeds.
*/
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static inline void __set_bit(long nr, volatile unsigned long *addr)
{
asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
}
@@ -91,11 +103,11 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static __always_inline void
-clear_bit(int nr, volatile unsigned long *addr)
+clear_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -116,13 +128,13 @@ clear_bit(int nr, volatile unsigned long *addr)
* clear_bit() is atomic and implies release semantics before the memory
* operation. It can be used for an unlock.
*/
-static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
{
barrier();
clear_bit(nr, addr);
}
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static inline void __clear_bit(long nr, volatile unsigned long *addr)
{
asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
}
@@ -139,15 +151,12 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
* No memory barrier is required here, because x86 cannot reorder stores past
* older loads. Same principle as spin_unlock.
*/
-static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
barrier();
__clear_bit(nr, addr);
}
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
/**
* __change_bit - Toggle a bit in memory
* @nr: the bit to change
@@ -157,7 +166,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
* If it's called on the same region of memory simultaneously, the effect
* may be that only one operation succeeds.
*/
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static inline void __change_bit(long nr, volatile unsigned long *addr)
{
asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
}
@@ -171,7 +180,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -192,14 +201,9 @@ static inline void change_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
{
- int oldbit;
-
- asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
- "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
- return oldbit;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
}
/**
@@ -210,7 +214,7 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
* This is the same as test_and_set_bit on x86.
*/
static __always_inline int
-test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+test_and_set_bit_lock(long nr, volatile unsigned long *addr)
{
return test_and_set_bit(nr, addr);
}
@@ -224,7 +228,7 @@ test_and_set_bit_lock(int nr, volatile unsigned long *addr)
* If two examples of this operation race, one can appear to succeed
* but actually fail. You must protect multiple accesses with a lock.
*/
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
@@ -243,15 +247,9 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
{
- int oldbit;
-
- asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
- "sbb %0,%0"
- : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
- return oldbit;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
}
/**
@@ -262,8 +260,15 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
* This operation is non-atomic and can be reordered.
* If two examples of this operation race, one can appear to succeed
* but actually fail. You must protect multiple accesses with a lock.
+ *
+ * Note: the operation is performed atomically with respect to
+ * the local CPU, but not other CPUs. Portable code should not
+ * rely on this behaviour.
+ * KVM relies on this behaviour on x86 for modifying memory that is also
+ * accessed from a hypervisor on the same CPU if running in a VM: don't change
+ * this without also updating arch/x86/kernel/kvm.c
*/
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
@@ -275,7 +280,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
}
/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
@@ -295,24 +300,18 @@ static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
{
- int oldbit;
-
- asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
- "sbb %0,%0"
- : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
- return oldbit;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
}
-static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
{
- return ((1UL << (nr % BITS_PER_LONG)) &
- (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+ return ((1UL << (nr & (BITS_PER_LONG-1))) &
+ (addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
}
-static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
{
int oldbit;
@@ -346,7 +345,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
*/
static inline unsigned long __ffs(unsigned long word)
{
- asm("bsf %1,%0"
+ asm("rep; bsf %1,%0"
: "=r" (word)
: "rm" (word));
return word;
@@ -360,7 +359,7 @@ static inline unsigned long __ffs(unsigned long word)
*/
static inline unsigned long ffz(unsigned long word)
{
- asm("bsf %1,%0"
+ asm("rep; bsf %1,%0"
: "=r" (word)
: "r" (~word));
return word;
@@ -380,6 +379,8 @@ static inline unsigned long __fls(unsigned long word)
return word;
}
+#undef ADDR
+
#ifdef __KERNEL__
/**
* ffs - find first set bit in word
@@ -395,10 +396,24 @@ static inline unsigned long __fls(unsigned long word)
static inline int ffs(int x)
{
int r;
-#ifdef CONFIG_X86_CMOV
+
+#ifdef CONFIG_X86_64
+ /*
+ * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the
+ * dest reg is undefined if x==0, but their CPU architect says its
+ * value is written to set it to the same as before, except that the
+ * top 32 bits will be cleared.
+ *
+ * We cannot do this on 32 bits because at the very least some
+ * 486 CPUs did not behave this way.
+ */
+ asm("bsfl %1,%0"
+ : "=r" (r)
+ : "rm" (x), "0" (-1));
+#elif defined(CONFIG_X86_CMOV)
asm("bsfl %1,%0\n\t"
"cmovzl %2,%0"
- : "=r" (r) : "rm" (x), "r" (-1));
+ : "=&r" (r) : "rm" (x), "r" (-1));
#else
asm("bsfl %1,%0\n\t"
"jnz 1f\n\t"
@@ -422,7 +437,21 @@ static inline int ffs(int x)
static inline int fls(int x)
{
int r;
-#ifdef CONFIG_X86_CMOV
+
+#ifdef CONFIG_X86_64
+ /*
+ * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the
+ * dest reg is undefined if x==0, but their CPU architect says its
+ * value is written to set it to the same as before, except that the
+ * top 32 bits will be cleared.
+ *
+ * We cannot do this on 32 bits because at the very least some
+ * 486 CPUs did not behave this way.
+ */
+ asm("bsrl %1,%0"
+ : "=r" (r)
+ : "rm" (x), "0" (-1));
+#elif defined(CONFIG_X86_CMOV)
asm("bsrl %1,%0\n\t"
"cmovzl %2,%0"
: "=&r" (r) : "rm" (x), "rm" (-1));
@@ -434,32 +463,49 @@ static inline int fls(int x)
#endif
return r + 1;
}
-#endif /* __KERNEL__ */
-#undef ADDR
+/**
+ * fls64 - find last set bit in a 64-bit word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffsll, but returns the position of the most significant set bit.
+ *
+ * fls64(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 64.
+ */
+#ifdef CONFIG_X86_64
+static __always_inline int fls64(__u64 x)
+{
+ int bitpos = -1;
+ /*
+ * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
+ * dest reg is undefined if x==0, but their CPU architect says its
+ * value is written to set it to the same as before.
+ */
+ asm("bsrq %1,%q0"
+ : "+r" (bitpos)
+ : "rm" (x));
+ return bitpos + 1;
+}
+#else
+#include <asm-generic/bitops/fls64.h>
+#endif
-#ifdef __KERNEL__
+#include <asm-generic/bitops/find.h>
#include <asm-generic/bitops/sched.h>
#define ARCH_HAS_FAST_MULTIPLIER 1
-#include <asm-generic/bitops/hweight.h>
-
-#endif /* __KERNEL__ */
-
-#include <asm-generic/bitops/fls64.h>
-
-#ifdef __KERNEL__
+#include <asm/arch_hweight.h>
-#include <asm-generic/bitops/ext2-non-atomic.h>
+#include <asm-generic/bitops/const_hweight.h>
-#define ext2_set_bit_atomic(lock, nr, addr) \
- test_and_set_bit((nr), (unsigned long *)(addr))
-#define ext2_clear_bit_atomic(lock, nr, addr) \
- test_and_clear_bit((nr), (unsigned long *)(addr))
+#include <asm-generic/bitops/le.h>
-#include <asm-generic/bitops/minix.h>
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
#endif /* __KERNEL__ */
#endif /* _ASM_X86_BITOPS_H */
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 7a1065958ba..4fa687a47a6 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -1,14 +1,9 @@
#ifndef _ASM_X86_BOOT_H
#define _ASM_X86_BOOT_H
-/* Internal svga startup constants */
-#define NORMAL_VGA 0xffff /* 80x25 mode */
-#define EXTENDED_VGA 0xfffe /* 80x50 mode */
-#define ASK_VGA 0xfffd /* ask for it at bootup */
-
-#ifdef __KERNEL__
#include <asm/pgtable_types.h>
+#include <uapi/asm/boot.h>
/* Physical address where kernel should be loaded. */
#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
@@ -19,12 +14,12 @@
#ifdef CONFIG_X86_64
#define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT
#else
-#define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT + THREAD_ORDER)
+#define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT + THREAD_SIZE_ORDER)
#endif
#define MIN_KERNEL_ALIGN (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
#if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \
- (CONFIG_PHYSICAL_ALIGN < (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2))
+ (CONFIG_PHYSICAL_ALIGN < MIN_KERNEL_ALIGN)
#error "Invalid value for CONFIG_PHYSICAL_ALIGN"
#endif
@@ -32,11 +27,7 @@
#define BOOT_HEAP_SIZE 0x400000
#else /* !CONFIG_KERNEL_BZIP2 */
-#ifdef CONFIG_X86_64
-#define BOOT_HEAP_SIZE 0x7000
-#else
-#define BOOT_HEAP_SIZE 0x4000
-#endif
+#define BOOT_HEAP_SIZE 0x8000
#endif /* !CONFIG_KERNEL_BZIP2 */
@@ -46,6 +37,4 @@
#define BOOT_STACK_SIZE 0x1000
#endif
-#endif /* __KERNEL__ */
-
#endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
new file mode 100644
index 00000000000..4a8cb8d7cbd
--- /dev/null
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -0,0 +1,54 @@
+#ifndef _ASM_X86_BOOTPARAM_UTILS_H
+#define _ASM_X86_BOOTPARAM_UTILS_H
+
+#include <asm/bootparam.h>
+
+/*
+ * This file is included from multiple environments. Do not
+ * add completing #includes to make it standalone.
+ */
+
+/*
+ * Deal with bootloaders which fail to initialize unknown fields in
+ * boot_params to zero. The list fields in this list are taken from
+ * analysis of kexec-tools; if other broken bootloaders initialize a
+ * different set of fields we will need to figure out how to disambiguate.
+ *
+ * Note: efi_info is commonly left uninitialized, but that field has a
+ * private magic, so it is better to leave it unchanged.
+ */
+static void sanitize_boot_params(struct boot_params *boot_params)
+{
+ /*
+ * IMPORTANT NOTE TO BOOTLOADER AUTHORS: do not simply clear
+ * this field. The purpose of this field is to guarantee
+ * compliance with the x86 boot spec located in
+ * Documentation/x86/boot.txt . That spec says that the
+ * *whole* structure should be cleared, after which only the
+ * portion defined by struct setup_header (boot_params->hdr)
+ * should be copied in.
+ *
+ * If you're having an issue because the sentinel is set, you
+ * need to change the whole structure to be cleared, not this
+ * (or any other) individual field, or you will soon have
+ * problems again.
+ */
+ if (boot_params->sentinel) {
+ /* fields in boot_params are left uninitialized, clear them */
+ memset(&boot_params->ext_ramdisk_image, 0,
+ (char *)&boot_params->efi_info -
+ (char *)&boot_params->ext_ramdisk_image);
+ memset(&boot_params->kbd_status, 0,
+ (char *)&boot_params->hdr -
+ (char *)&boot_params->kbd_status);
+ memset(&boot_params->_pad7[0], 0,
+ (char *)&boot_params->edd_mbr_sig_buffer[0] -
+ (char *)&boot_params->_pad7[0]);
+ memset(&boot_params->_pad8[0], 0,
+ (char *)&boot_params->eddbuf[0] -
+ (char *)&boot_params->_pad8[0]);
+ memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9));
+ }
+}
+
+#endif /* _ASM_X86_BOOTPARAM_UTILS_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f654d1bb17f..ba38ebbaced 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -1,7 +1,6 @@
#ifndef _ASM_X86_BUG_H
#define _ASM_X86_BUG_H
-#ifdef CONFIG_BUG
#define HAVE_ARCH_BUG
#ifdef CONFIG_DEBUG_BUGVERBOSE
@@ -33,7 +32,6 @@ do { \
} while (0)
#endif
-#endif /* !CONFIG_BUG */
-
#include <asm-generic/bug.h>
+
#endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
index 2f9047cfaac..48f99f15452 100644
--- a/arch/x86/include/asm/cache.h
+++ b/arch/x86/include/asm/cache.h
@@ -7,7 +7,7 @@
#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT)
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+#define __read_mostly __attribute__((__section__(".data..read_mostly")))
#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT
#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 634c40a739a..9863ee3747d 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -1,51 +1,9 @@
#ifndef _ASM_X86_CACHEFLUSH_H
#define _ASM_X86_CACHEFLUSH_H
-/* Keep includes the same across arches. */
-#include <linux/mm.h>
-
/* Caches aren't brain-dead on the intel. */
-static inline void flush_cache_all(void) { }
-static inline void flush_cache_mm(struct mm_struct *mm) { }
-static inline void flush_cache_dup_mm(struct mm_struct *mm) { }
-static inline void flush_cache_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end) { }
-static inline void flush_cache_page(struct vm_area_struct *vma,
- unsigned long vmaddr, unsigned long pfn) { }
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-static inline void flush_dcache_page(struct page *page) { }
-static inline void flush_dcache_mmap_lock(struct address_space *mapping) { }
-static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { }
-static inline void flush_icache_range(unsigned long start,
- unsigned long end) { }
-static inline void flush_icache_page(struct vm_area_struct *vma,
- struct page *page) { }
-static inline void flush_icache_user_range(struct vm_area_struct *vma,
- struct page *page,
- unsigned long addr,
- unsigned long len) { }
-static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
-static inline void flush_cache_vunmap(unsigned long start,
- unsigned long end) { }
-
-static inline void copy_to_user_page(struct vm_area_struct *vma,
- struct page *page, unsigned long vaddr,
- void *dst, const void *src,
- unsigned long len)
-{
- memcpy(dst, src, len);
-}
-
-static inline void copy_from_user_page(struct vm_area_struct *vma,
- struct page *page, unsigned long vaddr,
- void *dst, const void *src,
- unsigned long len)
-{
- memcpy(dst, src, len);
-}
-
-#define PG_WC PG_arch_1
-PAGEFLAG(WC, WC)
+#include <asm-generic/cacheflush.h>
+#include <asm/special_insns.h>
#ifdef CONFIG_X86_PAT
/*
@@ -55,16 +13,24 @@ PAGEFLAG(WC, WC)
* _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not
* been changed from its default (value of -1 used to denote this).
* Note we do not support _PAGE_CACHE_UC here.
- *
- * Caller must hold memtype_lock for atomicity.
*/
+
+#define _PGMT_DEFAULT 0
+#define _PGMT_WC (1UL << PG_arch_1)
+#define _PGMT_UC_MINUS (1UL << PG_uncached)
+#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_CLEAR_MASK (~_PGMT_MASK)
+
static inline unsigned long get_page_memtype(struct page *pg)
{
- if (!PageUncached(pg) && !PageWC(pg))
+ unsigned long pg_flags = pg->flags & _PGMT_MASK;
+
+ if (pg_flags == _PGMT_DEFAULT)
return -1;
- else if (!PageUncached(pg) && PageWC(pg))
+ else if (pg_flags == _PGMT_WC)
return _PAGE_CACHE_WC;
- else if (PageUncached(pg) && !PageWC(pg))
+ else if (pg_flags == _PGMT_UC_MINUS)
return _PAGE_CACHE_UC_MINUS;
else
return _PAGE_CACHE_WB;
@@ -72,25 +38,26 @@ static inline unsigned long get_page_memtype(struct page *pg)
static inline void set_page_memtype(struct page *pg, unsigned long memtype)
{
+ unsigned long memtype_flags = _PGMT_DEFAULT;
+ unsigned long old_flags;
+ unsigned long new_flags;
+
switch (memtype) {
case _PAGE_CACHE_WC:
- ClearPageUncached(pg);
- SetPageWC(pg);
+ memtype_flags = _PGMT_WC;
break;
case _PAGE_CACHE_UC_MINUS:
- SetPageUncached(pg);
- ClearPageWC(pg);
+ memtype_flags = _PGMT_UC_MINUS;
break;
case _PAGE_CACHE_WB:
- SetPageUncached(pg);
- SetPageWC(pg);
- break;
- default:
- case -1:
- ClearPageUncached(pg);
- ClearPageWC(pg);
+ memtype_flags = _PGMT_WB;
break;
}
+
+ do {
+ old_flags = pg->flags;
+ new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
+ } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
}
#else
static inline unsigned long get_page_memtype(struct page *pg) { return -1; }
@@ -105,7 +72,7 @@ static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
* Read/Write : ReadOnly, ReadWrite
* Presence : NotPresent
*
- * Within a catagory, the attributes are mutually exclusive.
+ * Within a category, the attributes are mutually exclusive.
*
* The implementation of this API will take care of various aspects that
* are associated with changing such attributes, such as:
@@ -139,9 +106,11 @@ int set_memory_np(unsigned long addr, int numpages);
int set_memory_4k(unsigned long addr, int numpages);
int set_memory_array_uc(unsigned long *addr, int addrinarray);
+int set_memory_array_wc(unsigned long *addr, int addrinarray);
int set_memory_array_wb(unsigned long *addr, int addrinarray);
int set_pages_array_uc(struct page **pages, int addrinarray);
+int set_pages_array_wc(struct page **pages, int addrinarray);
int set_pages_array_wb(struct page **pages, int addrinarray);
/*
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
index 0918654305a..0d467b33883 100644
--- a/arch/x86/include/asm/calgary.h
+++ b/arch/x86/include/asm/calgary.h
@@ -62,9 +62,9 @@ struct cal_chipset_ops {
extern int use_calgary;
#ifdef CONFIG_CALGARY_IOMMU
-extern void detect_calgary(void);
+extern int detect_calgary(void);
#else
-static inline void detect_calgary(void) { return; }
+static inline int detect_calgary(void) { return -ENODEV; }
#endif
#endif /* _ASM_X86_CALGARY_H */
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0e63c9a2a8d..cb4c73bfeb4 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -46,6 +46,9 @@ For 32-bit we have the following conventions - kernel is built with
*/
+#include <asm/dwarf2.h>
+
+#ifdef CONFIG_X86_64
/*
* 64-bit system call stack frame layout defines and helpers,
@@ -82,72 +85,57 @@ For 32-bit we have the following conventions - kernel is built with
#define ARGOFFSET R11
#define SWFRAME ORIG_RAX
- .macro SAVE_ARGS addskip=0, norcx=0, nor891011=0
+ .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1
subq $9*8+\addskip, %rsp
CFI_ADJUST_CFA_OFFSET 9*8+\addskip
- movq %rdi, 8*8(%rsp)
- CFI_REL_OFFSET rdi, 8*8
- movq %rsi, 7*8(%rsp)
- CFI_REL_OFFSET rsi, 7*8
- movq %rdx, 6*8(%rsp)
- CFI_REL_OFFSET rdx, 6*8
- .if \norcx
- .else
- movq %rcx, 5*8(%rsp)
- CFI_REL_OFFSET rcx, 5*8
+ movq_cfi rdi, 8*8
+ movq_cfi rsi, 7*8
+ movq_cfi rdx, 6*8
+
+ .if \save_rcx
+ movq_cfi rcx, 5*8
.endif
- movq %rax, 4*8(%rsp)
- CFI_REL_OFFSET rax, 4*8
- .if \nor891011
- .else
- movq %r8, 3*8(%rsp)
- CFI_REL_OFFSET r8, 3*8
- movq %r9, 2*8(%rsp)
- CFI_REL_OFFSET r9, 2*8
- movq %r10, 1*8(%rsp)
- CFI_REL_OFFSET r10, 1*8
- movq %r11, (%rsp)
- CFI_REL_OFFSET r11, 0*8
+
+ movq_cfi rax, 4*8
+
+ .if \save_r891011
+ movq_cfi r8, 3*8
+ movq_cfi r9, 2*8
+ movq_cfi r10, 1*8
+ movq_cfi r11, 0*8
.endif
+
.endm
-#define ARG_SKIP 9*8
+#define ARG_SKIP (9*8)
- .macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
- skipr8910=0, skiprdx=0
- .if \skipr11
- .else
- movq (%rsp), %r11
- CFI_RESTORE r11
+ .macro RESTORE_ARGS rstor_rax=1, addskip=0, rstor_rcx=1, rstor_r11=1, \
+ rstor_r8910=1, rstor_rdx=1
+ .if \rstor_r11
+ movq_cfi_restore 0*8, r11
.endif
- .if \skipr8910
- .else
- movq 1*8(%rsp), %r10
- CFI_RESTORE r10
- movq 2*8(%rsp), %r9
- CFI_RESTORE r9
- movq 3*8(%rsp), %r8
- CFI_RESTORE r8
+
+ .if \rstor_r8910
+ movq_cfi_restore 1*8, r10
+ movq_cfi_restore 2*8, r9
+ movq_cfi_restore 3*8, r8
.endif
- .if \skiprax
- .else
- movq 4*8(%rsp), %rax
- CFI_RESTORE rax
+
+ .if \rstor_rax
+ movq_cfi_restore 4*8, rax
.endif
- .if \skiprcx
- .else
- movq 5*8(%rsp), %rcx
- CFI_RESTORE rcx
+
+ .if \rstor_rcx
+ movq_cfi_restore 5*8, rcx
.endif
- .if \skiprdx
- .else
- movq 6*8(%rsp), %rdx
- CFI_RESTORE rdx
+
+ .if \rstor_rdx
+ movq_cfi_restore 6*8, rdx
.endif
- movq 7*8(%rsp), %rsi
- CFI_RESTORE rsi
- movq 8*8(%rsp), %rdi
- CFI_RESTORE rdi
+
+ movq_cfi_restore 7*8, rsi
+ movq_cfi_restore 8*8, rdi
+
.if ARG_SKIP+\addskip > 0
addq $ARG_SKIP+\addskip, %rsp
CFI_ADJUST_CFA_OFFSET -(ARG_SKIP+\addskip)
@@ -169,38 +157,26 @@ For 32-bit we have the following conventions - kernel is built with
.endif
.endm
-#define REST_SKIP 6*8
+#define REST_SKIP (6*8)
.macro SAVE_REST
subq $REST_SKIP, %rsp
CFI_ADJUST_CFA_OFFSET REST_SKIP
- movq %rbx, 5*8(%rsp)
- CFI_REL_OFFSET rbx, 5*8
- movq %rbp, 4*8(%rsp)
- CFI_REL_OFFSET rbp, 4*8
- movq %r12, 3*8(%rsp)
- CFI_REL_OFFSET r12, 3*8
- movq %r13, 2*8(%rsp)
- CFI_REL_OFFSET r13, 2*8
- movq %r14, 1*8(%rsp)
- CFI_REL_OFFSET r14, 1*8
- movq %r15, (%rsp)
- CFI_REL_OFFSET r15, 0*8
+ movq_cfi rbx, 5*8
+ movq_cfi rbp, 4*8
+ movq_cfi r12, 3*8
+ movq_cfi r13, 2*8
+ movq_cfi r14, 1*8
+ movq_cfi r15, 0*8
.endm
.macro RESTORE_REST
- movq (%rsp), %r15
- CFI_RESTORE r15
- movq 1*8(%rsp), %r14
- CFI_RESTORE r14
- movq 2*8(%rsp), %r13
- CFI_RESTORE r13
- movq 3*8(%rsp), %r12
- CFI_RESTORE r12
- movq 4*8(%rsp), %rbp
- CFI_RESTORE rbp
- movq 5*8(%rsp), %rbx
- CFI_RESTORE rbx
+ movq_cfi_restore 0*8, r15
+ movq_cfi_restore 1*8, r14
+ movq_cfi_restore 2*8, r13
+ movq_cfi_restore 3*8, r12
+ movq_cfi_restore 4*8, rbp
+ movq_cfi_restore 5*8, rbx
addq $REST_SKIP, %rsp
CFI_ADJUST_CFA_OFFSET -(REST_SKIP)
.endm
@@ -212,9 +188,57 @@ For 32-bit we have the following conventions - kernel is built with
.macro RESTORE_ALL addskip=0
RESTORE_REST
- RESTORE_ARGS 0, \addskip
+ RESTORE_ARGS 1, \addskip
.endm
.macro icebp
.byte 0xf1
.endm
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
+ * are different from the entry_32.S versions in not changing the segment
+ * registers. So only suitable for in kernel use, not when transitioning
+ * from or to user space. The resulting stack frame is not a standard
+ * pt_regs frame. The main use case is calling C code from assembler
+ * when all the registers need to be preserved.
+ */
+
+ .macro SAVE_ALL
+ pushl_cfi %eax
+ CFI_REL_OFFSET eax, 0
+ pushl_cfi %ebp
+ CFI_REL_OFFSET ebp, 0
+ pushl_cfi %edi
+ CFI_REL_OFFSET edi, 0
+ pushl_cfi %esi
+ CFI_REL_OFFSET esi, 0
+ pushl_cfi %edx
+ CFI_REL_OFFSET edx, 0
+ pushl_cfi %ecx
+ CFI_REL_OFFSET ecx, 0
+ pushl_cfi %ebx
+ CFI_REL_OFFSET ebx, 0
+ .endm
+
+ .macro RESTORE_ALL
+ popl_cfi %ebx
+ CFI_RESTORE ebx
+ popl_cfi %ecx
+ CFI_RESTORE ecx
+ popl_cfi %edx
+ CFI_RESTORE edx
+ popl_cfi %esi
+ CFI_RESTORE esi
+ popl_cfi %edi
+ CFI_RESTORE edi
+ popl_cfi %ebp
+ CFI_RESTORE ebp
+ popl_cfi %eax
+ CFI_RESTORE eax
+ .endm
+
+#endif /* CONFIG_X86_64 */
+
diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h
new file mode 100644
index 00000000000..e656ad8c0a2
--- /dev/null
+++ b/arch/x86/include/asm/ce4100.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_CE4100_H_
+#define _ASM_CE4100_H_
+
+int ce4100_pci_init(void);
+
+#endif
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index 848850fd7d6..5f5bb0f9736 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "checksum_32.h"
+# include <asm/checksum_32.h>
#else
-# include "checksum_64.h"
+# include <asm/checksum_64.h>
#endif
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 46fc474fd81..f50de695173 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src,
int len, __wsum sum,
int *err_ptr)
{
+ __wsum ret;
+
might_sleep();
- return csum_partial_copy_generic((__force void *)src, dst,
- len, sum, err_ptr, NULL);
+ stac();
+ ret = csum_partial_copy_generic((__force void *)src, dst,
+ len, sum, err_ptr, NULL);
+ clac();
+
+ return ret;
}
/*
@@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src,
int len, __wsum sum,
int *err_ptr)
{
+ __wsum ret;
+
might_sleep();
- if (access_ok(VERIFY_WRITE, dst, len))
- return csum_partial_copy_generic(src, (__force void *)dst,
- len, sum, NULL, err_ptr);
+ if (access_ok(VERIFY_WRITE, dst, len)) {
+ stac();
+ ret = csum_partial_copy_generic(src, (__force void *)dst,
+ len, sum, NULL, err_ptr);
+ clac();
+ return ret;
+ }
if (len)
*err_ptr = -EFAULT;
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 9bfdc41629e..cd00e177449 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -133,7 +133,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
/* Do not call this directly. Use the wrappers below */
-extern __wsum csum_partial_copy_generic(const void *src, const void *dst,
+extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst,
int len, __wsum sum,
int *src_err_ptr, int *dst_err_ptr);
@@ -184,8 +184,15 @@ static inline unsigned add32_with_carry(unsigned a, unsigned b)
asm("addl %2,%0\n\t"
"adcl $0,%0"
: "=r" (a)
- : "0" (a), "r" (b));
+ : "0" (a), "rm" (b));
return a;
}
+#define HAVE_ARCH_CSUM_ADD
+static inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+ return (__force __wsum)add32_with_carry((__force unsigned)csum,
+ (__force unsigned)addend);
+}
+
#endif /* _ASM_X86_CHECKSUM_64_H */
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
new file mode 100644
index 00000000000..eda81dc0f4a
--- /dev/null
+++ b/arch/x86/include/asm/clocksource.h
@@ -0,0 +1,15 @@
+/* x86-specific clocksource additions */
+
+#ifndef _ASM_X86_CLOCKSOURCE_H
+#define _ASM_X86_CLOCKSOURCE_H
+
+#define VCLOCK_NONE 0 /* No vDSO clock available. */
+#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */
+#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */
+#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */
+
+struct arch_clocksource_data {
+ int vclock_mode;
+};
+
+#endif /* _ASM_X86_CLOCKSOURCE_H */
diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h
new file mode 100644
index 00000000000..e01f7f7ccb0
--- /dev/null
+++ b/arch/x86/include/asm/cmdline.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_CMDLINE_H
+#define _ASM_X86_CMDLINE_H
+
+int cmdline_find_option_bool(const char *cmdline_ptr, const char *option);
+
+#endif /* _ASM_X86_CMDLINE_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index a460fa088d4..d47786acb01 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -1,5 +1,233 @@
+#ifndef ASM_X86_CMPXCHG_H
+#define ASM_X86_CMPXCHG_H
+
+#include <linux/compiler.h>
+#include <asm/alternative.h> /* Provides LOCK_PREFIX */
+
+/*
+ * Non-existant functions to indicate usage errors at link time
+ * (or compile-time if the compiler implements __compiletime_error().
+ */
+extern void __xchg_wrong_size(void)
+ __compiletime_error("Bad argument size for xchg");
+extern void __cmpxchg_wrong_size(void)
+ __compiletime_error("Bad argument size for cmpxchg");
+extern void __xadd_wrong_size(void)
+ __compiletime_error("Bad argument size for xadd");
+extern void __add_wrong_size(void)
+ __compiletime_error("Bad argument size for add");
+
+/*
+ * Constants for operation sizes. On 32-bit, the 64-bit size it set to
+ * -1 because sizeof will never return -1, thereby making those switch
+ * case statements guaranteeed dead code which the compiler will
+ * eliminate, and allowing the "missing symbol in the default case" to
+ * indicate a usage error.
+ */
+#define __X86_CASE_B 1
+#define __X86_CASE_W 2
+#define __X86_CASE_L 4
+#ifdef CONFIG_64BIT
+#define __X86_CASE_Q 8
+#else
+#define __X86_CASE_Q -1 /* sizeof will never return -1 */
+#endif
+
+/*
+ * An exchange-type operation, which takes a value and a pointer, and
+ * returns the old value.
+ */
+#define __xchg_op(ptr, arg, op, lock) \
+ ({ \
+ __typeof__ (*(ptr)) __ret = (arg); \
+ switch (sizeof(*(ptr))) { \
+ case __X86_CASE_B: \
+ asm volatile (lock #op "b %b0, %1\n" \
+ : "+q" (__ret), "+m" (*(ptr)) \
+ : : "memory", "cc"); \
+ break; \
+ case __X86_CASE_W: \
+ asm volatile (lock #op "w %w0, %1\n" \
+ : "+r" (__ret), "+m" (*(ptr)) \
+ : : "memory", "cc"); \
+ break; \
+ case __X86_CASE_L: \
+ asm volatile (lock #op "l %0, %1\n" \
+ : "+r" (__ret), "+m" (*(ptr)) \
+ : : "memory", "cc"); \
+ break; \
+ case __X86_CASE_Q: \
+ asm volatile (lock #op "q %q0, %1\n" \
+ : "+r" (__ret), "+m" (*(ptr)) \
+ : : "memory", "cc"); \
+ break; \
+ default: \
+ __ ## op ## _wrong_size(); \
+ } \
+ __ret; \
+ })
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway.
+ * Since this is generally used to protect other memory information, we
+ * use "asm volatile" and "memory" clobbers to prevent gcc from moving
+ * information around.
+ */
+#define xchg(ptr, v) __xchg_op((ptr), (v), xchg, "")
+
+/*
+ * Atomic compare and exchange. Compare OLD with MEM, if identical,
+ * store NEW in MEM. Return the initial value in MEM. Success is
+ * indicated by comparing RETURN with OLD.
+ */
+#define __raw_cmpxchg(ptr, old, new, size, lock) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __typeof__(*(ptr)) __old = (old); \
+ __typeof__(*(ptr)) __new = (new); \
+ switch (size) { \
+ case __X86_CASE_B: \
+ { \
+ volatile u8 *__ptr = (volatile u8 *)(ptr); \
+ asm volatile(lock "cmpxchgb %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "q" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_W: \
+ { \
+ volatile u16 *__ptr = (volatile u16 *)(ptr); \
+ asm volatile(lock "cmpxchgw %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "r" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_L: \
+ { \
+ volatile u32 *__ptr = (volatile u32 *)(ptr); \
+ asm volatile(lock "cmpxchgl %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "r" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ case __X86_CASE_Q: \
+ { \
+ volatile u64 *__ptr = (volatile u64 *)(ptr); \
+ asm volatile(lock "cmpxchgq %2,%1" \
+ : "=a" (__ret), "+m" (*__ptr) \
+ : "r" (__new), "0" (__old) \
+ : "memory"); \
+ break; \
+ } \
+ default: \
+ __cmpxchg_wrong_size(); \
+ } \
+ __ret; \
+})
+
+#define __cmpxchg(ptr, old, new, size) \
+ __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
+
+#define __sync_cmpxchg(ptr, old, new, size) \
+ __raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
+
+#define __cmpxchg_local(ptr, old, new, size) \
+ __raw_cmpxchg((ptr), (old), (new), (size), "")
+
#ifdef CONFIG_X86_32
-# include "cmpxchg_32.h"
+# include <asm/cmpxchg_32.h>
#else
-# include "cmpxchg_64.h"
+# include <asm/cmpxchg_64.h>
+#endif
+
+#ifdef __HAVE_ARCH_CMPXCHG
+#define cmpxchg(ptr, old, new) \
+ __cmpxchg(ptr, old, new, sizeof(*(ptr)))
+
+#define sync_cmpxchg(ptr, old, new) \
+ __sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
+
+#define cmpxchg_local(ptr, old, new) \
+ __cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
#endif
+
+/*
+ * xadd() adds "inc" to "*ptr" and atomically returns the previous
+ * value of "*ptr".
+ *
+ * xadd() is locked when multiple CPUs are online
+ * xadd_sync() is always locked
+ * xadd_local() is never locked
+ */
+#define __xadd(ptr, inc, lock) __xchg_op((ptr), (inc), xadd, lock)
+#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX)
+#define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ")
+#define xadd_local(ptr, inc) __xadd((ptr), (inc), "")
+
+#define __add(ptr, inc, lock) \
+ ({ \
+ __typeof__ (*(ptr)) __ret = (inc); \
+ switch (sizeof(*(ptr))) { \
+ case __X86_CASE_B: \
+ asm volatile (lock "addb %b1, %0\n" \
+ : "+m" (*(ptr)) : "qi" (inc) \
+ : "memory", "cc"); \
+ break; \
+ case __X86_CASE_W: \
+ asm volatile (lock "addw %w1, %0\n" \
+ : "+m" (*(ptr)) : "ri" (inc) \
+ : "memory", "cc"); \
+ break; \
+ case __X86_CASE_L: \
+ asm volatile (lock "addl %1, %0\n" \
+ : "+m" (*(ptr)) : "ri" (inc) \
+ : "memory", "cc"); \
+ break; \
+ case __X86_CASE_Q: \
+ asm volatile (lock "addq %1, %0\n" \
+ : "+m" (*(ptr)) : "ri" (inc) \
+ : "memory", "cc"); \
+ break; \
+ default: \
+ __add_wrong_size(); \
+ } \
+ __ret; \
+ })
+
+/*
+ * add_*() adds "inc" to "*ptr"
+ *
+ * __add() takes a lock prefix
+ * add_smp() is locked when multiple CPUs are online
+ * add_sync() is always locked
+ */
+#define add_smp(ptr, inc) __add((ptr), (inc), LOCK_PREFIX)
+#define add_sync(ptr, inc) __add((ptr), (inc), "lock; ")
+
+#define __cmpxchg_double(pfx, p1, p2, o1, o2, n1, n2) \
+({ \
+ bool __ret; \
+ __typeof__(*(p1)) __old1 = (o1), __new1 = (n1); \
+ __typeof__(*(p2)) __old2 = (o2), __new2 = (n2); \
+ BUILD_BUG_ON(sizeof(*(p1)) != sizeof(long)); \
+ BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long)); \
+ VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long))); \
+ VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2)); \
+ asm volatile(pfx "cmpxchg%c4b %2; sete %0" \
+ : "=a" (__ret), "+d" (__old2), \
+ "+m" (*(p1)), "+m" (*(p2)) \
+ : "i" (2 * sizeof(long)), "a" (__old1), \
+ "b" (__new1), "c" (__new2)); \
+ __ret; \
+})
+
+#define cmpxchg_double(p1, p2, o1, o2, n1, n2) \
+ __cmpxchg_double(LOCK_PREFIX, p1, p2, o1, o2, n1, n2)
+
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2) \
+ __cmpxchg_double(, p1, p2, o1, o2, n1, n2)
+
+#endif /* ASM_X86_CMPXCHG_H */
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index ffb9bb6b6c3..f8bf2eecab8 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -1,171 +1,41 @@
#ifndef _ASM_X86_CMPXCHG_32_H
#define _ASM_X86_CMPXCHG_32_H
-#include <linux/bitops.h> /* for LOCK_PREFIX */
-
/*
* Note: if you use set64_bit(), __cmpxchg64(), or their variants, you
* you need to test for the feature in boot_cpu_data.
*/
-extern void __xchg_wrong_size(void);
-
-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- * but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-
-struct __xchg_dummy {
- unsigned long a[100];
-};
-#define __xg(x) ((struct __xchg_dummy *)(x))
-
-#define __xchg(x, ptr, size) \
-({ \
- __typeof(*(ptr)) __x = (x); \
- switch (size) { \
- case 1: \
- asm volatile("xchgb %b0,%1" \
- : "=q" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- case 2: \
- asm volatile("xchgw %w0,%1" \
- : "=r" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- case 4: \
- asm volatile("xchgl %0,%1" \
- : "=r" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- default: \
- __xchg_wrong_size(); \
- } \
- __x; \
-})
-
-#define xchg(ptr, v) \
- __xchg((v), (ptr), sizeof(*ptr))
-
/*
- * The semantics of XCHGCMP8B are a bit strange, this is why
- * there is a loop and the loading of %%eax and %%edx has to
- * be inside. This inlines well in most cases, the cached
- * cost is around ~38 cycles. (in the future we might want
- * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
- * might have an implicit FPU-save as a cost, so it's not
- * clear which path to go.)
+ * CMPXCHG8B only writes to the target if we had the previous
+ * value in registers, otherwise it acts as a read and gives us the
+ * "new previous" value. That is why there is a loop. Preloading
+ * EDX:EAX is a performance optimization: in the common case it means
+ * we need only one locked operation.
*
- * cmpxchg8b must be used with the lock prefix here to allow
- * the instruction to be executed atomically, see page 3-102
- * of the instruction set reference 24319102.pdf. We need
- * the reader side to see the coherent 64bit value.
+ * A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very
+ * least an FPU save and/or %cr0.ts manipulation.
+ *
+ * cmpxchg8b must be used with the lock prefix here to allow the
+ * instruction to be executed atomically. We need to have the reader
+ * side to see the coherent 64bit value.
*/
-static inline void __set_64bit(unsigned long long *ptr,
- unsigned int low, unsigned int high)
+static inline void set_64bit(volatile u64 *ptr, u64 value)
{
+ u32 low = value;
+ u32 high = value >> 32;
+ u64 prev = *ptr;
+
asm volatile("\n1:\t"
- "movl (%0), %%eax\n\t"
- "movl 4(%0), %%edx\n\t"
- LOCK_PREFIX "cmpxchg8b (%0)\n\t"
+ LOCK_PREFIX "cmpxchg8b %0\n\t"
"jnz 1b"
- : /* no outputs */
- : "D"(ptr),
- "b"(low),
- "c"(high)
- : "ax", "dx", "memory");
-}
-
-static inline void __set_64bit_constant(unsigned long long *ptr,
- unsigned long long value)
-{
- __set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32));
-}
-
-#define ll_low(x) *(((unsigned int *)&(x)) + 0)
-#define ll_high(x) *(((unsigned int *)&(x)) + 1)
-
-static inline void __set_64bit_var(unsigned long long *ptr,
- unsigned long long value)
-{
- __set_64bit(ptr, ll_low(value), ll_high(value));
+ : "=m" (*ptr), "+A" (prev)
+ : "b" (low), "c" (high)
+ : "memory");
}
-#define set_64bit(ptr, value) \
- (__builtin_constant_p((value)) \
- ? __set_64bit_constant((ptr), (value)) \
- : __set_64bit_var((ptr), (value)))
-
-#define _set_64bit(ptr, value) \
- (__builtin_constant_p(value) \
- ? __set_64bit(ptr, (unsigned int)(value), \
- (unsigned int)((value) >> 32)) \
- : __set_64bit(ptr, ll_low((value)), ll_high((value))))
-
-extern void __cmpxchg_wrong_size(void);
-
-/*
- * Atomic compare and exchange. Compare OLD with MEM, if identical,
- * store NEW in MEM. Return the initial value in MEM. Success is
- * indicated by comparing RETURN with OLD.
- */
-#define __raw_cmpxchg(ptr, old, new, size, lock) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- switch (size) { \
- case 1: \
- asm volatile(lock "cmpxchgb %b1,%2" \
- : "=a"(__ret) \
- : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- case 2: \
- asm volatile(lock "cmpxchgw %w1,%2" \
- : "=a"(__ret) \
- : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- case 4: \
- asm volatile(lock "cmpxchgl %1,%2" \
- : "=a"(__ret) \
- : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- default: \
- __cmpxchg_wrong_size(); \
- } \
- __ret; \
-})
-
-#define __cmpxchg(ptr, old, new, size) \
- __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
-
-#define __sync_cmpxchg(ptr, old, new, size) \
- __raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
-
-#define __cmpxchg_local(ptr, old, new, size) \
- __raw_cmpxchg((ptr), (old), (new), (size), "")
-
-#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
-#define cmpxchg(ptr, old, new) \
- __cmpxchg((ptr), (old), (new), sizeof(*ptr))
-
-#define sync_cmpxchg(ptr, old, new) \
- __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
-
-#define cmpxchg_local(ptr, old, new) \
- __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
-#endif
-
#ifdef CONFIG_X86_CMPXCHG64
#define cmpxchg64(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
@@ -175,103 +45,45 @@ extern void __cmpxchg_wrong_size(void);
(unsigned long long)(n)))
#endif
-static inline unsigned long long __cmpxchg64(volatile void *ptr,
- unsigned long long old,
- unsigned long long new)
+static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
{
- unsigned long long prev;
- asm volatile(LOCK_PREFIX "cmpxchg8b %3"
- : "=A"(prev)
- : "b"((unsigned long)new),
- "c"((unsigned long)(new >> 32)),
- "m"(*__xg(ptr)),
- "0"(old)
+ u64 prev;
+ asm volatile(LOCK_PREFIX "cmpxchg8b %1"
+ : "=A" (prev),
+ "+m" (*ptr)
+ : "b" ((u32)new),
+ "c" ((u32)(new >> 32)),
+ "0" (old)
: "memory");
return prev;
}
-static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
- unsigned long long old,
- unsigned long long new)
+static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
{
- unsigned long long prev;
- asm volatile("cmpxchg8b %3"
- : "=A"(prev)
- : "b"((unsigned long)new),
- "c"((unsigned long)(new >> 32)),
- "m"(*__xg(ptr)),
- "0"(old)
+ u64 prev;
+ asm volatile("cmpxchg8b %1"
+ : "=A" (prev),
+ "+m" (*ptr)
+ : "b" ((u32)new),
+ "c" ((u32)(new >> 32)),
+ "0" (old)
: "memory");
return prev;
}
-#ifndef CONFIG_X86_CMPXCHG
-/*
- * Building a kernel capable running on 80386. It may be necessary to
- * simulate the cmpxchg on the 80386 CPU. For that purpose we define
- * a function for each of the sizes we support.
- */
-
-extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
-extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
-extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
-
-static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
- unsigned long new, int size)
-{
- switch (size) {
- case 1:
- return cmpxchg_386_u8(ptr, old, new);
- case 2:
- return cmpxchg_386_u16(ptr, old, new);
- case 4:
- return cmpxchg_386_u32(ptr, old, new);
- }
- return old;
-}
-
-#define cmpxchg(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- if (likely(boot_cpu_data.x86 > 3)) \
- __ret = (__typeof__(*(ptr)))__cmpxchg((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- else \
- __ret = (__typeof__(*(ptr)))cmpxchg_386((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- __ret; \
-})
-#define cmpxchg_local(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- if (likely(boot_cpu_data.x86 > 3)) \
- __ret = (__typeof__(*(ptr)))__cmpxchg_local((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- else \
- __ret = (__typeof__(*(ptr)))cmpxchg_386((ptr), \
- (unsigned long)(o), (unsigned long)(n), \
- sizeof(*(ptr))); \
- __ret; \
-})
-#endif
-
#ifndef CONFIG_X86_CMPXCHG64
/*
* Building a kernel capable running on 80386 and 80486. It may be necessary
* to simulate the cmpxchg8b on the 80386 and 80486 CPU.
*/
-extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
-
#define cmpxchg64(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
__typeof__(*(ptr)) __old = (o); \
__typeof__(*(ptr)) __new = (n); \
- alternative_io("call cmpxchg8b_emu", \
+ alternative_io(LOCK_PREFIX_HERE \
+ "call cmpxchg8b_emu", \
"lock; cmpxchg8b (%%esi)" , \
X86_FEATURE_CX8, \
"=A" (__ret), \
@@ -282,21 +94,23 @@ extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
__ret; })
-
-#define cmpxchg64_local(ptr, o, n) \
-({ \
- __typeof__(*(ptr)) __ret; \
- if (likely(boot_cpu_data.x86 > 4)) \
- __ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr), \
- (unsigned long long)(o), \
- (unsigned long long)(n)); \
- else \
- __ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr), \
- (unsigned long long)(o), \
- (unsigned long long)(n)); \
- __ret; \
-})
+#define cmpxchg64_local(ptr, o, n) \
+({ \
+ __typeof__(*(ptr)) __ret; \
+ __typeof__(*(ptr)) __old = (o); \
+ __typeof__(*(ptr)) __new = (n); \
+ alternative_io("call cmpxchg8b_emu", \
+ "cmpxchg8b (%%esi)" , \
+ X86_FEATURE_CX8, \
+ "=A" (__ret), \
+ "S" ((ptr)), "0" (__old), \
+ "b" ((unsigned int)__new), \
+ "c" ((unsigned int)(__new>>32)) \
+ : "memory"); \
+ __ret; })
#endif
+#define system_has_cmpxchg_double() cpu_has_cx8
+
#endif /* _ASM_X86_CMPXCHG_32_H */
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 485ae415fae..614be87f1a9 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -1,123 +1,13 @@
#ifndef _ASM_X86_CMPXCHG_64_H
#define _ASM_X86_CMPXCHG_64_H
-#include <asm/alternative.h> /* Provides LOCK_PREFIX */
-
-#define __xg(x) ((volatile long *)(x))
-
-static inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
+static inline void set_64bit(volatile u64 *ptr, u64 val)
{
*ptr = val;
}
-#define _set_64bit set_64bit
-
-extern void __xchg_wrong_size(void);
-extern void __cmpxchg_wrong_size(void);
-
-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- * but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-#define __xchg(x, ptr, size) \
-({ \
- __typeof(*(ptr)) __x = (x); \
- switch (size) { \
- case 1: \
- asm volatile("xchgb %b0,%1" \
- : "=q" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- case 2: \
- asm volatile("xchgw %w0,%1" \
- : "=r" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- case 4: \
- asm volatile("xchgl %k0,%1" \
- : "=r" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- case 8: \
- asm volatile("xchgq %0,%1" \
- : "=r" (__x) \
- : "m" (*__xg(ptr)), "0" (__x) \
- : "memory"); \
- break; \
- default: \
- __xchg_wrong_size(); \
- } \
- __x; \
-})
-
-#define xchg(ptr, v) \
- __xchg((v), (ptr), sizeof(*ptr))
-
#define __HAVE_ARCH_CMPXCHG 1
-/*
- * Atomic compare and exchange. Compare OLD with MEM, if identical,
- * store NEW in MEM. Return the initial value in MEM. Success is
- * indicated by comparing RETURN with OLD.
- */
-#define __raw_cmpxchg(ptr, old, new, size, lock) \
-({ \
- __typeof__(*(ptr)) __ret; \
- __typeof__(*(ptr)) __old = (old); \
- __typeof__(*(ptr)) __new = (new); \
- switch (size) { \
- case 1: \
- asm volatile(lock "cmpxchgb %b1,%2" \
- : "=a"(__ret) \
- : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- case 2: \
- asm volatile(lock "cmpxchgw %w1,%2" \
- : "=a"(__ret) \
- : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- case 4: \
- asm volatile(lock "cmpxchgl %k1,%2" \
- : "=a"(__ret) \
- : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- case 8: \
- asm volatile(lock "cmpxchgq %1,%2" \
- : "=a"(__ret) \
- : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \
- : "memory"); \
- break; \
- default: \
- __cmpxchg_wrong_size(); \
- } \
- __ret; \
-})
-
-#define __cmpxchg(ptr, old, new, size) \
- __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
-
-#define __sync_cmpxchg(ptr, old, new, size) \
- __raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
-
-#define __cmpxchg_local(ptr, old, new, size) \
- __raw_cmpxchg((ptr), (old), (new), (size), "")
-
-#define cmpxchg(ptr, old, new) \
- __cmpxchg((ptr), (old), (new), sizeof(*ptr))
-
-#define sync_cmpxchg(ptr, old, new) \
- __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
-
-#define cmpxchg_local(ptr, old, new) \
- __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
-
#define cmpxchg64(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
@@ -130,4 +20,6 @@ extern void __cmpxchg_wrong_size(void);
cmpxchg_local((ptr), (o), (n)); \
})
+#define system_has_cmpxchg_double() cpu_has_cx16
+
#endif /* _ASM_X86_CMPXCHG_64_H */
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 9a9c7bdc923..59c6c401f79 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -6,9 +6,12 @@
*/
#include <linux/types.h>
#include <linux/sched.h>
+#include <asm/processor.h>
#include <asm/user32.h>
+#include <asm/unistd.h>
-#define COMPAT_USER_HZ 100
+#define COMPAT_USER_HZ 100
+#define COMPAT_UTS_MACHINE "i686\0\0"
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
@@ -38,6 +41,7 @@ typedef s64 __attribute__((aligned(4))) compat_s64;
typedef u32 compat_uint_t;
typedef u32 compat_ulong_t;
typedef u64 __attribute__((aligned(4))) compat_u64;
+typedef u32 compat_uptr_t;
struct compat_timespec {
compat_time_t tv_sec;
@@ -107,7 +111,8 @@ struct compat_statfs {
compat_fsid_t f_fsid;
int f_namelen; /* SunOS ignores this field. */
int f_frsize;
- int f_spare[5];
+ int f_flags;
+ int f_spare[4];
};
#define COMPAT_RLIM_OLD_INFINITY 0x7fffffff
@@ -120,6 +125,78 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */
typedef u32 compat_sigset_word;
+typedef union compat_sigval {
+ compat_int_t sival_int;
+ compat_uptr_t sival_ptr;
+} compat_sigval_t;
+
+typedef struct compat_siginfo {
+ int si_signo;
+ int si_errno;
+ int si_code;
+
+ union {
+ int _pad[128/sizeof(int) - 3];
+
+ /* kill() */
+ struct {
+ unsigned int _pid; /* sender's pid */
+ unsigned int _uid; /* sender's uid */
+ } _kill;
+
+ /* POSIX.1b timers */
+ struct {
+ compat_timer_t _tid; /* timer id */
+ int _overrun; /* overrun count */
+ compat_sigval_t _sigval; /* same as below */
+ int _sys_private; /* not to be passed to user */
+ int _overrun_incr; /* amount to add to overrun */
+ } _timer;
+
+ /* POSIX.1b signals */
+ struct {
+ unsigned int _pid; /* sender's pid */
+ unsigned int _uid; /* sender's uid */
+ compat_sigval_t _sigval;
+ } _rt;
+
+ /* SIGCHLD */
+ struct {
+ unsigned int _pid; /* which child */
+ unsigned int _uid; /* sender's uid */
+ int _status; /* exit code */
+ compat_clock_t _utime;
+ compat_clock_t _stime;
+ } _sigchld;
+
+ /* SIGCHLD (x32 version) */
+ struct {
+ unsigned int _pid; /* which child */
+ unsigned int _uid; /* sender's uid */
+ int _status; /* exit code */
+ compat_s64 _utime;
+ compat_s64 _stime;
+ } _sigchld_x32;
+
+ /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+ struct {
+ unsigned int _addr; /* faulting insn/memory ref. */
+ } _sigfault;
+
+ /* SIGPOLL */
+ struct {
+ int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
+ int _fd;
+ } _sigpoll;
+
+ struct {
+ unsigned int _call_addr; /* calling insn */
+ int _syscall; /* triggering system call number */
+ unsigned int _arch; /* AUDIT_ARCH_* of syscall */
+ } _sigsys;
+ } _sifields;
+} compat_siginfo_t;
+
#define COMPAT_OFF_T_MAX 0x7fffffff
#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL
@@ -184,7 +261,20 @@ struct compat_shmid64_ds {
/*
* The type of struct elf_prstatus.pr_reg in compatible core dumps.
*/
+#ifdef CONFIG_X86_X32_ABI
+typedef struct user_regs_struct compat_elf_gregset_t;
+
+#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
+#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
+#define SET_PR_FPVALID(S,V) \
+ do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+ while (0)
+
+#define COMPAT_USE_64BIT_TIME \
+ (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
+#else
typedef struct user_regs_struct32 compat_elf_gregset_t;
+#endif
/*
* A pointer passed in from user mode. This should not
@@ -192,7 +282,6 @@ typedef struct user_regs_struct32 compat_elf_gregset_t;
* as pointers because the syscall entry code will have
* appropriately converted them already.
*/
-typedef u32 compat_uptr_t;
static inline void __user *compat_ptr(compat_uptr_t uptr)
{
@@ -204,15 +293,32 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
return (u32)(unsigned long)uptr;
}
-static inline void __user *compat_alloc_user_space(long len)
+static inline void __user *arch_compat_alloc_user_space(long len)
+{
+ compat_uptr_t sp;
+
+ if (test_thread_flag(TIF_IA32)) {
+ sp = task_pt_regs(current)->sp;
+ } else {
+ /* -128 for the x32 ABI redzone */
+ sp = this_cpu_read(old_rsp) - 128;
+ }
+
+ return (void __user *)round_down(sp - len, 16);
+}
+
+static inline bool is_x32_task(void)
{
- struct pt_regs *regs = task_pt_regs(current);
- return (void __user *)regs->sp - len;
+#ifdef CONFIG_X86_X32_ABI
+ if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
+ return true;
+#endif
+ return false;
}
-static inline int is_compat_task(void)
+static inline bool is_compat_task(void)
{
- return current_thread_info()->status & TS_COMPAT;
+ return is_ia32_task() || is_x32_task();
}
#endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/context_tracking.h b/arch/x86/include/asm/context_tracking.h
new file mode 100644
index 00000000000..1fe49704b14
--- /dev/null
+++ b/arch/x86/include/asm/context_tracking.h
@@ -0,0 +1,10 @@
+#ifndef _ASM_X86_CONTEXT_TRACKING_H
+#define _ASM_X86_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING
+# define SCHEDULE_USER call schedule_user
+#else
+# define SCHEDULE_USER call schedule
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091bf19..d2b12988d2e 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,10 +28,14 @@ struct x86_cpu {
#ifdef CONFIG_HOTPLUG_CPU
extern int arch_register_cpu(int num);
extern void arch_unregister_cpu(int);
+extern void start_cpu0(void);
+#ifdef CONFIG_DEBUG_HOTPLUG_CPU0
+extern int _debug_hotplug_cpu(int cpu, int action);
+#endif
#endif
DECLARE_PER_CPU(int, cpu_state);
-extern unsigned int boot_cpu_id;
+int mwait_usable(const struct cpuinfo_x86 *);
#endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
new file mode 100644
index 00000000000..ff501e511d9
--- /dev/null
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -0,0 +1,13 @@
+#ifndef _CPU_DEVICE_ID
+#define _CPU_DEVICE_ID 1
+
+/*
+ * Declare drivers belonging to specific x86 CPUs
+ * Similar in spirit to pci_device_id and related PCI functions
+ */
+
+#include <linux/mod_devicetable.h>
+
+extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 637e1ec963c..e265ff95d16 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -4,9 +4,12 @@
#ifndef _ASM_X86_CPUFEATURE_H
#define _ASM_X86_CPUFEATURE_H
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
#include <asm/required-features.h>
+#endif
-#define NCAPINTS 9 /* N 32-bit words worth of info */
+#define NCAPINTS 10 /* N 32-bit words worth of info */
+#define NBUGINTS 1 /* N 32-bit bug flags */
/*
* Note: If the comment begins with a quoted string, that string is used
@@ -34,7 +37,7 @@
#define X86_FEATURE_PAT (0*32+16) /* Page Attribute Table */
#define X86_FEATURE_PSE36 (0*32+17) /* 36-bit PSEs */
#define X86_FEATURE_PN (0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH (0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_CLFLUSH (0*32+19) /* CLFLUSH instruction */
#define X86_FEATURE_DS (0*32+21) /* "dts" Debug Store */
#define X86_FEATURE_ACPI (0*32+22) /* ACPI via MSR */
#define X86_FEATURE_MMX (0*32+23) /* Multimedia Extensions */
@@ -89,7 +92,7 @@
#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
#define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */
#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_AMDC1E (3*32+21) /* AMD C1E detected */
+#define X86_FEATURE_ALWAYS (3*32+21) /* "" Always-present feature */
#define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */
#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */
@@ -97,6 +100,8 @@
#define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */
#define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF (3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU (3*32+29) /* "eagerfpu" Non lazy FPU restore */
+#define X86_FEATURE_NONSTOP_TSC_S3 (3*32+30) /* TSC doesn't stop in S3 state */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
@@ -114,16 +119,20 @@
#define X86_FEATURE_CX16 (4*32+13) /* CMPXCHG16B */
#define X86_FEATURE_XTPR (4*32+14) /* Send Task Priority Messages */
#define X86_FEATURE_PDCM (4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_PCID (4*32+17) /* Process Context Identifiers */
#define X86_FEATURE_DCA (4*32+18) /* Direct Cache Access */
#define X86_FEATURE_XMM4_1 (4*32+19) /* "sse4_1" SSE-4.1 */
#define X86_FEATURE_XMM4_2 (4*32+20) /* "sse4_2" SSE-4.2 */
#define X86_FEATURE_X2APIC (4*32+21) /* x2APIC */
#define X86_FEATURE_MOVBE (4*32+22) /* MOVBE instruction */
#define X86_FEATURE_POPCNT (4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER (4*32+24) /* Tsc deadline timer */
#define X86_FEATURE_AES (4*32+25) /* AES instructions */
#define X86_FEATURE_XSAVE (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
#define X86_FEATURE_OSXSAVE (4*32+27) /* "" XSAVE enabled in the OS */
#define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */
+#define X86_FEATURE_RDRAND (4*32+30) /* The RDRAND instruction */
#define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */
/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
@@ -150,27 +159,87 @@
#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
#define X86_FEATURE_OSVW (6*32+ 9) /* OS Visible Workaround */
#define X86_FEATURE_IBS (6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_SSE5 (6*32+11) /* SSE-5 */
+#define X86_FEATURE_XOP (6*32+11) /* extended AVX instructions */
#define X86_FEATURE_SKINIT (6*32+12) /* SKINIT/STGI instructions */
#define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP (6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4 (6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE (6*32+17) /* translation cache extension */
#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE (6*32+23) /* core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB (6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_PERFCTR_L2 (6*32+28) /* L2 performance counter extensions */
/*
* Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc
+ * CPUID levels like 0x6, 0xA etc, word 7
*/
#define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */
#define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */
+#define X86_FEATURE_CPB (7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB (7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */
+#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK (7*32+ 9) /* AMD ProcFeedbackInterface */
-/* Virtualization flags: Linux defined */
+/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */
#define X86_FEATURE_VNMI (8*32+ 1) /* Intel Virtual NMI */
#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
#define X86_FEATURE_EPT (8*32+ 3) /* Intel Extended Page Table */
#define X86_FEATURE_VPID (8*32+ 4) /* Intel Virtual Processor ID */
+#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */
+#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */
+#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
+#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
+#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST (9*32+ 1) /* TSC adjustment MSR 0x3b */
+#define X86_FEATURE_BMI1 (9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE (9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2 (9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP (9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2 (9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS (9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID (9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_MPX (9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F (9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT (9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF (9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER (9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD (9*32+28) /* AVX-512 Conflict Detection */
+
+/*
+ * BUG word(s)
+ */
+#define X86_BUG(x) (NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* AMD Erratum 400 */
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#include <asm/asm.h>
#include <linux/bitops.h>
extern const char * const x86_cap_flags[NCAPINTS*32];
@@ -179,8 +248,7 @@ extern const char * const x86_power_flags[32];
#define test_cpu_cap(c, bit) \
test_bit(bit, (unsigned long *)((c)->x86_capability))
-#define cpu_has(c, bit) \
- (__builtin_constant_p(bit) && \
+#define REQUIRED_MASK_BIT_SET(bit) \
( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) || \
(((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) || \
(((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) || \
@@ -188,10 +256,18 @@ extern const char * const x86_power_flags[32];
(((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) || \
(((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) || \
(((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \
- (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ) \
- ? 1 : \
+ (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \
+ (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \
+ (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+
+#define cpu_has(c, bit) \
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
test_cpu_cap(c, bit))
+#define this_cpu_has(bit) \
+ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
+ x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+
#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit)
#define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability))
@@ -220,7 +296,10 @@ extern const char * const x86_power_flags[32];
#define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM)
#define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2)
#define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3)
+#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3)
#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES)
+#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX)
+#define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2)
#define cpu_has_ht boot_cpu_has(X86_FEATURE_HT)
#define cpu_has_mp boot_cpu_has(X86_FEATURE_MP)
#define cpu_has_nx boot_cpu_has(X86_FEATURE_NX)
@@ -239,7 +318,7 @@ extern const char * const x86_power_flags[32];
#define cpu_has_pmm_enabled boot_cpu_has(X86_FEATURE_PMM_EN)
#define cpu_has_ds boot_cpu_has(X86_FEATURE_DS)
#define cpu_has_pebs boot_cpu_has(X86_FEATURE_PEBS)
-#define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLSH)
+#define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH)
#define cpu_has_bts boot_cpu_has(X86_FEATURE_BTS)
#define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES)
#define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
@@ -248,14 +327,17 @@ extern const char * const x86_power_flags[32];
#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2)
#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT)
+#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ)
-
-#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
-# define cpu_has_invlpg 1
-#else
-# define cpu_has_invlpg (boot_cpu_data.x86 > 3)
-#endif
+#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
+#define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB)
+#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2)
+#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8)
+#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16)
+#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU)
+#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT)
#ifdef CONFIG_X86_64
@@ -279,6 +361,198 @@ extern const char * const x86_power_flags[32];
#endif /* CONFIG_X86_64 */
+#if __GNUC__ >= 4
+extern void warn_pre_alternatives(void);
+extern bool __static_cpu_has_safe(u16 bit);
+
+/*
+ * Static testing of CPU features. Used the same as boot_cpu_has().
+ * These are only valid after alternatives have run, but will statically
+ * patch the target code for additional performance.
+ */
+static __always_inline __pure bool __static_cpu_has(u16 bit)
+{
+#ifdef CC_HAVE_ASM_GOTO
+
+#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+
+ /*
+ * Catch too early usage of this before alternatives
+ * have run.
+ */
+ asm_volatile_goto("1: jmp %l[t_warn]\n"
+ "2:\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n"
+ " .long 0\n" /* no replacement */
+ " .word %P0\n" /* 1: do replace */
+ " .byte 2b - 1b\n" /* source len */
+ " .byte 0\n" /* replacement len */
+ ".previous\n"
+ /* skipping size check since replacement size = 0 */
+ : : "i" (X86_FEATURE_ALWAYS) : : t_warn);
+
+#endif
+
+ asm_volatile_goto("1: jmp %l[t_no]\n"
+ "2:\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n"
+ " .long 0\n" /* no replacement */
+ " .word %P0\n" /* feature bit */
+ " .byte 2b - 1b\n" /* source len */
+ " .byte 0\n" /* replacement len */
+ ".previous\n"
+ /* skipping size check since replacement size = 0 */
+ : : "i" (bit) : : t_no);
+ return true;
+ t_no:
+ return false;
+
+#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+ t_warn:
+ warn_pre_alternatives();
+ return false;
+#endif
+
+#else /* CC_HAVE_ASM_GOTO */
+
+ u8 flag;
+ /* Open-coded due to __stringify() in ALTERNATIVE() */
+ asm volatile("1: movb $0,%0\n"
+ "2:\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n"
+ " .long 3f - .\n"
+ " .word %P1\n" /* feature bit */
+ " .byte 2b - 1b\n" /* source len */
+ " .byte 4f - 3f\n" /* replacement len */
+ ".previous\n"
+ ".section .discard,\"aw\",@progbits\n"
+ " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
+ ".previous\n"
+ ".section .altinstr_replacement,\"ax\"\n"
+ "3: movb $1,%0\n"
+ "4:\n"
+ ".previous\n"
+ : "=qm" (flag) : "i" (bit));
+ return flag;
+
+#endif /* CC_HAVE_ASM_GOTO */
+}
+
+#define static_cpu_has(bit) \
+( \
+ __builtin_constant_p(boot_cpu_has(bit)) ? \
+ boot_cpu_has(bit) : \
+ __builtin_constant_p(bit) ? \
+ __static_cpu_has(bit) : \
+ boot_cpu_has(bit) \
+)
+
+static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
+{
+#ifdef CC_HAVE_ASM_GOTO
+/*
+ * We need to spell the jumps to the compiler because, depending on the offset,
+ * the replacement jump can be bigger than the original jump, and this we cannot
+ * have. Thus, we force the jump to the widest, 4-byte, signed relative
+ * offset even though the last would often fit in less bytes.
+ */
+ asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+ "2:\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n" /* src offset */
+ " .long 3f - .\n" /* repl offset */
+ " .word %P1\n" /* always replace */
+ " .byte 2b - 1b\n" /* src len */
+ " .byte 4f - 3f\n" /* repl len */
+ ".previous\n"
+ ".section .altinstr_replacement,\"ax\"\n"
+ "3: .byte 0xe9\n .long %l[t_no] - 2b\n"
+ "4:\n"
+ ".previous\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n" /* src offset */
+ " .long 0\n" /* no replacement */
+ " .word %P0\n" /* feature bit */
+ " .byte 2b - 1b\n" /* src len */
+ " .byte 0\n" /* repl len */
+ ".previous\n"
+ : : "i" (bit), "i" (X86_FEATURE_ALWAYS)
+ : : t_dynamic, t_no);
+ return true;
+ t_no:
+ return false;
+ t_dynamic:
+ return __static_cpu_has_safe(bit);
+#else
+ u8 flag;
+ /* Open-coded due to __stringify() in ALTERNATIVE() */
+ asm volatile("1: movb $2,%0\n"
+ "2:\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n" /* src offset */
+ " .long 3f - .\n" /* repl offset */
+ " .word %P2\n" /* always replace */
+ " .byte 2b - 1b\n" /* source len */
+ " .byte 4f - 3f\n" /* replacement len */
+ ".previous\n"
+ ".section .discard,\"aw\",@progbits\n"
+ " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */
+ ".previous\n"
+ ".section .altinstr_replacement,\"ax\"\n"
+ "3: movb $0,%0\n"
+ "4:\n"
+ ".previous\n"
+ ".section .altinstructions,\"a\"\n"
+ " .long 1b - .\n" /* src offset */
+ " .long 5f - .\n" /* repl offset */
+ " .word %P1\n" /* feature bit */
+ " .byte 4b - 3b\n" /* src len */
+ " .byte 6f - 5f\n" /* repl len */
+ ".previous\n"
+ ".section .discard,\"aw\",@progbits\n"
+ " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */
+ ".previous\n"
+ ".section .altinstr_replacement,\"ax\"\n"
+ "5: movb $1,%0\n"
+ "6:\n"
+ ".previous\n"
+ : "=qm" (flag)
+ : "i" (bit), "i" (X86_FEATURE_ALWAYS));
+ return (flag == 2 ? __static_cpu_has_safe(bit) : flag);
+#endif /* CC_HAVE_ASM_GOTO */
+}
+
+#define static_cpu_has_safe(bit) \
+( \
+ __builtin_constant_p(boot_cpu_has(bit)) ? \
+ boot_cpu_has(bit) : \
+ _static_cpu_has_safe(bit) \
+)
+#else
+/*
+ * gcc 3.x is too stupid to do the static test; fall back to dynamic.
+ */
+#define static_cpu_has(bit) boot_cpu_has(bit)
+#define static_cpu_has_safe(bit) boot_cpu_has(bit)
+#endif
+
+#define cpu_has_bug(c, bit) cpu_has(c, (bit))
+#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
+#define clear_cpu_bug(c, bit) clear_cpu_cap(c, (bit));
+
+#define static_cpu_has_bug(bit) static_cpu_has((bit))
+#define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit))
+
+#define MAX_CPU_FEATURES (NCAPINTS * 32)
+#define cpu_have_feature boot_cpu_has
+
+#define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X"
+#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
+ boot_cpu_data.x86_model
+
#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
#endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/cputime.h b/arch/x86/include/asm/cputime.h
deleted file mode 100644
index 6d68ad7e0ea..00000000000
--- a/arch/x86/include/asm/cputime.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/crypto/aes.h
index 80545a1cbe3..80545a1cbe3 100644
--- a/arch/x86/include/asm/aes.h
+++ b/arch/x86/include/asm/crypto/aes.h
diff --git a/arch/x86/include/asm/crypto/camellia.h b/arch/x86/include/asm/crypto/camellia.h
new file mode 100644
index 00000000000..bb93333d920
--- /dev/null
+++ b/arch/x86/include/asm/crypto/camellia.h
@@ -0,0 +1,101 @@
+#ifndef ASM_X86_CAMELLIA_H
+#define ASM_X86_CAMELLIA_H
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+
+#define CAMELLIA_MIN_KEY_SIZE 16
+#define CAMELLIA_MAX_KEY_SIZE 32
+#define CAMELLIA_BLOCK_SIZE 16
+#define CAMELLIA_TABLE_BYTE_LEN 272
+#define CAMELLIA_PARALLEL_BLOCKS 2
+
+struct camellia_ctx {
+ u64 key_table[CAMELLIA_TABLE_BYTE_LEN / sizeof(u64)];
+ u32 key_length;
+};
+
+struct camellia_lrw_ctx {
+ struct lrw_table_ctx lrw_table;
+ struct camellia_ctx camellia_ctx;
+};
+
+struct camellia_xts_ctx {
+ struct camellia_ctx tweak_ctx;
+ struct camellia_ctx crypt_ctx;
+};
+
+extern int __camellia_setkey(struct camellia_ctx *cctx,
+ const unsigned char *key,
+ unsigned int key_len, u32 *flags);
+
+extern int lrw_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen);
+extern void lrw_camellia_exit_tfm(struct crypto_tfm *tfm);
+
+extern int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen);
+
+/* regular block cipher functions */
+asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+/* 2-way parallel cipher functions */
+asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+/* 16-way parallel cipher functions (avx/aes-ni) */
+asmlinkage void camellia_ecb_enc_16way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src);
+asmlinkage void camellia_ecb_dec_16way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+asmlinkage void camellia_cbc_dec_16way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src);
+asmlinkage void camellia_ctr_16way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src, le128 *iv);
+
+asmlinkage void camellia_xts_enc_16way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src, le128 *iv);
+asmlinkage void camellia_xts_dec_16way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src, le128 *iv);
+
+static inline void camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __camellia_enc_blk(ctx, dst, src, false);
+}
+
+static inline void camellia_enc_blk_xor(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __camellia_enc_blk(ctx, dst, src, true);
+}
+
+static inline void camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __camellia_enc_blk_2way(ctx, dst, src, false);
+}
+
+static inline void camellia_enc_blk_xor_2way(struct camellia_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __camellia_enc_blk_2way(ctx, dst, src, true);
+}
+
+/* glue helpers */
+extern void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src);
+extern void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+extern void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+
+extern void camellia_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);
+extern void camellia_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);
+
+#endif /* ASM_X86_CAMELLIA_H */
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
new file mode 100644
index 00000000000..1eef55596e8
--- /dev/null
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -0,0 +1,145 @@
+/*
+ * Shared glue code for 128bit block ciphers
+ */
+
+#ifndef _CRYPTO_GLUE_HELPER_H
+#define _CRYPTO_GLUE_HELPER_H
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <asm/i387.h>
+#include <crypto/b128ops.h>
+
+typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
+typedef void (*common_glue_cbc_func_t)(void *ctx, u128 *dst, const u128 *src);
+typedef void (*common_glue_ctr_func_t)(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+typedef void (*common_glue_xts_func_t)(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+
+#define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn))
+#define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn))
+#define GLUE_CTR_FUNC_CAST(fn) ((common_glue_ctr_func_t)(fn))
+#define GLUE_XTS_FUNC_CAST(fn) ((common_glue_xts_func_t)(fn))
+
+struct common_glue_func_entry {
+ unsigned int num_blocks; /* number of blocks that @fn will process */
+ union {
+ common_glue_func_t ecb;
+ common_glue_cbc_func_t cbc;
+ common_glue_ctr_func_t ctr;
+ common_glue_xts_func_t xts;
+ } fn_u;
+};
+
+struct common_glue_ctx {
+ unsigned int num_funcs;
+ int fpu_blocks_limit; /* -1 means fpu not needed at all */
+
+ /*
+ * First funcs entry must have largest num_blocks and last funcs entry
+ * must have num_blocks == 1!
+ */
+ struct common_glue_func_entry funcs[];
+};
+
+static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit,
+ struct blkcipher_desc *desc,
+ bool fpu_enabled, unsigned int nbytes)
+{
+ if (likely(fpu_blocks_limit < 0))
+ return false;
+
+ if (fpu_enabled)
+ return true;
+
+ /*
+ * Vector-registers are only used when chunk to be processed is large
+ * enough, so do not enable FPU until it is necessary.
+ */
+ if (nbytes < bsize * (unsigned int)fpu_blocks_limit)
+ return false;
+
+ if (desc) {
+ /* prevent sleeping if FPU is in use */
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ }
+
+ kernel_fpu_begin();
+ return true;
+}
+
+static inline void glue_fpu_end(bool fpu_enabled)
+{
+ if (fpu_enabled)
+ kernel_fpu_end();
+}
+
+static inline void le128_to_be128(be128 *dst, const le128 *src)
+{
+ dst->a = cpu_to_be64(le64_to_cpu(src->a));
+ dst->b = cpu_to_be64(le64_to_cpu(src->b));
+}
+
+static inline void be128_to_le128(le128 *dst, const be128 *src)
+{
+ dst->a = cpu_to_le64(be64_to_cpu(src->a));
+ dst->b = cpu_to_le64(be64_to_cpu(src->b));
+}
+
+static inline void le128_inc(le128 *i)
+{
+ u64 a = le64_to_cpu(i->a);
+ u64 b = le64_to_cpu(i->b);
+
+ b++;
+ if (!b)
+ a++;
+
+ i->a = cpu_to_le64(a);
+ i->b = cpu_to_le64(b);
+}
+
+static inline void le128_gf128mul_x_ble(le128 *dst, const le128 *src)
+{
+ u64 a = le64_to_cpu(src->a);
+ u64 b = le64_to_cpu(src->b);
+ u64 _tt = ((s64)a >> 63) & 0x87;
+
+ dst->a = cpu_to_le64((a << 1) ^ (b >> 63));
+ dst->b = cpu_to_le64((b << 1) ^ _tt);
+}
+
+extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+ struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes);
+
+extern int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+ struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src,
+ unsigned int nbytes);
+
+extern int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
+ struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src,
+ unsigned int nbytes);
+
+extern int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
+ struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes);
+
+extern int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
+ struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes,
+ common_glue_func_t tweak_fn, void *tweak_ctx,
+ void *crypt_ctx);
+
+extern void glue_xts_crypt_128bit_one(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv, common_glue_func_t fn);
+
+#endif /* _CRYPTO_GLUE_HELPER_H */
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
new file mode 100644
index 00000000000..33c2b8a435d
--- /dev/null
+++ b/arch/x86/include/asm/crypto/serpent-avx.h
@@ -0,0 +1,48 @@
+#ifndef ASM_X86_SERPENT_AVX_H
+#define ASM_X86_SERPENT_AVX_H
+
+#include <linux/crypto.h>
+#include <crypto/serpent.h>
+
+#define SERPENT_PARALLEL_BLOCKS 8
+
+struct serpent_lrw_ctx {
+ struct lrw_table_ctx lrw_table;
+ struct serpent_ctx serpent_ctx;
+};
+
+struct serpent_xts_ctx {
+ struct serpent_ctx tweak_ctx;
+ struct serpent_ctx crypt_ctx;
+};
+
+asmlinkage void serpent_ecb_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src);
+asmlinkage void serpent_ecb_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+asmlinkage void serpent_cbc_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src);
+asmlinkage void serpent_ctr_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src, le128 *iv);
+
+asmlinkage void serpent_xts_enc_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src, le128 *iv);
+asmlinkage void serpent_xts_dec_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src, le128 *iv);
+
+extern void __serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+
+extern void serpent_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv);
+extern void serpent_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv);
+
+extern int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen);
+
+extern void lrw_serpent_exit_tfm(struct crypto_tfm *tfm);
+
+extern int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen);
+
+#endif
diff --git a/arch/x86/include/asm/crypto/serpent-sse2.h b/arch/x86/include/asm/crypto/serpent-sse2.h
new file mode 100644
index 00000000000..e6e77dffbda
--- /dev/null
+++ b/arch/x86/include/asm/crypto/serpent-sse2.h
@@ -0,0 +1,63 @@
+#ifndef ASM_X86_SERPENT_SSE2_H
+#define ASM_X86_SERPENT_SSE2_H
+
+#include <linux/crypto.h>
+#include <crypto/serpent.h>
+
+#ifdef CONFIG_X86_32
+
+#define SERPENT_PARALLEL_BLOCKS 4
+
+asmlinkage void __serpent_enc_blk_4way(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void serpent_dec_blk_4way(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __serpent_enc_blk_4way(ctx, dst, src, false);
+}
+
+static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __serpent_enc_blk_4way(ctx, dst, src, true);
+}
+
+static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ serpent_dec_blk_4way(ctx, dst, src);
+}
+
+#else
+
+#define SERPENT_PARALLEL_BLOCKS 8
+
+asmlinkage void __serpent_enc_blk_8way(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void serpent_dec_blk_8way(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __serpent_enc_blk_8way(ctx, dst, src, false);
+}
+
+static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __serpent_enc_blk_8way(ctx, dst, src, true);
+}
+
+static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ serpent_dec_blk_8way(ctx, dst, src);
+}
+
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h
new file mode 100644
index 00000000000..878c51ceebb
--- /dev/null
+++ b/arch/x86/include/asm/crypto/twofish.h
@@ -0,0 +1,46 @@
+#ifndef ASM_X86_TWOFISH_H
+#define ASM_X86_TWOFISH_H
+
+#include <linux/crypto.h>
+#include <crypto/twofish.h>
+#include <crypto/lrw.h>
+#include <crypto/b128ops.h>
+
+struct twofish_lrw_ctx {
+ struct lrw_table_ctx lrw_table;
+ struct twofish_ctx twofish_ctx;
+};
+
+struct twofish_xts_ctx {
+ struct twofish_ctx tweak_ctx;
+ struct twofish_ctx crypt_ctx;
+};
+
+/* regular block cipher functions from twofish_x86_64 module */
+asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
+ const u8 *src);
+asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+/* 3-way parallel cipher functions */
+asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+/* helpers from twofish_x86_64-3way module */
+extern void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src);
+extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
+ le128 *iv);
+
+extern int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen);
+
+extern void lrw_twofish_exit_tfm(struct crypto_tfm *tfm);
+
+extern int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen);
+
+#endif /* ASM_X86_TWOFISH_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 4d447b732d8..9476c04ee63 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -11,7 +11,7 @@ DECLARE_PER_CPU(struct task_struct *, current_task);
static __always_inline struct task_struct *get_current(void)
{
- return percpu_read_stable(current_task);
+ return this_cpu_read_stable(current_task);
}
#define current get_current()
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 8240f76b531..4b528a970bd 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -2,80 +2,75 @@
#define _ASM_X86_DEBUGREG_H
-/* Indicate the register numbers for a number of the specific
- debug registers. Registers 0-3 contain the addresses we wish to trap on */
-#define DR_FIRSTADDR 0 /* u_debugreg[DR_FIRSTADDR] */
-#define DR_LASTADDR 3 /* u_debugreg[DR_LASTADDR] */
+#include <linux/bug.h>
+#include <uapi/asm/debugreg.h>
-#define DR_STATUS 6 /* u_debugreg[DR_STATUS] */
-#define DR_CONTROL 7 /* u_debugreg[DR_CONTROL] */
-
-/* Define a few things for the status register. We can use this to determine
- which debugging register was responsible for the trap. The other bits
- are either reserved or not of interest to us. */
-
-#define DR_TRAP0 (0x1) /* db0 */
-#define DR_TRAP1 (0x2) /* db1 */
-#define DR_TRAP2 (0x4) /* db2 */
-#define DR_TRAP3 (0x8) /* db3 */
-#define DR_TRAP_BITS (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)
-
-#define DR_STEP (0x4000) /* single-step */
-#define DR_SWITCH (0x8000) /* task switch */
-
-/* Now define a bunch of things for manipulating the control register.
- The top two bytes of the control register consist of 4 fields of 4
- bits - each field corresponds to one of the four debug registers,
- and indicates what types of access we trap on, and how large the data
- field is that we are looking at */
-
-#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
-#define DR_CONTROL_SIZE 4 /* 4 control bits per register */
-
-#define DR_RW_EXECUTE (0x0) /* Settings for the access types to trap on */
-#define DR_RW_WRITE (0x1)
-#define DR_RW_READ (0x3)
-
-#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
-#define DR_LEN_2 (0x4)
-#define DR_LEN_4 (0xC)
-#define DR_LEN_8 (0x8)
-
-/* The low byte to the control register determine which registers are
- enabled. There are 4 fields of two bits. One bit is "local", meaning
- that the processor will reset the bit after a task switch and the other
- is global meaning that we have to explicitly reset the bit. With linux,
- you can use either one, since we explicitly zero the register when we enter
- kernel mode. */
-
-#define DR_LOCAL_ENABLE_SHIFT 0 /* Extra shift to the local enable bit */
-#define DR_GLOBAL_ENABLE_SHIFT 1 /* Extra shift to the global enable bit */
-#define DR_LOCAL_ENABLE (0x1) /* Local enable for reg 0 */
-#define DR_GLOBAL_ENABLE (0x2) /* Global enable for reg 0 */
-#define DR_ENABLE_SIZE 2 /* 2 enable bits per register */
-
-#define DR_LOCAL_ENABLE_MASK (0x55) /* Set local bits for all 4 regs */
-#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
-
-/* The second byte to the control register has a few special things.
- We can slow the instruction pipeline for instructions coming via the
- gdt or the ldt if we want to. I am not sure why this is an advantage */
-
-#ifdef __i386__
-#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
-#else
-#define DR_CONTROL_RESERVED (0xFFFFFFFF0000FC00UL) /* Reserved */
-#endif
-
-#define DR_LOCAL_SLOWDOWN (0x100) /* Local slow the pipeline */
-#define DR_GLOBAL_SLOWDOWN (0x200) /* Global slow the pipeline */
+DECLARE_PER_CPU(unsigned long, cpu_dr7);
+#ifndef CONFIG_PARAVIRT
/*
- * HW breakpoint additions
+ * These special macros can be used to get or set a debugging register
*/
-#ifdef __KERNEL__
+#define get_debugreg(var, register) \
+ (var) = native_get_debugreg(register)
+#define set_debugreg(value, register) \
+ native_set_debugreg(register, value)
+#endif
-DECLARE_PER_CPU(unsigned long, cpu_dr7);
+static inline unsigned long native_get_debugreg(int regno)
+{
+ unsigned long val = 0; /* Damn you, gcc! */
+
+ switch (regno) {
+ case 0:
+ asm("mov %%db0, %0" :"=r" (val));
+ break;
+ case 1:
+ asm("mov %%db1, %0" :"=r" (val));
+ break;
+ case 2:
+ asm("mov %%db2, %0" :"=r" (val));
+ break;
+ case 3:
+ asm("mov %%db3, %0" :"=r" (val));
+ break;
+ case 6:
+ asm("mov %%db6, %0" :"=r" (val));
+ break;
+ case 7:
+ asm("mov %%db7, %0" :"=r" (val));
+ break;
+ default:
+ BUG();
+ }
+ return val;
+}
+
+static inline void native_set_debugreg(int regno, unsigned long value)
+{
+ switch (regno) {
+ case 0:
+ asm("mov %0, %%db0" ::"r" (value));
+ break;
+ case 1:
+ asm("mov %0, %%db1" ::"r" (value));
+ break;
+ case 2:
+ asm("mov %0, %%db2" ::"r" (value));
+ break;
+ case 3:
+ asm("mov %0, %%db3" ::"r" (value));
+ break;
+ case 6:
+ asm("mov %0, %%db6" ::"r" (value));
+ break;
+ case 7:
+ asm("mov %0, %%db7" ::"r" (value));
+ break;
+ default:
+ BUG();
+ }
+}
static inline void hw_breakpoint_disable(void)
{
@@ -91,13 +86,33 @@ static inline void hw_breakpoint_disable(void)
static inline int hw_breakpoint_active(void)
{
- return __get_cpu_var(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
+ return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK;
}
extern void aout_dump_debugregs(struct user *dump);
extern void hw_breakpoint_restore(void);
-#endif /* __KERNEL__ */
+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU(int, debug_stack_usage);
+static inline void debug_stack_usage_inc(void)
+{
+ __get_cpu_var(debug_stack_usage)++;
+}
+static inline void debug_stack_usage_dec(void)
+{
+ __get_cpu_var(debug_stack_usage)--;
+}
+int is_debug_stack(unsigned long addr);
+void debug_stack_set_zero(void);
+void debug_stack_reset(void);
+#else /* !X86_64 */
+static inline int is_debug_stack(unsigned long addr) { return 0; }
+static inline void debug_stack_set_zero(void) { }
+static inline void debug_stack_reset(void) { }
+static inline void debug_stack_usage_inc(void) { }
+static inline void debug_stack_usage_dec(void) { }
+#endif /* X86_64 */
+
#endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h
index 409a649204a..9b3b4f2754c 100644
--- a/arch/x86/include/asm/delay.h
+++ b/arch/x86/include/asm/delay.h
@@ -1,30 +1,7 @@
#ifndef _ASM_X86_DELAY_H
#define _ASM_X86_DELAY_H
-/*
- * Copyright (C) 1993 Linus Torvalds
- *
- * Delay routines calling functions in arch/x86/lib/delay.c
- */
-
-/* Undefined functions to get compile-time errors */
-extern void __bad_udelay(void);
-extern void __bad_ndelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __ndelay(unsigned long nsecs);
-extern void __const_udelay(unsigned long xloops);
-extern void __delay(unsigned long loops);
-
-/* 0x10c7 is 2**32 / 1000000 (rounded up) */
-#define udelay(n) (__builtin_constant_p(n) ? \
- ((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
- __udelay(n))
-
-/* 0x5 is 2**32 / 1000000000 (rounded up) */
-#define ndelay(n) (__builtin_constant_p(n) ? \
- ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
- __ndelay(n))
+#include <asm-generic/delay.h>
void use_tsc_delay(void);
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 617bd56b307..50d033a8947 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -4,38 +4,45 @@
#include <asm/desc_defs.h>
#include <asm/ldt.h>
#include <asm/mmu.h>
+
#include <linux/smp.h>
+#include <linux/percpu.h>
+
+static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info)
+{
+ desc->limit0 = info->limit & 0x0ffff;
+
+ desc->base0 = (info->base_addr & 0x0000ffff);
+ desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
+
+ desc->type = (info->read_exec_only ^ 1) << 1;
+ desc->type |= info->contents << 2;
+
+ desc->s = 1;
+ desc->dpl = 0x3;
+ desc->p = info->seg_not_present ^ 1;
+ desc->limit = (info->limit & 0xf0000) >> 16;
+ desc->avl = info->useable;
+ desc->d = info->seg_32bit;
+ desc->g = info->limit_in_pages;
-static inline void fill_ldt(struct desc_struct *desc,
- const struct user_desc *info)
-{
- desc->limit0 = info->limit & 0x0ffff;
- desc->base0 = info->base_addr & 0x0000ffff;
-
- desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
- desc->type = (info->read_exec_only ^ 1) << 1;
- desc->type |= info->contents << 2;
- desc->s = 1;
- desc->dpl = 0x3;
- desc->p = info->seg_not_present ^ 1;
- desc->limit = (info->limit & 0xf0000) >> 16;
- desc->avl = info->useable;
- desc->d = info->seg_32bit;
- desc->g = info->limit_in_pages;
- desc->base2 = (info->base_addr & 0xff000000) >> 24;
+ desc->base2 = (info->base_addr & 0xff000000) >> 24;
/*
- * Don't allow setting of the lm bit. It is useless anyway
- * because 64bit system calls require __USER_CS:
+ * Don't allow setting of the lm bit. It would confuse
+ * user_64bit_mode and would get overridden by sysret anyway.
*/
- desc->l = 0;
+ desc->l = 0;
}
extern struct desc_ptr idt_descr;
extern gate_desc idt_table[];
+extern struct desc_ptr debug_idt_descr;
+extern gate_desc debug_idt_table[];
struct gdt_page {
struct desc_struct gdt[GDT_ENTRIES];
} __attribute__((aligned(PAGE_SIZE)));
+
DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
@@ -48,16 +55,16 @@ static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
unsigned dpl, unsigned ist, unsigned seg)
{
- gate->offset_low = PTR_LOW(func);
- gate->segment = __KERNEL_CS;
- gate->ist = ist;
- gate->p = 1;
- gate->dpl = dpl;
- gate->zero0 = 0;
- gate->zero1 = 0;
- gate->type = type;
- gate->offset_middle = PTR_MIDDLE(func);
- gate->offset_high = PTR_HIGH(func);
+ gate->offset_low = PTR_LOW(func);
+ gate->segment = __KERNEL_CS;
+ gate->ist = ist;
+ gate->p = 1;
+ gate->dpl = dpl;
+ gate->zero0 = 0;
+ gate->zero1 = 0;
+ gate->type = type;
+ gate->offset_middle = PTR_MIDDLE(func);
+ gate->offset_high = PTR_HIGH(func);
}
#else
@@ -66,8 +73,7 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
unsigned short seg)
{
gate->a = (seg << 16) | (base & 0xffff);
- gate->b = (base & 0xffff0000) |
- (((0x80 | type | (dpl << 5)) & 0xff) << 8);
+ gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8);
}
#endif
@@ -75,31 +81,29 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
static inline int desc_empty(const void *ptr)
{
const u32 *desc = ptr;
+
return !(desc[0] | desc[1]);
}
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
-#define load_TR_desc() native_load_tr_desc()
-#define load_gdt(dtr) native_load_gdt(dtr)
-#define load_idt(dtr) native_load_idt(dtr)
-#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
-#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
-
-#define store_gdt(dtr) native_store_gdt(dtr)
-#define store_idt(dtr) native_store_idt(dtr)
-#define store_tr(tr) (tr = native_store_tr())
-
-#define load_TLS(t, cpu) native_load_tls(t, cpu)
-#define set_ldt native_set_ldt
-
-#define write_ldt_entry(dt, entry, desc) \
- native_write_ldt_entry(dt, entry, desc)
-#define write_gdt_entry(dt, entry, desc, type) \
- native_write_gdt_entry(dt, entry, desc, type)
-#define write_idt_entry(dt, entry, g) \
- native_write_idt_entry(dt, entry, g)
+#define load_TR_desc() native_load_tr_desc()
+#define load_gdt(dtr) native_load_gdt(dtr)
+#define load_idt(dtr) native_load_idt(dtr)
+#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
+
+#define store_gdt(dtr) native_store_gdt(dtr)
+#define store_idt(dtr) native_store_idt(dtr)
+#define store_tr(tr) (tr = native_store_tr())
+
+#define load_TLS(t, cpu) native_load_tls(t, cpu)
+#define set_ldt native_set_ldt
+
+#define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc)
+#define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type)
+#define write_idt_entry(dt, entry, g) native_write_idt_entry(dt, entry, g)
static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
@@ -112,33 +116,27 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
-static inline void native_write_idt_entry(gate_desc *idt, int entry,
- const gate_desc *gate)
+static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate)
{
memcpy(&idt[entry], gate, sizeof(*gate));
}
-static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry,
- const void *desc)
+static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc)
{
memcpy(&ldt[entry], desc, 8);
}
-static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry,
- const void *desc, int type)
+static inline void
+native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type)
{
unsigned int size;
+
switch (type) {
- case DESC_TSS:
- size = sizeof(tss_desc);
- break;
- case DESC_LDT:
- size = sizeof(ldt_desc);
- break;
- default:
- size = sizeof(struct desc_struct);
- break;
+ case DESC_TSS: size = sizeof(tss_desc); break;
+ case DESC_LDT: size = sizeof(ldt_desc); break;
+ default: size = sizeof(*gdt); break;
}
+
memcpy(&gdt[entry], desc, size);
}
@@ -154,20 +152,21 @@ static inline void pack_descriptor(struct desc_struct *desc, unsigned long base,
}
-static inline void set_tssldt_descriptor(void *d, unsigned long addr,
- unsigned type, unsigned size)
+static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size)
{
#ifdef CONFIG_X86_64
struct ldttss_desc64 *desc = d;
+
memset(desc, 0, sizeof(*desc));
- desc->limit0 = size & 0xFFFF;
- desc->base0 = PTR_LOW(addr);
- desc->base1 = PTR_MIDDLE(addr) & 0xFF;
- desc->type = type;
- desc->p = 1;
- desc->limit1 = (size >> 16) & 0xF;
- desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
- desc->base3 = PTR_HIGH(addr);
+
+ desc->limit0 = size & 0xFFFF;
+ desc->base0 = PTR_LOW(addr);
+ desc->base1 = PTR_MIDDLE(addr) & 0xFF;
+ desc->type = type;
+ desc->p = 1;
+ desc->limit1 = (size >> 16) & 0xF;
+ desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
+ desc->base3 = PTR_HIGH(addr);
#else
pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0);
#endif
@@ -237,14 +236,16 @@ static inline void native_store_idt(struct desc_ptr *dtr)
static inline unsigned long native_store_tr(void)
{
unsigned long tr;
+
asm volatile("str %0":"=r" (tr));
+
return tr;
}
static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
{
- unsigned int i;
struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+ unsigned int i;
for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
@@ -309,16 +310,56 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
desc->limit = (limit >> 16) & 0xf;
}
+#ifdef CONFIG_X86_64
+static inline void set_nmi_gate(int gate, void *addr)
+{
+ gate_desc s;
+
+ pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS);
+ write_idt_entry(debug_idt_table, gate, &s);
+}
+#endif
+
+#ifdef CONFIG_TRACING
+extern struct desc_ptr trace_idt_descr;
+extern gate_desc trace_idt_table[];
+static inline void write_trace_idt_entry(int entry, const gate_desc *gate)
+{
+ write_idt_entry(trace_idt_table, entry, gate);
+}
+
+static inline void _trace_set_gate(int gate, unsigned type, void *addr,
+ unsigned dpl, unsigned ist, unsigned seg)
+{
+ gate_desc s;
+
+ pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
+ /*
+ * does not need to be atomic because it is only done once at
+ * setup time
+ */
+ write_trace_idt_entry(gate, &s);
+}
+#else
+static inline void write_trace_idt_entry(int entry, const gate_desc *gate)
+{
+}
+
+#define _trace_set_gate(gate, type, addr, dpl, ist, seg)
+#endif
+
static inline void _set_gate(int gate, unsigned type, void *addr,
unsigned dpl, unsigned ist, unsigned seg)
{
gate_desc s;
+
pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
/*
* does not need to be atomic because it is only done once at
* setup time
*/
write_idt_entry(idt_table, gate, &s);
+ write_trace_idt_entry(gate, &s);
}
/*
@@ -327,11 +368,14 @@ static inline void _set_gate(int gate, unsigned type, void *addr,
* Pentium F0 0F bugfix can have resulted in the mapped
* IDT being write-protected.
*/
-static inline void set_intr_gate(unsigned int n, void *addr)
-{
- BUG_ON((unsigned)n > 0xFF);
- _set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
-}
+#define set_intr_gate(n, addr) \
+ do { \
+ BUG_ON((unsigned)n > 0xFF); \
+ _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \
+ __KERNEL_CS); \
+ _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\
+ 0, 0, __KERNEL_CS); \
+ } while (0)
extern int first_system_vector;
/* used_vectors is BITMAP for irq is not managed by percpu vector_irq */
@@ -343,15 +387,16 @@ static inline void alloc_system_vector(int vector)
set_bit(vector, used_vectors);
if (first_system_vector > vector)
first_system_vector = vector;
- } else
+ } else {
BUG();
+ }
}
-static inline void alloc_intr_gate(unsigned int n, void *addr)
-{
- alloc_system_vector(n);
- set_intr_gate(n, addr);
-}
+#define alloc_intr_gate(n, addr) \
+ do { \
+ alloc_system_vector(n); \
+ set_intr_gate(n, addr); \
+ } while (0)
/*
* This routine sets up an interrupt gate at directory privilege level 3.
@@ -392,4 +437,70 @@ static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist)
_set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS);
}
+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU(u32, debug_idt_ctr);
+static inline bool is_debug_idt_enabled(void)
+{
+ if (this_cpu_read(debug_idt_ctr))
+ return true;
+
+ return false;
+}
+
+static inline void load_debug_idt(void)
+{
+ load_idt((const struct desc_ptr *)&debug_idt_descr);
+}
+#else
+static inline bool is_debug_idt_enabled(void)
+{
+ return false;
+}
+
+static inline void load_debug_idt(void)
+{
+}
+#endif
+
+#ifdef CONFIG_TRACING
+extern atomic_t trace_idt_ctr;
+static inline bool is_trace_idt_enabled(void)
+{
+ if (atomic_read(&trace_idt_ctr))
+ return true;
+
+ return false;
+}
+
+static inline void load_trace_idt(void)
+{
+ load_idt((const struct desc_ptr *)&trace_idt_descr);
+}
+#else
+static inline bool is_trace_idt_enabled(void)
+{
+ return false;
+}
+
+static inline void load_trace_idt(void)
+{
+}
+#endif
+
+/*
+ * The load_current_idt() must be called with interrupts disabled
+ * to avoid races. That way the IDT will always be set back to the expected
+ * descriptor. It's also called when a CPU is being initialized, and
+ * that doesn't need to disable interrupts, as nothing should be
+ * bothering the CPU then.
+ */
+static inline void load_current_idt(void)
+{
+ if (is_debug_idt_enabled())
+ load_debug_idt();
+ else if (is_trace_idt_enabled())
+ load_trace_idt();
+ else
+ load_idt((const struct desc_ptr *)&idt_descr);
+}
#endif /* _ASM_X86_DESC_H */
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 029f230ab63..03dd72957d2 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -2,13 +2,10 @@
#define _ASM_X86_DEVICE_H
struct dev_archdata {
-#ifdef CONFIG_ACPI
- void *acpi_handle;
+#ifdef CONFIG_X86_DEV_DMA_OPS
+ struct dma_map_ops *dma_ops;
#endif
-#ifdef CONFIG_X86_64
-struct dma_map_ops *dma_ops;
-#endif
-#if defined(CONFIG_DMAR) || defined(CONFIG_AMD_IOMMU)
+#if defined(CONFIG_INTEL_IOMMU) || defined(CONFIG_AMD_IOMMU)
void *iommu; /* hook for IOMMU specific extension */
#endif
};
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index 9a2d644c08e..ced283ac79d 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -4,6 +4,7 @@
#ifdef CONFIG_X86_32
#include <linux/types.h>
+#include <linux/log2.h>
/*
* do_div() is NOT a C function. It wants to return
@@ -21,15 +22,20 @@
({ \
unsigned long __upper, __low, __high, __mod, __base; \
__base = (base); \
- asm("":"=a" (__low), "=d" (__high) : "A" (n)); \
- __upper = __high; \
- if (__high) { \
- __upper = __high % (__base); \
- __high = __high / (__base); \
+ if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \
+ __mod = n & (__base - 1); \
+ n >>= ilog2(__base); \
+ } else { \
+ asm("" : "=a" (__low), "=d" (__high) : "A" (n));\
+ __upper = __high; \
+ if (__high) { \
+ __upper = __high % (__base); \
+ __high = __high / (__base); \
+ } \
+ asm("divl %2" : "=a" (__low), "=d" (__mod) \
+ : "rm" (__base), "0" (__low), "1" (__upper)); \
+ asm("" : "=A" (n) : "a" (__low), "d" (__high)); \
} \
- asm("divl %2":"=a" (__low), "=d" (__mod) \
- : "rm" (__base), "0" (__low), "1" (__upper)); \
- asm("":"=A" (n) : "a" (__low), "d" (__high)); \
__mod; \
})
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
new file mode 100644
index 00000000000..b4b38bacb40
--- /dev/null
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -0,0 +1,12 @@
+#ifndef ASMX86_DMA_CONTIGUOUS_H
+#define ASMX86_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ac91eed2106..808dae63eee 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -2,7 +2,7 @@
#define _ASM_X86_DMA_MAPPING_H
/*
- * IOMMU interface. See Documentation/PCI/PCI-DMA-mapping.txt and
+ * IOMMU interface. See Documentation/DMA-API-HOWTO.txt and
* Documentation/DMA-API.txt for documentation.
*/
@@ -13,6 +13,7 @@
#include <asm/io.h>
#include <asm/swiotlb.h>
#include <asm-generic/dma-coherent.h>
+#include <linux/dma-contiguous.h>
#ifdef CONFIG_ISA
# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -30,7 +31,7 @@ extern struct dma_map_ops *dma_ops;
static inline struct dma_map_ops *get_dma_ops(struct device *dev)
{
-#ifdef CONFIG_X86_32
+#ifndef CONFIG_X86_DEV_DMA_OPS
return dma_ops;
#else
if (unlikely(!dev) || !dev->archdata.dma_ops)
@@ -46,6 +47,7 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
struct dma_map_ops *ops = get_dma_ops(dev);
+ debug_dma_mapping_error(dev, dma_addr);
if (ops->mapping_error)
return ops->mapping_error(dev, dma_addr);
@@ -54,13 +56,23 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_is_consistent(d, h) (1)
extern int dma_supported(struct device *hwdev, u64 mask);
extern int dma_set_mask(struct device *dev, u64 mask);
extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t *dma_addr, gfp_t flag);
+ dma_addr_t *dma_addr, gfp_t flag,
+ struct dma_attrs *attrs);
+
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_addr,
+ struct dma_attrs *attrs);
+
+#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
+extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
+extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+extern phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
+#else
static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
{
@@ -79,6 +91,7 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
{
return daddr;
}
+#endif /* CONFIG_X86_DMA_REMAP */
static inline void
dma_cache_sync(struct device *dev, void *vaddr, size_t size,
@@ -87,13 +100,6 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size,
flush_write_buffers();
}
-static inline int dma_get_cache_alignment(void)
-{
- /* no easy way to get cache size on all x86, so return the
- * maximum possible, to be safe */
- return boot_cpu_data.x86_clflush_size;
-}
-
static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
gfp_t gfp)
{
@@ -119,9 +125,11 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
return gfp;
}
+#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL)
+
static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
- gfp_t gfp)
+dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, struct dma_attrs *attrs)
{
struct dma_map_ops *ops = get_dma_ops(dev);
void *memory;
@@ -137,18 +145,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
if (!is_device_dma_capable(dev))
return NULL;
- if (!ops->alloc_coherent)
+ if (!ops->alloc)
return NULL;
- memory = ops->alloc_coherent(dev, size, dma_handle,
- dma_alloc_coherent_gfp_flags(dev, gfp));
+ memory = ops->alloc(dev, size, dma_handle,
+ dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
return memory;
}
-static inline void dma_free_coherent(struct device *dev, size_t size,
- void *vaddr, dma_addr_t bus)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t bus,
+ struct dma_attrs *attrs)
{
struct dma_map_ops *ops = get_dma_ops(dev);
@@ -158,8 +169,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
return;
debug_dma_free_coherent(dev, size, vaddr, bus);
- if (ops->free_coherent)
- ops->free_coherent(dev, size, vaddr, bus);
+ if (ops->free)
+ ops->free(dev, size, vaddr, bus, attrs);
}
#endif
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index ca1098a7e58..0bdb0c54d9a 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -10,7 +10,6 @@
#include <linux/spinlock.h> /* And spinlocks */
#include <asm/io.h> /* need byte IO */
-#include <linux/delay.h>
#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
#define dma_outb outb_p
@@ -70,22 +69,18 @@
#define MAX_DMA_CHANNELS 8
-#ifdef CONFIG_X86_32
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000)
-
-#else
-
/* 16MB ISA DMA zone */
#define MAX_DMA_PFN ((16 * 1024 * 1024) >> PAGE_SHIFT)
/* 4GB broken PCI/AGP hardware bus master zone */
#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+#ifdef CONFIG_X86_32
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000)
+#else
/* Compat define for old dma zone */
#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
-
#endif
/* 8237 DMA controllers */
@@ -151,6 +146,7 @@
#define DMA_AUTOINIT 0x10
+#ifdef CONFIG_ISA_DMA_API
extern spinlock_t dma_spin_lock;
static inline unsigned long claim_dma_lock(void)
@@ -164,6 +160,7 @@ static inline void release_dma_lock(unsigned long flags)
{
spin_unlock_irqrestore(&dma_spin_lock, flags);
}
+#endif /* CONFIG_ISA_DMA_API */
/* enable/disable a specific DMA channel */
static inline void enable_dma(unsigned int dmanr)
@@ -303,9 +300,11 @@ static inline int get_dma_residue(unsigned int dmanr)
}
-/* These are in kernel/dma.c: */
+/* These are in kernel/dma.c because x86 uses CONFIG_GENERIC_ISA_DMA */
+#ifdef CONFIG_ISA_DMA_API
extern int request_dma(unsigned int dmanr, const char *device_id);
extern void free_dma(unsigned int dmanr);
+#endif
/* From PCI */
diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index fd8f9e2ca35..535192f6bfa 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -13,7 +13,9 @@ static __always_inline __init void *dmi_alloc(unsigned len)
}
/* Use early IO mappings for DMI because it's initialized early */
-#define dmi_ioremap early_ioremap
-#define dmi_iounmap early_iounmap
+#define dmi_early_remap early_ioremap
+#define dmi_early_unmap early_iounmap
+#define dmi_remap ioremap
+#define dmi_unmap iounmap
#endif /* _ASM_X86_DMI_H */
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
deleted file mode 100644
index 70dac199b09..00000000000
--- a/arch/x86/include/asm/ds.h
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * Debug Store (DS) support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - DS and BTS hardware configuration
- * - buffer overflow handling (to be done)
- * - buffer access
- *
- * It does not do:
- * - security checking (is the caller allowed to trace the task)
- * - buffer allocation (memory accounting)
- *
- *
- * Copyright (C) 2007-2009 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
- */
-
-#ifndef _ASM_X86_DS_H
-#define _ASM_X86_DS_H
-
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/err.h>
-
-
-#ifdef CONFIG_X86_DS
-
-struct task_struct;
-struct ds_context;
-struct ds_tracer;
-struct bts_tracer;
-struct pebs_tracer;
-
-typedef void (*bts_ovfl_callback_t)(struct bts_tracer *);
-typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
-
-
-/*
- * A list of features plus corresponding macros to talk about them in
- * the ds_request function's flags parameter.
- *
- * We use the enum to index an array of corresponding control bits;
- * we use the macro to index a flags bit-vector.
- */
-enum ds_feature {
- dsf_bts = 0,
- dsf_bts_kernel,
-#define BTS_KERNEL (1 << dsf_bts_kernel)
- /* trace kernel-mode branches */
-
- dsf_bts_user,
-#define BTS_USER (1 << dsf_bts_user)
- /* trace user-mode branches */
-
- dsf_bts_overflow,
- dsf_bts_max,
- dsf_pebs = dsf_bts_max,
-
- dsf_pebs_max,
- dsf_ctl_max = dsf_pebs_max,
- dsf_bts_timestamps = dsf_ctl_max,
-#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps)
- /* add timestamps into BTS trace */
-
-#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS)
-};
-
-
-/*
- * Request BTS or PEBS
- *
- * Due to alignement constraints, the actual buffer may be slightly
- * smaller than the requested or provided buffer.
- *
- * Returns a pointer to a tracer structure on success, or
- * ERR_PTR(errcode) on failure.
- *
- * The interrupt threshold is independent from the overflow callback
- * to allow users to use their own overflow interrupt handling mechanism.
- *
- * The function might sleep.
- *
- * task: the task to request recording for
- * cpu: the cpu to request recording for
- * base: the base pointer for the (non-pageable) buffer;
- * size: the size of the provided buffer in bytes
- * ovfl: pointer to a function to be called on buffer overflow;
- * NULL if cyclic buffer requested
- * th: the interrupt threshold in records from the end of the buffer;
- * -1 if no interrupt threshold is requested.
- * flags: a bit-mask of the above flags
- */
-extern struct bts_tracer *ds_request_bts_task(struct task_struct *task,
- void *base, size_t size,
- bts_ovfl_callback_t ovfl,
- size_t th, unsigned int flags);
-extern struct bts_tracer *ds_request_bts_cpu(int cpu, void *base, size_t size,
- bts_ovfl_callback_t ovfl,
- size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_task(struct task_struct *task,
- void *base, size_t size,
- pebs_ovfl_callback_t ovfl,
- size_t th, unsigned int flags);
-extern struct pebs_tracer *ds_request_pebs_cpu(int cpu,
- void *base, size_t size,
- pebs_ovfl_callback_t ovfl,
- size_t th, unsigned int flags);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Must be called with irq's enabled.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern void ds_release_bts(struct bts_tracer *tracer);
-extern void ds_suspend_bts(struct bts_tracer *tracer);
-extern void ds_resume_bts(struct bts_tracer *tracer);
-extern void ds_release_pebs(struct pebs_tracer *tracer);
-extern void ds_suspend_pebs(struct pebs_tracer *tracer);
-extern void ds_resume_pebs(struct pebs_tracer *tracer);
-
-/*
- * Release BTS or PEBS resources
- * Suspend and resume BTS or PEBS tracing
- *
- * Cpu tracers must call this on the traced cpu.
- * Task tracers must call ds_release_~_noirq() for themselves.
- *
- * May be called with irq's disabled.
- *
- * Returns 0 if successful;
- * -EPERM if the cpu tracer does not trace the current cpu.
- * -EPERM if the task tracer does not trace itself.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_release_bts_noirq(struct bts_tracer *tracer);
-extern int ds_suspend_bts_noirq(struct bts_tracer *tracer);
-extern int ds_resume_bts_noirq(struct bts_tracer *tracer);
-extern int ds_release_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_suspend_pebs_noirq(struct pebs_tracer *tracer);
-extern int ds_resume_pebs_noirq(struct pebs_tracer *tracer);
-
-
-/*
- * The raw DS buffer state as it is used for BTS and PEBS recording.
- *
- * This is the low-level, arch-dependent interface for working
- * directly on the raw trace data.
- */
-struct ds_trace {
- /* the number of bts/pebs records */
- size_t n;
- /* the size of a bts/pebs record in bytes */
- size_t size;
- /* pointers into the raw buffer:
- - to the first entry */
- void *begin;
- /* - one beyond the last entry */
- void *end;
- /* - one beyond the newest entry */
- void *top;
- /* - the interrupt threshold */
- void *ith;
- /* flags given on ds_request() */
- unsigned int flags;
-};
-
-/*
- * An arch-independent view on branch trace data.
- */
-enum bts_qualifier {
- bts_invalid,
-#define BTS_INVALID bts_invalid
-
- bts_branch,
-#define BTS_BRANCH bts_branch
-
- bts_task_arrives,
-#define BTS_TASK_ARRIVES bts_task_arrives
-
- bts_task_departs,
-#define BTS_TASK_DEPARTS bts_task_departs
-
- bts_qual_bit_size = 4,
- bts_qual_max = (1 << bts_qual_bit_size),
-};
-
-struct bts_struct {
- __u64 qualifier;
- union {
- /* BTS_BRANCH */
- struct {
- __u64 from;
- __u64 to;
- } lbr;
- /* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
- struct {
- __u64 clock;
- pid_t pid;
- } event;
- } variant;
-};
-
-
-/*
- * The BTS state.
- *
- * This gives access to the raw DS state and adds functions to provide
- * an arch-independent view of the BTS data.
- */
-struct bts_trace {
- struct ds_trace ds;
-
- int (*read)(struct bts_tracer *tracer, const void *at,
- struct bts_struct *out);
- int (*write)(struct bts_tracer *tracer, const struct bts_struct *in);
-};
-
-
-/*
- * The PEBS state.
- *
- * This gives access to the raw DS state and the PEBS-specific counter
- * reset value.
- */
-struct pebs_trace {
- struct ds_trace ds;
-
- /* the number of valid counters in the below array */
- unsigned int counters;
-
-#define MAX_PEBS_COUNTERS 4
- /* the counter reset value */
- unsigned long long counter_reset[MAX_PEBS_COUNTERS];
-};
-
-
-/*
- * Read the BTS or PEBS trace.
- *
- * Returns a view on the trace collected for the parameter tracer.
- *
- * The view remains valid as long as the traced task is not running or
- * the tracer is suspended.
- * Writes into the trace buffer are not reflected.
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer);
-extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer);
-
-
-/*
- * Reset the write pointer of the BTS/PEBS buffer.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_reset_bts(struct bts_tracer *tracer);
-extern int ds_reset_pebs(struct pebs_tracer *tracer);
-
-/*
- * Set the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_pebs()
- * counter: the index of the counter
- * value: the new counter reset value
- */
-extern int ds_set_pebs_reset(struct pebs_tracer *tracer,
- unsigned int counter, u64 value);
-
-/*
- * Initialization
- */
-struct cpuinfo_x86;
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
-
-/*
- * Context switch work
- */
-extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
-
-#else /* CONFIG_X86_DS */
-
-struct cpuinfo_x86;
-static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
-static inline void ds_switch_to(struct task_struct *prev,
- struct task_struct *next) {}
-
-#endif /* CONFIG_X86_DS */
-#endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index ae6253ab902..f6f15986df6 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -27,6 +27,7 @@
#define CFI_REMEMBER_STATE .cfi_remember_state
#define CFI_RESTORE_STATE .cfi_restore_state
#define CFI_UNDEFINED .cfi_undefined
+#define CFI_ESCAPE .cfi_escape
#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
#define CFI_SIGNAL_FRAME .cfi_signal_frame
@@ -34,6 +35,18 @@
#define CFI_SIGNAL_FRAME
#endif
+#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
+ /*
+ * Emit CFI data in .debug_frame sections, not .eh_frame sections.
+ * The latter we currently just discard since we don't do DWARF
+ * unwinding at runtime. So only the offline DWARF information is
+ * useful to anyone. Note we should not use this directive if this
+ * file is used in the vDSO assembly, or if vmlinux.lds.S gets
+ * changed so it doesn't discard .eh_frame.
+ */
+ .cfi_sections .debug_frame
+#endif
+
#else
/*
@@ -56,6 +69,7 @@
#define CFI_REMEMBER_STATE cfi_ignore
#define CFI_RESTORE_STATE cfi_ignore
#define CFI_UNDEFINED cfi_ignore
+#define CFI_ESCAPE cfi_ignore
#define CFI_SIGNAL_FRAME cfi_ignore
#endif
@@ -77,6 +91,16 @@
CFI_ADJUST_CFA_OFFSET -8
.endm
+ .macro pushfq_cfi
+ pushfq
+ CFI_ADJUST_CFA_OFFSET 8
+ .endm
+
+ .macro popfq_cfi
+ popfq
+ CFI_ADJUST_CFA_OFFSET -8
+ .endm
+
.macro movq_cfi reg offset=0
movq %\reg, \offset(%rsp)
CFI_REL_OFFSET \reg, \offset
@@ -97,6 +121,16 @@
CFI_ADJUST_CFA_OFFSET -4
.endm
+ .macro pushfl_cfi
+ pushfl
+ CFI_ADJUST_CFA_OFFSET 4
+ .endm
+
+ .macro popfl_cfi
+ popfl
+ CFI_ADJUST_CFA_OFFSET -4
+ .endm
+
.macro movl_cfi reg offset=0
movl %\reg, \offset(%esp)
CFI_REL_OFFSET \reg, \offset
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 761249e396f..779c2efe2e9 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -1,73 +1,14 @@
#ifndef _ASM_X86_E820_H
#define _ASM_X86_E820_H
-#define E820MAP 0x2d0 /* our map */
-#define E820MAX 128 /* number of entries in E820MAP */
-/*
- * Legacy E820 BIOS limits us to 128 (E820MAX) nodes due to the
- * constrained space in the zeropage. If we have more nodes than
- * that, and if we've booted off EFI firmware, then the EFI tables
- * passed us from the EFI firmware can list more nodes. Size our
- * internal memory map tables to have room for these additional
- * nodes, based on up to three entries per node for which the
- * kernel was built: MAX_NUMNODES == (1 << CONFIG_NODES_SHIFT),
- * plus E820MAX, allowing space for the possible duplicate E820
- * entries that might need room in the same arrays, prior to the
- * call to sanitize_e820_map() to remove duplicates. The allowance
- * of three memory map entries per node is "enough" entries for
- * the initial hardware platform motivating this mechanism to make
- * use of additional EFI map entries. Future platforms may want
- * to allow more than three entries per node or otherwise refine
- * this size.
- */
-
-/*
- * Odd: 'make headers_check' complains about numa.h if I try
- * to collapse the next two #ifdef lines to a single line:
- * #if defined(__KERNEL__) && defined(CONFIG_EFI)
- */
-#ifdef __KERNEL__
#ifdef CONFIG_EFI
#include <linux/numa.h>
#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
#else /* ! CONFIG_EFI */
#define E820_X_MAX E820MAX
#endif
-#else /* ! __KERNEL__ */
-#define E820_X_MAX E820MAX
-#endif
-
-#define E820NR 0x1e8 /* # entries in E820MAP */
-
-#define E820_RAM 1
-#define E820_RESERVED 2
-#define E820_ACPI 3
-#define E820_NVS 4
-#define E820_UNUSABLE 5
-
-/* reserved RAM used by kernel itself */
-#define E820_RESERVED_KERN 128
-
+#include <uapi/asm/e820.h>
#ifndef __ASSEMBLY__
-#include <linux/types.h>
-struct e820entry {
- __u64 addr; /* start of memory segment */
- __u64 size; /* size of memory segment */
- __u32 type; /* type of memory segment */
-} __attribute__((packed));
-
-struct e820map {
- __u32 nr_map;
- struct e820entry map[E820_X_MAX];
-};
-
-#define ISA_START_ADDRESS 0xa0000
-#define ISA_END_ADDRESS 0x100000
-
-#define BIOS_BEGIN 0x000a0000
-#define BIOS_END 0x00100000
-
-#ifdef __KERNEL__
/* see comment in arch/x86/kernel/e820.c */
extern struct e820map e820;
extern struct e820map e820_saved;
@@ -88,7 +29,7 @@ extern void e820_setup_gap(void);
extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
unsigned long start_addr, unsigned long long end_addr);
struct setup_data;
-extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
+extern void parse_e820_ext(u64 phys_addr, u32 data_len);
#if defined(CONFIG_X86_64) || \
(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
@@ -107,26 +48,13 @@ static inline void early_memtest(unsigned long start, unsigned long end)
}
#endif
-extern unsigned long end_user_pfn;
-
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-
extern unsigned long e820_end_of_ram_pfn(void);
extern unsigned long e820_end_of_low_ram_pfn(void);
-extern int e820_find_active_region(const struct e820entry *ei,
- unsigned long start_pfn,
- unsigned long last_pfn,
- unsigned long *ei_startpfn,
- unsigned long *ei_endpfn);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
- unsigned long end_pfn);
-extern u64 e820_hole_size(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 sizet, u64 align);
+
+void memblock_x86_fill(void);
+void memblock_find_dma_reserve(void);
+
extern void finish_e820_parsing(void);
extern void e820_reserve_resources(void);
extern void e820_reserve_resources_late(void);
@@ -142,13 +70,8 @@ static inline bool is_ISA_range(u64 s, u64 e)
return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
}
-#endif /* __KERNEL__ */
#endif /* __ASSEMBLY__ */
-
-#ifdef __KERNEL__
#include <linux/ioport.h>
#define HIGH_MEMORY (1024*1024)
-#endif /* __KERNEL__ */
-
#endif /* _ASM_X86_E820_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 8406ed7f992..1eb5f6433ad 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -1,100 +1,162 @@
#ifndef _ASM_X86_EFI_H
#define _ASM_X86_EFI_H
+#include <asm/i387.h>
+/*
+ * We map the EFI regions needed for runtime services non-contiguously,
+ * with preserved alignment on virtual addresses starting from -4G down
+ * for a total max space of 64G. This way, we provide for stable runtime
+ * services addresses across kernels so that a kexec'd kernel can still
+ * use them.
+ *
+ * This is the main reason why we're doing stable VA mappings for RT
+ * services.
+ *
+ * This flag is used in conjuction with a chicken bit called
+ * "efi=old_map" which can be used as a fallback to the old runtime
+ * services mapping method in case there's some b0rkage with a
+ * particular EFI implementation (haha, it is hard to hold up the
+ * sarcasm here...).
+ */
+#define EFI_OLD_MEMMAP EFI_ARCH_1
+
+#define EFI32_LOADER_SIGNATURE "EL32"
+#define EFI64_LOADER_SIGNATURE "EL64"
+
#ifdef CONFIG_X86_32
+
extern unsigned long asmlinkage efi_call_phys(void *, ...);
-#define efi_call_phys0(f) efi_call_phys(f)
-#define efi_call_phys1(f, a1) efi_call_phys(f, a1)
-#define efi_call_phys2(f, a1, a2) efi_call_phys(f, a1, a2)
-#define efi_call_phys3(f, a1, a2, a3) efi_call_phys(f, a1, a2, a3)
-#define efi_call_phys4(f, a1, a2, a3, a4) \
- efi_call_phys(f, a1, a2, a3, a4)
-#define efi_call_phys5(f, a1, a2, a3, a4, a5) \
- efi_call_phys(f, a1, a2, a3, a4, a5)
-#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6) \
- efi_call_phys(f, a1, a2, a3, a4, a5, a6)
/*
* Wrap all the virtual calls in a way that forces the parameters on the stack.
*/
+/* Use this macro if your virtual returns a non-void value */
#define efi_call_virt(f, args...) \
- ((efi_##f##_t __attribute__((regparm(0)))*)efi.systab->runtime->f)(args)
+({ \
+ efi_status_t __s; \
+ kernel_fpu_begin(); \
+ __s = ((efi_##f##_t __attribute__((regparm(0)))*) \
+ efi.systab->runtime->f)(args); \
+ kernel_fpu_end(); \
+ __s; \
+})
-#define efi_call_virt0(f) efi_call_virt(f)
-#define efi_call_virt1(f, a1) efi_call_virt(f, a1)
-#define efi_call_virt2(f, a1, a2) efi_call_virt(f, a1, a2)
-#define efi_call_virt3(f, a1, a2, a3) efi_call_virt(f, a1, a2, a3)
-#define efi_call_virt4(f, a1, a2, a3, a4) \
- efi_call_virt(f, a1, a2, a3, a4)
-#define efi_call_virt5(f, a1, a2, a3, a4, a5) \
- efi_call_virt(f, a1, a2, a3, a4, a5)
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \
- efi_call_virt(f, a1, a2, a3, a4, a5, a6)
+/* Use this macro if your virtual call does not return any value */
+#define __efi_call_virt(f, args...) \
+({ \
+ kernel_fpu_begin(); \
+ ((efi_##f##_t __attribute__((regparm(0)))*) \
+ efi.systab->runtime->f)(args); \
+ kernel_fpu_end(); \
+})
-#define efi_ioremap(addr, size, type) ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size)
#else /* !CONFIG_X86_32 */
-extern u64 efi_call0(void *fp);
-extern u64 efi_call1(void *fp, u64 arg1);
-extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
-extern u64 efi_call3(void *fp, u64 arg1, u64 arg2, u64 arg3);
-extern u64 efi_call4(void *fp, u64 arg1, u64 arg2, u64 arg3, u64 arg4);
-extern u64 efi_call5(void *fp, u64 arg1, u64 arg2, u64 arg3,
- u64 arg4, u64 arg5);
-extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
- u64 arg4, u64 arg5, u64 arg6);
-
-#define efi_call_phys0(f) \
- efi_call0((void *)(f))
-#define efi_call_phys1(f, a1) \
- efi_call1((void *)(f), (u64)(a1))
-#define efi_call_phys2(f, a1, a2) \
- efi_call2((void *)(f), (u64)(a1), (u64)(a2))
-#define efi_call_phys3(f, a1, a2, a3) \
- efi_call3((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3))
-#define efi_call_phys4(f, a1, a2, a3, a4) \
- efi_call4((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3), \
- (u64)(a4))
-#define efi_call_phys5(f, a1, a2, a3, a4, a5) \
- efi_call5((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3), \
- (u64)(a4), (u64)(a5))
-#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6) \
- efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3), \
- (u64)(a4), (u64)(a5), (u64)(a6))
-
-#define efi_call_virt0(f) \
- efi_call0((void *)(efi.systab->runtime->f))
-#define efi_call_virt1(f, a1) \
- efi_call1((void *)(efi.systab->runtime->f), (u64)(a1))
-#define efi_call_virt2(f, a1, a2) \
- efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
-#define efi_call_virt3(f, a1, a2, a3) \
- efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
- (u64)(a3))
-#define efi_call_virt4(f, a1, a2, a3, a4) \
- efi_call4((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
- (u64)(a3), (u64)(a4))
-#define efi_call_virt5(f, a1, a2, a3, a4, a5) \
- efi_call5((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
- (u64)(a3), (u64)(a4), (u64)(a5))
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \
- efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
- (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+#define EFI_LOADER_SIGNATURE "EL64"
+
+extern u64 asmlinkage efi_call(void *fp, ...);
+
+#define efi_call_phys(f, args...) efi_call((f), args)
+
+#define efi_call_virt(f, ...) \
+({ \
+ efi_status_t __s; \
+ \
+ efi_sync_low_kernel_mappings(); \
+ preempt_disable(); \
+ __kernel_fpu_begin(); \
+ __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \
+ __kernel_fpu_end(); \
+ preempt_enable(); \
+ __s; \
+})
+
+/*
+ * All X86_64 virt calls return non-void values. Thus, use non-void call for
+ * virt calls that would be void on X86_32.
+ */
+#define __efi_call_virt(f, args...) efi_call_virt(f, args)
extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
- u32 type);
+ u32 type, u64 attribute);
#endif /* CONFIG_X86_32 */
extern int add_efi_memmap;
-extern void efi_reserve_early(void);
+extern struct efi_scratch efi_scratch;
+extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
+extern int efi_memblock_x86_reserve_range(void);
extern void efi_call_phys_prelog(void);
extern void efi_call_phys_epilog(void);
+extern void efi_unmap_memmap(void);
+extern void efi_memory_uc(u64 addr, unsigned long size);
+extern void __init efi_map_region(efi_memory_desc_t *md);
+extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
+extern void efi_sync_low_kernel_mappings(void);
+extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void __init old_map_region(efi_memory_desc_t *md);
+extern void __init runtime_code_page_mkexec(void);
+extern void __init efi_runtime_mkexec(void);
+extern void __init efi_dump_pagetable(void);
+extern void __init efi_apply_memmap_quirks(void);
+
+struct efi_setup_data {
+ u64 fw_vendor;
+ u64 runtime;
+ u64 tables;
+ u64 smbios;
+ u64 reserved[8];
+};
+
+extern u64 efi_setup;
+
+#ifdef CONFIG_EFI
+
+static inline bool efi_is_native(void)
+{
+ return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
+}
+
+static inline bool efi_runtime_supported(void)
+{
+ if (efi_is_native())
+ return true;
+
+ if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP))
+ return true;
+
+ return false;
+}
+
+extern struct console early_efi_console;
+extern void parse_efi_setup(u64 phys_addr, u32 data_len);
-#ifndef CONFIG_EFI
+#ifdef CONFIG_EFI_MIXED
+extern void efi_thunk_runtime_setup(void);
+extern efi_status_t efi_thunk_set_virtual_address_map(
+ void *phys_set_virtual_address_map,
+ unsigned long memory_map_size,
+ unsigned long descriptor_size,
+ u32 descriptor_version,
+ efi_memory_desc_t *virtual_map);
+#else
+static inline void efi_thunk_runtime_setup(void) {}
+static inline efi_status_t efi_thunk_set_virtual_address_map(
+ void *phys_set_virtual_address_map,
+ unsigned long memory_map_size,
+ unsigned long descriptor_size,
+ u32 descriptor_version,
+ efi_memory_desc_t *virtual_map)
+{
+ return EFI_SUCCESS;
+}
+#endif /* CONFIG_EFI_MIXED */
+#else
/*
* IF EFI is not configured, have the EFI calls return -ENOSYS.
*/
@@ -105,6 +167,7 @@ extern void efi_call_phys_epilog(void);
#define efi_call4(_f, _a1, _a2, _a3, _a4) (-ENOSYS)
#define efi_call5(_f, _a1, _a2, _a3, _a4, _a5) (-ENOSYS)
#define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6) (-ENOSYS)
+static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
#endif /* CONFIG_EFI */
#endif /* _ASM_X86_EFI_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index f2ad2163109..1a055c81d86 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -4,6 +4,7 @@
/*
* ELF register definitions..
*/
+#include <linux/thread_info.h>
#include <asm/ptrace.h>
#include <asm/user.h>
@@ -74,7 +75,12 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
#include <asm/vdso.h>
-extern unsigned int vdso_enabled;
+#ifdef CONFIG_X86_64
+extern unsigned int vdso64_enabled;
+#endif
+#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
+extern unsigned int vdso32_enabled;
+#endif
/*
* This is used to ensure we don't load something for the wrong architecture.
@@ -83,7 +89,6 @@ extern unsigned int vdso_enabled;
(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
#include <asm/processor.h>
-#include <asm/system.h>
#ifdef CONFIG_X86_32
#include <asm/desc.h>
@@ -155,7 +160,12 @@ do { \
#define elf_check_arch(x) \
((x)->e_machine == EM_X86_64)
-#define compat_elf_check_arch(x) elf_check_arch_ia32(x)
+#define compat_elf_check_arch(x) \
+ (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+
+#if __USER32_DS != __USER_DS
+# error "The following code assumes __USER32_DS == __USER_DS"
+#endif
static inline void elf_common_init(struct thread_struct *t,
struct pt_regs *regs, const u16 ds)
@@ -178,8 +188,9 @@ static inline void elf_common_init(struct thread_struct *t,
void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
#define compat_start_thread start_thread_ia32
-void set_personality_ia32(void);
-#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
+void set_personality_ia32(bool);
+#define COMPAT_SET_PERSONALITY(ex) \
+ set_personality_ia32((ex).e_machine == EM_X86_64)
#define COMPAT_ELF_PLATFORM ("i686")
@@ -263,9 +274,9 @@ extern int force_personality32;
struct task_struct;
-#define ARCH_DLINFO_IA32(vdso_enabled) \
+#define ARCH_DLINFO_IA32 \
do { \
- if (vdso_enabled) { \
+ if (vdso32_enabled) { \
NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \
NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \
} \
@@ -275,29 +286,37 @@ do { \
#define STACK_RND_MASK (0x7ff)
-#define VDSO_HIGH_BASE (__fix_to_virt(FIX_VDSO))
-
-#define ARCH_DLINFO ARCH_DLINFO_IA32(vdso_enabled)
+#define ARCH_DLINFO ARCH_DLINFO_IA32
/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
#else /* CONFIG_X86_32 */
-#define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */
-
/* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
#define ARCH_DLINFO \
do { \
- if (vdso_enabled) \
+ if (vdso64_enabled) \
NEW_AUX_ENT(AT_SYSINFO_EHDR, \
- (unsigned long)current->mm->context.vdso); \
+ (unsigned long __force)current->mm->context.vdso); \
+} while (0)
+
+/* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */
+#define ARCH_DLINFO_X32 \
+do { \
+ if (vdso64_enabled) \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, \
+ (unsigned long __force)current->mm->context.vdso); \
} while (0)
#define AT_SYSINFO 32
-#define COMPAT_ARCH_DLINFO ARCH_DLINFO_IA32(sysctl_vsyscall32)
+#define COMPAT_ARCH_DLINFO \
+if (test_thread_flag(TIF_X32)) \
+ ARCH_DLINFO_X32; \
+else \
+ ARCH_DLINFO_IA32
#define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000)
@@ -306,18 +325,47 @@ do { \
#define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso)
#define VDSO_ENTRY \
- ((unsigned long)VDSO32_SYMBOL(VDSO_CURRENT_BASE, vsyscall))
+ ((unsigned long)current->mm->context.vdso + \
+ selected_vdso32->sym___kernel_vsyscall)
struct linux_binprm;
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp);
-
-extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
-#define compat_arch_setup_additional_pages syscall32_setup_pages
+extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
+#define compat_arch_setup_additional_pages compat_arch_setup_additional_pages
extern unsigned long arch_randomize_brk(struct mm_struct *mm);
#define arch_randomize_brk arch_randomize_brk
+/*
+ * True on X86_32 or when emulating IA32 on X86_64
+ */
+static inline int mmap_is_ia32(void)
+{
+#ifdef CONFIG_X86_32
+ return 1;
+#endif
+#ifdef CONFIG_IA32_EMULATION
+ if (test_thread_flag(TIF_ADDR32))
+ return 1;
+#endif
+ return 0;
+}
+
+/* Do not change the values. See get_align_mask() */
+enum align_flags {
+ ALIGN_VA_32 = BIT(0),
+ ALIGN_VA_64 = BIT(1),
+};
+
+struct va_alignment {
+ int flags;
+ unsigned long mask;
+} ____cacheline_aligned;
+
+extern struct va_alignment va_align;
+extern unsigned long align_vdso_addr(unsigned long);
#endif /* _ASM_X86_ELF_H */
diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h
index cc70c1c78ca..77a99ac06d0 100644
--- a/arch/x86/include/asm/emergency-restart.h
+++ b/arch/x86/include/asm/emergency-restart.h
@@ -1,20 +1,6 @@
#ifndef _ASM_X86_EMERGENCY_RESTART_H
#define _ASM_X86_EMERGENCY_RESTART_H
-enum reboot_type {
- BOOT_TRIPLE = 't',
- BOOT_KBD = 'k',
-#ifdef CONFIG_X86_32
- BOOT_BIOS = 'b',
-#endif
- BOOT_ACPI = 'a',
- BOOT_EFI = 'e',
- BOOT_CF9 = 'p',
- BOOT_CF9_COND = 'q',
-};
-
-extern enum reboot_type reboot_type;
-
extern void machine_emergency_restart(void);
#endif /* _ASM_X86_EMERGENCY_RESTART_H */
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 8e8ec663a98..dc5fa661465 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -13,29 +13,18 @@
BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
-BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
-BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
-
-BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
- smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
- smp_invalidate_interrupt)
+BUILD_INTERRUPT3(irq_move_cleanup_interrupt, IRQ_MOVE_CLEANUP_VECTOR,
+ smp_irq_move_cleanup_interrupt)
+BUILD_INTERRUPT3(reboot_interrupt, REBOOT_VECTOR, smp_reboot_interrupt)
#endif
BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
+#ifdef CONFIG_HAVE_KVM
+BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR,
+ smp_kvm_posted_intr_ipi)
+#endif
+
/*
* every pentium local APIC has two 'local interrupts', with a
* soft-definable vector attached to both interrupts, one of
@@ -49,8 +38,8 @@ BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
-#ifdef CONFIG_PERF_EVENTS
-BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
+#ifdef CONFIG_IRQ_WORK
+BUILD_INTERRUPT(irq_work_interrupt, IRQ_WORK_VECTOR)
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
@@ -61,8 +50,4 @@ BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
#endif
-#ifdef CONFIG_X86_MCE
-BUILD_INTERRUPT(mce_self_interrupt,MCE_SELF_VECTOR)
-#endif
-
#endif
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
new file mode 100644
index 00000000000..99efebb2f69
--- /dev/null
+++ b/arch/x86/include/asm/espfix.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h
new file mode 100644
index 00000000000..54c2e1db274
--- /dev/null
+++ b/arch/x86/include/asm/exec.h
@@ -0,0 +1 @@
+/* define arch_align_stack() here */
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
index 53018464aea..2519d0679d9 100644
--- a/arch/x86/include/asm/fb.h
+++ b/arch/x86/include/asm/fb.h
@@ -12,10 +12,6 @@ static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
}
-#ifdef CONFIG_X86_32
extern int fb_is_primary_device(struct fb_info *info);
-#else
-static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
-#endif
#endif /* _ASM_X86_FB_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 14f9890eb49..b0910f97a3e 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -19,11 +19,12 @@
#include <asm/acpi.h>
#include <asm/apicdef.h>
#include <asm/page.h>
+#include <asm/pvclock.h>
#ifdef CONFIG_X86_32
#include <linux/threads.h>
#include <asm/kmap_types.h>
#else
-#include <asm/vsyscall.h>
+#include <uapi/asm/vsyscall.h>
#endif
/*
@@ -39,15 +40,9 @@
*/
extern unsigned long __FIXADDR_TOP;
#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP)
-
-#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1)
#else
-#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE)
-
-/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
-#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL)
-#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE)
+#define FIXADDR_TOP (round_up(VSYSCALL_ADDR + PAGE_SIZE, 1<<PMD_SHIFT) - \
+ PAGE_SIZE)
#endif
@@ -73,15 +68,18 @@ extern unsigned long __FIXADDR_TOP;
enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_HOLE,
- FIX_VDSO,
#else
- VSYSCALL_LAST_PAGE,
- VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
- + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
- VSYSCALL_HPET,
+ VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
+#ifdef CONFIG_PARAVIRT_CLOCK
+ PVCLOCK_FIXMAP_BEGIN,
+ PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
+#endif
#endif
FIX_DBGP_BASE,
FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+ FIX_OHCI1394_BASE,
+#endif
#ifdef CONFIG_X86_LOCAL_APIC
FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */
#endif
@@ -89,18 +87,7 @@ enum fixed_addresses {
FIX_IO_APIC_BASE_0,
FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
#endif
-#ifdef CONFIG_X86_VISWS_APIC
- FIX_CO_CPU, /* Cobalt timer */
- FIX_CO_APIC, /* Cobalt APIC Redirection Table */
- FIX_LI_PCIA, /* Lithium PCI Bridge A */
- FIX_LI_PCIB, /* Lithium PCI Bridge B */
-#endif
-#ifdef CONFIG_X86_F00F_BUG
- FIX_F00F_IDT, /* Virtual mapping for IDT */
-#endif
-#ifdef CONFIG_X86_CYCLONE_TIMER
- FIX_CYCLONE_TIMER, /*cyclone timer register*/
-#endif
+ FIX_RO_IDT, /* Virtual mapping for read-only IDT */
#ifdef CONFIG_X86_32
FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -113,22 +100,29 @@ enum fixed_addresses {
#endif
FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */
FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
+#ifdef CONFIG_X86_INTEL_MID
+ FIX_LNW_VRTC,
+#endif
__end_of_permanent_fixed_addresses,
+
/*
* 256 temporary boot-time mappings, used by early_ioremap(),
* before ioremap() is functional.
*
- * We round it up to the next 256 pages boundary so that we
- * can have a single pgd entry and a single pte table:
+ * If necessary we round it up to the next 256 pages boundary so
+ * that we can have a single pgd entry and a single pte table:
*/
#define NR_FIX_BTMAPS 64
#define FIX_BTMAPS_SLOTS 4
- FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
- (__end_of_permanent_fixed_addresses & 255),
- FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
- FIX_OHCI1394_BASE,
-#endif
+#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
+ FIX_BTMAP_END =
+ (__end_of_permanent_fixed_addresses ^
+ (__end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS - 1)) &
+ -PTRS_PER_PTE
+ ? __end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS -
+ (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1))
+ : __end_of_permanent_fixed_addresses,
+ FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1,
#ifdef CONFIG_X86_32
FIX_WP_TEST,
#endif
@@ -164,49 +158,13 @@ static inline void __set_fixmap(enum fixed_addresses idx,
}
#endif
-#define set_fixmap(idx, phys) \
- __set_fixmap(idx, phys, PAGE_KERNEL)
+#include <asm-generic/fixmap.h>
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys) \
- __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-
-#define clear_fixmap(idx) \
- __set_fixmap(idx, 0, __pgprot(0))
-
-#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without translation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static __always_inline unsigned long fix_to_virt(const unsigned int idx)
-{
- /*
- * this branch gets completely eliminated after inlining,
- * except when someone tries to use fixaddr indices in an
- * illegal way. (such as mixing up address types or using
- * out-of-range indices).
- *
- * If it doesn't get removed, the linker will complain
- * loudly with a reasonably clear error message..
- */
- if (idx >= __end_of_fixed_addresses)
- __this_fixmap_does_not_exist();
+#define __late_set_fixmap(idx, phys, flags) __set_fixmap(idx, phys, flags)
+#define __late_clear_fixmap(idx) __set_fixmap(idx, 0, __pgprot(0))
- return __fix_to_virt(idx);
-}
+void __early_set_fixmap(enum fixed_addresses idx,
+ phys_addr_t phys, pgprot_t flags);
-static inline unsigned long virt_to_fix(const unsigned long vaddr)
-{
- BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
- return __virt_to_fix(vaddr);
-}
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h
index dbe82a5c5ea..1c7eefe3250 100644
--- a/arch/x86/include/asm/floppy.h
+++ b/arch/x86/include/asm/floppy.h
@@ -99,7 +99,7 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id)
virtual_dma_residue += virtual_dma_count;
virtual_dma_count = 0;
#ifdef TRACE_FLPY_INT
- printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+ printk(KERN_DEBUG "count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
virtual_dma_count, virtual_dma_residue, calls, bytes,
dma_wait);
calls = 0;
@@ -145,10 +145,10 @@ static int fd_request_irq(void)
{
if (can_use_virtual_dma)
return request_irq(FLOPPY_IRQ, floppy_hardint,
- IRQF_DISABLED, "floppy", NULL);
+ 0, "floppy", NULL);
else
return request_irq(FLOPPY_IRQ, floppy_interrupt,
- IRQF_DISABLED, "floppy", NULL);
+ 0, "floppy", NULL);
}
static unsigned long dma_mem_alloc(unsigned long size)
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
new file mode 100644
index 00000000000..115e3689cd5
--- /dev/null
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -0,0 +1,619 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ * Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _FPU_INTERNAL_H
+#define _FPU_INTERNAL_H
+
+#include <linux/kernel_stat.h>
+#include <linux/regset.h>
+#include <linux/compat.h>
+#include <linux/slab.h>
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/uaccess.h>
+#include <asm/xsave.h>
+#include <asm/smap.h>
+
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+struct ksignal;
+int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct ksignal *ksig,
+ compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct user_i387_struct
+# define user32_fxsr_struct user_fxsr_struct
+# define ia32_setup_frame __setup_frame
+# define ia32_setup_rt_frame __setup_rt_frame
+#endif
+
+extern unsigned int mxcsr_feature_mask;
+extern void fpu_init(void);
+extern void eager_fpu_init(void);
+
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env);
+
+extern user_regset_active_fn fpregs_active, xfpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+ xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+ xstateregs_set;
+
+/*
+ * xstateregs_active == fpregs_active. Please refer to the comment
+ * at the definition of fpregs_active.
+ */
+#define xstateregs_active fpregs_active
+
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
+static inline int is_ia32_compat_frame(void)
+{
+ return config_enabled(CONFIG_IA32_EMULATION) &&
+ test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+ return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+ return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
+#define X87_FSW_ES (1 << 7) /* Exception Summary */
+
+static __always_inline __pure bool use_eager_fpu(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_EAGER_FPU);
+}
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+ return static_cpu_has_safe(X86_FEATURE_FXSR);
+}
+
+static inline void fx_finit(struct i387_fxsave_struct *fx)
+{
+ memset(fx, 0, xstate_size);
+ fx->cwd = 0x37f;
+ fx->mxcsr = MXCSR_DEFAULT;
+}
+
+extern void __sanitize_i387_state(struct task_struct *);
+
+static inline void sanitize_i387_state(struct task_struct *tsk)
+{
+ if (!use_xsaveopt())
+ return;
+ __sanitize_i387_state(tsk);
+}
+
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile(ASM_STAC "\n" \
+ "1:" #insn "\n\t" \
+ "2: " ASM_CLAC "\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define check_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+static inline int fsave_user(struct i387_fsave_struct __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
+}
+
+static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
+
+ /* See comment in fpu_fxsave() below. */
+ return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
+}
+
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+ /* See comment in fpu_fxsave() below. */
+ return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
+}
+
+static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+
+ /* See comment in fpu_fxsave() below. */
+ return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
+}
+
+static inline int frstor_checking(struct i387_fsave_struct *fx)
+{
+ return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline int frstor_user(struct i387_fsave_struct __user *fx)
+{
+ return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
+
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+ if (config_enabled(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
+ else {
+ /* Using "rex64; fxsave %0" is broken because, if the memory
+ * operand uses any extended registers for addressing, a second
+ * REX prefix will be generated (to the assembler, rex64
+ * followed by semicolon is a separate instruction), and hence
+ * the 64-bitness is lost.
+ *
+ * Using "fxsaveq %0" would be the ideal choice, but is only
+ * supported starting with gas 2.16.
+ *
+ * Using, as a workaround, the properly prefixed form below
+ * isn't accepted by any binutils version so far released,
+ * complaining that the same type of prefix is used twice if
+ * an extended register is needed for addressing (fix submitted
+ * to mainline 2005-11-21).
+ *
+ * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
+ *
+ * This, however, we can work around by forcing the compiler to
+ * select an addressing mode that doesn't require extended
+ * registers.
+ */
+ asm volatile( "rex64/fxsave (%[fx])"
+ : "=m" (fpu->state->fxsave)
+ : [fx] "R" (&fpu->state->fxsave));
+ }
+}
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
+ */
+static inline int fpu_save_init(struct fpu *fpu)
+{
+ if (use_xsave()) {
+ fpu_xsave(fpu);
+
+ /*
+ * xsave header may indicate the init state of the FP.
+ */
+ if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+ return 1;
+ } else if (use_fxsr()) {
+ fpu_fxsave(fpu);
+ } else {
+ asm volatile("fnsave %[fx]; fwait"
+ : [fx] "=m" (fpu->state->fsave));
+ return 0;
+ }
+
+ /*
+ * If exceptions are pending, we need to clear them so
+ * that we don't randomly get exceptions later.
+ *
+ * FIXME! Is this perhaps only true for the old-style
+ * irq13 case? Maybe we could leave the x87 state
+ * intact otherwise?
+ */
+ if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
+ asm volatile("fnclex");
+ return 0;
+ }
+ return 1;
+}
+
+static inline int __save_init_fpu(struct task_struct *tsk)
+{
+ return fpu_save_init(&tsk->thread.fpu);
+}
+
+static inline int fpu_restore_checking(struct fpu *fpu)
+{
+ if (use_xsave())
+ return fpu_xrstor_checking(&fpu->state->xsave);
+ else if (use_fxsr())
+ return fxrstor_checking(&fpu->state->fxsave);
+ else
+ return frstor_checking(&fpu->state->fsave);
+}
+
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+ /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+ is pending. Clear the x87 state here by setting it to fixed
+ values. "m" is a random variable that should be in L1 */
+ if (unlikely(static_cpu_has_safe(X86_FEATURE_FXSAVE_LEAK))) {
+ asm volatile(
+ "fnclex\n\t"
+ "emms\n\t"
+ "fildl %P[addr]" /* set F?P to defined value */
+ : : [addr] "m" (tsk->thread.fpu.has_fpu));
+ }
+
+ return fpu_restore_checking(&tsk->thread.fpu);
+}
+
+/*
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
+ */
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+ return tsk->thread.fpu.has_fpu;
+}
+
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
+{
+ tsk->thread.fpu.has_fpu = 0;
+ this_cpu_write(fpu_owner_task, NULL);
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+ tsk->thread.fpu.has_fpu = 1;
+ this_cpu_write(fpu_owner_task, tsk);
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+ __thread_clear_has_fpu(tsk);
+ if (!use_eager_fpu())
+ stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+ if (!static_cpu_has_safe(X86_FEATURE_EAGER_FPU))
+ clts();
+ __thread_set_has_fpu(tsk);
+}
+
+static inline void __drop_fpu(struct task_struct *tsk)
+{
+ if (__thread_has_fpu(tsk)) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ __thread_fpu_end(tsk);
+ }
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+ /*
+ * Forget coprocessor state..
+ */
+ preempt_disable();
+ tsk->thread.fpu_counter = 0;
+ __drop_fpu(tsk);
+ clear_used_math();
+ preempt_enable();
+}
+
+static inline void drop_init_fpu(struct task_struct *tsk)
+{
+ if (!use_eager_fpu())
+ drop_fpu(tsk);
+ else {
+ if (use_xsave())
+ xrstor_state(init_xstate_buf, -1);
+ else
+ fxrstor_checking(&init_xstate_buf->i387);
+ }
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ * - switch_fpu_prepare() saves the old state and
+ * sets the new state of the CR0.TS bit. This is
+ * done within the context of the old process.
+ *
+ * - switch_fpu_finish() restores the new state as
+ * necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * Must be run with preemption disabled: this clears the fpu_owner_task,
+ * on this CPU.
+ *
+ * This will disable any lazy FPU state restore of the current FPU state,
+ * but if the current thread owns the FPU, it will still be saved by.
+ */
+static inline void __cpu_disable_lazy_restore(unsigned int cpu)
+{
+ per_cpu(fpu_owner_task, cpu) = NULL;
+}
+
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+ return new == this_cpu_read_stable(fpu_owner_task) &&
+ cpu == new->thread.fpu.last_cpu;
+}
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
+{
+ fpu_switch_t fpu;
+
+ /*
+ * If the task has used the math, pre-load the FPU on xsave processors
+ * or if the past 5 consecutive context-switches used math.
+ */
+ fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
+ new->thread.fpu_counter > 5);
+ if (__thread_has_fpu(old)) {
+ if (!__save_init_fpu(old))
+ cpu = ~0;
+ old->thread.fpu.last_cpu = cpu;
+ old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */
+
+ /* Don't change CR0.TS if we just switch! */
+ if (fpu.preload) {
+ new->thread.fpu_counter++;
+ __thread_set_has_fpu(new);
+ prefetch(new->thread.fpu.state);
+ } else if (!use_eager_fpu())
+ stts();
+ } else {
+ old->thread.fpu_counter = 0;
+ old->thread.fpu.last_cpu = ~0;
+ if (fpu.preload) {
+ new->thread.fpu_counter++;
+ if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
+ fpu.preload = 0;
+ else
+ prefetch(new->thread.fpu.state);
+ __thread_fpu_begin(new);
+ }
+ }
+ return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+ if (fpu.preload) {
+ if (unlikely(restore_fpu_checking(new)))
+ drop_init_fpu(new);
+ }
+}
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
+extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
+
+static inline int xstate_sigframe_size(void)
+{
+ return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
+{
+ void __user *buf_fx = buf;
+ int size = xstate_sigframe_size();
+
+ if (ia32_frame && use_fxsr()) {
+ buf_fx = buf + sizeof(struct i387_fsave_struct);
+ size += sizeof(struct i387_fsave_struct);
+ }
+
+ return __restore_xstate_sig(buf, buf_fx, size);
+}
+
+/*
+ * Need to be preemption-safe.
+ *
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * it. This function does not do any save/restore on their own.
+ */
+static inline void user_fpu_begin(void)
+{
+ preempt_disable();
+ if (!user_has_fpu())
+ __thread_fpu_begin(current);
+ preempt_enable();
+}
+
+static inline void __save_fpu(struct task_struct *tsk)
+{
+ if (use_xsave())
+ xsave_state(&tsk->thread.fpu.state->xsave, -1);
+ else
+ fpu_fxsave(&tsk->thread.fpu);
+}
+
+/*
+ * These disable preemption on their own and are safe
+ */
+static inline void save_init_fpu(struct task_struct *tsk)
+{
+ WARN_ON_ONCE(!__thread_has_fpu(tsk));
+
+ if (use_eager_fpu()) {
+ __save_fpu(tsk);
+ return;
+ }
+
+ preempt_disable();
+ __save_init_fpu(tsk);
+ __thread_fpu_end(tsk);
+ preempt_enable();
+}
+
+/*
+ * i387 state interaction
+ */
+static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
+{
+ if (cpu_has_fxsr) {
+ return tsk->thread.fpu.state->fxsave.cwd;
+ } else {
+ return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
+ }
+}
+
+static inline unsigned short get_fpu_swd(struct task_struct *tsk)
+{
+ if (cpu_has_fxsr) {
+ return tsk->thread.fpu.state->fxsave.swd;
+ } else {
+ return (unsigned short)tsk->thread.fpu.state->fsave.swd;
+ }
+}
+
+static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
+{
+ if (cpu_has_xmm) {
+ return tsk->thread.fpu.state->fxsave.mxcsr;
+ } else {
+ return MXCSR_DEFAULT;
+ }
+}
+
+static bool fpu_allocated(struct fpu *fpu)
+{
+ return fpu->state != NULL;
+}
+
+static inline int fpu_alloc(struct fpu *fpu)
+{
+ if (fpu_allocated(fpu))
+ return 0;
+ fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
+ if (!fpu->state)
+ return -ENOMEM;
+ WARN_ON((unsigned long)fpu->state & 15);
+ return 0;
+}
+
+static inline void fpu_free(struct fpu *fpu)
+{
+ if (fpu->state) {
+ kmem_cache_free(task_xstate_cachep, fpu->state);
+ fpu->state = NULL;
+ }
+}
+
+static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
+{
+ if (use_eager_fpu()) {
+ memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
+ __save_fpu(dst);
+ } else {
+ struct fpu *dfpu = &dst->thread.fpu;
+ struct fpu *sfpu = &src->thread.fpu;
+
+ unlazy_fpu(src);
+ memcpy(dfpu->state, sfpu->state, xstate_size);
+ }
+}
+
+static inline unsigned long
+alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
+ unsigned long *size)
+{
+ unsigned long frame_size = xstate_sigframe_size();
+
+ *buf_fx = sp = round_down(sp - frame_size, 64);
+ if (ia32_frame && use_fxsr()) {
+ frame_size += sizeof(struct i387_fsave_struct);
+ sp -= sizeof(struct i387_fsave_struct);
+ }
+
+ *size = frame_size;
+ return sp;
+}
+
+#endif
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index 06850a7194e..3b629f47eb6 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -1,5 +1,6 @@
#ifdef __ASSEMBLY__
+#include <asm/asm.h>
#include <asm/dwarf2.h>
/* The annotation hides the frame from the unwinder and makes it look
@@ -7,15 +8,13 @@
frame pointer later */
#ifdef CONFIG_FRAME_POINTER
.macro FRAME
- pushl %ebp
- CFI_ADJUST_CFA_OFFSET 4
- CFI_REL_OFFSET ebp,0
- movl %esp,%ebp
+ __ASM_SIZE(push,_cfi) %__ASM_REG(bp)
+ CFI_REL_OFFSET __ASM_REG(bp), 0
+ __ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp)
.endm
.macro ENDFRAME
- popl %ebp
- CFI_ADJUST_CFA_OFFSET -4
- CFI_RESTORE ebp
+ __ASM_SIZE(pop,_cfi) %__ASM_REG(bp)
+ CFI_RESTORE __ASM_REG(bp)
.endm
#else
.macro FRAME
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index db24c2278be..0525a8bdf65 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -3,46 +3,61 @@
#ifdef __ASSEMBLY__
- .macro MCOUNT_SAVE_FRAME
- /* taken from glibc */
- subq $0x38, %rsp
- movq %rax, (%rsp)
- movq %rcx, 8(%rsp)
- movq %rdx, 16(%rsp)
- movq %rsi, 24(%rsp)
- movq %rdi, 32(%rsp)
- movq %r8, 40(%rsp)
- movq %r9, 48(%rsp)
+ /* skip is set if the stack was already partially adjusted */
+ .macro MCOUNT_SAVE_FRAME skip=0
+ /*
+ * We add enough stack to save all regs.
+ */
+ subq $(SS+8-\skip), %rsp
+ movq %rax, RAX(%rsp)
+ movq %rcx, RCX(%rsp)
+ movq %rdx, RDX(%rsp)
+ movq %rsi, RSI(%rsp)
+ movq %rdi, RDI(%rsp)
+ movq %r8, R8(%rsp)
+ movq %r9, R9(%rsp)
+ /* Move RIP to its proper location */
+ movq SS+8(%rsp), %rdx
+ movq %rdx, RIP(%rsp)
.endm
- .macro MCOUNT_RESTORE_FRAME
- movq 48(%rsp), %r9
- movq 40(%rsp), %r8
- movq 32(%rsp), %rdi
- movq 24(%rsp), %rsi
- movq 16(%rsp), %rdx
- movq 8(%rsp), %rcx
- movq (%rsp), %rax
- addq $0x38, %rsp
+ .macro MCOUNT_RESTORE_FRAME skip=0
+ movq R9(%rsp), %r9
+ movq R8(%rsp), %r8
+ movq RDI(%rsp), %rdi
+ movq RSI(%rsp), %rsi
+ movq RDX(%rsp), %rdx
+ movq RCX(%rsp), %rcx
+ movq RAX(%rsp), %rax
+ addq $(SS+8-\skip), %rsp
.endm
#endif
#ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR ((long)(mcount))
+#ifdef CC_USING_FENTRY
+# define MCOUNT_ADDR ((long)(__fentry__))
+#else
+# define MCOUNT_ADDR ((long)(mcount))
+#endif
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#endif
+
#ifndef __ASSEMBLY__
extern void mcount(void);
+extern atomic_t modifying_ftrace_code;
+extern void __fentry__(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
/*
- * call mcount is "e8 <4 byte offset>"
- * The addr points to the 4 byte offset and the caller of this
- * function wants the pointer to e8. Simply subtract one.
+ * addr is the address of the mcount call instruction.
+ * recordmcount does the necessary offset calculation.
*/
- return addr - 1;
+ return addr;
}
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -51,8 +66,34 @@ struct dyn_arch_ftrace {
/* No extra data needed for x86 */
};
+int ftrace_int3_handler(struct pt_regs *regs);
+
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* __ASSEMBLY__ */
#endif /* CONFIG_FUNCTION_TRACER */
+
+#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
+
+#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
+#include <asm/compat.h>
+
+/*
+ * Because ia32 syscalls do not map to x86_64 syscall numbers
+ * this screws up the trace output when tracing a ia32 task.
+ * Instead of reporting bogus syscalls, just do not trace them.
+ *
+ * If the user realy wants these, then they should use the
+ * raw syscall tracepoints with filtering.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+ if (is_compat_task())
+ return true;
+ return false;
+}
+#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
+#endif /* !__ASSEMBLY__ && !COMPILE_OFFSETS */
+
#endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 1f11ce44e95..b4c1f545343 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,11 +9,13 @@
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/processor.h>
-#include <asm/system.h>
+#include <asm/smap.h>
#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
- asm volatile("1:\t" insn "\n" \
- "2:\t.section .fixup,\"ax\"\n" \
+ asm volatile("\t" ASM_STAC "\n" \
+ "1:\t" insn "\n" \
+ "2:\t" ASM_CLAC "\n" \
+ "\t.section .fixup,\"ax\"\n" \
"3:\tmov\t%3, %1\n" \
"\tjmp\t2b\n" \
"\t.previous\n" \
@@ -22,12 +24,14 @@
: "i" (-EFAULT), "0" (oparg), "1" (0))
#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \
- asm volatile("1:\tmovl %2, %0\n" \
+ asm volatile("\t" ASM_STAC "\n" \
+ "1:\tmovl %2, %0\n" \
"\tmovl\t%0, %3\n" \
"\t" insn "\n" \
"2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \
"\tjnz\t1b\n" \
- "3:\t.section .fixup,\"ax\"\n" \
+ "3:\t" ASM_CLAC "\n" \
+ "\t.section .fixup,\"ax\"\n" \
"4:\tmov\t%5, %1\n" \
"\tjmp\t3b\n" \
"\t.previous\n" \
@@ -37,7 +41,7 @@
"+m" (*uaddr), "=&r" (tem) \
: "r" (oparg), "i" (-EFAULT), "1" (0))
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
{
int op = (encoded_op >> 28) & 7;
int cmp = (encoded_op >> 24) & 15;
@@ -48,15 +52,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
oparg = 1 << oparg;
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+ if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
- /* Real i386 machines can only support FUTEX_OP_SET */
- if (op != FUTEX_OP_SET && boot_cpu_data.x86 == 3)
- return -ENOSYS;
-#endif
-
pagefault_disable();
switch (op) {
@@ -109,31 +107,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
return ret;
}
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
- int newval)
+static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+ u32 oldval, u32 newval)
{
-
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
- /* Real i386 machines have no cmpxchg instruction */
- if (boot_cpu_data.x86 == 3)
- return -ENOSYS;
-#endif
-
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
- return -EFAULT;
-
- asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
- "2:\t.section .fixup, \"ax\"\n"
- "3:\tmov %2, %0\n"
- "\tjmp 2b\n"
- "\t.previous\n"
- _ASM_EXTABLE(1b, 3b)
- : "=a" (oldval), "+m" (*uaddr)
- : "i" (-EFAULT), "r" (newval), "0" (oldval)
- : "memory"
- );
-
- return oldval;
+ return user_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval);
}
#endif
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 4ac5b0f33fc..156cd5d18d2 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -17,6 +17,7 @@ extern int fix_aperture;
#define GARTEN (1<<0)
#define DISGARTCPU (1<<4)
#define DISGARTIO (1<<5)
+#define DISTLBWALKPRB (1<<6)
/* GART cache control register bits. */
#define INVGART (1<<0)
@@ -27,7 +28,6 @@ extern int fix_aperture;
#define AMD64_GARTAPERTUREBASE 0x94
#define AMD64_GARTTABLEBASE 0x98
#define AMD64_GARTCACHECTL 0x9c
-#define AMD64_GARTEN (1<<0)
#ifdef CONFIG_GART_IOMMU
extern int gart_iommu_aperture;
@@ -37,7 +37,7 @@ extern int gart_iommu_aperture_disabled;
extern void early_gart_iommu_check(void);
extern int gart_iommu_init(void);
extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
+extern int gart_iommu_hole_init(void);
#else
#define gart_iommu_aperture 0
@@ -50,28 +50,42 @@ static inline void early_gart_iommu_check(void)
static inline void gart_parse_options(char *options)
{
}
-static inline void gart_iommu_hole_init(void)
+static inline int gart_iommu_hole_init(void)
{
+ return -ENODEV;
}
#endif
extern int agp_amd64_init(void);
+static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
+{
+ u32 ctl;
+
+ /*
+ * Don't enable translation but enable GART IO and CPU accesses.
+ * Also, set DISTLBWALKPRB since GART tables memory is UC.
+ */
+ ctl = order << 1;
+
+ pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+}
+
static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
{
u32 tmp, ctl;
- /* address of the mappings table */
- addr >>= 12;
- tmp = (u32) addr<<4;
- tmp &= ~0xf;
- pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
-
- /* Enable GART translation for this hammer. */
- pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
- ctl |= GARTEN;
- ctl &= ~(DISGARTCPU | DISGARTIO);
- pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+ /* address of the mappings table */
+ addr >>= 12;
+ tmp = (u32) addr<<4;
+ tmp &= ~0xf;
+ pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+ /* Enable GART translation for this hammer. */
+ pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+ ctl |= GARTEN | DISTLBWALKPRB;
+ ctl &= ~(DISGARTCPU | DISGARTIO);
+ pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
}
static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
diff --git a/arch/x86/include/asm/gpio.h b/arch/x86/include/asm/gpio.h
index 49dbfdfa50f..b3799d88ffc 100644
--- a/arch/x86/include/asm/gpio.h
+++ b/arch/x86/include/asm/gpio.h
@@ -1,56 +1,4 @@
-/*
- * Generic GPIO API implementation for x86.
- *
- * Derived from the generic GPIO API for powerpc:
- *
- * Copyright (c) 2007-2008 MontaVista Software, Inc.
- *
- * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef _ASM_X86_GPIO_H
-#define _ASM_X86_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#ifdef CONFIG_GPIOLIB
-
-/*
- * Just call gpiolib.
- */
-static inline int gpio_get_value(unsigned int gpio)
-{
- return __gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned int gpio, int value)
-{
- __gpio_set_value(gpio, value);
-}
-
-static inline int gpio_cansleep(unsigned int gpio)
-{
- return __gpio_cansleep(gpio);
-}
-
-/*
- * Not implemented, yet.
- */
-static inline int gpio_to_irq(unsigned int gpio)
-{
- return -ENOSYS;
-}
-
-static inline int irq_to_gpio(unsigned int irq)
-{
- return -EINVAL;
-}
-
-#endif /* CONFIG_GPIOLIB */
-
-#endif /* _ASM_X86_GPIO_H */
+#ifndef __LINUX_GPIO_H
+#warning Include linux/gpio.h instead of asm/gpio.h
+#include <linux/gpio.h>
+#endif
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0f8576427cf..230853da4ec 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -7,17 +7,24 @@
typedef struct {
unsigned int __softirq_pending;
unsigned int __nmi_count; /* arch dependent */
- unsigned int irq0_irqs;
#ifdef CONFIG_X86_LOCAL_APIC
unsigned int apic_timer_irqs; /* arch dependent */
unsigned int irq_spurious_count;
+ unsigned int icr_read_retry_count;
+#endif
+#ifdef CONFIG_HAVE_KVM
+ unsigned int kvm_posted_intr_ipis;
#endif
unsigned int x86_platform_ipis; /* arch dependent */
unsigned int apic_perf_irqs;
- unsigned int apic_pending_irqs;
+ unsigned int apic_irq_work_irqs;
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
+ /*
+ * irq_tlb_count is double-counted in irq_call_count, so it must be
+ * subtracted from irq_call_count when displaying irq_call_count
+ */
unsigned int irq_tlb_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
@@ -26,6 +33,9 @@ typedef struct {
#ifdef CONFIG_X86_MCE_THRESHOLD
unsigned int irq_threshold_count;
#endif
+#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
+ unsigned int irq_hv_callback_count;
+#endif
} ____cacheline_aligned irq_cpustat_t;
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
@@ -35,14 +45,15 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
#define __ARCH_IRQ_STAT
-#define inc_irq_stat(member) percpu_add(irq_stat.member, 1)
+#define inc_irq_stat(member) this_cpu_inc(irq_stat.member)
-#define local_softirq_pending() percpu_read(irq_stat.__softirq_pending)
+#define local_softirq_pending() this_cpu_read(irq_stat.__softirq_pending)
#define __ARCH_SET_SOFTIRQ_PENDING
-#define set_softirq_pending(x) percpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x) percpu_or(irq_stat.__softirq_pending, (x))
+#define set_softirq_pending(x) \
+ this_cpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x) this_cpu_or(irq_stat.__softirq_pending, (x))
extern void ack_bad_irq(unsigned int irq);
diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h
new file mode 100644
index 00000000000..e8c58f88b1d
--- /dev/null
+++ b/arch/x86/include/asm/hash.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_HASH_H
+#define _ASM_X86_HASH_H
+
+struct fast_hash_ops;
+extern void setup_arch_fast_hash(struct fast_hash_ops *ops);
+
+#endif /* _ASM_X86_HASH_H */
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 014c2b85ae4..302a323b3f6 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -59,16 +59,13 @@ extern void kunmap_high(struct page *page);
void *kmap(struct page *page);
void kunmap(struct page *page);
-void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
-void *kmap_atomic(struct page *page, enum km_type type);
-void kunmap_atomic(void *kvaddr, enum km_type type);
-void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
-void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
-struct page *kmap_atomic_to_page(void *ptr);
-#ifndef CONFIG_PARAVIRT
-#define kmap_atomic_pte(page, type) kmap_atomic(page, type)
-#endif
+void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+void *kmap_atomic(struct page *page);
+void __kunmap_atomic(void *kvaddr);
+void *kmap_atomic_pfn(unsigned long pfn);
+void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
+struct page *kmap_atomic_to_page(void *ptr);
#define flush_cache_kmaps() do { } while (0)
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 1d5c08a1bdf..36f7125945e 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -35,8 +35,6 @@
#define HPET_ID_NUMBER_SHIFT 8
#define HPET_ID_VENDOR_SHIFT 16
-#define HPET_ID_VENDOR_8086 0x8086
-
#define HPET_CFG_ENABLE 0x001
#define HPET_CFG_LEGACY 0x002
#define HPET_LEGACY_8254 2
@@ -65,6 +63,7 @@
/* hpet memory map physical address */
extern unsigned long hpet_address;
extern unsigned long force_hpet_address;
+extern int boot_hpet_disable;
extern u8 hpet_blockid;
extern int hpet_force_user;
extern u8 hpet_msi_disable;
@@ -74,15 +73,17 @@ extern void hpet_disable(void);
extern unsigned int hpet_readl(unsigned int a);
extern void force_hpet_resume(void);
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+struct irq_data;
+extern void hpet_msi_unmask(struct irq_data *data);
+extern void hpet_msi_mask(struct irq_data *data);
+struct hpet_dev;
+extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
#ifdef CONFIG_PCI_MSI
-extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);
+extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
#else
-static inline int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
+static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id)
{
return -EINVAL;
}
@@ -111,6 +112,7 @@ extern void hpet_unregister_irq_handler(rtc_irq_handler handler);
static inline int hpet_enable(void) { return 0; }
static inline int is_hpet_enabled(void) { return 0; }
#define hpet_readl(a) 0
+#define default_setup_hpet_msi NULL
#endif
#endif /* _ASM_X86_HPET_H */
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 439a9acc132..68c05398bba 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -2,6 +2,7 @@
#define _ASM_X86_HUGETLB_H
#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
static inline int is_hugepage_only_range(struct mm_struct *mm,
@@ -51,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
+ ptep_clear_flush(vma, addr, ptep);
}
static inline int huge_pte_none(pte_t pte)
@@ -90,4 +92,8 @@ static inline void arch_release_hugepage(struct page *page)
{
}
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+}
+
#endif /* _ASM_X86_HUGETLB_H */
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 0675a7c4c20..ef1c4d2d41e 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -1,7 +1,8 @@
#ifndef _I386_HW_BREAKPOINT_H
#define _I386_HW_BREAKPOINT_H
-#ifdef __KERNEL__
+#include <uapi/asm/hw_breakpoint.h>
+
#define __ARCH_HW_BREAKPOINT_H
/*
@@ -10,7 +11,6 @@
* (display/resolving)
*/
struct arch_hw_breakpoint {
- char *name; /* Contains name of the symbol to set bkpt */
unsigned long address;
u8 len;
u8 type;
@@ -21,10 +21,10 @@ struct arch_hw_breakpoint {
#include <linux/list.h>
/* Available HW breakpoint length encodings */
+#define X86_BREAKPOINT_LEN_X 0x40
#define X86_BREAKPOINT_LEN_1 0x40
#define X86_BREAKPOINT_LEN_2 0x44
#define X86_BREAKPOINT_LEN_4 0x4c
-#define X86_BREAKPOINT_LEN_EXECUTE 0x40
#ifdef CONFIG_X86_64
#define X86_BREAKPOINT_LEN_8 0x48
@@ -42,12 +42,16 @@ struct arch_hw_breakpoint {
/* Total number of available HW breakpoint registers */
#define HBP_NUM 4
+static inline int hw_breakpoint_slots(int type)
+{
+ return HBP_NUM;
+}
+
struct perf_event;
struct pmu;
-extern int arch_check_va_in_userspace(unsigned long va, u8 hbp_len);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp,
- struct task_struct *tsk);
+extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
unsigned long val, void *data);
@@ -68,6 +72,4 @@ extern int arch_bp_generic_fields(int x86_len, int x86_type,
extern struct pmu perf_ops_bp;
-#endif /* __KERNEL__ */
#endif /* _I386_HW_BREAKPOINT_H */
-
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index eeac829a0f4..4615906d83d 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -21,50 +21,83 @@
#include <linux/profile.h>
#include <linux/smp.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/irq.h>
#include <asm/sections.h>
/* Interrupt handlers registered during init_IRQ */
-extern void apic_timer_interrupt(void);
-extern void x86_platform_ipi(void);
-extern void error_interrupt(void);
-extern void perf_pending_interrupt(void);
-
-extern void spurious_interrupt(void);
-extern void thermal_interrupt(void);
-extern void reschedule_interrupt(void);
-extern void mce_self_interrupt(void);
-
-extern void invalidate_interrupt(void);
-extern void invalidate_interrupt0(void);
-extern void invalidate_interrupt1(void);
-extern void invalidate_interrupt2(void);
-extern void invalidate_interrupt3(void);
-extern void invalidate_interrupt4(void);
-extern void invalidate_interrupt5(void);
-extern void invalidate_interrupt6(void);
-extern void invalidate_interrupt7(void);
-
-extern void irq_move_cleanup_interrupt(void);
-extern void reboot_interrupt(void);
-extern void threshold_interrupt(void);
-
-extern void call_function_interrupt(void);
-extern void call_function_single_interrupt(void);
-
-/* PIC specific functions */
-extern void disable_8259A_irq(unsigned int irq);
-extern void enable_8259A_irq(unsigned int irq);
-extern int i8259A_irq_pending(unsigned int irq);
-extern void make_8259A_irq(unsigned int irq);
-extern void init_8259A(int aeoi);
+extern asmlinkage void apic_timer_interrupt(void);
+extern asmlinkage void x86_platform_ipi(void);
+extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void error_interrupt(void);
+extern asmlinkage void irq_work_interrupt(void);
+
+extern asmlinkage void spurious_interrupt(void);
+extern asmlinkage void thermal_interrupt(void);
+extern asmlinkage void reschedule_interrupt(void);
+
+extern asmlinkage void invalidate_interrupt(void);
+extern asmlinkage void invalidate_interrupt0(void);
+extern asmlinkage void invalidate_interrupt1(void);
+extern asmlinkage void invalidate_interrupt2(void);
+extern asmlinkage void invalidate_interrupt3(void);
+extern asmlinkage void invalidate_interrupt4(void);
+extern asmlinkage void invalidate_interrupt5(void);
+extern asmlinkage void invalidate_interrupt6(void);
+extern asmlinkage void invalidate_interrupt7(void);
+extern asmlinkage void invalidate_interrupt8(void);
+extern asmlinkage void invalidate_interrupt9(void);
+extern asmlinkage void invalidate_interrupt10(void);
+extern asmlinkage void invalidate_interrupt11(void);
+extern asmlinkage void invalidate_interrupt12(void);
+extern asmlinkage void invalidate_interrupt13(void);
+extern asmlinkage void invalidate_interrupt14(void);
+extern asmlinkage void invalidate_interrupt15(void);
+extern asmlinkage void invalidate_interrupt16(void);
+extern asmlinkage void invalidate_interrupt17(void);
+extern asmlinkage void invalidate_interrupt18(void);
+extern asmlinkage void invalidate_interrupt19(void);
+extern asmlinkage void invalidate_interrupt20(void);
+extern asmlinkage void invalidate_interrupt21(void);
+extern asmlinkage void invalidate_interrupt22(void);
+extern asmlinkage void invalidate_interrupt23(void);
+extern asmlinkage void invalidate_interrupt24(void);
+extern asmlinkage void invalidate_interrupt25(void);
+extern asmlinkage void invalidate_interrupt26(void);
+extern asmlinkage void invalidate_interrupt27(void);
+extern asmlinkage void invalidate_interrupt28(void);
+extern asmlinkage void invalidate_interrupt29(void);
+extern asmlinkage void invalidate_interrupt30(void);
+extern asmlinkage void invalidate_interrupt31(void);
+
+extern asmlinkage void irq_move_cleanup_interrupt(void);
+extern asmlinkage void reboot_interrupt(void);
+extern asmlinkage void threshold_interrupt(void);
+
+extern asmlinkage void call_function_interrupt(void);
+extern asmlinkage void call_function_single_interrupt(void);
+
+#ifdef CONFIG_TRACING
+/* Interrupt handlers registered during init_IRQ */
+extern void trace_apic_timer_interrupt(void);
+extern void trace_x86_platform_ipi(void);
+extern void trace_error_interrupt(void);
+extern void trace_irq_work_interrupt(void);
+extern void trace_spurious_interrupt(void);
+extern void trace_thermal_interrupt(void);
+extern void trace_reschedule_interrupt(void);
+extern void trace_threshold_interrupt(void);
+extern void trace_call_function_interrupt(void);
+extern void trace_call_function_single_interrupt(void);
+#define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt
+#define trace_reboot_interrupt reboot_interrupt
+#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
+#endif /* CONFIG_TRACING */
/* IOAPIC */
#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
extern unsigned long io_apic_irqs;
-extern void init_VISWS_APIC_irqs(void);
extern void setup_IO_APIC(void);
extern void disable_IO_APIC(void);
@@ -85,6 +118,20 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
irq_attr->polarity = polarity;
}
+/* Intel specific interrupt remapping information */
+struct irq_2_iommu {
+ struct intel_iommu *iommu;
+ u16 irte_index;
+ u16 sub_handle;
+ u8 irte_mask;
+};
+
+/* AMD specific interrupt remapping information */
+struct irq_2_irte {
+ u16 devid; /* Device ID for IRTE table */
+ u16 index; /* Index into IRTE table*/
+};
+
/*
* This is performance-critical, we want to do it O(1)
*
@@ -96,15 +143,21 @@ struct irq_cfg {
cpumask_var_t old_domain;
u8 vector;
u8 move_in_progress : 1;
+#ifdef CONFIG_IRQ_REMAP
+ u8 remapped : 1;
+ union {
+ struct irq_2_iommu irq_2_iommu;
+ struct irq_2_irte irq_2_irte;
+ };
+#endif
};
-extern struct irq_cfg *irq_cfg(unsigned int);
extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
extern void send_cleanup_vector(struct irq_cfg *);
-struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
- unsigned int *dest_id);
+struct irq_data;
+int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
+ unsigned int *dest_id);
extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
extern void setup_ioapic_dest(void);
@@ -118,28 +171,31 @@ extern atomic_t irq_mis_count;
extern void eisa_set_level_irq(unsigned int irq);
/* SMP */
-extern void smp_apic_timer_interrupt(struct pt_regs *);
-extern void smp_spurious_interrupt(struct pt_regs *);
-extern void smp_x86_platform_ipi(struct pt_regs *);
-extern void smp_error_interrupt(struct pt_regs *);
+extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
+extern __visible void smp_spurious_interrupt(struct pt_regs *);
+extern __visible void smp_x86_platform_ipi(struct pt_regs *);
+extern __visible void smp_error_interrupt(struct pt_regs *);
#ifdef CONFIG_X86_IO_APIC
extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
#endif
#ifdef CONFIG_SMP
-extern void smp_reschedule_interrupt(struct pt_regs *);
-extern void smp_call_function_interrupt(struct pt_regs *);
-extern void smp_call_function_single_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_32
-extern void smp_invalidate_interrupt(struct pt_regs *);
-#else
-extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
-#endif
+extern __visible void smp_reschedule_interrupt(struct pt_regs *);
+extern __visible void smp_call_function_interrupt(struct pt_regs *);
+extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
+extern __visible void smp_invalidate_interrupt(struct pt_regs *);
#endif
extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
+#ifdef CONFIG_TRACING
+#define trace_interrupt interrupt
+#endif
+
+#define VECTOR_UNDEFINED (-1)
+#define VECTOR_RETRIGGERED (-2)
typedef int vector_irq_t[NR_VECTORS];
DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern void setup_vector_irq(int cpu);
#ifdef CONFIG_X86_IO_APIC
extern void lock_vector_lock(void);
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index b78c0941e42..e42f758a0fb 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -17,10 +17,48 @@
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
*/
-#ifndef ASM_X86__HYPERVISOR_H
-#define ASM_X86__HYPERVISOR_H
+#ifndef _ASM_X86_HYPERVISOR_H
+#define _ASM_X86_HYPERVISOR_H
+
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/xen/hypervisor.h>
+
+/*
+ * x86 hypervisor information
+ */
+struct hypervisor_x86 {
+ /* Hypervisor name */
+ const char *name;
+
+ /* Detection routine */
+ uint32_t (*detect)(void);
+
+ /* Adjust CPU feature bits (run once per CPU) */
+ void (*set_cpu_features)(struct cpuinfo_x86 *);
+
+ /* Platform setup (run once per boot) */
+ void (*init_platform)(void);
+
+ /* X2APIC detection (run once per boot) */
+ bool (*x2apic_available)(void);
+};
+
+extern const struct hypervisor_x86 *x86_hyper;
+
+/* Recognized hypervisors */
+extern const struct hypervisor_x86 x86_hyper_vmware;
+extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
+extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+extern const struct hypervisor_x86 x86_hyper_kvm;
extern void init_hypervisor(struct cpuinfo_x86 *c);
extern void init_hypervisor_platform(void);
-
-#endif
+extern bool hypervisor_x2apic_available(void);
+#else
+static inline void init_hypervisor(struct cpuinfo_x86 *c) { }
+static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_x2apic_available(void) { return false; }
+#endif /* CONFIG_HYPERVISOR_GUEST */
+#endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h