summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/.gitignore1
-rw-r--r--arch/x86/Kconfig67
-rw-r--r--arch/x86/Kconfig.cpu6
-rw-r--r--arch/x86/Kconfig.debug25
-rw-r--r--arch/x86/Makefile6
-rw-r--r--arch/x86/boot/compressed/Makefile10
-rw-r--r--arch/x86/boot/compressed/eboot.c1022
-rw-r--r--arch/x86/boot/compressed/eboot.h61
-rw-r--r--arch/x86/boot/compressed/efi_stub_32.S86
-rw-r--r--arch/x86/boot/compressed/efi_stub_64.S1
-rw-r--r--arch/x86/boot/compressed/head_32.S22
-rw-r--r--arch/x86/boot/compressed/head_64.S20
-rw-r--r--arch/x86/boot/compressed/misc.c2
-rw-r--r--arch/x86/boot/compressed/string.c9
-rw-r--r--arch/x86/boot/header.S158
-rw-r--r--arch/x86/boot/string.c35
-rw-r--r--arch/x86/boot/tools/build.c39
-rw-r--r--arch/x86/crypto/Makefile4
-rw-r--r--arch/x86/crypto/serpent-sse2-i586-asm_32.S638
-rw-r--r--arch/x86/crypto/serpent-sse2-x86_64-asm_64.S761
-rw-r--r--arch/x86/crypto/serpent_sse2_glue.c1070
-rw-r--r--arch/x86/crypto/twofish_glue_3way.c218
-rw-r--r--arch/x86/ia32/Makefile1
-rw-r--r--arch/x86/ia32/ia32entry.S373
-rw-r--r--arch/x86/ia32/nosyscall.c7
-rw-r--r--arch/x86/ia32/syscall_ia32.c25
-rw-r--r--arch/x86/include/asm/Kbuild5
-rw-r--r--arch/x86/include/asm/amd_nb.h2
-rw-r--r--arch/x86/include/asm/atomic64_32.h2
-rw-r--r--arch/x86/include/asm/bootparam.h2
-rw-r--r--arch/x86/include/asm/cmpxchg.h6
-rw-r--r--arch/x86/include/asm/cpufeature.h1
-rw-r--r--arch/x86/include/asm/debugreg.h22
-rw-r--r--arch/x86/include/asm/desc.h12
-rw-r--r--arch/x86/include/asm/efi.h4
-rw-r--r--arch/x86/include/asm/fixmap.h2
-rw-r--r--arch/x86/include/asm/ia32_unistd.h13
-rw-r--r--arch/x86/include/asm/init.h2
-rw-r--r--arch/x86/include/asm/iommu.h1
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/pci.h9
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/serpent.h63
-rw-r--r--arch/x86/include/asm/setup.h2
-rw-r--r--arch/x86/include/asm/smp.h6
-rw-r--r--arch/x86/include/asm/syscall.h1
-rw-r--r--arch/x86/include/asm/thread_info.h4
-rw-r--r--arch/x86/include/asm/topology.h2
-rw-r--r--arch/x86/include/asm/unistd.h55
-rw-r--r--arch/x86/include/asm/unistd_32.h401
-rw-r--r--arch/x86/include/asm/unistd_64.h732
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h107
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h4
-rw-r--r--arch/x86/include/asm/x86_init.h1
-rw-r--r--arch/x86/kernel/Makefile4
-rw-r--r--arch/x86/kernel/amd_nb.c31
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c7
-rw-r--r--arch/x86/kernel/apm_32.c16
-rw-r--r--arch/x86/kernel/asm-offsets.c2
-rw-r--r--arch/x86/kernel/asm-offsets_32.c8
-rw-r--r--arch/x86/kernel/asm-offsets_64.c19
-rw-r--r--arch/x86/kernel/cpu/common.c24
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c18
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c18
-rw-r--r--arch/x86/kernel/dumpstack.c3
-rw-r--r--arch/x86/kernel/dumpstack_64.c8
-rw-r--r--arch/x86/kernel/e820.c63
-rw-r--r--arch/x86/kernel/early_printk.c2
-rw-r--r--arch/x86/kernel/entry_32.S47
-rw-r--r--arch/x86/kernel/entry_64.S232
-rw-r--r--arch/x86/kernel/head_64.S4
-rw-r--r--arch/x86/kernel/irq_32.c5
-rw-r--r--arch/x86/kernel/irq_64.c35
-rw-r--r--arch/x86/kernel/microcode_amd.c24
-rw-r--r--arch/x86/kernel/nmi.c102
-rw-r--r--arch/x86/kernel/nmi_selftest.c180
-rw-r--r--arch/x86/kernel/pci-dma.c11
-rw-r--r--arch/x86/kernel/ptrace.c25
-rw-r--r--arch/x86/kernel/reboot.c36
-rw-r--r--arch/x86/kernel/setup.c7
-rw-r--r--arch/x86/kernel/signal.c6
-rw-r--r--arch/x86/kernel/smp.c72
-rw-r--r--arch/x86/kernel/smpboot.c17
-rw-r--r--arch/x86/kernel/syscall_32.c25
-rw-r--r--arch/x86/kernel/syscall_64.c20
-rw-r--r--arch/x86/kernel/syscall_table_32.S350
-rw-r--r--arch/x86/kernel/traps.c20
-rw-r--r--arch/x86/kernel/tsc.c34
-rw-r--r--arch/x86/kernel/vm86_32.c6
-rw-r--r--arch/x86/kernel/x86_init.c1
-rw-r--r--arch/x86/kvm/mmu.c2
-rw-r--r--arch/x86/kvm/vmx.c18
-rw-r--r--arch/x86/kvm/x86.c4
-rw-r--r--arch/x86/lguest/boot.c21
-rw-r--r--arch/x86/lib/x86-opcode-map.txt8
-rw-r--r--arch/x86/mm/fault.c4
-rw-r--r--arch/x86/mm/init.c23
-rw-r--r--arch/x86/mm/init_32.c29
-rw-r--r--arch/x86/mm/init_64.c11
-rw-r--r--arch/x86/mm/mmap.c4
-rw-r--r--arch/x86/mm/mmio-mod.c4
-rw-r--r--arch/x86/mm/numa.c12
-rw-r--r--arch/x86/mm/pageattr.c6
-rw-r--r--arch/x86/mm/srat.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c36
-rw-r--r--arch/x86/pci/Makefile5
-rw-r--r--arch/x86/pci/acpi.c75
-rw-r--r--arch/x86/pci/amd_bus.c43
-rw-r--r--arch/x86/pci/broadcom_bus.c62
-rw-r--r--arch/x86/pci/bus_numa.c31
-rw-r--r--arch/x86/pci/common.c19
-rw-r--r--arch/x86/pci/i386.c20
-rw-r--r--arch/x86/pci/legacy.c3
-rw-r--r--arch/x86/pci/numaq_32.c2
-rw-r--r--arch/x86/platform/geode/alix.c2
-rw-r--r--arch/x86/platform/iris/iris.c2
-rw-r--r--arch/x86/platform/mrst/Makefile6
-rw-r--r--arch/x86/platform/mrst/mrst.c4
-rw-r--r--arch/x86/platform/uv/tlb_uv.c390
-rw-r--r--arch/x86/platform/uv/uv_irq.c2
-rw-r--r--arch/x86/syscalls/Makefile43
-rw-r--r--arch/x86/syscalls/syscall_32.tbl357
-rw-r--r--arch/x86/syscalls/syscall_64.tbl320
-rw-r--r--arch/x86/syscalls/syscallhdr.sh27
-rw-r--r--arch/x86/syscalls/syscalltbl.sh15
-rw-r--r--arch/x86/um/Kconfig8
-rw-r--r--arch/x86/um/Makefile3
-rw-r--r--arch/x86/um/shared/sysdep/ptrace.h10
-rw-r--r--arch/x86/um/sys_call_table_32.S26
-rw-r--r--arch/x86/um/sys_call_table_32.c55
-rw-r--r--arch/x86/um/sys_call_table_64.c33
-rw-r--r--arch/x86/um/user-offsets.c15
-rw-r--r--arch/x86/xen/spinlock.c27
133 files changed, 6938 insertions, 2467 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
index 028079065af6..7cab8c08e6d1 100644
--- a/arch/x86/.gitignore
+++ b/arch/x86/.gitignore
@@ -1,3 +1,4 @@
boot/compressed/vmlinux
tools/test_get_len
+tools/insn_sanity
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d2a69dd36d8..5bed94e189fa 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -60,8 +60,12 @@ config X86
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
select ANON_INODES
+ select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
+ select HAVE_CMPXCHG_LOCAL if !M386
+ select HAVE_CMPXCHG_DOUBLE
select HAVE_ARCH_KMEMCHECK
select HAVE_USER_RETURN_NOTIFIER
+ select ARCH_BINFMT_ELF_RANDOMIZE_PIE
select HAVE_ARCH_JUMP_LABEL
select HAVE_TEXT_POKE_SMP
select HAVE_GENERIC_HARDIRQS
@@ -77,6 +81,7 @@ config X86
select HAVE_BPF_JIT if (X86_64 && NET)
select CLKEVT_I8253
select ARCH_HAVE_NMI_SAFE_CMPXCHG
+ select GENERIC_IOMAP
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
@@ -120,16 +125,6 @@ config HAVE_LATENCYTOP_SUPPORT
config MMU
def_bool y
-config ZONE_DMA
- bool "DMA memory allocation support" if EXPERT
- default y
- help
- DMA memory allocation support allows devices with less than 32-bit
- addressing to allocate within the first 16MB of address space.
- Disable if no such devices will be used.
-
- If unsure, say Y.
-
config SBUS
bool
@@ -142,9 +137,6 @@ config NEED_SG_DMA_LENGTH
config GENERIC_ISA_DMA
def_bool ISA_DMA_API
-config GENERIC_IOMAP
- def_bool y
-
config GENERIC_BUG
def_bool y
depends on BUG
@@ -253,6 +245,16 @@ source "kernel/Kconfig.freezer"
menu "Processor type and features"
+config ZONE_DMA
+ bool "DMA memory allocation support" if EXPERT
+ default y
+ help
+ DMA memory allocation support allows devices with less than 32-bit
+ addressing to allocate within the first 16MB of address space.
+ Disable if no such devices will be used.
+
+ If unsure, say Y.
+
source "kernel/time/Kconfig"
config SMP
@@ -358,7 +360,6 @@ config X86_NUMACHIP
depends on NUMA
depends on SMP
depends on X86_X2APIC
- depends on !EDAC_AMD64
---help---
Adds support for Numascale NumaChip large-SMP systems. Needed to
enable more than ~168 cores.
@@ -421,12 +422,14 @@ config X86_MRST
depends on PCI
depends on PCI_GOANY
depends on X86_IO_APIC
+ select X86_INTEL_MID
+ select SFI
+ select DW_APB_TIMER
select APB_TIMER
select I2C
select SPI
select INTEL_SCU_IPC
select X86_PLATFORM_DEVICES
- select X86_INTEL_MID
---help---
Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
Internet Device(MID) platform. Moorestown consists of two chips:
@@ -435,6 +438,26 @@ config X86_MRST
nor standard legacy replacement devices/features. e.g. Moorestown does
not contain i8259, i8254, HPET, legacy BIOS, most of the io ports.
+config X86_MDFLD
+ bool "Medfield MID platform"
+ depends on PCI
+ depends on PCI_GOANY
+ depends on X86_IO_APIC
+ select X86_INTEL_MID
+ select SFI
+ select DW_APB_TIMER
+ select APB_TIMER
+ select I2C
+ select SPI
+ select INTEL_SCU_IPC
+ select X86_PLATFORM_DEVICES
+ ---help---
+ Medfield is Intel's Low Power Intel Architecture (LPIA) based Moblin
+ Internet Device(MID) platform.
+ Unlike standard x86 PCs, Medfield does not have many legacy devices
+ nor standard legacy replacement devices/features. e.g. Medfield does
+ not contain i8259, i8254, HPET, legacy BIOS, most of the io ports.
+
endif
config X86_RDC321X
@@ -632,7 +655,7 @@ config X86_SUMMIT_NUMA
config X86_CYCLONE_TIMER
def_bool y
- depends on X86_32_NON_STANDARD
+ depends on X86_SUMMIT
source "arch/x86/Kconfig.cpu"
@@ -660,9 +683,10 @@ config HPET_EMULATE_RTC
depends on HPET_TIMER && (RTC=y || RTC=m || RTC_DRV_CMOS=m || RTC_DRV_CMOS=y)
config APB_TIMER
- def_bool y if MRST
- prompt "Langwell APB Timer Support" if X86_MRST
+ def_bool y if X86_INTEL_MID
+ prompt "Intel MID APB Timer Support" if X86_INTEL_MID
select DW_APB_TIMER
+ depends on X86_INTEL_MID && SFI
help
APB timer is the replacement for 8254, HPET on X86 MID platforms.
The APBT provides a stable time base on SMP
@@ -1490,6 +1514,13 @@ config EFI
resultant kernel should continue to boot on existing non-EFI
platforms.
+config EFI_STUB
+ bool "EFI stub support"
+ depends on EFI
+ ---help---
+ This kernel feature allows a bzImage to be loaded directly
+ by EFI firmware without the use of a bootloader.
+
config SECCOMP
def_bool y
prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index e3ca7e0d858c..3c57033e2211 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -309,12 +309,6 @@ config X86_INTERNODE_CACHE_SHIFT
config X86_CMPXCHG
def_bool X86_64 || (X86_32 && !M386)
-config CMPXCHG_LOCAL
- def_bool X86_64 || (X86_32 && !M386)
-
-config CMPXCHG_DOUBLE
- def_bool y
-
config X86_L1_CACHE_SHIFT
int
default "7" if MPENTIUM4 || MPSC
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bf56e1793272..e46c2147397f 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -43,9 +43,9 @@ config EARLY_PRINTK
with klogd/syslogd or the X server. You should normally N here,
unless you want to debug such a crash.
-config EARLY_PRINTK_MRST
- bool "Early printk for MRST platform support"
- depends on EARLY_PRINTK && X86_MRST
+config EARLY_PRINTK_INTEL_MID
+ bool "Early printk for Intel MID platform support"
+ depends on EARLY_PRINTK && X86_INTEL_MID
config EARLY_PRINTK_DBGP
bool "Early printk via EHCI debug port"
@@ -63,8 +63,11 @@ config DEBUG_STACKOVERFLOW
bool "Check for stack overflows"
depends on DEBUG_KERNEL
---help---
- This option will cause messages to be printed if free stack space
- drops below a certain limit.
+ Say Y here if you want to check the overflows of kernel, IRQ
+ and exception stacks. This option will cause messages of the
+ stacks in detail when free stack space drops below a certain
+ limit.
+ If in doubt, say "N".
config X86_PTDUMP
bool "Export kernel pagetable layout to userspace via debugfs"
@@ -284,4 +287,16 @@ config DEBUG_STRICT_USER_COPY_CHECKS
If unsure, or if you run an older (pre 4.4) gcc, say N.
+config DEBUG_NMI_SELFTEST
+ bool "NMI Selftest"
+ depends on DEBUG_KERNEL && X86_LOCAL_APIC
+ ---help---
+ Enabling this option turns on a quick NMI selftest to verify
+ that the NMI behaves correctly.
+
+ This might help diagnose strange hangs that rely on NMI to
+ function properly.
+
+ If unsure, say N.
+
endmenu
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index b02e509072a7..209ba1294592 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -118,6 +118,12 @@ KBUILD_CFLAGS += $(mflags-y)
KBUILD_AFLAGS += $(mflags-y)
###
+# Syscall table generation
+
+archheaders:
+ $(Q)$(MAKE) $(build)=arch/x86/syscalls all
+
+###
# Kernel objects
head-y := arch/x86/kernel/head_$(BITS).o
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 09664efb9cee..b123b9a8f5b3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -23,7 +23,15 @@ LDFLAGS_vmlinux := -T
hostprogs-y := mkpiggy
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o $(obj)/piggy.o FORCE
+VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
+ $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
+ $(obj)/piggy.o
+
+ifeq ($(CONFIG_EFI_STUB), y)
+ VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
+endif
+
+$(obj)/vmlinux: $(VMLINUX_OBJS) FORCE
$(call if_changed,ld)
@:
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
new file mode 100644
index 000000000000..fec216f4fbc3
--- /dev/null
+++ b/arch/x86/boot/compressed/eboot.c
@@ -0,0 +1,1022 @@
+/* -----------------------------------------------------------------------
+ *
+ * Copyright 2011 Intel Corporation; author Matt Fleming
+ *
+ * This file is part of the Linux kernel, and is made available under
+ * the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+#include <linux/efi.h>
+#include <asm/efi.h>
+#include <asm/setup.h>
+#include <asm/desc.h>
+
+#include "eboot.h"
+
+static efi_system_table_t *sys_table;
+
+static efi_status_t __get_map(efi_memory_desc_t **map, unsigned long *map_size,
+ unsigned long *desc_size)
+{
+ efi_memory_desc_t *m = NULL;
+ efi_status_t status;
+ unsigned long key;
+ u32 desc_version;
+
+ *map_size = sizeof(*m) * 32;
+again:
+ /*
+ * Add an additional efi_memory_desc_t because we're doing an
+ * allocation which may be in a new descriptor region.
+ */
+ *map_size += sizeof(*m);
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, *map_size, (void **)&m);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = efi_call_phys5(sys_table->boottime->get_memory_map, map_size,
+ m, &key, desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ efi_call_phys1(sys_table->boottime->free_pool, m);
+ goto again;
+ }
+
+ if (status != EFI_SUCCESS)
+ efi_call_phys1(sys_table->boottime->free_pool, m);
+
+fail:
+ *map = m;
+ return status;
+}
+
+/*
+ * Allocate at the highest possible address that is not above 'max'.
+ */
+static efi_status_t high_alloc(unsigned long size, unsigned long align,
+ unsigned long *addr, unsigned long max)
+{
+ unsigned long map_size, desc_size;
+ efi_memory_desc_t *map;
+ efi_status_t status;
+ unsigned long nr_pages;
+ u64 max_addr = 0;
+ int i;
+
+ status = __get_map(&map, &map_size, &desc_size);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+again:
+ for (i = 0; i < map_size / desc_size; i++) {
+ efi_memory_desc_t *desc;
+ unsigned long m = (unsigned long)map;
+ u64 start, end;
+
+ desc = (efi_memory_desc_t *)(m + (i * desc_size));
+ if (desc->type != EFI_CONVENTIONAL_MEMORY)
+ continue;
+
+ if (desc->num_pages < nr_pages)
+ continue;
+
+ start = desc->phys_addr;
+ end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+ if ((start + size) > end || (start + size) > max)
+ continue;
+
+ if (end - size > max)
+ end = max;
+
+ if (round_down(end - size, align) < start)
+ continue;
+
+ start = round_down(end - size, align);
+
+ /*
+ * Don't allocate at 0x0. It will confuse code that
+ * checks pointers against NULL.
+ */
+ if (start == 0x0)
+ continue;
+
+ if (start > max_addr)
+ max_addr = start;
+ }
+
+ if (!max_addr)
+ status = EFI_NOT_FOUND;
+ else {
+ status = efi_call_phys4(sys_table->boottime->allocate_pages,
+ EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+ nr_pages, &max_addr);
+ if (status != EFI_SUCCESS) {
+ max = max_addr;
+ max_addr = 0;
+ goto again;
+ }
+
+ *addr = max_addr;
+ }
+
+free_pool:
+ efi_call_phys1(sys_table->boottime->free_pool, map);
+
+fail:
+ return status;
+}
+
+/*
+ * Allocate at the lowest possible address.
+ */
+static efi_status_t low_alloc(unsigned long size, unsigned long align,
+ unsigned long *addr)
+{
+ unsigned long map_size, desc_size;
+ efi_memory_desc_t *map;
+ efi_status_t status;
+ unsigned long nr_pages;
+ int i;
+
+ status = __get_map(&map, &map_size, &desc_size);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ for (i = 0; i < map_size / desc_size; i++) {
+ efi_memory_desc_t *desc;
+ unsigned long m = (unsigned long)map;
+ u64 start, end;
+
+ desc = (efi_memory_desc_t *)(m + (i * desc_size));
+
+ if (desc->type != EFI_CONVENTIONAL_MEMORY)
+ continue;
+
+ if (desc->num_pages < nr_pages)
+ continue;
+
+ start = desc->phys_addr;
+ end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
+
+ /*
+ * Don't allocate at 0x0. It will confuse code that
+ * checks pointers against NULL. Skip the first 8
+ * bytes so we start at a nice even number.
+ */
+ if (start == 0x0)
+ start += 8;
+
+ start = round_up(start, align);
+ if ((start + size) > end)
+ continue;
+
+ status = efi_call_phys4(sys_table->boottime->allocate_pages,
+ EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+ nr_pages, &start);
+ if (status == EFI_SUCCESS) {
+ *addr = start;
+ break;
+ }
+ }
+
+ if (i == map_size / desc_size)
+ status = EFI_NOT_FOUND;
+
+free_pool:
+ efi_call_phys1(sys_table->boottime->free_pool, map);
+fail:
+ return status;
+}
+
+static void low_free(unsigned long size, unsigned long addr)
+{
+ unsigned long nr_pages;
+
+ nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ efi_call_phys2(sys_table->boottime->free_pages, addr, size);
+}
+
+static void find_bits(unsigned long mask, u8 *pos, u8 *size)
+{
+ u8 first, len;
+
+ first = 0;
+ len = 0;
+
+ if (mask) {
+ while (!(mask & 0x1)) {
+ mask = mask >> 1;
+ first++;
+ }
+
+ while (mask & 0x1) {
+ mask = mask >> 1;
+ len++;
+ }
+ }
+
+ *pos = first;
+ *size = len;
+}
+
+/*
+ * See if we have Graphics Output Protocol
+ */
+static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
+ unsigned long size)
+{
+ struct efi_graphics_output_protocol *gop, *first_gop;
+ struct efi_pixel_bitmask pixel_info;
+ unsigned long nr_gops;
+ efi_status_t status;
+ void **gop_handle;
+ u16 width, height;
+ u32 fb_base, fb_size;
+ u32 pixels_per_scan_line;
+ int pixel_format;
+ int i;
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, size, &gop_handle);
+ if (status != EFI_SUCCESS)
+ return status;
+
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, proto,
+ NULL, &size, gop_handle);
+ if (status != EFI_SUCCESS)
+ goto free_handle;
+
+ first_gop = NULL;
+
+ nr_gops = size / sizeof(void *);
+ for (i = 0; i < nr_gops; i++) {
+ struct efi_graphics_output_mode_info *info;
+ efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ void *pciio;
+ void *h = gop_handle[i];
+
+ status = efi_call_phys3(sys_table->boottime->handle_protocol,
+ h, proto, &gop);
+ if (status != EFI_SUCCESS)
+ continue;
+
+ efi_call_phys3(sys_table->boottime->handle_protocol,
+ h, &pciio_proto, &pciio);
+
+ status = efi_call_phys4(gop->query_mode, gop,
+ gop->mode->mode, &size, &info);
+ if (status == EFI_SUCCESS && (!first_gop || pciio)) {
+ /*
+ * Apple provide GOPs that are not backed by
+ * real hardware (they're used to handle
+ * multiple displays). The workaround is to
+ * search for a GOP implementing the PCIIO
+ * protocol, and if one isn't found, to just
+ * fallback to the first GOP.
+ */
+ width = info->horizontal_resolution;
+ height = info->vertical_resolution;
+ fb_base = gop->mode->frame_buffer_base;
+ fb_size = gop->mode->frame_buffer_size;
+ pixel_format = info->pixel_format;
+ pixel_info = info->pixel_information;
+ pixels_per_scan_line = info->pixels_per_scan_line;
+
+ /*
+ * Once we've found a GOP supporting PCIIO,
+ * don't bother looking any further.
+ */
+ if (pciio)
+ break;
+
+ first_gop = gop;
+ }
+ }
+
+ /* Did we find any GOPs? */
+ if (!first_gop)
+ goto free_handle;
+
+ /* EFI framebuffer */
+ si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+ si->lfb_width = width;
+ si->lfb_height = height;
+ si->lfb_base = fb_base;
+ si->lfb_size = fb_size;
+ si->pages = 1;
+
+ if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
+ si->lfb_depth = 32;
+ si->lfb_linelength = pixels_per_scan_line * 4;
+ si->red_size = 8;
+ si->red_pos = 0;
+ si->green_size = 8;
+ si->green_pos = 8;
+ si->blue_size = 8;
+ si->blue_pos = 16;
+ si->rsvd_size = 8;
+ si->rsvd_pos = 24;
+ } else if (pixel_format == PIXEL_BGR_RESERVED_8BIT_PER_COLOR) {
+ si->lfb_depth = 32;
+ si->lfb_linelength = pixels_per_scan_line * 4;
+ si->red_size = 8;
+ si->red_pos = 16;
+ si->green_size = 8;
+ si->green_pos = 8;
+ si->blue_size = 8;
+ si->blue_pos = 0;
+ si->rsvd_size = 8;
+ si->rsvd_pos = 24;
+ } else if (pixel_format == PIXEL_BIT_MASK) {
+ find_bits(pixel_info.red_mask, &si->red_pos, &si->red_size);
+ find_bits(pixel_info.green_mask, &si->green_pos,
+ &si->green_size);
+ find_bits(pixel_info.blue_mask, &si->blue_pos, &si->blue_size);
+ find_bits(pixel_info.reserved_mask, &si->rsvd_pos,
+ &si->rsvd_size);
+ si->lfb_depth = si->red_size + si->green_size +
+ si->blue_size + si->rsvd_size;
+ si->lfb_linelength = (pixels_per_scan_line * si->lfb_depth) / 8;
+ } else {
+ si->lfb_depth = 4;
+ si->lfb_linelength = si->lfb_width / 2;
+ si->red_size = 0;
+ si->red_pos = 0;
+ si->green_size = 0;
+ si->green_pos = 0;
+ si->blue_size = 0;
+ si->blue_pos = 0;
+ si->rsvd_size = 0;
+ si->rsvd_pos = 0;
+ }
+
+free_handle:
+ efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
+ return status;
+}
+
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
+static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+ unsigned long size)
+{
+ struct efi_uga_draw_protocol *uga, *first_uga;
+ unsigned long nr_ugas;
+ efi_status_t status;
+ u32 width, height;
+ void **uga_handle = NULL;
+ int i;
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, size, &uga_handle);
+ if (status != EFI_SUCCESS)
+ return status;
+
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, uga_proto,
+ NULL, &size, uga_handle);
+ if (status != EFI_SUCCESS)
+ goto free_handle;
+
+ first_uga = NULL;
+
+ nr_ugas = size / sizeof(void *);
+ for (i = 0; i < nr_ugas; i++) {
+ efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+ void *handle = uga_handle[i];
+ u32 w, h, depth, refresh;
+ void *pciio;
+
+ status = efi_call_phys3(sys_table->boottime->handle_protocol,
+ handle, uga_proto, &uga);
+ if (status != EFI_SUCCESS)
+ continue;
+
+ efi_call_phys3(sys_table->boottime->handle_protocol,
+ handle, &pciio_proto, &pciio);
+
+ status = efi_call_phys5(uga->get_mode, uga, &w, &h,
+ &depth, &refresh);
+ if (status == EFI_SUCCESS && (!first_uga || pciio)) {
+ width = w;
+ height = h;
+
+ /*
+ * Once we've found a UGA supporting PCIIO,
+ * don't bother looking any further.
+ */
+ if (pciio)
+ break;
+
+ first_uga = uga;
+ }
+ }
+
+ if (!first_uga)
+ goto free_handle;
+
+ /* EFI framebuffer */
+ si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+ si->lfb_depth = 32;
+ si->lfb_width = width;
+ si->lfb_height = height;
+
+ si->red_size = 8;
+ si->red_pos = 16;
+ si->green_size = 8;
+ si->green_pos = 8;
+ si->blue_size = 8;
+ si->blue_pos = 0;
+ si->rsvd_size = 8;
+ si->rsvd_pos = 24;
+
+
+free_handle:
+ efi_call_phys1(sys_table->boottime->free_pool, uga_handle);
+ return status;
+}
+
+void setup_graphics(struct boot_params *boot_params)
+{
+ efi_guid_t graphics_proto = EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID;
+ struct screen_info *si;
+ efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+ efi_status_t status;
+ unsigned long size;
+ void **gop_handle = NULL;
+ void **uga_handle = NULL;
+
+ si = &boot_params->screen_info;
+ memset(si, 0, sizeof(*si));
+
+ size = 0;
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
+ NULL, &size, gop_handle);
+ if (status == EFI_BUFFER_TOO_SMALL)
+ status = setup_gop(si, &graphics_proto, size);
+
+ if (status != EFI_SUCCESS) {
+ size = 0;
+ status = efi_call_phys5(sys_table->boottime->locate_handle,
+ EFI_LOCATE_BY_PROTOCOL, &uga_proto,
+ NULL, &size, uga_handle);
+ if (status == EFI_BUFFER_TOO_SMALL)
+ setup_uga(si, &uga_proto, size);
+ }
+}
+
+struct initrd {
+ efi_file_handle_t *handle;
+ u64 size;
+};
+
+/*
+ * Check the cmdline for a LILO-style initrd= arguments.
+ *
+ * We only support loading an initrd from the same filesystem as the
+ * kernel image.
+ */
+static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
+ struct setup_header *hdr)
+{
+ struct initrd *initrds;
+ unsigned long initrd_addr;
+ efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+ u64 initrd_total;
+ efi_file_io_interface_t *io;
+ efi_file_handle_t *fh;
+ efi_status_t status;
+ int nr_initrds;
+ char *str;
+ int i, j, k;
+
+ initrd_addr = 0;
+ initrd_total = 0;
+
+ str = (char *)(unsigned long)hdr->cmd_line_ptr;
+
+ j = 0; /* See close_handles */
+
+ if (!str || !*str)
+ return EFI_SUCCESS;
+
+ for (nr_initrds = 0; *str; nr_initrds++) {
+ str = strstr(str, "initrd=");
+ if (!str)
+ break;
+
+ str += 7;
+
+ /* Skip any leading slashes */
+ while (*str == '/' || *str == '\\')
+ str++;
+
+ while (*str && *str != ' ' && *str != '\n')
+ str++;
+ }
+
+ if (!nr_initrds)
+ return EFI_SUCCESS;
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA,
+ nr_initrds * sizeof(*initrds),
+ &initrds);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ str = (char *)(unsigned long)hdr->cmd_line_ptr;
+ for (i = 0; i < nr_initrds; i++) {
+ struct initrd *initrd;
+ efi_file_handle_t *h;
+ efi_file_info_t *info;
+ efi_char16_t filename[256];
+ unsigned long info_sz;
+ efi_guid_t info_guid = EFI_FILE_INFO_ID;
+ efi_char16_t *p;
+ u64 file_sz;
+
+ str = strstr(str, "initrd=");
+ if (!str)
+ break;
+
+ str += 7;
+
+ initrd = &initrds[i];
+ p = filename;
+
+ /* Skip any leading slashes */
+ while (*str == '/' || *str == '\\')
+ str++;
+
+ while (*str && *str != ' ' && *str != '\n') {
+ if (p >= filename + sizeof(filename))
+ break;
+
+ *p++ = *str++;
+ }
+
+ *p = '\0';
+
+ /* Only open the volume once. */
+ if (!i) {
+ efi_boot_services_t *boottime;
+
+ boottime = sys_table->boottime;
+
+ status = efi_call_phys3(boottime->handle_protocol,
+ image->device_handle, &fs_proto, &io);
+ if (status != EFI_SUCCESS)
+ goto free_initrds;
+
+ status = efi_call_phys2(io->open_volume, io, &fh);
+ if (status != EFI_SUCCESS)
+ goto free_initrds;
+ }
+
+ status = efi_call_phys5(fh->open, fh, &h, filename,
+ EFI_FILE_MODE_READ, (u64)0);
+ if (status != EFI_SUCCESS)
+ goto close_handles;
+
+ initrd->handle = h;
+
+ info_sz = 0;
+ status = efi_call_phys4(h->get_info, h, &info_guid,
+ &info_sz, NULL);
+ if (status != EFI_BUFFER_TOO_SMALL)
+ goto close_handles;
+
+grow:
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, info_sz, &info);
+ if (status != EFI_SUCCESS)
+ goto close_handles;
+
+ status = efi_call_phys4(h->get_info, h, &info_guid,
+ &info_sz, info);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ efi_call_phys1(sys_table->boottime->free_pool, info);
+ goto grow;
+ }
+
+ file_sz = info->file_size;
+ efi_call_phys1(sys_table->boottime->free_pool, info);
+
+ if (status != EFI_SUCCESS)
+ goto close_handles;
+
+ initrd->size = file_sz;
+ initrd_total += file_sz;
+ }
+
+ if (initrd_total) {
+ unsigned long addr;
+
+ /*
+ * Multiple initrd's need to be at consecutive
+ * addresses in memory, so allocate enough memory for
+ * all the initrd's.
+ */
+ status = high_alloc(initrd_total, 0x1000,
+ &initrd_addr, hdr->initrd_addr_max);
+ if (status != EFI_SUCCESS)
+ goto close_handles;
+
+ /* We've run out of free low memory. */
+ if (initrd_addr > hdr->initrd_addr_max) {
+ status = EFI_INVALID_PARAMETER;
+ goto free_initrd_total;
+ }
+
+ addr = initrd_addr;
+ for (j = 0; j < nr_initrds; j++) {
+ u64 size;
+
+ size = initrds[j].size;
+ while (size) {
+ u64 chunksize;
+ if (size > EFI_READ_CHUNK_SIZE)
+ chunksize = EFI_READ_CHUNK_SIZE;
+ else
+ chunksize = size;
+ status = efi_call_phys3(fh->read,
+ initrds[j].handle,
+ &chunksize, addr);
+ if (status != EFI_SUCCESS)
+ goto free_initrd_total;
+ addr += chunksize;
+ size -= chunksize;
+ }
+
+ efi_call_phys1(fh->close, initrds[j].handle);
+ }
+
+ }
+
+ efi_call_phys1(sys_table->boottime->free_pool, initrds);
+
+ hdr->ramdisk_image = initrd_addr;
+ hdr->ramdisk_size = initrd_total;
+
+ return status;
+
+free_initrd_total:
+ low_free(initrd_total, initrd_addr);
+
+close_handles:
+ for (k = j; k < nr_initrds; k++)
+ efi_call_phys1(fh->close, initrds[k].handle);
+free_initrds:
+ efi_call_phys1(sys_table->boottime->free_pool, initrds);
+fail:
+ hdr->ramdisk_image = 0;
+ hdr->ramdisk_size = 0;
+
+ return status;
+}
+
+/*
+ * Because the x86 boot code expects to be passed a boot_params we
+ * need to create one ourselves (usually the bootloader would create
+ * one for us).
+ */
+static efi_status_t make_boot_params(struct boot_params *boot_params,
+ efi_loaded_image_t *image,
+ void *handle)
+{
+ struct efi_info *efi = &boot_params->efi_info;
+ struct apm_bios_info *bi = &boot_params->apm_bios_info;
+ struct sys_desc_table *sdt = &boot_params->sys_desc_table;
+ struct e820entry *e820_map = &boot_params->e820_map[0];
+ struct e820entry *prev = NULL;
+ struct setup_header *hdr = &boot_params->hdr;
+ unsigned long size, key, desc_size, _size;
+ efi_memory_desc_t *mem_map;
+ void *options = image->load_options;
+ u32 load_options_size = image->load_options_size / 2; /* ASCII */
+ int options_size = 0;
+ efi_status_t status;
+ __u32 desc_version;
+ unsigned long cmdline;
+ u8 nr_entries;
+ u16 *s2;
+ u8 *s1;
+ int i;
+
+ hdr->type_of_loader = 0x21;
+
+ /* Convert unicode cmdline to ascii */
+ cmdline = 0;
+ s2 = (u16 *)options;
+
+ if (s2) {
+ while (*s2 && *s2 != '\n' && options_size < load_options_size) {
+ s2++;
+ options_size++;
+ }
+
+ if (options_size) {
+ if (options_size > hdr->cmdline_size)
+ options_size = hdr->cmdline_size;
+
+ options_size++; /* NUL termination */
+
+ status = low_alloc(options_size, 1, &cmdline);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ s1 = (u8 *)(unsigned long)cmdline;
+ s2 = (u16 *)options;
+
+ for (i = 0; i < options_size - 1; i++)
+ *s1++ = *s2++;
+
+ *s1 = '\0';
+ }
+ }
+
+ hdr->cmd_line_ptr = cmdline;
+
+ hdr->ramdisk_image = 0;
+ hdr->ramdisk_size = 0;
+
+ status = handle_ramdisks(image, hdr);
+ if (status != EFI_SUCCESS)
+ goto free_cmdline;
+
+ setup_graphics(boot_params);
+
+ /* Clear APM BIOS info */
+ memset(bi, 0, sizeof(*bi));
+
+ memset(sdt, 0, sizeof(*sdt));
+
+ memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+
+ size = sizeof(*mem_map) * 32;
+
+again:
+ size += sizeof(*mem_map);
+ _size = size;
+ status = low_alloc(size, 1, (unsigned long *)&mem_map);
+ if (status != EFI_SUCCESS)
+ goto free_cmdline;
+
+ status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
+ mem_map, &key, &desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL) {
+ low_free(_size, (unsigned long)mem_map);
+ goto again;
+ }
+
+ if (status != EFI_SUCCESS)
+ goto free_mem_map;
+
+ efi->efi_systab = (unsigned long)sys_table;
+ efi->efi_memdesc_size = desc_size;
+ efi->efi_memdesc_version = desc_version;
+ efi->efi_memmap = (unsigned long)mem_map;
+ efi->efi_memmap_size = size;
+
+#ifdef CONFIG_X86_64
+ efi->efi_systab_hi = (unsigned long)sys_table >> 32;
+ efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+#endif
+
+ /* Might as well exit boot services now */
+ status = efi_call_phys2(sys_table->boottime->exit_boot_services,
+ handle, key);
+ if (status != EFI_SUCCESS)
+ goto free_mem_map;
+
+ /* Historic? */
+ boot_params->alt_mem_k = 32 * 1024;
+
+ /*
+ * Convert the EFI memory map to E820.
+ */
+ nr_entries = 0;
+ for (i = 0; i < size / desc_size; i++) {
+ efi_memory_desc_t *d;
+ unsigned int e820_type = 0;
+ unsigned long m = (unsigned long)mem_map;
+
+ d = (efi_memory_desc_t *)(m + (i * desc_size));
+ switch (d->type) {
+ case EFI_RESERVED_TYPE:
+ case EFI_RUNTIME_SERVICES_CODE:
+ case EFI_RUNTIME_SERVICES_DATA:
+ case EFI_MEMORY_MAPPED_IO:
+ case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
+ case EFI_PAL_CODE:
+ e820_type = E820_RESERVED;
+ break;
+
+ case EFI_UNUSABLE_MEMORY:
+ e820_type = E820_UNUSABLE;
+ break;
+
+ case EFI_ACPI_RECLAIM_MEMORY:
+ e820_type = E820_ACPI;
+ break;
+
+ case EFI_LOADER_CODE:
+ case EFI_LOADER_DATA:
+ case EFI_BOOT_SERVICES_CODE:
+ case EFI_BOOT_SERVICES_DATA:
+ case EFI_CONVENTIONAL_MEMORY:
+ e820_type = E820_RAM;
+ break;
+
+ case EFI_ACPI_MEMORY_NVS:
+ e820_type = E820_NVS;
+ break;
+
+ default:
+ continue;
+ }
+
+ /* Merge adjacent mappings */
+ if (prev && prev->type == e820_type &&
+ (prev->addr + prev->size) == d->phys_addr)
+ prev->size += d->num_pages << 12;
+ else {
+ e820_map->addr = d->phys_addr;
+ e820_map->size = d->num_pages << 12;
+ e820_map->type = e820_type;
+ prev = e820_map++;
+ nr_entries++;
+ }
+ }
+
+ boot_params->e820_entries = nr_entries;
+
+ return EFI_SUCCESS;
+
+free_mem_map:
+ low_free(_size, (unsigned long)mem_map);
+free_cmdline:
+ if (options_size)
+ low_free(options_size, hdr->cmd_line_ptr);
+fail:
+ return status;
+}
+
+/*
+ * On success we return a pointer to a boot_params structure, and NULL
+ * on failure.
+ */
+struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
+{
+ struct boot_params *boot_params;
+ unsigned long start, nr_pages;
+ struct desc_ptr *gdt, *idt;
+ efi_loaded_image_t *image;
+ struct setup_header *hdr;
+ efi_status_t status;
+ efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
+ struct desc_struct *desc;
+
+ sys_table = _table;
+
+ /* Check if we were booted by the EFI firmware */
+ if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+ goto fail;
+
+ status = efi_call_phys3(sys_table->boottime->handle_protocol,
+ handle, &proto, (void *)&image);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ memset(boot_params, 0x0, 0x4000);
+
+ /* Copy first two sectors to boot_params */
+ memcpy(boot_params, image->image_base, 1024);
+
+ hdr = &boot_params->hdr;
+
+ /*
+ * The EFI firmware loader could have placed the kernel image
+ * anywhere in memory, but the kernel has various restrictions
+ * on the max physical address it can run at. Attempt to move
+ * the kernel to boot_params.pref_address, or as low as
+ * possible.
+ */
+ start = hdr->pref_address;
+ nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+
+ status = efi_call_phys4(sys_table->boottime->allocate_pages,
+ EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
+ nr_pages, &start);
+ if (status != EFI_SUCCESS) {
+ status = low_alloc(hdr->init_size, hdr->kernel_alignment,
+ &start);
+ if (status != EFI_SUCCESS)
+ goto fail;
+ }
+
+ hdr->code32_start = (__u32)start;
+ hdr->pref_address = (__u64)(unsigned long)image->image_base;
+
+ memcpy((void *)start, image->image_base, image->image_size);
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, sizeof(*gdt),
+ (void **)&gdt);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ gdt->size = 0x800;
+ status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, sizeof(*idt),
+ (void **)&idt);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ idt->size = 0;
+ idt->address = 0;
+
+ status = make_boot_params(boot_params, image, handle);
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ memset((char *)gdt->address, 0x0, gdt->size);
+ desc = (struct desc_struct *)gdt->address;
+
+ /* The first GDT is a dummy and the second is unused. */
+ desc += 2;
+
+ desc->limit0 = 0xffff;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+ desc->s = DESC_TYPE_CODE_DATA;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit = 0xf;
+ desc->avl = 0;
+ desc->l = 0;
+ desc->d = SEG_OP_SIZE_32BIT;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
+
+ desc++;
+ desc->limit0 = 0xffff;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
+ desc->s = DESC_TYPE_CODE_DATA;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit = 0xf;
+ desc->avl = 0;
+ desc->l = 0;
+ desc->d = SEG_OP_SIZE_32BIT;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
+
+#ifdef CONFIG_X86_64
+ /* Task segment value */
+ desc++;
+ desc->limit0 = 0x0000;
+ desc->base0 = 0x0000;
+ desc->base1 = 0x0000;
+ desc->type = SEG_TYPE_TSS;
+ desc->s = 0;
+ desc->dpl = 0;
+ desc->p = 1;
+ desc->limit = 0x0;
+ desc->avl = 0;
+ desc->l = 0;
+ desc->d = 0;
+ desc->g = SEG_GRANULARITY_4KB;
+ desc->base2 = 0x00;
+#endif /* CONFIG_X86_64 */
+
+ asm volatile ("lidt %0" : : "m" (*idt));
+ asm volatile ("lgdt %0" : : "m" (*gdt));
+
+ asm volatile("cli");
+
+ return boot_params;
+fail:
+ return NULL;
+}
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
new file mode 100644
index 000000000000..39251663e65b
--- /dev/null
+++ b/arch/x86/boot/compressed/eboot.h
@@ -0,0 +1,61 @@
+#ifndef BOOT_COMPRESSED_EBOOT_H
+#define BOOT_COMPRESSED_EBOOT_H
+
+#define SEG_TYPE_DATA (0 << 3)
+#define SEG_TYPE_READ_WRITE (1 << 1)
+#define SEG_TYPE_CODE (1 << 3)
+#define SEG_TYPE_EXEC_READ (1 << 1)
+#define SEG_TYPE_TSS ((1 << 3) | (1 << 0))
+#define SEG_OP_SIZE_32BIT (1 << 0)
+#define SEG_GRANULARITY_4KB (1 << 0)
+
+#define DESC_TYPE_CODE_DATA (1 << 0)
+
+#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
+#define EFI_READ_CHUNK_SIZE (1024 * 1024)
+
+#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR 0
+#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR 1
+#define PIXEL_BIT_MASK 2
+#define PIXEL_BLT_ONLY 3
+#define PIXEL_FORMAT_MAX 4
+
+struct efi_pixel_bitmask {
+ u32 red_mask;
+ u32 green_mask;
+ u32 blue_mask;
+ u32 reserved_mask;
+};
+
+struct efi_graphics_output_mode_info {
+ u32 version;
+ u32 horizontal_resolution;
+ u32 vertical_resolution;
+ int pixel_format;
+ struct efi_pixel_bitmask pixel_information;
+ u32 pixels_per_scan_line;
+} __packed;
+
+struct efi_graphics_output_protocol_mode {
+ u32 max_mode;
+ u32 mode;
+ unsigned long info;
+ unsigned long size_of_info;
+ u64 frame_buffer_base;
+ unsigned long frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol {
+ void *query_mode;
+ unsigned long set_mode;
+ unsigned long blt;
+ struct efi_graphics_output_protocol_mode *mode;
+};
+
+struct efi_uga_draw_protocol {
+ void *get_mode;
+ void *set_mode;
+ void *blt;
+};
+
+#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/efi_stub_32.S b/arch/x86/boot/compressed/efi_stub_32.S
new file mode 100644
index 000000000000..a53440e81d52
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_stub_32.S
@@ -0,0 +1,86 @@
+/*
+ * EFI call stub for IA32.
+ *
+ * This stub allows us to make EFI calls in physical mode with interrupts
+ * turned off. Note that this implementation is different from the one in
+ * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical
+ * mode at this point.
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+/*
+ * efi_call_phys(void *, ...) is a function with variable parameters.
+ * All the callers of this function assure that all the parameters are 4-bytes.
+ */
+
+/*
+ * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save.
+ * So we'd better save all of them at the beginning of this function and restore
+ * at the end no matter how many we use, because we can not assure EFI runtime
+ * service functions will comply with gcc calling convention, too.
+ */
+
+.text
+ENTRY(efi_call_phys)
+ /*
+ * 0. The function can only be called in Linux kernel. So CS has been
+ * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
+ * the values of these registers are the same. And, the corresponding
+ * GDT entries are identical. So I will do nothing about segment reg
+ * and GDT, but change GDT base register in prelog and epilog.
+ */
+
+ /*
+ * 1. Because we haven't been relocated by this point we need to
+ * use relative addressing.
+ */
+ call 1f
+1: popl %edx
+ subl $1b, %edx
+
+ /*
+ * 2. Now on the top of stack is the return
+ * address in the caller of efi_call_phys(), then parameter 1,
+ * parameter 2, ..., param n. To make things easy, we save the return
+ * address of efi_call_phys in a global variable.
+ */
+ popl %ecx
+ movl %ecx, saved_return_addr(%edx)
+ /* get the function pointer into ECX*/
+ popl %ecx
+ movl %ecx, efi_rt_function_ptr(%edx)
+
+ /*
+ * 3. Call the physical function.
+ */
+ call *%ecx
+
+ /*
+ * 4. Balance the stack. And because EAX contain the return value,
+ * we'd better not clobber it. We need to calculate our address
+ * again because %ecx and %edx are not preserved across EFI function
+ * calls.
+ */
+ call 1f
+1: popl %edx
+ subl $1b, %edx
+
+ movl efi_rt_function_ptr(%edx), %ecx
+ pushl %ecx
+
+ /*
+ * 10. Push the saved return address onto the stack and return.
+ */
+ movl saved_return_addr(%edx), %ecx
+ pushl %ecx
+ ret
+ENDPROC(efi_call_phys)
+.previous
+
+.data
+saved_return_addr:
+ .long 0
+efi_rt_function_ptr:
+ .long 0
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
new file mode 100644
index 000000000000..cedc60de86eb
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -0,0 +1 @@
+#include "../../platform/efi/efi_stub_64.S"
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 67a655a39ce4..a0559930a180 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -32,6 +32,28 @@
__HEAD
ENTRY(startup_32)
+#ifdef CONFIG_EFI_STUB
+ /*
+ * We don't need the return address, so set up the stack so
+ * efi_main() can find its arugments.
+ */
+ add $0x4, %esp
+
+ call efi_main
+ cmpl $0, %eax
+ je preferred_addr
+ movl %eax, %esi
+ call 1f
+1:
+ popl %eax
+ subl $1b, %eax
+ subl BP_pref_address(%esi), %eax
+ add BP_code32_start(%esi), %eax
+ leal preferred_addr(%eax), %eax
+ jmp *%eax
+
+preferred_addr:
+#endif
cld
/*
* Test KEEP_SEGMENTS flag to see if the bootloader is asking
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 35af09d13dc1..558d76ce23bc 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -199,6 +199,26 @@ ENTRY(startup_64)
* an identity mapped page table being provied that maps our
* entire text+data+bss and hopefully all of memory.
*/
+#ifdef CONFIG_EFI_STUB
+ pushq %rsi
+ mov %rcx, %rdi
+ mov %rdx, %rsi
+ call efi_main
+ popq %rsi
+ cmpq $0,%rax
+ je preferred_addr
+ movq %rax,%rsi
+ call 1f
+1:
+ popq %rax
+ subq $1b, %rax
+ subq BP_pref_address(%rsi), %rax
+ add BP_code32_start(%esi), %eax
+ leaq preferred_addr(%rax), %rax
+ jmp *%rax
+
+preferred_addr:
+#endif
/* Setup data segments. */
xorl %eax, %eax
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 3a19d04cebeb..7116dcba0c9e 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -321,6 +321,8 @@ static void parse_elf(void *output)
default: /* Ignore other PT_* */ break;
}
}
+
+ free(phdrs);
}
asmlinkage void decompress_kernel(void *rmode, memptr heap,
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index 19b3e693cd72..ffb9c5c9d748 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -1,2 +1,11 @@
#include "misc.h"
+
+int memcmp(const void *s1, const void *s2, size_t len)
+{
+ u8 diff;
+ asm("repe; cmpsb; setnz %0"
+ : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+ return diff;
+}
+
#include "../string.c"
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index bdb4d458ec8c..f1bbeeb09148 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -45,6 +45,11 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
.global bootsect_start
bootsect_start:
+#ifdef CONFIG_EFI_STUB
+ # "MZ", MS-DOS header
+ .byte 0x4d
+ .byte 0x5a
+#endif
# Normalize the start address
ljmp $BOOTSEG, $start2
@@ -79,6 +84,14 @@ bs_die:
# invoke the BIOS reset code...
ljmp $0xf000,$0xfff0
+#ifdef CONFIG_EFI_STUB
+ .org 0x3c
+ #
+ # Offset to the PE header.
+ #
+ .long pe_header
+#endif /* CONFIG_EFI_STUB */
+
.section ".bsdata", "a"
bugger_off_msg:
.ascii "Direct booting from floppy is no longer supported.\r\n"
@@ -87,6 +100,141 @@ bugger_off_msg:
.ascii "Remove disk and press any key to reboot . . .\r\n"
.byte 0
+#ifdef CONFIG_EFI_STUB
+pe_header:
+ .ascii "PE"
+ .word 0
+
+coff_header:
+#ifdef CONFIG_X86_32
+ .word 0x14c # i386
+#else
+ .word 0x8664 # x86-64
+#endif
+ .word 2 # nr_sections
+ .long 0 # TimeDateStamp
+ .long 0 # PointerToSymbolTable
+ .long 1 # NumberOfSymbols
+ .word section_table - optional_header # SizeOfOptionalHeader
+#ifdef CONFIG_X86_32
+ .word 0x306 # Characteristics.
+ # IMAGE_FILE_32BIT_MACHINE |
+ # IMAGE_FILE_DEBUG_STRIPPED |
+ # IMAGE_FILE_EXECUTABLE_IMAGE |
+ # IMAGE_FILE_LINE_NUMS_STRIPPED
+#else
+ .word 0x206 # Characteristics
+ # IMAGE_FILE_DEBUG_STRIPPED |
+ # IMAGE_FILE_EXECUTABLE_IMAGE |
+ # IMAGE_FILE_LINE_NUMS_STRIPPED
+#endif
+
+optional_header:
+#ifdef CONFIG_X86_32
+ .word 0x10b # PE32 format
+#else
+ .word 0x20b # PE32+ format
+#endif
+ .byte 0x02 # MajorLinkerVersion
+ .byte 0x14 # MinorLinkerVersion
+
+ # Filled in by build.c
+ .long 0 # SizeOfCode
+
+ .long 0 # SizeOfInitializedData
+ .long 0 # SizeOfUninitializedData
+
+ # Filled in by build.c
+ .long 0x0000 # AddressOfEntryPoint
+
+ .long 0x0000 # BaseOfCode
+#ifdef CONFIG_X86_32
+ .long 0 # data
+#endif
+
+extra_header_fields:
+#ifdef CONFIG_X86_32
+ .long 0 # ImageBase
+#else
+ .quad 0 # ImageBase
+#endif
+ .long 0x1000 # SectionAlignment
+ .long 0x200 # FileAlignment
+ .word 0 # MajorOperatingSystemVersion
+ .word 0 # MinorOperatingSystemVersion
+ .word 0 # MajorImageVersion
+ .word 0 # MinorImageVersion
+ .word 0 # MajorSubsystemVersion
+ .word 0 # MinorSubsystemVersion
+ .long 0 # Win32VersionValue
+
+ #
+ # The size of the bzImage is written in tools/build.c
+ #
+ .long 0 # SizeOfImage
+
+ .long 0x200 # SizeOfHeaders
+ .long 0 # CheckSum
+ .word 0xa # Subsystem (EFI application)
+ .word 0 # DllCharacteristics
+#ifdef CONFIG_X86_32
+ .long 0 # SizeOfStackReserve
+ .long 0 # SizeOfStackCommit
+ .long 0 # SizeOfHeapReserve
+ .long 0 # SizeOfHeapCommit
+#else
+ .quad 0 # SizeOfStackReserve
+ .quad 0 # SizeOfStackCommit
+ .quad 0 # SizeOfHeapReserve
+ .quad 0 # SizeOfHeapCommit
+#endif
+ .long 0 # LoaderFlags
+ .long 0x1 # NumberOfRvaAndSizes
+
+ .quad 0 # ExportTable
+ .quad 0 # ImportTable
+ .quad 0 # ResourceTable
+ .quad 0 # ExceptionTable
+ .quad 0 # CertificationTable
+ .quad 0 # BaseRelocationTable
+
+ # Section table
+section_table:
+ .ascii ".text"
+ .byte 0
+ .byte 0
+ .byte 0
+ .long 0
+ .long 0x0 # startup_{32,64}
+ .long 0 # Size of initialized data
+ # on disk
+ .long 0x0 # startup_{32,64}
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x60500020 # Characteristics (section flags)
+
+ #
+ # The EFI application loader requires a relocation section
+ # because EFI applications are relocatable and not having
+ # this section seems to confuse it. But since we don't need
+ # the loader to fixup any relocs for us just fill it with a
+ # single dummy reloc.
+ #
+ .ascii ".reloc"
+ .byte 0
+ .byte 0
+ .long reloc_end - reloc_start
+ .long reloc_start
+ .long reloc_end - reloc_start # SizeOfRawData
+ .long reloc_start # PointerToRawData
+ .long 0 # PointerToRelocations
+ .long 0 # PointerToLineNumbers
+ .word 0 # NumberOfRelocations
+ .word 0 # NumberOfLineNumbers
+ .long 0x42100040 # Characteristics (section flags)
+#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
# header, from the old boot sector.
@@ -318,3 +466,13 @@ die:
setup_corrupt:
.byte 7
.string "No setup signature found...\n"
+
+ .data
+dummy: .long 0
+
+ .section .reloc
+reloc_start:
+ .long dummy - reloc_start
+ .long 10
+ .word 0
+reloc_end:
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 3cbc4058dd26..574dedfe2890 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -111,3 +111,38 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas
return result;
}
+
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t strlen(const char *s)
+{
+ const char *sc;
+
+ for (sc = s; *sc != '\0'; ++sc)
+ /* nothing */;
+ return sc - s;
+}
+
+/**
+ * strstr - Find the first substring in a %NUL terminated string
+ * @s1: The string to be searched
+ * @s2: The string to search for
+ */
+char *strstr(const char *s1, const char *s2)
+{
+ size_t l1, l2;
+
+ l2 = strlen(s2);
+ if (!l2)
+ return (char *)s1;
+ l1 = strlen(s1);
+ while (l1 >= l2) {
+ l1--;
+ if (!memcmp(s1, s2, l2))
+ return (char *)s1;
+ s1++;
+ }
+ return NULL;
+}
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index fdc60a0b3c20..4e9bd6bcafa6 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -135,6 +135,9 @@ static void usage(void)
int main(int argc, char ** argv)
{
+#ifdef CONFIG_EFI_STUB
+ unsigned int file_sz, pe_header;
+#endif
unsigned int i, sz, setup_sectors;
int c;
u32 sys_size;
@@ -194,6 +197,42 @@ int main(int argc, char ** argv)
buf[0x1f6] = sys_size >> 16;
buf[0x1f7] = sys_size >> 24;
+#ifdef CONFIG_EFI_STUB
+ file_sz = sz + i + ((sys_size * 16) - sz);
+
+ pe_header = *(unsigned int *)&buf[0x3c];
+
+ /* Size of code */
+ *(unsigned int *)&buf[pe_header + 0x1c] = file_sz;
+
+ /* Size of image */
+ *(unsigned int *)&buf[pe_header + 0x50] = file_sz;
+
+#ifdef CONFIG_X86_32
+ /* Address of entry point */
+ *(unsigned int *)&buf[pe_header + 0x28] = i;
+
+ /* .text size */
+ *(unsigned int *)&buf[pe_header + 0xb0] = file_sz;
+
+ /* .text size of initialised data */
+ *(unsigned int *)&buf[pe_header + 0xb8] = file_sz;
+#else
+ /*
+ * Address of entry point. startup_32 is at the beginning and
+ * the 64-bit entry point (startup_64) is always 512 bytes
+ * after.
+ */
+ *(unsigned int *)&buf[pe_header + 0x28] = i + 512;
+
+ /* .text size */
+ *(unsigned int *)&buf[pe_header + 0xc0] = file_sz;
+
+ /* .text size of initialised data */
+ *(unsigned int *)&buf[pe_header + 0xc8] = file_sz;
+#endif /* CONFIG_X86_32 */
+#endif /* CONFIG_EFI_STUB */
+
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, stdout) != i)
die("Writing setup failed");
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 3537d4b91f74..2b0b9631474b 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -5,12 +5,14 @@
obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
+obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
+obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
@@ -20,12 +22,14 @@ obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
aes-i586-y := aes-i586-asm_32.o aes_glue.o
twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
+serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
+serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
new file mode 100644
index 000000000000..4e37677ca851
--- /dev/null
+++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S
@@ -0,0 +1,638 @@
+/*
+ * Serpent Cipher 4-way parallel algorithm (i586/SSE2)
+ *
+ * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on crypto/serpent.c by
+ * Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no>
+ * 2003 Herbert Valerio Riedel <hvr@gnu.org>
+ *
+ * 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.
+ *
+ * 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
+ *
+ */
+
+.file "serpent-sse2-i586-asm_32.S"
+.text
+
+#define arg_ctx 4
+#define arg_dst 8
+#define arg_src 12
+#define arg_xor 16
+
+/**********************************************************************
+ 4-way SSE2 serpent
+ **********************************************************************/
+#define CTX %edx
+
+#define RA %xmm0
+#define RB %xmm1
+#define RC %xmm2
+#define RD %xmm3
+#define RE %xmm4
+
+#define RT0 %xmm5
+#define RT1 %xmm6
+
+#define RNOT %xmm7
+
+#define get_key(i, j, t) \
+ movd (4*(i)+(j))*4(CTX), t; \
+ pshufd $0, t, t;
+
+#define K(x0, x1, x2, x3, x4, i) \
+ get_key(i, 0, x4); \
+ get_key(i, 1, RT0); \
+ get_key(i, 2, RT1); \
+ pxor x4, x0; \
+ pxor RT0, x1; \
+ pxor RT1, x2; \
+ get_key(i, 3, x4); \
+ pxor x4, x3;
+
+#define LK(x0, x1, x2, x3, x4, i) \
+ movdqa x0, x4; \
+ pslld $13, x0; \
+ psrld $(32 - 13), x4; \
+ por x4, x0; \
+ pxor x0, x1; \
+ movdqa x2, x4; \
+ pslld $3, x2; \
+ psrld $(32 - 3), x4; \
+ por x4, x2; \
+ pxor x2, x1; \
+ movdqa x1, x4; \
+ pslld $1, x1; \
+ psrld $(32 - 1), x4; \
+ por x4, x1; \
+ movdqa x0, x4; \
+ pslld $3, x4; \
+ pxor x2, x3; \
+ pxor x4, x3; \
+ movdqa x3, x4; \
+ pslld $7, x3; \
+ psrld $(32 - 7), x4; \
+ por x4, x3; \
+ movdqa x1, x4; \
+ pslld $7, x4; \
+ pxor x1, x0; \
+ pxor x3, x0; \
+ pxor x3, x2; \
+ pxor x4, x2; \
+ movdqa x0, x4; \
+ get_key(i, 1, RT0); \
+ pxor RT0, x1; \
+ get_key(i, 3, RT0); \
+ pxor RT0, x3; \
+ pslld $5, x0; \
+ psrld $(32 - 5), x4; \
+ por x4, x0; \
+ movdqa x2, x4; \
+ pslld $22, x2; \
+ psrld $(32 - 22), x4; \
+ por x4, x2; \
+ get_key(i, 0, RT0); \
+ pxor RT0, x0; \
+ get_key(i, 2, RT0); \
+ pxor RT0, x2;
+
+#define KL(x0, x1, x2, x3, x4, i) \
+ K(x0, x1, x2, x3, x4, i); \
+ movdqa x0, x4; \
+ psrld $5, x0; \
+ pslld $(32 - 5), x4; \
+ por x4, x0; \
+ movdqa x2, x4; \
+ psrld $22, x2; \
+ pslld $(32 - 22), x4; \
+ por x4, x2; \
+ pxor x3, x2; \
+ pxor x3, x0; \
+ movdqa x1, x4; \
+ pslld $7, x4; \
+ pxor x1, x0; \
+ pxor x4, x2; \
+ movdqa x1, x4; \
+ psrld $1, x1; \
+ pslld $(32 - 1), x4; \
+ por x4, x1; \
+ movdqa x3, x4; \
+ psrld $7, x3; \
+ pslld $(32 - 7), x4; \
+ por x4, x3; \
+ pxor x0, x1; \
+ movdqa x0, x4; \
+ pslld $3, x4; \
+ pxor x4, x3; \
+ movdqa x0, x4; \
+ psrld $13, x0; \
+ pslld $(32 - 13), x4; \
+ por x4, x0; \
+ pxor x2, x1; \
+ pxor x2, x3; \
+ movdqa x2, x4; \
+ psrld $3, x2; \
+ pslld $(32 - 3), x4; \
+ por x4, x2;
+
+#define S0(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ por x0, x3; \
+ pxor x4, x0; \
+ pxor x2, x4; \
+ pxor RNOT, x4; \
+ pxor x1, x3; \
+ pand x0, x1; \
+ pxor x4, x1; \
+ pxor x0, x2; \
+ pxor x3, x0; \
+ por x0, x4; \
+ pxor x2, x0; \
+ pand x1, x2; \
+ pxor x2, x3; \
+ pxor RNOT, x1; \
+ pxor x4, x2; \
+ pxor x2, x1;
+
+#define S1(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ pxor x0, x1; \
+ pxor x3, x0; \
+ pxor RNOT, x3; \
+ pand x1, x4; \
+ por x1, x0; \
+ pxor x2, x3; \
+ pxor x3, x0; \
+ pxor x3, x1; \
+ pxor x4, x3; \
+ por x4, x1; \
+ pxor x2, x4; \
+ pand x0, x2; \
+ pxor x1, x2; \
+ por x0, x1; \
+ pxor RNOT, x0; \
+ pxor x2, x0; \
+ pxor x1, x4;
+
+#define S2(x0, x1, x2, x3, x4) \
+ pxor RNOT, x3; \
+ pxor x0, x1; \
+ movdqa x0, x4; \
+ pand x2, x0; \
+ pxor x3, x0; \
+ por x4, x3; \
+ pxor x1, x2; \
+ pxor x1, x3; \
+ pand x0, x1; \
+ pxor x2, x0; \
+ pand x3, x2; \
+ por x1, x3; \
+ pxor RNOT, x0; \
+ pxor x0, x3; \
+ pxor x0, x4; \
+ pxor x2, x0; \
+ por x2, x1;
+
+#define S3(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ pxor x3, x1; \
+ por x0, x3; \
+ pand x0, x4; \
+ pxor x2, x0; \
+ pxor x1, x2; \
+ pand x3, x1; \
+ pxor x3, x2; \
+ por x4, x0; \
+ pxor x3, x4; \
+ pxor x0, x1; \
+ pand x3, x0; \
+ pand x4, x3; \
+ pxor x2, x3; \
+ por x1, x4; \
+ pand x1, x2; \
+ pxor x3, x4; \
+ pxor x3, x0; \
+ pxor x2, x3;
+
+#define S4(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ pand x0, x3; \
+ pxor x4, x0; \
+ pxor x2, x3; \
+ por x4, x2; \
+ pxor x1, x0; \
+ pxor x3, x4; \
+ por x0, x2; \
+ pxor x1, x2; \
+ pand x0, x1; \
+ pxor x4, x1; \
+ pand x2, x4; \
+ pxor x3, x2; \
+ pxor x0, x4; \
+ por x1, x3; \
+ pxor RNOT, x1; \
+ pxor x0, x3;
+
+#define S5(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ por x0, x1; \
+ pxor x1, x2; \
+ pxor RNOT, x3; \
+ pxor x0, x4; \
+ pxor x2, x0; \
+ pand x4, x1; \
+ por x3, x4; \
+ pxor x0, x4; \
+ pand x3, x0; \
+ pxor x3, x1; \
+ pxor x2, x3; \
+ pxor x1, x0; \
+ pand x4, x2; \
+ pxor x2, x1; \
+ pand x0, x2; \
+ pxor x2, x3;
+
+#define S6(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ pxor x0, x3; \
+ pxor x2, x1; \
+ pxor x0, x2; \
+ pand x3, x0; \
+ por x3, x1; \
+ pxor RNOT, x4; \
+ pxor x1, x0; \
+ pxor x2, x1; \
+ pxor x4, x3; \
+ pxor x0, x4; \
+ pand x0, x2; \
+ pxor x1, x4; \
+ pxor x3, x2; \
+ pand x1, x3; \
+ pxor x0, x3; \
+ pxor x2, x1;
+
+#define S7(x0, x1, x2, x3, x4) \
+ pxor RNOT, x1; \
+ movdqa x1, x4; \
+ pxor RNOT, x0; \
+ pand x2, x1; \
+ pxor x3, x1; \
+ por x4, x3; \
+ pxor x2, x4; \
+ pxor x3, x2; \
+ pxor x0, x3; \
+ por x1, x0; \
+ pand x0, x2; \
+ pxor x4, x0; \
+ pxor x3, x4; \
+ pand x0, x3; \
+ pxor x1, x4; \
+ pxor x4, x2; \
+ pxor x1, x3; \
+ por x0, x4; \
+ pxor x1, x4;
+
+#define SI0(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ pxor x0, x1; \
+ por x1, x3; \
+ pxor x1, x4; \
+ pxor RNOT, x0; \
+ pxor x3, x2; \
+ pxor x0, x3; \
+ pand x1, x0; \
+ pxor x2, x0; \
+ pand x3, x2; \
+ pxor x4, x3; \
+ pxor x3, x2; \
+ pxor x3, x1; \
+ pand x0, x3; \
+ pxor x0, x1; \
+ pxor x2, x0; \
+ pxor x3, x4;
+
+#define SI1(x0, x1, x2, x3, x4) \
+ pxor x3, x1; \
+ movdqa x0, x4; \
+ pxor x2, x0; \
+ pxor RNOT, x2; \
+ por x1, x4; \
+ pxor x3, x4; \
+ pand x1, x3; \
+ pxor x2, x1; \
+ pand x4, x2; \
+ pxor x1, x4; \
+ por x3, x1; \
+ pxor x0, x3; \
+ pxor x0, x2; \
+ por x4, x0; \
+ pxor x4, x2; \
+ pxor x0, x1; \
+ pxor x1, x4;
+
+#define SI2(x0, x1, x2, x3, x4) \
+ pxor x1, x2; \
+ movdqa x3, x4; \
+ pxor RNOT, x3; \
+ por x2, x3; \
+ pxor x4, x2; \
+ pxor x0, x4; \
+ pxor x1, x3; \
+ por x2, x1; \
+ pxor x0, x2; \
+ pxor x4, x1; \
+ por x3, x4; \
+ pxor x3, x2; \
+ pxor x2, x4; \
+ pand x1, x2; \
+ pxor x3, x2; \
+ pxor x4, x3; \
+ pxor x0, x4;
+
+#define SI3(x0, x1, x2, x3, x4) \
+ pxor x1, x2; \
+ movdqa x1, x4; \
+ pand x2, x1; \
+ pxor x0, x1; \
+ por x4, x0; \
+ pxor x3, x4; \
+ pxor x3, x0; \
+ por x1, x3; \
+ pxor x2, x1; \
+ pxor x3, x1; \
+ pxor x2, x0; \
+ pxor x3, x2; \
+ pand x1, x3; \
+ pxor x0, x1; \
+ pand x2, x0; \
+ pxor x3, x4; \
+ pxor x0, x3; \
+ pxor x1, x0;
+
+#define SI4(x0, x1, x2, x3, x4) \
+ pxor x3, x2; \
+ movdqa x0, x4; \
+ pand x1, x0; \
+ pxor x2, x0; \
+ por x3, x2; \
+ pxor RNOT, x4; \
+ pxor x0, x1; \
+ pxor x2, x0; \
+ pand x4, x2; \
+ pxor x0, x2; \
+ por x4, x0; \
+ pxor x3, x0; \
+ pand x2, x3; \
+ pxor x3, x4; \
+ pxor x1, x3; \
+ pand x0, x1; \
+ pxor x1, x4; \
+ pxor x3, x0;
+
+#define SI5(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ por x2, x1; \
+ pxor x4, x2; \
+ pxor x3, x1; \
+ pand x4, x3; \
+ pxor x3, x2; \
+ por x0, x3; \
+ pxor RNOT, x0; \
+ pxor x2, x3; \
+ por x0, x2; \
+ pxor x1, x4; \
+ pxor x4, x2; \
+ pand x0, x4; \
+ pxor x1, x0; \
+ pxor x3, x1; \
+ pand x2, x0; \
+ pxor x3, x2; \
+ pxor x2, x0; \
+ pxor x4, x2; \
+ pxor x3, x4;
+
+#define SI6(x0, x1, x2, x3, x4) \
+ pxor x2, x0; \
+ movdqa x0, x4; \
+ pand x3, x0; \
+ pxor x3, x2; \
+ pxor x2, x0; \
+ pxor x1, x3; \
+ por x4, x2; \
+ pxor x3, x2; \
+ pand x0, x3; \
+ pxor RNOT, x0; \
+ pxor x1, x3; \
+ pand x2, x1; \
+ pxor x0, x4; \
+ pxor x4, x3; \
+ pxor x2, x4; \
+ pxor x1, x0; \
+ pxor x0, x2;
+
+#define SI7(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ pand x0, x3; \
+ pxor x2, x0; \
+ por x4, x2; \
+ pxor x1, x4; \
+ pxor RNOT, x0; \
+ por x3, x1; \
+ pxor x0, x4; \
+ pand x2, x0; \
+ pxor x1, x0; \
+ pand x2, x1; \
+ pxor x2, x3; \
+ pxor x3, x4; \
+ pand x3, x2; \
+ por x0, x3; \
+ pxor x4, x1; \
+ pxor x4, x3; \
+ pand x0, x4; \
+ pxor x2, x4;
+
+#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \
+ movdqa x2, t3; \
+ movdqa x0, t1; \
+ unpcklps x3, t3; \
+ movdqa x0, t2; \
+ unpcklps x1, t1; \
+ unpckhps x1, t2; \
+ movdqa t3, x1; \
+ unpckhps x3, x2; \
+ movdqa t1, x0; \
+ movhlps t1, x1; \
+ movdqa t2, t1; \
+ movlhps t3, x0; \
+ movlhps x2, t1; \
+ movhlps t2, x2; \
+ movdqa x2, x3; \
+ movdqa t1, x2;
+
+#define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \
+ movdqu (0*4*4)(in), x0; \
+ movdqu (1*4*4)(in), x1; \
+ movdqu (2*4*4)(in), x2; \
+ movdqu (3*4*4)(in), x3; \
+ \
+ transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define write_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+ \
+ movdqu x0, (0*4*4)(out); \
+ movdqu x1, (1*4*4)(out); \
+ movdqu x2, (2*4*4)(out); \
+ movdqu x3, (3*4*4)(out);
+
+#define xor_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+ \
+ movdqu (0*4*4)(out), t0; \
+ pxor t0, x0; \
+ movdqu x0, (0*4*4)(out); \
+ movdqu (1*4*4)(out), t0; \
+ pxor t0, x1; \
+ movdqu x1, (1*4*4)(out); \
+ movdqu (2*4*4)(out), t0; \
+ pxor t0, x2; \
+ movdqu x2, (2*4*4)(out); \
+ movdqu (3*4*4)(out), t0; \
+ pxor t0, x3; \
+ movdqu x3, (3*4*4)(out);
+
+.align 8
+.global __serpent_enc_blk_4way
+.type __serpent_enc_blk_4way,@function;
+
+__serpent_enc_blk_4way:
+ /* input:
+ * arg_ctx(%esp): ctx, CTX
+ * arg_dst(%esp): dst
+ * arg_src(%esp): src
+ * arg_xor(%esp): bool, if true: xor output
+ */
+
+ pcmpeqd RNOT, RNOT;
+
+ movl arg_ctx(%esp), CTX;
+
+ movl arg_src(%esp), %eax;
+ read_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+ K(RA, RB, RC, RD, RE, 0);
+ S0(RA, RB, RC, RD, RE); LK(RC, RB, RD, RA, RE, 1);
+ S1(RC, RB, RD, RA, RE); LK(RE, RD, RA, RC, RB, 2);
+ S2(RE, RD, RA, RC, RB); LK(RB, RD, RE, RC, RA, 3);
+ S3(RB, RD, RE, RC, RA); LK(RC, RA, RD, RB, RE, 4);
+ S4(RC, RA, RD, RB, RE); LK(RA, RD, RB, RE, RC, 5);
+ S5(RA, RD, RB, RE, RC); LK(RC, RA, RD, RE, RB, 6);
+ S6(RC, RA, RD, RE, RB); LK(RD, RB, RA, RE, RC, 7);
+ S7(RD, RB, RA, RE, RC); LK(RC, RA, RE, RD, RB, 8);
+ S0(RC, RA, RE, RD, RB); LK(RE, RA, RD, RC, RB, 9);
+ S1(RE, RA, RD, RC, RB); LK(RB, RD, RC, RE, RA, 10);
+ S2(RB, RD, RC, RE, RA); LK(RA, RD, RB, RE, RC, 11);
+ S3(RA, RD, RB, RE, RC); LK(RE, RC, RD, RA, RB, 12);
+ S4(RE, RC, RD, RA, RB); LK(RC, RD, RA, RB, RE, 13);
+ S5(RC, RD, RA, RB, RE); LK(RE, RC, RD, RB, RA, 14);
+ S6(RE, RC, RD, RB, RA); LK(RD, RA, RC, RB, RE, 15);
+ S7(RD, RA, RC, RB, RE); LK(RE, RC, RB, RD, RA, 16);
+ S0(RE, RC, RB, RD, RA); LK(RB, RC, RD, RE, RA, 17);
+ S1(RB, RC, RD, RE, RA); LK(RA, RD, RE, RB, RC, 18);
+ S2(RA, RD, RE, RB, RC); LK(RC, RD, RA, RB, RE, 19);
+ S3(RC, RD, RA, RB, RE); LK(RB, RE, RD, RC, RA, 20);
+ S4(RB, RE, RD, RC, RA); LK(RE, RD, RC, RA, RB, 21);
+ S5(RE, RD, RC, RA, RB); LK(RB, RE, RD, RA, RC, 22);
+ S6(RB, RE, RD, RA, RC); LK(RD, RC, RE, RA, RB, 23);
+ S7(RD, RC, RE, RA, RB); LK(RB, RE, RA, RD, RC, 24);
+ S0(RB, RE, RA, RD, RC); LK(RA, RE, RD, RB, RC, 25);
+ S1(RA, RE, RD, RB, RC); LK(RC, RD, RB, RA, RE, 26);
+ S2(RC, RD, RB, RA, RE); LK(RE, RD, RC, RA, RB, 27);
+ S3(RE, RD, RC, RA, RB); LK(RA, RB, RD, RE, RC, 28);
+ S4(RA, RB, RD, RE, RC); LK(RB, RD, RE, RC, RA, 29);
+ S5(RB, RD, RE, RC, RA); LK(RA, RB, RD, RC, RE, 30);
+ S6(RA, RB, RD, RC, RE); LK(RD, RE, RB, RC, RA, 31);
+ S7(RD, RE, RB, RC, RA); K(RA, RB, RC, RD, RE, 32);
+
+ movl arg_dst(%esp), %eax;
+
+ cmpb $0, arg_xor(%esp);
+ jnz __enc_xor4;
+
+ write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+ ret;
+
+__enc_xor4:
+ xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+ ret;
+
+.align 8
+.global serpent_dec_blk_4way
+.type serpent_dec_blk_4way,@function;
+
+serpent_dec_blk_4way:
+ /* input:
+ * arg_ctx(%esp): ctx, CTX
+ * arg_dst(%esp): dst
+ * arg_src(%esp): src
+ */
+
+ pcmpeqd RNOT, RNOT;
+
+ movl arg_ctx(%esp), CTX;
+
+ movl arg_src(%esp), %eax;
+ read_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);
+
+ K(RA, RB, RC, RD, RE, 32);
+ SI7(RA, RB, RC, RD, RE); KL(RB, RD, RA, RE, RC, 31);
+ SI6(RB, RD, RA, RE, RC); KL(RA, RC, RE, RB, RD, 30);
+ SI5(RA, RC, RE, RB, RD); KL(RC, RD, RA, RE, RB, 29);
+ SI4(RC, RD, RA, RE, RB); KL(RC, RA, RB, RE, RD, 28);
+ SI3(RC, RA, RB, RE, RD); KL(RB, RC, RD, RE, RA, 27);
+ SI2(RB, RC, RD, RE, RA); KL(RC, RA, RE, RD, RB, 26);
+ SI1(RC, RA, RE, RD, RB); KL(RB, RA, RE, RD, RC, 25);
+ SI0(RB, RA, RE, RD, RC); KL(RE, RC, RA, RB, RD, 24);
+ SI7(RE, RC, RA, RB, RD); KL(RC, RB, RE, RD, RA, 23);
+ SI6(RC, RB, RE, RD, RA); KL(RE, RA, RD, RC, RB, 22);
+ SI5(RE, RA, RD, RC, RB); KL(RA, RB, RE, RD, RC, 21);
+ SI4(RA, RB, RE, RD, RC); KL(RA, RE, RC, RD, RB, 20);
+ SI3(RA, RE, RC, RD, RB); KL(RC, RA, RB, RD, RE, 19);
+ SI2(RC, RA, RB, RD, RE); KL(RA, RE, RD, RB, RC, 18);
+ SI1(RA, RE, RD, RB, RC); KL(RC, RE, RD, RB, RA, 17);
+ SI0(RC, RE, RD, RB, RA); KL(RD, RA, RE, RC, RB, 16);
+ SI7(RD, RA, RE, RC, RB); KL(RA, RC, RD, RB, RE, 15);
+ SI6(RA, RC, RD, RB, RE); KL(RD, RE, RB, RA, RC, 14);
+ SI5(RD, RE, RB, RA, RC); KL(RE, RC, RD, RB, RA, 13);
+ SI4(RE, RC, RD, RB, RA); KL(RE, RD, RA, RB, RC, 12);
+ SI3(RE, RD, RA, RB, RC); KL(RA, RE, RC, RB, RD, 11);
+ SI2(RA, RE, RC, RB, RD); KL(RE, RD, RB, RC, RA, 10);
+ SI1(RE, RD, RB, RC, RA); KL(RA, RD, RB, RC, RE, 9);
+ SI0(RA, RD, RB, RC, RE); KL(RB, RE, RD, RA, RC, 8);
+ SI7(RB, RE, RD, RA, RC); KL(RE, RA, RB, RC, RD, 7);
+ SI6(RE, RA, RB, RC, RD); KL(RB, RD, RC, RE, RA, 6);
+ SI5(RB, RD, RC, RE, RA); KL(RD, RA, RB, RC, RE, 5);
+ SI4(RD, RA, RB, RC, RE); KL(RD, RB, RE, RC, RA, 4);
+ SI3(RD, RB, RE, RC, RA); KL(RE, RD, RA, RC, RB, 3);
+ SI2(RE, RD, RA, RC, RB); KL(RD, RB, RC, RA, RE, 2);
+ SI1(RD, RB, RC, RA, RE); KL(RE, RB, RC, RA, RD, 1);
+ SI0(RE, RB, RC, RA, RD); K(RC, RD, RB, RE, RA, 0);
+
+ movl arg_dst(%esp), %eax;
+ write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);
+
+ ret;
diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
new file mode 100644
index 000000000000..7f24a1540821
--- /dev/null
+++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S
@@ -0,0 +1,761 @@
+/*
+ * Serpent Cipher 8-way parallel algorithm (x86_64/SSE2)
+ *
+ * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on crypto/serpent.c by
+ * Copyright (C) 2002 Dag Arne Osvik <osvik@ii.uib.no>
+ * 2003 Herbert Valerio Riedel <hvr@gnu.org>
+ *
+ * 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.
+ *
+ * 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
+ *
+ */
+
+.file "serpent-sse2-x86_64-asm_64.S"
+.text
+
+#define CTX %rdi
+
+/**********************************************************************
+ 8-way SSE2 serpent
+ **********************************************************************/
+#define RA1 %xmm0
+#define RB1 %xmm1
+#define RC1 %xmm2
+#define RD1 %xmm3
+#define RE1 %xmm4
+
+#define RA2 %xmm5
+#define RB2 %xmm6
+#define RC2 %xmm7
+#define RD2 %xmm8
+#define RE2 %xmm9
+
+#define RNOT %xmm10
+
+#define RK0 %xmm11
+#define RK1 %xmm12
+#define RK2 %xmm13
+#define RK3 %xmm14
+
+#define S0_1(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ por x0, x3; \
+ pxor x4, x0; \
+ pxor x2, x4; \
+ pxor RNOT, x4; \
+ pxor x1, x3; \
+ pand x0, x1; \
+ pxor x4, x1; \
+ pxor x0, x2;
+#define S0_2(x0, x1, x2, x3, x4) \
+ pxor x3, x0; \
+ por x0, x4; \
+ pxor x2, x0; \
+ pand x1, x2; \
+ pxor x2, x3; \
+ pxor RNOT, x1; \
+ pxor x4, x2; \
+ pxor x2, x1;
+
+#define S1_1(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ pxor x0, x1; \
+ pxor x3, x0; \
+ pxor RNOT, x3; \
+ pand x1, x4; \
+ por x1, x0; \
+ pxor x2, x3; \
+ pxor x3, x0; \
+ pxor x3, x1;
+#define S1_2(x0, x1, x2, x3, x4) \
+ pxor x4, x3; \
+ por x4, x1; \
+ pxor x2, x4; \
+ pand x0, x2; \
+ pxor x1, x2; \
+ por x0, x1; \
+ pxor RNOT, x0; \
+ pxor x2, x0; \
+ pxor x1, x4;
+
+#define S2_1(x0, x1, x2, x3, x4) \
+ pxor RNOT, x3; \
+ pxor x0, x1; \
+ movdqa x0, x4; \
+ pand x2, x0; \
+ pxor x3, x0; \
+ por x4, x3; \
+ pxor x1, x2; \
+ pxor x1, x3; \
+ pand x0, x1;
+#define S2_2(x0, x1, x2, x3, x4) \
+ pxor x2, x0; \
+ pand x3, x2; \
+ por x1, x3; \
+ pxor RNOT, x0; \
+ pxor x0, x3; \
+ pxor x0, x4; \
+ pxor x2, x0; \
+ por x2, x1;
+
+#define S3_1(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ pxor x3, x1; \
+ por x0, x3; \
+ pand x0, x4; \
+ pxor x2, x0; \
+ pxor x1, x2; \
+ pand x3, x1; \
+ pxor x3, x2; \
+ por x4, x0; \
+ pxor x3, x4;
+#define S3_2(x0, x1, x2, x3, x4) \
+ pxor x0, x1; \
+ pand x3, x0; \
+ pand x4, x3; \
+ pxor x2, x3; \
+ por x1, x4; \
+ pand x1, x2; \
+ pxor x3, x4; \
+ pxor x3, x0; \
+ pxor x2, x3;
+
+#define S4_1(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ pand x0, x3; \
+ pxor x4, x0; \
+ pxor x2, x3; \
+ por x4, x2; \
+ pxor x1, x0; \
+ pxor x3, x4; \
+ por x0, x2; \
+ pxor x1, x2;
+#define S4_2(x0, x1, x2, x3, x4) \
+ pand x0, x1; \
+ pxor x4, x1; \
+ pand x2, x4; \
+ pxor x3, x2; \
+ pxor x0, x4; \
+ por x1, x3; \
+ pxor RNOT, x1; \
+ pxor x0, x3;
+
+#define S5_1(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ por x0, x1; \
+ pxor x1, x2; \
+ pxor RNOT, x3; \
+ pxor x0, x4; \
+ pxor x2, x0; \
+ pand x4, x1; \
+ por x3, x4; \
+ pxor x0, x4;
+#define S5_2(x0, x1, x2, x3, x4) \
+ pand x3, x0; \
+ pxor x3, x1; \
+ pxor x2, x3; \
+ pxor x1, x0; \
+ pand x4, x2; \
+ pxor x2, x1; \
+ pand x0, x2; \
+ pxor x2, x3;
+
+#define S6_1(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ pxor x0, x3; \
+ pxor x2, x1; \
+ pxor x0, x2; \
+ pand x3, x0; \
+ por x3, x1; \
+ pxor RNOT, x4; \
+ pxor x1, x0; \
+ pxor x2, x1;
+#define S6_2(x0, x1, x2, x3, x4) \
+ pxor x4, x3; \
+ pxor x0, x4; \
+ pand x0, x2; \
+ pxor x1, x4; \
+ pxor x3, x2; \
+ pand x1, x3; \
+ pxor x0, x3; \
+ pxor x2, x1;
+
+#define S7_1(x0, x1, x2, x3, x4) \
+ pxor RNOT, x1; \
+ movdqa x1, x4; \
+ pxor RNOT, x0; \
+ pand x2, x1; \
+ pxor x3, x1; \
+ por x4, x3; \
+ pxor x2, x4; \
+ pxor x3, x2; \
+ pxor x0, x3; \
+ por x1, x0;
+#define S7_2(x0, x1, x2, x3, x4) \
+ pand x0, x2; \
+ pxor x4, x0; \
+ pxor x3, x4; \
+ pand x0, x3; \
+ pxor x1, x4; \
+ pxor x4, x2; \
+ pxor x1, x3; \
+ por x0, x4; \
+ pxor x1, x4;
+
+#define SI0_1(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ pxor x0, x1; \
+ por x1, x3; \
+ pxor x1, x4; \
+ pxor RNOT, x0; \
+ pxor x3, x2; \
+ pxor x0, x3; \
+ pand x1, x0; \
+ pxor x2, x0;
+#define SI0_2(x0, x1, x2, x3, x4) \
+ pand x3, x2; \
+ pxor x4, x3; \
+ pxor x3, x2; \
+ pxor x3, x1; \
+ pand x0, x3; \
+ pxor x0, x1; \
+ pxor x2, x0; \
+ pxor x3, x4;
+
+#define SI1_1(x0, x1, x2, x3, x4) \
+ pxor x3, x1; \
+ movdqa x0, x4; \
+ pxor x2, x0; \
+ pxor RNOT, x2; \
+ por x1, x4; \
+ pxor x3, x4; \
+ pand x1, x3; \
+ pxor x2, x1; \
+ pand x4, x2;
+#define SI1_2(x0, x1, x2, x3, x4) \
+ pxor x1, x4; \
+ por x3, x1; \
+ pxor x0, x3; \
+ pxor x0, x2; \
+ por x4, x0; \
+ pxor x4, x2; \
+ pxor x0, x1; \
+ pxor x1, x4;
+
+#define SI2_1(x0, x1, x2, x3, x4) \
+ pxor x1, x2; \
+ movdqa x3, x4; \
+ pxor RNOT, x3; \
+ por x2, x3; \
+ pxor x4, x2; \
+ pxor x0, x4; \
+ pxor x1, x3; \
+ por x2, x1; \
+ pxor x0, x2;
+#define SI2_2(x0, x1, x2, x3, x4) \
+ pxor x4, x1; \
+ por x3, x4; \
+ pxor x3, x2; \
+ pxor x2, x4; \
+ pand x1, x2; \
+ pxor x3, x2; \
+ pxor x4, x3; \
+ pxor x0, x4;
+
+#define SI3_1(x0, x1, x2, x3, x4) \
+ pxor x1, x2; \
+ movdqa x1, x4; \
+ pand x2, x1; \
+ pxor x0, x1; \
+ por x4, x0; \
+ pxor x3, x4; \
+ pxor x3, x0; \
+ por x1, x3; \
+ pxor x2, x1;
+#define SI3_2(x0, x1, x2, x3, x4) \
+ pxor x3, x1; \
+ pxor x2, x0; \
+ pxor x3, x2; \
+ pand x1, x3; \
+ pxor x0, x1; \
+ pand x2, x0; \
+ pxor x3, x4; \
+ pxor x0, x3; \
+ pxor x1, x0;
+
+#define SI4_1(x0, x1, x2, x3, x4) \
+ pxor x3, x2; \
+ movdqa x0, x4; \
+ pand x1, x0; \
+ pxor x2, x0; \
+ por x3, x2; \
+ pxor RNOT, x4; \
+ pxor x0, x1; \
+ pxor x2, x0; \
+ pand x4, x2;
+#define SI4_2(x0, x1, x2, x3, x4) \
+ pxor x0, x2; \
+ por x4, x0; \
+ pxor x3, x0; \
+ pand x2, x3; \
+ pxor x3, x4; \
+ pxor x1, x3; \
+ pand x0, x1; \
+ pxor x1, x4; \
+ pxor x3, x0;
+
+#define SI5_1(x0, x1, x2, x3, x4) \
+ movdqa x1, x4; \
+ por x2, x1; \
+ pxor x4, x2; \
+ pxor x3, x1; \
+ pand x4, x3; \
+ pxor x3, x2; \
+ por x0, x3; \
+ pxor RNOT, x0; \
+ pxor x2, x3; \
+ por x0, x2;
+#define SI5_2(x0, x1, x2, x3, x4) \
+ pxor x1, x4; \
+ pxor x4, x2; \
+ pand x0, x4; \
+ pxor x1, x0; \
+ pxor x3, x1; \
+ pand x2, x0; \
+ pxor x3, x2; \
+ pxor x2, x0; \
+ pxor x4, x2; \
+ pxor x3, x4;
+
+#define SI6_1(x0, x1, x2, x3, x4) \
+ pxor x2, x0; \
+ movdqa x0, x4; \
+ pand x3, x0; \
+ pxor x3, x2; \
+ pxor x2, x0; \
+ pxor x1, x3; \
+ por x4, x2; \
+ pxor x3, x2; \
+ pand x0, x3;
+#define SI6_2(x0, x1, x2, x3, x4) \
+ pxor RNOT, x0; \
+ pxor x1, x3; \
+ pand x2, x1; \
+ pxor x0, x4; \
+ pxor x4, x3; \
+ pxor x2, x4; \
+ pxor x1, x0; \
+ pxor x0, x2;
+
+#define SI7_1(x0, x1, x2, x3, x4) \
+ movdqa x3, x4; \
+ pand x0, x3; \
+ pxor x2, x0; \
+ por x4, x2; \
+ pxor x1, x4; \
+ pxor RNOT, x0; \
+ por x3, x1; \
+ pxor x0, x4; \
+ pand x2, x0; \
+ pxor x1, x0;
+#define SI7_2(x0, x1, x2, x3, x4) \
+ pand x2, x1; \
+ pxor x2, x3; \
+ pxor x3, x4; \
+ pand x3, x2; \
+ por x0, x3; \
+ pxor x4, x1; \
+ pxor x4, x3; \
+ pand x0, x4; \
+ pxor x2, x4;
+
+#define get_key(i, j, t) \
+ movd (4*(i)+(j))*4(CTX), t; \
+ pshufd $0, t, t;
+
+#define K2(x0, x1, x2, x3, x4, i) \
+ get_key(i, 0, RK0); \
+ get_key(i, 1, RK1); \
+ get_key(i, 2, RK2); \
+ get_key(i, 3, RK3); \
+ pxor RK0, x0 ## 1; \
+ pxor RK1, x1 ## 1; \
+ pxor RK2, x2 ## 1; \
+ pxor RK3, x3 ## 1; \
+ pxor RK0, x0 ## 2; \
+ pxor RK1, x1 ## 2; \
+ pxor RK2, x2 ## 2; \
+ pxor RK3, x3 ## 2;
+
+#define LK2(x0, x1, x2, x3, x4, i) \
+ movdqa x0 ## 1, x4 ## 1; \
+ pslld $13, x0 ## 1; \
+ psrld $(32 - 13), x4 ## 1; \
+ por x4 ## 1, x0 ## 1; \
+ pxor x0 ## 1, x1 ## 1; \
+ movdqa x2 ## 1, x4 ## 1; \
+ pslld $3, x2 ## 1; \
+ psrld $(32 - 3), x4 ## 1; \
+ por x4 ## 1, x2 ## 1; \
+ pxor x2 ## 1, x1 ## 1; \
+ movdqa x0 ## 2, x4 ## 2; \
+ pslld $13, x0 ## 2; \
+ psrld $(32 - 13), x4 ## 2; \
+ por x4 ## 2, x0 ## 2; \
+ pxor x0 ## 2, x1 ## 2; \
+ movdqa x2 ## 2, x4 ## 2; \
+ pslld $3, x2 ## 2; \
+ psrld $(32 - 3), x4 ## 2; \
+ por x4 ## 2, x2 ## 2; \
+ pxor x2 ## 2, x1 ## 2; \
+ movdqa x1 ## 1, x4 ## 1; \
+ pslld $1, x1 ## 1; \
+ psrld $(32 - 1), x4 ## 1; \
+ por x4 ## 1, x1 ## 1; \
+ movdqa x0 ## 1, x4 ## 1; \
+ pslld $3, x4 ## 1; \
+ pxor x2 ## 1, x3 ## 1; \
+ pxor x4 ## 1, x3 ## 1; \
+ movdqa x3 ## 1, x4 ## 1; \
+ get_key(i, 1, RK1); \
+ movdqa x1 ## 2, x4 ## 2; \
+ pslld $1, x1 ## 2; \
+ psrld $(32 - 1), x4 ## 2; \
+ por x4 ## 2, x1 ## 2; \
+ movdqa x0 ## 2, x4 ## 2; \
+ pslld $3, x4 ## 2; \
+ pxor x2 ## 2, x3 ## 2; \
+ pxor x4 ## 2, x3 ## 2; \
+ movdqa x3 ## 2, x4 ## 2; \
+ get_key(i, 3, RK3); \
+ pslld $7, x3 ## 1; \
+ psrld $(32 - 7), x4 ## 1; \
+ por x4 ## 1, x3 ## 1; \
+ movdqa x1 ## 1, x4 ## 1; \
+ pslld $7, x4 ## 1; \
+ pxor x1 ## 1, x0 ## 1; \
+ pxor x3 ## 1, x0 ## 1; \
+ pxor x3 ## 1, x2 ## 1; \
+ pxor x4 ## 1, x2 ## 1; \
+ get_key(i, 0, RK0); \
+ pslld $7, x3 ## 2; \
+ psrld $(32 - 7), x4 ## 2; \
+ por x4 ## 2, x3 ## 2; \
+ movdqa x1 ## 2, x4 ## 2; \
+ pslld $7, x4 ## 2; \
+ pxor x1 ## 2, x0 ## 2; \
+ pxor x3 ## 2, x0 ## 2; \
+ pxor x3 ## 2, x2 ## 2; \
+ pxor x4 ## 2, x2 ## 2; \
+ get_key(i, 2, RK2); \
+ pxor RK1, x1 ## 1; \
+ pxor RK3, x3 ## 1; \
+ movdqa x0 ## 1, x4 ## 1; \
+ pslld $5, x0 ## 1; \
+ psrld $(32 - 5), x4 ## 1; \
+ por x4 ## 1, x0 ## 1; \
+ movdqa x2 ## 1, x4 ## 1; \
+ pslld $22, x2 ## 1; \
+ psrld $(32 - 22), x4 ## 1; \
+ por x4 ## 1, x2 ## 1; \
+ pxor RK0, x0 ## 1; \
+ pxor RK2, x2 ## 1; \
+ pxor RK1, x1 ## 2; \
+ pxor RK3, x3 ## 2; \
+ movdqa x0 ## 2, x4 ## 2; \
+ pslld $5, x0 ## 2; \
+ psrld $(32 - 5), x4 ## 2; \
+ por x4 ## 2, x0 ## 2; \
+ movdqa x2 ## 2, x4 ## 2; \
+ pslld $22, x2 ## 2; \
+ psrld $(32 - 22), x4 ## 2; \
+ por x4 ## 2, x2 ## 2; \
+ pxor RK0, x0 ## 2; \
+ pxor RK2, x2 ## 2;
+
+#define KL2(x0, x1, x2, x3, x4, i) \
+ pxor RK0, x0 ## 1; \
+ pxor RK2, x2 ## 1; \
+ movdqa x0 ## 1, x4 ## 1; \
+ psrld $5, x0 ## 1; \
+ pslld $(32 - 5), x4 ## 1; \
+ por x4 ## 1, x0 ## 1; \
+ pxor RK3, x3 ## 1; \
+ pxor RK1, x1 ## 1; \
+ movdqa x2 ## 1, x4 ## 1; \
+ psrld $22, x2 ## 1; \
+ pslld $(32 - 22), x4 ## 1; \
+ por x4 ## 1, x2 ## 1; \
+ pxor x3 ## 1, x2 ## 1; \
+ pxor RK0, x0 ## 2; \
+ pxor RK2, x2 ## 2; \
+ movdqa x0 ## 2, x4 ## 2; \
+ psrld $5, x0 ## 2; \
+ pslld $(32 - 5), x4 ## 2; \
+ por x4 ## 2, x0 ## 2; \
+ pxor RK3, x3 ## 2; \
+ pxor RK1, x1 ## 2; \
+ movdqa x2 ## 2, x4 ## 2; \
+ psrld $22, x2 ## 2; \
+ pslld $(32 - 22), x4 ## 2; \
+ por x4 ## 2, x2 ## 2; \
+ pxor x3 ## 2, x2 ## 2; \
+ pxor x3 ## 1, x0 ## 1; \
+ movdqa x1 ## 1, x4 ## 1; \
+ pslld $7, x4 ## 1; \
+ pxor x1 ## 1, x0 ## 1; \
+ pxor x4 ## 1, x2 ## 1; \
+ movdqa x1 ## 1, x4 ## 1; \
+ psrld $1, x1 ## 1; \
+ pslld $(32 - 1), x4 ## 1; \
+ por x4 ## 1, x1 ## 1; \
+ pxor x3 ## 2, x0 ## 2; \
+ movdqa x1 ## 2, x4 ## 2; \
+ pslld $7, x4 ## 2; \
+ pxor x1 ## 2, x0 ## 2; \
+ pxor x4 ## 2, x2 ## 2; \
+ movdqa x1 ## 2, x4 ## 2; \
+ psrld $1, x1 ## 2; \
+ pslld $(32 - 1), x4 ## 2; \
+ por x4 ## 2, x1 ## 2; \
+ movdqa x3 ## 1, x4 ## 1; \
+ psrld $7, x3 ## 1; \
+ pslld $(32 - 7), x4 ## 1; \
+ por x4 ## 1, x3 ## 1; \
+ pxor x0 ## 1, x1 ## 1; \
+ movdqa x0 ## 1, x4 ## 1; \
+ pslld $3, x4 ## 1; \
+ pxor x4 ## 1, x3 ## 1; \
+ movdqa x0 ## 1, x4 ## 1; \
+ movdqa x3 ## 2, x4 ## 2; \
+ psrld $7, x3 ## 2; \
+ pslld $(32 - 7), x4 ## 2; \
+ por x4 ## 2, x3 ## 2; \
+ pxor x0 ## 2, x1 ## 2; \
+ movdqa x0 ## 2, x4 ## 2; \
+ pslld $3, x4 ## 2; \
+ pxor x4 ## 2, x3 ## 2; \
+ movdqa x0 ## 2, x4 ## 2; \
+ psrld $13, x0 ## 1; \
+ pslld $(32 - 13), x4 ## 1; \
+ por x4 ## 1, x0 ## 1; \
+ pxor x2 ## 1, x1 ## 1; \
+ pxor x2 ## 1, x3 ## 1; \
+ movdqa x2 ## 1, x4 ## 1; \
+ psrld $3, x2 ## 1; \
+ pslld $(32 - 3), x4 ## 1; \
+ por x4 ## 1, x2 ## 1; \
+ psrld $13, x0 ## 2; \
+ pslld $(32 - 13), x4 ## 2; \
+ por x4 ## 2, x0 ## 2; \
+ pxor x2 ## 2, x1 ## 2; \
+ pxor x2 ## 2, x3 ## 2; \
+ movdqa x2 ## 2, x4 ## 2; \
+ psrld $3, x2 ## 2; \
+ pslld $(32 - 3), x4 ## 2; \
+ por x4 ## 2, x2 ## 2;
+
+#define S(SBOX, x0, x1, x2, x3, x4) \
+ SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+ SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+ SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+ SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2);
+
+#define SP(SBOX, x0, x1, x2, x3, x4, i) \
+ get_key(i, 0, RK0); \
+ SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+ get_key(i, 2, RK2); \
+ SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+ get_key(i, 3, RK3); \
+ SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+ get_key(i, 1, RK1); \
+ SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+
+#define transpose_4x4(x0, x1, x2, x3, t1, t2, t3) \
+ movdqa x2, t3; \
+ movdqa x0, t1; \
+ unpcklps x3, t3; \
+ movdqa x0, t2; \
+ unpcklps x1, t1; \
+ unpckhps x1, t2; \
+ movdqa t3, x1; \
+ unpckhps x3, x2; \
+ movdqa t1, x0; \
+ movhlps t1, x1; \
+ movdqa t2, t1; \
+ movlhps t3, x0; \
+ movlhps x2, t1; \
+ movhlps t2, x2; \
+ movdqa x2, x3; \
+ movdqa t1, x2;
+
+#define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \
+ movdqu (0*4*4)(in), x0; \
+ movdqu (1*4*4)(in), x1; \
+ movdqu (2*4*4)(in), x2; \
+ movdqu (3*4*4)(in), x3; \
+ \
+ transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define write_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+ \
+ movdqu x0, (0*4*4)(out); \
+ movdqu x1, (1*4*4)(out); \
+ movdqu x2, (2*4*4)(out); \
+ movdqu x3, (3*4*4)(out);
+
+#define xor_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+ \
+ movdqu (0*4*4)(out), t0; \
+ pxor t0, x0; \
+ movdqu x0, (0*4*4)(out); \
+ movdqu (1*4*4)(out), t0; \
+ pxor t0, x1; \
+ movdqu x1, (1*4*4)(out); \
+ movdqu (2*4*4)(out), t0; \
+ pxor t0, x2; \
+ movdqu x2, (2*4*4)(out); \
+ movdqu (3*4*4)(out), t0; \
+ pxor t0, x3; \
+ movdqu x3, (3*4*4)(out);
+
+.align 8
+.global __serpent_enc_blk_8way
+.type __serpent_enc_blk_8way,@function;
+
+__serpent_enc_blk_8way:
+ /* input:
+ * %rdi: ctx, CTX
+ * %rsi: dst
+ * %rdx: src
+ * %rcx: bool, if true: xor output
+ */
+
+ pcmpeqd RNOT, RNOT;
+
+ leaq (4*4*4)(%rdx), %rax;
+ read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+ read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+ K2(RA, RB, RC, RD, RE, 0);
+ S(S0, RA, RB, RC, RD, RE); LK2(RC, RB, RD, RA, RE, 1);
+ S(S1, RC, RB, RD, RA, RE); LK2(RE, RD, RA, RC, RB, 2);
+ S(S2, RE, RD, RA, RC, RB); LK2(RB, RD, RE, RC, RA, 3);
+ S(S3, RB, RD, RE, RC, RA); LK2(RC, RA, RD, RB, RE, 4);
+ S(S4, RC, RA, RD, RB, RE); LK2(RA, RD, RB, RE, RC, 5);
+ S(S5, RA, RD, RB, RE, RC); LK2(RC, RA, RD, RE, RB, 6);
+ S(S6, RC, RA, RD, RE, RB); LK2(RD, RB, RA, RE, RC, 7);
+ S(S7, RD, RB, RA, RE, RC); LK2(RC, RA, RE, RD, RB, 8);
+ S(S0, RC, RA, RE, RD, RB); LK2(RE, RA, RD, RC, RB, 9);
+ S(S1, RE, RA, RD, RC, RB); LK2(RB, RD, RC, RE, RA, 10);
+ S(S2, RB, RD, RC, RE, RA); LK2(RA, RD, RB, RE, RC, 11);
+ S(S3, RA, RD, RB, RE, RC); LK2(RE, RC, RD, RA, RB, 12);
+ S(S4, RE, RC, RD, RA, RB); LK2(RC, RD, RA, RB, RE, 13);
+ S(S5, RC, RD, RA, RB, RE); LK2(RE, RC, RD, RB, RA, 14);
+ S(S6, RE, RC, RD, RB, RA); LK2(RD, RA, RC, RB, RE, 15);
+ S(S7, RD, RA, RC, RB, RE); LK2(RE, RC, RB, RD, RA, 16);
+ S(S0, RE, RC, RB, RD, RA); LK2(RB, RC, RD, RE, RA, 17);
+ S(S1, RB, RC, RD, RE, RA); LK2(RA, RD, RE, RB, RC, 18);
+ S(S2, RA, RD, RE, RB, RC); LK2(RC, RD, RA, RB, RE, 19);
+ S(S3, RC, RD, RA, RB, RE); LK2(RB, RE, RD, RC, RA, 20);
+ S(S4, RB, RE, RD, RC, RA); LK2(RE, RD, RC, RA, RB, 21);
+ S(S5, RE, RD, RC, RA, RB); LK2(RB, RE, RD, RA, RC, 22);
+ S(S6, RB, RE, RD, RA, RC); LK2(RD, RC, RE, RA, RB, 23);
+ S(S7, RD, RC, RE, RA, RB); LK2(RB, RE, RA, RD, RC, 24);
+ S(S0, RB, RE, RA, RD, RC); LK2(RA, RE, RD, RB, RC, 25);
+ S(S1, RA, RE, RD, RB, RC); LK2(RC, RD, RB, RA, RE, 26);
+ S(S2, RC, RD, RB, RA, RE); LK2(RE, RD, RC, RA, RB, 27);
+ S(S3, RE, RD, RC, RA, RB); LK2(RA, RB, RD, RE, RC, 28);
+ S(S4, RA, RB, RD, RE, RC); LK2(RB, RD, RE, RC, RA, 29);
+ S(S5, RB, RD, RE, RC, RA); LK2(RA, RB, RD, RC, RE, 30);
+ S(S6, RA, RB, RD, RC, RE); LK2(RD, RE, RB, RC, RA, 31);
+ S(S7, RD, RE, RB, RC, RA); K2(RA, RB, RC, RD, RE, 32);
+
+ leaq (4*4*4)(%rsi), %rax;
+
+ testb %cl, %cl;
+ jnz __enc_xor8;
+
+ write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+ write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+ ret;
+
+__enc_xor8:
+ xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+ xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+ ret;
+
+.align 8
+.global serpent_dec_blk_8way
+.type serpent_dec_blk_8way,@function;
+
+serpent_dec_blk_8way:
+ /* input:
+ * %rdi: ctx, CTX
+ * %rsi: dst
+ * %rdx: src
+ */
+
+ pcmpeqd RNOT, RNOT;
+
+ leaq (4*4*4)(%rdx), %rax;
+ read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+ read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+ K2(RA, RB, RC, RD, RE, 32);
+ SP(SI7, RA, RB, RC, RD, RE, 31); KL2(RB, RD, RA, RE, RC, 31);
+ SP(SI6, RB, RD, RA, RE, RC, 30); KL2(RA, RC, RE, RB, RD, 30);
+ SP(SI5, RA, RC, RE, RB, RD, 29); KL2(RC, RD, RA, RE, RB, 29);
+ SP(SI4, RC, RD, RA, RE, RB, 28); KL2(RC, RA, RB, RE, RD, 28);
+ SP(SI3, RC, RA, RB, RE, RD, 27); KL2(RB, RC, RD, RE, RA, 27);
+ SP(SI2, RB, RC, RD, RE, RA, 26); KL2(RC, RA, RE, RD, RB, 26);
+ SP(SI1, RC, RA, RE, RD, RB, 25); KL2(RB, RA, RE, RD, RC, 25);
+ SP(SI0, RB, RA, RE, RD, RC, 24); KL2(RE, RC, RA, RB, RD, 24);
+ SP(SI7, RE, RC, RA, RB, RD, 23); KL2(RC, RB, RE, RD, RA, 23);
+ SP(SI6, RC, RB, RE, RD, RA, 22); KL2(RE, RA, RD, RC, RB, 22);
+ SP(SI5, RE, RA, RD, RC, RB, 21); KL2(RA, RB, RE, RD, RC, 21);
+ SP(SI4, RA, RB, RE, RD, RC, 20); KL2(RA, RE, RC, RD, RB, 20);
+ SP(SI3, RA, RE, RC, RD, RB, 19); KL2(RC, RA, RB, RD, RE, 19);
+ SP(SI2, RC, RA, RB, RD, RE, 18); KL2(RA, RE, RD, RB, RC, 18);
+ SP(SI1, RA, RE, RD, RB, RC, 17); KL2(RC, RE, RD, RB, RA, 17);
+ SP(SI0, RC, RE, RD, RB, RA, 16); KL2(RD, RA, RE, RC, RB, 16);
+ SP(SI7, RD, RA, RE, RC, RB, 15); KL2(RA, RC, RD, RB, RE, 15);
+ SP(SI6, RA, RC, RD, RB, RE, 14); KL2(RD, RE, RB, RA, RC, 14);
+ SP(SI5, RD, RE, RB, RA, RC, 13); KL2(RE, RC, RD, RB, RA, 13);
+ SP(SI4, RE, RC, RD, RB, RA, 12); KL2(RE, RD, RA, RB, RC, 12);
+ SP(SI3, RE, RD, RA, RB, RC, 11); KL2(RA, RE, RC, RB, RD, 11);
+ SP(SI2, RA, RE, RC, RB, RD, 10); KL2(RE, RD, RB, RC, RA, 10);
+ SP(SI1, RE, RD, RB, RC, RA, 9); KL2(RA, RD, RB, RC, RE, 9);
+ SP(SI0, RA, RD, RB, RC, RE, 8); KL2(RB, RE, RD, RA, RC, 8);
+ SP(SI7, RB, RE, RD, RA, RC, 7); KL2(RE, RA, RB, RC, RD, 7);
+ SP(SI6, RE, RA, RB, RC, RD, 6); KL2(RB, RD, RC, RE, RA, 6);
+ SP(SI5, RB, RD, RC, RE, RA, 5); KL2(RD, RA, RB, RC, RE, 5);
+ SP(SI4, RD, RA, RB, RC, RE, 4); KL2(RD, RB, RE, RC, RA, 4);
+ SP(SI3, RD, RB, RE, RC, RA, 3); KL2(RE, RD, RA, RC, RB, 3);
+ SP(SI2, RE, RD, RA, RC, RB, 2); KL2(RD, RB, RC, RA, RE, 2);
+ SP(SI1, RD, RB, RC, RA, RE, 1); KL2(RE, RB, RC, RA, RD, 1);
+ S(SI0, RE, RB, RC, RA, RD); K2(RC, RD, RB, RE, RA, 0);
+
+ leaq (4*4*4)(%rsi), %rax;
+ write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2);
+ write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
+
+ ret;
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
new file mode 100644
index 000000000000..7955a9b76b91
--- /dev/null
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -0,0 +1,1070 @@
+/*
+ * Glue Code for SSE2 assembler versions of Serpent Cipher
+ *
+ * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Glue code based on aesni-intel_glue.c by:
+ * Copyright (C) 2008, Intel Corp.
+ * Author: Huang Ying <ying.huang@intel.com>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ * CTR part based on code (crypto/ctr.c) by:
+ * (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.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.
+ *
+ * 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
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/algapi.h>
+#include <crypto/serpent.h>
+#include <crypto/cryptd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ctr.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/i387.h>
+#include <asm/serpent.h>
+#include <crypto/scatterwalk.h>
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+
+struct async_serpent_ctx {
+ struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+ if (fpu_enabled)
+ return true;
+
+ /* SSE2 is only used when chunk to be processed is large enough, so
+ * do not enable FPU until it is necessary.
+ */
+ if (nbytes < SERPENT_BLOCK_SIZE * SERPENT_PARALLEL_BLOCKS)
+ return false;
+
+ kernel_fpu_begin();
+ return true;
+}
+
+static inline void serpent_fpu_end(bool fpu_enabled)
+{
+ if (fpu_enabled)
+ kernel_fpu_end();
+}
+
+static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
+ bool enc)
+{
+ bool fpu_enabled = false;
+ struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ const unsigned int bsize = SERPENT_BLOCK_SIZE;
+ unsigned int nbytes;
+ int err;
+
+ err = blkcipher_walk_virt(desc, walk);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ while ((nbytes = walk->nbytes)) {
+ u8 *wsrc = walk->src.virt.addr;
+ u8 *wdst = walk->dst.virt.addr;
+
+ fpu_enabled = serpent_fpu_begin(fpu_enabled, nbytes);
+
+ /* Process multi-block batch */
+ if (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS) {
+ do {
+ if (enc)
+ serpent_enc_blk_xway(ctx, wdst, wsrc);
+ else
+ serpent_dec_blk_xway(ctx, wdst, wsrc);
+
+ wsrc += bsize * SERPENT_PARALLEL_BLOCKS;
+ wdst += bsize * SERPENT_PARALLEL_BLOCKS;
+ nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
+ } while (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS);
+
+ if (nbytes < bsize)
+ goto done;
+ }
+
+ /* Handle leftovers */
+ do {
+ if (enc)
+ __serpent_encrypt(ctx, wdst, wsrc);
+ else
+ __serpent_decrypt(ctx, wdst, wsrc);
+
+ wsrc += bsize;
+ wdst += bsize;
+ nbytes -= bsize;
+ } while (nbytes >= bsize);
+
+done:
+ err = blkcipher_walk_done(desc, walk, nbytes);
+ }
+
+ serpent_fpu_end(fpu_enabled);
+ return err;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct blkcipher_walk walk;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ return ecb_crypt(desc, &walk, true);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct blkcipher_walk walk;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ return ecb_crypt(desc, &walk, false);
+}
+
+static struct crypto_alg blk_ecb_alg = {
+ .cra_name = "__ecb-serpent-sse2",
+ .cra_driver_name = "__driver-ecb-serpent-sse2",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list),
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE,
+ .setkey = serpent_setkey,
+ .encrypt = ecb_encrypt,
+ .decrypt = ecb_decrypt,
+ },
+ },
+};
+
+static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk)
+{
+ struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ const unsigned int bsize = SERPENT_BLOCK_SIZE;
+ unsigned int nbytes = walk->nbytes;
+ u128 *src = (u128 *)walk->src.virt.addr;
+ u128 *dst = (u128 *)walk->dst.virt.addr;
+ u128 *iv = (u128 *)walk->iv;
+
+ do {
+ u128_xor(dst, src, iv);
+ __serpent_encrypt(ctx, (u8 *)dst, (u8 *)dst);
+ iv = dst;
+
+ src += 1;
+ dst += 1;
+ nbytes -= bsize;
+ } while (nbytes >= bsize);
+
+ u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
+ return nbytes;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+
+ while ((nbytes = walk.nbytes)) {
+ nbytes = __cbc_encrypt(desc, &walk);
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+
+ return err;
+}
+
+static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk)
+{
+ struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ const unsigned int bsize = SERPENT_BLOCK_SIZE;
+ unsigned int nbytes = walk->nbytes;
+ u128 *src = (u128 *)walk->src.virt.addr;
+ u128 *dst = (u128 *)walk->dst.virt.addr;
+ u128 ivs[SERPENT_PARALLEL_BLOCKS - 1];
+ u128 last_iv;
+ int i;
+
+ /* Start of the last block. */
+ src += nbytes / bsize - 1;
+ dst += nbytes / bsize - 1;
+
+ last_iv = *src;
+
+ /* Process multi-block batch */
+ if (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS) {
+ do {
+ nbytes -= bsize * (SERPENT_PARALLEL_BLOCKS - 1);
+ src -= SERPENT_PARALLEL_BLOCKS - 1;
+ dst -= SERPENT_PARALLEL_BLOCKS - 1;
+
+ for (i = 0; i < SERPENT_PARALLEL_BLOCKS - 1; i++)
+ ivs[i] = src[i];
+
+ serpent_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
+
+ for (i = 0; i < SERPENT_PARALLEL_BLOCKS - 1; i++)
+ u128_xor(dst + (i + 1), dst + (i + 1), ivs + i);
+
+ nbytes -= bsize;
+ if (nbytes < bsize)
+ goto done;
+
+ u128_xor(dst, dst, src - 1);
+ src -= 1;
+ dst -= 1;
+ } while (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS);
+
+ if (nbytes < bsize)
+ goto done;
+ }
+
+ /* Handle leftovers */
+ for (;;) {
+ __serpent_decrypt(ctx, (u8 *)dst, (u8 *)src);
+
+ nbytes -= bsize;
+ if (nbytes < bsize)
+ break;
+
+ u128_xor(dst, dst, src - 1);
+ src -= 1;
+ dst -= 1;
+ }
+
+done:
+ u128_xor(dst, dst, (u128 *)walk->iv);
+ *(u128 *)walk->iv = last_iv;
+
+ return nbytes;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ bool fpu_enabled = false;
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt(desc, &walk);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ while ((nbytes = walk.nbytes)) {
+ fpu_enabled = serpent_fpu_begin(fpu_enabled, nbytes);
+ nbytes = __cbc_decrypt(desc, &walk);
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+
+ serpent_fpu_end(fpu_enabled);
+ return err;
+}
+
+static struct crypto_alg blk_cbc_alg = {
+ .cra_name = "__cbc-serpent-sse2",
+ .cra_driver_name = "__driver-cbc-serpent-sse2",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list),
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE,
+ .setkey = serpent_setkey,
+ .encrypt = cbc_encrypt,
+ .decrypt = cbc_decrypt,
+ },
+ },
+};
+
+static inline void u128_to_be128(be128 *dst, const u128 *src)
+{
+ dst->a = cpu_to_be64(src->a);
+ dst->b = cpu_to_be64(src->b);
+}
+
+static inline void be128_to_u128(u128 *dst, const be128 *src)
+{
+ dst->a = be64_to_cpu(src->a);
+ dst->b = be64_to_cpu(src->b);
+}
+
+static inline void u128_inc(u128 *i)
+{
+ i->b++;
+ if (!i->b)
+ i->a++;
+}
+
+static void ctr_crypt_final(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk)
+{
+ struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ u8 *ctrblk = walk->iv;
+ u8 keystream[SERPENT_BLOCK_SIZE];
+ u8 *src = walk->src.virt.addr;
+ u8 *dst = walk->dst.virt.addr;
+ unsigned int nbytes = walk->nbytes;
+
+ __serpent_encrypt(ctx, keystream, ctrblk);
+ crypto_xor(keystream, src, nbytes);
+ memcpy(dst, keystream, nbytes);
+
+ crypto_inc(ctrblk, SERPENT_BLOCK_SIZE);
+}
+
+static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
+ struct blkcipher_walk *walk)
+{
+ struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ const unsigned int bsize = SERPENT_BLOCK_SIZE;
+ unsigned int nbytes = walk->nbytes;
+ u128 *src = (u128 *)walk->src.virt.addr;
+ u128 *dst = (u128 *)walk->dst.virt.addr;
+ u128 ctrblk;
+ be128 ctrblocks[SERPENT_PARALLEL_BLOCKS];
+ int i;
+
+ be128_to_u128(&ctrblk, (be128 *)walk->iv);
+
+ /* Process multi-block batch */
+ if (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS) {
+ do {
+ /* create ctrblks for parallel encrypt */
+ for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) {
+ if (dst != src)
+ dst[i] = src[i];
+
+ u128_to_be128(&ctrblocks[i], &ctrblk);
+ u128_inc(&ctrblk);
+ }
+
+ serpent_enc_blk_xway_xor(ctx, (u8 *)dst,
+ (u8 *)ctrblocks);
+
+ src += SERPENT_PARALLEL_BLOCKS;
+ dst += SERPENT_PARALLEL_BLOCKS;
+ nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
+ } while (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS);
+
+ if (nbytes < bsize)
+ goto done;
+ }
+
+ /* Handle leftovers */
+ do {
+ if (dst != src)
+ *dst = *src;
+
+ u128_to_be128(&ctrblocks[0], &ctrblk);
+ u128_inc(&ctrblk);
+
+ __serpent_encrypt(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
+ u128_xor(dst, dst, (u128 *)ctrblocks);
+
+ src += 1;
+ dst += 1;
+ nbytes -= bsize;
+ } while (nbytes >= bsize);
+
+done:
+ u128_to_be128((be128 *)walk->iv, &ctrblk);
+ return nbytes;
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ bool fpu_enabled = false;
+ struct blkcipher_walk walk;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, SERPENT_BLOCK_SIZE);
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ while ((nbytes = walk.nbytes) >= SERPENT_BLOCK_SIZE) {
+ fpu_enabled = serpent_fpu_begin(fpu_enabled, nbytes);
+ nbytes = __ctr_crypt(desc, &walk);
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+
+ serpent_fpu_end(fpu_enabled);
+
+ if (walk.nbytes) {
+ ctr_crypt_final(desc, &walk);
+ err = blkcipher_walk_done(desc, &walk, 0);
+ }
+
+ return err;
+}
+
+static struct crypto_alg blk_ctr_alg = {
+ .cra_name = "__ctr-serpent-sse2",
+ .cra_driver_name = "__driver-ctr-serpent-sse2",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_ctr_alg.cra_list),
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = serpent_setkey,
+ .encrypt = ctr_crypt,
+ .decrypt = ctr_crypt,
+ },
+ },
+};
+
+struct crypt_priv {
+ struct serpent_ctx *ctx;
+ bool fpu_enabled;
+};
+
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+ const unsigned int bsize = SERPENT_BLOCK_SIZE;
+ struct crypt_priv *ctx = priv;
+ int i;
+
+ ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
+
+ if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+ serpent_enc_blk_xway(ctx->ctx, srcdst, srcdst);
+ return;
+ }
+
+ for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+ __serpent_encrypt(ctx->ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+ const unsigned int bsize = SERPENT_BLOCK_SIZE;
+ struct crypt_priv *ctx = priv;
+ int i;
+
+ ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
+
+ if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+ serpent_dec_blk_xway(ctx->ctx, srcdst, srcdst);
+ return;
+ }
+
+ for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+ __serpent_decrypt(ctx->ctx, srcdst, srcdst);
+}
+
+struct serpent_lrw_ctx {
+ struct lrw_table_ctx lrw_table;
+ struct serpent_ctx serpent_ctx;
+};
+
+static int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+ int err;
+
+ err = __serpent_setkey(&ctx->serpent_ctx, key, keylen -
+ SERPENT_BLOCK_SIZE);
+ if (err)
+ return err;
+
+ return lrw_init_table(&ctx->lrw_table, key + keylen -
+ SERPENT_BLOCK_SIZE);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[SERPENT_PARALLEL_BLOCKS];
+ struct crypt_priv crypt_ctx = {
+ .ctx = &ctx->serpent_ctx,
+ .fpu_enabled = false,
+ };
+ struct lrw_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .table_ctx = &ctx->lrw_table,
+ .crypt_ctx = &crypt_ctx,
+ .crypt_fn = encrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ ret = lrw_crypt(desc, dst, src, nbytes, &req);
+ serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+ return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[SERPENT_PARALLEL_BLOCKS];
+ struct crypt_priv crypt_ctx = {
+ .ctx = &ctx->serpent_ctx,
+ .fpu_enabled = false,
+ };
+ struct lrw_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .table_ctx = &ctx->lrw_table,
+ .crypt_ctx = &crypt_ctx,
+ .crypt_fn = decrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ ret = lrw_crypt(desc, dst, src, nbytes, &req);
+ serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+ return ret;
+}
+
+static void lrw_exit_tfm(struct crypto_tfm *tfm)
+{
+ struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ lrw_free_table(&ctx->lrw_table);
+}
+
+static struct crypto_alg blk_lrw_alg = {
+ .cra_name = "__lrw-serpent-sse2",
+ .cra_driver_name = "__driver-lrw-serpent-sse2",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct serpent_lrw_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_lrw_alg.cra_list),
+ .cra_exit = lrw_exit_tfm,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE +
+ SERPENT_BLOCK_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE +
+ SERPENT_BLOCK_SIZE,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = lrw_serpent_setkey,
+ .encrypt = lrw_encrypt,
+ .decrypt = lrw_decrypt,
+ },
+ },
+};
+
+struct serpent_xts_ctx {
+ struct serpent_ctx tweak_ctx;
+ struct serpent_ctx crypt_ctx;
+};
+
+static int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct serpent_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+ u32 *flags = &tfm->crt_flags;
+ int err;
+
+ /* key consists of keys of equal size concatenated, therefore
+ * the length must be even
+ */
+ if (keylen % 2) {
+ *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+ }
+
+ /* first half of xts-key is for crypt */
+ err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
+ if (err)
+ return err;
+
+ /* second half of xts-key is for tweak */
+ return __serpent_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[SERPENT_PARALLEL_BLOCKS];
+ struct crypt_priv crypt_ctx = {
+ .ctx = &ctx->crypt_ctx,
+ .fpu_enabled = false,
+ };
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = &ctx->tweak_ctx,
+ .tweak_fn = XTS_TWEAK_CAST(__serpent_encrypt),
+ .crypt_ctx = &crypt_ctx,
+ .crypt_fn = encrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ ret = xts_crypt(desc, dst, src, nbytes, &req);
+ serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+ return ret;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[SERPENT_PARALLEL_BLOCKS];
+ struct crypt_priv crypt_ctx = {
+ .ctx = &ctx->crypt_ctx,
+ .fpu_enabled = false,
+ };
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = &ctx->tweak_ctx,
+ .tweak_fn = XTS_TWEAK_CAST(__serpent_encrypt),
+ .crypt_ctx = &crypt_ctx,
+ .crypt_fn = decrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ ret = xts_crypt(desc, dst, src, nbytes, &req);
+ serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+ return ret;
+}
+
+static struct crypto_alg blk_xts_alg = {
+ .cra_name = "__xts-serpent-sse2",
+ .cra_driver_name = "__driver-xts-serpent-sse2",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct serpent_xts_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_xts_alg.cra_list),
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE * 2,
+ .max_keysize = SERPENT_MAX_KEY_SIZE * 2,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = xts_serpent_setkey,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+ },
+ },
+};
+
+static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+ unsigned int key_len)
+{
+ struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
+ int err;
+
+ crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+ crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
+ & CRYPTO_TFM_REQ_MASK);
+ err = crypto_ablkcipher_setkey(child, key, key_len);
+ crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
+ & CRYPTO_TFM_RES_MASK);
+ return err;
+}
+
+static int __ablk_encrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+ struct blkcipher_desc desc;
+
+ desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+ desc.info = req->info;
+ desc.flags = 0;
+
+ return crypto_blkcipher_crt(desc.tfm)->encrypt(
+ &desc, req->dst, req->src, req->nbytes);
+}
+
+static int ablk_encrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+ if (!irq_fpu_usable()) {
+ struct ablkcipher_request *cryptd_req =
+ ablkcipher_request_ctx(req);
+
+ memcpy(cryptd_req, req, sizeof(*req));
+ ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+ return crypto_ablkcipher_encrypt(cryptd_req);
+ } else {
+ return __ablk_encrypt(req);
+ }
+}
+
+static int ablk_decrypt(struct ablkcipher_request *req)
+{
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+ struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+ if (!irq_fpu_usable()) {
+ struct ablkcipher_request *cryptd_req =
+ ablkcipher_request_ctx(req);
+
+ memcpy(cryptd_req, req, sizeof(*req));
+ ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+ return crypto_ablkcipher_decrypt(cryptd_req);
+ } else {
+ struct blkcipher_desc desc;
+
+ desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+ desc.info = req->info;
+ desc.flags = 0;
+
+ return crypto_blkcipher_crt(desc.tfm)->decrypt(
+ &desc, req->dst, req->src, req->nbytes);
+ }
+}
+
+static void ablk_exit(struct crypto_tfm *tfm)
+{
+ struct async_serpent_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ cryptd_free_ablkcipher(ctx->cryptd_tfm);
+}
+
+static void ablk_init_common(struct crypto_tfm *tfm,
+ struct cryptd_ablkcipher *cryptd_tfm)
+{
+ struct async_serpent_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->cryptd_tfm = cryptd_tfm;
+ tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
+ crypto_ablkcipher_reqsize(&cryptd_tfm->base);
+}
+
+static int ablk_ecb_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ecb-serpent-sse2", 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_ecb_alg = {
+ .cra_name = "ecb(serpent)",
+ .cra_driver_name = "ecb-serpent-sse2",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_ecb_alg.cra_list),
+ .cra_init = ablk_ecb_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+
+static int ablk_cbc_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("__driver-cbc-serpent-sse2", 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_cbc_alg = {
+ .cra_name = "cbc(serpent)",
+ .cra_driver_name = "cbc-serpent-sse2",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_cbc_alg.cra_list),
+ .cra_init = ablk_cbc_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = __ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+
+static int ablk_ctr_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ctr-serpent-sse2", 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_ctr_alg = {
+ .cra_name = "ctr(serpent)",
+ .cra_driver_name = "ctr-serpent-sse2",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = 1,
+ .cra_ctxsize = sizeof(struct async_serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_ctr_alg.cra_list),
+ .cra_init = ablk_ctr_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_encrypt,
+ .geniv = "chainiv",
+ },
+ },
+};
+
+static int ablk_lrw_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("__driver-lrw-serpent-sse2", 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_lrw_alg = {
+ .cra_name = "lrw(serpent)",
+ .cra_driver_name = "lrw-serpent-sse2",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_lrw_alg.cra_list),
+ .cra_init = ablk_lrw_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE +
+ SERPENT_BLOCK_SIZE,
+ .max_keysize = SERPENT_MAX_KEY_SIZE +
+ SERPENT_BLOCK_SIZE,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+
+static int ablk_xts_init(struct crypto_tfm *tfm)
+{
+ struct cryptd_ablkcipher *cryptd_tfm;
+
+ cryptd_tfm = cryptd_alloc_ablkcipher("__driver-xts-serpent-sse2", 0, 0);
+ if (IS_ERR(cryptd_tfm))
+ return PTR_ERR(cryptd_tfm);
+ ablk_init_common(tfm, cryptd_tfm);
+ return 0;
+}
+
+static struct crypto_alg ablk_xts_alg = {
+ .cra_name = "xts(serpent)",
+ .cra_driver_name = "xts-serpent-sse2",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SERPENT_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct async_serpent_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_ablkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(ablk_xts_alg.cra_list),
+ .cra_init = ablk_xts_init,
+ .cra_exit = ablk_exit,
+ .cra_u = {
+ .ablkcipher = {
+ .min_keysize = SERPENT_MIN_KEY_SIZE * 2,
+ .max_keysize = SERPENT_MAX_KEY_SIZE * 2,
+ .ivsize = SERPENT_BLOCK_SIZE,
+ .setkey = ablk_set_key,
+ .encrypt = ablk_encrypt,
+ .decrypt = ablk_decrypt,
+ },
+ },
+};
+
+static int __init serpent_sse2_init(void)
+{
+ int err;
+
+ if (!cpu_has_xmm2) {
+ printk(KERN_INFO "SSE2 instructions are not detected.\n");
+ return -ENODEV;
+ }
+
+ err = crypto_register_alg(&blk_ecb_alg);
+ if (err)
+ goto blk_ecb_err;
+ err = crypto_register_alg(&blk_cbc_alg);
+ if (err)
+ goto blk_cbc_err;
+ err = crypto_register_alg(&blk_ctr_alg);
+ if (err)
+ goto blk_ctr_err;
+ err = crypto_register_alg(&ablk_ecb_alg);
+ if (err)
+ goto ablk_ecb_err;
+ err = crypto_register_alg(&ablk_cbc_alg);
+ if (err)
+ goto ablk_cbc_err;
+ err = crypto_register_alg(&ablk_ctr_alg);
+ if (err)
+ goto ablk_ctr_err;
+ err = crypto_register_alg(&blk_lrw_alg);
+ if (err)
+ goto blk_lrw_err;
+ err = crypto_register_alg(&ablk_lrw_alg);
+ if (err)
+ goto ablk_lrw_err;
+ err = crypto_register_alg(&blk_xts_alg);
+ if (err)
+ goto blk_xts_err;
+ err = crypto_register_alg(&ablk_xts_alg);
+ if (err)
+ goto ablk_xts_err;
+ return err;
+
+ crypto_unregister_alg(&ablk_xts_alg);
+ablk_xts_err:
+ crypto_unregister_alg(&blk_xts_alg);
+blk_xts_err:
+ crypto_unregister_alg(&ablk_lrw_alg);
+ablk_lrw_err:
+ crypto_unregister_alg(&blk_lrw_alg);
+blk_lrw_err:
+ crypto_unregister_alg(&ablk_ctr_alg);
+ablk_ctr_err:
+ crypto_unregister_alg(&ablk_cbc_alg);
+ablk_cbc_err:
+ crypto_unregister_alg(&ablk_ecb_alg);
+ablk_ecb_err:
+ crypto_unregister_alg(&blk_ctr_alg);
+blk_ctr_err:
+ crypto_unregister_alg(&blk_cbc_alg);
+blk_cbc_err:
+ crypto_unregister_alg(&blk_ecb_alg);
+blk_ecb_err:
+ return err;
+}
+
+static void __exit serpent_sse2_exit(void)
+{
+ crypto_unregister_alg(&ablk_xts_alg);
+ crypto_unregister_alg(&blk_xts_alg);
+ crypto_unregister_alg(&ablk_lrw_alg);
+ crypto_unregister_alg(&blk_lrw_alg);
+ crypto_unregister_alg(&ablk_ctr_alg);
+ crypto_unregister_alg(&ablk_cbc_alg);
+ crypto_unregister_alg(&ablk_ecb_alg);
+ crypto_unregister_alg(&blk_ctr_alg);
+ crypto_unregister_alg(&blk_cbc_alg);
+ crypto_unregister_alg(&blk_ecb_alg);
+}
+
+module_init(serpent_sse2_init);
+module_exit(serpent_sse2_exit);
+
+MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("serpent");
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 5ede9c444c3e..7fee8c152f93 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -32,6 +32,8 @@
#include <crypto/algapi.h>
#include <crypto/twofish.h>
#include <crypto/b128ops.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
/* regular block cipher functions from twofish_x86_64 module */
asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
@@ -432,6 +434,209 @@ static struct crypto_alg blk_ctr_alg = {
},
};
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+ const unsigned int bsize = TF_BLOCK_SIZE;
+ struct twofish_ctx *ctx = priv;
+ int i;
+
+ if (nbytes == 3 * bsize) {
+ twofish_enc_blk_3way(ctx, srcdst, srcdst);
+ return;
+ }
+
+ for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+ twofish_enc_blk(ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+ const unsigned int bsize = TF_BLOCK_SIZE;
+ struct twofish_ctx *ctx = priv;
+ int i;
+
+ if (nbytes == 3 * bsize) {
+ twofish_dec_blk_3way(ctx, srcdst, srcdst);
+ return;
+ }
+
+ for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+ twofish_dec_blk(ctx, srcdst, srcdst);
+}
+
+struct twofish_lrw_ctx {
+ struct lrw_table_ctx lrw_table;
+ struct twofish_ctx twofish_ctx;
+};
+
+static int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+ int err;
+
+ err = __twofish_setkey(&ctx->twofish_ctx, key, keylen - TF_BLOCK_SIZE,
+ &tfm->crt_flags);
+ if (err)
+ return err;
+
+ return lrw_init_table(&ctx->lrw_table, key + keylen - TF_BLOCK_SIZE);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[3];
+ struct lrw_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .table_ctx = &ctx->lrw_table,
+ .crypt_ctx = &ctx->twofish_ctx,
+ .crypt_fn = encrypt_callback,
+ };
+
+ return lrw_crypt(desc, dst, src, nbytes, &req);
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[3];
+ struct lrw_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .table_ctx = &ctx->lrw_table,
+ .crypt_ctx = &ctx->twofish_ctx,
+ .crypt_fn = decrypt_callback,
+ };
+
+ return lrw_crypt(desc, dst, src, nbytes, &req);
+}
+
+static void lrw_exit_tfm(struct crypto_tfm *tfm)
+{
+ struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ lrw_free_table(&ctx->lrw_table);
+}
+
+static struct crypto_alg blk_lrw_alg = {
+ .cra_name = "lrw(twofish)",
+ .cra_driver_name = "lrw-twofish-3way",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = TF_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct twofish_lrw_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_lrw_alg.cra_list),
+ .cra_exit = lrw_exit_tfm,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = TF_MIN_KEY_SIZE + TF_BLOCK_SIZE,
+ .max_keysize = TF_MAX_KEY_SIZE + TF_BLOCK_SIZE,
+ .ivsize = TF_BLOCK_SIZE,
+ .setkey = lrw_twofish_setkey,
+ .encrypt = lrw_encrypt,
+ .decrypt = lrw_decrypt,
+ },
+ },
+};
+
+struct twofish_xts_ctx {
+ struct twofish_ctx tweak_ctx;
+ struct twofish_ctx crypt_ctx;
+};
+
+static int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct twofish_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+ u32 *flags = &tfm->crt_flags;
+ int err;
+
+ /* key consists of keys of equal size concatenated, therefore
+ * the length must be even
+ */
+ if (keylen % 2) {
+ *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+ }
+
+ /* first half of xts-key is for crypt */
+ err = __twofish_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
+ if (err)
+ return err;
+
+ /* second half of xts-key is for tweak */
+ return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
+ flags);
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[3];
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = &ctx->tweak_ctx,
+ .tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
+ .crypt_ctx = &ctx->crypt_ctx,
+ .crypt_fn = encrypt_callback,
+ };
+
+ return xts_crypt(desc, dst, src, nbytes, &req);
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[3];
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = &ctx->tweak_ctx,
+ .tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
+ .crypt_ctx = &ctx->crypt_ctx,
+ .crypt_fn = decrypt_callback,
+ };
+
+ return xts_crypt(desc, dst, src, nbytes, &req);
+}
+
+static struct crypto_alg blk_xts_alg = {
+ .cra_name = "xts(twofish)",
+ .cra_driver_name = "xts-twofish-3way",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = TF_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct twofish_xts_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(blk_xts_alg.cra_list),
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = TF_MIN_KEY_SIZE * 2,
+ .max_keysize = TF_MAX_KEY_SIZE * 2,
+ .ivsize = TF_BLOCK_SIZE,
+ .setkey = xts_twofish_setkey,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+ },
+ },
+};
+
int __init init(void)
{
int err;
@@ -445,9 +650,20 @@ int __init init(void)
err = crypto_register_alg(&blk_ctr_alg);
if (err)
goto ctr_err;
+ err = crypto_register_alg(&blk_lrw_alg);
+ if (err)
+ goto blk_lrw_err;
+ err = crypto_register_alg(&blk_xts_alg);
+ if (err)
+ goto blk_xts_err;
return 0;
+ crypto_unregister_alg(&blk_xts_alg);
+blk_xts_err:
+ crypto_unregister_alg(&blk_lrw_alg);
+blk_lrw_err:
+ crypto_unregister_alg(&blk_ctr_alg);
ctr_err:
crypto_unregister_alg(&blk_cbc_alg);
cbc_err:
@@ -458,6 +674,8 @@ ecb_err:
void __exit fini(void)
{
+ crypto_unregister_alg(&blk_xts_alg);
+ crypto_unregister_alg(&blk_lrw_alg);
crypto_unregister_alg(&blk_ctr_alg);
crypto_unregister_alg(&blk_cbc_alg);
crypto_unregister_alg(&blk_ecb_alg);
diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile
index 52d0ccfcf6ea..455646e0e532 100644
--- a/arch/x86/ia32/Makefile
+++ b/arch/x86/ia32/Makefile
@@ -3,6 +3,7 @@
#
obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o
+obj-$(CONFIG_IA32_EMULATION) += nosyscall.o syscall_ia32.o
sysv-$(CONFIG_SYSVIPC) := ipc32.o
obj-$(CONFIG_IA32_EMULATION) += $(sysv-y)
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 3e274564f6bf..e3e734005e19 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -14,6 +14,7 @@
#include <asm/segment.h>
#include <asm/irqflags.h>
#include <linux/linkage.h>
+#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
@@ -27,8 +28,6 @@
.section .entry.text, "ax"
-#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8)
-
.macro IA32_ARG_FIXUP noebp=0
movl %edi,%r8d
.if \noebp
@@ -191,7 +190,7 @@ sysexit_from_sys_call:
movl %ebx,%edx /* 3rd arg: 1st syscall arg */
movl %eax,%esi /* 2nd arg: syscall number */
movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */
- call audit_syscall_entry
+ call __audit_syscall_entry
movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */
cmpq $(IA32_NR_syscalls-1),%rax
ja ia32_badsys
@@ -208,12 +207,13 @@ sysexit_from_sys_call:
TRACE_IRQS_ON
sti
movl %eax,%esi /* second arg, syscall return value */
- cmpl $0,%eax /* is it < 0? */
- setl %al /* 1 if so, 0 if not */
+ cmpl $-MAX_ERRNO,%eax /* is it an error ? */
+ jbe 1f
+ movslq %eax, %rsi /* if error sign extend to 64 bits */
+1: setbe %al /* 1 if error, 0 if not */
movzbl %al,%edi /* zero-extend that into %edi */
- inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
- call audit_syscall_exit
- movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall return value */
+ call __audit_syscall_exit
+ movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */
movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
cli
TRACE_IRQS_OFF
@@ -447,9 +447,6 @@ ia32_badsys:
movq $-ENOSYS,%rax
jmp ia32_sysret
-quiet_ni_syscall:
- movq $-ENOSYS,%rax
- ret
CFI_ENDPROC
.macro PTREGSCALL label, func, arg
@@ -494,357 +491,3 @@ ia32_ptregs_common:
jmp ia32_sysret /* misbalances the return cache */
CFI_ENDPROC
END(ia32_ptregs_common)
-
- .section .rodata,"a"
- .align 8
-ia32_sys_call_table:
- .quad sys_restart_syscall
- .quad sys_exit
- .quad stub32_fork
- .quad sys_read
- .quad sys_write
- .quad compat_sys_open /* 5 */
- .quad sys_close
- .quad sys32_waitpid
- .quad sys_creat
- .quad sys_link
- .quad sys_unlink /* 10 */
- .quad stub32_execve
- .quad sys_chdir
- .quad compat_sys_time
- .quad sys_mknod
- .quad sys_chmod /* 15 */
- .quad sys_lchown16
- .quad quiet_ni_syscall /* old break syscall holder */
- .quad sys_stat
- .quad sys32_lseek
- .quad sys_getpid /* 20 */
- .quad compat_sys_mount /* mount */
- .quad sys_oldumount /* old_umount */
- .quad sys_setuid16
- .quad sys_getuid16
- .quad compat_sys_stime /* stime */ /* 25 */
- .quad compat_sys_ptrace /* ptrace */
- .quad sys_alarm
- .quad sys_fstat /* (old)fstat */
- .quad sys_pause
- .quad compat_sys_utime /* 30 */
- .quad quiet_ni_syscall /* old stty syscall holder */
- .quad quiet_ni_syscall /* old gtty syscall holder */
- .quad sys_access
- .quad sys_nice
- .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */
- .quad sys_sync
- .quad sys32_kill
- .quad sys_rename
- .quad sys_mkdir
- .quad sys_rmdir /* 40 */
- .quad sys_dup
- .quad sys_pipe
- .quad compat_sys_times
- .quad quiet_ni_syscall /* old prof syscall holder */
- .quad sys_brk /* 45 */
- .quad sys_setgid16
- .quad sys_getgid16
- .quad sys_signal
- .quad sys_geteuid16
- .quad sys_getegid16 /* 50 */
- .quad sys_acct
- .quad sys_umount /* new_umount */
- .quad quiet_ni_syscall /* old lock syscall holder */
- .quad compat_sys_ioctl
- .quad compat_sys_fcntl64 /* 55 */
- .quad quiet_ni_syscall /* old mpx syscall holder */
- .quad sys_setpgid
- .quad quiet_ni_syscall /* old ulimit syscall holder */
- .quad sys_olduname
- .quad sys_umask /* 60 */
- .quad sys_chroot
- .quad compat_sys_ustat
- .quad sys_dup2
- .quad sys_getppid
- .quad sys_getpgrp /* 65 */
- .quad sys_setsid
- .quad sys32_sigaction
- .quad sys_sgetmask
- .quad sys_ssetmask
- .quad sys_setreuid16 /* 70 */
- .quad sys_setregid16
- .quad sys32_sigsuspend
- .quad compat_sys_sigpending
- .quad sys_sethostname
- .quad compat_sys_setrlimit /* 75 */
- .quad compat_sys_old_getrlimit /* old_getrlimit */
- .quad compat_sys_getrusage
- .quad compat_sys_gettimeofday
- .quad compat_sys_settimeofday
- .quad sys_getgroups16 /* 80 */
- .quad sys_setgroups16
- .quad compat_sys_old_select
- .quad sys_symlink
- .quad sys_lstat
- .quad sys_readlink /* 85 */
- .quad sys_uselib
- .quad sys_swapon
- .quad sys_reboot
- .quad compat_sys_old_readdir
- .quad sys32_mmap /* 90 */
- .quad sys_munmap
- .quad sys_truncate
- .quad sys_ftruncate
- .quad sys_fchmod
- .quad sys_fchown16 /* 95 */
- .quad sys_getpriority
- .quad sys_setpriority
- .quad quiet_ni_syscall /* old profil syscall holder */
- .quad compat_sys_statfs
- .quad compat_sys_fstatfs /* 100 */
- .quad sys_ioperm
- .quad compat_sys_socketcall
- .quad sys_syslog
- .quad compat_sys_setitimer
- .quad compat_sys_getitimer /* 105 */
- .quad compat_sys_newstat
- .quad compat_sys_newlstat
- .quad compat_sys_newfstat
- .quad sys_uname
- .quad stub32_iopl /* 110 */
- .quad sys_vhangup
- .quad quiet_ni_syscall /* old "idle" system call */
- .quad sys32_vm86_warning /* vm86old */
- .quad compat_sys_wait4
- .quad sys_swapoff /* 115 */
- .quad compat_sys_sysinfo
- .quad sys32_ipc
- .quad sys_fsync
- .quad stub32_sigreturn
- .quad stub32_clone /* 120 */
- .quad sys_setdomainname
- .quad sys_newuname
- .quad sys_modify_ldt
- .quad compat_sys_adjtimex
- .quad sys32_mprotect /* 125 */
- .quad compat_sys_sigprocmask
- .quad quiet_ni_syscall /* create_module */
- .quad sys_init_module
- .quad sys_delete_module
- .quad quiet_ni_syscall /* 130 get_kernel_syms */
- .quad sys32_quotactl
- .quad sys_getpgid
- .quad sys_fchdir
- .quad quiet_ni_syscall /* bdflush */
- .quad sys_sysfs /* 135 */
- .quad sys_personality
- .quad quiet_ni_syscall /* for afs_syscall */
- .quad sys_setfsuid16
- .quad sys_setfsgid16
- .quad sys_llseek /* 140 */
- .quad compat_sys_getdents
- .quad compat_sys_select
- .quad sys_flock
- .quad sys_msync
- .quad compat_sys_readv /* 145 */
- .quad compat_sys_writev
- .quad sys_getsid
- .quad sys_fdatasync
- .quad compat_sys_sysctl /* sysctl */
- .quad sys_mlock /* 150 */
- .quad sys_munlock
- .quad sys_mlockall
- .quad sys_munlockall
- .quad sys_sched_setparam
- .quad sys_sched_getparam /* 155 */
- .quad sys_sched_setscheduler
- .quad sys_sched_getscheduler
- .quad sys_sched_yield
- .quad sys_sched_get_priority_max
- .quad sys_sched_get_priority_min /* 160 */
- .quad sys32_sched_rr_get_interval
- .quad compat_sys_nanosleep
- .quad sys_mremap
- .quad sys_setresuid16
- .quad sys_getresuid16 /* 165 */
- .quad sys32_vm86_warning /* vm86 */
- .quad quiet_ni_syscall /* query_module */
- .quad sys_poll
- .quad quiet_ni_syscall /* old nfsservctl */
- .quad sys_setresgid16 /* 170 */
- .quad sys_getresgid16
- .quad sys_prctl
- .quad stub32_rt_sigreturn
- .quad sys32_rt_sigaction
- .quad sys32_rt_sigprocmask /* 175 */
- .quad sys32_rt_sigpending
- .quad compat_sys_rt_sigtimedwait
- .quad sys32_rt_sigqueueinfo
- .quad sys_rt_sigsuspend
- .quad sys32_pread /* 180 */
- .quad sys32_pwrite
- .quad sys_chown16
- .quad sys_getcwd
- .quad sys_capget
- .quad sys_capset
- .quad stub32_sigaltstack
- .quad sys32_sendfile
- .quad quiet_ni_syscall /* streams1 */
- .quad quiet_ni_syscall /* streams2 */
- .quad stub32_vfork /* 190 */
- .quad compat_sys_getrlimit
- .quad sys_mmap_pgoff
- .quad sys32_truncate64
- .quad sys32_ftruncate64
- .quad sys32_stat64 /* 195 */
- .quad sys32_lstat64
- .quad sys32_fstat64
- .quad sys_lchown
- .quad sys_getuid
- .quad sys_getgid /* 200 */
- .quad sys_geteuid
- .quad sys_getegid
- .quad sys_setreuid
- .quad sys_setregid
- .quad sys_getgroups /* 205 */
- .quad sys_setgroups
- .quad sys_fchown
- .quad sys_setresuid
- .quad sys_getresuid
- .quad sys_setresgid /* 210 */
- .quad sys_getresgid
- .quad sys_chown
- .quad sys_setuid
- .quad sys_setgid
- .quad sys_setfsuid /* 215 */
- .quad sys_setfsgid
- .quad sys_pivot_root
- .quad sys_mincore
- .quad sys_madvise
- .quad compat_sys_getdents64 /* 220 getdents64 */
- .quad compat_sys_fcntl64
- .quad quiet_ni_syscall /* tux */
- .quad quiet_ni_syscall /* security */
- .quad sys_gettid
- .quad sys32_readahead /* 225 */
- .quad sys_setxattr
- .quad sys_lsetxattr
- .quad sys_fsetxattr
- .quad sys_getxattr
- .quad sys_lgetxattr /* 230 */
- .quad sys_fgetxattr
- .quad sys_listxattr
- .quad sys_llistxattr
- .quad sys_flistxattr
- .quad sys_removexattr /* 235 */
- .quad sys_lremovexattr
- .quad sys_fremovexattr
- .quad sys_tkill
- .quad sys_sendfile64
- .quad compat_sys_futex /* 240 */
- .quad compat_sys_sched_setaffinity
- .quad compat_sys_sched_getaffinity
- .quad sys_set_thread_area
- .quad sys_get_thread_area
- .quad compat_sys_io_setup /* 245 */
- .quad sys_io_destroy
- .quad compat_sys_io_getevents
- .quad compat_sys_io_submit
- .quad sys_io_cancel
- .quad sys32_fadvise64 /* 250 */
- .quad quiet_ni_syscall /* free_huge_pages */
- .quad sys_exit_group
- .quad sys32_lookup_dcookie
- .quad sys_epoll_create
- .quad sys_epoll_ctl /* 255 */
- .quad sys_epoll_wait
- .quad sys_remap_file_pages
- .quad sys_set_tid_address
- .quad compat_sys_timer_create
- .quad compat_sys_timer_settime /* 260 */
- .quad compat_sys_timer_gettime
- .quad sys_timer_getoverrun
- .quad sys_timer_delete
- .quad compat_sys_clock_settime
- .quad compat_sys_clock_gettime /* 265 */
- .quad compat_sys_clock_getres
- .quad compat_sys_clock_nanosleep
- .quad compat_sys_statfs64
- .quad compat_sys_fstatfs64
- .quad sys_tgkill /* 270 */
- .quad compat_sys_utimes
- .quad sys32_fadvise64_64
- .quad quiet_ni_syscall /* sys_vserver */
- .quad sys_mbind
- .quad compat_sys_get_mempolicy /* 275 */
- .quad sys_set_mempolicy
- .quad compat_sys_mq_open
- .quad sys_mq_unlink
- .quad compat_sys_mq_timedsend
- .quad compat_sys_mq_timedreceive /* 280 */
- .quad compat_sys_mq_notify
- .quad compat_sys_mq_getsetattr
- .quad compat_sys_kexec_load /* reserved for kexec */
- .quad compat_sys_waitid
- .quad quiet_ni_syscall /* 285: sys_altroot */
- .quad sys_add_key
- .quad sys_request_key
- .quad sys_keyctl
- .quad sys_ioprio_set
- .quad sys_ioprio_get /* 290 */
- .quad sys_inotify_init
- .quad sys_inotify_add_watch
- .quad sys_inotify_rm_watch
- .quad sys_migrate_pages
- .quad compat_sys_openat /* 295 */
- .quad sys_mkdirat
- .quad sys_mknodat
- .quad sys_fchownat
- .quad compat_sys_futimesat
- .quad sys32_fstatat /* 300 */
- .quad sys_unlinkat
- .quad sys_renameat
- .quad sys_linkat
- .quad sys_symlinkat
- .quad sys_readlinkat /* 305 */
- .quad sys_fchmodat
- .quad sys_faccessat
- .quad compat_sys_pselect6
- .quad compat_sys_ppoll
- .quad sys_unshare /* 310 */
- .quad compat_sys_set_robust_list
- .quad compat_sys_get_robust_list
- .quad sys_splice
- .quad sys32_sync_file_range
- .quad sys_tee /* 315 */
- .quad compat_sys_vmsplice
- .quad compat_sys_move_pages
- .quad sys_getcpu
- .quad sys_epoll_pwait
- .quad compat_sys_utimensat /* 320 */
- .quad compat_sys_signalfd
- .quad sys_timerfd_create
- .quad sys_eventfd
- .quad sys32_fallocate
- .quad compat_sys_timerfd_settime /* 325 */
- .quad compat_sys_timerfd_gettime
- .quad compat_sys_signalfd4
- .quad sys_eventfd2
- .quad sys_epoll_create1
- .quad sys_dup3 /* 330 */
- .quad sys_pipe2
- .quad sys_inotify_init1
- .quad compat_sys_preadv
- .quad compat_sys_pwritev
- .quad compat_sys_rt_tgsigqueueinfo /* 335 */
- .quad sys_perf_event_open
- .quad compat_sys_recvmmsg
- .quad sys_fanotify_init
- .quad sys32_fanotify_mark
- .quad sys_prlimit64 /* 340 */
- .quad sys_name_to_handle_at
- .quad compat_sys_open_by_handle_at
- .quad compat_sys_clock_adjtime
- .quad sys_syncfs
- .quad compat_sys_sendmmsg /* 345 */
- .quad sys_setns
- .quad compat_sys_process_vm_readv
- .quad compat_sys_process_vm_writev
-ia32_syscall_end:
diff --git a/arch/x86/ia32/nosyscall.c b/arch/x86/ia32/nosyscall.c
new file mode 100644
index 000000000000..51ecd5b4e787
--- /dev/null
+++ b/arch/x86/ia32/nosyscall.c
@@ -0,0 +1,7 @@
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+long compat_ni_syscall(void)
+{
+ return -ENOSYS;
+}
diff --git a/arch/x86/ia32/syscall_ia32.c b/arch/x86/ia32/syscall_ia32.c
new file mode 100644
index 000000000000..4754ba0f5d9f
--- /dev/null
+++ b/arch/x86/ia32/syscall_ia32.c
@@ -0,0 +1,25 @@
+/* System call table for ia32 emulation. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void compat(void) ;
+#include <asm/syscalls_32.h>
+#undef __SYSCALL_I386
+
+#define __SYSCALL_I386(nr, sym, compat) [nr] = compat,
+
+typedef void (*sys_call_ptr_t)(void);
+
+extern void compat_ni_syscall(void);
+
+const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_ia32_syscall_max] = &compat_ni_syscall,
+#include <asm/syscalls_32.h>
+};
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 6fa90a845e4c..b57e6a43a37a 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -19,7 +19,8 @@ header-y += processor-flags.h
header-y += ptrace-abi.h
header-y += sigcontext32.h
header-y += ucontext.h
-header-y += unistd_32.h
-header-y += unistd_64.h
header-y += vm86.h
header-y += vsyscall.h
+
+genhdr-y += unistd_32.h
+genhdr-y += unistd_64.h
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 8e41071704a5..49ad773f4b9f 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -1,6 +1,7 @@
#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 {
@@ -13,6 +14,7 @@ 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);
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 24098aafce0d..fa13f0ec2874 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -82,7 +82,7 @@ static inline void atomic64_set(atomic64_t *v, long long i)
*
* Atomically reads the value of @v and returns it.
*/
-static inline long long atomic64_read(atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
{
long long r;
asm volatile(ATOMIC64_ALTERNATIVE(read)
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index e020d88ec02d..2f90c51cc49d 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -64,6 +64,8 @@ struct setup_header {
__u32 payload_offset;
__u32 payload_length;
__u64 setup_data;
+ __u64 pref_address;
+ __u32 init_size;
} __attribute__((packed));
struct sys_desc_table {
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 0c9fa2745f13..b3b733262909 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
#ifdef __HAVE_ARCH_CMPXCHG
#define cmpxchg(ptr, old, new) \
- __cmpxchg((ptr), (old), (new), sizeof(*ptr))
+ __cmpxchg(ptr, old, new, sizeof(*(ptr)))
#define sync_cmpxchg(ptr, old, new) \
- __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+ __sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
#define cmpxchg_local(ptr, old, new) \
- __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+ __cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
#endif
/*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 17c5d4bdee5e..8d67d428b0f9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -159,6 +159,7 @@
#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 */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 078ad0caefc6..b903d5ea3941 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -101,6 +101,28 @@ extern void aout_dump_debugregs(struct user *dump);
extern void hw_breakpoint_restore(void);
+#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 /* __KERNEL__ */
#endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 41935fadfdfc..e95822d683f4 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -35,6 +35,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
extern struct desc_ptr idt_descr;
extern gate_desc idt_table[];
+extern struct desc_ptr nmi_idt_descr;
+extern gate_desc nmi_idt_table[];
struct gdt_page {
struct desc_struct gdt[GDT_ENTRIES];
@@ -307,6 +309,16 @@ 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(nmi_idt_table, gate, &s);
+}
+#endif
+
static inline void _set_gate(int gate, unsigned type, void *addr,
unsigned dpl, unsigned ist, unsigned seg)
{
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 7093e4a6a0bc..844f735fd63a 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -3,6 +3,8 @@
#ifdef CONFIG_X86_32
+#define EFI_LOADER_SIGNATURE "EL32"
+
extern unsigned long asmlinkage efi_call_phys(void *, ...);
#define efi_call_phys0(f) efi_call_phys(f)
@@ -37,6 +39,8 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
#else /* !CONFIG_X86_32 */
+#define EFI_LOADER_SIGNATURE "EL64"
+
extern u64 efi_call0(void *fp);
extern u64 efi_call1(void *fp, u64 arg1);
extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 460c74e4852c..4da3c0c4c974 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -117,7 +117,7 @@ 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_MRST
+#ifdef CONFIG_X86_INTEL_MID
FIX_LNW_VRTC,
#endif
__end_of_permanent_fixed_addresses,
diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h
index 976f6ecd2ce6..b0d5716ca1e4 100644
--- a/arch/x86/include/asm/ia32_unistd.h
+++ b/arch/x86/include/asm/ia32_unistd.h
@@ -2,17 +2,10 @@
#define _ASM_X86_IA32_UNISTD_H
/*
- * This file contains the system call numbers of the ia32 port,
+ * This file contains the system call numbers of the ia32 compat ABI,
* this is for the kernel only.
- * Only add syscalls here where some part of the kernel needs to know
- * the number. This should be otherwise in sync with asm-x86/unistd_32.h. -AK
*/
-
-#define __NR_ia32_restart_syscall 0
-#define __NR_ia32_exit 1
-#define __NR_ia32_read 3
-#define __NR_ia32_write 4
-#define __NR_ia32_sigreturn 119
-#define __NR_ia32_rt_sigreturn 173
+#define __SYSCALL_ia32_NR(x) (x)
+#include <asm/unistd_32_ia32.h>
#endif /* _ASM_X86_IA32_UNISTD_H */
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 8dbe353e41e1..adcc0ae73d09 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -5,6 +5,8 @@
extern void __init early_ioremap_page_table_range_init(void);
#endif
+extern void __init zone_sizes_init(void);
+
extern unsigned long __init
kernel_physical_mapping_init(unsigned long start,
unsigned long end,
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 345c99cef152..dffc38ee6255 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -5,6 +5,7 @@ extern struct dma_map_ops nommu_dma_ops;
extern int force_iommu, no_iommu;
extern int iommu_detected;
extern int iommu_pass_through;
+extern int iommu_group_mf;
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index f35ce43c1a77..6aefb14cbbc5 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -151,7 +151,7 @@ static inline void enable_p5_mce(void) {}
void mce_setup(struct mce *m);
void mce_log(struct mce *m);
-DECLARE_PER_CPU(struct device, mce_device);
+extern struct device *mce_device[CONFIG_NR_CPUS];
/*
* Maximum banks number.
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d498943b906c..df75d07571ce 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -112,19 +112,28 @@ static inline void x86_teardown_msi_irq(unsigned int irq)
{
x86_msi.teardown_msi_irq(irq);
}
+static inline void x86_restore_msi_irqs(struct pci_dev *dev, int irq)
+{
+ x86_msi.restore_msi_irqs(dev, irq);
+}
#define arch_setup_msi_irqs x86_setup_msi_irqs
#define arch_teardown_msi_irqs x86_teardown_msi_irqs
#define arch_teardown_msi_irq x86_teardown_msi_irq
+#define arch_restore_msi_irqs x86_restore_msi_irqs
/* implemented in arch/x86/kernel/apic/io_apic. */
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
void native_teardown_msi_irq(unsigned int irq);
+void native_restore_msi_irqs(struct pci_dev *dev, int irq);
/* default to the implementation in drivers/lib/msi.c */
#define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+#define HAVE_DEFAULT_MSI_RESTORE_IRQS
void default_teardown_msi_irqs(struct pci_dev *dev);
+void default_restore_msi_irqs(struct pci_dev *dev, int irq);
#else
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
#define default_teardown_msi_irqs NULL
+#define default_restore_msi_irqs NULL
#endif
#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index e38197806853..b3a531746026 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -44,8 +44,6 @@ enum pci_bf_sort_state {
/* pci-i386.c */
-extern unsigned int pcibios_max_latency;
-
void pcibios_resource_survey(void);
void pcibios_set_cache_line_size(void);
diff --git a/arch/x86/include/asm/serpent.h b/arch/x86/include/asm/serpent.h
new file mode 100644
index 000000000000..d3ef63fe0c81
--- /dev/null
+++ b/arch/x86/include/asm/serpent.h
@@ -0,0 +1,63 @@
+#ifndef ASM_X86_SERPENT_H
+#define ASM_X86_SERPENT_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/setup.h b/arch/x86/include/asm/setup.h
index 9756551ec760..d0f19f9fb846 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -47,7 +47,7 @@ extern void reserve_standard_io_resources(void);
extern void i386_reserve_resources(void);
extern void setup_default_timer_irq(void);
-#ifdef CONFIG_X86_MRST
+#ifdef CONFIG_X86_INTEL_MID
extern void x86_mrst_early_setup(void);
#else
static inline void x86_mrst_early_setup(void) { }
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 73b11bc0ae6f..0434c400287c 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -225,5 +225,11 @@ extern int hard_smp_processor_id(void);
#endif /* CONFIG_X86_LOCAL_APIC */
+#ifdef CONFIG_DEBUG_NMI_SELFTEST
+extern void nmi_selftest(void);
+#else
+#define nmi_selftest() do { } while (0)
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index c4a348f7bd43..d962e5652a73 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -15,6 +15,7 @@
#include <linux/sched.h>
#include <linux/err.h>
+#include <asm/asm-offsets.h> /* For NR_syscalls */
extern const unsigned long sys_call_table[];
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 74047159d0ab..bc817cd8b443 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -40,8 +40,8 @@ struct thread_info {
*/
__u8 supervisor_stack[0];
#endif
- int sig_on_uaccess_error:1;
- int uaccess_err:1; /* uaccess failed */
+ unsigned int sig_on_uaccess_error:1;
+ unsigned int uaccess_err:1; /* uaccess failed */
};
#define INIT_THREAD_INFO(tsk) \
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 800f77c60051..b9676ae37ada 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -172,7 +172,7 @@ static inline void arch_fix_phys_package_id(int num, u32 slot)
}
struct pci_bus;
-void x86_pci_root_bus_res_quirks(struct pci_bus *b);
+void x86_pci_root_bus_resources(int bus, struct list_head *resources);
#ifdef CONFIG_SMP
#define mc_capable() ((boot_cpu_data.x86_max_cores > 1) && \
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 2a58ed3e51d8..21f77b89e47a 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -1,13 +1,60 @@
+#ifndef _ASM_X86_UNISTD_H
+#define _ASM_X86_UNISTD_H 1
+
#ifdef __KERNEL__
# ifdef CONFIG_X86_32
-# include "unistd_32.h"
+
+# include <asm/unistd_32.h>
+# define __ARCH_WANT_IPC_PARSE_VERSION
+# define __ARCH_WANT_STAT64
+# define __ARCH_WANT_SYS_IPC
+# define __ARCH_WANT_SYS_OLD_MMAP
+# define __ARCH_WANT_SYS_OLD_SELECT
+
# else
-# include "unistd_64.h"
+
+# include <asm/unistd_64.h>
+# define __ARCH_WANT_COMPAT_SYS_TIME
+
# endif
+
+# define __ARCH_WANT_OLD_READDIR
+# define __ARCH_WANT_OLD_STAT
+# define __ARCH_WANT_SYS_ALARM
+# define __ARCH_WANT_SYS_FADVISE64
+# define __ARCH_WANT_SYS_GETHOSTNAME
+# define __ARCH_WANT_SYS_GETPGRP
+# define __ARCH_WANT_SYS_LLSEEK
+# define __ARCH_WANT_SYS_NICE
+# define __ARCH_WANT_SYS_OLDUMOUNT
+# define __ARCH_WANT_SYS_OLD_GETRLIMIT
+# define __ARCH_WANT_SYS_OLD_UNAME
+# define __ARCH_WANT_SYS_PAUSE
+# define __ARCH_WANT_SYS_RT_SIGACTION
+# define __ARCH_WANT_SYS_RT_SIGSUSPEND
+# define __ARCH_WANT_SYS_SGETMASK
+# define __ARCH_WANT_SYS_SIGNAL
+# define __ARCH_WANT_SYS_SIGPENDING
+# define __ARCH_WANT_SYS_SIGPROCMASK
+# define __ARCH_WANT_SYS_SOCKETCALL
+# define __ARCH_WANT_SYS_TIME
+# define __ARCH_WANT_SYS_UTIME
+# define __ARCH_WANT_SYS_WAITPID
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+# define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+
#else
# ifdef __i386__
-# include "unistd_32.h"
+# include <asm/unistd_32.h>
# else
-# include "unistd_64.h"
+# include <asm/unistd_64.h>
# endif
#endif
+
+#endif /* _ASM_X86_UNISTD_H */
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
deleted file mode 100644
index 599c77d38f33..000000000000
--- a/arch/x86/include/asm/unistd_32.h
+++ /dev/null
@@ -1,401 +0,0 @@
-#ifndef _ASM_X86_UNISTD_32_H
-#define _ASM_X86_UNISTD_32_H
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_restart_syscall 0
-#define __NR_exit 1
-#define __NR_fork 2
-#define __NR_read 3
-#define __NR_write 4
-#define __NR_open 5
-#define __NR_close 6
-#define __NR_waitpid 7
-#define __NR_creat 8
-#define __NR_link 9
-#define __NR_unlink 10
-#define __NR_execve 11
-#define __NR_chdir 12
-#define __NR_time 13
-#define __NR_mknod 14
-#define __NR_chmod 15
-#define __NR_lchown 16
-#define __NR_break 17
-#define __NR_oldstat 18
-#define __NR_lseek 19
-#define __NR_getpid 20
-#define __NR_mount 21
-#define __NR_umount 22
-#define __NR_setuid 23
-#define __NR_getuid 24
-#define __NR_stime 25
-#define __NR_ptrace 26
-#define __NR_alarm 27
-#define __NR_oldfstat 28
-#define __NR_pause 29
-#define __NR_utime 30
-#define __NR_stty 31
-#define __NR_gtty 32
-#define __NR_access 33
-#define __NR_nice 34
-#define __NR_ftime 35
-#define __NR_sync 36
-#define __NR_kill 37
-#define __NR_rename 38
-#define __NR_mkdir 39
-#define __NR_rmdir 40
-#define __NR_dup 41
-#define __NR_pipe 42
-#define __NR_times 43
-#define __NR_prof 44
-#define __NR_brk 45
-#define __NR_setgid 46
-#define __NR_getgid 47
-#define __NR_signal 48
-#define __NR_geteuid 49
-#define __NR_getegid 50
-#define __NR_acct 51
-#define __NR_umount2 52
-#define __NR_lock 53
-#define __NR_ioctl 54
-#define __NR_fcntl 55
-#define __NR_mpx 56
-#define __NR_setpgid 57
-#define __NR_ulimit 58
-#define __NR_oldolduname 59
-#define __NR_umask 60
-#define __NR_chroot 61
-#define __NR_ustat 62
-#define __NR_dup2 63
-#define __NR_getppid 64
-#define __NR_getpgrp 65
-#define __NR_setsid 66
-#define __NR_sigaction 67
-#define __NR_sgetmask 68
-#define __NR_ssetmask 69
-#define __NR_setreuid 70
-#define __NR_setregid 71
-#define __NR_sigsuspend 72
-#define __NR_sigpending 73
-#define __NR_sethostname 74
-#define __NR_setrlimit 75
-#define __NR_getrlimit 76 /* Back compatible 2Gig limited rlimit */
-#define __NR_getrusage 77
-#define __NR_gettimeofday 78
-#define __NR_settimeofday 79
-#define __NR_getgroups 80
-#define __NR_setgroups 81
-#define __NR_select 82
-#define __NR_symlink 83
-#define __NR_oldlstat 84
-#define __NR_readlink 85
-#define __NR_uselib 86
-#define __NR_swapon 87
-#define __NR_reboot 88
-#define __NR_readdir 89
-#define __NR_mmap 90
-#define __NR_munmap 91
-#define __NR_truncate 92
-#define __NR_ftruncate 93
-#define __NR_fchmod 94
-#define __NR_fchown 95
-#define __NR_getpriority 96
-#define __NR_setpriority 97
-#define __NR_profil 98
-#define __NR_statfs 99
-#define __NR_fstatfs 100
-#define __NR_ioperm 101
-#define __NR_socketcall 102
-#define __NR_syslog 103
-#define __NR_setitimer 104
-#define __NR_getitimer 105
-#define __NR_stat 106
-#define __NR_lstat 107
-#define __NR_fstat 108
-#define __NR_olduname 109
-#define __NR_iopl 110
-#define __NR_vhangup 111
-#define __NR_idle 112
-#define __NR_vm86old 113
-#define __NR_wait4 114
-#define __NR_swapoff 115
-#define __NR_sysinfo 116
-#define __NR_ipc 117
-#define __NR_fsync 118
-#define __NR_sigreturn 119
-#define __NR_clone 120
-#define __NR_setdomainname 121
-#define __NR_uname 122
-#define __NR_modify_ldt 123
-#define __NR_adjtimex 124
-#define __NR_mprotect 125
-#define __NR_sigprocmask 126
-#define __NR_create_module 127
-#define __NR_init_module 128
-#define __NR_delete_module 129
-#define __NR_get_kernel_syms 130
-#define __NR_quotactl 131
-#define __NR_getpgid 132
-#define __NR_fchdir 133
-#define __NR_bdflush 134
-#define __NR_sysfs 135
-#define __NR_personality 136
-#define __NR_afs_syscall 137 /* Syscall for Andrew File System */
-#define __NR_setfsuid 138
-#define __NR_setfsgid 139
-#define __NR__llseek 140
-#define __NR_getdents 141
-#define __NR__newselect 142
-#define __NR_flock 143
-#define __NR_msync 144
-#define __NR_readv 145
-#define __NR_writev 146
-#define __NR_getsid 147
-#define __NR_fdatasync 148
-#define __NR__sysctl 149
-#define __NR_mlock 150
-#define __NR_munlock 151
-#define __NR_mlockall 152
-#define __NR_munlockall 153
-#define __NR_sched_setparam 154
-#define __NR_sched_getparam 155
-#define __NR_sched_setscheduler 156
-#define __NR_sched_getscheduler 157
-#define __NR_sched_yield 158
-#define __NR_sched_get_priority_max 159
-#define __NR_sched_get_priority_min 160
-#define __NR_sched_rr_get_interval 161
-#define __NR_nanosleep 162
-#define __NR_mremap 163
-#define __NR_setresuid 164
-#define __NR_getresuid 165
-#define __NR_vm86 166
-#define __NR_query_module 167
-#define __NR_poll 168
-#define __NR_nfsservctl 169
-#define __NR_setresgid 170
-#define __NR_getresgid 171
-#define __NR_prctl 172
-#define __NR_rt_sigreturn 173
-#define __NR_rt_sigaction 174
-#define __NR_rt_sigprocmask 175
-#define __NR_rt_sigpending 176
-#define __NR_rt_sigtimedwait 177
-#define __NR_rt_sigqueueinfo 178
-#define __NR_rt_sigsuspend 179
-#define __NR_pread64 180
-#define __NR_pwrite64 181
-#define __NR_chown 182
-#define __NR_getcwd 183
-#define __NR_capget 184
-#define __NR_capset 185
-#define __NR_sigaltstack 186
-#define __NR_sendfile 187
-#define __NR_getpmsg 188 /* some people actually want streams */
-#define __NR_putpmsg 189 /* some people actually want streams */
-#define __NR_vfork 190
-#define __NR_ugetrlimit 191 /* SuS compliant getrlimit */
-#define __NR_mmap2 192
-#define __NR_truncate64 193
-#define __NR_ftruncate64 194
-#define __NR_stat64 195
-#define __NR_lstat64 196
-#define __NR_fstat64 197
-#define __NR_lchown32 198
-#define __NR_getuid32 199
-#define __NR_getgid32 200
-#define __NR_geteuid32 201
-#define __NR_getegid32 202
-#define __NR_setreuid32 203
-#define __NR_setregid32 204
-#define __NR_getgroups32 205
-#define __NR_setgroups32 206
-#define __NR_fchown32 207
-#define __NR_setresuid32 208
-#define __NR_getresuid32 209
-#define __NR_setresgid32 210
-#define __NR_getresgid32 211
-#define __NR_chown32 212
-#define __NR_setuid32 213
-#define __NR_setgid32 214
-#define __NR_setfsuid32 215
-#define __NR_setfsgid32 216
-#define __NR_pivot_root 217
-#define __NR_mincore 218
-#define __NR_madvise 219
-#define __NR_madvise1 219 /* delete when C lib stub is removed */
-#define __NR_getdents64 220
-#define __NR_fcntl64 221
-/* 223 is unused */
-#define __NR_gettid 224
-#define __NR_readahead 225
-#define __NR_setxattr 226
-#define __NR_lsetxattr 227
-#define __NR_fsetxattr 228
-#define __NR_getxattr 229
-#define __NR_lgetxattr 230
-#define __NR_fgetxattr 231
-#define __NR_listxattr 232
-#define __NR_llistxattr 233
-#define __NR_flistxattr 234
-#define __NR_removexattr 235
-#define __NR_lremovexattr 236
-#define __NR_fremovexattr 237
-#define __NR_tkill 238
-#define __NR_sendfile64 239
-#define __NR_futex 240
-#define __NR_sched_setaffinity 241
-#define __NR_sched_getaffinity 242
-#define __NR_set_thread_area 243
-#define __NR_get_thread_area 244
-#define __NR_io_setup 245
-#define __NR_io_destroy 246
-#define __NR_io_getevents 247
-#define __NR_io_submit 248
-#define __NR_io_cancel 249
-#define __NR_fadvise64 250
-/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */
-#define __NR_exit_group 252
-#define __NR_lookup_dcookie 253
-#define __NR_epoll_create 254
-#define __NR_epoll_ctl 255
-#define __NR_epoll_wait 256
-#define __NR_remap_file_pages 257
-#define __NR_set_tid_address 258
-#define __NR_timer_create 259
-#define __NR_timer_settime (__NR_timer_create+1)
-#define __NR_timer_gettime (__NR_timer_create+2)
-#define __NR_timer_getoverrun (__NR_timer_create+3)
-#define __NR_timer_delete (__NR_timer_create+4)
-#define __NR_clock_settime (__NR_timer_create+5)
-#define __NR_clock_gettime (__NR_timer_create+6)
-#define __NR_clock_getres (__NR_timer_create+7)
-#define __NR_clock_nanosleep (__NR_timer_create+8)
-#define __NR_statfs64 268
-#define __NR_fstatfs64 269
-#define __NR_tgkill 270
-#define __NR_utimes 271
-#define __NR_fadvise64_64 272
-#define __NR_vserver 273
-#define __NR_mbind 274
-#define __NR_get_mempolicy 275
-#define __NR_set_mempolicy 276
-#define __NR_mq_open 277
-#define __NR_mq_unlink (__NR_mq_open+1)
-#define __NR_mq_timedsend (__NR_mq_open+2)
-#define __NR_mq_timedreceive (__NR_mq_open+3)
-#define __NR_mq_notify (__NR_mq_open+4)
-#define __NR_mq_getsetattr (__NR_mq_open+5)
-#define __NR_kexec_load 283
-#define __NR_waitid 284
-/* #define __NR_sys_setaltroot 285 */
-#define __NR_add_key 286
-#define __NR_request_key 287
-#define __NR_keyctl 288
-#define __NR_ioprio_set 289
-#define __NR_ioprio_get 290
-#define __NR_inotify_init 291
-#define __NR_inotify_add_watch 292
-#define __NR_inotify_rm_watch 293
-#define __NR_migrate_pages 294
-#define __NR_openat 295
-#define __NR_mkdirat 296
-#define __NR_mknodat 297
-#define __NR_fchownat 298
-#define __NR_futimesat 299
-#define __NR_fstatat64 300
-#define __NR_unlinkat 301
-#define __NR_renameat 302
-#define __NR_linkat 303
-#define __NR_symlinkat 304
-#define __NR_readlinkat 305
-#define __NR_fchmodat 306
-#define __NR_faccessat 307
-#define __NR_pselect6 308
-#define __NR_ppoll 309
-#define __NR_unshare 310
-#define __NR_set_robust_list 311
-#define __NR_get_robust_list 312
-#define __NR_splice 313
-#define __NR_sync_file_range 314
-#define __NR_tee 315
-#define __NR_vmsplice 316
-#define __NR_move_pages 317
-#define __NR_getcpu 318
-#define __NR_epoll_pwait 319
-#define __NR_utimensat 320
-#define __NR_signalfd 321
-#define __NR_timerfd_create 322
-#define __NR_eventfd 323
-#define __NR_fallocate 324
-#define __NR_timerfd_settime 325
-#define __NR_timerfd_gettime 326
-#define __NR_signalfd4 327
-#define __NR_eventfd2 328
-#define __NR_epoll_create1 329
-#define __NR_dup3 330
-#define __NR_pipe2 331
-#define __NR_inotify_init1 332
-#define __NR_preadv 333
-#define __NR_pwritev 334
-#define __NR_rt_tgsigqueueinfo 335
-#define __NR_perf_event_open 336
-#define __NR_recvmmsg 337
-#define __NR_fanotify_init 338
-#define __NR_fanotify_mark 339
-#define __NR_prlimit64 340
-#define __NR_name_to_handle_at 341
-#define __NR_open_by_handle_at 342
-#define __NR_clock_adjtime 343
-#define __NR_syncfs 344
-#define __NR_sendmmsg 345
-#define __NR_setns 346
-#define __NR_process_vm_readv 347
-#define __NR_process_vm_writev 348
-
-#ifdef __KERNEL__
-
-#define NR_syscalls 349
-
-#define __ARCH_WANT_IPC_PARSE_VERSION
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_IPC
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLD_UNAME
-#define __ARCH_WANT_SYS_OLD_MMAP
-#define __ARCH_WANT_SYS_OLD_SELECT
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#ifndef cond_syscall
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#endif
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_X86_UNISTD_32_H */
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
deleted file mode 100644
index 0431f193c3f2..000000000000
--- a/arch/x86/include/asm/unistd_64.h
+++ /dev/null
@@ -1,732 +0,0 @@
-#ifndef _ASM_X86_UNISTD_64_H
-#define _ASM_X86_UNISTD_64_H
-
-#ifndef __SYSCALL
-#define __SYSCALL(a, b)
-#endif
-
-/*
- * This file contains the system call numbers.
- *
- * Note: holes are not allowed.
- */
-
-/* at least 8 syscall per cacheline */
-#define __NR_read 0
-__SYSCALL(__NR_read, sys_read)
-#define __NR_write 1
-__SYSCALL(__NR_write, sys_write)
-#define __NR_open 2
-__SYSCALL(__NR_open, sys_open)
-#define __NR_close 3
-__SYSCALL(__NR_close, sys_close)
-#define __NR_stat 4
-__SYSCALL(__NR_stat, sys_newstat)
-#define __NR_fstat 5
-__SYSCALL(__NR_fstat, sys_newfstat)
-#define __NR_lstat 6
-__SYSCALL(__NR_lstat, sys_newlstat)
-#define __NR_poll 7
-__SYSCALL(__NR_poll, sys_poll)
-
-#define __NR_lseek 8
-__SYSCALL(__NR_lseek, sys_lseek)
-#define __NR_mmap 9
-__SYSCALL(__NR_mmap, sys_mmap)
-#define __NR_mprotect 10
-__SYSCALL(__NR_mprotect, sys_mprotect)
-#define __NR_munmap 11
-__SYSCALL(__NR_munmap, sys_munmap)
-#define __NR_brk 12
-__SYSCALL(__NR_brk, sys_brk)
-#define __NR_rt_sigaction 13
-__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction)
-#define __NR_rt_sigprocmask 14
-__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask)
-#define __NR_rt_sigreturn 15
-__SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn)
-
-#define __NR_ioctl 16
-__SYSCALL(__NR_ioctl, sys_ioctl)
-#define __NR_pread64 17
-__SYSCALL(__NR_pread64, sys_pread64)
-#define __NR_pwrite64 18
-__SYSCALL(__NR_pwrite64, sys_pwrite64)
-#define __NR_readv 19
-__SYSCALL(__NR_readv, sys_readv)
-#define __NR_writev 20
-__SYSCALL(__NR_writev, sys_writev)
-#define __NR_access 21
-__SYSCALL(__NR_access, sys_access)
-#define __NR_pipe 22
-__SYSCALL(__NR_pipe, sys_pipe)
-#define __NR_select 23
-__SYSCALL(__NR_select, sys_select)
-
-#define __NR_sched_yield 24
-__SYSCALL(__NR_sched_yield, sys_sched_yield)
-#define __NR_mremap 25
-__SYSCALL(__NR_mremap, sys_mremap)
-#define __NR_msync 26
-__SYSCALL(__NR_msync, sys_msync)
-#define __NR_mincore 27
-__SYSCALL(__NR_mincore, sys_mincore)
-#define __NR_madvise 28
-__SYSCALL(__NR_madvise, sys_madvise)
-#define __NR_shmget 29
-__SYSCALL(__NR_shmget, sys_shmget)
-#define __NR_shmat 30
-__SYSCALL(__NR_shmat, sys_shmat)
-#define __NR_shmctl 31
-__SYSCALL(__NR_shmctl, sys_shmctl)
-
-#define __NR_dup 32
-__SYSCALL(__NR_dup, sys_dup)
-#define __NR_dup2 33
-__SYSCALL(__NR_dup2, sys_dup2)
-#define __NR_pause 34
-__SYSCALL(__NR_pause, sys_pause)
-#define __NR_nanosleep 35
-__SYSCALL(__NR_nanosleep, sys_nanosleep)
-#define __NR_getitimer 36
-__SYSCALL(__NR_getitimer, sys_getitimer)
-#define __NR_alarm 37
-__SYSCALL(__NR_alarm, sys_alarm)
-#define __NR_setitimer 38
-__SYSCALL(__NR_setitimer, sys_setitimer)
-#define __NR_getpid 39
-__SYSCALL(__NR_getpid, sys_getpid)
-
-#define __NR_sendfile 40
-__SYSCALL(__NR_sendfile, sys_sendfile64)
-#define __NR_socket 41
-__SYSCALL(__NR_socket, sys_socket)
-#define __NR_connect 42
-__SYSCALL(__NR_connect, sys_connect)
-#define __NR_accept 43
-__SYSCALL(__NR_accept, sys_accept)
-#define __NR_sendto 44
-__SYSCALL(__NR_sendto, sys_sendto)
-#define __NR_recvfrom 45
-__SYSCALL(__NR_recvfrom, sys_recvfrom)
-#define __NR_sendmsg 46
-__SYSCALL(__NR_sendmsg, sys_sendmsg)
-#define __NR_recvmsg 47
-__SYSCALL(__NR_recvmsg, sys_recvmsg)
-
-#define __NR_shutdown 48
-__SYSCALL(__NR_shutdown, sys_shutdown)
-#define __NR_bind 49
-__SYSCALL(__NR_bind, sys_bind)
-#define __NR_listen 50
-__SYSCALL(__NR_listen, sys_listen)
-#define __NR_getsockname 51
-__SYSCALL(__NR_getsockname, sys_getsockname)
-#define __NR_getpeername 52
-__SYSCALL(__NR_getpeername, sys_getpeername)
-#define __NR_socketpair 53
-__SYSCALL(__NR_socketpair, sys_socketpair)
-#define __NR_setsockopt 54
-__SYSCALL(__NR_setsockopt, sys_setsockopt)
-#define __NR_getsockopt 55
-__SYSCALL(__NR_getsockopt, sys_getsockopt)
-
-#define __NR_clone 56
-__SYSCALL(__NR_clone, stub_clone)
-#define __NR_fork 57
-__SYSCALL(__NR_fork, stub_fork)
-#define __NR_vfork 58
-__SYSCALL(__NR_vfork, stub_vfork)
-#define __NR_execve 59
-__SYSCALL(__NR_execve, stub_execve)
-#define __NR_exit 60
-__SYSCALL(__NR_exit, sys_exit)
-#define __NR_wait4 61
-__SYSCALL(__NR_wait4, sys_wait4)
-#define __NR_kill 62
-__SYSCALL(__NR_kill, sys_kill)
-#define __NR_uname 63
-__SYSCALL(__NR_uname, sys_newuname)
-
-#define __NR_semget 64
-__SYSCALL(__NR_semget, sys_semget)
-#define __NR_semop 65
-__SYSCALL(__NR_semop, sys_semop)
-#define __NR_semctl 66
-__SYSCALL(__NR_semctl, sys_semctl)
-#define __NR_shmdt 67
-__SYSCALL(__NR_shmdt, sys_shmdt)
-#define __NR_msgget 68
-__SYSCALL(__NR_msgget, sys_msgget)
-#define __NR_msgsnd 69
-__SYSCALL(__NR_msgsnd, sys_msgsnd)
-#define __NR_msgrcv 70
-__SYSCALL(__NR_msgrcv, sys_msgrcv)
-#define __NR_msgctl 71
-__SYSCALL(__NR_msgctl, sys_msgctl)
-
-#define __NR_fcntl 72
-__SYSCALL(__NR_fcntl, sys_fcntl)
-#define __NR_flock 73
-__SYSCALL(__NR_flock, sys_flock)
-#define __NR_fsync 74
-__SYSCALL(__NR_fsync, sys_fsync)
-#define __NR_fdatasync 75
-__SYSCALL(__NR_fdatasync, sys_fdatasync)
-#define __NR_truncate 76
-__SYSCALL(__NR_truncate, sys_truncate)
-#define __NR_ftruncate 77
-__SYSCALL(__NR_ftruncate, sys_ftruncate)
-#define __NR_getdents 78
-__SYSCALL(__NR_getdents, sys_getdents)
-#define __NR_getcwd 79
-__SYSCALL(__NR_getcwd, sys_getcwd)
-
-#define __NR_chdir 80
-__SYSCALL(__NR_chdir, sys_chdir)
-#define __NR_fchdir 81
-__SYSCALL(__NR_fchdir, sys_fchdir)
-#define __NR_rename 82
-__SYSCALL(__NR_rename, sys_rename)
-#define __NR_mkdir 83
-__SYSCALL(__NR_mkdir, sys_mkdir)
-#define __NR_rmdir 84
-__SYSCALL(__NR_rmdir, sys_rmdir)
-#define __NR_creat 85
-__SYSCALL(__NR_creat, sys_creat)
-#define __NR_link 86
-__SYSCALL(__NR_link, sys_link)
-#define __NR_unlink 87
-__SYSCALL(__NR_unlink, sys_unlink)
-
-#define __NR_symlink 88
-__SYSCALL(__NR_symlink, sys_symlink)
-#define __NR_readlink 89
-__SYSCALL(__NR_readlink, sys_readlink)
-#define __NR_chmod 90
-__SYSCALL(__NR_chmod, sys_chmod)
-#define __NR_fchmod 91
-__SYSCALL(__NR_fchmod, sys_fchmod)
-#define __NR_chown 92
-__SYSCALL(__NR_chown, sys_chown)
-#define __NR_fchown 93
-__SYSCALL(__NR_fchown, sys_fchown)
-#define __NR_lchown 94
-__SYSCALL(__NR_lchown, sys_lchown)
-#define __NR_umask 95
-__SYSCALL(__NR_umask, sys_umask)
-
-#define __NR_gettimeofday 96
-__SYSCALL(__NR_gettimeofday, sys_gettimeofday)
-#define __NR_getrlimit 97
-__SYSCALL(__NR_getrlimit, sys_getrlimit)
-#define __NR_getrusage 98
-__SYSCALL(__NR_getrusage, sys_getrusage)
-#define __NR_sysinfo 99
-__SYSCALL(__NR_sysinfo, sys_sysinfo)
-#define __NR_times 100
-__SYSCALL(__NR_times, sys_times)
-#define __NR_ptrace 101
-__SYSCALL(__NR_ptrace, sys_ptrace)
-#define __NR_getuid 102
-__SYSCALL(__NR_getuid, sys_getuid)
-#define __NR_syslog 103
-__SYSCALL(__NR_syslog, sys_syslog)
-
-/* at the very end the stuff that never runs during the benchmarks */
-#define __NR_getgid 104
-__SYSCALL(__NR_getgid, sys_getgid)
-#define __NR_setuid 105
-__SYSCALL(__NR_setuid, sys_setuid)
-#define __NR_setgid 106
-__SYSCALL(__NR_setgid, sys_setgid)
-#define __NR_geteuid 107
-__SYSCALL(__NR_geteuid, sys_geteuid)
-#define __NR_getegid 108
-__SYSCALL(__NR_getegid, sys_getegid)
-#define __NR_setpgid 109
-__SYSCALL(__NR_setpgid, sys_setpgid)
-#define __NR_getppid 110
-__SYSCALL(__NR_getppid, sys_getppid)
-#define __NR_getpgrp 111
-__SYSCALL(__NR_getpgrp, sys_getpgrp)
-
-#define __NR_setsid 112
-__SYSCALL(__NR_setsid, sys_setsid)
-#define __NR_setreuid 113
-__SYSCALL(__NR_setreuid, sys_setreuid)
-#define __NR_setregid 114
-__SYSCALL(__NR_setregid, sys_setregid)
-#define __NR_getgroups 115
-__SYSCALL(__NR_getgroups, sys_getgroups)
-#define __NR_setgroups 116
-__SYSCALL(__NR_setgroups, sys_setgroups)
-#define __NR_setresuid 117
-__SYSCALL(__NR_setresuid, sys_setresuid)
-#define __NR_getresuid 118
-__SYSCALL(__NR_getresuid, sys_getresuid)
-#define __NR_setresgid 119
-__SYSCALL(__NR_setresgid, sys_setresgid)
-
-#define __NR_getresgid 120
-__SYSCALL(__NR_getresgid, sys_getresgid)
-#define __NR_getpgid 121
-__SYSCALL(__NR_getpgid, sys_getpgid)
-#define __NR_setfsuid 122
-__SYSCALL(__NR_setfsuid, sys_setfsuid)
-#define __NR_setfsgid 123
-__SYSCALL(__NR_setfsgid, sys_setfsgid)
-#define __NR_getsid 124
-__SYSCALL(__NR_getsid, sys_getsid)
-#define __NR_capget 125
-__SYSCALL(__NR_capget, sys_capget)
-#define __NR_capset 126
-__SYSCALL(__NR_capset, sys_capset)
-
-#define __NR_rt_sigpending 127
-__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending)
-#define __NR_rt_sigtimedwait 128
-__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
-#define __NR_rt_sigqueueinfo 129
-__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
-#define __NR_rt_sigsuspend 130
-__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend)
-#define __NR_sigaltstack 131
-__SYSCALL(__NR_sigaltstack, stub_sigaltstack)
-#define __NR_utime 132
-__SYSCALL(__NR_utime, sys_utime)
-#define __NR_mknod 133
-__SYSCALL(__NR_mknod, sys_mknod)
-
-/* Only needed for a.out */
-#define __NR_uselib 134
-__SYSCALL(__NR_uselib, sys_ni_syscall)
-#define __NR_personality 135
-__SYSCALL(__NR_personality, sys_personality)
-
-#define __NR_ustat 136
-__SYSCALL(__NR_ustat, sys_ustat)
-#define __NR_statfs 137
-__SYSCALL(__NR_statfs, sys_statfs)
-#define __NR_fstatfs 138
-__SYSCALL(__NR_fstatfs, sys_fstatfs)
-#define __NR_sysfs 139
-__SYSCALL(__NR_sysfs, sys_sysfs)
-
-#define __NR_getpriority 140
-__SYSCALL(__NR_getpriority, sys_getpriority)
-#define __NR_setpriority 141
-__SYSCALL(__NR_setpriority, sys_setpriority)
-#define __NR_sched_setparam 142
-__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
-#define __NR_sched_getparam 143
-__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
-#define __NR_sched_setscheduler 144
-__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
-#define __NR_sched_getscheduler 145
-__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
-#define __NR_sched_get_priority_max 146
-__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
-#define __NR_sched_get_priority_min 147
-__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
-#define __NR_sched_rr_get_interval 148
-__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval)
-
-#define __NR_mlock 149
-__SYSCALL(__NR_mlock, sys_mlock)
-#define __NR_munlock 150
-__SYSCALL(__NR_munlock, sys_munlock)
-#define __NR_mlockall 151
-__SYSCALL(__NR_mlockall, sys_mlockall)
-#define __NR_munlockall 152
-__SYSCALL(__NR_munlockall, sys_munlockall)
-
-#define __NR_vhangup 153
-__SYSCALL(__NR_vhangup, sys_vhangup)
-
-#define __NR_modify_ldt 154
-__SYSCALL(__NR_modify_ldt, sys_modify_ldt)
-
-#define __NR_pivot_root 155
-__SYSCALL(__NR_pivot_root, sys_pivot_root)
-
-#define __NR__sysctl 156
-__SYSCALL(__NR__sysctl, sys_sysctl)
-
-#define __NR_prctl 157
-__SYSCALL(__NR_prctl, sys_prctl)
-#define __NR_arch_prctl 158
-__SYSCALL(__NR_arch_prctl, sys_arch_prctl)
-
-#define __NR_adjtimex 159
-__SYSCALL(__NR_adjtimex, sys_adjtimex)
-
-#define __NR_setrlimit 160
-__SYSCALL(__NR_setrlimit, sys_setrlimit)
-
-#define __NR_chroot 161
-__SYSCALL(__NR_chroot, sys_chroot)
-
-#define __NR_sync 162
-__SYSCALL(__NR_sync, sys_sync)
-
-#define __NR_acct 163
-__SYSCALL(__NR_acct, sys_acct)
-
-#define __NR_settimeofday 164
-__SYSCALL(__NR_settimeofday, sys_settimeofday)
-
-#define __NR_mount 165
-__SYSCALL(__NR_mount, sys_mount)
-#define __NR_umount2 166
-__SYSCALL(__NR_umount2, sys_umount)
-
-#define __NR_swapon 167
-__SYSCALL(__NR_swapon, sys_swapon)
-#define __NR_swapoff 168
-__SYSCALL(__NR_swapoff, sys_swapoff)
-
-#define __NR_reboot 169
-__SYSCALL(__NR_reboot, sys_reboot)
-
-#define __NR_sethostname 170
-__SYSCALL(__NR_sethostname, sys_sethostname)
-#define __NR_setdomainname 171
-__SYSCALL(__NR_setdomainname, sys_setdomainname)
-
-#define __NR_iopl 172
-__SYSCALL(__NR_iopl, stub_iopl)
-#define __NR_ioperm 173
-__SYSCALL(__NR_ioperm, sys_ioperm)
-
-#define __NR_create_module 174
-__SYSCALL(__NR_create_module, sys_ni_syscall)
-#define __NR_init_module 175
-__SYSCALL(__NR_init_module, sys_init_module)
-#define __NR_delete_module 176
-__SYSCALL(__NR_delete_module, sys_delete_module)
-#define __NR_get_kernel_syms 177
-__SYSCALL(__NR_get_kernel_syms, sys_ni_syscall)
-#define __NR_query_module 178
-__SYSCALL(__NR_query_module, sys_ni_syscall)
-
-#define __NR_quotactl 179
-__SYSCALL(__NR_quotactl, sys_quotactl)
-
-#define __NR_nfsservctl 180
-__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
-
-/* reserved for LiS/STREAMS */
-#define __NR_getpmsg 181
-__SYSCALL(__NR_getpmsg, sys_ni_syscall)
-#define __NR_putpmsg 182
-__SYSCALL(__NR_putpmsg, sys_ni_syscall)
-
-/* reserved for AFS */
-#define __NR_afs_syscall 183
-__SYSCALL(__NR_afs_syscall, sys_ni_syscall)
-
-/* reserved for tux */
-#define __NR_tuxcall 184
-__SYSCALL(__NR_tuxcall, sys_ni_syscall)
-
-#define __NR_security 185
-__SYSCALL(__NR_security, sys_ni_syscall)
-
-#define __NR_gettid 186
-__SYSCALL(__NR_gettid, sys_gettid)
-
-#define __NR_readahead 187
-__SYSCALL(__NR_readahead, sys_readahead)
-#define __NR_setxattr 188
-__SYSCALL(__NR_setxattr, sys_setxattr)
-#define __NR_lsetxattr 189
-__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
-#define __NR_fsetxattr 190
-__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
-#define __NR_getxattr 191
-__SYSCALL(__NR_getxattr, sys_getxattr)
-#define __NR_lgetxattr 192
-__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
-#define __NR_fgetxattr 193
-__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
-#define __NR_listxattr 194
-__SYSCALL(__NR_listxattr, sys_listxattr)
-#define __NR_llistxattr 195
-__SYSCALL(__NR_llistxattr, sys_llistxattr)
-#define __NR_flistxattr 196
-__SYSCALL(__NR_flistxattr, sys_flistxattr)
-#define __NR_removexattr 197
-__SYSCALL(__NR_removexattr, sys_removexattr)
-#define __NR_lremovexattr 198
-__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
-#define __NR_fremovexattr 199
-__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
-#define __NR_tkill 200
-__SYSCALL(__NR_tkill, sys_tkill)
-#define __NR_time 201
-__SYSCALL(__NR_time, sys_time)
-#define __NR_futex 202
-__SYSCALL(__NR_futex, sys_futex)
-#define __NR_sched_setaffinity 203
-__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity)
-#define __NR_sched_getaffinity 204
-__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity)
-#define __NR_set_thread_area 205
-__SYSCALL(__NR_set_thread_area, sys_ni_syscall) /* use arch_prctl */
-#define __NR_io_setup 206
-__SYSCALL(__NR_io_setup, sys_io_setup)
-#define __NR_io_destroy 207
-__SYSCALL(__NR_io_destroy, sys_io_destroy)
-#define __NR_io_getevents 208
-__SYSCALL(__NR_io_getevents, sys_io_getevents)
-#define __NR_io_submit 209
-__SYSCALL(__NR_io_submit, sys_io_submit)
-#define __NR_io_cancel 210
-__SYSCALL(__NR_io_cancel, sys_io_cancel)
-#define __NR_get_thread_area 211
-__SYSCALL(__NR_get_thread_area, sys_ni_syscall) /* use arch_prctl */
-#define __NR_lookup_dcookie 212
-__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie)
-#define __NR_epoll_create 213
-__SYSCALL(__NR_epoll_create, sys_epoll_create)
-#define __NR_epoll_ctl_old 214
-__SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall)
-#define __NR_epoll_wait_old 215
-__SYSCALL(__NR_epoll_wait_old, sys_ni_syscall)
-#define __NR_remap_file_pages 216
-__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
-#define __NR_getdents64 217
-__SYSCALL(__NR_getdents64, sys_getdents64)
-#define __NR_set_tid_address 218
-__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
-#define __NR_restart_syscall 219
-__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
-#define __NR_semtimedop 220
-__SYSCALL(__NR_semtimedop, sys_semtimedop)
-#define __NR_fadvise64 221
-__SYSCALL(__NR_fadvise64, sys_fadvise64)
-#define __NR_timer_create 222
-__SYSCALL(__NR_timer_create, sys_timer_create)
-#define __NR_timer_settime 223
-__SYSCALL(__NR_timer_settime, sys_timer_settime)
-#define __NR_timer_gettime 224
-__SYSCALL(__NR_timer_gettime, sys_timer_gettime)
-#define __NR_timer_getoverrun 225
-__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
-#define __NR_timer_delete 226
-__SYSCALL(__NR_timer_delete, sys_timer_delete)
-#define __NR_clock_settime 227
-__SYSCALL(__NR_clock_settime, sys_clock_settime)
-#define __NR_clock_gettime 228
-__SYSCALL(__NR_clock_gettime, sys_clock_gettime)
-#define __NR_clock_getres 229
-__SYSCALL(__NR_clock_getres, sys_clock_getres)
-#define __NR_clock_nanosleep 230
-__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep)
-#define __NR_exit_group 231
-__SYSCALL(__NR_exit_group, sys_exit_group)
-#define __NR_epoll_wait 232
-__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
-#define __NR_epoll_ctl 233
-__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
-#define __NR_tgkill 234
-__SYSCALL(__NR_tgkill, sys_tgkill)
-#define __NR_utimes 235
-__SYSCALL(__NR_utimes, sys_utimes)
-#define __NR_vserver 236
-__SYSCALL(__NR_vserver, sys_ni_syscall)
-#define __NR_mbind 237
-__SYSCALL(__NR_mbind, sys_mbind)
-#define __NR_set_mempolicy 238
-__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
-#define __NR_get_mempolicy 239
-__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
-#define __NR_mq_open 240
-__SYSCALL(__NR_mq_open, sys_mq_open)
-#define __NR_mq_unlink 241
-__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
-#define __NR_mq_timedsend 242
-__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend)
-#define __NR_mq_timedreceive 243
-__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive)
-#define __NR_mq_notify 244
-__SYSCALL(__NR_mq_notify, sys_mq_notify)
-#define __NR_mq_getsetattr 245
-__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr)
-#define __NR_kexec_load 246
-__SYSCALL(__NR_kexec_load, sys_kexec_load)
-#define __NR_waitid 247
-__SYSCALL(__NR_waitid, sys_waitid)
-#define __NR_add_key 248
-__SYSCALL(__NR_add_key, sys_add_key)
-#define __NR_request_key 249
-__SYSCALL(__NR_request_key, sys_request_key)
-#define __NR_keyctl 250
-__SYSCALL(__NR_keyctl, sys_keyctl)
-#define __NR_ioprio_set 251
-__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
-#define __NR_ioprio_get 252
-__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
-#define __NR_inotify_init 253
-__SYSCALL(__NR_inotify_init, sys_inotify_init)
-#define __NR_inotify_add_watch 254
-__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
-#define __NR_inotify_rm_watch 255
-__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
-#define __NR_migrate_pages 256
-__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
-#define __NR_openat 257
-__SYSCALL(__NR_openat, sys_openat)
-#define __NR_mkdirat 258
-__SYSCALL(__NR_mkdirat, sys_mkdirat)
-#define __NR_mknodat 259
-__SYSCALL(__NR_mknodat, sys_mknodat)
-#define __NR_fchownat 260
-__SYSCALL(__NR_fchownat, sys_fchownat)
-#define __NR_futimesat 261
-__SYSCALL(__NR_futimesat, sys_futimesat)
-#define __NR_newfstatat 262
-__SYSCALL(__NR_newfstatat, sys_newfstatat)
-#define __NR_unlinkat 263
-__SYSCALL(__NR_unlinkat, sys_unlinkat)
-#define __NR_renameat 264
-__SYSCALL(__NR_renameat, sys_renameat)
-#define __NR_linkat 265
-__SYSCALL(__NR_linkat, sys_linkat)
-#define __NR_symlinkat 266
-__SYSCALL(__NR_symlinkat, sys_symlinkat)
-#define __NR_readlinkat 267
-__SYSCALL(__NR_readlinkat, sys_readlinkat)
-#define __NR_fchmodat 268
-__SYSCALL(__NR_fchmodat, sys_fchmodat)
-#define __NR_faccessat 269
-__SYSCALL(__NR_faccessat, sys_faccessat)
-#define __NR_pselect6 270
-__SYSCALL(__NR_pselect6, sys_pselect6)
-#define __NR_ppoll 271
-__SYSCALL(__NR_ppoll, sys_ppoll)
-#define __NR_unshare 272
-__SYSCALL(__NR_unshare, sys_unshare)
-#define __NR_set_robust_list 273
-__SYSCALL(__NR_set_robust_list, sys_set_robust_list)
-#define __NR_get_robust_list 274
-__SYSCALL(__NR_get_robust_list, sys_get_robust_list)
-#define __NR_splice 275
-__SYSCALL(__NR_splice, sys_splice)
-#define __NR_tee 276
-__SYSCALL(__NR_tee, sys_tee)
-#define __NR_sync_file_range 277
-__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
-#define __NR_vmsplice 278
-__SYSCALL(__NR_vmsplice, sys_vmsplice)
-#define __NR_move_pages 279
-__SYSCALL(__NR_move_pages, sys_move_pages)
-#define __NR_utimensat 280
-__SYSCALL(__NR_utimensat, sys_utimensat)
-#define __NR_epoll_pwait 281
-__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait)
-#define __NR_signalfd 282
-__SYSCALL(__NR_signalfd, sys_signalfd)
-#define __NR_timerfd_create 283
-__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
-#define __NR_eventfd 284
-__SYSCALL(__NR_eventfd, sys_eventfd)
-#define __NR_fallocate 285
-__SYSCALL(__NR_fallocate, sys_fallocate)
-#define __NR_timerfd_settime 286
-__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
-#define __NR_timerfd_gettime 287
-__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
-#define __NR_accept4 288
-__SYSCALL(__NR_accept4, sys_accept4)
-#define __NR_signalfd4 289
-__SYSCALL(__NR_signalfd4, sys_signalfd4)
-#define __NR_eventfd2 290
-__SYSCALL(__NR_eventfd2, sys_eventfd2)
-#define __NR_epoll_create1 291
-__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
-#define __NR_dup3 292
-__SYSCALL(__NR_dup3, sys_dup3)
-#define __NR_pipe2 293
-__SYSCALL(__NR_pipe2, sys_pipe2)
-#define __NR_inotify_init1 294
-__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
-#define __NR_preadv 295
-__SYSCALL(__NR_preadv, sys_preadv)
-#define __NR_pwritev 296
-__SYSCALL(__NR_pwritev, sys_pwritev)
-#define __NR_rt_tgsigqueueinfo 297
-__SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo)
-#define __NR_perf_event_open 298
-__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
-#define __NR_recvmmsg 299
-__SYSCALL(__NR_recvmmsg, sys_recvmmsg)
-#define __NR_fanotify_init 300
-__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
-#define __NR_fanotify_mark 301
-__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
-#define __NR_prlimit64 302
-__SYSCALL(__NR_prlimit64, sys_prlimit64)
-#define __NR_name_to_handle_at 303
-__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
-#define __NR_open_by_handle_at 304
-__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
-#define __NR_clock_adjtime 305
-__SYSCALL(__NR_clock_adjtime, sys_clock_adjtime)
-#define __NR_syncfs 306
-__SYSCALL(__NR_syncfs, sys_syncfs)
-#define __NR_sendmmsg 307
-__SYSCALL(__NR_sendmmsg, sys_sendmmsg)
-#define __NR_setns 308
-__SYSCALL(__NR_setns, sys_setns)
-#define __NR_getcpu 309
-__SYSCALL(__NR_getcpu, sys_getcpu)
-#define __NR_process_vm_readv 310
-__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv)
-#define __NR_process_vm_writev 311
-__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev)
-
-#ifndef __NO_STUBS
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLD_UNAME
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_COMPAT_SYS_TIME
-#endif /* __NO_STUBS */
-
-#ifdef __KERNEL__
-
-#ifndef COMPILE_OFFSETS
-#include <asm/asm-offsets.h>
-#define NR_syscalls (__NR_syscall_max + 1)
-#endif
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_UNISTD_64_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 8e862aaf0d90..becf47b81735 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -65,7 +65,7 @@
* UV2: Bit 19 selects between
* (0): 10 microsecond timebase and
* (1): 80 microseconds
- * we're using 655us, similar to UV1: 65 units of 10us
+ * we're using 560us, similar to UV1: 65 units of 10us
*/
#define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
#define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (15UL)
@@ -167,6 +167,7 @@
#define FLUSH_RETRY_TIMEOUT 2
#define FLUSH_GIVEUP 3
#define FLUSH_COMPLETE 4
+#define FLUSH_RETRY_BUSYBUG 5
/*
* tuning the action when the numalink network is extremely delayed
@@ -235,10 +236,10 @@ struct bau_msg_payload {
/*
- * Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * UV1 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
* see table 4.2.3.0.1 in broacast_assist spec.
*/
-struct bau_msg_header {
+struct uv1_bau_msg_header {
unsigned int dest_subnodeid:6; /* must be 0x10, for the LB */
/* bits 5:0 */
unsigned int base_dest_nasid:15; /* nasid of the first bit */
@@ -318,19 +319,87 @@ struct bau_msg_header {
};
/*
+ * UV2 Message header: 16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see figure 9-2 of harp_sys.pdf
+ */
+struct uv2_bau_msg_header {
+ unsigned int base_dest_nasid:15; /* nasid of the first bit */
+ /* bits 14:0 */ /* in uvhub map */
+ unsigned int dest_subnodeid:5; /* must be 0x10, for the LB */
+ /* bits 19:15 */
+ unsigned int rsvd_1:1; /* must be zero */
+ /* bit 20 */
+ /* Address bits 59:21 */
+ /* bits 25:2 of address (44:21) are payload */
+ /* these next 24 bits become bytes 12-14 of msg */
+ /* bits 28:21 land in byte 12 */
+ unsigned int replied_to:1; /* sent as 0 by the source to
+ byte 12 */
+ /* bit 21 */
+ unsigned int msg_type:3; /* software type of the
+ message */
+ /* bits 24:22 */
+ unsigned int canceled:1; /* message canceled, resource
+ is to be freed*/
+ /* bit 25 */
+ unsigned int payload_1:3; /* not currently used */
+ /* bits 28:26 */
+
+ /* bits 36:29 land in byte 13 */
+ unsigned int payload_2a:3; /* not currently used */
+ unsigned int payload_2b:5; /* not currently used */
+ /* bits 36:29 */
+
+ /* bits 44:37 land in byte 14 */
+ unsigned int payload_3:8; /* not currently used */
+ /* bits 44:37 */
+
+ unsigned int rsvd_2:7; /* reserved */
+ /* bits 51:45 */
+ unsigned int swack_flag:1; /* software acknowledge flag */
+ /* bit 52 */
+ unsigned int rsvd_3a:3; /* must be zero */
+ unsigned int rsvd_3b:8; /* must be zero */
+ unsigned int rsvd_3c:8; /* must be zero */
+ unsigned int rsvd_3d:3; /* must be zero */
+ /* bits 74:53 */
+ unsigned int fairness:3; /* usually zero */
+ /* bits 77:75 */
+
+ unsigned int sequence:16; /* message sequence number */
+ /* bits 93:78 Suppl_A */
+ unsigned int chaining:1; /* next descriptor is part of
+ this activation*/
+ /* bit 94 */
+ unsigned int multilevel:1; /* multi-level multicast
+ format */
+ /* bit 95 */
+ unsigned int rsvd_4:24; /* ordered / source node /
+ source subnode / aging
+ must be zero */
+ /* bits 119:96 */
+ unsigned int command:8; /* message type */
+ /* bits 127:120 */
+};
+
+/*
* The activation descriptor:
* The format of the message to send, plus all accompanying control
* Should be 64 bytes
*/
struct bau_desc {
- struct pnmask distribution;
+ struct pnmask distribution;
/*
* message template, consisting of header and payload:
*/
- struct bau_msg_header header;
- struct bau_msg_payload payload;
+ union bau_msg_header {
+ struct uv1_bau_msg_header uv1_hdr;
+ struct uv2_bau_msg_header uv2_hdr;
+ } header;
+
+ struct bau_msg_payload payload;
};
-/*
+/* UV1:
* -payload-- ---------header------
* bytes 0-11 bits 41-56 bits 58-81
* A B (2) C (3)
@@ -340,6 +409,16 @@ struct bau_desc {
* bytes 0-11 bytes 12-14 bytes 16-17 (byte 15 filled in by hw as vector)
* ------------payload queue-----------
*/
+/* UV2:
+ * -payload-- ---------header------
+ * bytes 0-11 bits 70-78 bits 21-44
+ * A B (2) C (3)
+ *
+ * A/B/C are moved to:
+ * A C B
+ * bytes 0-11 bytes 12-14 bytes 16-17 (byte 15 filled in by hw as vector)
+ * ------------payload queue-----------
+ */
/*
* The payload queue on the destination side is an array of these.
@@ -385,7 +464,6 @@ struct bau_pq_entry {
struct msg_desc {
struct bau_pq_entry *msg;
int msg_slot;
- int swack_slot;
struct bau_pq_entry *queue_first;
struct bau_pq_entry *queue_last;
};
@@ -405,6 +483,7 @@ struct ptc_stats {
requests */
unsigned long s_stimeout; /* source side timeouts */
unsigned long s_dtimeout; /* destination side timeouts */
+ unsigned long s_strongnacks; /* number of strong nack's */
unsigned long s_time; /* time spent in sending side */
unsigned long s_retriesok; /* successful retries */
unsigned long s_ntargcpu; /* total number of cpu's
@@ -439,6 +518,9 @@ struct ptc_stats {
unsigned long s_retry_messages; /* retry broadcasts */
unsigned long s_bau_reenabled; /* for bau enable/disable */
unsigned long s_bau_disabled; /* for bau enable/disable */
+ unsigned long s_uv2_wars; /* uv2 workaround, perm. busy */
+ unsigned long s_uv2_wars_hw; /* uv2 workaround, hiwater */
+ unsigned long s_uv2_war_waits; /* uv2 workaround, long waits */
/* destination statistics */
unsigned long d_alltlb; /* times all tlb's on this
cpu were flushed */
@@ -511,9 +593,12 @@ struct bau_control {
short osnode;
short uvhub_cpu;
short uvhub;
+ short uvhub_version;
short cpus_in_socket;
short cpus_in_uvhub;
short partition_base_pnode;
+ short using_desc; /* an index, like uvhub_cpu */
+ unsigned int inuse_map;
unsigned short message_number;
unsigned short uvhub_quiesce;
short socket_acknowledge_count[DEST_Q_SIZE];
@@ -531,6 +616,7 @@ struct bau_control {
int cong_response_us;
int cong_reps;
int cong_period;
+ unsigned long clocks_per_100_usec;
cycles_t period_time;
long period_requests;
struct hub_and_pnode *thp;
@@ -591,6 +677,11 @@ static inline void write_mmr_sw_ack(unsigned long mr)
uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
}
+static inline void write_gmmr_sw_ack(int pnode, unsigned long mr)
+{
+ write_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
static inline unsigned long read_mmr_sw_ack(void)
{
return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 54a13aaebc40..21f7385badb8 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa)
/* UV global physical address --> socket phys RAM */
static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
{
- unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+ unsigned long paddr;
unsigned long remap_base = uv_hub_info->lowmem_remap_base;
unsigned long remap_top = uv_hub_info->lowmem_remap_top;
gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
- gpa = gpa & uv_hub_info->gpa_mask;
+ paddr = gpa & uv_hub_info->gpa_mask;
if (paddr >= remap_base && paddr < remap_base + remap_top)
paddr -= remap_base;
return paddr;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 1ac860a09849..517d4767ffdd 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -179,6 +179,7 @@ struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
void (*teardown_msi_irq)(unsigned int irq);
void (*teardown_msi_irqs)(struct pci_dev *dev);
+ void (*restore_msi_irqs)(struct pci_dev *dev, int irq);
};
extern struct x86_init_ops x86_init;
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8baca3c4871c..5369059c07a9 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -25,7 +25,8 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-y += probe_roms.o
obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
-obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o
+obj-y += syscall_$(BITS).o
+obj-$(CONFIG_X86_64) += vsyscall_64.o
obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
@@ -80,6 +81,7 @@ obj-$(CONFIG_APB_TIMER) += apb_timer.o
obj-$(CONFIG_AMD_NB) += amd_nb.o
obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
+obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
obj-$(CONFIG_KVM_GUEST) += kvm.o
obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 013c1810ce72..be16854591cc 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -119,6 +119,37 @@ bool __init early_is_amd_nb(u32 device)
return false;
}
+struct resource *amd_get_mmconfig_range(struct resource *res)
+{
+ u32 address;
+ u64 base, msr;
+ unsigned segn_busn_bits;
+
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+ return NULL;
+
+ /* assume all cpus from fam10h have mmconfig */
+ if (boot_cpu_data.x86 < 0x10)
+ return NULL;
+
+ address = MSR_FAM10H_MMIO_CONF_BASE;
+ rdmsrl(address, msr);
+
+ /* mmconfig is not enabled */
+ if (!(msr & FAM10H_MMIO_CONF_ENABLE))
+ return NULL;
+
+ base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
+
+ segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
+ FAM10H_MMIO_CONF_BUSRANGE_MASK;
+
+ res->flags = IORESOURCE_MEM;
+ res->start = base;
+ res->end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
+ return res;
+}
+
int amd_get_subcaches(int cpu)
{
struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 9d59bbacd4e3..79b05b88aa19 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -769,7 +769,12 @@ void __init uv_system_init(void)
for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
uv_possible_blades +=
hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
- printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
+
+ /* uv_num_possible_blades() is really the hub count */
+ printk(KERN_INFO "UV: Found %d blades, %d hubs\n",
+ is_uv1_hub() ? uv_num_possible_blades() :
+ (uv_num_possible_blades() + 1) / 2,
+ uv_num_possible_blades());
bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
uv_blade_info = kzalloc(bytes, GFP_KERNEL);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index a46bd383953c..f76623cbe263 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -383,21 +383,21 @@ static int ignore_sys_suspend;
static int ignore_normal_resume;
static int bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL;
-static int debug __read_mostly;
-static int smp __read_mostly;
+static bool debug __read_mostly;
+static bool smp __read_mostly;
static int apm_disabled = -1;
#ifdef CONFIG_SMP
-static int power_off;
+static bool power_off;
#else
-static int power_off = 1;
+static bool power_off = 1;
#endif
-static int realmode_power_off;
+static bool realmode_power_off;
#ifdef CONFIG_APM_ALLOW_INTS
-static int allow_ints = 1;
+static bool allow_ints = 1;
#else
-static int allow_ints;
+static bool allow_ints;
#endif
-static int broken_psr;
+static bool broken_psr;
static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue);
static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 4f13fafc5264..68de2dc962ec 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -67,4 +67,6 @@ void common(void) {
OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
OFFSET(BP_version, boot_params, hdr.version);
OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
+ OFFSET(BP_pref_address, boot_params, hdr.pref_address);
+ OFFSET(BP_code32_start, boot_params, hdr.code32_start);
}
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 395a10e68067..85d98ab15cdc 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -3,6 +3,11 @@
#include <linux/lguest.h>
#include "../../../drivers/lguest/lg.h"
+#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+static char syscalls[] = {
+#include <asm/syscalls_32.h>
+};
+
/* workaround for a warning with -Wmissing-prototypes */
void foo(void);
@@ -76,4 +81,7 @@ void foo(void)
OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
#endif
+ BLANK();
+ DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+ DEFINE(NR_syscalls, sizeof(syscalls));
}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index e72a1194af22..834e897b1e25 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,11 +1,12 @@
#include <asm/ia32.h>
-#define __NO_STUBS 1
-#undef __SYSCALL
-#undef _ASM_X86_UNISTD_64_H
-#define __SYSCALL(nr, sym) [nr] = 1,
-static char syscalls[] = {
-#include <asm/unistd.h>
+#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+static char syscalls_64[] = {
+#include <asm/syscalls_64.h>
+};
+#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+static char syscalls_ia32[] = {
+#include <asm/syscalls_32.h>
};
int main(void)
@@ -72,7 +73,11 @@ int main(void)
OFFSET(TSS_ist, tss_struct, x86_tss.ist);
BLANK();
- DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+ DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
+ DEFINE(NR_syscalls, sizeof(syscalls_64));
+
+ DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1);
+ DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32));
return 0;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 850f2963a420..d43cad74f166 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1021,6 +1021,8 @@ __setup("clearcpuid=", setup_disablecpuid);
#ifdef CONFIG_X86_64
struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
+struct desc_ptr nmi_idt_descr = { NR_VECTORS * 16 - 1,
+ (unsigned long) nmi_idt_table };
DEFINE_PER_CPU_FIRST(union irq_stack_union,
irq_stack_union) __aligned(PAGE_SIZE);
@@ -1085,6 +1087,26 @@ unsigned long kernel_eflags;
*/
DEFINE_PER_CPU(struct orig_ist, orig_ist);
+static DEFINE_PER_CPU(unsigned long, debug_stack_addr);
+DEFINE_PER_CPU(int, debug_stack_usage);
+
+int is_debug_stack(unsigned long addr)
+{
+ return __get_cpu_var(debug_stack_usage) ||
+ (addr <= __get_cpu_var(debug_stack_addr) &&
+ addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
+}
+
+void debug_stack_set_zero(void)
+{
+ load_idt((const struct desc_ptr *)&nmi_idt_descr);
+}
+
+void debug_stack_reset(void)
+{
+ load_idt((const struct desc_ptr *)&idt_descr);
+}
+
#else /* CONFIG_X86_64 */
DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
@@ -1212,6 +1234,8 @@ void __cpuinit cpu_init(void)
estacks += exception_stack_sizes[v];
oist->ist[v] = t->x86_tss.ist[v] =
(unsigned long)estacks;
+ if (v == DEBUG_STACK-1)
+ per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks;
}
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index f22a9f7f6390..5a11ae2e9e91 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1859,7 +1859,7 @@ static struct bus_type mce_subsys = {
.dev_name = "machinecheck",
};
-DEFINE_PER_CPU(struct device, mce_device);
+struct device *mce_device[CONFIG_NR_CPUS];
__cpuinitdata
void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
@@ -2001,19 +2001,27 @@ static struct device_attribute *mce_device_attrs[] = {
static cpumask_var_t mce_device_initialized;
+static void mce_device_release(struct device *dev)
+{
+ kfree(dev);
+}
+
/* Per cpu device init. All of the cpus still share the same ctrl bank: */
static __cpuinit int mce_device_create(unsigned int cpu)
{
- struct device *dev = &per_cpu(mce_device, cpu);
+ struct device *dev;
int err;
int i, j;
if (!mce_available(&boot_cpu_data))
return -EIO;
- memset(&dev->kobj, 0, sizeof(struct kobject));
+ dev = kzalloc(sizeof *dev, GFP_KERNEL);
+ if (!dev)
+ return -ENOMEM;
dev->id = cpu;
dev->bus = &mce_subsys;
+ dev->release = &mce_device_release;
err = device_register(dev);
if (err)
@@ -2030,6 +2038,7 @@ static __cpuinit int mce_device_create(unsigned int cpu)
goto error2;
}
cpumask_set_cpu(cpu, mce_device_initialized);
+ mce_device[cpu] = dev;
return 0;
error2:
@@ -2046,7 +2055,7 @@ error:
static __cpuinit void mce_device_remove(unsigned int cpu)
{
- struct device *dev = &per_cpu(mce_device, cpu);
+ struct device *dev = mce_device[cpu];
int i;
if (!cpumask_test_cpu(cpu, mce_device_initialized))
@@ -2060,6 +2069,7 @@ static __cpuinit void mce_device_remove(unsigned int cpu)
device_unregister(dev);
cpumask_clear_cpu(cpu, mce_device_initialized);
+ mce_device[cpu] = NULL;
}
/* Make sure there are no machine checks on offlined CPUs. */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ba0b94a7e204..786e76a86322 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -523,6 +523,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
{
int i, err = 0;
struct threshold_bank *b = NULL;
+ struct device *dev = mce_device[cpu];
char name[32];
sprintf(name, "threshold_bank%i", bank);
@@ -543,8 +544,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (!b)
goto out;
- err = sysfs_create_link(&per_cpu(mce_device, cpu).kobj,
- b->kobj, name);
+ err = sysfs_create_link(&dev->kobj, b->kobj, name);
if (err)
goto out;
@@ -565,7 +565,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
goto out;
}
- b->kobj = kobject_create_and_add(name, &per_cpu(mce_device, cpu).kobj);
+ b->kobj = kobject_create_and_add(name, &dev->kobj);
if (!b->kobj)
goto out_free;
@@ -585,8 +585,9 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (i == cpu)
continue;
- err = sysfs_create_link(&per_cpu(mce_device, i).kobj,
- b->kobj, name);
+ dev = mce_device[i];
+ if (dev)
+ err = sysfs_create_link(&dev->kobj,b->kobj, name);
if (err)
goto out;
@@ -649,6 +650,7 @@ static void deallocate_threshold_block(unsigned int cpu,
static void threshold_remove_bank(unsigned int cpu, int bank)
{
struct threshold_bank *b;
+ struct device *dev;
char name[32];
int i = 0;
@@ -663,7 +665,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
#ifdef CONFIG_SMP
/* sibling symlink */
if (shared_bank[bank] && b->blocks->cpu != cpu) {
- sysfs_remove_link(&per_cpu(mce_device, cpu).kobj, name);
+ sysfs_remove_link(&mce_device[cpu]->kobj, name);
per_cpu(threshold_banks, cpu)[bank] = NULL;
return;
@@ -675,7 +677,9 @@ static void threshold_remove_bank(unsigned int cpu, int bank)
if (i == cpu)
continue;
- sysfs_remove_link(&per_cpu(mce_device, i).kobj, name);
+ dev = mce_device[i];
+ if (dev)
+ sysfs_remove_link(&dev->kobj, name);
per_cpu(threshold_banks, i)[bank] = NULL;
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 1aae78f775fc..4025fe4f928f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -252,7 +252,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
unsigned short ss;
unsigned long sp;
#endif
- printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+ printk(KERN_DEFAULT
+ "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
printk("PREEMPT ");
#endif
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6d728d9284bd..17107bd6e1f0 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
if (!stack) {
if (regs)
stack = (unsigned long *)regs->sp;
- else if (task && task != current)
+ else if (task != current)
stack = (unsigned long *)task->thread.sp;
else
stack = &dummy;
@@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs)
unsigned char c;
u8 *ip;
- printk(KERN_EMERG "Stack:\n");
+ printk(KERN_DEFAULT "Stack:\n");
show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
- 0, KERN_EMERG);
+ 0, KERN_DEFAULT);
- printk(KERN_EMERG "Code: ");
+ printk(KERN_DEFAULT "Code: ");
ip = (u8 *)regs->ip - code_prologue;
if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 8071e2f3d6eb..62d61e9976eb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -19,6 +19,7 @@
#include <linux/acpi.h>
#include <linux/firmware-map.h>
#include <linux/memblock.h>
+#include <linux/sort.h>
#include <asm/e820.h>
#include <asm/proto.h>
@@ -227,22 +228,38 @@ void __init e820_print_map(char *who)
* ____________________33__
* ______________________4_
*/
+struct change_member {
+ struct e820entry *pbios; /* pointer to original bios entry */
+ unsigned long long addr; /* address for this change point */
+};
+
+static int __init cpcompare(const void *a, const void *b)
+{
+ struct change_member * const *app = a, * const *bpp = b;
+ const struct change_member *ap = *app, *bp = *bpp;
+
+ /*
+ * Inputs are pointers to two elements of change_point[]. If their
+ * addresses are unequal, their difference dominates. If the addresses
+ * are equal, then consider one that represents the end of its region
+ * to be greater than one that does not.
+ */
+ if (ap->addr != bp->addr)
+ return ap->addr > bp->addr ? 1 : -1;
+
+ return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr);
+}
int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
u32 *pnr_map)
{
- struct change_member {
- struct e820entry *pbios; /* pointer to original bios entry */
- unsigned long long addr; /* address for this change point */
- };
static struct change_member change_point_list[2*E820_X_MAX] __initdata;
static struct change_member *change_point[2*E820_X_MAX] __initdata;
static struct e820entry *overlap_list[E820_X_MAX] __initdata;
static struct e820entry new_bios[E820_X_MAX] __initdata;
- struct change_member *change_tmp;
unsigned long current_type, last_type;
unsigned long long last_addr;
- int chgidx, still_changing;
+ int chgidx;
int overlap_entries;
int new_bios_entry;
int old_nr, new_nr, chg_nr;
@@ -279,35 +296,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
chg_nr = chgidx;
/* sort change-point list by memory addresses (low -> high) */
- still_changing = 1;
- while (still_changing) {
- still_changing = 0;
- for (i = 1; i < chg_nr; i++) {
- unsigned long long curaddr, lastaddr;
- unsigned long long curpbaddr, lastpbaddr;
-
- curaddr = change_point[i]->addr;
- lastaddr = change_point[i - 1]->addr;
- curpbaddr = change_point[i]->pbios->addr;
- lastpbaddr = change_point[i - 1]->pbios->addr;
-
- /*
- * swap entries, when:
- *
- * curaddr > lastaddr or
- * curaddr == lastaddr and curaddr == curpbaddr and
- * lastaddr != lastpbaddr
- */
- if (curaddr < lastaddr ||
- (curaddr == lastaddr && curaddr == curpbaddr &&
- lastaddr != lastpbaddr)) {
- change_tmp = change_point[i];
- change_point[i] = change_point[i-1];
- change_point[i-1] = change_tmp;
- still_changing = 1;
- }
- }
- }
+ sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL);
/* create a new bios memory map, removing overlaps */
overlap_entries = 0; /* number of entries in the overlap table */
@@ -714,7 +703,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
}
#endif
-#ifdef CONFIG_HIBERNATION
+#ifdef CONFIG_ACPI
/**
* Mark ACPI NVS memory region, so that we can save/restore it during
* hibernation and the subsequent resume.
@@ -727,7 +716,7 @@ static int __init e820_mark_nvs_memory(void)
struct e820entry *ei = &e820.map[i];
if (ei->type == E820_NVS)
- suspend_nvs_register(ei->addr, ei->size);
+ acpi_nvs_register(ei->addr, ei->size);
}
return 0;
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 9d42a52d2331..9b9f18b49918 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -240,7 +240,7 @@ static int __init setup_early_printk(char *buf)
if (!strncmp(buf, "xen", 3))
early_console_register(&xenboot_console, keep);
#endif
-#ifdef CONFIG_EARLY_PRINTK_MRST
+#ifdef CONFIG_EARLY_PRINTK_INTEL_MID
if (!strncmp(buf, "mrst", 4)) {
mrst_early_console_init();
early_console_register(&early_mrst_console, keep);
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 22d0e21b4dd7..79d97e68f042 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -42,6 +42,7 @@
*/
#include <linux/linkage.h>
+#include <linux/err.h>
#include <asm/thread_info.h>
#include <asm/irqflags.h>
#include <asm/errno.h>
@@ -81,8 +82,6 @@
* enough to patch inline, increasing performance.
*/
-#define nr_syscalls ((syscall_table_size)/4)
-
#ifdef CONFIG_PREEMPT
#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
#else
@@ -423,7 +422,7 @@ sysenter_past_esp:
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
jnz sysenter_audit
sysenter_do_call:
- cmpl $(nr_syscalls), %eax
+ cmpl $(NR_syscalls), %eax
jae syscall_badsys
call *sys_call_table(,%eax,4)
movl %eax,PT_EAX(%esp)
@@ -455,7 +454,7 @@ sysenter_audit:
movl %ebx,%ecx /* 3rd arg: 1st syscall arg */
movl %eax,%edx /* 2nd arg: syscall number */
movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */
- call audit_syscall_entry
+ call __audit_syscall_entry
pushl_cfi %ebx
movl PT_EAX(%esp),%eax /* reload syscall number */
jmp sysenter_do_call
@@ -466,11 +465,10 @@ sysexit_audit:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
movl %eax,%edx /* second arg, syscall return value */
- cmpl $0,%eax /* is it < 0? */
- setl %al /* 1 if so, 0 if not */
+ cmpl $-MAX_ERRNO,%eax /* is it an error ? */
+ setbe %al /* 1 if so, 0 if not */
movzbl %al,%eax /* zero-extend that */
- inc %eax /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
- call audit_syscall_exit
+ call __audit_syscall_exit
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
@@ -504,7 +502,7 @@ ENTRY(system_call)
# system call tracing in operation / emulation
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp)
jnz syscall_trace_entry
- cmpl $(nr_syscalls), %eax
+ cmpl $(NR_syscalls), %eax
jae syscall_badsys
syscall_call:
call *sys_call_table(,%eax,4)
@@ -654,7 +652,7 @@ syscall_trace_entry:
movl %esp, %eax
call syscall_trace_enter
/* What it returned is what we'll actually use. */
- cmpl $(nr_syscalls), %eax
+ cmpl $(NR_syscalls), %eax
jnae syscall_call
jmp syscall_exit
END(syscall_trace_entry)
@@ -694,29 +692,28 @@ END(syscall_badsys)
* System calls that need a pt_regs pointer.
*/
#define PTREGSCALL0(name) \
- ALIGN; \
-ptregs_##name: \
+ENTRY(ptregs_##name) ; \
leal 4(%esp),%eax; \
- jmp sys_##name;
+ jmp sys_##name; \
+ENDPROC(ptregs_##name)
#define PTREGSCALL1(name) \
- ALIGN; \
-ptregs_##name: \
+ENTRY(ptregs_##name) ; \
leal 4(%esp),%edx; \
movl (PT_EBX+4)(%esp),%eax; \
- jmp sys_##name;
+ jmp sys_##name; \
+ENDPROC(ptregs_##name)
#define PTREGSCALL2(name) \
- ALIGN; \
-ptregs_##name: \
+ENTRY(ptregs_##name) ; \
leal 4(%esp),%ecx; \
movl (PT_ECX+4)(%esp),%edx; \
movl (PT_EBX+4)(%esp),%eax; \
- jmp sys_##name;
+ jmp sys_##name; \
+ENDPROC(ptregs_##name)
#define PTREGSCALL3(name) \
- ALIGN; \
-ptregs_##name: \
+ENTRY(ptregs_##name) ; \
CFI_STARTPROC; \
leal 4(%esp),%eax; \
pushl_cfi %eax; \
@@ -741,8 +738,7 @@ PTREGSCALL2(vm86)
PTREGSCALL1(vm86old)
/* Clone is an oddball. The 4th arg is in %edi */
- ALIGN;
-ptregs_clone:
+ENTRY(ptregs_clone)
CFI_STARTPROC
leal 4(%esp),%eax
pushl_cfi %eax
@@ -1213,11 +1209,6 @@ return_to_handler:
jmp *%ecx
#endif
-.section .rodata,"a"
-#include "syscall_table_32.S"
-
-syscall_table_size=(.-sys_call_table)
-
/*
* Some functions should be protected against kprobes
*/
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a20e1cb9dc87..3fe8239fd8fb 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -55,6 +55,7 @@
#include <asm/paravirt.h>
#include <asm/ftrace.h>
#include <asm/percpu.h>
+#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
@@ -548,7 +549,7 @@ badsys:
#ifdef CONFIG_AUDITSYSCALL
/*
* Fast path for syscall audit without full syscall trace.
- * We just call audit_syscall_entry() directly, and then
+ * We just call __audit_syscall_entry() directly, and then
* jump back to the normal fast path.
*/
auditsys:
@@ -558,22 +559,21 @@ auditsys:
movq %rdi,%rdx /* 3rd arg: 1st syscall arg */
movq %rax,%rsi /* 2nd arg: syscall number */
movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */
- call audit_syscall_entry
+ call __audit_syscall_entry
LOAD_ARGS 0 /* reload call-clobbered registers */
jmp system_call_fastpath
/*
- * Return fast path for syscall audit. Call audit_syscall_exit()
+ * Return fast path for syscall audit. Call __audit_syscall_exit()
* directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
* masked off.
*/
sysret_audit:
movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */
- cmpq $0,%rsi /* is it < 0? */
- setl %al /* 1 if so, 0 if not */
+ cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */
+ setbe %al /* 1 if so, 0 if not */
movzbl %al,%edi /* zero-extend that into %edi */
- inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
- call audit_syscall_exit
+ call __audit_syscall_exit
movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
jmp sysret_check
#endif /* CONFIG_AUDITSYSCALL */
@@ -1480,62 +1480,214 @@ ENTRY(error_exit)
CFI_ENDPROC
END(error_exit)
+/*
+ * Test if a given stack is an NMI stack or not.
+ */
+ .macro test_in_nmi reg stack nmi_ret normal_ret
+ cmpq %\reg, \stack
+ ja \normal_ret
+ subq $EXCEPTION_STKSZ, %\reg
+ cmpq %\reg, \stack
+ jb \normal_ret
+ jmp \nmi_ret
+ .endm
/* runs on exception stack */
ENTRY(nmi)
INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
- pushq_cfi $-1
+ /*
+ * We allow breakpoints in NMIs. If a breakpoint occurs, then
+ * the iretq it performs will take us out of NMI context.
+ * This means that we can have nested NMIs where the next
+ * NMI is using the top of the stack of the previous NMI. We
+ * can't let it execute because the nested NMI will corrupt the
+ * stack of the previous NMI. NMI handlers are not re-entrant
+ * anyway.
+ *
+ * To handle this case we do the following:
+ * Check the a special location on the stack that contains
+ * a variable that is set when NMIs are executing.
+ * The interrupted task's stack is also checked to see if it
+ * is an NMI stack.
+ * If the variable is not set and the stack is not the NMI
+ * stack then:
+ * o Set the special variable on the stack
+ * o Copy the interrupt frame into a "saved" location on the stack
+ * o Copy the interrupt frame into a "copy" location on the stack
+ * o Continue processing the NMI
+ * If the variable is set or the previous stack is the NMI stack:
+ * o Modify the "copy" location to jump to the repeate_nmi
+ * o return back to the first NMI
+ *
+ * Now on exit of the first NMI, we first clear the stack variable
+ * The NMI stack will tell any nested NMIs at that point that it is
+ * nested. Then we pop the stack normally with iret, and if there was
+ * a nested NMI that updated the copy interrupt stack frame, a
+ * jump will be made to the repeat_nmi code that will handle the second
+ * NMI.
+ */
+
+ /* Use %rdx as out temp variable throughout */
+ pushq_cfi %rdx
+
+ /*
+ * Check the special variable on the stack to see if NMIs are
+ * executing.
+ */
+ cmp $1, -8(%rsp)
+ je nested_nmi
+
+ /*
+ * Now test if the previous stack was an NMI stack.
+ * We need the double check. We check the NMI stack to satisfy the
+ * race when the first NMI clears the variable before returning.
+ * We check the variable because the first NMI could be in a
+ * breakpoint routine using a breakpoint stack.
+ */
+ lea 6*8(%rsp), %rdx
+ test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi
+
+nested_nmi:
+ /*
+ * Do nothing if we interrupted the fixup in repeat_nmi.
+ * It's about to repeat the NMI handler, so we are fine
+ * with ignoring this one.
+ */
+ movq $repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja 1f
+ movq $end_repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja nested_nmi_out
+
+1:
+ /* Set up the interrupted NMIs stack to jump to repeat_nmi */
+ leaq -6*8(%rsp), %rdx
+ movq %rdx, %rsp
+ CFI_ADJUST_CFA_OFFSET 6*8
+ pushq_cfi $__KERNEL_DS
+ pushq_cfi %rdx
+ pushfq_cfi
+ pushq_cfi $__KERNEL_CS
+ pushq_cfi $repeat_nmi
+
+ /* Put stack back */
+ addq $(11*8), %rsp
+ CFI_ADJUST_CFA_OFFSET -11*8
+
+nested_nmi_out:
+ popq_cfi %rdx
+
+ /* No need to check faults here */
+ INTERRUPT_RETURN
+
+first_nmi:
+ /*
+ * Because nested NMIs will use the pushed location that we
+ * stored in rdx, we must keep that space available.
+ * Here's what our stack frame will look like:
+ * +-------------------------+
+ * | original SS |
+ * | original Return RSP |
+ * | original RFLAGS |
+ * | original CS |
+ * | original RIP |
+ * +-------------------------+
+ * | temp storage for rdx |
+ * +-------------------------+
+ * | NMI executing variable |
+ * +-------------------------+
+ * | Saved SS |
+ * | Saved Return RSP |
+ * | Saved RFLAGS |
+ * | Saved CS |
+ * | Saved RIP |
+ * +-------------------------+
+ * | copied SS |
+ * | copied Return RSP |
+ * | copied RFLAGS |
+ * | copied CS |
+ * | copied RIP |
+ * +-------------------------+
+ * | pt_regs |
+ * +-------------------------+
+ *
+ * The saved RIP is used to fix up the copied RIP that a nested
+ * NMI may zero out. The original stack frame and the temp storage
+ * is also used by nested NMIs and can not be trusted on exit.
+ */
+ /* Set the NMI executing variable on the stack. */
+ pushq_cfi $1
+
+ /* Copy the stack frame to the Saved frame */
+ .rept 5
+ pushq_cfi 6*8(%rsp)
+ .endr
+
+ /* Make another copy, this one may be modified by nested NMIs */
+ .rept 5
+ pushq_cfi 4*8(%rsp)
+ .endr
+
+ /* Do not pop rdx, nested NMIs will corrupt it */
+ movq 11*8(%rsp), %rdx
+
+ /*
+ * Everything below this point can be preempted by a nested
+ * NMI if the first NMI took an exception. Repeated NMIs
+ * caused by an exception and nested NMI will start here, and
+ * can still be preempted by another NMI.
+ */
+restart_nmi:
+ pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
+ /*
+ * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit
+ * as we should not be calling schedule in NMI context.
+ * Even with normal interrupts enabled. An NMI should not be
+ * setting NEED_RESCHED or anything that normal interrupts and
+ * exceptions might do.
+ */
call save_paranoid
DEFAULT_FRAME 0
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
movq %rsp,%rdi
movq $-1,%rsi
call do_nmi
-#ifdef CONFIG_TRACE_IRQFLAGS
- /* paranoidexit; without TRACE_IRQS_OFF */
- /* ebx: no swapgs flag */
- DISABLE_INTERRUPTS(CLBR_NONE)
testl %ebx,%ebx /* swapgs needed? */
jnz nmi_restore
- testl $3,CS(%rsp)
- jnz nmi_userspace
nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
RESTORE_ALL 8
+ /* Clear the NMI executing stack variable */
+ movq $0, 10*8(%rsp)
jmp irq_return
-nmi_userspace:
- GET_THREAD_INFO(%rcx)
- movl TI_flags(%rcx),%ebx
- andl $_TIF_WORK_MASK,%ebx
- jz nmi_swapgs
- movq %rsp,%rdi /* &pt_regs */
- call sync_regs
- movq %rax,%rsp /* switch stack for scheduling */
- testl $_TIF_NEED_RESCHED,%ebx
- jnz nmi_schedule
- movl %ebx,%edx /* arg3: thread flags */
- ENABLE_INTERRUPTS(CLBR_NONE)
- xorl %esi,%esi /* arg2: oldset */
- movq %rsp,%rdi /* arg1: &pt_regs */
- call do_notify_resume
- DISABLE_INTERRUPTS(CLBR_NONE)
- jmp nmi_userspace
-nmi_schedule:
- ENABLE_INTERRUPTS(CLBR_ANY)
- call schedule
- DISABLE_INTERRUPTS(CLBR_ANY)
- jmp nmi_userspace
- CFI_ENDPROC
-#else
- jmp paranoid_exit
CFI_ENDPROC
-#endif
END(nmi)
+ /*
+ * If an NMI hit an iret because of an exception or breakpoint,
+ * it can lose its NMI context, and a nested NMI may come in.
+ * In that case, the nested NMI will change the preempted NMI's
+ * stack to jump to here when it does the final iret.
+ */
+repeat_nmi:
+ INTR_FRAME
+ /* Update the stack variable to say we are still in NMI */
+ movq $1, 5*8(%rsp)
+
+ /* copy the saved stack back to copy stack */
+ .rept 5
+ pushq_cfi 4*8(%rsp)
+ .endr
+
+ jmp restart_nmi
+ CFI_ENDPROC
+end_repeat_nmi:
+
ENTRY(ignore_sysret)
CFI_STARTPROC
mov $-ENOSYS,%eax
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e11e39478a49..40f4eb3766d1 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -417,6 +417,10 @@ ENTRY(phys_base)
ENTRY(idt_table)
.skip IDT_ENTRIES * 16
+ .align L1_CACHE_BYTES
+ENTRY(nmi_idt_table)
+ .skip IDT_ENTRIES * 16
+
__PAGE_ALIGNED_BSS
.align PAGE_SIZE
ENTRY(empty_zero_page)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 72090705a656..40fc86161d92 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -28,6 +28,9 @@ DEFINE_PER_CPU(struct pt_regs *, irq_regs);
EXPORT_PER_CPU_SYMBOL(irq_regs);
#ifdef CONFIG_DEBUG_STACKOVERFLOW
+
+int sysctl_panic_on_stackoverflow __read_mostly;
+
/* Debugging check for stack overflow: is there less than 1KB free? */
static int check_stack_overflow(void)
{
@@ -43,6 +46,8 @@ static void print_stack_overflow(void)
{
printk(KERN_WARNING "low stack detected by irq handler\n");
dump_stack();
+ if (sysctl_panic_on_stackoverflow)
+ panic("low stack detected by irq handler - check messages\n");
}
#else
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 69bca468c47a..d04d3ecded62 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,6 +26,8 @@ EXPORT_PER_CPU_SYMBOL(irq_stat);
DEFINE_PER_CPU(struct pt_regs *, irq_regs);
EXPORT_PER_CPU_SYMBOL(irq_regs);
+int sysctl_panic_on_stackoverflow;
+
/*
* Probabilistic stack overflow check:
*
@@ -36,18 +38,39 @@ EXPORT_PER_CPU_SYMBOL(irq_regs);
static inline void stack_overflow_check(struct pt_regs *regs)
{
#ifdef CONFIG_DEBUG_STACKOVERFLOW
+#define STACK_TOP_MARGIN 128
+ struct orig_ist *oist;
+ u64 irq_stack_top, irq_stack_bottom;
+ u64 estack_top, estack_bottom;
u64 curbase = (u64)task_stack_page(current);
if (user_mode_vm(regs))
return;
- WARN_ONCE(regs->sp >= curbase &&
- regs->sp <= curbase + THREAD_SIZE &&
- regs->sp < curbase + sizeof(struct thread_info) +
- sizeof(struct pt_regs) + 128,
+ if (regs->sp >= curbase + sizeof(struct thread_info) +
+ sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
+ regs->sp <= curbase + THREAD_SIZE)
+ return;
+
+ irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+ STACK_TOP_MARGIN;
+ irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+ if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
+ return;
+
+ oist = &__get_cpu_var(orig_ist);
+ estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
+ estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
+ if (regs->sp >= estack_top && regs->sp <= estack_bottom)
+ return;
+
+ WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+ current->comm, curbase, regs->sp,
+ irq_stack_top, irq_stack_bottom,
+ estack_top, estack_bottom);
- "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
- current->comm, curbase, regs->sp);
+ if (sysctl_panic_on_stackoverflow)
+ panic("low stack detected by irq handler - check messages\n");
#endif
}
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index fe86493f3ed1..ac0417be9131 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -311,13 +311,33 @@ out:
return state;
}
+/*
+ * AMD microcode firmware naming convention, up to family 15h they are in
+ * the legacy file:
+ *
+ * amd-ucode/microcode_amd.bin
+ *
+ * This legacy file is always smaller than 2K in size.
+ *
+ * Starting at family 15h they are in family specific firmware files:
+ *
+ * amd-ucode/microcode_amd_fam15h.bin
+ * amd-ucode/microcode_amd_fam16h.bin
+ * ...
+ *
+ * These might be larger than 2K.
+ */
static enum ucode_state request_microcode_amd(int cpu, struct device *device)
{
- const char *fw_name = "amd-ucode/microcode_amd.bin";
+ char fw_name[36] = "amd-ucode/microcode_amd.bin";
const struct firmware *fw;
enum ucode_state ret = UCODE_NFOUND;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ if (c->x86 >= 0x15)
+ snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
- if (request_firmware(&fw, fw_name, device)) {
+ if (request_firmware(&fw, (const char *)fw_name, device)) {
pr_err("failed to load file %s\n", fw_name);
goto out;
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index e88f37b58ddd..47acaf319165 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -405,9 +405,108 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
unknown_nmi_error(reason, regs);
}
+/*
+ * NMIs can hit breakpoints which will cause it to lose its
+ * NMI context with the CPU when the breakpoint does an iret.
+ */
+#ifdef CONFIG_X86_32
+/*
+ * For i386, NMIs use the same stack as the kernel, and we can
+ * add a workaround to the iret problem in C. Simply have 3 states
+ * the NMI can be in.
+ *
+ * 1) not running
+ * 2) executing
+ * 3) latched
+ *
+ * When no NMI is in progress, it is in the "not running" state.
+ * When an NMI comes in, it goes into the "executing" state.
+ * Normally, if another NMI is triggered, it does not interrupt
+ * the running NMI and the HW will simply latch it so that when
+ * the first NMI finishes, it will restart the second NMI.
+ * (Note, the latch is binary, thus multiple NMIs triggering,
+ * when one is running, are ignored. Only one NMI is restarted.)
+ *
+ * If an NMI hits a breakpoint that executes an iret, another
+ * NMI can preempt it. We do not want to allow this new NMI
+ * to run, but we want to execute it when the first one finishes.
+ * We set the state to "latched", and the first NMI will perform
+ * an cmpxchg on the state, and if it doesn't successfully
+ * reset the state to "not running" it will restart the next
+ * NMI.
+ */
+enum nmi_states {
+ NMI_NOT_RUNNING,
+ NMI_EXECUTING,
+ NMI_LATCHED,
+};
+static DEFINE_PER_CPU(enum nmi_states, nmi_state);
+
+#define nmi_nesting_preprocess(regs) \
+ do { \
+ if (__get_cpu_var(nmi_state) != NMI_NOT_RUNNING) { \
+ __get_cpu_var(nmi_state) = NMI_LATCHED; \
+ return; \
+ } \
+ nmi_restart: \
+ __get_cpu_var(nmi_state) = NMI_EXECUTING; \
+ } while (0)
+
+#define nmi_nesting_postprocess() \
+ do { \
+ if (cmpxchg(&__get_cpu_var(nmi_state), \
+ NMI_EXECUTING, NMI_NOT_RUNNING) != NMI_EXECUTING) \
+ goto nmi_restart; \
+ } while (0)
+#else /* x86_64 */
+/*
+ * In x86_64 things are a bit more difficult. This has the same problem
+ * where an NMI hitting a breakpoint that calls iret will remove the
+ * NMI context, allowing a nested NMI to enter. What makes this more
+ * difficult is that both NMIs and breakpoints have their own stack.
+ * When a new NMI or breakpoint is executed, the stack is set to a fixed
+ * point. If an NMI is nested, it will have its stack set at that same
+ * fixed address that the first NMI had, and will start corrupting the
+ * stack. This is handled in entry_64.S, but the same problem exists with
+ * the breakpoint stack.
+ *
+ * If a breakpoint is being processed, and the debug stack is being used,
+ * if an NMI comes in and also hits a breakpoint, the stack pointer
+ * will be set to the same fixed address as the breakpoint that was
+ * interrupted, causing that stack to be corrupted. To handle this case,
+ * check if the stack that was interrupted is the debug stack, and if
+ * so, change the IDT so that new breakpoints will use the current stack
+ * and not switch to the fixed address. On return of the NMI, switch back
+ * to the original IDT.
+ */
+static DEFINE_PER_CPU(int, update_debug_stack);
+
+static inline void nmi_nesting_preprocess(struct pt_regs *regs)
+{
+ /*
+ * If we interrupted a breakpoint, it is possible that
+ * the nmi handler will have breakpoints too. We need to
+ * change the IDT such that breakpoints that happen here
+ * continue to use the NMI stack.
+ */
+ if (unlikely(is_debug_stack(regs->sp))) {
+ debug_stack_set_zero();
+ __get_cpu_var(update_debug_stack) = 1;
+ }
+}
+
+static inline void nmi_nesting_postprocess(void)
+{
+ if (unlikely(__get_cpu_var(update_debug_stack)))
+ debug_stack_reset();
+}
+#endif
+
dotraplinkage notrace __kprobes void
do_nmi(struct pt_regs *regs, long error_code)
{
+ nmi_nesting_preprocess(regs);
+
nmi_enter();
inc_irq_stat(__nmi_count);
@@ -416,6 +515,9 @@ do_nmi(struct pt_regs *regs, long error_code)
default_do_nmi(regs);
nmi_exit();
+
+ /* On i386, may loop back to preprocess */
+ nmi_nesting_postprocess();
}
void stop_nmi(void)
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
new file mode 100644
index 000000000000..0d01a8ea4e11
--- /dev/null
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -0,0 +1,180 @@
+/*
+ * arch/x86/kernel/nmi-selftest.c
+ *
+ * Testsuite for NMI: IPIs
+ *
+ * Started by Don Zickus:
+ * (using lib/locking-selftest.c as a guide)
+ *
+ * Copyright (C) 2011 Red Hat, Inc., Don Zickus <dzickus@redhat.com>
+ */
+
+#include <linux/smp.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+
+#include <asm/apic.h>
+#include <asm/nmi.h>
+
+#define SUCCESS 0
+#define FAILURE 1
+#define TIMEOUT 2
+
+static int nmi_fail;
+
+/* check to see if NMI IPIs work on this machine */
+static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __read_mostly;
+
+static int testcase_total;
+static int testcase_successes;
+static int expected_testcase_failures;
+static int unexpected_testcase_failures;
+static int unexpected_testcase_unknowns;
+
+static int nmi_unk_cb(unsigned int val, struct pt_regs *regs)
+{
+ unexpected_testcase_unknowns++;
+ return NMI_HANDLED;
+}
+
+static void init_nmi_testsuite(void)
+{
+ /* trap all the unknown NMIs we may generate */
+ register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+}
+
+static void cleanup_nmi_testsuite(void)
+{
+ unregister_nmi_handler(NMI_UNKNOWN, "nmi_selftest_unk");
+}
+
+static int test_nmi_ipi_callback(unsigned int val, struct pt_regs *regs)
+{
+ int cpu = raw_smp_processor_id();
+
+ if (cpumask_test_and_clear_cpu(cpu, to_cpumask(nmi_ipi_mask)))
+ return NMI_HANDLED;
+
+ return NMI_DONE;
+}
+
+static void test_nmi_ipi(struct cpumask *mask)
+{
+ unsigned long timeout;
+
+ if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+ NMI_FLAG_FIRST, "nmi_selftest")) {
+ nmi_fail = FAILURE;
+ return;
+ }
+
+ /* sync above data before sending NMI */
+ wmb();
+
+ apic->send_IPI_mask(mask, NMI_VECTOR);
+
+ /* Don't wait longer than a second */
+ timeout = USEC_PER_SEC;
+ while (!cpumask_empty(mask) && timeout--)
+ udelay(1);
+
+ /* What happens if we timeout, do we still unregister?? */
+ unregister_nmi_handler(NMI_LOCAL, "nmi_selftest");
+
+ if (!timeout)
+ nmi_fail = TIMEOUT;
+ return;
+}
+
+static void remote_ipi(void)
+{
+ cpumask_copy(to_cpumask(nmi_ipi_mask), cpu_online_mask);
+ cpumask_clear_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask));
+ if (!cpumask_empty(to_cpumask(nmi_ipi_mask)))
+ test_nmi_ipi(to_cpumask(nmi_ipi_mask));
+}
+
+static void local_ipi(void)
+{
+ cpumask_clear(to_cpumask(nmi_ipi_mask));
+ cpumask_set_cpu(smp_processor_id(), to_cpumask(nmi_ipi_mask));
+ test_nmi_ipi(to_cpumask(nmi_ipi_mask));
+}
+
+static void reset_nmi(void)
+{
+ nmi_fail = 0;
+}
+
+static void dotest(void (*testcase_fn)(void), int expected)
+{
+ testcase_fn();
+ /*
+ * Filter out expected failures:
+ */
+ if (nmi_fail != expected) {
+ unexpected_testcase_failures++;
+
+ if (nmi_fail == FAILURE)
+ printk("FAILED |");
+ else if (nmi_fail == TIMEOUT)
+ printk("TIMEOUT|");
+ else
+ printk("ERROR |");
+ dump_stack();
+ } else {
+ testcase_successes++;
+ printk(" ok |");
+ }
+ testcase_total++;
+
+ reset_nmi();
+}
+
+static inline void print_testname(const char *testname)
+{
+ printk("%12s:", testname);
+}
+
+void nmi_selftest(void)
+{
+ init_nmi_testsuite();
+
+ /*
+ * Run the testsuite:
+ */
+ printk("----------------\n");
+ printk("| NMI testsuite:\n");
+ printk("--------------------\n");
+
+ print_testname("remote IPI");
+ dotest(remote_ipi, SUCCESS);
+ printk("\n");
+ print_testname("local IPI");
+ dotest(local_ipi, SUCCESS);
+ printk("\n");
+
+ cleanup_nmi_testsuite();
+
+ if (unexpected_testcase_failures) {
+ printk("--------------------\n");
+ printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
+ unexpected_testcase_failures, testcase_total);
+ printk("-----------------------------------------------------------------\n");
+ } else if (expected_testcase_failures && testcase_successes) {
+ printk("--------------------\n");
+ printk("%3d out of %3d testcases failed, as expected. |\n",
+ expected_testcase_failures, testcase_total);
+ printk("----------------------------------------------------\n");
+ } else if (expected_testcase_failures && !testcase_successes) {
+ printk("--------------------\n");
+ printk("All %3d testcases failed, as expected. |\n",
+ expected_testcase_failures);
+ printk("----------------------------------------\n");
+ } else {
+ printk("--------------------\n");
+ printk("Good, all %3d testcases passed! |\n",
+ testcase_successes);
+ printk("---------------------------------\n");
+ }
+}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 80dc793b3f63..1c4d769e21ea 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -45,6 +45,15 @@ int iommu_detected __read_mostly = 0;
*/
int iommu_pass_through __read_mostly;
+/*
+ * Group multi-function PCI devices into a single device-group for the
+ * iommu_device_group interface. This tells the iommu driver to pretend
+ * it cannot distinguish between functions of a device, exposing only one
+ * group for the device. Useful for disallowing use of individual PCI
+ * functions from userspace drivers.
+ */
+int iommu_group_mf __read_mostly;
+
extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
/* Dummy device used for NULL arguments (normally ISA). */
@@ -169,6 +178,8 @@ static __init int iommu_setup(char *p)
#endif
if (!strncmp(p, "pt", 2))
iommu_pass_through = 1;
+ if (!strncmp(p, "group_mf", 8))
+ iommu_group_mf = 1;
gart_parse_options(p);
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 89a04c7b5bb6..50267386b766 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1392,20 +1392,18 @@ long syscall_trace_enter(struct pt_regs *regs)
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->orig_ax);
- if (unlikely(current->audit_context)) {
- if (IS_IA32)
- audit_syscall_entry(AUDIT_ARCH_I386,
- regs->orig_ax,
- regs->bx, regs->cx,
- regs->dx, regs->si);
+ if (IS_IA32)
+ audit_syscall_entry(AUDIT_ARCH_I386,
+ regs->orig_ax,
+ regs->bx, regs->cx,
+ regs->dx, regs->si);
#ifdef CONFIG_X86_64
- else
- audit_syscall_entry(AUDIT_ARCH_X86_64,
- regs->orig_ax,
- regs->di, regs->si,
- regs->dx, regs->r10);
+ else
+ audit_syscall_entry(AUDIT_ARCH_X86_64,
+ regs->orig_ax,
+ regs->di, regs->si,
+ regs->dx, regs->r10);
#endif
- }
return ret ?: regs->orig_ax;
}
@@ -1414,8 +1412,7 @@ void syscall_trace_leave(struct pt_regs *regs)
{
bool step;
- if (unlikely(current->audit_context))
- audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
+ audit_syscall_exit(regs);
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_exit(regs, regs->ax);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 37a458b521a6..d840e69a853c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -39,6 +39,14 @@ static int reboot_mode;
enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;
+/* This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line). This is needed so that we can
+ * suppress DMI scanning for reboot quirks. Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+static int reboot_default = 1;
+
#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
static int reboot_cpu = -1;
#endif
@@ -67,6 +75,12 @@ bool port_cf9_safe = false;
static int __init reboot_setup(char *str)
{
for (;;) {
+ /* Having anything passed on the command line via
+ * reboot= will cause us to disable DMI checking
+ * below.
+ */
+ reboot_default = 0;
+
switch (*str) {
case 'w':
reboot_mode = 0x1234;
@@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
- { /* Handle problems with rebooting on VersaLogic Menlow boards */
- .callback = set_bios_reboot,
- .ident = "VersaLogic Menlow based board",
- .matches = {
- DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
- DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
- },
- },
{ /* Handle reboot issue on Acer Aspire one */
.callback = set_kbd_reboot,
.ident = "Acer Aspire One A110",
@@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
static int __init reboot_init(void)
{
- dmi_check_system(reboot_dmi_table);
+ /* Only do the DMI check if reboot_type hasn't been overridden
+ * on the command line
+ */
+ if (reboot_default) {
+ dmi_check_system(reboot_dmi_table);
+ }
return 0;
}
core_initcall(reboot_init);
@@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
static int __init pci_reboot_init(void)
{
- dmi_check_system(pci_reboot_dmi_table);
+ /* Only do the DMI check if reboot_type hasn't been overridden
+ * on the command line
+ */
+ if (reboot_default) {
+ dmi_check_system(pci_reboot_dmi_table);
+ }
return 0;
}
core_initcall(pci_reboot_init);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d05444ac2aea..d7d5099fe874 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -749,12 +749,7 @@ void __init setup_arch(char **cmdline_p)
#endif
#ifdef CONFIG_EFI
if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
-#ifdef CONFIG_X86_32
- "EL32",
-#else
- "EL64",
-#endif
- 4)) {
+ EFI_LOADER_SIGNATURE, 4)) {
efi_enabled = 1;
efi_memblock_x86_reserve_range();
}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 54ddaeb221c1..46a01bdc27e2 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -682,7 +682,6 @@ static int
handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
struct pt_regs *regs)
{
- sigset_t blocked;
int ret;
/* Are we from a system call? */
@@ -733,10 +732,7 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
*/
regs->flags &= ~X86_EFLAGS_TF;
- sigorsets(&blocked, &current->blocked, &ka->sa.sa_mask);
- if (!(ka->sa.sa_flags & SA_NODEFER))
- sigaddset(&blocked, sig);
- set_current_blocked(&blocked);
+ block_sigmask(ka, sig);
tracehook_signal_handler(sig, info, ka, regs,
test_thread_flag(TIF_SINGLESTEP));
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 16204dc15484..66c74f481cab 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -29,6 +29,7 @@
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/apic.h>
+#include <asm/nmi.h>
/*
* Some notes on x86 processor bugs affecting SMP operation:
*
@@ -148,6 +149,60 @@ void native_send_call_func_ipi(const struct cpumask *mask)
free_cpumask_var(allbutself);
}
+static atomic_t stopping_cpu = ATOMIC_INIT(-1);
+
+static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
+{
+ /* We are registered on stopping cpu too, avoid spurious NMI */
+ if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
+ return NMI_HANDLED;
+
+ stop_this_cpu(NULL);
+
+ return NMI_HANDLED;
+}
+
+static void native_nmi_stop_other_cpus(int wait)
+{
+ unsigned long flags;
+ unsigned long timeout;
+
+ if (reboot_force)
+ return;
+
+ /*
+ * Use an own vector here because smp_call_function
+ * does lots of things not suitable in a panic situation.
+ */
+ if (num_online_cpus() > 1) {
+ /* did someone beat us here? */
+ if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1)
+ return;
+
+ if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
+ NMI_FLAG_FIRST, "smp_stop"))
+ /* Note: we ignore failures here */
+ return;
+
+ /* sync above data before sending NMI */
+ wmb();
+
+ apic->send_IPI_allbutself(NMI_VECTOR);
+
+ /*
+ * Don't wait longer than a second if the caller
+ * didn't ask us to wait.
+ */
+ timeout = USEC_PER_SEC;
+ while (num_online_cpus() > 1 && (wait || timeout--))
+ udelay(1);
+ }
+
+ local_irq_save(flags);
+ disable_local_APIC();
+ local_irq_restore(flags);
+}
+
/*
* this function calls the 'stop' function on all other CPUs in the system.
*/
@@ -160,7 +215,7 @@ asmlinkage void smp_reboot_interrupt(void)
irq_exit();
}
-static void native_stop_other_cpus(int wait)
+static void native_irq_stop_other_cpus(int wait)
{
unsigned long flags;
unsigned long timeout;
@@ -194,6 +249,11 @@ static void native_stop_other_cpus(int wait)
local_irq_restore(flags);
}
+static void native_smp_disable_nmi_ipi(void)
+{
+ smp_ops.stop_other_cpus = native_irq_stop_other_cpus;
+}
+
/*
* Reschedule call back.
*/
@@ -225,12 +285,20 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
irq_exit();
}
+static int __init nonmi_ipi_setup(char *str)
+{
+ native_smp_disable_nmi_ipi();
+ return 1;
+}
+
+__setup("nonmi_ipi", nonmi_ipi_setup);
+
struct smp_ops smp_ops = {
.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
.smp_prepare_cpus = native_smp_prepare_cpus,
.smp_cpus_done = native_smp_cpus_done,
- .stop_other_cpus = native_stop_other_cpus,
+ .stop_other_cpus = native_nmi_stop_other_cpus,
.smp_send_reschedule = native_smp_send_reschedule,
.cpu_up = native_cpu_up,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e38e21754eea..66d250c00d11 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -207,23 +207,29 @@ static void __cpuinit smp_callin(void)
* Need to setup vector mappings before we enable interrupts.
*/
setup_vector_irq(smp_processor_id());
+
+ /*
+ * Save our processor parameters. Note: this information
+ * is needed for clock calibration.
+ */
+ smp_store_cpu_info(cpuid);
+
/*
* Get our bogomips.
+ * Update loops_per_jiffy in cpu_data. Previous call to
+ * smp_store_cpu_info() stored a value that is close but not as
+ * accurate as the value just calculated.
*
* Need to enable IRQs because it can take longer and then
* the NMI watchdog might kill us.
*/
local_irq_enable();
calibrate_delay();
+ cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
local_irq_disable();
pr_debug("Stack at about %p\n", &cpuid);
/*
- * Save our processor parameters
- */
- smp_store_cpu_info(cpuid);
-
- /*
* This must be done before setting cpu_online_mask
* or calling notify_cpu_starting.
*/
@@ -1143,6 +1149,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
{
pr_debug("Boot done.\n");
+ nmi_selftest();
impress_friends();
#ifdef CONFIG_X86_IO_APIC
setup_ioapic_dest();
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c
new file mode 100644
index 000000000000..147fcd4941c4
--- /dev/null
+++ b/arch/x86/kernel/syscall_32.c
@@ -0,0 +1,25 @@
+/* System call table for i386. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ;
+#include <asm/syscalls_32.h>
+#undef __SYSCALL_I386
+
+#define __SYSCALL_I386(nr, sym, compat) [nr] = sym,
+
+typedef asmlinkage void (*sys_call_ptr_t)(void);
+
+extern asmlinkage void sys_ni_syscall(void);
+
+const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_max] = &sys_ni_syscall,
+#include <asm/syscalls_32.h>
+};
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index de87d6008295..7ac7943be02c 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -5,15 +5,11 @@
#include <linux/cache.h>
#include <asm/asm-offsets.h>
-#define __NO_STUBS
+#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
+#include <asm/syscalls_64.h>
+#undef __SYSCALL_64
-#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ;
-#undef _ASM_X86_UNISTD_64_H
-#include <asm/unistd_64.h>
-
-#undef __SYSCALL
-#define __SYSCALL(nr, sym) [nr] = sym,
-#undef _ASM_X86_UNISTD_64_H
+#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
typedef void (*sys_call_ptr_t)(void);
@@ -21,9 +17,9 @@ extern void sys_ni_syscall(void);
const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
/*
- *Smells like a like a compiler bug -- it doesn't work
- *when the & below is removed.
- */
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
[0 ... __NR_syscall_max] = &sys_ni_syscall,
-#include <asm/unistd_64.h>
+#include <asm/syscalls_64.h>
};
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
deleted file mode 100644
index 9a0e31293920..000000000000
--- a/arch/x86/kernel/syscall_table_32.S
+++ /dev/null
@@ -1,350 +0,0 @@
-ENTRY(sys_call_table)
- .long sys_restart_syscall /* 0 - old "setup()" system call, used for restarting */
- .long sys_exit
- .long ptregs_fork
- .long sys_read
- .long sys_write
- .long sys_open /* 5 */
- .long sys_close
- .long sys_waitpid
- .long sys_creat
- .long sys_link
- .long sys_unlink /* 10 */
- .long ptregs_execve
- .long sys_chdir
- .long sys_time
- .long sys_mknod
- .long sys_chmod /* 15 */
- .long sys_lchown16
- .long sys_ni_syscall /* old break syscall holder */
- .long sys_stat
- .long sys_lseek
- .long sys_getpid /* 20 */
- .long sys_mount
- .long sys_oldumount
- .long sys_setuid16
- .long sys_getuid16
- .long sys_stime /* 25 */
- .long sys_ptrace
- .long sys_alarm
- .long sys_fstat
- .long sys_pause
- .long sys_utime /* 30 */
- .long sys_ni_syscall /* old stty syscall holder */
- .long sys_ni_syscall /* old gtty syscall holder */
- .long sys_access
- .long sys_nice
- .long sys_ni_syscall /* 35 - old ftime syscall holder */
- .long sys_sync
- .long sys_kill
- .long sys_rename
- .long sys_mkdir
- .long sys_rmdir /* 40 */
- .long sys_dup
- .long sys_pipe
- .long sys_times
- .long sys_ni_syscall /* old prof syscall holder */
- .long sys_brk /* 45 */
- .long sys_setgid16
- .long sys_getgid16
- .long sys_signal
- .long sys_geteuid16
- .long sys_getegid16 /* 50 */
- .long sys_acct
- .long sys_umount /* recycled never used phys() */
- .long sys_ni_syscall /* old lock syscall holder */
- .long sys_ioctl
- .long sys_fcntl /* 55 */
- .long sys_ni_syscall /* old mpx syscall holder */
- .long sys_setpgid
- .long sys_ni_syscall /* old ulimit syscall holder */
- .long sys_olduname
- .long sys_umask /* 60 */
- .long sys_chroot
- .long sys_ustat
- .long sys_dup2
- .long sys_getppid
- .long sys_getpgrp /* 65 */
- .long sys_setsid
- .long sys_sigaction
- .long sys_sgetmask
- .long sys_ssetmask
- .long sys_setreuid16 /* 70 */
- .long sys_setregid16
- .long sys_sigsuspend
- .long sys_sigpending
- .long sys_sethostname
- .long sys_setrlimit /* 75 */
- .long sys_old_getrlimit
- .long sys_getrusage
- .long sys_gettimeofday
- .long sys_settimeofday
- .long sys_getgroups16 /* 80 */
- .long sys_setgroups16
- .long sys_old_select
- .long sys_symlink
- .long sys_lstat
- .long sys_readlink /* 85 */
- .long sys_uselib
- .long sys_swapon
- .long sys_reboot
- .long sys_old_readdir
- .long sys_old_mmap /* 90 */
- .long sys_munmap
- .long sys_truncate
- .long sys_ftruncate
- .long sys_fchmod
- .long sys_fchown16 /* 95 */
- .long sys_getpriority
- .long sys_setpriority
- .long sys_ni_syscall /* old profil syscall holder */
- .long sys_statfs
- .long sys_fstatfs /* 100 */
- .long sys_ioperm
- .long sys_socketcall
- .long sys_syslog
- .long sys_setitimer
- .long sys_getitimer /* 105 */
- .long sys_newstat
- .long sys_newlstat
- .long sys_newfstat
- .long sys_uname
- .long ptregs_iopl /* 110 */
- .long sys_vhangup
- .long sys_ni_syscall /* old "idle" system call */
- .long ptregs_vm86old
- .long sys_wait4
- .long sys_swapoff /* 115 */
- .long sys_sysinfo
- .long sys_ipc
- .long sys_fsync
- .long ptregs_sigreturn
- .long ptregs_clone /* 120 */
- .long sys_setdomainname
- .long sys_newuname
- .long sys_modify_ldt
- .long sys_adjtimex
- .long sys_mprotect /* 125 */
- .long sys_sigprocmask
- .long sys_ni_syscall /* old "create_module" */
- .long sys_init_module
- .long sys_delete_module
- .long sys_ni_syscall /* 130: old "get_kernel_syms" */
- .long sys_quotactl
- .long sys_getpgid
- .long sys_fchdir
- .long sys_bdflush
- .long sys_sysfs /* 135 */
- .long sys_personality
- .long sys_ni_syscall /* reserved for afs_syscall */
- .long sys_setfsuid16
- .long sys_setfsgid16
- .long sys_llseek /* 140 */
- .long sys_getdents
- .long sys_select
- .long sys_flock
- .long sys_msync
- .long sys_readv /* 145 */
- .long sys_writev
- .long sys_getsid
- .long sys_fdatasync
- .long sys_sysctl
- .long sys_mlock /* 150 */
- .long sys_munlock
- .long sys_mlockall
- .long sys_munlockall
- .long sys_sched_setparam
- .long sys_sched_getparam /* 155 */
- .long sys_sched_setscheduler
- .long sys_sched_getscheduler
- .long sys_sched_yield
- .long sys_sched_get_priority_max
- .long sys_sched_get_priority_min /* 160 */
- .long sys_sched_rr_get_interval
- .long sys_nanosleep
- .long sys_mremap
- .long sys_setresuid16
- .long sys_getresuid16 /* 165 */
- .long ptregs_vm86
- .long sys_ni_syscall /* Old sys_query_module */
- .long sys_poll
- .long sys_ni_syscall /* Old nfsservctl */
- .long sys_setresgid16 /* 170 */
- .long sys_getresgid16
- .long sys_prctl
- .long ptregs_rt_sigreturn
- .long sys_rt_sigaction
- .long sys_rt_sigprocmask /* 175 */
- .long sys_rt_sigpending
- .long sys_rt_sigtimedwait
- .long sys_rt_sigqueueinfo
- .long sys_rt_sigsuspend
- .long sys_pread64 /* 180 */
- .long sys_pwrite64
- .long sys_chown16
- .long sys_getcwd
- .long sys_capget
- .long sys_capset /* 185 */
- .long ptregs_sigaltstack
- .long sys_sendfile
- .long sys_ni_syscall /* reserved for streams1 */
- .long sys_ni_syscall /* reserved for streams2 */
- .long ptregs_vfork /* 190 */
- .long sys_getrlimit
- .long sys_mmap_pgoff
- .long sys_truncate64
- .long sys_ftruncate64
- .long sys_stat64 /* 195 */
- .long sys_lstat64
- .long sys_fstat64
- .long sys_lchown
- .long sys_getuid
- .long sys_getgid /* 200 */
- .long sys_geteuid
- .long sys_getegid
- .long sys_setreuid
- .long sys_setregid
- .long sys_getgroups /* 205 */
- .long sys_setgroups
- .long sys_fchown
- .long sys_setresuid
- .long sys_getresuid
- .long sys_setresgid /* 210 */
- .long sys_getresgid
- .long sys_chown
- .long sys_setuid
- .long sys_setgid
- .long sys_setfsuid /* 215 */
- .long sys_setfsgid
- .long sys_pivot_root
- .long sys_mincore
- .long sys_madvise
- .long sys_getdents64 /* 220 */
- .long sys_fcntl64
- .long sys_ni_syscall /* reserved for TUX */
- .long sys_ni_syscall
- .long sys_gettid
- .long sys_readahead /* 225 */
- .long sys_setxattr
- .long sys_lsetxattr
- .long sys_fsetxattr
- .long sys_getxattr
- .long sys_lgetxattr /* 230 */
- .long sys_fgetxattr
- .long sys_listxattr
- .long sys_llistxattr
- .long sys_flistxattr
- .long sys_removexattr /* 235 */
- .long sys_lremovexattr
- .long sys_fremovexattr
- .long sys_tkill
- .long sys_sendfile64
- .long sys_futex /* 240 */
- .long sys_sched_setaffinity
- .long sys_sched_getaffinity
- .long sys_set_thread_area
- .long sys_get_thread_area
- .long sys_io_setup /* 245 */
- .long sys_io_destroy
- .long sys_io_getevents
- .long sys_io_submit
- .long sys_io_cancel
- .long sys_fadvise64 /* 250 */
- .long sys_ni_syscall
- .long sys_exit_group
- .long sys_lookup_dcookie
- .long sys_epoll_create
- .long sys_epoll_ctl /* 255 */
- .long sys_epoll_wait
- .long sys_remap_file_pages
- .long sys_set_tid_address
- .long sys_timer_create
- .long sys_timer_settime /* 260 */
- .long sys_timer_gettime
- .long sys_timer_getoverrun
- .long sys_timer_delete
- .long sys_clock_settime
- .long sys_clock_gettime /* 265 */
- .long sys_clock_getres
- .long sys_clock_nanosleep
- .long sys_statfs64
- .long sys_fstatfs64
- .long sys_tgkill /* 270 */
- .long sys_utimes
- .long sys_fadvise64_64
- .long sys_ni_syscall /* sys_vserver */
- .long sys_mbind
- .long sys_get_mempolicy
- .long sys_set_mempolicy
- .long sys_mq_open
- .long sys_mq_unlink
- .long sys_mq_timedsend
- .long sys_mq_timedreceive /* 280 */
- .long sys_mq_notify
- .long sys_mq_getsetattr
- .long sys_kexec_load
- .long sys_waitid
- .long sys_ni_syscall /* 285 */ /* available */
- .long sys_add_key
- .long sys_request_key
- .long sys_keyctl
- .long sys_ioprio_set
- .long sys_ioprio_get /* 290 */
- .long sys_inotify_init
- .long sys_inotify_add_watch
- .long sys_inotify_rm_watch
- .long sys_migrate_pages
- .long sys_openat /* 295 */
- .long sys_mkdirat
- .long sys_mknodat
- .long sys_fchownat
- .long sys_futimesat
- .long sys_fstatat64 /* 300 */
- .long sys_unlinkat
- .long sys_renameat
- .long sys_linkat
- .long sys_symlinkat
- .long sys_readlinkat /* 305 */
- .long sys_fchmodat
- .long sys_faccessat
- .long sys_pselect6
- .long sys_ppoll
- .long sys_unshare /* 310 */
- .long sys_set_robust_list
- .long sys_get_robust_list
- .long sys_splice
- .long sys_sync_file_range
- .long sys_tee /* 315 */
- .long sys_vmsplice
- .long sys_move_pages
- .long sys_getcpu
- .long sys_epoll_pwait
- .long sys_utimensat /* 320 */
- .long sys_signalfd
- .long sys_timerfd_create
- .long sys_eventfd
- .long sys_fallocate
- .long sys_timerfd_settime /* 325 */
- .long sys_timerfd_gettime
- .long sys_signalfd4
- .long sys_eventfd2
- .long sys_epoll_create1
- .long sys_dup3 /* 330 */
- .long sys_pipe2
- .long sys_inotify_init1
- .long sys_preadv
- .long sys_pwritev
- .long sys_rt_tgsigqueueinfo /* 335 */
- .long sys_perf_event_open
- .long sys_recvmmsg
- .long sys_fanotify_init
- .long sys_fanotify_mark
- .long sys_prlimit64 /* 340 */
- .long sys_name_to_handle_at
- .long sys_open_by_handle_at
- .long sys_clock_adjtime
- .long sys_syncfs
- .long sys_sendmmsg /* 345 */
- .long sys_setns
- .long sys_process_vm_readv
- .long sys_process_vm_writev
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index fa1191fb679d..482ec3af2067 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -311,9 +311,15 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
== NOTIFY_STOP)
return;
+ /*
+ * Let others (NMI) know that the debug stack is in use
+ * as we may switch to the interrupt stack.
+ */
+ debug_stack_usage_inc();
preempt_conditional_sti(regs);
do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
+ debug_stack_usage_dec();
}
#ifdef CONFIG_X86_64
@@ -406,6 +412,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
SIGTRAP) == NOTIFY_STOP)
return;
+ /*
+ * Let others (NMI) know that the debug stack is in use
+ * as we may switch to the interrupt stack.
+ */
+ debug_stack_usage_inc();
+
/* It's safe to allow irq's after DR6 has been saved */
preempt_conditional_sti(regs);
@@ -413,6 +425,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
handle_vm86_trap((struct kernel_vm86_regs *) regs,
error_code, 1);
preempt_conditional_cli(regs);
+ debug_stack_usage_dec();
return;
}
@@ -432,6 +445,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
send_sigtrap(tsk, regs, error_code, si_code);
preempt_conditional_cli(regs);
+ debug_stack_usage_dec();
return;
}
@@ -718,4 +732,10 @@ void __init trap_init(void)
cpu_init();
x86_init.irqs.trap_init();
+
+#ifdef CONFIG_X86_64
+ memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16);
+ set_nmi_gate(1, &debug);
+ set_nmi_gate(3, &int3);
+#endif
}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 2c9cf0fd78f5..a62c201c97ec 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -290,14 +290,15 @@ static inline int pit_verify_msb(unsigned char val)
static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
{
int count;
- u64 tsc = 0;
+ u64 tsc = 0, prev_tsc = 0;
for (count = 0; count < 50000; count++) {
if (!pit_verify_msb(val))
break;
+ prev_tsc = tsc;
tsc = get_cycles();
}
- *deltap = get_cycles() - tsc;
+ *deltap = get_cycles() - prev_tsc;
*tscp = tsc;
/*
@@ -311,9 +312,9 @@ static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *de
* How many MSB values do we want to see? We aim for
* a maximum error rate of 500ppm (in practice the
* real error is much smaller), but refuse to spend
- * more than 25ms on it.
+ * more than 50ms on it.
*/
-#define MAX_QUICK_PIT_MS 25
+#define MAX_QUICK_PIT_MS 50
#define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
static unsigned long quick_pit_calibrate(void)
@@ -383,15 +384,12 @@ success:
*
* As a result, we can depend on there not being
* any odd delays anywhere, and the TSC reads are
- * reliable (within the error). We also adjust the
- * delta to the middle of the error bars, just
- * because it looks nicer.
+ * reliable (within the error).
*
* kHz = ticks / time-in-seconds / 1000;
* kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000
* kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000)
*/
- delta += (long)(d2 - d1)/2;
delta *= PIT_TICK_RATE;
do_div(delta, i*256*1000);
printk("Fast TSC calibration using PIT\n");
@@ -995,3 +993,23 @@ void __init tsc_init(void)
check_system_tsc_reliable();
}
+#ifdef CONFIG_SMP
+/*
+ * If we have a constant TSC and are using the TSC for the delay loop,
+ * we can skip clock calibration if another cpu in the same socket has already
+ * been calibrated. This assumes that CONSTANT_TSC applies to all
+ * cpus in the socket - this should be a safe assumption.
+ */
+unsigned long __cpuinit calibrate_delay_is_known(void)
+{
+ int i, cpu = smp_processor_id();
+
+ if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC))
+ return 0;
+
+ for_each_online_cpu(i)
+ if (cpu_data(i).phys_proc_id == cpu_data(cpu).phys_proc_id)
+ return cpu_data(i).loops_per_jiffy;
+ return 0;
+}
+#endif
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 863f8753ab0a..b466cab5ba15 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -335,9 +335,11 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
if (info->flags & VM86_SCREEN_BITMAP)
mark_screen_rdonly(tsk->mm);
- /*call audit_syscall_exit since we do not exit via the normal paths */
+ /*call __audit_syscall_exit since we do not exit via the normal paths */
+#ifdef CONFIG_AUDITSYSCALL
if (unlikely(current->audit_context))
- audit_syscall_exit(AUDITSC_RESULT(0), 0);
+ __audit_syscall_exit(1, 0);
+#endif
__asm__ __volatile__(
"movl %0,%%esp\n\t"
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 91f83e21b989..947a06ccc673 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -115,4 +115,5 @@ struct x86_msi_ops x86_msi = {
.setup_msi_irqs = native_setup_msi_irqs,
.teardown_msi_irq = native_teardown_msi_irq,
.teardown_msi_irqs = default_teardown_msi_irqs,
+ .restore_msi_irqs = default_restore_msi_irqs,
};
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2a2a9b40db19..224b02c3cda9 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -74,7 +74,7 @@ enum {
#endif
#ifdef MMU_DEBUG
-static int dbg = 0;
+static bool dbg = 0;
module_param(dbg, bool, 0644);
#endif
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 906a7e84200f..d29216c462b3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -51,29 +51,29 @@
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
-static int __read_mostly enable_vpid = 1;
+static bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
-static int __read_mostly flexpriority_enabled = 1;
+static bool __read_mostly flexpriority_enabled = 1;
module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO);
-static int __read_mostly enable_ept = 1;
+static bool __read_mostly enable_ept = 1;
module_param_named(ept, enable_ept, bool, S_IRUGO);
-static int __read_mostly enable_unrestricted_guest = 1;
+static bool __read_mostly enable_unrestricted_guest = 1;
module_param_named(unrestricted_guest,
enable_unrestricted_guest, bool, S_IRUGO);
-static int __read_mostly emulate_invalid_guest_state = 0;
+static bool __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
-static int __read_mostly vmm_exclusive = 1;
+static bool __read_mostly vmm_exclusive = 1;
module_param(vmm_exclusive, bool, S_IRUGO);
-static int __read_mostly yield_on_hlt = 1;
+static bool __read_mostly yield_on_hlt = 1;
module_param(yield_on_hlt, bool, S_IRUGO);
-static int __read_mostly fasteoi = 1;
+static bool __read_mostly fasteoi = 1;
module_param(fasteoi, bool, S_IRUGO);
/*
@@ -81,7 +81,7 @@ module_param(fasteoi, bool, S_IRUGO);
* VMX and be a hypervisor for its own guests. If nested=0, guests may not
* use VMX instructions.
*/
-static int __read_mostly nested = 0;
+static bool __read_mostly nested = 0;
module_param(nested, bool, S_IRUGO);
#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1171def5f96b..14d6cadc4ba6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -88,8 +88,8 @@ static void process_nmi(struct kvm_vcpu *vcpu);
struct kvm_x86_ops *kvm_x86_ops;
EXPORT_SYMBOL_GPL(kvm_x86_ops);
-int ignore_msrs = 0;
-module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);
+static bool ignore_msrs = 0;
+module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index cf4603ba866f..642d8805bc1b 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -856,18 +856,23 @@ static void __init lguest_init_IRQ(void)
}
/*
- * With CONFIG_SPARSE_IRQ, interrupt descriptors are allocated as-needed, so
- * rather than set them in lguest_init_IRQ we are called here every time an
- * lguest device needs an interrupt.
- *
- * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should
- * pass that up!
+ * Interrupt descriptors are allocated as-needed, but low-numbered ones are
+ * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it
+ * tells us the irq is already used: other errors (ie. ENOMEM) we take
+ * seriously.
*/
-void lguest_setup_irq(unsigned int irq)
+int lguest_setup_irq(unsigned int irq)
{
- irq_alloc_desc_at(irq, 0);
+ int err;
+
+ /* Returns -ve error or vector number. */
+ err = irq_alloc_desc_at(irq, 0);
+ if (err < 0 && err != -EEXIST)
+ return err;
+
irq_set_chip_and_handler_name(irq, &lguest_irq_controller,
handle_level_irq, "level");
+ return 0;
}
/*
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5b83c51c12e0..819137904428 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -219,7 +219,9 @@ ab: STOS/W/D/Q Yv,rAX
ac: LODS/B AL,Xb
ad: LODS/W/D/Q rAX,Xv
ae: SCAS/B AL,Yb
-af: SCAS/W/D/Q rAX,Xv
+# Note: The May 2011 Intel manual shows Xv for the second parameter of the
+# next instruction but Yv is correct
+af: SCAS/W/D/Q rAX,Yv
# 0xb0 - 0xbf
b0: MOV AL/R8L,Ib
b1: MOV CL/R9L,Ib
@@ -729,8 +731,8 @@ de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
-f3: ANDN Gy,By,Ey (v)
-f4: Grp17 (1A)
+f2: ANDN Gy,By,Ey (v)
+f3: Grp17 (1A)
f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
f6: MULX By,Gy,rDX,Ey (F2),(v)
f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d74824a708d..f0b4caf85c1a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -673,7 +673,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
stackend = end_of_stack(tsk);
if (tsk != &init_task && *stackend != STACK_END_MAGIC)
- printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+ printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
tsk->thread.cr2 = address;
tsk->thread.trap_no = 14;
@@ -684,7 +684,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
sig = 0;
/* Executive summary in case the body of the oops scrolled away */
- printk(KERN_EMERG "CR2: %016lx\n", address);
+ printk(KERN_DEFAULT "CR2: %016lx\n", address);
oops_end(flags, regs, sig);
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a298914058f9..6cabf6570d64 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -3,6 +3,7 @@
#include <linux/ioport.h>
#include <linux/swap.h>
#include <linux/memblock.h>
+#include <linux/bootmem.h> /* for max_low_pfn */
#include <asm/cacheflush.h>
#include <asm/e820.h>
@@ -15,6 +16,7 @@
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <asm/proto.h>
+#include <asm/dma.h> /* for MAX_DMA_PFN */
unsigned long __initdata pgt_buf_start;
unsigned long __meminitdata pgt_buf_end;
@@ -392,3 +394,24 @@ void free_initrd_mem(unsigned long start, unsigned long end)
free_init_pages("initrd memory", start, PAGE_ALIGN(end));
}
#endif
+
+void __init zone_sizes_init(void)
+{
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+
+#ifdef CONFIG_ZONE_DMA
+ max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+#endif
+#ifdef CONFIG_ZONE_DMA32
+ max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+#endif
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+ max_zone_pfns[ZONE_HIGHMEM] = max_pfn;
+#endif
+
+ free_area_init_nodes(max_zone_pfns);
+}
+
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 0c1da394a634..8663f6c47ccb 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -668,22 +668,6 @@ void __init initmem_init(void)
}
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
-static void __init zone_sizes_init(void)
-{
- unsigned long max_zone_pfns[MAX_NR_ZONES];
- memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] =
- virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-#endif
- max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
-#ifdef CONFIG_HIGHMEM
- max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
-#endif
-
- free_area_init_nodes(max_zone_pfns);
-}
-
void __init setup_bootmem_allocator(void)
{
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
@@ -754,6 +738,17 @@ void __init mem_init(void)
#ifdef CONFIG_FLATMEM
BUG_ON(!mem_map);
#endif
+ /*
+ * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to
+ * be done before free_all_bootmem(). Memblock use free low memory for
+ * temporary data (see find_range_array()) and for this purpose can use
+ * pages that was already passed to the buddy allocator, hence marked as
+ * not accessible in the page tables when compiled with
+ * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not
+ * important here.
+ */
+ set_highmem_pages_init();
+
/* this will put all low memory onto the freelists */
totalram_pages += free_all_bootmem();
@@ -765,8 +760,6 @@ void __init mem_init(void)
if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
reservedpages++;
- set_highmem_pages_init();
-
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a8a56ce3a962..436a0309db33 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -614,15 +614,6 @@ void __init initmem_init(void)
void __init paging_init(void)
{
- unsigned long max_zone_pfns[MAX_NR_ZONES];
-
- memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
- max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
- max_zone_pfns[ZONE_NORMAL] = max_pfn;
-
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
@@ -634,7 +625,7 @@ void __init paging_init(void)
*/
node_clear_state(0, N_NORMAL_MEMORY);
- free_area_init_nodes(max_zone_pfns);
+ zone_sizes_init();
}
/*
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 4b5ba85eb5c9..845df6835f9f 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -75,9 +75,9 @@ static unsigned long mmap_rnd(void)
*/
if (current->flags & PF_RANDOMIZE) {
if (mmap_is_ia32())
- rnd = (long)get_random_int() % (1<<8);
+ rnd = get_random_int() % (1<<8);
else
- rnd = (long)(get_random_int() % (1<<28));
+ rnd = get_random_int() % (1<<28);
}
return rnd << PAGE_SHIFT;
}
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index de54b9b278a7..dc0b727742f4 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -75,8 +75,8 @@ static LIST_HEAD(trace_list); /* struct remap_trace */
/* module parameters */
static unsigned long filter_offset;
-static int nommiotrace;
-static int trace_pc;
+static bool nommiotrace;
+static bool trace_pc;
module_param(filter_offset, ulong, 0);
module_param(nommiotrace, bool, 0);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 496f494593bf..19d3fa08b119 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -110,7 +110,7 @@ void __cpuinit numa_clear_node(int cpu)
* Allocate node_to_cpumask_map based on number of available nodes
* Requires node_possible_map to be valid.
*
- * Note: node_to_cpumask() is not valid until after this is done.
+ * Note: cpumask_of_node() is not valid until after this is done.
* (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
*/
void __init setup_node_to_cpumask_map(void)
@@ -422,8 +422,9 @@ static int __init numa_alloc_distance(void)
* calls are ignored until the distance table is reset with
* numa_reset_distance().
*
- * If @from or @to is higher than the highest known node at the time of
- * table creation or @distance doesn't make sense, the call is ignored.
+ * If @from or @to is higher than the highest known node or lower than zero
+ * at the time of table creation or @distance doesn't make sense, the call
+ * is ignored.
* This is to allow simplification of specific NUMA config implementations.
*/
void __init numa_set_distance(int from, int to, int distance)
@@ -431,8 +432,9 @@ void __init numa_set_distance(int from, int to, int distance)
if (!numa_distance && numa_alloc_distance() < 0)
return;
- if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
- printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+ from < 0 || to < 0) {
+ pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index eda2acbb6e81..e1ebde315210 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1334,12 +1334,6 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
}
/*
- * If page allocator is not up yet then do not call c_p_a():
- */
- if (!debug_pagealloc_enabled)
- return;
-
- /*
* The return value is ignored as the calls cannot fail.
* Large pages for identity mappings are not used at boot time
* and hence no memory allocations during large page split.
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index fd61b3fb7341..1c1c4f46a7c1 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -109,6 +109,8 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
return;
pxm = pa->proximity_domain_lo;
+ if (acpi_srat_revision >= 2)
+ pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
@@ -160,6 +162,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
start = ma->base_address;
end = start + ma->length;
pxm = ma->proximity_domain;
+ if (acpi_srat_revision <= 1)
+ pxm &= 0xff;
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains.\n");
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7b65f752c5f8..7c1b765ecc59 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -151,17 +151,18 @@ void bpf_jit_compile(struct sk_filter *fp)
cleanup_addr = proglen; /* epilogue address */
for (pass = 0; pass < 10; pass++) {
+ u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
/* no prologue/epilogue for trivial filters (RET something) */
proglen = 0;
prog = temp;
- if (seen) {
+ if (seen_or_pass0) {
EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */
/* note : must save %rbx in case bpf_error is hit */
- if (seen & (SEEN_XREG | SEEN_DATAREF))
+ if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF))
EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
- if (seen & SEEN_XREG)
+ if (seen_or_pass0 & SEEN_XREG)
CLEAR_X(); /* make sure we dont leek kernel memory */
/*
@@ -170,7 +171,7 @@ void bpf_jit_compile(struct sk_filter *fp)
* r9 = skb->len - skb->data_len
* r8 = skb->data
*/
- if (seen & SEEN_DATAREF) {
+ if (seen_or_pass0 & SEEN_DATAREF) {
if (offsetof(struct sk_buff, len) <= 127)
/* mov off8(%rdi),%r9d */
EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
@@ -260,9 +261,14 @@ void bpf_jit_compile(struct sk_filter *fp)
case BPF_S_ALU_DIV_X: /* A /= X; */
seen |= SEEN_XREG;
EMIT2(0x85, 0xdb); /* test %ebx,%ebx */
- if (pc_ret0 != -1)
- EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4));
- else {
+ if (pc_ret0 > 0) {
+ /* addrs[pc_ret0 - 1] is start address of target
+ * (addrs[i] - 4) is the address following this jmp
+ * ("xor %edx,%edx; div %ebx" being 4 bytes long)
+ */
+ EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
+ (addrs[i] - 4));
+ } else {
EMIT_COND_JMP(X86_JNE, 2 + 5);
CLEAR_A();
EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
@@ -335,12 +341,12 @@ void bpf_jit_compile(struct sk_filter *fp)
}
/* fallinto */
case BPF_S_RET_A:
- if (seen) {
+ if (seen_or_pass0) {
if (i != flen - 1) {
EMIT_JMP(cleanup_addr - addrs[i]);
break;
}
- if (seen & SEEN_XREG)
+ if (seen_or_pass0 & SEEN_XREG)
EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */
EMIT1(0xc9); /* leaveq */
}
@@ -483,8 +489,9 @@ common_load: seen |= SEEN_DATAREF;
goto common_load;
case BPF_S_LDX_B_MSH:
if ((int)K < 0) {
- if (pc_ret0 != -1) {
- EMIT_JMP(addrs[pc_ret0] - addrs[i]);
+ if (pc_ret0 > 0) {
+ /* addrs[pc_ret0 - 1] is the start address */
+ EMIT_JMP(addrs[pc_ret0 - 1] - addrs[i]);
break;
}
CLEAR_A();
@@ -599,13 +606,14 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i];
* use it to give the cleanup instruction(s) addr
*/
cleanup_addr = proglen - 1; /* ret */
- if (seen)
+ if (seen_or_pass0)
cleanup_addr -= 1; /* leaveq */
- if (seen & SEEN_XREG)
+ if (seen_or_pass0 & SEEN_XREG)
cleanup_addr -= 4; /* mov -8(%rbp),%rbx */
if (image) {
- WARN_ON(proglen != oldproglen);
+ if (proglen != oldproglen)
+ pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen);
break;
}
if (proglen == oldproglen) {
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 6b8759f7634e..e76e18c94a3c 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -15,11 +15,12 @@ obj-$(CONFIG_X86_VISWS) += visws.o
obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
-obj-$(CONFIG_X86_MRST) += mrst.o
+obj-$(CONFIG_X86_INTEL_MID) += mrst.o
obj-y += common.o early.o
-obj-y += amd_bus.o bus_numa.o
+obj-y += bus_numa.o
+obj-$(CONFIG_AMD_NB) += amd_bus.o
obj-$(CONFIG_PCI_CNB20LE_QUIRK) += broadcom_bus.o
ifeq ($(CONFIG_PCI_DEBUG),y)
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 404f21a3ff9e..a312e76063a7 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -12,7 +12,7 @@ struct pci_root_info {
char *name;
unsigned int res_num;
struct resource *res;
- struct pci_bus *bus;
+ struct list_head *resources;
int busnum;
};
@@ -24,6 +24,12 @@ static int __init set_use_crs(const struct dmi_system_id *id)
return 0;
}
+static int __init set_nouse_crs(const struct dmi_system_id *id)
+{
+ pci_use_crs = false;
+ return 0;
+}
+
static const struct dmi_system_id pci_use_crs_table[] __initconst = {
/* http://bugzilla.kernel.org/show_bug.cgi?id=14183 */
{
@@ -54,6 +60,29 @@ static const struct dmi_system_id pci_use_crs_table[] __initconst = {
DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
},
},
+
+ /* Now for the blacklist.. */
+
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=769657 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Dell Studio 1557",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Studio 1557"),
+ DMI_MATCH(DMI_BIOS_VERSION, "A09"),
+ },
+ },
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=769657 */
+ {
+ .callback = set_nouse_crs,
+ .ident = "Thinkpad SL510",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_BOARD_NAME, "2847DFG"),
+ DMI_MATCH(DMI_BIOS_VERSION, "6JET85WW (1.43 )"),
+ },
+ },
{}
};
@@ -149,7 +178,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
struct acpi_resource_address64 addr;
acpi_status status;
unsigned long flags;
- u64 start, end;
+ u64 start, orig_end, end;
status = resource_to_addr(acpi_res, &addr);
if (!ACPI_SUCCESS(status))
@@ -165,7 +194,21 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
return AE_OK;
start = addr.minimum + addr.translation_offset;
- end = addr.maximum + addr.translation_offset;
+ orig_end = end = addr.maximum + addr.translation_offset;
+
+ /* Exclude non-addressable range or non-addressable portion of range */
+ end = min(end, (u64)iomem_resource.end);
+ if (end <= start) {
+ dev_info(&info->bridge->dev,
+ "host bridge window [%#llx-%#llx] "
+ "(ignored, not CPU addressable)\n", start, orig_end);
+ return AE_OK;
+ } else if (orig_end != end) {
+ dev_info(&info->bridge->dev,
+ "host bridge window [%#llx-%#llx] "
+ "([%#llx-%#llx] ignored, not CPU addressable)\n",
+ start, orig_end, end + 1, orig_end);
+ }
res = &info->res[info->res_num];
res->name = info->name;
@@ -261,23 +304,20 @@ static void add_resources(struct pci_root_info *info)
"ignoring host bridge window %pR (conflicts with %s %pR)\n",
res, conflict->name, conflict);
else
- pci_bus_add_resource(info->bus, res, 0);
+ pci_add_resource(info->resources, res);
}
}
static void
get_current_resources(struct acpi_device *device, int busnum,
- int domain, struct pci_bus *bus)
+ int domain, struct list_head *resources)
{
struct pci_root_info info;
size_t size;
- if (pci_use_crs)
- pci_bus_remove_resources(bus);
-
info.bridge = device;
- info.bus = bus;
info.res_num = 0;
+ info.resources = resources;
acpi_walk_resources(device->handle, METHOD_NAME__CRS, count_resource,
&info);
if (!info.res_num)
@@ -286,7 +326,7 @@ get_current_resources(struct acpi_device *device, int busnum,
size = sizeof(*info.res) * info.res_num;
info.res = kmalloc(size, GFP_KERNEL);
if (!info.res)
- goto res_alloc_fail;
+ return;
info.name = kasprintf(GFP_KERNEL, "PCI Bus %04x:%02x", domain, busnum);
if (!info.name)
@@ -301,8 +341,6 @@ get_current_resources(struct acpi_device *device, int busnum,
name_alloc_fail:
kfree(info.res);
-res_alloc_fail:
- return;
}
struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
@@ -310,6 +348,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
struct acpi_device *device = root->device;
int domain = root->segment;
int busnum = root->secondary.start;
+ LIST_HEAD(resources);
struct pci_bus *bus;
struct pci_sysdata *sd;
int node;
@@ -364,11 +403,15 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root)
memcpy(bus->sysdata, sd, sizeof(*sd));
kfree(sd);
} else {
- bus = pci_create_bus(NULL, busnum, &pci_root_ops, sd);
- if (bus) {
- get_current_resources(device, busnum, domain, bus);
+ get_current_resources(device, busnum, domain, &resources);
+ if (list_empty(&resources))
+ x86_pci_root_bus_resources(busnum, &resources);
+ bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, sd,
+ &resources);
+ if (bus)
bus->subordinate = pci_scan_child_bus(bus);
- }
+ else
+ pci_free_resource_list(&resources);
}
/* After the PCI-E bus has been walked and all devices discovered,
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 026e4931d162..0567df3890e1 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -30,34 +30,6 @@ static struct pci_hostbridge_probe pci_probes[] __initdata = {
{ 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 },
};
-static u64 __initdata fam10h_mmconf_start;
-static u64 __initdata fam10h_mmconf_end;
-static void __init get_pci_mmcfg_amd_fam10h_range(void)
-{
- u32 address;
- u64 base, msr;
- unsigned segn_busn_bits;
-
- /* assume all cpus from fam10h have mmconf */
- if (boot_cpu_data.x86 < 0x10)
- return;
-
- address = MSR_FAM10H_MMIO_CONF_BASE;
- rdmsrl(address, msr);
-
- /* mmconfig is not enable */
- if (!(msr & FAM10H_MMIO_CONF_ENABLE))
- return;
-
- base = msr & (FAM10H_MMIO_CONF_BASE_MASK<<FAM10H_MMIO_CONF_BASE_SHIFT);
-
- segn_busn_bits = (msr >> FAM10H_MMIO_CONF_BUSRANGE_SHIFT) &
- FAM10H_MMIO_CONF_BUSRANGE_MASK;
-
- fam10h_mmconf_start = base;
- fam10h_mmconf_end = base + (1ULL<<(segn_busn_bits + 20)) - 1;
-}
-
#define RANGE_NUM 16
/**
@@ -85,6 +57,9 @@ static int __init early_fill_mp_bus_info(void)
u64 val;
u32 address;
bool found;
+ struct resource fam10h_mmconf_res, *fam10h_mmconf;
+ u64 fam10h_mmconf_start;
+ u64 fam10h_mmconf_end;
if (!early_pci_allowed())
return -1;
@@ -211,12 +186,17 @@ static int __init early_fill_mp_bus_info(void)
subtract_range(range, RANGE_NUM, 0, end);
/* get mmconfig */
- get_pci_mmcfg_amd_fam10h_range();
+ fam10h_mmconf = amd_get_mmconfig_range(&fam10h_mmconf_res);
/* need to take out mmconf range */
- if (fam10h_mmconf_end) {
- printk(KERN_DEBUG "Fam 10h mmconf [%llx, %llx]\n", fam10h_mmconf_start, fam10h_mmconf_end);
+ if (fam10h_mmconf) {
+ printk(KERN_DEBUG "Fam 10h mmconf %pR\n", fam10h_mmconf);
+ fam10h_mmconf_start = fam10h_mmconf->start;
+ fam10h_mmconf_end = fam10h_mmconf->end;
subtract_range(range, RANGE_NUM, fam10h_mmconf_start,
fam10h_mmconf_end + 1);
+ } else {
+ fam10h_mmconf_start = 0;
+ fam10h_mmconf_end = 0;
}
/* mmio resource */
@@ -403,7 +383,6 @@ static void __init pci_enable_pci_io_ecs(void)
++n;
}
}
- pr_info("Extended Config Space enabled on %u nodes\n", n);
#endif
}
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index ab8269b0da29..f3a7c569a403 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -15,10 +15,11 @@
#include <linux/pci.h>
#include <linux/init.h>
#include <asm/pci_x86.h>
+#include <asm/pci-direct.h>
#include "bus_numa.h"
-static void __devinit cnb20le_res(struct pci_dev *dev)
+static void __init cnb20le_res(u8 bus, u8 slot, u8 func)
{
struct pci_root_info *info;
struct resource res;
@@ -26,21 +27,12 @@ static void __devinit cnb20le_res(struct pci_dev *dev)
u8 fbus, lbus;
int i;
-#ifdef CONFIG_ACPI
- /*
- * We should get host bridge information from ACPI unless the BIOS
- * doesn't support it.
- */
- if (acpi_os_get_root_pointer())
- return;
-#endif
-
info = &pci_root_info[pci_root_num];
pci_root_num++;
/* read the PCI bus numbers */
- pci_read_config_byte(dev, 0x44, &fbus);
- pci_read_config_byte(dev, 0x45, &lbus);
+ fbus = read_pci_config_byte(bus, slot, func, 0x44);
+ lbus = read_pci_config_byte(bus, slot, func, 0x45);
info->bus_min = fbus;
info->bus_max = lbus;
@@ -59,8 +51,8 @@ static void __devinit cnb20le_res(struct pci_dev *dev)
}
/* read the non-prefetchable memory window */
- pci_read_config_word(dev, 0xc0, &word1);
- pci_read_config_word(dev, 0xc2, &word2);
+ word1 = read_pci_config_16(bus, slot, func, 0xc0);
+ word2 = read_pci_config_16(bus, slot, func, 0xc2);
if (word1 != word2) {
res.start = (word1 << 16) | 0x0000;
res.end = (word2 << 16) | 0xffff;
@@ -69,8 +61,8 @@ static void __devinit cnb20le_res(struct pci_dev *dev)
}
/* read the prefetchable memory window */
- pci_read_config_word(dev, 0xc4, &word1);
- pci_read_config_word(dev, 0xc6, &word2);
+ word1 = read_pci_config_16(bus, slot, func, 0xc4);
+ word2 = read_pci_config_16(bus, slot, func, 0xc6);
if (word1 != word2) {
res.start = (word1 << 16) | 0x0000;
res.end = (word2 << 16) | 0xffff;
@@ -79,8 +71,8 @@ static void __devinit cnb20le_res(struct pci_dev *dev)
}
/* read the IO port window */
- pci_read_config_word(dev, 0xd0, &word1);
- pci_read_config_word(dev, 0xd2, &word2);
+ word1 = read_pci_config_16(bus, slot, func, 0xd0);
+ word2 = read_pci_config_16(bus, slot, func, 0xd2);
if (word1 != word2) {
res.start = word1;
res.end = word2;
@@ -92,13 +84,37 @@ static void __devinit cnb20le_res(struct pci_dev *dev)
res.start = fbus;
res.end = lbus;
res.flags = IORESOURCE_BUS;
- dev_info(&dev->dev, "CNB20LE PCI Host Bridge (domain %04x %pR)\n",
- pci_domain_nr(dev->bus), &res);
+ printk(KERN_INFO "CNB20LE PCI Host Bridge (domain 0000 %pR)\n", &res);
for (i = 0; i < info->res_num; i++)
- dev_info(&dev->dev, "host bridge window %pR\n", &info->res[i]);
+ printk(KERN_INFO "host bridge window %pR\n", &info->res[i]);
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_DEVICE_ID_SERVERWORKS_LE,
- cnb20le_res);
+static int __init broadcom_postcore_init(void)
+{
+ u8 bus = 0, slot = 0;
+ u32 id;
+ u16 vendor, device;
+
+#ifdef CONFIG_ACPI
+ /*
+ * We should get host bridge information from ACPI unless the BIOS
+ * doesn't support it.
+ */
+ if (acpi_os_get_root_pointer())
+ return 0;
+#endif
+
+ id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID);
+ vendor = id & 0xffff;
+ device = (id >> 16) & 0xffff;
+
+ if (vendor == PCI_VENDOR_ID_SERVERWORKS &&
+ device == PCI_DEVICE_ID_SERVERWORKS_LE) {
+ cnb20le_res(bus, slot, 0);
+ cnb20le_res(bus, slot, 1);
+ }
+ return 0;
+}
+postcore_initcall(broadcom_postcore_init);
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 64a122883896..fd3f65510e9d 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -7,45 +7,50 @@
int pci_root_num;
struct pci_root_info pci_root_info[PCI_ROOT_NR];
-void x86_pci_root_bus_res_quirks(struct pci_bus *b)
+void x86_pci_root_bus_resources(int bus, struct list_head *resources)
{
int i;
int j;
struct pci_root_info *info;
- /* don't go for it if _CRS is used already */
- if (b->resource[0] != &ioport_resource ||
- b->resource[1] != &iomem_resource)
- return;
-
if (!pci_root_num)
- return;
+ goto default_resources;
for (i = 0; i < pci_root_num; i++) {
- if (pci_root_info[i].bus_min == b->number)
+ if (pci_root_info[i].bus_min == bus)
break;
}
if (i == pci_root_num)
- return;
+ goto default_resources;
- printk(KERN_DEBUG "PCI: peer root bus %02x res updated from pci conf\n",
- b->number);
+ printk(KERN_DEBUG "PCI: root bus %02x: hardware-probed resources\n",
+ bus);
- pci_bus_remove_resources(b);
info = &pci_root_info[i];
for (j = 0; j < info->res_num; j++) {
struct resource *res;
struct resource *root;
res = &info->res[j];
- pci_bus_add_resource(b, res, 0);
+ pci_add_resource(resources, res);
if (res->flags & IORESOURCE_IO)
root = &ioport_resource;
else
root = &iomem_resource;
insert_resource(root, res);
}
+ return;
+
+default_resources:
+ /*
+ * We don't have any host bridge aperture information from the
+ * "native host bridge drivers," e.g., amd_bus or broadcom_bus,
+ * so fall back to the defaults historically used by pci_create_bus().
+ */
+ printk(KERN_DEBUG "PCI: root bus %02x: using default resources\n", bus);
+ pci_add_resource(resources, &ioport_resource);
+ pci_add_resource(resources, &iomem_resource);
}
void __devinit update_res(struct pci_root_info *info, resource_size_t start,
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 7962ccb4d9b2..323481e06ef8 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -164,9 +164,6 @@ void __devinit pcibios_fixup_bus(struct pci_bus *b)
{
struct pci_dev *dev;
- /* root bus? */
- if (!b->parent)
- x86_pci_root_bus_res_quirks(b);
pci_read_bridge_bases(b);
list_for_each_entry(dev, &b->devices, bus_list)
pcibios_fixup_device_resources(dev);
@@ -433,6 +430,7 @@ void __init dmi_check_pciprobe(void)
struct pci_bus * __devinit pcibios_scan_root(int busnum)
{
+ LIST_HEAD(resources);
struct pci_bus *bus = NULL;
struct pci_sysdata *sd;
@@ -456,9 +454,12 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
sd->node = get_mp_bus_to_node(busnum);
printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum);
- bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
- if (!bus)
+ x86_pci_root_bus_resources(busnum, &resources);
+ bus = pci_scan_root_bus(NULL, busnum, &pci_root_ops, sd, &resources);
+ if (!bus) {
+ pci_free_resource_list(&resources);
kfree(sd);
+ }
return bus;
}
@@ -639,6 +640,7 @@ int pci_ext_cfg_avail(struct pci_dev *dev)
struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node)
{
+ LIST_HEAD(resources);
struct pci_bus *bus = NULL;
struct pci_sysdata *sd;
@@ -653,9 +655,12 @@ struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops,
return NULL;
}
sd->node = node;
- bus = pci_scan_bus(busno, ops, sd);
- if (!bus)
+ x86_pci_root_bus_resources(busno, &resources);
+ bus = pci_scan_root_bus(NULL, busno, ops, sd, &resources);
+ if (!bus) {
+ pci_free_resource_list(&resources);
kfree(sd);
+ }
return bus;
}
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 794b092d01ae..91821a1a0c3a 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -254,26 +254,6 @@ void __init pcibios_resource_survey(void)
*/
fs_initcall(pcibios_assign_resources);
-/*
- * If we set up a device for bus mastering, we need to check the latency
- * timer as certain crappy BIOSes forget to set it properly.
- */
-unsigned int pcibios_max_latency = 255;
-
-void pcibios_set_master(struct pci_dev *dev)
-{
- u8 lat;
- pci_read_config_byte(dev, PCI_LATENCY_TIMER, &lat);
- if (lat < 16)
- lat = (64 <= pcibios_max_latency) ? 64 : pcibios_max_latency;
- else if (lat > pcibios_max_latency)
- lat = pcibios_max_latency;
- else
- return;
- dev_printk(KERN_DEBUG, &dev->dev, "setting latency timer to %d\n", lat);
- pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
-}
-
static const struct vm_operations_struct pci_mmap_ops = {
.access = generic_access_phys,
};
diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c
index 2c2aeabc2609..a1df191129d3 100644
--- a/arch/x86/pci/legacy.c
+++ b/arch/x86/pci/legacy.c
@@ -31,9 +31,6 @@ int __init pci_legacy_init(void)
printk("PCI: Probing PCI hardware\n");
pci_root_bus = pcibios_scan_root(0);
- if (pci_root_bus)
- pci_bus_add_devices(pci_root_bus);
-
return 0;
}
diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c
index 51abf02f9226..83e125b95ca6 100644
--- a/arch/x86/pci/numaq_32.c
+++ b/arch/x86/pci/numaq_32.c
@@ -153,8 +153,6 @@ int __init pci_numaq_init(void)
raw_pci_ops = &pci_direct_conf1_mq;
pci_root_bus = pcibios_scan_root(0);
- if (pci_root_bus)
- pci_bus_add_devices(pci_root_bus);
if (num_online_nodes() > 1)
for_each_online_node(quad) {
if (quad == 0)
diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c
index ca1973699d3d..dc5f1d32aced 100644
--- a/arch/x86/platform/geode/alix.c
+++ b/arch/x86/platform/geode/alix.c
@@ -27,7 +27,7 @@
#include <asm/geode.h>
-static int force = 0;
+static bool force = 0;
module_param(force, bool, 0444);
/* FIXME: Award bios is not automatically detected as Alix platform */
MODULE_PARM_DESC(force, "Force detection as ALIX.2/ALIX.3 platform");
diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
index 1ba7f5ed8c9b..5917eb56b313 100644
--- a/arch/x86/platform/iris/iris.c
+++ b/arch/x86/platform/iris/iris.c
@@ -42,7 +42,7 @@ MODULE_AUTHOR("S├ębastien Hinderer <Sebastien.Hinderer@ens-lyon.org>");
MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille");
MODULE_SUPPORTED_DEVICE("Eurobraille/Iris");
-static int force;
+static bool force;
module_param(force, bool, 0);
MODULE_PARM_DESC(force, "Set to one to force poweroff handler installation.");
diff --git a/arch/x86/platform/mrst/Makefile b/arch/x86/platform/mrst/Makefile
index 1ea38775a6d3..7baed5135e0f 100644
--- a/arch/x86/platform/mrst/Makefile
+++ b/arch/x86/platform/mrst/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_X86_MRST) += mrst.o
-obj-$(CONFIG_X86_MRST) += vrtc.o
-obj-$(CONFIG_EARLY_PRINTK_MRST) += early_printk_mrst.o
+obj-$(CONFIG_X86_INTEL_MID) += mrst.o
+obj-$(CONFIG_X86_INTEL_MID) += vrtc.o
+obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_mrst.o
obj-$(CONFIG_X86_MRST) += pmu.o
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index ad4ec1cb097e..475e2cd0f3c3 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -848,8 +848,7 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *entry)
if (mrst_has_msic())
return;
- /* ID as IRQ is a hack that will go away */
- pdev = platform_device_alloc(entry->name, entry->irq);
+ pdev = platform_device_alloc(entry->name, 0);
if (pdev == NULL) {
pr_err("out of memory for SFI platform device '%s'.\n",
entry->name);
@@ -1030,6 +1029,7 @@ static int __init pb_keys_init(void)
num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
for (i = 0; i < num; i++) {
gb[i].gpio = get_gpio_by_name(gb[i].desc);
+ pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc, gb[i].gpio);
if (gb[i].gpio == -1)
continue;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 5b552198f774..3ae0e61abd23 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -157,13 +157,14 @@ static int __init uvhub_to_first_apicid(int uvhub)
* clear of the Timeout bit (as well) will free the resource. No reply will
* be sent (the hardware will only do one reply per message).
*/
-static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp)
+static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp,
+ int do_acknowledge)
{
unsigned long dw;
struct bau_pq_entry *msg;
msg = mdp->msg;
- if (!msg->canceled) {
+ if (!msg->canceled && do_acknowledge) {
dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
write_mmr_sw_ack(dw);
}
@@ -212,8 +213,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
unsigned long mr;
/*
- * is the resource timed out?
- * make everyone ignore the cancelled message.
+ * Is the resource timed out?
+ * Make everyone ignore the cancelled message.
*/
msg2->canceled = 1;
stat->d_canceled++;
@@ -231,8 +232,8 @@ static void bau_process_retry_msg(struct msg_desc *mdp,
* Do all the things a cpu should do for a TLB shootdown message.
* Other cpu's may come here at the same time for this message.
*/
-static void bau_process_message(struct msg_desc *mdp,
- struct bau_control *bcp)
+static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp,
+ int do_acknowledge)
{
short socket_ack_count = 0;
short *sp;
@@ -284,8 +285,9 @@ static void bau_process_message(struct msg_desc *mdp,
if (msg_ack_count == bcp->cpus_in_uvhub) {
/*
* All cpus in uvhub saw it; reply
+ * (unless we are in the UV2 workaround)
*/
- reply_to_message(mdp, bcp);
+ reply_to_message(mdp, bcp, do_acknowledge);
}
}
@@ -491,27 +493,138 @@ static int uv1_wait_completion(struct bau_desc *bau_desc,
/*
* UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
*/
-static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu)
+static unsigned long uv2_read_status(unsigned long offset, int rshft, int desc)
{
unsigned long descriptor_status;
unsigned long descriptor_status2;
descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
- descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL;
+ descriptor_status2 = (read_mmr_uv2_status() >> desc) & 0x1UL;
descriptor_status = (descriptor_status << 1) | descriptor_status2;
return descriptor_status;
}
+/*
+ * Return whether the status of the descriptor that is normally used for this
+ * cpu (the one indexed by its hub-relative cpu number) is busy.
+ * The status of the original 32 descriptors is always reflected in the 64
+ * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0.
+ * The bit provided by the activation_status_2 register is irrelevant to
+ * the status if it is only being tested for busy or not busy.
+ */
+int normal_busy(struct bau_control *bcp)
+{
+ int cpu = bcp->uvhub_cpu;
+ int mmr_offset;
+ int right_shift;
+
+ mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+ right_shift = cpu * UV_ACT_STATUS_SIZE;
+ return (((((read_lmmr(mmr_offset) >> right_shift) &
+ UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY);
+}
+
+/*
+ * Entered when a bau descriptor has gone into a permanent busy wait because
+ * of a hardware bug.
+ * Workaround the bug.
+ */
+int handle_uv2_busy(struct bau_control *bcp)
+{
+ int busy_one = bcp->using_desc;
+ int normal = bcp->uvhub_cpu;
+ int selected = -1;
+ int i;
+ unsigned long descriptor_status;
+ unsigned long status;
+ int mmr_offset;
+ struct bau_desc *bau_desc_old;
+ struct bau_desc *bau_desc_new;
+ struct bau_control *hmaster = bcp->uvhub_master;
+ struct ptc_stats *stat = bcp->statp;
+ cycles_t ttm;
+
+ stat->s_uv2_wars++;
+ spin_lock(&hmaster->uvhub_lock);
+ /* try for the original first */
+ if (busy_one != normal) {
+ if (!normal_busy(bcp))
+ selected = normal;
+ }
+ if (selected < 0) {
+ /* can't use the normal, select an alternate */
+ mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+ descriptor_status = read_lmmr(mmr_offset);
+
+ /* scan available descriptors 32-63 */
+ for (i = 0; i < UV_CPUS_PER_AS; i++) {
+ if ((hmaster->inuse_map & (1 << i)) == 0) {
+ status = ((descriptor_status >>
+ (i * UV_ACT_STATUS_SIZE)) &
+ UV_ACT_STATUS_MASK) << 1;
+ if (status != UV2H_DESC_BUSY) {
+ selected = i + UV_CPUS_PER_AS;
+ break;
+ }
+ }
+ }
+ }
+
+ if (busy_one != normal)
+ /* mark the busy alternate as not in-use */
+ hmaster->inuse_map &= ~(1 << (busy_one - UV_CPUS_PER_AS));
+
+ if (selected >= 0) {
+ /* switch to the selected descriptor */
+ if (selected != normal) {
+ /* set the selected alternate as in-use */
+ hmaster->inuse_map |=
+ (1 << (selected - UV_CPUS_PER_AS));
+ if (selected > stat->s_uv2_wars_hw)
+ stat->s_uv2_wars_hw = selected;
+ }
+ bau_desc_old = bcp->descriptor_base;
+ bau_desc_old += (ITEMS_PER_DESC * busy_one);
+ bcp->using_desc = selected;
+ bau_desc_new = bcp->descriptor_base;
+ bau_desc_new += (ITEMS_PER_DESC * selected);
+ *bau_desc_new = *bau_desc_old;
+ } else {
+ /*
+ * All are busy. Wait for the normal one for this cpu to
+ * free up.
+ */
+ stat->s_uv2_war_waits++;
+ spin_unlock(&hmaster->uvhub_lock);
+ ttm = get_cycles();
+ do {
+ cpu_relax();
+ } while (normal_busy(bcp));
+ spin_lock(&hmaster->uvhub_lock);
+ /* switch to the original descriptor */
+ bcp->using_desc = normal;
+ bau_desc_old = bcp->descriptor_base;
+ bau_desc_old += (ITEMS_PER_DESC * bcp->using_desc);
+ bcp->using_desc = (ITEMS_PER_DESC * normal);
+ bau_desc_new = bcp->descriptor_base;
+ bau_desc_new += (ITEMS_PER_DESC * normal);
+ *bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
+ }
+ spin_unlock(&hmaster->uvhub_lock);
+ return FLUSH_RETRY_BUSYBUG;
+}
+
static int uv2_wait_completion(struct bau_desc *bau_desc,
unsigned long mmr_offset, int right_shift,
struct bau_control *bcp, long try)
{
unsigned long descriptor_stat;
cycles_t ttm;
- int cpu = bcp->uvhub_cpu;
+ int desc = bcp->using_desc;
+ long busy_reps = 0;
struct ptc_stats *stat = bcp->statp;
- descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+ descriptor_stat = uv2_read_status(mmr_offset, right_shift, desc);
/* spin on the status MMR, waiting for it to go idle */
while (descriptor_stat != UV2H_DESC_IDLE) {
@@ -522,32 +635,35 @@ static int uv2_wait_completion(struct bau_desc *bau_desc,
* our message and its state will stay IDLE.
*/
if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) ||
- (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) ||
(descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) {
stat->s_stimeout++;
return FLUSH_GIVEUP;
+ } else if (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) {
+ stat->s_strongnacks++;
+ bcp->conseccompletes = 0;
+ return FLUSH_GIVEUP;
} else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) {
stat->s_dtimeout++;
- ttm = get_cycles();
- /*
- * Our retries may be blocked by all destination
- * swack resources being consumed, and a timeout
- * pending. In that case hardware returns the
- * ERROR that looks like a destination timeout.
- */
- if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
- bcp->conseccompletes = 0;
- return FLUSH_RETRY_PLUGGED;
- }
bcp->conseccompletes = 0;
return FLUSH_RETRY_TIMEOUT;
} else {
+ busy_reps++;
+ if (busy_reps > 1000000) {
+ /* not to hammer on the clock */
+ busy_reps = 0;
+ ttm = get_cycles();
+ if ((ttm - bcp->send_message) >
+ (bcp->clocks_per_100_usec)) {
+ return handle_uv2_busy(bcp);
+ }
+ }
/*
* descriptor_stat is still BUSY
*/
cpu_relax();
}
- descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+ descriptor_stat = uv2_read_status(mmr_offset, right_shift,
+ desc);
}
bcp->conseccompletes++;
return FLUSH_COMPLETE;
@@ -563,17 +679,17 @@ static int wait_completion(struct bau_desc *bau_desc,
{
int right_shift;
unsigned long mmr_offset;
- int cpu = bcp->uvhub_cpu;
+ int desc = bcp->using_desc;
- if (cpu < UV_CPUS_PER_AS) {
+ if (desc < UV_CPUS_PER_AS) {
mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
- right_shift = cpu * UV_ACT_STATUS_SIZE;
+ right_shift = desc * UV_ACT_STATUS_SIZE;
} else {
mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
- right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
+ right_shift = ((desc - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
}
- if (is_uv1_hub())
+ if (bcp->uvhub_version == 1)
return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
bcp, try);
else
@@ -752,19 +868,22 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc,
* Returns 1 if it gives up entirely and the original cpu mask is to be
* returned to the kernel.
*/
-int uv_flush_send_and_wait(struct bau_desc *bau_desc,
- struct cpumask *flush_mask, struct bau_control *bcp)
+int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp)
{
int seq_number = 0;
int completion_stat = 0;
+ int uv1 = 0;
long try = 0;
unsigned long index;
cycles_t time1;
cycles_t time2;
struct ptc_stats *stat = bcp->statp;
struct bau_control *hmaster = bcp->uvhub_master;
+ struct uv1_bau_msg_header *uv1_hdr = NULL;
+ struct uv2_bau_msg_header *uv2_hdr = NULL;
+ struct bau_desc *bau_desc;
- if (is_uv1_hub())
+ if (bcp->uvhub_version == 1)
uv1_throttle(hmaster, stat);
while (hmaster->uvhub_quiesce)
@@ -772,22 +891,39 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
time1 = get_cycles();
do {
- if (try == 0) {
- bau_desc->header.msg_type = MSG_REGULAR;
+ bau_desc = bcp->descriptor_base;
+ bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
+ if (bcp->uvhub_version == 1) {
+ uv1 = 1;
+ uv1_hdr = &bau_desc->header.uv1_hdr;
+ } else
+ uv2_hdr = &bau_desc->header.uv2_hdr;
+ if ((try == 0) || (completion_stat == FLUSH_RETRY_BUSYBUG)) {
+ if (uv1)
+ uv1_hdr->msg_type = MSG_REGULAR;
+ else
+ uv2_hdr->msg_type = MSG_REGULAR;
seq_number = bcp->message_number++;
} else {
- bau_desc->header.msg_type = MSG_RETRY;
+ if (uv1)
+ uv1_hdr->msg_type = MSG_RETRY;
+ else
+ uv2_hdr->msg_type = MSG_RETRY;
stat->s_retry_messages++;
}
- bau_desc->header.sequence = seq_number;
- index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
+ if (uv1)
+ uv1_hdr->sequence = seq_number;
+ else
+ uv2_hdr->sequence = seq_number;
+ index = (1UL << AS_PUSH_SHIFT) | bcp->using_desc;
bcp->send_message = get_cycles();
write_mmr_activation(index);
try++;
completion_stat = wait_completion(bau_desc, bcp, try);
+ /* UV2: wait_completion() may change the bcp->using_desc */
handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
@@ -798,6 +934,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
}
cpu_relax();
} while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
+ (completion_stat == FLUSH_RETRY_BUSYBUG) ||
(completion_stat == FLUSH_RETRY_TIMEOUT));
time2 = get_cycles();
@@ -812,6 +949,7 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
record_send_stats(time1, time2, bcp, stat, completion_stat, try);
if (completion_stat == FLUSH_GIVEUP)
+ /* FLUSH_GIVEUP will fall back to using IPI's for tlb flush */
return 1;
return 0;
}
@@ -967,7 +1105,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
stat->s_ntargself++;
bau_desc = bcp->descriptor_base;
- bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu;
+ bau_desc += (ITEMS_PER_DESC * bcp->using_desc);
bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
return NULL;
@@ -980,13 +1118,86 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
* uv_flush_send_and_wait returns 0 if all cpu's were messaged,
* or 1 if it gave up and the original cpumask should be returned.
*/
- if (!uv_flush_send_and_wait(bau_desc, flush_mask, bcp))
+ if (!uv_flush_send_and_wait(flush_mask, bcp))
return NULL;
else
return cpumask;
}
/*
+ * Search the message queue for any 'other' message with the same software
+ * acknowledge resource bit vector.
+ */
+struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg,
+ struct bau_control *bcp, unsigned char swack_vec)
+{
+ struct bau_pq_entry *msg_next = msg + 1;
+
+ if (msg_next > bcp->queue_last)
+ msg_next = bcp->queue_first;
+ while ((msg_next->swack_vec != 0) && (msg_next != msg)) {
+ if (msg_next->swack_vec == swack_vec)
+ return msg_next;
+ msg_next++;
+ if (msg_next > bcp->queue_last)
+ msg_next = bcp->queue_first;
+ }
+ return NULL;
+}
+
+/*
+ * UV2 needs to work around a bug in which an arriving message has not
+ * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register.
+ * Such a message must be ignored.
+ */
+void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp)
+{
+ unsigned long mmr_image;
+ unsigned char swack_vec;
+ struct bau_pq_entry *msg = mdp->msg;
+ struct bau_pq_entry *other_msg;
+
+ mmr_image = read_mmr_sw_ack();
+ swack_vec = msg->swack_vec;
+
+ if ((swack_vec & mmr_image) == 0) {
+ /*
+ * This message was assigned a swack resource, but no
+ * reserved acknowlegment is pending.
+ * The bug has prevented this message from setting the MMR.
+ * And no other message has used the same sw_ack resource.
+ * Do the requested shootdown but do not reply to the msg.
+ * (the 0 means make no acknowledge)
+ */
+ bau_process_message(mdp, bcp, 0);
+ return;
+ }
+
+ /*
+ * Some message has set the MMR 'pending' bit; it might have been
+ * another message. Look for that message.
+ */
+ other_msg = find_another_by_swack(msg, bcp, msg->swack_vec);
+ if (other_msg) {
+ /* There is another. Do not ack the current one. */
+ bau_process_message(mdp, bcp, 0);
+ /*
+ * Let the natural processing of that message acknowledge
+ * it. Don't get the processing of sw_ack's out of order.
+ */
+ return;
+ }
+
+ /*
+ * There is no other message using this sw_ack, so it is safe to
+ * acknowledge it.
+ */
+ bau_process_message(mdp, bcp, 1);
+
+ return;
+}
+
+/*
* The BAU message interrupt comes here. (registered by set_intr_gate)
* See entry_64.S
*
@@ -1009,6 +1220,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
struct ptc_stats *stat;
struct msg_desc msgdesc;
+ ack_APIC_irq();
time_start = get_cycles();
bcp = &per_cpu(bau_control, smp_processor_id());
@@ -1022,9 +1234,11 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
count++;
msgdesc.msg_slot = msg - msgdesc.queue_first;
- msgdesc.swack_slot = ffs(msg->swack_vec) - 1;
msgdesc.msg = msg;
- bau_process_message(&msgdesc, bcp);
+ if (bcp->uvhub_version == 2)
+ process_uv2_message(&msgdesc, bcp);
+ else
+ bau_process_message(&msgdesc, bcp, 1);
msg++;
if (msg > msgdesc.queue_last)
@@ -1036,8 +1250,6 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
stat->d_nomsg++;
else if (count > 1)
stat->d_multmsg++;
-
- ack_APIC_irq();
}
/*
@@ -1083,7 +1295,7 @@ static void __init enable_timeouts(void)
*/
mmr_image |= (1L << SOFTACK_MSHIFT);
if (is_uv2_hub()) {
- mmr_image |= (1L << UV2_LEG_SHFT);
+ mmr_image &= ~(1L << UV2_LEG_SHFT);
mmr_image |= (1L << UV2_EXT_SHFT);
}
write_mmr_misc_control(pnode, mmr_image);
@@ -1136,13 +1348,13 @@ static int ptc_seq_show(struct seq_file *file, void *data)
seq_printf(file,
"remotehub numuvhubs numuvhubs16 numuvhubs8 ");
seq_printf(file,
- "numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok ");
+ "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries rok ");
seq_printf(file,
"resetp resett giveup sto bz throt swack recv rtime ");
seq_printf(file,
"all one mult none retry canc nocan reset rcan ");
seq_printf(file,
- "disable enable\n");
+ "disable enable wars warshw warwaits\n");
}
if (cpu < num_possible_cpus() && cpu_online(cpu)) {
stat = &per_cpu(ptcstats, cpu);
@@ -1154,10 +1366,10 @@ static int ptc_seq_show(struct seq_file *file, void *data)
stat->s_ntargremotes, stat->s_ntargcpu,
stat->s_ntarglocaluvhub, stat->s_ntargremoteuvhub,
stat->s_ntarguvhub, stat->s_ntarguvhub16);
- seq_printf(file, "%ld %ld %ld %ld %ld ",
+ seq_printf(file, "%ld %ld %ld %ld %ld %ld ",
stat->s_ntarguvhub8, stat->s_ntarguvhub4,
stat->s_ntarguvhub2, stat->s_ntarguvhub1,
- stat->s_dtimeout);
+ stat->s_dtimeout, stat->s_strongnacks);
seq_printf(file, "%ld %ld %ld %ld %ld %ld %ld %ld ",
stat->s_retry_messages, stat->s_retriesok,
stat->s_resets_plug, stat->s_resets_timeout,
@@ -1173,8 +1385,10 @@ static int ptc_seq_show(struct seq_file *file, void *data)
stat->d_nomsg, stat->d_retries, stat->d_canceled,
stat->d_nocanceled, stat->d_resets,
stat->d_rcanceled);
- seq_printf(file, "%ld %ld\n",
- stat->s_bau_disabled, stat->s_bau_reenabled);
+ seq_printf(file, "%ld %ld %ld %ld %ld\n",
+ stat->s_bau_disabled, stat->s_bau_reenabled,
+ stat->s_uv2_wars, stat->s_uv2_wars_hw,
+ stat->s_uv2_war_waits);
}
return 0;
}
@@ -1432,12 +1646,15 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
{
int i;
int cpu;
+ int uv1 = 0;
unsigned long gpa;
unsigned long m;
unsigned long n;
size_t dsize;
struct bau_desc *bau_desc;
struct bau_desc *bd2;
+ struct uv1_bau_msg_header *uv1_hdr;
+ struct uv2_bau_msg_header *uv2_hdr;
struct bau_control *bcp;
/*
@@ -1451,6 +1668,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
gpa = uv_gpa(bau_desc);
n = uv_gpa_to_gnode(gpa);
m = uv_gpa_to_offset(gpa);
+ if (is_uv1_hub())
+ uv1 = 1;
/* the 14-bit pnode */
write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
@@ -1461,21 +1680,33 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
*/
for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) {
memset(bd2, 0, sizeof(struct bau_desc));
- bd2->header.swack_flag = 1;
- /*
- * The base_dest_nasid set in the message header is the nasid
- * of the first uvhub in the partition. The bit map will
- * indicate destination pnode numbers relative to that base.
- * They may not be consecutive if nasid striding is being used.
- */
- bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode);
- bd2->header.dest_subnodeid = UV_LB_SUBNODEID;
- bd2->header.command = UV_NET_ENDPOINT_INTD;
- bd2->header.int_both = 1;
- /*
- * all others need to be set to zero:
- * fairness chaining multilevel count replied_to
- */
+ if (uv1) {
+ uv1_hdr = &bd2->header.uv1_hdr;
+ uv1_hdr->swack_flag = 1;
+ /*
+ * The base_dest_nasid set in the message header
+ * is the nasid of the first uvhub in the partition.
+ * The bit map will indicate destination pnode numbers
+ * relative to that base. They may not be consecutive
+ * if nasid striding is being used.
+ */
+ uv1_hdr->base_dest_nasid =
+ UV_PNODE_TO_NASID(base_pnode);
+ uv1_hdr->dest_subnodeid = UV_LB_SUBNODEID;
+ uv1_hdr->command = UV_NET_ENDPOINT_INTD;
+ uv1_hdr->int_both = 1;
+ /*
+ * all others need to be set to zero:
+ * fairness chaining multilevel count replied_to
+ */
+ } else {
+ uv2_hdr = &bd2->header.uv2_hdr;
+ uv2_hdr->swack_flag = 1;
+ uv2_hdr->base_dest_nasid =
+ UV_PNODE_TO_NASID(base_pnode);
+ uv2_hdr->dest_subnodeid = UV_LB_SUBNODEID;
+ uv2_hdr->command = UV_NET_ENDPOINT_INTD;
+ }
}
for_each_present_cpu(cpu) {
if (pnode != uv_blade_to_pnode(uv_cpu_to_blade_id(cpu)))
@@ -1531,6 +1762,7 @@ static void pq_init(int node, int pnode)
write_mmr_payload_first(pnode, pn_first);
write_mmr_payload_tail(pnode, first);
write_mmr_payload_last(pnode, last);
+ write_gmmr_sw_ack(pnode, 0xffffUL);
/* in effect, all msg_type's are set to MSG_NOOP */
memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
@@ -1584,14 +1816,14 @@ static int calculate_destination_timeout(void)
ts_ns = base * mult1 * mult2;
ret = ts_ns / 1000;
} else {
- /* 4 bits 0/1 for 10/80us, 3 bits of multiplier */
- mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+ /* 4 bits 0/1 for 10/80us base, 3 bits of multiplier */
+ mmr_image = uv_read_local_mmr(UVH_LB_BAU_MISC_CONTROL);
mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT;
if (mmr_image & (1L << UV2_ACK_UNITS_SHFT))
- mult1 = 80;
+ base = 80;
else
- mult1 = 10;
- base = mmr_image & UV2_ACK_MASK;
+ base = 10;
+ mult1 = mmr_image & UV2_ACK_MASK;
ret = mult1 * base;
}
return ret;
@@ -1618,6 +1850,9 @@ static void __init init_per_cpu_tunables(void)
bcp->cong_response_us = congested_respns_us;
bcp->cong_reps = congested_reps;
bcp->cong_period = congested_period;
+ bcp->clocks_per_100_usec = usec_2_cycles(100);
+ spin_lock_init(&bcp->queue_lock);
+ spin_lock_init(&bcp->uvhub_lock);
}
}
@@ -1728,8 +1963,17 @@ static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
bcp->cpus_in_socket = sdp->num_cpus;
bcp->socket_master = *smasterp;
bcp->uvhub = bdp->uvhub;
+ if (is_uv1_hub())
+ bcp->uvhub_version = 1;
+ else if (is_uv2_hub())
+ bcp->uvhub_version = 2;
+ else {
+ printk(KERN_EMERG "uvhub version not 1 or 2\n");
+ return 1;
+ }
bcp->uvhub_master = *hmasterp;
bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+ bcp->using_desc = bcp->uvhub_cpu;
if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
printk(KERN_EMERG "%d cpus per uvhub invalid\n",
bcp->uvhub_cpu);
@@ -1845,6 +2089,8 @@ static int __init uv_bau_init(void)
uv_base_pnode = uv_blade_to_pnode(uvhub);
}
+ enable_timeouts();
+
if (init_per_cpu(nuvhubs, uv_base_pnode)) {
nobau = 1;
return 0;
@@ -1855,7 +2101,6 @@ static int __init uv_bau_init(void)
if (uv_blade_nr_possible_cpus(uvhub))
init_uvhub(uvhub, vector, uv_base_pnode);
- enable_timeouts();
alloc_intr_gate(vector, uv_bau_message_intr1);
for_each_possible_blade(uvhub) {
@@ -1867,7 +2112,8 @@ static int __init uv_bau_init(void)
val = 1L << 63;
write_gmmr_activation(pnode, val);
mmr = 1; /* should be 1 to broadcast to both sockets */
- write_mmr_data_broadcast(pnode, mmr);
+ if (!is_uv1_hub())
+ write_mmr_data_broadcast(pnode, mmr);
}
}
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 374a05d8ad22..f25c2765a5c9 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -25,7 +25,7 @@ struct uv_irq_2_mmr_pnode{
int irq;
};
-static spinlock_t uv_irq_lock;
+static DEFINE_SPINLOCK(uv_irq_lock);
static struct rb_root uv_irq_root;
static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile
new file mode 100644
index 000000000000..564b2476fede
--- /dev/null
+++ b/arch/x86/syscalls/Makefile
@@ -0,0 +1,43 @@
+out := $(obj)/../include/generated/asm
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+syscall32 := $(srctree)/$(src)/syscall_32.tbl
+syscall64 := $(srctree)/$(src)/syscall_64.tbl
+
+syshdr := $(srctree)/$(src)/syscallhdr.sh
+systbl := $(srctree)/$(src)/syscalltbl.sh
+
+quiet_cmd_syshdr = SYSHDR $@
+ cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' $< $@ \
+ $(syshdr_abi_$(basetarget)) $(syshdr_pfx_$(basetarget))
+quiet_cmd_systbl = SYSTBL $@
+ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
+
+syshdr_abi_unistd_32 := i386
+$(out)/unistd_32.h: $(syscall32) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_32_ia32 := i386
+syshdr_pfx_unistd_32_ia32 := ia32_
+$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_64 := 64
+$(out)/unistd_64.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+$(out)/syscalls_32.h: $(syscall32) $(systbl)
+ $(call if_changed,systbl)
+$(out)/syscalls_64.h: $(syscall64) $(systbl)
+ $(call if_changed,systbl)
+
+syshdr-y += unistd_32.h unistd_64.h
+syshdr-y += syscalls_32.h
+syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h
+syshdr-$(CONFIG_X86_64) += syscalls_64.h
+
+targets += $(syshdr-y)
+
+all: $(addprefix $(out)/,$(targets))
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
new file mode 100644
index 000000000000..ce98e287c066
--- /dev/null
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -0,0 +1,357 @@
+#
+# 32-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The abi is always "i386" for this file.
+#
+0 i386 restart_syscall sys_restart_syscall
+1 i386 exit sys_exit
+2 i386 fork ptregs_fork stub32_fork
+3 i386 read sys_read
+4 i386 write sys_write
+5 i386 open sys_open compat_sys_open
+6 i386 close sys_close
+7 i386 waitpid sys_waitpid sys32_waitpid
+8 i386 creat sys_creat
+9 i386 link sys_link
+10 i386 unlink sys_unlink
+11 i386 execve ptregs_execve stub32_execve
+12 i386 chdir sys_chdir
+13 i386 time sys_time compat_sys_time
+14 i386 mknod sys_mknod
+15 i386 chmod sys_chmod
+16 i386 lchown sys_lchown16
+17 i386 break
+18 i386 oldstat sys_stat
+19 i386 lseek sys_lseek sys32_lseek
+20 i386 getpid sys_getpid
+21 i386 mount sys_mount compat_sys_mount
+22 i386 umount sys_oldumount
+23 i386 setuid sys_setuid16
+24 i386 getuid sys_getuid16
+25 i386 stime sys_stime compat_sys_stime
+26 i386 ptrace sys_ptrace compat_sys_ptrace
+27 i386 alarm sys_alarm
+28 i386 oldfstat sys_fstat
+29 i386 pause sys_pause
+30 i386 utime sys_utime compat_sys_utime
+31 i386 stty
+32 i386 gtty
+33 i386 access sys_access
+34 i386 nice sys_nice
+35 i386 ftime
+36 i386 sync sys_sync
+37 i386 kill sys_kill sys32_kill
+38 i386 rename sys_rename
+39 i386 mkdir sys_mkdir
+40 i386 rmdir sys_rmdir
+41 i386 dup sys_dup
+42 i386 pipe sys_pipe
+43 i386 times sys_times compat_sys_times
+44 i386 prof
+45 i386 brk sys_brk
+46 i386 setgid sys_setgid16
+47 i386 getgid sys_getgid16
+48 i386 signal sys_signal
+49 i386 geteuid sys_geteuid16
+50 i386 getegid sys_getegid16
+51 i386 acct sys_acct
+52 i386 umount2 sys_umount
+53 i386 lock
+54 i386 ioctl sys_ioctl compat_sys_ioctl
+55 i386 fcntl sys_fcntl compat_sys_fcntl64
+56 i386 mpx
+57 i386 setpgid sys_setpgid
+58 i386 ulimit
+59 i386 oldolduname sys_olduname
+60 i386 umask sys_umask
+61 i386 chroot sys_chroot
+62 i386 ustat sys_ustat compat_sys_ustat
+63 i386 dup2 sys_dup2
+64 i386 getppid sys_getppid
+65 i386 getpgrp sys_getpgrp
+66 i386 setsid sys_setsid
+67 i386 sigaction sys_sigaction sys32_sigaction
+68 i386 sgetmask sys_sgetmask
+69 i386 ssetmask sys_ssetmask
+70 i386 setreuid sys_setreuid16
+71 i386 setregid sys_setregid16
+72 i386 sigsuspend sys_sigsuspend sys32_sigsuspend
+73 i386 sigpending sys_sigpending compat_sys_sigpending
+74 i386 sethostname sys_sethostname
+75 i386 setrlimit sys_setrlimit compat_sys_setrlimit
+76 i386 getrlimit sys_old_getrlimit compat_sys_old_getrlimit
+77 i386 getrusage sys_getrusage compat_sys_getrusage
+78 i386 gettimeofday sys_gettimeofday compat_sys_gettimeofday
+79 i386 settimeofday sys_settimeofday compat_sys_settimeofday
+80 i386 getgroups sys_getgroups16
+81 i386 setgroups sys_setgroups16
+82 i386 select sys_old_select compat_sys_old_select
+83 i386 symlink sys_symlink
+84 i386 oldlstat sys_lstat
+85 i386 readlink sys_readlink
+86 i386 uselib sys_uselib
+87 i386 swapon sys_swapon
+88 i386 reboot sys_reboot
+89 i386 readdir sys_old_readdir compat_sys_old_readdir
+90 i386 mmap sys_old_mmap sys32_mmap
+91 i386 munmap sys_munmap
+92 i386 truncate sys_truncate
+93 i386 ftruncate sys_ftruncate
+94 i386 fchmod sys_fchmod
+95 i386 fchown sys_fchown16
+96 i386 getpriority sys_getpriority
+97 i386 setpriority sys_setpriority
+98 i386 profil
+99 i386 statfs sys_statfs compat_sys_statfs
+100 i386 fstatfs sys_fstatfs compat_sys_fstatfs
+101 i386 ioperm sys_ioperm
+102 i386 socketcall sys_socketcall compat_sys_socketcall
+103 i386 syslog sys_syslog
+104 i386 setitimer sys_setitimer compat_sys_setitimer
+105 i386 getitimer sys_getitimer compat_sys_getitimer
+106 i386 stat sys_newstat compat_sys_newstat
+107 i386 lstat sys_newlstat compat_sys_newlstat
+108 i386 fstat sys_newfstat compat_sys_newfstat
+109 i386 olduname sys_uname
+110 i386 iopl ptregs_iopl stub32_iopl
+111 i386 vhangup sys_vhangup
+112 i386 idle
+113 i386 vm86old ptregs_vm86old sys32_vm86_warning
+114 i386 wait4 sys_wait4 compat_sys_wait4
+115 i386 swapoff sys_swapoff
+116 i386 sysinfo sys_sysinfo compat_sys_sysinfo
+117 i386 ipc sys_ipc sys32_ipc
+118 i386 fsync sys_fsync
+119 i386 sigreturn ptregs_sigreturn stub32_sigreturn
+120 i386 clone ptregs_clone stub32_clone
+121 i386 setdomainname sys_setdomainname
+122 i386 uname sys_newuname
+123 i386 modify_ldt sys_modify_ldt
+124 i386 adjtimex sys_adjtimex compat_sys_adjtimex
+125 i386 mprotect sys_mprotect sys32_mprotect
+126 i386 sigprocmask sys_sigprocmask compat_sys_sigprocmask
+127 i386 create_module
+128 i386 init_module sys_init_module
+129 i386 delete_module sys_delete_module
+130 i386 get_kernel_syms
+131 i386 quotactl sys_quotactl sys32_quotactl
+132 i386 getpgid sys_getpgid
+133 i386 fchdir sys_fchdir
+134 i386 bdflush sys_bdflush
+135 i386 sysfs sys_sysfs
+136 i386 personality sys_personality
+137 i386 afs_syscall
+138 i386 setfsuid sys_setfsuid16
+139 i386 setfsgid sys_setfsgid16
+140 i386 _llseek sys_llseek
+141 i386 getdents sys_getdents compat_sys_getdents
+142 i386 _newselect sys_select compat_sys_select
+143 i386 flock sys_flock
+144 i386 msync sys_msync
+145 i386 readv sys_readv compat_sys_readv
+146 i386 writev sys_writev compat_sys_writev
+147 i386 getsid sys_getsid
+148 i386 fdatasync sys_fdatasync
+149 i386 _sysctl sys_sysctl compat_sys_sysctl
+150 i386 mlock sys_mlock
+151 i386 munlock sys_munlock
+152 i386 mlockall sys_mlockall
+153 i386 munlockall sys_munlockall
+154 i386 sched_setparam sys_sched_setparam
+155 i386 sched_getparam sys_sched_getparam
+156 i386 sched_setscheduler sys_sched_setscheduler
+157 i386 sched_getscheduler sys_sched_getscheduler
+158 i386 sched_yield sys_sched_yield
+159 i386 sched_get_priority_max sys_sched_get_priority_max
+160 i386 sched_get_priority_min sys_sched_get_priority_min
+161 i386 sched_rr_get_interval sys_sched_rr_get_interval sys32_sched_rr_get_interval
+162 i386 nanosleep sys_nanosleep compat_sys_nanosleep
+163 i386 mremap sys_mremap
+164 i386 setresuid sys_setresuid16
+165 i386 getresuid sys_getresuid16
+166 i386 vm86 ptregs_vm86 sys32_vm86_warning
+167 i386 query_module
+168 i386 poll sys_poll
+169 i386 nfsservctl
+170 i386 setresgid sys_setresgid16
+171 i386 getresgid sys_getresgid16
+172 i386 prctl sys_prctl
+173 i386 rt_sigreturn ptregs_rt_sigreturn stub32_rt_sigreturn
+174 i386 rt_sigaction sys_rt_sigaction sys32_rt_sigaction
+175 i386 rt_sigprocmask sys_rt_sigprocmask sys32_rt_sigprocmask
+176 i386 rt_sigpending sys_rt_sigpending sys32_rt_sigpending
+177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
+178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo sys32_rt_sigqueueinfo
+179 i386 rt_sigsuspend sys_rt_sigsuspend
+180 i386 pread64 sys_pread64 sys32_pread
+181 i386 pwrite64 sys_pwrite64 sys32_pwrite
+182 i386 chown sys_chown16
+183 i386 getcwd sys_getcwd
+184 i386 capget sys_capget
+185 i386 capset sys_capset
+186 i386 sigaltstack ptregs_sigaltstack stub32_sigaltstack
+187 i386 sendfile sys_sendfile sys32_sendfile
+188 i386 getpmsg
+189 i386 putpmsg
+190 i386 vfork ptregs_vfork stub32_vfork
+191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit
+192 i386 mmap2 sys_mmap_pgoff
+193 i386 truncate64 sys_truncate64 sys32_truncate64
+194 i386 ftruncate64 sys_ftruncate64 sys32_ftruncate64
+195 i386 stat64 sys_stat64 sys32_stat64
+196 i386 lstat64 sys_lstat64 sys32_lstat64
+197 i386 fstat64 sys_fstat64 sys32_fstat64
+198 i386 lchown32 sys_lchown
+199 i386 getuid32 sys_getuid
+200 i386 getgid32 sys_getgid
+201 i386 geteuid32 sys_geteuid
+202 i386 getegid32 sys_getegid
+203 i386 setreuid32 sys_setreuid
+204 i386 setregid32 sys_setregid
+205 i386 getgroups32 sys_getgroups
+206 i386 setgroups32 sys_setgroups
+207 i386 fchown32 sys_fchown
+208 i386 setresuid32 sys_setresuid
+209 i386 getresuid32 sys_getresuid
+210 i386 setresgid32 sys_setresgid
+211 i386 getresgid32 sys_getresgid
+212 i386 chown32 sys_chown
+213 i386 setuid32 sys_setuid
+214 i386 setgid32 sys_setgid
+215 i386 setfsuid32 sys_setfsuid
+216 i386 setfsgid32 sys_setfsgid
+217 i386 pivot_root sys_pivot_root
+218 i386 mincore sys_mincore
+219 i386 madvise sys_madvise
+220 i386 getdents64 sys_getdents64 compat_sys_getdents64
+221 i386 fcntl64 sys_fcntl64 compat_sys_fcntl64
+# 222 is unused
+# 223 is unused
+224 i386 gettid sys_gettid
+225 i386 readahead sys_readahead sys32_readahead
+226 i386 setxattr sys_setxattr
+227 i386 lsetxattr sys_lsetxattr
+228 i386 fsetxattr sys_fsetxattr
+229 i386 getxattr sys_getxattr
+230 i386 lgetxattr sys_lgetxattr
+231 i386 fgetxattr sys_fgetxattr
+232 i386 listxattr sys_listxattr
+233 i386 llistxattr sys_llistxattr
+234 i386 flistxattr sys_flistxattr
+235 i386 removexattr sys_removexattr
+236 i386 lremovexattr sys_lremovexattr
+237 i386 fremovexattr sys_fremovexattr
+238 i386 tkill sys_tkill
+239 i386 sendfile64 sys_sendfile64
+240 i386 futex sys_futex compat_sys_futex
+241 i386 sched_setaffinity sys_sched_setaffinity compat_sys_sched_setaffinity
+242 i386 sched_getaffinity sys_sched_getaffinity compat_sys_sched_getaffinity
+243 i386 set_thread_area sys_set_thread_area
+244 i386 get_thread_area sys_get_thread_area
+245 i386 io_setup sys_io_setup compat_sys_io_setup
+246 i386 io_destroy sys_io_destroy
+247 i386 io_getevents sys_io_getevents compat_sys_io_getevents
+248 i386 io_submit sys_io_submit compat_sys_io_submit
+249 i386 io_cancel sys_io_cancel
+250 i386 fadvise64 sys_fadvise64 sys32_fadvise64
+# 251 is available for reuse (was briefly sys_set_zone_reclaim)
+252 i386 exit_group sys_exit_group
+253 i386 lookup_dcookie sys_lookup_dcookie sys32_lookup_dcookie
+254 i386 epoll_create sys_epoll_create
+255 i386 epoll_ctl sys_epoll_ctl
+256 i386 epoll_wait sys_epoll_wait
+257 i386 remap_file_pages sys_remap_file_pages
+258 i386 set_tid_address sys_set_tid_address
+259 i386 timer_create sys_timer_create compat_sys_timer_create
+260 i386 timer_settime sys_timer_settime compat_sys_timer_settime
+261 i386 timer_gettime sys_timer_gettime compat_sys_timer_gettime
+262 i386 timer_getoverrun sys_timer_getoverrun
+263 i386 timer_delete sys_timer_delete
+264 i386 clock_settime sys_clock_settime compat_sys_clock_settime
+265 i386 clock_gettime sys_clock_gettime compat_sys_clock_gettime
+266 i386 clock_getres sys_clock_getres compat_sys_clock_getres
+267 i386 clock_nanosleep sys_clock_nanosleep compat_sys_clock_nanosleep
+268 i386 statfs64 sys_statfs64 compat_sys_statfs64
+269 i386 fstatfs64 sys_fstatfs64 compat_sys_fstatfs64
+270 i386 tgkill sys_tgkill
+271 i386 utimes sys_utimes compat_sys_utimes
+272 i386 fadvise64_64 sys_fadvise64_64 sys32_fadvise64_64
+273 i386 vserver
+274 i386 mbind sys_mbind
+275 i386 get_mempolicy sys_get_mempolicy compat_sys_get_mempolicy
+276 i386 set_mempolicy sys_set_mempolicy
+277 i386 mq_open sys_mq_open compat_sys_mq_open
+278 i386 mq_unlink sys_mq_unlink
+279 i386 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend
+280 i386 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive
+281 i386 mq_notify sys_mq_notify compat_sys_mq_notify
+282 i386 mq_getsetaddr sys_mq_getsetattr compat_sys_mq_getsetattr
+283 i386 kexec_load sys_kexec_load compat_sys_kexec_load
+284 i386 waitid sys_waitid compat_sys_waitid
+# 285 sys_setaltroot
+286 i386 add_key sys_add_key
+287 i386 request_key sys_request_key
+288 i386 keyctl sys_keyctl
+289 i386 ioprio_set sys_ioprio_set
+290 i386 ioprio_get sys_ioprio_get
+291 i386 inotify_init sys_inotify_init
+292 i386 inotify_add_watch sys_inotify_add_watch
+293 i386 inotify_rm_watch sys_inotify_rm_watch
+294 i386 migrate_pages sys_migrate_pages
+295 i386 openat sys_openat compat_sys_openat
+296 i386 mkdirat sys_mkdirat
+297 i386 mknodat sys_mknodat
+298 i386 fchownat sys_fchownat
+299 i386 futimesat sys_futimesat compat_sys_futimesat
+300 i386 fstatat64 sys_fstatat64 sys32_fstatat
+301 i386 unlinkat sys_unlinkat
+302 i386 renameat sys_renameat
+303 i386 linkat sys_linkat
+304 i386 symlinkat sys_symlinkat
+305 i386 readlinkat sys_readlinkat
+306 i386 fchmodat sys_fchmodat
+307 i386 faccessat sys_faccessat
+308 i386 pselect6 sys_pselect6 compat_sys_pselect6
+309 i386 ppoll sys_ppoll compat_sys_ppoll
+310 i386 unshare sys_unshare
+311 i386 set_robust_list sys_set_robust_list compat_sys_set_robust_list
+312 i386 get_robust_list sys_get_robust_list compat_sys_get_robust_list
+313 i386 splice sys_splice
+314 i386 sync_file_range sys_sync_file_range sys32_sync_file_range
+315 i386 tee sys_tee
+316 i386 vmsplice sys_vmsplice compat_sys_vmsplice
+317 i386 move_pages sys_move_pages compat_sys_move_pages
+318 i386 getcpu sys_getcpu
+319 i386 epoll_pwait sys_epoll_pwait
+320 i386 utimensat sys_utimensat compat_sys_utimensat
+321 i386 signalfd sys_signalfd compat_sys_signalfd
+322 i386 timerfd_create sys_timerfd_create
+323 i386 eventfd sys_eventfd
+324 i386 fallocate sys_fallocate sys32_fallocate
+325 i386 timerfd_settime sys_timerfd_settime compat_sys_timerfd_settime
+326 i386 timerfd_gettime sys_timerfd_gettime compat_sys_timerfd_gettime
+327 i386 signalfd4 sys_signalfd4 compat_sys_signalfd4
+328 i386 eventfd2 sys_eventfd2
+329 i386 epoll_create1 sys_epoll_create1
+330 i386 dup3 sys_dup3
+331 i386 pipe2 sys_pipe2
+332 i386 inotify_init1 sys_inotify_init1
+333 i386 preadv sys_preadv compat_sys_preadv
+334 i386 pwritev sys_pwritev compat_sys_pwritev
+335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo compat_sys_rt_tgsigqueueinfo
+336 i386 perf_event_open sys_perf_event_open
+337 i386 recvmmsg sys_recvmmsg compat_sys_recvmmsg
+338 i386 fanotify_init sys_fanotify_init
+339 i386 fanotify_mark sys_fanotify_mark sys32_fanotify_mark
+340 i386 prlimit64 sys_prlimit64
+341 i386 name_to_handle_at sys_name_to_handle_at
+342 i386 open_by_handle_at sys_open_by_handle_at compat_sys_open_by_handle_at
+343 i386 clock_adjtime sys_clock_adjtime compat_sys_clock_adjtime
+344 i386 syncfs sys_syncfs
+345 i386 sendmmsg sys_sendmmsg compat_sys_sendmmsg
+346 i386 setns sys_setns
+347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv
+348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
new file mode 100644
index 000000000000..b440a8f7eefa
--- /dev/null
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -0,0 +1,320 @@
+#
+# 64-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point>
+#
+# The abi is always "64" for this file (for now.)
+#
+0 64 read sys_read
+1 64 write sys_write
+2 64 open sys_open
+3 64 close sys_close
+4 64 stat sys_newstat
+5 64 fstat sys_newfstat
+6 64 lstat sys_newlstat
+7 64 poll sys_poll
+8 64 lseek sys_lseek
+9 64 mmap sys_mmap
+10 64 mprotect sys_mprotect
+11 64 munmap sys_munmap
+12 64 brk sys_brk
+13 64 rt_sigaction sys_rt_sigaction
+14 64 rt_sigprocmask sys_rt_sigprocmask
+15 64 rt_sigreturn stub_rt_sigreturn
+16 64 ioctl sys_ioctl
+17 64 pread64 sys_pread64
+18 64 pwrite64 sys_pwrite64
+19 64 readv sys_readv
+20 64 writev sys_writev
+21 64 access sys_access
+22 64 pipe sys_pipe
+23 64 select sys_select
+24 64 sched_yield sys_sched_yield
+25 64 mremap sys_mremap
+26 64 msync sys_msync
+27 64 mincore sys_mincore
+28 64 madvise sys_madvise
+29 64 shmget sys_shmget
+30 64 shmat sys_shmat
+31 64 shmctl sys_shmctl
+32 64 dup sys_dup
+33 64 dup2 sys_dup2
+34 64 pause sys_pause
+35 64 nanosleep sys_nanosleep
+36 64 getitimer sys_getitimer
+37 64 alarm sys_alarm
+38 64 setitimer sys_setitimer
+39 64 getpid sys_getpid
+40 64 sendfile sys_sendfile64
+41 64 socket sys_socket
+42 64 connect sys_connect
+43 64 accept sys_accept
+44 64 sendto sys_sendto
+45 64 recvfrom sys_recvfrom
+46 64 sendmsg sys_sendmsg
+47 64 recvmsg sys_recvmsg
+48 64 shutdown sys_shutdown
+49 64 bind sys_bind
+50 64 listen sys_listen
+51 64 getsockname sys_getsockname
+52 64 getpeername sys_getpeername
+53 64 socketpair sys_socketpair
+54 64 setsockopt sys_setsockopt
+55 64 getsockopt sys_getsockopt
+56 64 clone stub_clone
+57 64 fork stub_fork
+58 64 vfork stub_vfork
+59 64 execve stub_execve
+60 64 exit sys_exit
+61 64 wait4 sys_wait4
+62 64 kill sys_kill
+63 64 uname sys_newuname
+64 64 semget sys_semget
+65 64 semop sys_semop
+66 64 semctl sys_semctl
+67 64 shmdt sys_shmdt
+68 64 msgget sys_msgget
+69 64 msgsnd sys_msgsnd
+70 64 msgrcv sys_msgrcv
+71 64 msgctl sys_msgctl
+72 64 fcntl sys_fcntl
+73 64 flock sys_flock
+74 64 fsync sys_fsync
+75 64 fdatasync sys_fdatasync
+76 64 truncate sys_truncate
+77 64 ftruncate sys_ftruncate
+78 64 getdents sys_getdents
+79 64 getcwd sys_getcwd
+80 64 chdir sys_chdir
+81 64 fchdir sys_fchdir
+82 64 rename sys_rename
+83 64 mkdir sys_mkdir
+84 64 rmdir sys_rmdir
+85 64 creat sys_creat
+86 64 link sys_link
+87 64 unlink sys_unlink
+88 64 symlink sys_symlink
+89 64 readlink sys_readlink
+90 64 chmod sys_chmod
+91 64 fchmod sys_fchmod
+92 64 chown sys_chown
+93 64 fchown sys_fchown
+94 64 lchown sys_lchown
+95 64 umask sys_umask
+96 64 gettimeofday sys_gettimeofday
+97 64 getrlimit sys_getrlimit
+98 64 getrusage sys_getrusage
+99 64 sysinfo sys_sysinfo
+100 64 times sys_times
+101 64 ptrace sys_ptrace
+102 64 getuid sys_getuid
+103 64 syslog sys_syslog
+104 64 getgid sys_getgid
+105 64 setuid sys_setuid
+106 64 setgid sys_setgid
+107 64 geteuid sys_geteuid
+108 64 getegid sys_getegid
+109 64 setpgid sys_setpgid
+110 64 getppid sys_getppid
+111 64 getpgrp sys_getpgrp
+112 64 setsid sys_setsid
+113 64 setreuid sys_setreuid
+114 64 setregid sys_setregid
+115 64 getgroups sys_getgroups
+116 64 setgroups sys_setgroups
+117 64 setresuid sys_setresuid
+118 64 getresuid sys_getresuid
+119 64 setresgid sys_setresgid
+120 64 getresgid sys_getresgid
+121 64 getpgid sys_getpgid
+122 64 setfsuid sys_setfsuid
+123 64 setfsgid sys_setfsgid
+124 64 getsid sys_getsid
+125 64 capget sys_capget
+126 64 capset sys_capset
+127 64 rt_sigpending sys_rt_sigpending
+128 64 rt_sigtimedwait sys_rt_sigtimedwait
+129 64 rt_sigqueueinfo sys_rt_sigqueueinfo
+130 64 rt_sigsuspend sys_rt_sigsuspend
+131 64 sigaltstack stub_sigaltstack
+132 64 utime sys_utime
+133 64 mknod sys_mknod
+134 64 uselib
+135 64 personality sys_personality
+136 64 ustat sys_ustat
+137 64 statfs sys_statfs
+138 64 fstatfs sys_fstatfs
+139 64 sysfs sys_sysfs
+140 64 getpriority sys_getpriority
+141 64 setpriority sys_setpriority
+142 64 sched_setparam sys_sched_setparam
+143 64 sched_getparam sys_sched_getparam
+144 64 sched_setscheduler sys_sched_setscheduler
+145 64 sched_getscheduler sys_sched_getscheduler
+146 64 sched_get_priority_max sys_sched_get_priority_max
+147 64 sched_get_priority_min sys_sched_get_priority_min
+148 64 sched_rr_get_interval sys_sched_rr_get_interval
+149 64 mlock sys_mlock
+150 64 munlock sys_munlock
+151 64 mlockall sys_mlockall
+152 64 munlockall sys_munlockall
+153 64 vhangup sys_vhangup
+154 64 modify_ldt sys_modify_ldt
+155 64 pivot_root sys_pivot_root
+156 64 _sysctl sys_sysctl
+157 64 prctl sys_prctl
+158 64 arch_prctl sys_arch_prctl
+159 64 adjtimex sys_adjtimex
+160 64 setrlimit sys_setrlimit
+161 64 chroot sys_chroot
+162 64 sync sys_sync
+163 64 acct sys_acct
+164 64 settimeofday sys_settimeofday
+165 64 mount sys_mount
+166 64 umount2 sys_umount
+167 64 swapon sys_swapon
+168 64 swapoff sys_swapoff
+169 64 reboot sys_reboot
+170 64 sethostname sys_sethostname
+171 64 setdomainname sys_setdomainname
+172 64 iopl stub_iopl
+173 64 ioperm sys_ioperm
+174 64 create_module
+175 64 init_module sys_init_module
+176 64 delete_module sys_delete_module
+177 64 get_kernel_syms
+178 64 query_module
+179 64 quotactl sys_quotactl
+180 64 nfsservctl
+181 64 getpmsg
+182 64 putpmsg
+183 64 afs_syscall
+184 64 tuxcall
+185 64 security
+186 64 gettid sys_gettid
+187 64 readahead sys_readahead
+188 64 setxattr sys_setxattr
+189 64 lsetxattr sys_lsetxattr
+190 64 fsetxattr sys_fsetxattr
+191 64 getxattr sys_getxattr
+192 64 lgetxattr sys_lgetxattr
+193 64 fgetxattr sys_fgetxattr
+194 64 listxattr sys_listxattr
+195 64 llistxattr sys_llistxattr
+196 64 flistxattr sys_flistxattr
+197 64 removexattr sys_removexattr
+198 64 lremovexattr sys_lremovexattr
+199 64 fremovexattr sys_fremovexattr
+200 64 tkill sys_tkill
+201 64 time sys_time
+202 64 futex sys_futex
+203 64 sched_setaffinity sys_sched_setaffinity
+204 64 sched_getaffinity sys_sched_getaffinity
+205 64 set_thread_area
+206 64 io_setup sys_io_setup
+207 64 io_destroy sys_io_destroy
+208 64 io_getevents sys_io_getevents
+209 64 io_submit sys_io_submit
+210 64 io_cancel sys_io_cancel
+211 64 get_thread_area
+212 64 lookup_dcookie sys_lookup_dcookie
+213 64 epoll_create sys_epoll_create
+214 64 epoll_ctl_old
+215 64 epoll_wait_old
+216 64 remap_file_pages sys_remap_file_pages
+217 64 getdents64 sys_getdents64
+218 64 set_tid_address sys_set_tid_address
+219 64 restart_syscall sys_restart_syscall
+220 64 semtimedop sys_semtimedop
+221 64 fadvise64 sys_fadvise64
+222 64 timer_create sys_timer_create
+223 64 timer_settime sys_timer_settime
+224 64 timer_gettime sys_timer_gettime
+225 64 timer_getoverrun sys_timer_getoverrun
+226 64 timer_delete sys_timer_delete
+227 64 clock_settime sys_clock_settime
+228 64 clock_gettime sys_clock_gettime
+229 64 clock_getres sys_clock_getres
+230 64 clock_nanosleep sys_clock_nanosleep
+231 64 exit_group sys_exit_group
+232 64 epoll_wait sys_epoll_wait
+233 64 epoll_ctl sys_epoll_ctl
+234 64 tgkill sys_tgkill
+235 64 utimes sys_utimes
+236 64 vserver
+237 64 mbind sys_mbind
+238 64 set_mempolicy sys_set_mempolicy
+239 64 get_mempolicy sys_get_mempolicy
+240 64 mq_open sys_mq_open
+241 64 mq_unlink sys_mq_unlink
+242 64 mq_timedsend sys_mq_timedsend
+243 64 mq_timedreceive sys_mq_timedreceive
+244 64 mq_notify sys_mq_notify
+245 64 mq_getsetattr sys_mq_getsetattr
+246 64 kexec_load sys_kexec_load
+247 64 waitid sys_waitid
+248 64 add_key sys_add_key
+249 64 request_key sys_request_key
+250 64 keyctl sys_keyctl
+251 64 ioprio_set sys_ioprio_set
+252 64 ioprio_get sys_ioprio_get
+253 64 inotify_init sys_inotify_init
+254 64 inotify_add_watch sys_inotify_add_watch
+255 64 inotify_rm_watch sys_inotify_rm_watch
+256 64 migrate_pages sys_migrate_pages
+257 64 openat sys_openat
+258 64 mkdirat sys_mkdirat
+259 64 mknodat sys_mknodat
+260 64 fchownat sys_fchownat
+261 64 futimesat sys_futimesat
+262 64 newfstatat sys_newfstatat
+263 64 unlinkat sys_unlinkat
+264 64 renameat sys_renameat
+265 64 linkat sys_linkat
+266 64 symlinkat sys_symlinkat
+267 64 readlinkat sys_readlinkat
+268 64 fchmodat sys_fchmodat
+269 64 faccessat sys_faccessat
+270 64 pselect6 sys_pselect6
+271 64 ppoll sys_ppoll
+272 64 unshare sys_unshare
+273 64 set_robust_list sys_set_robust_list
+274 64 get_robust_list sys_get_robust_list
+275 64 splice sys_splice
+276 64 tee sys_tee
+277 64 sync_file_range sys_sync_file_range
+278 64 vmsplice sys_vmsplice
+279 64 move_pages sys_move_pages
+280 64 utimensat sys_utimensat
+281 64 epoll_pwait sys_epoll_pwait
+282 64 signalfd sys_signalfd
+283 64 timerfd_create sys_timerfd_create
+284 64 eventfd sys_eventfd
+285 64 fallocate sys_fallocate
+286 64 timerfd_settime sys_timerfd_settime
+287 64 timerfd_gettime sys_timerfd_gettime
+288 64 accept4 sys_accept4
+289 64 signalfd4 sys_signalfd4
+290 64 eventfd2 sys_eventfd2
+291 64 epoll_create1 sys_epoll_create1
+292 64 dup3 sys_dup3
+293 64 pipe2 sys_pipe2
+294 64 inotify_init1 sys_inotify_init1
+295 64 preadv sys_preadv
+296 64 pwritev sys_pwritev
+297 64 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo
+298 64 perf_event_open sys_perf_event_open
+299 64 recvmmsg sys_recvmmsg
+300 64 fanotify_init sys_fanotify_init
+301 64 fanotify_mark sys_fanotify_mark
+302 64 prlimit64 sys_prlimit64
+303 64 name_to_handle_at sys_name_to_handle_at
+304 64 open_by_handle_at sys_open_by_handle_at
+305 64 clock_adjtime sys_clock_adjtime
+306 64 syncfs sys_syncfs
+307 64 sendmmsg sys_sendmmsg
+308 64 setns sys_setns
+309 64 getcpu sys_getcpu
+310 64 process_vm_readv sys_process_vm_readv
+311 64 process_vm_writev sys_process_vm_writev
diff --git a/arch/x86/syscalls/syscallhdr.sh b/arch/x86/syscalls/syscallhdr.sh
new file mode 100644
index 000000000000..31fd5f1f38f7
--- /dev/null
+++ b/arch/x86/syscalls/syscallhdr.sh
@@ -0,0 +1,27 @@
+#!/bin/sh
+
+in="$1"
+out="$2"
+my_abis=`echo "($3)" | tr ',' '|'`
+prefix="$4"
+offset="$5"
+
+fileguard=_ASM_X86_`basename "$out" | sed \
+ -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
+ -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
+grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
+ echo "#ifndef ${fileguard}"
+ echo "#define ${fileguard} 1"
+ echo ""
+
+ while read nr abi name entry ; do
+ if [ -z "$offset" ]; then
+ echo "#define __NR_${prefix}${name} $nr"
+ else
+ echo "#define __NR_${prefix}${name} ($offset + $nr)"
+ fi
+ done
+
+ echo ""
+ echo "#endif /* ${fileguard} */"
+) > "$out"
diff --git a/arch/x86/syscalls/syscalltbl.sh b/arch/x86/syscalls/syscalltbl.sh
new file mode 100644
index 000000000000..0e7f8ec071e7
--- /dev/null
+++ b/arch/x86/syscalls/syscalltbl.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+
+in="$1"
+out="$2"
+
+grep '^[0-9]' "$in" | sort -n | (
+ while read nr abi name entry compat; do
+ abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
+ if [ -n "$compat" ]; then
+ echo "__SYSCALL_${abi}($nr, $entry, $compat)"
+ elif [ -n "$entry" ]; then
+ echo "__SYSCALL_${abi}($nr, $entry, $entry)"
+ fi
+ done
+) > "$out"
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 1d97bd84b6fb..b2b54d2edf53 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -6,14 +6,6 @@ menu "UML-specific options"
menu "Host processor type and features"
-config CMPXCHG_LOCAL
- bool
- default n
-
-config CMPXCHG_DOUBLE
- bool
- default n
-
source "arch/x86/Kconfig.cpu"
endmenu
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index 8fb58400e415..5d065b2222d3 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -37,7 +37,8 @@ subarch-$(CONFIG_MODULES) += ../kernel/module.o
USER_OBJS := bugs_$(BITS).o ptrace_user.o fault.o
extra-y += user-offsets.s
-$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS)
+$(obj)/user-offsets.s: c_flags = -Wp,-MD,$(depfile) $(USER_CFLAGS) \
+ -Iarch/x86/include/generated
UNPROFILE_OBJS := stub_segv.o
CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h
index 711b1621747f..2bbe1ec2d96a 100644
--- a/arch/x86/um/shared/sysdep/ptrace.h
+++ b/arch/x86/um/shared/sysdep/ptrace.h
@@ -1,5 +1,15 @@
+#ifndef __SYSDEP_X86_PTRACE_H
+#define __SYSDEP_X86_PTRACE_H
+
#ifdef __i386__
#include "ptrace_32.h"
#else
#include "ptrace_64.h"
#endif
+
+static inline long regs_return_value(struct uml_pt_regs *regs)
+{
+ return UPT_SYSCALL_RET(regs);
+}
+
+#endif /* __SYSDEP_X86_PTRACE_H */
diff --git a/arch/x86/um/sys_call_table_32.S b/arch/x86/um/sys_call_table_32.S
deleted file mode 100644
index a7ca80d2dceb..000000000000
--- a/arch/x86/um/sys_call_table_32.S
+++ /dev/null
@@ -1,26 +0,0 @@
-#include <linux/linkage.h>
-/* Steal i386 syscall table for our purposes, but with some slight changes.*/
-
-#define sys_iopl sys_ni_syscall
-#define sys_ioperm sys_ni_syscall
-
-#define sys_vm86old sys_ni_syscall
-#define sys_vm86 sys_ni_syscall
-
-#define old_mmap sys_old_mmap
-
-#define ptregs_fork sys_fork
-#define ptregs_execve sys_execve
-#define ptregs_iopl sys_iopl
-#define ptregs_vm86old sys_vm86old
-#define ptregs_clone sys_clone
-#define ptregs_vm86 sys_vm86
-#define ptregs_sigaltstack sys_sigaltstack
-#define ptregs_vfork sys_vfork
-
-.section .rodata,"a"
-
-#include "../kernel/syscall_table_32.S"
-
-ENTRY(syscall_table_size)
-.long .-sys_call_table
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
new file mode 100644
index 000000000000..416bd40c0eba
--- /dev/null
+++ b/arch/x86/um/sys_call_table_32.c
@@ -0,0 +1,55 @@
+/*
+ * System call table for UML/i386, copied from arch/x86/kernel/syscall_*.c
+ * with some changes for UML.
+ */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <generated/user_constants.h>
+
+#define __NO_STUBS
+
+/*
+ * Below you can see, in terms of #define's, the differences between the x86-64
+ * and the UML syscall table.
+ */
+
+/* Not going to be implemented by UML, since we have no hardware. */
+#define sys_iopl sys_ni_syscall
+#define sys_ioperm sys_ni_syscall
+
+#define sys_vm86old sys_ni_syscall
+#define sys_vm86 sys_ni_syscall
+
+#define old_mmap sys_old_mmap
+
+#define ptregs_fork sys_fork
+#define ptregs_execve sys_execve
+#define ptregs_iopl sys_iopl
+#define ptregs_vm86old sys_vm86old
+#define ptregs_clone sys_clone
+#define ptregs_vm86 sys_vm86
+#define ptregs_sigaltstack sys_sigaltstack
+#define ptregs_vfork sys_vfork
+
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ;
+#include <asm/syscalls_32.h>
+
+#undef __SYSCALL_I386
+#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym,
+
+typedef void (*sys_call_ptr_t)(void);
+
+extern void sys_ni_syscall(void);
+
+const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_max] = &sys_ni_syscall,
+#include <asm/syscalls_32.h>
+};
+
+int syscall_table_size = sizeof(sys_call_table);
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index 99522f78b162..fe626c3ba01b 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -1,11 +1,12 @@
/*
- * System call table for UML/x86-64, copied from arch/x86_64/kernel/syscall.c
+ * System call table for UML/x86-64, copied from arch/x86/kernel/syscall_*.c
* with some changes for UML.
*/
#include <linux/linkage.h>
#include <linux/sys.h>
#include <linux/cache.h>
+#include <generated/user_constants.h>
#define __NO_STUBS
@@ -34,31 +35,23 @@
#define stub_sigaltstack sys_sigaltstack
#define stub_rt_sigreturn sys_rt_sigreturn
-#define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ;
-#undef _ASM_X86_UNISTD_64_H
-#include "../../x86/include/asm/unistd_64.h"
+#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
+#include <asm/syscalls_64.h>
-#undef __SYSCALL
-#define __SYSCALL(nr, sym) [ nr ] = sym,
-#undef _ASM_X86_UNISTD_64_H
+#undef __SYSCALL_64
+#define __SYSCALL_64(nr, sym, compat) [ nr ] = sym,
typedef void (*sys_call_ptr_t)(void);
extern void sys_ni_syscall(void);
-/*
- * We used to have a trick here which made sure that holes in the
- * x86_64 table were filled in with sys_ni_syscall, but a comment in
- * unistd_64.h says that holes aren't allowed, so the trick was
- * removed.
- * The trick looked like this
- * [0 ... UM_NR_syscall_max] = &sys_ni_syscall
- * before including unistd_64.h - the later initializations overwrote
- * the sys_ni_syscall filler.
- */
-
-sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
-#include <asm/unistd_64.h>
+const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_max] = &sys_ni_syscall,
+#include <asm/syscalls_64.h>
};
int syscall_table_size = sizeof(sys_call_table);
diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c
index ca49be8ddd0c..5edf4f4bbf53 100644
--- a/arch/x86/um/user-offsets.c
+++ b/arch/x86/um/user-offsets.c
@@ -8,6 +8,18 @@
#include <asm/ptrace.h>
#include <asm/types.h>
+#ifdef __i386__
+#define __SYSCALL_I386(nr, sym, compat) [nr] = 1,
+static char syscalls[] = {
+#include <asm/syscalls_32.h>
+};
+#else
+#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+static char syscalls[] = {
+#include <asm/syscalls_64.h>
+};
+#endif
+
#define DEFINE(sym, val) \
asm volatile("\n->" #sym " %0 " #val : : "i" (val))
@@ -77,4 +89,7 @@ void foo(void)
DEFINE(UM_PROT_READ, PROT_READ);
DEFINE(UM_PROT_WRITE, PROT_WRITE);
DEFINE(UM_PROT_EXEC, PROT_EXEC);
+
+ DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
+ DEFINE(NR_syscalls, sizeof(syscalls));
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cc9b1e182fcf..d69cc6c3f808 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -116,9 +116,26 @@ static inline void spin_time_accum_blocked(u64 start)
}
#endif /* CONFIG_XEN_DEBUG_FS */
+/*
+ * Size struct xen_spinlock so it's the same as arch_spinlock_t.
+ */
+#if NR_CPUS < 256
+typedef u8 xen_spinners_t;
+# define inc_spinners(xl) \
+ asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+ asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
+#else
+typedef u16 xen_spinners_t;
+# define inc_spinners(xl) \
+ asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+ asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
+#endif
+
struct xen_spinlock {
unsigned char lock; /* 0 -> free; 1 -> locked */
- unsigned short spinners; /* count of waiting cpus */
+ xen_spinners_t spinners; /* count of waiting cpus */
};
static int xen_spin_is_locked(struct arch_spinlock *lock)
@@ -164,8 +181,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
wmb(); /* set lock of interest before count */
- asm(LOCK_PREFIX " incw %0"
- : "+m" (xl->spinners) : : "memory");
+ inc_spinners(xl);
return prev;
}
@@ -176,8 +192,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
*/
static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
{
- asm(LOCK_PREFIX " decw %0"
- : "+m" (xl->spinners) : : "memory");
+ dec_spinners(xl);
wmb(); /* decrement count before restoring lock */
__this_cpu_write(lock_spinners, prev);
}
@@ -373,6 +388,8 @@ void xen_uninit_lock_cpu(int cpu)
void __init xen_init_spinlocks(void)
{
+ BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+
pv_lock_ops.spin_is_locked = xen_spin_is_locked;
pv_lock_ops.spin_is_contended = xen_spin_is_contended;
pv_lock_ops.spin_lock = xen_spin_lock;