summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/boot/header.S42
-rw-r--r--arch/x86/boot/tools/build.c172
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S6
-rw-r--r--arch/x86/ia32/ia32_signal.c2
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/nmi.h14
-rw-r--r--arch/x86/include/asm/pgtable-3level.h30
-rw-r--r--arch/x86/include/asm/uaccess.h12
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h1
-rw-r--r--arch/x86/kernel/acpi/boot.c27
-rw-r--r--arch/x86/kernel/aperture_64.c6
-rw-r--r--arch/x86/kernel/apic/io_apic.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--arch/x86/kernel/cpu/mkcapflags.pl25
-rw-r--r--arch/x86/kernel/cpu/perf_event.c11
-rw-r--r--arch/x86/kernel/cpu/perf_event.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c145
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c9
-rw-r--r--arch/x86/kernel/cpu/scattered.c2
-rw-r--r--arch/x86/kernel/kgdb.c8
-rw-r--r--arch/x86/kernel/kvmclock.c5
-rw-r--r--arch/x86/kernel/nmi_selftest.c4
-rw-r--r--arch/x86/kernel/pci-dma.c3
-rw-r--r--arch/x86/kernel/reboot.c14
-rw-r--r--arch/x86/kernel/smpboot.c16
-rw-r--r--arch/x86/kvm/mmu.c3
-rw-r--r--arch/x86/lib/csum-wrappers_64.c2
-rw-r--r--arch/x86/lib/usercopy.c4
-rw-r--r--arch/x86/lib/x86-opcode-map.txt8
-rw-r--r--arch/x86/mm/init.c3
-rw-r--r--arch/x86/mm/ioremap.c4
-rw-r--r--arch/x86/mm/pageattr.c2
-rw-r--r--arch/x86/mm/srat.c2
-rw-r--r--arch/x86/platform/mrst/early_printk_mrst.c13
-rw-r--r--arch/x86/platform/mrst/mrst.c2
-rw-r--r--arch/x86/platform/uv/tlb_uv.c1
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk14
-rw-r--r--arch/x86/um/sys_call_table_32.c4
-rw-r--r--arch/x86/xen/enlighten.c8
-rw-r--r--arch/x86/xen/p2m.c36
-rw-r--r--arch/x86/xen/setup.c3
41 files changed, 458 insertions, 215 deletions
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 8bbea6a..efe5acf 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -94,10 +94,10 @@ bs_die:
.section ".bsdata", "a"
bugger_off_msg:
- .ascii "Direct booting from floppy is no longer supported.\r\n"
- .ascii "Please use a boot loader program instead.\r\n"
+ .ascii "Direct floppy boot is not supported. "
+ .ascii "Use a boot loader program instead.\r\n"
.ascii "\n"
- .ascii "Remove disk and press any key to reboot . . .\r\n"
+ .ascii "Remove disk and press any key to reboot ...\r\n"
.byte 0
#ifdef CONFIG_EFI_STUB
@@ -111,7 +111,7 @@ coff_header:
#else
.word 0x8664 # x86-64
#endif
- .word 2 # nr_sections
+ .word 3 # nr_sections
.long 0 # TimeDateStamp
.long 0 # PointerToSymbolTable
.long 1 # NumberOfSymbols
@@ -158,8 +158,8 @@ extra_header_fields:
#else
.quad 0 # ImageBase
#endif
- .long 0x1000 # SectionAlignment
- .long 0x200 # FileAlignment
+ .long 0x20 # SectionAlignment
+ .long 0x20 # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word 0 # MajorImageVersion
@@ -200,8 +200,10 @@ extra_header_fields:
# Section table
section_table:
- .ascii ".text"
- .byte 0
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .ascii ".setup"
.byte 0
.byte 0
.long 0
@@ -217,9 +219,8 @@ section_table:
#
# The EFI application loader requires a relocation section
- # because EFI applications must be relocatable. But since
- # we don't need the loader to fixup any relocs for us, we
- # just create an empty (zero-length) .reloc section header.
+ # because EFI applications must be relocatable. The .reloc
+ # offset & size fields are filled in by build.c.
#
.ascii ".reloc"
.byte 0
@@ -233,6 +234,25 @@ section_table:
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long 0x42100040 # Characteristics (section flags)
+
+ #
+ # The offset & size fields are filled in by build.c.
+ #
+ .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)
+
#endif /* CONFIG_EFI_STUB */
# Kernel attributes; used by setup. This is part 1 of the
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 3f61f6e..4b8e165 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -50,6 +50,8 @@ typedef unsigned int u32;
u8 buf[SETUP_SECT_MAX*512];
int is_big_kernel;
+#define PECOFF_RELOC_RESERVE 0x20
+
/*----------------------------------------------------------------------*/
static const u32 crctab32[] = {
@@ -133,11 +135,103 @@ static void usage(void)
die("Usage: build setup system [> image]");
}
-int main(int argc, char ** argv)
-{
#ifdef CONFIG_EFI_STUB
- unsigned int file_sz, pe_header;
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+ unsigned int pe_header;
+ unsigned short num_sections;
+ u8 *section;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+ num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+ section = &buf[pe_header + 0xa8];
+#else
+ section = &buf[pe_header + 0xb8];
#endif
+
+ while (num_sections > 0) {
+ if (strncmp((char*)section, section_name, 8) == 0) {
+ /* section header size field */
+ put_unaligned_le32(size, section + 0x8);
+
+ /* section header vma field */
+ put_unaligned_le32(offset, section + 0xc);
+
+ /* section header 'size of initialised data' field */
+ put_unaligned_le32(size, section + 0x10);
+
+ /* section header 'file offset' field */
+ put_unaligned_le32(offset, section + 0x14);
+
+ break;
+ }
+ section += 0x28;
+ num_sections--;
+ }
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+ u32 setup_offset = 0x200;
+ u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+ u32 setup_size = reloc_offset - setup_offset;
+
+ update_pecoff_section_header(".setup", setup_offset, setup_size);
+ update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+ /*
+ * Modify .reloc section contents with a single entry. The
+ * relocation is applied to offset 10 of the relocation section.
+ */
+ put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+ put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+ unsigned int pe_header;
+ unsigned int text_sz = file_sz - text_start;
+
+ pe_header = get_unaligned_le32(&buf[0x3c]);
+
+ /* Size of image */
+ put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
+
+ /*
+ * Size of code: Subtract the size of the first sector (512 bytes)
+ * which includes the header.
+ */
+ put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Address of entry point.
+ *
+ * The EFI stub entry point is +16 bytes from the start of
+ * the .text section.
+ */
+ put_unaligned_le32(text_start + 16, &buf[pe_header + 0x28]);
+#else
+ /*
+ * Address of entry point. startup_32 is at the beginning and
+ * the 64-bit entry point (startup_64) is always 512 bytes
+ * after. The EFI stub entry point is 16 bytes after that, as
+ * the first instruction allows legacy loaders to jump over
+ * the EFI stub initialisation
+ */
+ put_unaligned_le32(text_start + 528, &buf[pe_header + 0x28]);
+#endif /* CONFIG_X86_32 */
+
+ update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+#endif /* CONFIG_EFI_STUB */
+
+int main(int argc, char ** argv)
+{
unsigned int i, sz, setup_sectors;
int c;
u32 sys_size;
@@ -163,6 +257,12 @@ int main(int argc, char ** argv)
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
+#ifdef CONFIG_EFI_STUB
+ /* Reserve 0x20 bytes for .reloc section */
+ memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+ c += PECOFF_RELOC_RESERVE;
+#endif
+
/* Pad unused space with zeros */
setup_sectors = (c + 511) / 512;
if (setup_sectors < SETUP_SECT_MIN)
@@ -170,6 +270,10 @@ int main(int argc, char ** argv)
i = setup_sectors*512;
memset(buf+c, 0, i-c);
+#ifdef CONFIG_EFI_STUB
+ update_pecoff_setup_and_reloc(i);
+#endif
+
/* Set the default root device */
put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
@@ -194,66 +298,8 @@ int main(int argc, char ** argv)
put_unaligned_le32(sys_size, &buf[0x1f4]);
#ifdef CONFIG_EFI_STUB
- file_sz = sz + i + ((sys_size * 16) - sz);
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
-
- /* Size of image */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
-
- /*
- * Subtract the size of the first section (512 bytes) which
- * includes the header and .reloc section. The remaining size
- * is that of the .text section.
- */
- file_sz -= 512;
-
- /* Size of code */
- put_unaligned_le32(file_sz, &buf[pe_header + 0x1c]);
-
-#ifdef CONFIG_X86_32
- /*
- * Address of entry point.
- *
- * The EFI stub entry point is +16 bytes from the start of
- * the .text section.
- */
- put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xb4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xb8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xbc]);
-#else
- /*
- * Address of entry point. startup_32 is at the beginning and
- * the 64-bit entry point (startup_64) is always 512 bytes
- * after. The EFI stub entry point is 16 bytes after that, as
- * the first instruction allows legacy loaders to jump over
- * the EFI stub initialisation
- */
- put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
-
- /* .text size */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
-
- /* .text vma */
- put_unaligned_le32(0x200, &buf[pe_header + 0xc4]);
-
- /* .text size of initialised data */
- put_unaligned_le32(file_sz, &buf[pe_header + 0xc8]);
-
- /* .text file offset */
- put_unaligned_le32(0x200, &buf[pe_header + 0xcc]);
-#endif /* CONFIG_X86_32 */
-#endif /* CONFIG_EFI_STUB */
+ update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
+#endif
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, stdout) != i)
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index be6d9e3..3470624 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2460,10 +2460,12 @@ ENTRY(aesni_cbc_dec)
pxor IN3, STATE4
movaps IN4, IV
#else
- pxor (INP), STATE2
- pxor 0x10(INP), STATE3
pxor IN1, STATE4
movaps IN2, IV
+ movups (INP), IN1
+ pxor IN1, STATE2
+ movups 0x10(INP), IN2
+ pxor IN2, STATE3
#endif
movups STATE1, (OUTP)
movups STATE2, 0x10(OUTP)
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index daeca56..673ac9b 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -38,7 +38,7 @@
int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
{
int err = 0;
- bool ia32 = is_ia32_task();
+ bool ia32 = test_thread_flag(TIF_IA32);
if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 340ee49..f91e80f 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -176,7 +176,7 @@
#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */
#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */
#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_DTS (7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_DTHERM (7*32+ 7) /* Digital Thermal Sensor */
#define X86_FEATURE_HW_PSTATE (7*32+ 8) /* AMD HW-PState */
/* Virtualization flags: Linux defined, word 8 */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 0e3793b..dc580c4 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -54,6 +54,20 @@ struct nmiaction {
__register_nmi_handler((t), &fn##_na); \
})
+/*
+ * For special handlers that register/unregister in the
+ * init section only. This should be considered rare.
+ */
+#define register_nmi_handler_initonly(t, fn, fg, n) \
+({ \
+ static struct nmiaction fn##_na __initdata = { \
+ .handler = (fn), \
+ .name = (n), \
+ .flags = (fg), \
+ }; \
+ __register_nmi_handler((t), &fn##_na); \
+})
+
int __register_nmi_handler(unsigned int, struct nmiaction *);
void unregister_nmi_handler(unsigned int, const char *);
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 43876f1..cb00ccc 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -47,16 +47,26 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
* they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
* operations.
*
- * Without THP if the mmap_sem is hold for reading, the
- * pmd can only transition from null to not null while pmd_read_atomic runs.
- * So there's no need of literally reading it atomically.
+ * Without THP if the mmap_sem is hold for reading, the pmd can only
+ * transition from null to not null while pmd_read_atomic runs. So
+ * we can always return atomic pmd values with this function.
*
* With THP if the mmap_sem is hold for reading, the pmd can become
- * THP or null or point to a pte (and in turn become "stable") at any
- * time under pmd_read_atomic, so it's mandatory to read it atomically
- * with cmpxchg8b.
+ * trans_huge or none or point to a pte (and in turn become "stable")
+ * at any time under pmd_read_atomic. We could read it really
+ * atomically here with a atomic64_read for the THP enabled case (and
+ * it would be a whole lot simpler), but to avoid using cmpxchg8b we
+ * only return an atomic pmdval if the low part of the pmdval is later
+ * found stable (i.e. pointing to a pte). And we're returning a none
+ * pmdval if the low part of the pmd is none. In some cases the high
+ * and low part of the pmdval returned may not be consistent if THP is
+ * enabled (the low part may point to previously mapped hugepage,
+ * while the high part may point to a more recently mapped hugepage),
+ * but pmd_none_or_trans_huge_or_clear_bad() only needs the low part
+ * of the pmd to be read atomically to decide if the pmd is unstable
+ * or not, with the only exception of when the low part of the pmd is
+ * zero in which case we return a none pmd.
*/
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
{
pmdval_t ret;
@@ -74,12 +84,6 @@ static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
return (pmd_t) { ret };
}
-#else /* CONFIG_TRANSPARENT_HUGEPAGE */
-static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
-{
- return (pmd_t) { atomic64_read((atomic64_t *)pmdp) };
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 04cd688..e1f3a17 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -33,9 +33,8 @@
#define segment_eq(a, b) ((a).seg == (b).seg)
#define user_addr_max() (current_thread_info()->addr_limit.seg)
-#define __addr_ok(addr) \
- ((unsigned long __force)(addr) < \
- (current_thread_info()->addr_limit.seg))
+#define __addr_ok(addr) \
+ ((unsigned long __force)(addr) < user_addr_max())
/*
* Test whether a block of memory is a valid user space address.
@@ -47,14 +46,14 @@
* This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
*/
-#define __range_not_ok(addr, size) \
+#define __range_not_ok(addr, size, limit) \
({ \
unsigned long flag, roksum; \
__chk_user_ptr(addr); \
asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0" \
: "=&r" (flag), "=r" (roksum) \
: "1" (addr), "g" ((long)(size)), \
- "rm" (current_thread_info()->addr_limit.seg)); \
+ "rm" (limit)); \
flag; \
})
@@ -77,7 +76,8 @@
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*/
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+#define access_ok(type, addr, size) \
+ (likely(__range_not_ok(addr, size, user_addr_max()) == 0))
/*
* The exception table consists of pairs of addresses relative to the
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index becf47b..6149b47 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -149,7 +149,6 @@
/* 4 bits of software ack period */
#define UV2_ACK_MASK 0x7UL
#define UV2_ACK_UNITS_SHFT 3
-#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
/*
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8afb693..b2297e5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -422,12 +422,14 @@ acpi_parse_int_src_ovr(struct acpi_subtable_header * header,
return 0;
}
- if (intsrc->source_irq == 0 && intsrc->global_irq == 2) {
+ if (intsrc->source_irq == 0) {
if (acpi_skip_timer_override) {
- printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n");
+ printk(PREFIX "BIOS IRQ0 override ignored.\n");
return 0;
}
- if (acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) {
+
+ if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity
+ && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) {
intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK;
printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n");
}
@@ -1334,17 +1336,12 @@ static int __init dmi_disable_acpi(const struct dmi_system_id *d)
}
/*
- * Force ignoring BIOS IRQ0 pin2 override
+ * Force ignoring BIOS IRQ0 override
*/
static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
{
- /*
- * The ati_ixp4x0_rev() early PCI quirk should have set
- * the acpi_skip_timer_override flag already:
- */
if (!acpi_skip_timer_override) {
- WARN(1, KERN_ERR "ati_ixp4x0 quirk not complete.\n");
- pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n",
+ pr_notice("%s detected: Ignoring BIOS IRQ0 override\n",
d->ident);
acpi_skip_timer_override = 1;
}
@@ -1438,7 +1435,7 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = {
* is enabled. This input is incorrectly designated the
* ISA IRQ 0 via an interrupt source override even though
* it is wired to the output of the master 8259A and INTIN0
- * is not connected at all. Force ignoring BIOS IRQ0 pin2
+ * is not connected at all. Force ignoring BIOS IRQ0
* override in that cases.
*/
{
@@ -1473,6 +1470,14 @@ static struct dmi_system_id __initdata acpi_dmi_table_late[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq 6715b"),
},
},
+ {
+ .callback = dmi_ignore_irq0_timer_override,
+ .ident = "FUJITSU SIEMENS",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU SIEMENS"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "AMILO PRO V2030"),
+ },
+ },
{}
};
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6e76c19..d5fd66f 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -20,7 +20,6 @@
#include <linux/bitops.h>
#include <linux/ioport.h>
#include <linux/suspend.h>
-#include <linux/kmemleak.h>
#include <asm/e820.h>
#include <asm/io.h>
#include <asm/iommu.h>
@@ -95,11 +94,6 @@ static u32 __init allocate_aperture(void)
return 0;
}
memblock_reserve(addr, aper_size);
- /*
- * Kmemleak should not scan this block as it may not be mapped via the
- * kernel direct mapping.
- */
- kmemleak_ignore(phys_to_virt(addr));
printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
aper_size >> 10, addr);
insert_aperture_resource((u32)addr, aper_size);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ac96561..5f0ff59 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1195,7 +1195,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
BUG_ON(!cfg->vector);
vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ for_each_cpu(cpu, cfg->domain)
per_cpu(vector_irq, cpu)[vector] = -1;
cfg->vector = 0;
@@ -1203,7 +1203,7 @@ static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
if (likely(!cfg->move_in_progress))
return;
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for_each_cpu(cpu, cfg->old_domain) {
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
vector++) {
if (per_cpu(vector_irq, cpu)[vector] != irq)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a97f3c4..da27c5d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1557,7 +1557,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
static void __mcheck_cpu_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- unsigned long iv = __this_cpu_read(mce_next_interval);
+ unsigned long iv = check_interval * HZ;
setup_timer(t, mce_timer_fn, smp_processor_id());
diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl
index dfea390..c7b3fe2 100644
--- a/arch/x86/kernel/cpu/mkcapflags.pl
+++ b/arch/x86/kernel/cpu/mkcapflags.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/perl -w
#
# Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h
#
@@ -11,22 +11,35 @@ open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n";
print OUT "#include <asm/cpufeature.h>\n\n";
print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n";
+%features = ();
+$err = 0;
+
while (defined($line = <IN>)) {
if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) {
$macro = $1;
- $feature = $2;
+ $feature = "\L$2";
$tail = $3;
if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) {
- $feature = $1;
+ $feature = "\L$1";
}
- if ($feature ne '') {
- printf OUT "\t%-32s = \"%s\",\n",
- "[$macro]", "\L$feature";
+ next if ($feature eq '');
+
+ if ($features{$feature}++) {
+ print STDERR "$in: duplicate feature name: $feature\n";
+ $err++;
}
+ printf OUT "\t%-32s = \"%s\",\n", "[$macro]", $feature;
}
}
print OUT "};\n";
close(IN);
close(OUT);
+
+if ($err) {
+ unlink($out);
+ exit(1);
+}
+
+exit(0);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e049d6d..c4706cf 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1496,6 +1496,7 @@ static struct cpu_hw_events *allocate_fake_cpuc(void)
if (!cpuc->shared_regs)
goto error;
}
+ cpuc->is_fake = 1;
return cpuc;
error:
free_fake_cpuc(cpuc);
@@ -1756,6 +1757,12 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
}
+static inline int
+valid_user_frame(const void __user *fp, unsigned long size)
+{
+ return (__range_not_ok(fp, size, TASK_SIZE) == 0);
+}
+
#ifdef CONFIG_COMPAT
#include <asm/compat.h>
@@ -1780,7 +1787,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
if (bytes != sizeof(frame))
break;
- if (fp < compat_ptr(regs->sp))
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
@@ -1826,7 +1833,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
if (bytes != sizeof(frame))
break;
- if ((unsigned long)fp < regs->sp)
+ if (!valid_user_frame(fp, sizeof(frame)))
break;
perf_callchain_store(entry, frame.return_address);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6638aaf..7241e2f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -117,6 +117,7 @@ struct cpu_hw_events {
struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
unsigned int group_flag;
+ int is_fake;
/*
* Intel DebugStore bits
@@ -364,6 +365,7 @@ struct x86_pmu {
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
+ void (*pebs_aliases)(struct perf_event *event);
/*
* Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 166546e..187c294 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1119,27 +1119,33 @@ intel_bts_constraints(struct perf_event *event)
return NULL;
}
-static bool intel_try_alt_er(struct perf_event *event, int orig_idx)
+static int intel_alt_er(int idx)
{
if (!(x86_pmu.er_flags & ERF_HAS_RSP_1))
- return false;
+ return idx;
- if (event->hw.extra_reg.idx == EXTRA_REG_RSP_0) {
- event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
- event->hw.config |= 0x01bb;
- event->hw.extra_reg.idx = EXTRA_REG_RSP_1;
- event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
- } else if (event->hw.extra_reg.idx == EXTRA_REG_RSP_1) {
+ if (idx == EXTRA_REG_RSP_0)
+ return EXTRA_REG_RSP_1;
+
+ if (idx == EXTRA_REG_RSP_1)
+ return EXTRA_REG_RSP_0;
+
+ return idx;
+}
+
+static void intel_fixup_er(struct perf_event *event, int idx)
+{
+ event->hw.extra_reg.idx = idx;
+
+ if (idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
event->hw.config |= 0x01b7;
- event->hw.extra_reg.idx = EXTRA_REG_RSP_0;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
+ } else if (idx == EXTRA_REG_RSP_1) {
+ event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
+ event->hw.config |= 0x01bb;
+ event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
}
-
- if (event->hw.extra_reg.idx == orig_idx)
- return false;
-
- return true;
}
/*
@@ -1157,14 +1163,18 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
struct event_constraint *c = &emptyconstraint;
struct er_account *era;
unsigned long flags;
- int orig_idx = reg->idx;
+ int idx = reg->idx;
- /* already allocated shared msr */
- if (reg->alloc)
+ /*
+ * reg->alloc can be set due to existing state, so for fake cpuc we
+ * need to ignore this, otherwise we might fail to allocate proper fake
+ * state for this extra reg constraint. Also see the comment below.
+ */
+ if (reg->alloc && !cpuc->is_fake)
return NULL; /* call x86_get_event_constraint() */
again:
- era = &cpuc->shared_regs->regs[reg->idx];
+ era = &cpuc->shared_regs->regs[idx];
/*
* we use spin_lock_irqsave() to avoid lockdep issues when
* passing a fake cpuc
@@ -1173,6 +1183,29 @@ again:
if (!atomic_read(&era->ref) || era->config == reg->config) {
+ /*
+ * If its a fake cpuc -- as per validate_{group,event}() we
+ * shouldn't touch event state and we can avoid doing so
+ * since both will only call get_event_constraints() once
+ * on each event, this avoids the need for reg->alloc.
+ *
+ * Not doing the ER fixup will only result in era->reg being
+ * wrong, but since we won't actually try and program hardware
+ * this isn't a problem either.
+ */
+ if (!cpuc->is_fake) {
+ if (idx != reg->idx)
+ intel_fixup_er(event, idx);
+
+ /*
+ * x86_schedule_events() can call get_event_constraints()
+ * multiple times on events in the case of incremental
+ * scheduling(). reg->alloc ensures we only do the ER
+ * allocation once.
+ */
+ reg->alloc = 1;
+ }
+
/* lock in msr value */
era->config = reg->config;
era->reg = reg->reg;
@@ -1180,17 +1213,17 @@ again:
/* one more user */
atomic_inc(&era->ref);
- /* no need to reallocate during incremental event scheduling */
- reg->alloc = 1;
-
/*
* need to call x86_get_event_constraint()
* to check if associated event has constraints
*/
c = NULL;
- } else if (intel_try_alt_er(event, orig_idx)) {
- raw_spin_unlock_irqrestore(&era->lock, flags);
- goto again;
+ } else {
+ idx = intel_alt_er(idx);
+ if (idx != reg->idx) {
+ raw_spin_unlock_irqrestore(&era->lock, flags);
+ goto again;
+ }
}
raw_spin_unlock_irqrestore(&era->lock, flags);
@@ -1204,11 +1237,14 @@ __intel_shared_reg_put_constraints(struct cpu_hw_events *cpuc,
struct er_account *era;
/*
- * only put constraint if extra reg was actually
- * allocated. Also takes care of event which do
- * not use an extra shared reg
+ * Only put constraint if extra reg was actually allocated. Also takes
+ * care of event which do not use an extra shared reg.
+ *
+ * Also, if this is a fake cpuc we shouldn't touch any event state
+ * (reg->alloc) and we don't care about leaving inconsistent cpuc state
+ * either since it'll be thrown out.
*/
- if (!reg->alloc)
+ if (!reg->alloc || cpuc->is_fake)
return;
era = &cpuc->shared_regs->regs[reg->idx];
@@ -1300,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
intel_put_shared_regs_event_constraints(cpuc, event);
}
-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
{
- int ret = x86_pmu_hw_config(event);
-
- if (ret)
- return ret;
-
- if (event->attr.precise_ip &&
- (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
* Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
* (0x003c) so that we can use it with PEBS.
@@ -1329,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
*/
u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);
+ alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+ event->hw.config = alt_config;
+ }
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ /*
+ * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+ * (0x003c) so that we can use it with PEBS.
+ *
+ * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+ * PEBS capable. However we can use UOPS_RETIRED.ALL
+ * (0x01c2), which is a PEBS capable event, to get the same
+ * count.
+ *
+ * UOPS_RETIRED.ALL counts the number of cycles that retires
+ * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+ * larger than the maximum number of micro-ops that can be
+ * retired per cycle (4) and then inverting the condition, we
+ * count all cycles that retire 16 or less micro-ops, which
+ * is every cycle.
+ *
+ * Thereby we gain a PEBS capable cycle counter.
+ */
+ u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);
alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+ int ret = x86_pmu_hw_config(event);
+
+ if (ret)
+ return ret;
+
+ if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+ x86_pmu.pebs_aliases(event);
if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
@@ -1607,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
+ .pebs_aliases = intel_pebs_aliases_core2,
.format_attrs = intel_arch3_formats_attr,
@@ -1840,8 +1909,9 @@ __init int intel_pmu_init(void)
break;
case 42: /* SandyBridge */
- x86_add_quirk(intel_sandybridge_quirk);
case 45: /* SandyBridge, "Romely-EP" */
+ x86_add_quirk(intel_sandybridge_quirk);
+ case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -1849,6 +1919,7 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 5a3edc2..35e2192 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -400,14 +400,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf), /* MEM_UOP_RETIRED.STLB_MISS_STORES */
- INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOP_RETIRED.LOCK_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x22d0, 0xf), /* MEM_UOP_RETIRED.LOCK_STORES */
- INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf), /* MEM_UOP_RETIRED.SPLIT_STORES */
- INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOP_RETIRED.ANY_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x82d0, 0xf), /* MEM_UOP_RETIRED.ANY_STORES */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index addf9e8..ee8e9ab 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -31,7 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
const struct cpuid_bit *cb;
static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
- { X86_FEATURE_DTS, CR_EAX, 0, 0x00000006, 0 },
+ { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 },
{ X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 },
{ X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 },
{ X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 },
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 8bfb614..3f61904 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -444,12 +444,12 @@ void kgdb_roundup_cpus(unsigned long flags)
/**
* kgdb_arch_handle_exception - Handle architecture specific GDB packets.
- * @vector: The error vector of the exception that happened.
+ * @e_vector: The error vector of the exception that happened.
* @signo: The signal number of the exception that happened.
* @err_code: The error code of the exception that happened.
- * @remcom_in_buffer: The buffer of the packet we have read.
- * @remcom_out_buffer: The buffer of %BUFMAX bytes to write a packet into.
- * @regs: The &struct pt_regs of the current process.
+ * @remcomInBuffer: The buffer of the packet we have read.
+ * @remcomOutBuffer: The buffer of %BUFMAX bytes to write a packet into.
+ * @linux_regs: The &struct pt_regs of the current process.
*
* This function MUST handle the 'c' and 's' command packets,
* as well packets to set / remove a hardware breakpoint, if used.
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 086eb58..f1b42b3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -120,11 +120,6 @@ bool kvm_check_and_clear_guest_paused(void)
bool ret = false;
struct pvclock_vcpu_time_info *src;
- /*
- * per_cpu() is safe here because this function is only called from
- * timer functions where preemption is already disabled.
- */
- WARN_ON(!in_atomic());
src = &__get_cpu_var(hv_clock);
if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
__this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e31bf8d..149b8d9 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -42,7 +42,7 @@ static int __init nmi_unk_cb(unsigned int val, struct pt_regs *regs)
static void __init init_nmi_testsuite(void)
{
/* trap all the unknown NMIs we may generate */
- register_nmi_handler(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
+ register_nmi_handler_initonly(NMI_UNKNOWN, nmi_unk_cb, 0, "nmi_selftest_unk");
}
static void __init cleanup_nmi_testsuite(void)
@@ -64,7 +64,7 @@ static void __init test_nmi_ipi(struct cpumask *mask)
{
unsigned long timeout;
- if (register_nmi_handler(NMI_LOCAL, test_nmi_ipi_callback,
+ if (register_nmi_handler_initonly(NMI_LOCAL, test_nmi_ipi_callback,
NMI_FLAG_FIRST, "nmi_selftest")) {
nmi_fail = FAILURE;
return;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 62c9457..c0f420f 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,7 +100,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
struct dma_attrs *attrs)
{
unsigned long dma_mask;
- struct page *page = NULL;
+ struct page *page;
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
dma_addr_t addr;
@@ -108,6 +108,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
flag |= __GFP_ZERO;
again:
+ page = NULL;
if (!(flag & GFP_ATOMIC))
page = dma_alloc_from_contiguous(dev, count, get_order(size));
if (!page)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 79c45af..5de92f1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -451,6 +451,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
},
},
+ { /* Handle problems with rebooting on the Precision M6600. */
+ .callback = set_pci_reboot,
+ .ident = "Dell OptiPlex 990",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
+ },
+ },
{ }
};
@@ -639,9 +647,11 @@ void native_machine_shutdown(void)
set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
/*
- * O.K Now that I'm on the appropriate processor,
- * stop all of the others.
+ * O.K Now that I'm on the appropriate processor, stop all of the
+ * others. Also disable the local irq to not receive the per-cpu
+ * timer interrupt which may trigger scheduler's load balance.
*/
+ local_irq_disable();
stop_other_cpus();
#endif
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fd019d7..7bd8a08 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -349,9 +349,12 @@ static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (c->phys_proc_id == o->phys_proc_id)
- return topology_sane(c, o, "mc");
+ if (c->phys_proc_id == o->phys_proc_id) {
+ if (cpu_has(c, X86_FEATURE_AMD_DCM))
+ return true;
+ return topology_sane(c, o, "mc");
+ }
return false;
}
@@ -382,6 +385,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
if ((i == cpu) || (has_mc && match_llc(c, o)))
link_mask(llc_shared, cpu, i);
+ }
+
+ /*
+ * This needs a separate iteration over the cpus because we rely on all
+ * cpu_sibling_mask links to be set-up.
+ */
+ for_each_cpu(i, cpu_sibling_setup_mask) {
+ o = &cpu_data(i);
+
if ((i == cpu) || (has_mc && match_mc(c, o))) {
link_mask(core, cpu, i);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index be3cea4..57e168e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3934,6 +3934,9 @@ static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm,
{
struct kvm_mmu_page *page;
+ if (list_empty(&kvm->arch.active_mmu_pages))
+ return;
+
page = container_of(kvm->arch.active_mmu_pages.prev,
struct kvm_mmu_page, link);
kvm_mmu_prepare_zap_page(kvm, page, invalid_list);
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 459b58a..25b7ae8 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -115,7 +115,7 @@ EXPORT_SYMBOL(csum_partial_copy_to_user);
* @src: source address
* @dst: destination address
* @len: number of bytes to be copied.
- * @isum: initial sum that is added into the result (32bit unfolded)
+ * @sum: initial sum that is added into the result (32bit unfolded)
*
* Returns an 32bit unfolded checksum of the buffer.
*/
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index f61ee67..4f74d94 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -8,6 +8,7 @@
#include <linux/module.h>
#include <asm/word-at-a-time.h>
+#include <linux/sched.h>
/*
* best effort, GUP based copy_from_user() that is NMI-safe
@@ -21,6 +22,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
void *map;
int ret;
+ if (__range_not_ok(from, n, TASK_SIZE))
+ return len;
+
do {
ret = __get_user_pages_fast(addr, 1, 0, &page);
if (!ret)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 8191379..5d7e51f 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -28,7 +28,7 @@
# - (66): the last prefix is 0x66
# - (F3): the last prefix is 0xF3
# - (F2): the last prefix is 0xF2
-#
+# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
Table: one byte opcode
Referrer:
@@ -515,12 +515,12 @@ b4: LFS Gv,Mp
b5: LGS Gv,Mp
b6: MOVZX Gv,Eb
b7: MOVZX Gv,Ew
-b8: JMPE | POPCNT Gv,Ev (F3)
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
b9: Grp10 (1A)
ba: Grp8 Ev,Ib (1A)
bb: BTC Ev,Gv
-bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
-bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
be: MOVSX Gv,Eb
bf: MOVSX Gv,Ew
# 0x0f 0xc0-0xcf
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 97141c2..bc4e9d8 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -62,7 +62,8 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
extra += PMD_SIZE;
#endif
/* The first 2/4M doesn't use large pages. */
- extra += mr->end - mr->start;
+ if (mr->start < PMD_SIZE)
+ extra += mr->end - mr->start;
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index be1ef57..78fe3f1 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -180,7 +180,7 @@ err_free_memtype:
/**
* ioremap_nocache - map bus memory into CPU space
- * @offset: bus address of the memory
+ * @phys_addr: bus address of the memory
* @size: size of the resource to map
*
* ioremap_nocache performs a platform specific sequence of operations to
@@ -217,7 +217,7 @@ EXPORT_SYMBOL(ioremap_nocache);
/**
* ioremap_wc - map memory into CPU space write combined
- * @offset: bus address of the memory
+ * @phys_addr: bus address of the memory
* @size: size of the resource to map
*
* This version of ioremap ensures that the memory is marked write combining.
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e1ebde3..a718e0d 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -122,7 +122,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
/**
* clflush_cache_range - flush a cache range with clflush
- * @addr: virtual start address
+ * @vaddr: virtual start address
* @size: number of bytes to flush
*
* clflush is an unordered instruction which needs fencing with mfence
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 732af3a..4599c3e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -176,6 +176,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
return;
}
+ node_set(node, numa_nodes_parsed);
+
printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
node, pxm,
(unsigned long long) start, (unsigned long long) end - 1);
diff --git a/arch/x86/platform/mrst/early_printk_mrst.c b/arch/x86/platform/mrst/early_printk_mrst.c
index 3c6e328..028454f 100644
--- a/arch/x86/platform/mrst/early_printk_mrst.c
+++ b/arch/x86/platform/mrst/early_printk_mrst.c
@@ -110,19 +110,16 @@ static struct kmsg_dumper dw_dumper;
static int dumper_registered;
static void dw_kmsg_dump(struct kmsg_dumper *dumper,
- enum kmsg_dump_reason reason,
- const char *s1, unsigned long l1,
- const char *s2, unsigned long l2)
+ enum kmsg_dump_reason reason)
{
- int i;
+ static char line[1024];
+ size_t len;
/* When run to this, we'd better re-init the HW */
mrst_early_console_init();
- for (i = 0; i < l1; i++)
- early_mrst_console.write(&early_mrst_console, s1 + i, 1);
- for (i = 0; i < l2; i++)
- early_mrst_console.write(&early_mrst_console, s2 + i, 1);
+ while (kmsg_dump_get_line(dumper, true, line, sizeof(line), &len))
+ early_mrst_console.write(&early_mrst_console, line, len);
}
/* Set the ratio rate to 115200, 8n1, IRQ disabled */
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e31bcd8..fd41a92 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -782,7 +782,7 @@ BLOCKING_NOTIFIER_HEAD(intel_scu_notifier);
EXPORT_SYMBOL_GPL(intel_scu_notifier);
/* Called by IPC driver */
-void intel_scu_devices_create(void)
+void __devinit intel_scu_devices_create(void)
{
int i;
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3ae0e61..59880af 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1295,7 +1295,6 @@ 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_EXT_SHFT);
}
write_mmr_misc_control(pnode, mmr_image);
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5f6a5b6..ddcf39b 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -66,9 +66,10 @@ BEGIN {
rex_expr = "^REX(\\.[XRWB]+)*"
fpu_expr = "^ESC" # TODO
- lprefix1_expr = "\\(66\\)"
+ lprefix1_expr = "\\((66|!F3)\\)"
lprefix2_expr = "\\(F3\\)"
- lprefix3_expr = "\\(F2\\)"
+ lprefix3_expr = "\\((F2|!F3)\\)"
+ lprefix_expr = "\\((66|F2|F3)\\)"
max_lprefix = 4
# All opcodes starting with lower-case 'v' or with (v1) superscript
@@ -333,13 +334,16 @@ function convert_operands(count,opnd, i,j,imm,mod)
if (match(ext, lprefix1_expr)) {
lptable1[idx] = add_flags(lptable1[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix2_expr)) {
+ }
+ if (match(ext, lprefix2_expr)) {
lptable2[idx] = add_flags(lptable2[idx],flags)
variant = "INAT_VARIANT"
- } else if (match(ext, lprefix3_expr)) {
+ }
+ if (match(ext, lprefix3_expr)) {
lptable3[idx] = add_flags(lptable3[idx],flags)
variant = "INAT_VARIANT"
- } else {
+ }
+ if (!match(ext, lprefix_expr)){
table[idx] = add_flags(table[idx],flags)
}
}
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 416bd40..68d1dc9 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -39,9 +39,9 @@
#undef __SYSCALL_I386
#define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym,
-typedef void (*sys_call_ptr_t)(void);
+typedef asmlinkage void (*sys_call_ptr_t)(void);
-extern void sys_ni_syscall(void);
+extern asmlinkage void sys_ni_syscall(void);
const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
/*
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e74df95..ff962d4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -209,6 +209,9 @@ static void __init xen_banner(void)
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
}
+#define CPUID_THERM_POWER_LEAF 6
+#define APERFMPERF_PRESENT 0
+
static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
@@ -242,6 +245,11 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
*dx = cpuid_leaf5_edx_val;
return;
+ case CPUID_THERM_POWER_LEAF:
+ /* Disabling APERFMPERF for kernel usage */
+ maskecx = ~(1 << APERFMPERF_PRESENT);
+ break;
+
case 0xb:
/* Suppress extended topology stuff */
maskebx = 0;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index ffd08c4..64effdc6 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -706,6 +706,7 @@ int m2p_add_override(unsigned long mfn, struct page *page,
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
+ int ret = 0;
pfn = page_to_pfn(page);
if (!PageHighMem(page)) {
@@ -741,6 +742,24 @@ int m2p_add_override(unsigned long mfn, struct page *page,
list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]);
spin_unlock_irqrestore(&m2p_override_lock, flags);
+ /* p2m(m2p(mfn)) == mfn: the mfn is already present somewhere in
+ * this domain. Set the FOREIGN_FRAME_BIT in the p2m for the other
+ * pfn so that the following mfn_to_pfn(mfn) calls will return the
+ * pfn from the m2p_override (the backend pfn) instead.
+ * We need to do this because the pages shared by the frontend
+ * (xen-blkfront) can be already locked (lock_page, called by
+ * do_read_cache_page); when the userspace backend tries to use them
+ * with direct_IO, mfn_to_pfn returns the pfn of the frontend, so
+ * do_blockdev_direct_IO is going to try to lock the same pages
+ * again resulting in a deadlock.
+ * As a side effect get_user_pages_fast might not be safe on the
+ * frontend pages while they are being shared with the backend,
+ * because mfn_to_pfn (that ends up being called by GUPF) will
+ * return the backend pfn rather than the frontend pfn. */
+ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+ if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+ set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
+
return 0;
}
EXPORT_SYMBOL_GPL(m2p_add_override);
@@ -752,6 +771,7 @@ int m2p_remove_override(struct page *page, bool clear_pte)
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
+ int ret = 0;
pfn = page_to_pfn(page);
mfn = get_phys_to_machine(pfn);
@@ -821,6 +841,22 @@ int m2p_remove_override(struct page *page, bool clear_pte)
} else
set_phys_to_machine(pfn, page->index);
+ /* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
+ * somewhere in this domain, even before being added to the
+ * m2p_override (see comment above in m2p_add_override).
+ * If there are no other entries in the m2p_override corresponding
+ * to this mfn, then remove the FOREIGN_FRAME_BIT from the p2m for
+ * the original pfn (the one shared by the frontend): the backend
+ * cannot do any IO on this page anymore because it has been
+ * unshared. Removing the FOREIGN_FRAME_BIT from the p2m entry of
+ * the original pfn causes mfn_to_pfn(mfn) to return the frontend
+ * pfn again. */
+ mfn &= ~FOREIGN_FRAME_BIT;
+ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+ if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+ m2p_find_override(mfn) == NULL)
+ set_phys_to_machine(pfn, mfn);
+
return 0;
}
EXPORT_SYMBOL_GPL(m2p_remove_override);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 3ebba07..a4790bf 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -371,7 +371,8 @@ char * __init xen_memory_setup(void)
populated = xen_populate_chunk(map, memmap.nr_entries,
max_pfn, &last_pfn, xen_released_pages);
- extra_pages += (xen_released_pages - populated);
+ xen_released_pages -= populated;
+ extra_pages += xen_released_pages;
if (last_pfn > max_pfn) {
max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);