Merge branch 'x86/urgent' into x86/asm to pick up dependent fixes
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 54944c7..2a4ee63 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -196,3 +196,35 @@
"debugpat" boot parameter. With this parameter, various debug messages are
printed to dmesg log.
+PAT Initialization
+------------------
+
+The following table describes how PAT is initialized under various
+configurations. The PAT MSR must be updated by Linux in order to support WC
+and WT attributes. Otherwise, the PAT MSR has the value programmed in it
+by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests.
+
+ MTRR PAT Call Sequence PAT State PAT MSR
+ =========================================================
+ E E MTRR -> PAT init Enabled OS
+ E D MTRR -> PAT init Disabled -
+ D E MTRR -> PAT disable Disabled BIOS
+ D D MTRR -> PAT disable Disabled -
+ - np/E PAT -> PAT disable Disabled BIOS
+ - np/D PAT -> PAT disable Disabled -
+ E !P/E MTRR -> PAT init Disabled BIOS
+ D !P/E MTRR -> PAT disable Disabled BIOS
+ !M !P/E MTRR stub -> PAT disable Disabled BIOS
+
+ Legend
+ ------------------------------------------------
+ E Feature enabled in CPU
+ D Feature disabled/unsupported in CPU
+ np "nopat" boot option specified
+ !P CONFIG_X86_PAT option unset
+ !M CONFIG_MTRR option unset
+ Enabled PAT state set to enabled
+ Disabled PAT state set to disabled
+ OS PAT initializes PAT MSR with OS setting
+ BIOS PAT keeps PAT MSR with BIOS setting
+
diff --git a/MAINTAINERS b/MAINTAINERS
index 03e00c7..378ebff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11137,8 +11137,8 @@
F: net/tipc/
TILE ARCHITECTURE
-M: Chris Metcalf <cmetcalf@ezchip.com>
-W: http://www.ezchip.com/scm/
+M: Chris Metcalf <cmetcalf@mellanox.com>
+W: http://www.mellanox.com/repository/solutions/tile-scm/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile.git
S: Supported
F: arch/tile/
diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h
index 105c93b..1d12129 100644
--- a/arch/ia64/include/asm/iommu.h
+++ b/arch/ia64/include/asm/iommu.h
@@ -1,7 +1,6 @@
#ifndef _ASM_IA64_IOMMU_H
#define _ASM_IA64_IOMMU_H 1
-#define cpu_has_x2apic 0
/* 10 seconds */
#define DMAR_OPERATION_TIMEOUT (((cycles_t) local_cpu_data->itc_freq)*10)
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 718dd19..367c542 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -97,8 +97,7 @@
return 0;
#endif
- *addr64 = fdt_translate_address((const void *)initial_boot_params,
- node);
+ *addr64 = of_flat_dt_translate_address(node);
return *addr64 == OF_BAD_ADDR ? 0 : 1;
}
diff --git a/arch/sparc/include/asm/compat_signal.h b/arch/sparc/include/asm/compat_signal.h
index 9ed1f12..4b027b1 100644
--- a/arch/sparc/include/asm/compat_signal.h
+++ b/arch/sparc/include/asm/compat_signal.h
@@ -6,17 +6,17 @@
#ifdef CONFIG_COMPAT
struct __new_sigaction32 {
- unsigned sa_handler;
+ unsigned int sa_handler;
unsigned int sa_flags;
- unsigned sa_restorer; /* not used by Linux/SPARC yet */
+ unsigned int sa_restorer; /* not used by Linux/SPARC yet */
compat_sigset_t sa_mask;
};
struct __old_sigaction32 {
- unsigned sa_handler;
+ unsigned int sa_handler;
compat_old_sigset_t sa_mask;
unsigned int sa_flags;
- unsigned sa_restorer; /* not used by Linux/SPARC yet */
+ unsigned int sa_restorer; /* not used by Linux/SPARC yet */
};
#endif
diff --git a/arch/sparc/include/asm/obio.h b/arch/sparc/include/asm/obio.h
index 910c1d9..426ad75 100644
--- a/arch/sparc/include/asm/obio.h
+++ b/arch/sparc/include/asm/obio.h
@@ -117,9 +117,9 @@
"i" (ASI_M_CTL));
}
-static inline unsigned bw_get_prof_limit(int cpu)
+static inline unsigned int bw_get_prof_limit(int cpu)
{
- unsigned limit;
+ unsigned int limit;
__asm__ __volatile__ ("lda [%1] %2, %0" :
"=r" (limit) :
@@ -128,7 +128,7 @@
return limit;
}
-static inline void bw_set_prof_limit(int cpu, unsigned limit)
+static inline void bw_set_prof_limit(int cpu, unsigned int limit)
{
__asm__ __volatile__ ("sta %0, [%1] %2" : :
"r" (limit),
@@ -136,9 +136,9 @@
"i" (ASI_M_CTL));
}
-static inline unsigned bw_get_ctrl(int cpu)
+static inline unsigned int bw_get_ctrl(int cpu)
{
- unsigned ctrl;
+ unsigned int ctrl;
__asm__ __volatile__ ("lda [%1] %2, %0" :
"=r" (ctrl) :
@@ -147,7 +147,7 @@
return ctrl;
}
-static inline void bw_set_ctrl(int cpu, unsigned ctrl)
+static inline void bw_set_ctrl(int cpu, unsigned int ctrl)
{
__asm__ __volatile__ ("sta %0, [%1] %2" : :
"r" (ctrl),
@@ -155,9 +155,9 @@
"i" (ASI_M_CTL));
}
-static inline unsigned cc_get_ipen(void)
+static inline unsigned int cc_get_ipen(void)
{
- unsigned pending;
+ unsigned int pending;
__asm__ __volatile__ ("lduha [%1] %2, %0" :
"=r" (pending) :
@@ -166,7 +166,7 @@
return pending;
}
-static inline void cc_set_iclr(unsigned clear)
+static inline void cc_set_iclr(unsigned int clear)
{
__asm__ __volatile__ ("stha %0, [%1] %2" : :
"r" (clear),
@@ -174,9 +174,9 @@
"i" (ASI_M_MXCC));
}
-static inline unsigned cc_get_imsk(void)
+static inline unsigned int cc_get_imsk(void)
{
- unsigned mask;
+ unsigned int mask;
__asm__ __volatile__ ("lduha [%1] %2, %0" :
"=r" (mask) :
@@ -185,7 +185,7 @@
return mask;
}
-static inline void cc_set_imsk(unsigned mask)
+static inline void cc_set_imsk(unsigned int mask)
{
__asm__ __volatile__ ("stha %0, [%1] %2" : :
"r" (mask),
@@ -193,9 +193,9 @@
"i" (ASI_M_MXCC));
}
-static inline unsigned cc_get_imsk_other(int cpuid)
+static inline unsigned int cc_get_imsk_other(int cpuid)
{
- unsigned mask;
+ unsigned int mask;
__asm__ __volatile__ ("lduha [%1] %2, %0" :
"=r" (mask) :
@@ -204,7 +204,7 @@
return mask;
}
-static inline void cc_set_imsk_other(int cpuid, unsigned mask)
+static inline void cc_set_imsk_other(int cpuid, unsigned int mask)
{
__asm__ __volatile__ ("stha %0, [%1] %2" : :
"r" (mask),
@@ -212,7 +212,7 @@
"i" (ASI_M_CTL));
}
-static inline void cc_set_igen(unsigned gen)
+static inline void cc_set_igen(unsigned int gen)
{
__asm__ __volatile__ ("sta %0, [%1] %2" : :
"r" (gen),
diff --git a/arch/sparc/include/asm/openprom.h b/arch/sparc/include/asm/openprom.h
index 47eaafa..63374c4 100644
--- a/arch/sparc/include/asm/openprom.h
+++ b/arch/sparc/include/asm/openprom.h
@@ -29,12 +29,12 @@
/* V2 and later prom device operations. */
struct linux_dev_v2_funcs {
phandle (*v2_inst2pkg)(int d); /* Convert ihandle to phandle */
- char * (*v2_dumb_mem_alloc)(char *va, unsigned sz);
- void (*v2_dumb_mem_free)(char *va, unsigned sz);
+ char * (*v2_dumb_mem_alloc)(char *va, unsigned int sz);
+ void (*v2_dumb_mem_free)(char *va, unsigned int sz);
/* To map devices into virtual I/O space. */
- char * (*v2_dumb_mmap)(char *virta, int which_io, unsigned paddr, unsigned sz);
- void (*v2_dumb_munmap)(char *virta, unsigned size);
+ char * (*v2_dumb_mmap)(char *virta, int which_io, unsigned int paddr, unsigned int sz);
+ void (*v2_dumb_munmap)(char *virta, unsigned int size);
int (*v2_dev_open)(char *devpath);
void (*v2_dev_close)(int d);
@@ -50,7 +50,7 @@
struct linux_mlist_v0 {
struct linux_mlist_v0 *theres_more;
unsigned int start_adr;
- unsigned num_bytes;
+ unsigned int num_bytes;
};
struct linux_mem_v0 {
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 7a38d6a..f089cfa 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -218,7 +218,7 @@
extern pgprot_t PAGE_COPY;
extern pgprot_t PAGE_SHARED;
-/* XXX This uglyness is for the atyfb driver's sparc mmap() support. XXX */
+/* XXX This ugliness is for the atyfb driver's sparc mmap() support. XXX */
extern unsigned long _PAGE_IE;
extern unsigned long _PAGE_E;
extern unsigned long _PAGE_CACHE;
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 6924bde..ce2595c 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -201,7 +201,7 @@
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->u_regs[UREG_FP])
/* Please see the commentary in asm/backoff.h for a description of
- * what these instructions are doing and how they have been choosen.
+ * what these instructions are doing and how they have been chosen.
* To make a long story short, we are trying to yield the current cpu
* strand during busy loops.
*/
diff --git a/arch/sparc/include/asm/sigcontext.h b/arch/sparc/include/asm/sigcontext.h
index fc2df1e..f4eb630 100644
--- a/arch/sparc/include/asm/sigcontext.h
+++ b/arch/sparc/include/asm/sigcontext.h
@@ -25,7 +25,7 @@
int sigc_oswins; /* outstanding windows */
/* stack ptrs for each regwin buf */
- unsigned sigc_spbuf[__SUNOS_MAXWIN];
+ unsigned int sigc_spbuf[__SUNOS_MAXWIN];
/* Windows to restore after signal */
struct reg_window32 sigc_wbuf[__SUNOS_MAXWIN];
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index ecb49cf..c6a155c 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -149,7 +149,7 @@
* page size in question. So for PMD mappings (which fall on
* bit 23, for 8MB per PMD) we must propagate bit 22 for a
* 4MB huge page. For huge PUDs (which fall on bit 33, for
- * 8GB per PUD), we have to accomodate 256MB and 2GB huge
+ * 8GB per PUD), we have to accommodate 256MB and 2GB huge
* pages. So for those we propagate bits 32 to 28.
*/
#define KERN_PGTABLE_WALK(VADDR, REG1, REG2, FAIL_LABEL) \
diff --git a/arch/sparc/include/uapi/asm/stat.h b/arch/sparc/include/uapi/asm/stat.h
index a232e9e..2f0583a 100644
--- a/arch/sparc/include/uapi/asm/stat.h
+++ b/arch/sparc/include/uapi/asm/stat.h
@@ -6,13 +6,13 @@
#if defined(__sparc__) && defined(__arch64__)
/* 64 bit sparc */
struct stat {
- unsigned st_dev;
+ unsigned int st_dev;
ino_t st_ino;
mode_t st_mode;
short st_nlink;
uid_t st_uid;
gid_t st_gid;
- unsigned st_rdev;
+ unsigned int st_rdev;
off_t st_size;
time_t st_atime;
time_t st_mtime;
diff --git a/arch/sparc/kernel/audit.c b/arch/sparc/kernel/audit.c
index 24361b4..2585c1e 100644
--- a/arch/sparc/kernel/audit.c
+++ b/arch/sparc/kernel/audit.c
@@ -5,27 +5,27 @@
#include "kernel.h"
-static unsigned dir_class[] = {
+static unsigned int dir_class[] = {
#include <asm-generic/audit_dir_write.h>
~0U
};
-static unsigned read_class[] = {
+static unsigned int read_class[] = {
#include <asm-generic/audit_read.h>
~0U
};
-static unsigned write_class[] = {
+static unsigned int write_class[] = {
#include <asm-generic/audit_write.h>
~0U
};
-static unsigned chattr_class[] = {
+static unsigned int chattr_class[] = {
#include <asm-generic/audit_change_attr.h>
~0U
};
-static unsigned signal_class[] = {
+static unsigned int signal_class[] = {
#include <asm-generic/audit_signal.h>
~0U
};
@@ -39,7 +39,7 @@
return 0;
}
-int audit_classify_syscall(int abi, unsigned syscall)
+int audit_classify_syscall(int abi, unsigned int syscall)
{
#ifdef CONFIG_COMPAT
if (abi == AUDIT_ARCH_SPARC)
diff --git a/arch/sparc/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c
index 7062263..e5611cd 100644
--- a/arch/sparc/kernel/compat_audit.c
+++ b/arch/sparc/kernel/compat_audit.c
@@ -2,32 +2,32 @@
#include <asm/unistd.h>
#include "kernel.h"
-unsigned sparc32_dir_class[] = {
+unsigned int sparc32_dir_class[] = {
#include <asm-generic/audit_dir_write.h>
~0U
};
-unsigned sparc32_chattr_class[] = {
+unsigned int sparc32_chattr_class[] = {
#include <asm-generic/audit_change_attr.h>
~0U
};
-unsigned sparc32_write_class[] = {
+unsigned int sparc32_write_class[] = {
#include <asm-generic/audit_write.h>
~0U
};
-unsigned sparc32_read_class[] = {
+unsigned int sparc32_read_class[] = {
#include <asm-generic/audit_read.h>
~0U
};
-unsigned sparc32_signal_class[] = {
+unsigned int sparc32_signal_class[] = {
#include <asm-generic/audit_signal.h>
~0U
};
-int sparc32_classify_syscall(unsigned syscall)
+int sparc32_classify_syscall(unsigned int syscall)
{
switch(syscall) {
case __NR_open:
diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S
index a83707c..51aa6e8 100644
--- a/arch/sparc/kernel/entry.S
+++ b/arch/sparc/kernel/entry.S
@@ -1255,7 +1255,7 @@
kuw_patch1_7win: sll %o3, 6, %o3
/* No matter how much overhead this routine has in the worst
- * case scenerio, it is several times better than taking the
+ * case scenario, it is several times better than taking the
* traps with the old method of just doing flush_user_windows().
*/
kill_user_windows:
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 28fed53..ffd5ff4 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -131,7 +131,7 @@
EXPORT_SYMBOL(ioremap);
/*
- * Comlimentary to ioremap().
+ * Complementary to ioremap().
*/
void iounmap(volatile void __iomem *virtual)
{
@@ -233,7 +233,7 @@
}
/*
- * Comlimentary to _sparc_ioremap().
+ * Complementary to _sparc_ioremap().
*/
static void _sparc_free_io(struct resource *res)
{
@@ -532,7 +532,7 @@
}
/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA. This is the scather-gather version of the
+ * mode for DMA. This is the scatter-gather version of the
* above pci_map_single interface. Here the scatter gather list
* elements are each tagged with the appropriate dma address
* and length. They are obtained via sg_dma_{address,length}(SG).
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
index e7f652b..5057ec2 100644
--- a/arch/sparc/kernel/kernel.h
+++ b/arch/sparc/kernel/kernel.h
@@ -54,12 +54,12 @@
asmlinkage int do_sys32_sigstack(u32 u_ssptr, u32 u_ossptr, unsigned long sp);
/* compat_audit.c */
-extern unsigned sparc32_dir_class[];
-extern unsigned sparc32_chattr_class[];
-extern unsigned sparc32_write_class[];
-extern unsigned sparc32_read_class[];
-extern unsigned sparc32_signal_class[];
-int sparc32_classify_syscall(unsigned syscall);
+extern unsigned int sparc32_dir_class[];
+extern unsigned int sparc32_chattr_class[];
+extern unsigned int sparc32_write_class[];
+extern unsigned int sparc32_read_class[];
+extern unsigned int sparc32_signal_class[];
+int sparc32_classify_syscall(unsigned int syscall);
#endif
#ifdef CONFIG_SPARC32
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 42efcf8..33cd171 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -203,7 +203,7 @@
/*
* Build a LEON IRQ for the edge triggered LEON IRQ controller:
- * Edge (normal) IRQ - handle_simple_irq, ack=DONT-CARE, never ack
+ * Edge (normal) IRQ - handle_simple_irq, ack=DON'T-CARE, never ack
* Level IRQ (PCI|Level-GPIO) - handle_fasteoi_irq, ack=1, ack after ISR
* Per-CPU Edge - handle_percpu_irq, ack=0
*/
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 46a5964..c16ef1a 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -103,7 +103,7 @@
mm_segment_t old_fs;
__asm__ __volatile__ ("flushw");
- rw = compat_ptr((unsigned)regs->u_regs[14]);
+ rw = compat_ptr((unsigned int)regs->u_regs[14]);
old_fs = get_fs();
set_fs (USER_DS);
if (copy_from_user (&r_w, rw, sizeof(r_w))) {
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index baef495..69d75ff 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -109,7 +109,7 @@
unsigned char boot_cpu_id = 0xff; /* 0xff will make it into DATA section... */
static void
-prom_console_write(struct console *con, const char *s, unsigned n)
+prom_console_write(struct console *con, const char *s, unsigned int n)
{
prom_write(s, n);
}
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index f3185e2..26db95b 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -77,7 +77,7 @@
};
static void
-prom_console_write(struct console *con, const char *s, unsigned n)
+prom_console_write(struct console *con, const char *s, unsigned int n)
{
prom_write(s, n);
}
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 4eed773..3c25241 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -144,7 +144,7 @@
compat_uptr_t fpu_save;
compat_uptr_t rwin_save;
unsigned int psr;
- unsigned pc, npc;
+ unsigned int pc, npc;
sigset_t set;
compat_sigset_t seta;
int err, i;
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index b489e97..fe8b8ee 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -337,10 +337,10 @@
switch (call) {
case SEMOP:
err = sys_semtimedop(first, ptr,
- (unsigned)second, NULL);
+ (unsigned int)second, NULL);
goto out;
case SEMTIMEDOP:
- err = sys_semtimedop(first, ptr, (unsigned)second,
+ err = sys_semtimedop(first, ptr, (unsigned int)second,
(const struct timespec __user *)
(unsigned long) fifth);
goto out;
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index 7f41d40..fa8e21a 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -1,4 +1,4 @@
-/* sysfs.c: Toplogy sysfs support code for sparc64.
+/* sysfs.c: Topology sysfs support code for sparc64.
*
* Copyright (C) 2007 David S. Miller <davem@davemloft.net>
*/
diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c
index d89e97b..9aacb91 100644
--- a/arch/sparc/kernel/unaligned_64.c
+++ b/arch/sparc/kernel/unaligned_64.c
@@ -209,8 +209,8 @@
if (size == 16) {
size = 8;
zero = (((long)(reg_num ?
- (unsigned)fetch_reg(reg_num, regs) : 0)) << 32) |
- (unsigned)fetch_reg(reg_num + 1, regs);
+ (unsigned int)fetch_reg(reg_num, regs) : 0)) << 32) |
+ (unsigned int)fetch_reg(reg_num + 1, regs);
} else if (reg_num) {
src_val_p = fetch_reg_addr(reg_num, regs);
}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index c399e7b..b6c559c 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -303,10 +303,10 @@
fixup = search_extables_range(regs->pc, &g2);
/* Values below 10 are reserved for other things */
if (fixup > 10) {
- extern const unsigned __memset_start[];
- extern const unsigned __memset_end[];
- extern const unsigned __csum_partial_copy_start[];
- extern const unsigned __csum_partial_copy_end[];
+ extern const unsigned int __memset_start[];
+ extern const unsigned int __memset_end[];
+ extern const unsigned int __csum_partial_copy_start[];
+ extern const unsigned int __csum_partial_copy_end[];
#ifdef DEBUG_EXCEPTIONS
printk("Exception: PC<%08lx> faddr<%08lx>\n",
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 3e6e05a..a6d9204 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -351,7 +351,7 @@
*
* Sometimes we need to emit a branch earlier in the code
* sequence. And in these situations we adjust "destination"
- * to accomodate this difference. For example, if we needed
+ * to accommodate this difference. For example, if we needed
* to emit a branch (and it's delay slot) right before the
* final instruction emitted for a BPF opcode, we'd use
* "destination + 4" instead of just plain "destination" above.
diff --git a/arch/tile/include/hv/drv_mpipe_intf.h b/arch/tile/include/hv/drv_mpipe_intf.h
index c97e416..ff7f50f 100644
--- a/arch/tile/include/hv/drv_mpipe_intf.h
+++ b/arch/tile/include/hv/drv_mpipe_intf.h
@@ -211,7 +211,7 @@
* request shared data permission on the same link.
*
* No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA,
- * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed.
*/
#define GXIO_MPIPE_LINK_DATA 0x00000001UL
@@ -219,7 +219,7 @@
/** Do not request data permission on the specified link.
*
* No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA,
- * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed.
*/
#define GXIO_MPIPE_LINK_NO_DATA 0x00000002UL
@@ -230,7 +230,7 @@
* data permission on it, this open will fail.
*
* No more than one of ::GXIO_MPIPE_LINK_DATA, ::GXIO_MPIPE_LINK_NO_DATA,
- * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_DATA may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_DATA is assumed.
*/
#define GXIO_MPIPE_LINK_EXCL_DATA 0x00000004UL
@@ -241,7 +241,7 @@
* permission on the same link.
*
* No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS,
- * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed.
*/
#define GXIO_MPIPE_LINK_STATS 0x00000008UL
@@ -249,7 +249,7 @@
/** Do not request stats permission on the specified link.
*
* No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS,
- * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed.
*/
#define GXIO_MPIPE_LINK_NO_STATS 0x00000010UL
@@ -267,7 +267,7 @@
* reset by other statistics programs.
*
* No more than one of ::GXIO_MPIPE_LINK_STATS, ::GXIO_MPIPE_LINK_NO_STATS,
- * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_STATS may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_STATS is assumed.
*/
#define GXIO_MPIPE_LINK_EXCL_STATS 0x00000020UL
@@ -278,7 +278,7 @@
* permission on the same link.
*
* No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL,
- * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed.
*/
#define GXIO_MPIPE_LINK_CTL 0x00000040UL
@@ -286,7 +286,7 @@
/** Do not request control permission on the specified link.
*
* No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL,
- * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed.
*/
#define GXIO_MPIPE_LINK_NO_CTL 0x00000080UL
@@ -301,7 +301,7 @@
* it prevents programs like mpipe-link from configuring the link.
*
* No more than one of ::GXIO_MPIPE_LINK_CTL, ::GXIO_MPIPE_LINK_NO_CTL,
- * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specifed in a gxio_mpipe_link_open()
+ * or ::GXIO_MPIPE_LINK_EXCL_CTL may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_CTL is assumed.
*/
#define GXIO_MPIPE_LINK_EXCL_CTL 0x00000100UL
@@ -311,7 +311,7 @@
* change the desired state of the link when it is closed or the process
* exits. No more than one of ::GXIO_MPIPE_LINK_AUTO_UP,
* ::GXIO_MPIPE_LINK_AUTO_UPDOWN, ::GXIO_MPIPE_LINK_AUTO_DOWN, or
- * ::GXIO_MPIPE_LINK_AUTO_NONE may be specifed in a gxio_mpipe_link_open()
+ * ::GXIO_MPIPE_LINK_AUTO_NONE may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed.
*/
#define GXIO_MPIPE_LINK_AUTO_UP 0x00000200UL
@@ -322,7 +322,7 @@
* open, set the desired state of the link to down. No more than one of
* ::GXIO_MPIPE_LINK_AUTO_UP, ::GXIO_MPIPE_LINK_AUTO_UPDOWN,
* ::GXIO_MPIPE_LINK_AUTO_DOWN, or ::GXIO_MPIPE_LINK_AUTO_NONE may be
- * specifed in a gxio_mpipe_link_open() call. If none are specified,
+ * specified in a gxio_mpipe_link_open() call. If none are specified,
* ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed.
*/
#define GXIO_MPIPE_LINK_AUTO_UPDOWN 0x00000400UL
@@ -332,7 +332,7 @@
* process has the link open, set the desired state of the link to down.
* No more than one of ::GXIO_MPIPE_LINK_AUTO_UP,
* ::GXIO_MPIPE_LINK_AUTO_UPDOWN, ::GXIO_MPIPE_LINK_AUTO_DOWN, or
- * ::GXIO_MPIPE_LINK_AUTO_NONE may be specifed in a gxio_mpipe_link_open()
+ * ::GXIO_MPIPE_LINK_AUTO_NONE may be specified in a gxio_mpipe_link_open()
* call. If none are specified, ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed.
*/
#define GXIO_MPIPE_LINK_AUTO_DOWN 0x00000800UL
@@ -342,7 +342,7 @@
* closed or the process exits. No more than one of
* ::GXIO_MPIPE_LINK_AUTO_UP, ::GXIO_MPIPE_LINK_AUTO_UPDOWN,
* ::GXIO_MPIPE_LINK_AUTO_DOWN, or ::GXIO_MPIPE_LINK_AUTO_NONE may be
- * specifed in a gxio_mpipe_link_open() call. If none are specified,
+ * specified in a gxio_mpipe_link_open() call. If none are specified,
* ::GXIO_MPIPE_LINK_AUTO_UPDOWN is assumed.
*/
#define GXIO_MPIPE_LINK_AUTO_NONE 0x00001000UL
diff --git a/arch/tile/kernel/kgdb.c b/arch/tile/kernel/kgdb.c
index a506c2c..9247d6b 100644
--- a/arch/tile/kernel/kgdb.c
+++ b/arch/tile/kernel/kgdb.c
@@ -126,15 +126,15 @@
sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
{
struct pt_regs *thread_regs;
+ const int NGPRS = TREG_LAST_GPR + 1;
if (task == NULL)
return;
- /* Initialize to zero. */
- memset(gdb_regs, 0, NUMREGBYTES);
-
thread_regs = task_pt_regs(task);
- memcpy(gdb_regs, thread_regs, TREG_LAST_GPR * sizeof(unsigned long));
+ memcpy(gdb_regs, thread_regs, NGPRS * sizeof(unsigned long));
+ memset(&gdb_regs[NGPRS], 0,
+ (TILEGX_PC_REGNUM - NGPRS) * sizeof(unsigned long));
gdb_regs[TILEGX_PC_REGNUM] = thread_regs->pc;
gdb_regs[TILEGX_FAULTNUM_REGNUM] = thread_regs->faultnum;
}
@@ -433,9 +433,9 @@
struct kgdb_arch arch_kgdb_ops;
/*
- * kgdb_arch_init - Perform any architecture specific initalization.
+ * kgdb_arch_init - Perform any architecture specific initialization.
*
- * This function will handle the initalization of any architecture
+ * This function will handle the initialization of any architecture
* specific callbacks.
*/
int kgdb_arch_init(void)
@@ -447,9 +447,9 @@
}
/*
- * kgdb_arch_exit - Perform any architecture specific uninitalization.
+ * kgdb_arch_exit - Perform any architecture specific uninitialization.
*
- * This function will handle the uninitalization of any architecture
+ * This function will handle the uninitialization of any architecture
* specific callbacks, for dynamic registration and unregistration.
*/
void kgdb_arch_exit(void)
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index 4c017d0..aa2b44c 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -1326,7 +1326,7 @@
/*
- * See tile_cfg_read() for relevent comments.
+ * See tile_cfg_read() for relevant comments.
* Note that "val" is the value to write, not a pointer to that value.
*/
static int tile_cfg_write(struct pci_bus *bus, unsigned int devfn, int offset,
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index d844569..c37f702 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -562,7 +562,8 @@
{
const char *feature_name;
- if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+ if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes ||
+ !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
pr_info("AVX2 or AES-NI instructions are not detected.\n");
return -ENODEV;
}
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 93d8f29..65f6455 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -554,7 +554,7 @@
{
const char *feature_name;
- if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+ if (!cpu_has_avx || !cpu_has_aes || !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
pr_info("AVX or AES-NI instructions are not detected.\n");
return -ENODEV;
}
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 4264a3d..b283868 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -179,7 +179,7 @@
static int __init poly1305_simd_mod_init(void)
{
- if (!cpu_has_xmm2)
+ if (!boot_cpu_has(X86_FEATURE_XMM2))
return -ENODEV;
#ifdef CONFIG_AS_AVX2
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 6d19834..408cae2 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -538,7 +538,7 @@
{
const char *feature_name;
- if (!cpu_has_avx2 || !cpu_has_osxsave) {
+ if (!cpu_has_avx2 || !boot_cpu_has(X86_FEATURE_OSXSAVE)) {
pr_info("AVX2 instructions are not detected.\n");
return -ENODEV;
}
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 8943407..644f97a 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -600,7 +600,7 @@
static int __init serpent_sse2_init(void)
{
- if (!cpu_has_xmm2) {
+ if (!boot_cpu_has(X86_FEATURE_XMM2)) {
printk(KERN_INFO "SSE2 instructions are not detected.\n");
return -ENODEV;
}
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 858b555..1693c17 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -781,15 +781,15 @@
pushfq
DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
SWAPGS
-gs_change:
+.Lgs_change:
movl %edi, %gs
-2: mfence /* workaround */
+2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
SWAPGS
popfq
ret
END(native_load_gs_index)
- _ASM_EXTABLE(gs_change, bad_gs)
+ _ASM_EXTABLE(.Lgs_change, bad_gs)
.section .fixup, "ax"
/* running with kernelgs */
bad_gs:
@@ -1019,13 +1019,13 @@
movl %ecx, %eax /* zero extend */
cmpq %rax, RIP+8(%rsp)
je .Lbstep_iret
- cmpq $gs_change, RIP+8(%rsp)
+ cmpq $.Lgs_change, RIP+8(%rsp)
jne .Lerror_entry_done
/*
- * hack: gs_change can fail with user gsbase. If this happens, fix up
+ * hack: .Lgs_change can fail with user gsbase. If this happens, fix up
* gsbase and proceed. We'll fix up the exception and land in
- * gs_change's error handler with kernel gsbase.
+ * .Lgs_change's error handler with kernel gsbase.
*/
jmp .Lerror_entry_from_usermode_swapgs
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index b30dd81..4cddd17 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -384,5 +384,5 @@
375 i386 membarrier sys_membarrier
376 i386 mlock2 sys_mlock2
377 i386 copy_file_range sys_copy_file_range
-378 i386 preadv2 sys_preadv2
-379 i386 pwritev2 sys_pwritev2
+378 i386 preadv2 sys_preadv2 compat_sys_preadv2
+379 i386 pwritev2 sys_pwritev2 compat_sys_pwritev2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index cac6d17..555263e 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -374,3 +374,5 @@
543 x32 io_setup compat_sys_io_setup
544 x32 io_submit compat_sys_io_submit
545 x32 execveat compat_sys_execveat/ptregs
+534 x32 preadv2 compat_sys_preadv2
+535 x32 pwritev2 compat_sys_pwritev2
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 03c3eb7..2f02d23 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -13,7 +13,6 @@
#include <uapi/linux/time.h>
#include <asm/vgtod.h>
-#include <asm/hpet.h>
#include <asm/vvar.h>
#include <asm/unistd.h>
#include <asm/msr.h>
@@ -28,16 +27,6 @@
extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
extern time_t __vdso_time(time_t *t);
-#ifdef CONFIG_HPET_TIMER
-extern u8 hpet_page
- __attribute__((visibility("hidden")));
-
-static notrace cycle_t vread_hpet(void)
-{
- return *(const volatile u32 *)(&hpet_page + HPET_COUNTER);
-}
-#endif
-
#ifdef CONFIG_PARAVIRT_CLOCK
extern u8 pvclock_page
__attribute__((visibility("hidden")));
@@ -195,10 +184,6 @@
if (gtod->vclock_mode == VCLOCK_TSC)
cycles = vread_tsc();
-#ifdef CONFIG_HPET_TIMER
- else if (gtod->vclock_mode == VCLOCK_HPET)
- cycles = vread_hpet();
-#endif
#ifdef CONFIG_PARAVIRT_CLOCK
else if (gtod->vclock_mode == VCLOCK_PVCLOCK)
cycles = vread_pvclock(mode);
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
index 4158acc..a708aa9 100644
--- a/arch/x86/entry/vdso/vdso-layout.lds.S
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -25,7 +25,7 @@
* segment.
*/
- vvar_start = . - 3 * PAGE_SIZE;
+ vvar_start = . - 2 * PAGE_SIZE;
vvar_page = vvar_start;
/* Place all vvars at the offsets in asm/vvar.h. */
@@ -35,8 +35,7 @@
#undef __VVAR_KERNEL_LDS
#undef EMIT_VVAR
- hpet_page = vvar_start + PAGE_SIZE;
- pvclock_page = vvar_start + 2 * PAGE_SIZE;
+ pvclock_page = vvar_start + PAGE_SIZE;
. = SIZEOF_HEADERS;
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 10f7045..b3cf813 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -18,7 +18,6 @@
#include <asm/vdso.h>
#include <asm/vvar.h>
#include <asm/page.h>
-#include <asm/hpet.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
@@ -129,16 +128,6 @@
if (sym_offset == image->sym_vvar_page) {
ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
__pa_symbol(&__vvar_page) >> PAGE_SHIFT);
- } else if (sym_offset == image->sym_hpet_page) {
-#ifdef CONFIG_HPET_TIMER
- if (hpet_address && vclock_was_used(VCLOCK_HPET)) {
- ret = vm_insert_pfn_prot(
- vma,
- (unsigned long)vmf->virtual_address,
- hpet_address >> PAGE_SHIFT,
- pgprot_noncached(PAGE_READONLY));
- }
-#endif
} else if (sym_offset == image->sym_pvclock_page) {
struct pvclock_vsyscall_time_info *pvti =
pvclock_pvti_cpu0_va();
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 7946c42..d5045c8 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -677,7 +677,7 @@
{
int err;
- if (cpu_has_hypervisor)
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return -ENODEV;
err = cstate_init();
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 7012d18..3f6d8b5 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1383,7 +1383,7 @@
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return -ENODEV;
- if (cpu_has_hypervisor)
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return -ENODEV;
max_packages = topology_max_packages();
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 98f25bb..bc27611 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -239,10 +239,10 @@
extern void x2apic_setup(void);
static inline int x2apic_enabled(void)
{
- return cpu_has_x2apic && apic_is_x2apic_enabled();
+ return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled();
}
-#define x2apic_supported() (cpu_has_x2apic)
+#define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC))
#else /* !CONFIG_X86_X2APIC */
static inline void check_x2apic(void) { }
static inline void x2apic_setup(void) { }
diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index d194266..eae33c7 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -3,11 +3,10 @@
#ifndef _ASM_X86_CLOCKSOURCE_H
#define _ASM_X86_CLOCKSOURCE_H
-#define VCLOCK_NONE 0 /* No vDSO clock available. */
-#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */
-#define VCLOCK_HPET 2 /* vDSO should use vread_hpet. */
-#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */
-#define VCLOCK_MAX 3
+#define VCLOCK_NONE 0 /* No vDSO clock available. */
+#define VCLOCK_TSC 1 /* vDSO should use vread_tsc. */
+#define VCLOCK_PVCLOCK 2 /* vDSO should use vread_pvclock. */
+#define VCLOCK_MAX 2
struct arch_clocksource_data {
int vclock_mode;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3636ec0..c594e04 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -119,25 +119,15 @@
} while (0)
#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE)
#define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC)
-#define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE)
#define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC)
#define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR)
#define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM)
-#define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2)
#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES)
#define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX)
#define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2)
-#define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH)
-#define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES)
-#define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
-#define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT)
-#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
#define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES)
-#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE)
-#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
/*
* Do not add any more of those clumsy macros - use static_cpu_has() for
* fast paths and boot_cpu_has() otherwise!
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 8f9afef..7bfb6b7 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -294,6 +294,9 @@
#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */
+
#ifdef CONFIG_X86_32
/*
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f6..dbff145 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
#define _ASM_X86_MTRR_H
#include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
/*
@@ -83,9 +84,12 @@
static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
{
}
+static inline void mtrr_bp_init(void)
+{
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
#define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
#define set_mtrr_aps_delayed_init() do {} while (0)
#define mtrr_aps_init() do {} while (0)
#define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228..0b1ff4c 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,8 @@
#include <asm/pgtable_types.h>
bool pat_enabled(void);
+void pat_disable(const char *reason);
extern void pat_init(void);
-void pat_init_cache_modes(u64);
extern int reserve_memtype(u64 start, u64 end,
enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 97f3242..f86491a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -183,7 +183,7 @@
static inline int has_transparent_hugepage(void)
{
- return cpu_has_pse;
+ return boot_cpu_has(X86_FEATURE_PSE);
}
#ifdef __HAVE_ARCH_PTE_DEVMAP
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index c24b422..3628e6c 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -181,7 +181,7 @@
static inline void __flush_tlb_all(void)
{
- if (cpu_has_pge)
+ if (static_cpu_has(X86_FEATURE_PGE))
__flush_tlb_global();
else
__flush_tlb();
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7c0a517..e45e556 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@
#define AVX_XOR_SPEED \
do { \
- if (cpu_has_avx && cpu_has_osxsave) \
+ if (cpu_has_avx && boot_cpu_has(X86_FEATURE_OSXSAVE)) \
xor_speed(&xor_block_avx); \
} while (0)
#define AVX_SELECT(FASTEST) \
- (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
+ (cpu_has_avx && boot_cpu_has(X86_FEATURE_OSXSAVE) ? &xor_block_avx : FASTEST)
#else
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d356987..d7867c8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1561,7 +1561,7 @@
pr_info("x2apic: enabled by BIOS, switching to x2apic ops\n");
x2apic_mode = 1;
x2apic_state = X2APIC_ON;
- } else if (!cpu_has_x2apic) {
+ } else if (!boot_cpu_has(X86_FEATURE_X2APIC)) {
x2apic_state = X2APIC_DISABLED;
}
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7b76eb6..19d7dcf 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -628,6 +628,7 @@
*/
msr_set_bit(MSR_K7_HWCR, 6);
#endif
+ set_cpu_bug(c, X86_BUG_SWAPGS_FENCE);
}
static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -746,7 +747,7 @@
if (c->x86 >= 0xf)
set_cpu_cap(c, X86_FEATURE_K8);
- if (cpu_has_xmm2) {
+ if (cpu_has(c, X86_FEATURE_XMM2)) {
/* MFENCE stops RDTSC speculation */
set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC);
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8394b3d..28d3255 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -862,30 +862,34 @@
#else
set_cpu_cap(c, X86_FEATURE_NOPL);
#endif
+}
+static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_64
/*
- * ESPFIX is a strange bug. All real CPUs have it. Paravirt
- * systems that run Linux at CPL > 0 may or may not have the
- * issue, but, even if they have the issue, there's absolutely
- * nothing we can do about it because we can't use the real IRET
- * instruction.
+ * Empirically, writing zero to a segment selector on AMD does
+ * not clear the base, whereas writing zero to a segment
+ * selector on Intel does clear the base. Intel's behavior
+ * allows slightly faster context switches in the common case
+ * where GS is unused by the prev and next threads.
*
- * NB: For the time being, only 32-bit kernels support
- * X86_BUG_ESPFIX as such. 64-bit kernels directly choose
- * whether to apply espfix using paravirt hooks. If any
- * non-paravirt system ever shows up that does *not* have the
- * ESPFIX issue, we can change this.
+ * Since neither vendor documents this anywhere that I can see,
+ * detect it directly instead of hardcoding the choice by
+ * vendor.
+ *
+ * I've designated AMD's behavior as the "bug" because it's
+ * counterintuitive and less friendly.
*/
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_PARAVIRT
- do {
- extern void native_iret(void);
- if (pv_cpu_ops.iret == native_iret)
- set_cpu_bug(c, X86_BUG_ESPFIX);
- } while (0);
-#else
- set_cpu_bug(c, X86_BUG_ESPFIX);
-#endif
+
+ unsigned long old_base, tmp;
+ rdmsrl(MSR_FS_BASE, old_base);
+ wrmsrl(MSR_FS_BASE, 1);
+ loadsegment(fs, 0);
+ rdmsrl(MSR_FS_BASE, tmp);
+ if (tmp != 0)
+ set_cpu_bug(c, X86_BUG_NULL_SEG);
+ wrmsrl(MSR_FS_BASE, old_base);
#endif
}
@@ -921,6 +925,33 @@
get_model_name(c); /* Default name */
detect_nopl(c);
+
+ detect_null_seg_behavior(c);
+
+ /*
+ * ESPFIX is a strange bug. All real CPUs have it. Paravirt
+ * systems that run Linux at CPL > 0 may or may not have the
+ * issue, but, even if they have the issue, there's absolutely
+ * nothing we can do about it because we can't use the real IRET
+ * instruction.
+ *
+ * NB: For the time being, only 32-bit kernels support
+ * X86_BUG_ESPFIX as such. 64-bit kernels directly choose
+ * whether to apply espfix using paravirt hooks. If any
+ * non-paravirt system ever shows up that does *not* have the
+ * ESPFIX issue, we can change this.
+ */
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_PARAVIRT
+ do {
+ extern void native_iret(void);
+ if (pv_cpu_ops.iret == native_iret)
+ set_cpu_bug(c, X86_BUG_ESPFIX);
+ } while (0);
+# else
+ set_cpu_bug(c, X86_BUG_ESPFIX);
+# endif
+#endif
}
static void x86_init_cache_qos(struct cpuinfo_x86 *c)
@@ -1076,12 +1107,12 @@
struct tss_struct *tss;
int cpu;
+ if (!boot_cpu_has(X86_FEATURE_SEP))
+ return;
+
cpu = get_cpu();
tss = &per_cpu(cpu_tss, cpu);
- if (!boot_cpu_has(X86_FEATURE_SEP))
- goto out;
-
/*
* We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
* see the big comment in struct x86_hw_tss's definition.
@@ -1096,7 +1127,6 @@
wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
-out:
put_cpu();
}
#endif
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 1f7fdb9..f71a349 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -152,9 +152,9 @@
* the TLB when any changes are made to any of the page table entries.
* The operating system must reload CR3 to cause the TLB to be flushed"
*
- * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
- * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
- * to be modified
+ * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h
+ * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+ * to be modified.
*/
if (c->x86 == 5 && c->x86_model == 9) {
pr_info("Disabling PGE capability bit\n");
@@ -456,7 +456,7 @@
set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
}
- if (cpu_has_xmm2)
+ if (cpu_has(c, X86_FEATURE_XMM2))
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
if (boot_cpu_has(X86_FEATURE_DS)) {
@@ -468,7 +468,7 @@
set_cpu_cap(c, X86_FEATURE_PEBS);
}
- if (c->x86 == 6 && cpu_has_clflush &&
+ if (c->x86 == 6 && boot_cpu_has(X86_FEATURE_CLFLUSH) &&
(c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
set_cpu_bug(c, X86_BUG_CLFLUSH_MONITOR);
diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c
index f8c81ba..b1086f7 100644
--- a/arch/x86/kernel/cpu/mtrr/cyrix.c
+++ b/arch/x86/kernel/cpu/mtrr/cyrix.c
@@ -137,7 +137,7 @@
u32 cr0;
/* Save value of CR4 and clear Page Global Enable (bit 7) */
- if (cpu_has_pge) {
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
cr4 = __read_cr4();
__write_cr4(cr4 & ~X86_CR4_PGE);
}
@@ -170,7 +170,7 @@
write_cr0(read_cr0() & ~X86_CR0_CD);
/* Restore value of CR4 */
- if (cpu_has_pge)
+ if (boot_cpu_has(X86_FEATURE_PGE))
__write_cr4(cr4);
}
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 19f5736..16e37a25 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@
pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
}
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ prepare_set();
+
+ pat_init();
+
+ post_set();
+ local_irq_restore(flags);
+}
+
/* Grab all of the MTRR state for this CPU into *state */
bool __init get_mtrr_state(void)
{
struct mtrr_var_range *vrs;
- unsigned long flags;
unsigned lo, dummy;
unsigned int i;
@@ -481,15 +494,6 @@
mtrr_state_set = 1;
- /* PAT setup for BP. We need to go through sync steps here */
- local_irq_save(flags);
- prepare_set();
-
- pat_init();
-
- post_set();
- local_irq_restore(flags);
-
return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
}
@@ -741,7 +745,7 @@
wbinvd();
/* Save value of CR4 and clear Page Global Enable (bit 7) */
- if (cpu_has_pge) {
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
cr4 = __read_cr4();
__write_cr4(cr4 & ~X86_CR4_PGE);
}
@@ -771,7 +775,7 @@
write_cr0(read_cr0() & ~X86_CR0_CD);
/* Restore value of CR4 */
- if (cpu_has_pge)
+ if (boot_cpu_has(X86_FEATURE_PGE))
__write_cr4(cr4);
raw_spin_unlock(&set_atomicity_lock);
}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 10f8d47..7d393ec 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@
/* BIOS may override */
__mtrr_enabled = get_mtrr_state();
+ if (mtrr_enabled())
+ mtrr_bp_pat_init();
+
if (mtrr_cleanup(phys_addr)) {
changed_by_mtrr_cleanup = 1;
mtrr_if->set_all();
@@ -759,8 +762,16 @@
}
}
- if (!mtrr_enabled())
+ if (!mtrr_enabled()) {
pr_info("MTRR: Disabled\n");
+
+ /*
+ * PAT initialization relies on MTRR's rendezvous handler.
+ * Skip PAT init until the handler can initialize both
+ * features independently.
+ */
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+ }
}
void mtrr_ap_init(void)
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884d..6c7ced0 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@
void fill_mtrr_var_range(unsigned int index,
u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
extern void set_mtrr_ops(const struct mtrr_ops *ops);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 364e583..8cac429 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -94,7 +94,7 @@
*/
static uint32_t __init vmware_platform(void)
{
- if (cpu_has_hypervisor) {
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
unsigned int eax;
unsigned int hyper_vendor_id[3];
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index a1f0e4a..7282c2e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -773,7 +773,6 @@
.mask = HPET_MASK,
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
.resume = hpet_resume_counter,
- .archdata = { .vclock_mode = VCLOCK_HPET },
};
static int hpet_clocksource_register(void)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 8079508..dc1207e 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -522,7 +522,7 @@
if (boot_cpu_data.cpuid_level < 0)
return 0; /* So we don't blow up on old processors */
- if (cpu_has_hypervisor)
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
return 0;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6cbab31..50337ea 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -282,7 +282,7 @@
struct fpu *next_fpu = &next->fpu;
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
- unsigned fsindex, gsindex;
+ unsigned prev_fsindex, prev_gsindex;
fpu_switch_t fpu_switch;
fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu);
@@ -292,8 +292,8 @@
*
* (e.g. xen_load_tls())
*/
- savesegment(fs, fsindex);
- savesegment(gs, gsindex);
+ savesegment(fs, prev_fsindex);
+ savesegment(gs, prev_gsindex);
/*
* Load TLS before restoring any segments so that segment loads
@@ -336,66 +336,104 @@
* Switch FS and GS.
*
* These are even more complicated than DS and ES: they have
- * 64-bit bases are that controlled by arch_prctl. Those bases
- * only differ from the values in the GDT or LDT if the selector
- * is 0.
+ * 64-bit bases are that controlled by arch_prctl. The bases
+ * don't necessarily match the selectors, as user code can do
+ * any number of things to cause them to be inconsistent.
*
- * Loading the segment register resets the hidden base part of
- * the register to 0 or the value from the GDT / LDT. If the
- * next base address zero, writing 0 to the segment register is
- * much faster than using wrmsr to explicitly zero the base.
+ * We don't promise to preserve the bases if the selectors are
+ * nonzero. We also don't promise to preserve the base if the
+ * selector is zero and the base doesn't match whatever was
+ * most recently passed to ARCH_SET_FS/GS. (If/when the
+ * FSGSBASE instructions are enabled, we'll need to offer
+ * stronger guarantees.)
*
- * The thread_struct.fs and thread_struct.gs values are 0
- * if the fs and gs bases respectively are not overridden
- * from the values implied by fsindex and gsindex. They
- * are nonzero, and store the nonzero base addresses, if
- * the bases are overridden.
- *
- * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
- * be impossible.
- *
- * Therefore we need to reload the segment registers if either
- * the old or new selector is nonzero, and we need to override
- * the base address if next thread expects it to be overridden.
- *
- * This code is unnecessarily slow in the case where the old and
- * new indexes are zero and the new base is nonzero -- it will
- * unnecessarily write 0 to the selector before writing the new
- * base address.
- *
- * Note: This all depends on arch_prctl being the only way that
- * user code can override the segment base. Once wrfsbase and
- * wrgsbase are enabled, most of this code will need to change.
+ * As an invariant,
+ * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) is
+ * impossible.
*/
- if (unlikely(fsindex | next->fsindex | prev->fs)) {
+ if (next->fsindex) {
+ /* Loading a nonzero value into FS sets the index and base. */
loadsegment(fs, next->fsindex);
-
- /*
- * If user code wrote a nonzero value to FS, then it also
- * cleared the overridden base address.
- *
- * XXX: if user code wrote 0 to FS and cleared the base
- * address itself, we won't notice and we'll incorrectly
- * restore the prior base address next time we reschdule
- * the process.
- */
- if (fsindex)
- prev->fs = 0;
+ } else {
+ if (next->fs) {
+ /* Next index is zero but next base is nonzero. */
+ if (prev_fsindex)
+ loadsegment(fs, 0);
+ wrmsrl(MSR_FS_BASE, next->fs);
+ } else {
+ /* Next base and index are both zero. */
+ if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+ /*
+ * We don't know the previous base and can't
+ * find out without RDMSR. Forcibly clear it.
+ */
+ loadsegment(fs, __USER_DS);
+ loadsegment(fs, 0);
+ } else {
+ /*
+ * If the previous index is zero and ARCH_SET_FS
+ * didn't change the base, then the base is
+ * also zero and we don't need to do anything.
+ */
+ if (prev->fs || prev_fsindex)
+ loadsegment(fs, 0);
+ }
+ }
}
- if (next->fs)
- wrmsrl(MSR_FS_BASE, next->fs);
- prev->fsindex = fsindex;
+ /*
+ * Save the old state and preserve the invariant.
+ * NB: if prev_fsindex == 0, then we can't reliably learn the base
+ * without RDMSR because Intel user code can zero it without telling
+ * us and AMD user code can program any 32-bit value without telling
+ * us.
+ */
+ if (prev_fsindex)
+ prev->fs = 0;
+ prev->fsindex = prev_fsindex;
- if (unlikely(gsindex | next->gsindex | prev->gs)) {
+ if (next->gsindex) {
+ /* Loading a nonzero value into GS sets the index and base. */
load_gs_index(next->gsindex);
-
- /* This works (and fails) the same way as fsindex above. */
- if (gsindex)
- prev->gs = 0;
+ } else {
+ if (next->gs) {
+ /* Next index is zero but next base is nonzero. */
+ if (prev_gsindex)
+ load_gs_index(0);
+ wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
+ } else {
+ /* Next base and index are both zero. */
+ if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+ /*
+ * We don't know the previous base and can't
+ * find out without RDMSR. Forcibly clear it.
+ *
+ * This contains a pointless SWAPGS pair.
+ * Fixing it would involve an explicit check
+ * for Xen or a new pvop.
+ */
+ load_gs_index(__USER_DS);
+ load_gs_index(0);
+ } else {
+ /*
+ * If the previous index is zero and ARCH_SET_GS
+ * didn't change the base, then the base is
+ * also zero and we don't need to do anything.
+ */
+ if (prev->gs || prev_gsindex)
+ load_gs_index(0);
+ }
+ }
}
- if (next->gs)
- wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
- prev->gsindex = gsindex;
+ /*
+ * Save the old state and preserve the invariant.
+ * NB: if prev_gsindex == 0, then we can't reliably learn the base
+ * without RDMSR because Intel user code can zero it without telling
+ * us and AMD user code can program any 32-bit value without telling
+ * us.
+ */
+ if (prev_gsindex)
+ prev->gs = 0;
+ prev->gsindex = prev_gsindex;
switch_fpu_finish(next_fpu, fpu_switch);
@@ -566,10 +604,10 @@
break;
case ARCH_GET_FS: {
unsigned long base;
- if (task->thread.fsindex == FS_TLS_SEL)
- base = read_32bit_tls(task, FS_TLS);
- else if (doit)
+ if (doit)
rdmsrl(MSR_FS_BASE, base);
+ else if (task->thread.fsindex == FS_TLS_SEL)
+ base = read_32bit_tls(task, FS_TLS);
else
base = task->thread.fs;
ret = put_user(base, (unsigned long __user *)addr);
@@ -577,16 +615,11 @@
}
case ARCH_GET_GS: {
unsigned long base;
- unsigned gsindex;
- if (task->thread.gsindex == GS_TLS_SEL)
+ if (doit)
+ rdmsrl(MSR_KERNEL_GS_BASE, base);
+ else if (task->thread.gsindex == GS_TLS_SEL)
base = read_32bit_tls(task, GS_TLS);
- else if (doit) {
- savesegment(gs, gsindex);
- if (gsindex)
- rdmsrl(MSR_KERNEL_GS_BASE, base);
- else
- base = task->thread.gs;
- } else
+ else
base = task->thread.gs;
ret = put_user(base, (unsigned long __user *)addr);
break;
diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c
index ab40954..f386bad 100644
--- a/arch/x86/kernel/tce_64.c
+++ b/arch/x86/kernel/tce_64.c
@@ -40,7 +40,7 @@
static inline void flush_tce(void* tceaddr)
{
/* a single tce can't cross a cache line */
- if (cpu_has_clflush)
+ if (boot_cpu_has(X86_FEATURE_CLFLUSH))
clflush(tceaddr);
else
wbinvd();
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 70e95d0..bc1e0b6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3836,7 +3836,8 @@
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, false,
- cpu_has_gbpages, true, true);
+ boot_cpu_has(X86_FEATURE_GBPAGES),
+ true, true);
else
__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 2f1ea2f..b72743c 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -809,8 +809,7 @@
#define host_clocks \
{VCLOCK_NONE, "none"}, \
- {VCLOCK_TSC, "tsc"}, \
- {VCLOCK_HPET, "hpet"} \
+ {VCLOCK_TSC, "tsc"} \
TRACE_EVENT(kvm_update_master_clock,
TP_PROTO(bool use_master_clock, unsigned int host_clock, bool offset_matched),
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 91d93b9..b559d92 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -612,7 +612,7 @@
{
stac();
#ifdef CONFIG_X86_INTEL_USERCOPY
- if (n > 64 && cpu_has_xmm2)
+ if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
n = __copy_user_zeroing_intel_nocache(to, from, n);
else
__copy_user_zeroing(to, from, n);
@@ -629,7 +629,7 @@
{
stac();
#ifdef CONFIG_X86_INTEL_USERCOPY
- if (n > 64 && cpu_has_xmm2)
+ if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
n = __copy_user_intel_nocache(to, from, n);
else
__copy_user(to, from, n);
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 740d7ac..14a9505 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -162,7 +162,7 @@
unsigned long ps = memparse(opt, &opt);
if (ps == PMD_SIZE) {
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
- } else if (ps == PUD_SIZE && cpu_has_gbpages) {
+ } else if (ps == PUD_SIZE && boot_cpu_has(X86_FEATURE_GBPAGES)) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
} else {
printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n",
@@ -177,7 +177,7 @@
static __init int gigantic_pages_init(void)
{
/* With compaction or CMA we can allocate gigantic pages at runtime */
- if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
+ if (boot_cpu_has(X86_FEATURE_GBPAGES) && !size_to_hstate(1UL << PUD_SHIFT))
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
return 0;
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 9d56f27..372aad2 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -157,23 +157,23 @@
* This will simplify cpa(), which otherwise needs to support splitting
* large pages into small in interrupt context, etc.
*/
- if (cpu_has_pse && !debug_pagealloc_enabled())
+ if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled())
page_size_mask |= 1 << PG_LEVEL_2M;
#endif
/* Enable PSE if available */
- if (cpu_has_pse)
+ if (boot_cpu_has(X86_FEATURE_PSE))
cr4_set_bits_and_update_boot(X86_CR4_PSE);
/* Enable PGE if available */
- if (cpu_has_pge) {
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
cr4_set_bits_and_update_boot(X86_CR4_PGE);
__supported_pte_mask |= _PAGE_GLOBAL;
} else
__supported_pte_mask &= ~_PAGE_GLOBAL;
/* Enable 1 GB linear kernel mappings if available: */
- if (direct_gbpages && cpu_has_gbpages) {
+ if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
printk(KERN_INFO "Using GB pages for direct mapping\n");
page_size_mask |= 1 << PG_LEVEL_1G;
} else {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bd7a9b9..85af914 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -284,7 +284,7 @@
*/
mapping_iter = 1;
- if (!cpu_has_pse)
+ if (!boot_cpu_has(X86_FEATURE_PSE))
use_pse = 0;
repeat:
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 214afda..89d9747 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1295,7 +1295,7 @@
struct vmem_altmap *altmap = to_vmem_altmap(start);
int err;
- if (cpu_has_pse)
+ if (boot_cpu_has(X86_FEATURE_PSE))
err = vmemmap_populate_hugepages(start, end, node, altmap);
else if (altmap) {
pr_err_once("%s: no cpu support for altmap allocations\n",
@@ -1338,7 +1338,7 @@
}
get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
- if (!cpu_has_pse) {
+ if (!boot_cpu_has(X86_FEATURE_PSE)) {
next = (addr + PAGE_SIZE) & PAGE_MASK;
pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd))
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0d8d53d..f089491 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -378,7 +378,7 @@
int __init arch_ioremap_pud_supported(void)
{
#ifdef CONFIG_X86_64
- return cpu_has_gbpages;
+ return boot_cpu_has(X86_FEATURE_GBPAGES);
#else
return 0;
#endif
@@ -386,7 +386,7 @@
int __init arch_ioremap_pmd_supported(void)
{
- return cpu_has_pse;
+ return boot_cpu_has(X86_FEATURE_PSE);
}
/*
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 01be9ec..bbf462f 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1055,7 +1055,7 @@
/*
* Map everything starting from the Gb boundary, possibly with 1G pages
*/
- while (cpu_has_gbpages && end - start >= PUD_SIZE) {
+ while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
massage_pgprot(pud_pgprot)));
@@ -1460,7 +1460,7 @@
* error case we fall back to cpa_flush_all (which uses
* WBINVD):
*/
- if (!ret && cpu_has_clflush) {
+ if (!ret && boot_cpu_has(X86_FEATURE_CLFLUSH)) {
if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
cpa_flush_array(addr, numpages, cache,
cpa.flags, pages);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index faec01e..fb0604f 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -40,11 +40,22 @@
static bool boot_cpu_done;
static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
+static void init_cache_modes(void);
-static inline void pat_disable(const char *reason)
+void pat_disable(const char *reason)
{
+ if (!__pat_enabled)
+ return;
+
+ if (boot_cpu_done) {
+ WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
+ return;
+ }
+
__pat_enabled = 0;
pr_info("x86/PAT: %s\n", reason);
+
+ init_cache_modes();
}
static int __init nopat(char *str)
@@ -181,7 +192,7 @@
* configuration.
* Using lower indices is preferred, so we start with highest index.
*/
-void pat_init_cache_modes(u64 pat)
+static void __init_cache_modes(u64 pat)
{
enum page_cache_mode cache;
char pat_msg[33];
@@ -202,14 +213,11 @@
{
u64 tmp_pat;
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
pat_disable("PAT not supported by CPU.");
return;
}
- if (!pat_enabled())
- goto done;
-
rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
if (!tmp_pat) {
pat_disable("PAT MSR is 0, disabled.");
@@ -218,16 +226,12 @@
wrmsrl(MSR_IA32_CR_PAT, pat);
-done:
- pat_init_cache_modes(pat);
+ __init_cache_modes(pat);
}
static void pat_ap_init(u64 pat)
{
- if (!pat_enabled())
- return;
-
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
/*
* If this happens we are on a secondary CPU, but switched to
* PAT on the boot CPU. We have no way to undo PAT.
@@ -238,18 +242,32 @@
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-void pat_init(void)
+static void init_cache_modes(void)
{
- u64 pat;
- struct cpuinfo_x86 *c = &boot_cpu_data;
+ u64 pat = 0;
+ static int init_cm_done;
- if (!pat_enabled()) {
+ if (init_cm_done)
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PAT)) {
+ /*
+ * CPU supports PAT. Set PAT table to be consistent with
+ * PAT MSR. This case supports "nopat" boot option, and
+ * virtual machine environments which support PAT without
+ * MTRRs. In specific, Xen has unique setup to PAT MSR.
+ *
+ * If PAT MSR returns 0, it is considered invalid and emulates
+ * as No PAT.
+ */
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ }
+
+ if (!pat) {
/*
* No PAT. Emulate the PAT table that corresponds to the two
- * cache bits, PWT (Write Through) and PCD (Cache Disable). This
- * setup is the same as the BIOS default setup when the system
- * has PAT but the "nopat" boot option has been specified. This
- * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+ * cache bits, PWT (Write Through) and PCD (Cache Disable).
+ * This setup is also the same as the BIOS default setup.
*
* PTE encoding:
*
@@ -266,10 +284,36 @@
*/
pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+ }
- } else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
- (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
- ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+ __init_cache_modes(pat);
+
+ init_cm_done = 1;
+}
+
+/**
+ * pat_init - Initialize PAT MSR and PAT table
+ *
+ * This function initializes PAT MSR and PAT table with an OS-defined value
+ * to enable additional cache attributes, WC and WT.
+ *
+ * This function must be called on all CPUs using the specific sequence of
+ * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
+ * procedure for PAT.
+ */
+void pat_init(void)
+{
+ u64 pat;
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!pat_enabled()) {
+ init_cache_modes();
+ return;
+ }
+
+ if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+ (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+ ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
/*
* PAT support with the lower four entries. Intel Pentium 2,
* 3, M, and 4 are affected by PAT errata, which makes the
@@ -734,25 +778,6 @@
if (file->f_flags & O_DSYNC)
pcm = _PAGE_CACHE_MODE_UC_MINUS;
-#ifdef CONFIG_X86_32
- /*
- * On the PPro and successors, the MTRRs are used to set
- * memory types for physical addresses outside main memory,
- * so blindly setting UC or PWT on those pages is wrong.
- * For Pentiums and earlier, the surround logic should disable
- * caching for the high addresses through the KEN pin, but
- * we maintain the tradition of paranoia in this code.
- */
- if (!pat_enabled() &&
- !(boot_cpu_has(X86_FEATURE_MTRR) ||
- boot_cpu_has(X86_FEATURE_K6_MTRR) ||
- boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
- boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
- (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
- pcm = _PAGE_CACHE_MODE_UC;
- }
-#endif
-
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
cachemode2protval(pcm));
return 1;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 0e07e09..25171e9 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -636,7 +636,7 @@
__u8 cpu_model = boot_cpu_data.x86_model;
struct op_x86_model_spec *spec = &op_ppro_spec; /* default */
- if (force_cpu_type == arch_perfmon && cpu_has_arch_perfmon)
+ if (force_cpu_type == arch_perfmon && boot_cpu_has(X86_FEATURE_ARCH_PERFMON))
return 0;
/*
@@ -761,7 +761,7 @@
if (cpu_type)
break;
- if (!cpu_has_arch_perfmon)
+ if (!boot_cpu_has(X86_FEATURE_ARCH_PERFMON))
return -ENODEV;
/* use arch perfmon as fallback */
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index d90528e..350f709 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -75,7 +75,7 @@
u64 val;
int i;
- if (cpu_has_arch_perfmon) {
+ if (boot_cpu_has(X86_FEATURE_ARCH_PERFMON)) {
union cpuid10_eax eax;
eax.full = cpuid_eax(0xa);
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 291226b..9f14bd3 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -106,7 +106,7 @@
* normal page tables.
* NOTE: We can mark everything as executable here
*/
- if (cpu_has_pse) {
+ if (boot_cpu_has(X86_FEATURE_PSE)) {
set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC));
pfn += PTRS_PER_PTE;
} else {
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 880862c..9b8f1ea 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -75,7 +75,6 @@
#include <asm/mach_traps.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
-#include <asm/pat.h>
#include <asm/cpu.h>
#ifdef CONFIG_ACPI
@@ -1469,10 +1468,10 @@
* For BSP, PSE PGE are set in probe_page_size_mask(), for APs
* set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu().
*/
- if (cpu_has_pse)
+ if (boot_cpu_has(X86_FEATURE_PSE))
cr4_set_bits_and_update_boot(X86_CR4_PSE);
- if (cpu_has_pge)
+ if (boot_cpu_has(X86_FEATURE_PGE))
cr4_set_bits_and_update_boot(X86_CR4_PGE);
}
@@ -1511,7 +1510,6 @@
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
- u64 pat;
int rc;
if (!xen_start_info)
@@ -1618,13 +1616,6 @@
xen_start_info->nr_pages);
xen_reserve_special_pages();
- /*
- * Modify the cache mode translation tables to match Xen's PAT
- * configuration.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- pat_init_cache_modes(pat);
-
/* keep using Xen gdt for now; no urgent need to change it */
#ifdef CONFIG_X86_32
diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c
index 3bbdcc7..7d7a39b4 100644
--- a/crypto/asymmetric_keys/pkcs7_trust.c
+++ b/crypto/asymmetric_keys/pkcs7_trust.c
@@ -178,6 +178,8 @@
int cached_ret = -ENOKEY;
int ret;
+ *_trusted = false;
+
for (p = pkcs7->certs; p; p = p->next)
p->seen = false;
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 6743ff7..059f7c3 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -72,7 +72,7 @@
{
#if defined(CONFIG_X86)
- if (cpu_has_clflush) {
+ if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
drm_cache_flush_clflush(pages, num_pages);
return;
}
@@ -105,7 +105,7 @@
drm_clflush_sg(struct sg_table *st)
{
#if defined(CONFIG_X86)
- if (cpu_has_clflush) {
+ if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
struct sg_page_iter sg_iter;
mb();
@@ -129,7 +129,7 @@
drm_clflush_virt_range(void *addr, unsigned long length)
{
#if defined(CONFIG_X86)
- if (cpu_has_clflush) {
+ if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
const int size = boot_cpu_data.x86_clflush_size;
void *end = addr + length;
addr = (void *)(((unsigned long)addr) & -size);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3d31d3a..aaec8ae 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1732,7 +1732,7 @@
if (args->flags & ~(I915_MMAP_WC))
return -EINVAL;
- if (args->flags & I915_MMAP_WC && !cpu_has_pat)
+ if (args->flags & I915_MMAP_WC && !boot_cpu_has(X86_FEATURE_PAT))
return -ENODEV;
obj = drm_gem_object_lookup(dev, file, args->handle);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 1328bc5..b845f46 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -488,7 +488,7 @@
ret = relocate_entry_cpu(obj, reloc, target_offset);
else if (obj->map_and_fenceable)
ret = relocate_entry_gtt(obj, reloc, target_offset);
- else if (cpu_has_clflush)
+ else if (static_cpu_has(X86_FEATURE_CLFLUSH))
ret = relocate_entry_clflush(obj, reloc, target_offset);
else {
WARN_ONCE(1, "Impossible case in relocation handling\n");
diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c
index 36544c4..303d0c9 100644
--- a/drivers/hwmon/max1111.c
+++ b/drivers/hwmon/max1111.c
@@ -85,6 +85,9 @@
int max1111_read_channel(int channel)
{
+ if (!the_max1111 || !the_max1111->spi)
+ return -ENODEV;
+
return max1111_read(&the_max1111->spi->dev, channel);
}
EXPORT_SYMBOL(max1111_read_channel);
@@ -258,6 +261,9 @@
{
struct max1111_data *data = spi_get_drvdata(spi);
+#ifdef CONFIG_SHARPSL_PM
+ the_max1111 = NULL;
+#endif
hwmon_device_unregister(data->hwmon_dev);
sysfs_remove_group(&spi->dev.kobj, &max1110_attr_group);
sysfs_remove_group(&spi->dev.kobj, &max1111_attr_group);
diff --git a/drivers/ide/icside.c b/drivers/ide/icside.c
index 9f0a48e..80e933b 100644
--- a/drivers/ide/icside.c
+++ b/drivers/ide/icside.c
@@ -451,7 +451,7 @@
return ret;
}
-static const struct ide_port_info icside_v6_port_info __initconst = {
+static const struct ide_port_info icside_v6_port_info = {
.init_dma = icside_dma_off_init,
.port_ops = &icside_v6_no_dma_port_ops,
.host_flags = IDE_HFLAG_SERIALIZE | IDE_HFLAG_MMIO,
diff --git a/drivers/ide/palm_bk3710.c b/drivers/ide/palm_bk3710.c
index 8012e43..46427ea 100644
--- a/drivers/ide/palm_bk3710.c
+++ b/drivers/ide/palm_bk3710.c
@@ -325,6 +325,8 @@
clk_enable(clk);
rate = clk_get_rate(clk);
+ if (!rate)
+ return -EINVAL;
/* NOTE: round *down* to meet minimum timings; we count in clocks */
ideclk_period = 1000000000UL / rate;
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index adc162c..6e9042e 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -603,7 +603,7 @@
* doing this.
*/
get_online_cpus();
- if (cpu_has_pge) { /* We have a broader idea of "global". */
+ if (boot_cpu_has(X86_FEATURE_PGE)) { /* We have a broader idea of "global". */
/* Remember that this was originally set (for cleanup). */
cpu_had_pge = 1;
/*
diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c
index 5fbda7b..9cf4f84 100644
--- a/drivers/staging/unisys/visorbus/visorchipset.c
+++ b/drivers/staging/unisys/visorbus/visorchipset.c
@@ -2425,7 +2425,7 @@
{
unsigned int eax, ebx, ecx, edx;
- if (cpu_has_hypervisor) {
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
/* check the ID */
cpuid(UNISYS_SPAR_LEAF_ID, &eax, &ebx, &ecx, &edx);
return (ebx == UNISYS_SPAR_ID_EBX) &&
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 5191121..1669f62 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -343,13 +343,12 @@
struct dlm_cluster *cl = NULL;
struct dlm_spaces *sps = NULL;
struct dlm_comms *cms = NULL;
- void *gps = NULL;
cl = kzalloc(sizeof(struct dlm_cluster), GFP_NOFS);
sps = kzalloc(sizeof(struct dlm_spaces), GFP_NOFS);
cms = kzalloc(sizeof(struct dlm_comms), GFP_NOFS);
- if (!cl || !gps || !sps || !cms)
+ if (!cl || !sps || !cms)
goto fail;
config_group_init_type_name(&cl->group, name, &cluster_type);
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index b47ebd1..c73425de 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -9,6 +9,7 @@
TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
+TARGETS_C_64BIT_ONLY := fsgsbase
TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
new file mode 100644
index 0000000..5b2b4b3
--- /dev/null
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -0,0 +1,398 @@
+/*
+ * fsgsbase.c, an fsgsbase test
+ * Copyright (c) 2014-2016 Andy Lutomirski
+ * GPL v2
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <err.h>
+#include <sys/user.h>
+#include <asm/prctl.h>
+#include <sys/prctl.h>
+#include <signal.h>
+#include <limits.h>
+#include <sys/ucontext.h>
+#include <sched.h>
+#include <linux/futex.h>
+#include <pthread.h>
+#include <asm/ldt.h>
+#include <sys/mman.h>
+
+#ifndef __x86_64__
+# error This test is 64-bit only
+#endif
+
+static volatile sig_atomic_t want_segv;
+static volatile unsigned long segv_addr;
+
+static int nerrs;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+ struct sigaction sa;
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_handler = SIG_DFL;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static void sigsegv(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+ if (!want_segv) {
+ clearhandler(SIGSEGV);
+ return; /* Crash cleanly. */
+ }
+
+ want_segv = false;
+ segv_addr = (unsigned long)si->si_addr;
+
+ ctx->uc_mcontext.gregs[REG_RIP] += 4; /* Skip the faulting mov */
+
+}
+
+enum which_base { FS, GS };
+
+static unsigned long read_base(enum which_base which)
+{
+ unsigned long offset;
+ /*
+ * Unless we have FSGSBASE, there's no direct way to do this from
+ * user mode. We can get at it indirectly using signals, though.
+ */
+
+ want_segv = true;
+
+ offset = 0;
+ if (which == FS) {
+ /* Use a constant-length instruction here. */
+ asm volatile ("mov %%fs:(%%rcx), %%rax" : : "c" (offset) : "rax");
+ } else {
+ asm volatile ("mov %%gs:(%%rcx), %%rax" : : "c" (offset) : "rax");
+ }
+ if (!want_segv)
+ return segv_addr + offset;
+
+ /*
+ * If that didn't segfault, try the other end of the address space.
+ * Unless we get really unlucky and run into the vsyscall page, this
+ * is guaranteed to segfault.
+ */
+
+ offset = (ULONG_MAX >> 1) + 1;
+ if (which == FS) {
+ asm volatile ("mov %%fs:(%%rcx), %%rax"
+ : : "c" (offset) : "rax");
+ } else {
+ asm volatile ("mov %%gs:(%%rcx), %%rax"
+ : : "c" (offset) : "rax");
+ }
+ if (!want_segv)
+ return segv_addr + offset;
+
+ abort();
+}
+
+static void check_gs_value(unsigned long value)
+{
+ unsigned long base;
+ unsigned short sel;
+
+ printf("[RUN]\tARCH_SET_GS to 0x%lx\n", value);
+ if (syscall(SYS_arch_prctl, ARCH_SET_GS, value) != 0)
+ err(1, "ARCH_SET_GS");
+
+ asm volatile ("mov %%gs, %0" : "=rm" (sel));
+ base = read_base(GS);
+ if (base == value) {
+ printf("[OK]\tGSBASE was set as expected (selector 0x%hx)\n",
+ sel);
+ } else {
+ nerrs++;
+ printf("[FAIL]\tGSBASE was not as expected: got 0x%lx (selector 0x%hx)\n",
+ base, sel);
+ }
+
+ if (syscall(SYS_arch_prctl, ARCH_GET_GS, &base) != 0)
+ err(1, "ARCH_GET_GS");
+ if (base == value) {
+ printf("[OK]\tARCH_GET_GS worked as expected (selector 0x%hx)\n",
+ sel);
+ } else {
+ nerrs++;
+ printf("[FAIL]\tARCH_GET_GS was not as expected: got 0x%lx (selector 0x%hx)\n",
+ base, sel);
+ }
+}
+
+static void mov_0_gs(unsigned long initial_base, bool schedule)
+{
+ unsigned long base, arch_base;
+
+ printf("[RUN]\tARCH_SET_GS to 0x%lx then mov 0 to %%gs%s\n", initial_base, schedule ? " and schedule " : "");
+ if (syscall(SYS_arch_prctl, ARCH_SET_GS, initial_base) != 0)
+ err(1, "ARCH_SET_GS");
+
+ if (schedule)
+ usleep(10);
+
+ asm volatile ("mov %0, %%gs" : : "rm" (0));
+ base = read_base(GS);
+ if (syscall(SYS_arch_prctl, ARCH_GET_GS, &arch_base) != 0)
+ err(1, "ARCH_GET_GS");
+ if (base == arch_base) {
+ printf("[OK]\tGSBASE is 0x%lx\n", base);
+ } else {
+ nerrs++;
+ printf("[FAIL]\tGSBASE changed to 0x%lx but kernel reports 0x%lx\n", base, arch_base);
+ }
+}
+
+static volatile unsigned long remote_base;
+static volatile bool remote_hard_zero;
+static volatile unsigned int ftx;
+
+/*
+ * ARCH_SET_FS/GS(0) may or may not program a selector of zero. HARD_ZERO
+ * means to force the selector to zero to improve test coverage.
+ */
+#define HARD_ZERO 0xa1fa5f343cb85fa4
+
+static void do_remote_base()
+{
+ unsigned long to_set = remote_base;
+ bool hard_zero = false;
+ if (to_set == HARD_ZERO) {
+ to_set = 0;
+ hard_zero = true;
+ }
+
+ if (syscall(SYS_arch_prctl, ARCH_SET_GS, to_set) != 0)
+ err(1, "ARCH_SET_GS");
+
+ if (hard_zero)
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0));
+
+ unsigned short sel;
+ asm volatile ("mov %%gs, %0" : "=rm" (sel));
+ printf("\tother thread: ARCH_SET_GS(0x%lx)%s -- sel is 0x%hx\n",
+ to_set, hard_zero ? " and clear gs" : "", sel);
+}
+
+void do_unexpected_base(void)
+{
+ /*
+ * The goal here is to try to arrange for GS == 0, GSBASE !=
+ * 0, and for the the kernel the think that GSBASE == 0.
+ *
+ * To make the test as reliable as possible, this uses
+ * explicit descriptorss. (This is not the only way. This
+ * could use ARCH_SET_GS with a low, nonzero base, but the
+ * relevant side effect of ARCH_SET_GS could change.)
+ */
+
+ /* Step 1: tell the kernel that we have GSBASE == 0. */
+ if (syscall(SYS_arch_prctl, ARCH_SET_GS, 0) != 0)
+ err(1, "ARCH_SET_GS");
+
+ /* Step 2: change GSBASE without telling the kernel. */
+ struct user_desc desc = {
+ .entry_number = 0,
+ .base_addr = 0xBAADF00D,
+ .limit = 0xfffff,
+ .seg_32bit = 1,
+ .contents = 0, /* Data, grow-up */
+ .read_exec_only = 0,
+ .limit_in_pages = 1,
+ .seg_not_present = 0,
+ .useable = 0
+ };
+ if (syscall(SYS_modify_ldt, 1, &desc, sizeof(desc)) == 0) {
+ printf("\tother thread: using LDT slot 0\n");
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0x7));
+ } else {
+ /* No modify_ldt for us (configured out, perhaps) */
+
+ struct user_desc *low_desc = mmap(
+ NULL, sizeof(desc),
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_32BIT, -1, 0);
+ memcpy(low_desc, &desc, sizeof(desc));
+
+ low_desc->entry_number = -1;
+
+ /* 32-bit set_thread_area */
+ long ret;
+ asm volatile ("int $0x80"
+ : "=a" (ret) : "a" (243), "b" (low_desc)
+ : "flags");
+ memcpy(&desc, low_desc, sizeof(desc));
+ munmap(low_desc, sizeof(desc));
+
+ if (ret != 0) {
+ printf("[NOTE]\tcould not create a segment -- test won't do anything\n");
+ return;
+ }
+ printf("\tother thread: using GDT slot %d\n", desc.entry_number);
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)((desc.entry_number << 3) | 0x3)));
+ }
+
+ /*
+ * Step 3: set the selector back to zero. On AMD chips, this will
+ * preserve GSBASE.
+ */
+
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0));
+}
+
+static void *threadproc(void *ctx)
+{
+ while (1) {
+ while (ftx == 0)
+ syscall(SYS_futex, &ftx, FUTEX_WAIT, 0, NULL, NULL, 0);
+ if (ftx == 3)
+ return NULL;
+
+ if (ftx == 1)
+ do_remote_base();
+ else if (ftx == 2)
+ do_unexpected_base();
+ else
+ errx(1, "helper thread got bad command");
+
+ ftx = 0;
+ syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+ }
+}
+
+static void set_gs_and_switch_to(unsigned long local, unsigned long remote)
+{
+ unsigned long base;
+
+ bool hard_zero = false;
+ if (local == HARD_ZERO) {
+ hard_zero = true;
+ local = 0;
+ }
+
+ printf("[RUN]\tARCH_SET_GS(0x%lx)%s, then schedule to 0x%lx\n",
+ local, hard_zero ? " and clear gs" : "", remote);
+ if (syscall(SYS_arch_prctl, ARCH_SET_GS, local) != 0)
+ err(1, "ARCH_SET_GS");
+ if (hard_zero)
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0));
+
+ if (read_base(GS) != local) {
+ nerrs++;
+ printf("[FAIL]\tGSBASE wasn't set as expected\n");
+ }
+
+ remote_base = remote;
+ ftx = 1;
+ syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+ while (ftx != 0)
+ syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0);
+
+ base = read_base(GS);
+ if (base == local) {
+ printf("[OK]\tGSBASE remained 0x%lx\n", local);
+ } else {
+ nerrs++;
+ printf("[FAIL]\tGSBASE changed to 0x%lx\n", base);
+ }
+}
+
+static void test_unexpected_base(void)
+{
+ unsigned long base;
+
+ printf("[RUN]\tARCH_SET_GS(0), clear gs, then manipulate GSBASE in a different thread\n");
+ if (syscall(SYS_arch_prctl, ARCH_SET_GS, 0) != 0)
+ err(1, "ARCH_SET_GS");
+ asm volatile ("mov %0, %%gs" : : "rm" ((unsigned short)0));
+
+ ftx = 2;
+ syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+ while (ftx != 0)
+ syscall(SYS_futex, &ftx, FUTEX_WAIT, 1, NULL, NULL, 0);
+
+ base = read_base(GS);
+ if (base == 0) {
+ printf("[OK]\tGSBASE remained 0\n");
+ } else {
+ nerrs++;
+ printf("[FAIL]\tGSBASE changed to 0x%lx\n", base);
+ }
+}
+
+int main()
+{
+ pthread_t thread;
+
+ sethandler(SIGSEGV, sigsegv, 0);
+
+ check_gs_value(0);
+ check_gs_value(1);
+ check_gs_value(0x200000000);
+ check_gs_value(0);
+ check_gs_value(0x200000000);
+ check_gs_value(1);
+
+ for (int sched = 0; sched < 2; sched++) {
+ mov_0_gs(0, !!sched);
+ mov_0_gs(1, !!sched);
+ mov_0_gs(0x200000000, !!sched);
+ }
+
+ /* Set up for multithreading. */
+
+ cpu_set_t cpuset;
+ CPU_ZERO(&cpuset);
+ CPU_SET(0, &cpuset);
+ if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+ err(1, "sched_setaffinity to CPU 0"); /* should never fail */
+
+ if (pthread_create(&thread, 0, threadproc, 0) != 0)
+ err(1, "pthread_create");
+
+ static unsigned long bases_with_hard_zero[] = {
+ 0, HARD_ZERO, 1, 0x200000000,
+ };
+
+ for (int local = 0; local < 4; local++) {
+ for (int remote = 0; remote < 4; remote++) {
+ set_gs_and_switch_to(bases_with_hard_zero[local],
+ bases_with_hard_zero[remote]);
+ }
+ }
+
+ test_unexpected_base();
+
+ ftx = 3; /* Kill the thread. */
+ syscall(SYS_futex, &ftx, FUTEX_WAKE, 0, NULL, NULL, 0);
+
+ if (pthread_join(thread, NULL) != 0)
+ err(1, "pthread_join");
+
+ return nerrs == 0 ? 0 : 1;
+}