summaryrefslogtreecommitdiff
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile1
-rw-r--r--arch/x86/kernel/acpi/boot.c25
-rw-r--r--arch/x86/kernel/alternative.c163
-rw-r--r--arch/x86/kernel/apic/apic.c62
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c22
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c8
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c89
-rw-r--r--arch/x86/kernel/asm-offsets_32.c2
-rw-r--r--arch/x86/kernel/asm-offsets_64.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c5
-rw-r--r--arch/x86/kernel/cpu/common.c87
-rw-r--r--arch/x86/kernel/cpu/mkcapflags.sh2
-rw-r--r--arch/x86/kernel/cpu/perf_event.c18
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c10
-rw-r--r--arch/x86/kernel/crash.c2
-rw-r--r--arch/x86/kernel/dumpstack.c4
-rw-r--r--arch/x86/kernel/dumpstack_32.c4
-rw-r--r--arch/x86/kernel/early_printk.c32
-rw-r--r--arch/x86/kernel/entry_32.S93
-rw-r--r--arch/x86/kernel/entry_64.S972
-rw-r--r--arch/x86/kernel/head64.c3
-rw-r--r--arch/x86/kernel/head_32.S3
-rw-r--r--arch/x86/kernel/head_64.S6
-rw-r--r--arch/x86/kernel/i387.c2
-rw-r--r--arch/x86/kernel/ioport.c2
-rw-r--r--arch/x86/kernel/irq.c4
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/irq_64.c2
-rw-r--r--arch/x86/kernel/irqinit.c3
-rw-r--r--arch/x86/kernel/kgdb.c6
-rw-r--r--arch/x86/kernel/kprobes/core.c4
-rw-r--r--arch/x86/kernel/module.c3
-rw-r--r--arch/x86/kernel/perf_regs.c40
-rw-r--r--arch/x86/kernel/process.c87
-rw-r--r--arch/x86/kernel/process_32.c27
-rw-r--r--arch/x86/kernel/process_64.c24
-rw-r--r--arch/x86/kernel/ptrace.c12
-rw-r--r--arch/x86/kernel/pvclock.c44
-rw-r--r--arch/x86/kernel/reboot.c10
-rw-r--r--arch/x86/kernel/relocate_kernel_32.S8
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S16
-rw-r--r--arch/x86/kernel/setup.c15
-rw-r--r--arch/x86/kernel/signal.c50
-rw-r--r--arch/x86/kernel/smpboot.c38
-rw-r--r--arch/x86/kernel/syscall_32.c16
-rw-r--r--arch/x86/kernel/time.c2
-rw-r--r--arch/x86/kernel/traps.c52
-rw-r--r--arch/x86/kernel/uprobes.c2
-rw-r--r--arch/x86/kernel/vm86_32.c4
-rw-r--r--arch/x86/kernel/vsyscall_gtod.c24
-rw-r--r--arch/x86/kernel/xsave.c7
51 files changed, 1156 insertions, 964 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cdb1b70ddad0..c887cd944f0c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_X86_32) += i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += mcount_64.o
obj-y += syscall_$(BITS).o vsyscall_gtod.o
+obj-$(CONFIG_IA32_EMULATION) += syscall_32.o
obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3d525c6124f6..803b684676ff 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1338,6 +1338,26 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
}
/*
+ * ACPI offers an alternative platform interface model that removes
+ * ACPI hardware requirements for platforms that do not implement
+ * the PC Architecture.
+ *
+ * We initialize the Hardware-reduced ACPI model here:
+ */
+static void __init acpi_reduced_hw_init(void)
+{
+ if (acpi_gbl_reduced_hardware) {
+ /*
+ * Override x86_init functions and bypass legacy pic
+ * in Hardware-reduced ACPI mode
+ */
+ x86_init.timers.timer_init = x86_init_noop;
+ x86_init.irqs.pre_vector_init = x86_init_noop;
+ legacy_pic = &null_legacy_pic;
+ }
+}
+
+/*
* If your system is blacklisted here, but you find that acpi=force
* works for you, please contact linux-acpi@vger.kernel.org
*/
@@ -1536,6 +1556,11 @@ int __init early_acpi_boot_init(void)
*/
early_acpi_process_madt();
+ /*
+ * Hardware-reduced ACPI mode initialization:
+ */
+ acpi_reduced_hw_init();
+
return 0;
}
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 703130f469ec..aef653193160 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -52,10 +52,25 @@ static int __init setup_noreplace_paravirt(char *str)
__setup("noreplace-paravirt", setup_noreplace_paravirt);
#endif
-#define DPRINTK(fmt, ...) \
-do { \
- if (debug_alternative) \
- printk(KERN_DEBUG fmt, ##__VA_ARGS__); \
+#define DPRINTK(fmt, args...) \
+do { \
+ if (debug_alternative) \
+ printk(KERN_DEBUG "%s: " fmt "\n", __func__, ##args); \
+} while (0)
+
+#define DUMP_BYTES(buf, len, fmt, args...) \
+do { \
+ if (unlikely(debug_alternative)) { \
+ int j; \
+ \
+ if (!(len)) \
+ break; \
+ \
+ printk(KERN_DEBUG fmt, ##args); \
+ for (j = 0; j < (len) - 1; j++) \
+ printk(KERN_CONT "%02hhx ", buf[j]); \
+ printk(KERN_CONT "%02hhx\n", buf[j]); \
+ } \
} while (0)
/*
@@ -243,12 +258,89 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
void *text_poke_early(void *addr, const void *opcode, size_t len);
-/* Replace instructions with better alternatives for this CPU type.
- This runs before SMP is initialized to avoid SMP problems with
- self modifying code. This implies that asymmetric systems where
- APs have less capabilities than the boot processor are not handled.
- Tough. Make sure you disable such features by hand. */
+/*
+ * Are we looking at a near JMP with a 1 or 4-byte displacement.
+ */
+static inline bool is_jmp(const u8 opcode)
+{
+ return opcode == 0xeb || opcode == 0xe9;
+}
+
+static void __init_or_module
+recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf)
+{
+ u8 *next_rip, *tgt_rip;
+ s32 n_dspl, o_dspl;
+ int repl_len;
+
+ if (a->replacementlen != 5)
+ return;
+
+ o_dspl = *(s32 *)(insnbuf + 1);
+
+ /* next_rip of the replacement JMP */
+ next_rip = repl_insn + a->replacementlen;
+ /* target rip of the replacement JMP */
+ tgt_rip = next_rip + o_dspl;
+ n_dspl = tgt_rip - orig_insn;
+
+ DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl);
+
+ if (tgt_rip - orig_insn >= 0) {
+ if (n_dspl - 2 <= 127)
+ goto two_byte_jmp;
+ else
+ goto five_byte_jmp;
+ /* negative offset */
+ } else {
+ if (((n_dspl - 2) & 0xff) == (n_dspl - 2))
+ goto two_byte_jmp;
+ else
+ goto five_byte_jmp;
+ }
+
+two_byte_jmp:
+ n_dspl -= 2;
+
+ insnbuf[0] = 0xeb;
+ insnbuf[1] = (s8)n_dspl;
+ add_nops(insnbuf + 2, 3);
+
+ repl_len = 2;
+ goto done;
+
+five_byte_jmp:
+ n_dspl -= 5;
+
+ insnbuf[0] = 0xe9;
+ *(s32 *)&insnbuf[1] = n_dspl;
+ repl_len = 5;
+
+done:
+
+ DPRINTK("final displ: 0x%08x, JMP 0x%lx",
+ n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
+}
+
+static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
+{
+ if (instr[0] != 0x90)
+ return;
+
+ add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+
+ DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
+ instr, a->instrlen - a->padlen, a->padlen);
+}
+
+/*
+ * Replace instructions with better alternatives for this CPU type. This runs
+ * before SMP is initialized to avoid SMP problems with self modifying code.
+ * This implies that asymmetric systems where APs have less capabilities than
+ * the boot processor are not handled. Tough. Make sure you disable such
+ * features by hand.
+ */
void __init_or_module apply_alternatives(struct alt_instr *start,
struct alt_instr *end)
{
@@ -256,10 +348,10 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
u8 *instr, *replacement;
u8 insnbuf[MAX_PATCH_LEN];
- DPRINTK("%s: alt table %p -> %p\n", __func__, start, end);
+ DPRINTK("alt table %p -> %p", start, end);
/*
* The scan order should be from start to end. A later scanned
- * alternative code can overwrite a previous scanned alternative code.
+ * alternative code can overwrite previously scanned alternative code.
* Some kernel functions (e.g. memcpy, memset, etc) use this order to
* patch code.
*
@@ -267,29 +359,54 @@ void __init_or_module apply_alternatives(struct alt_instr *start,
* order.
*/
for (a = start; a < end; a++) {
+ int insnbuf_sz = 0;
+
instr = (u8 *)&a->instr_offset + a->instr_offset;
replacement = (u8 *)&a->repl_offset + a->repl_offset;
- BUG_ON(a->replacementlen > a->instrlen);
BUG_ON(a->instrlen > sizeof(insnbuf));
BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
- if (!boot_cpu_has(a->cpuid))
+ if (!boot_cpu_has(a->cpuid)) {
+ if (a->padlen > 1)
+ optimize_nops(a, instr);
+
continue;
+ }
+
+ DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d",
+ a->cpuid >> 5,
+ a->cpuid & 0x1f,
+ instr, a->instrlen,
+ replacement, a->replacementlen, a->padlen);
+
+ DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr);
+ DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement);
memcpy(insnbuf, replacement, a->replacementlen);
+ insnbuf_sz = a->replacementlen;
/* 0xe8 is a relative jump; fix the offset. */
- if (*insnbuf == 0xe8 && a->replacementlen == 5)
- *(s32 *)(insnbuf + 1) += replacement - instr;
+ if (*insnbuf == 0xe8 && a->replacementlen == 5) {
+ *(s32 *)(insnbuf + 1) += replacement - instr;
+ DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
+ *(s32 *)(insnbuf + 1),
+ (unsigned long)instr + *(s32 *)(insnbuf + 1) + 5);
+ }
+
+ if (a->replacementlen && is_jmp(replacement[0]))
+ recompute_jump(a, instr, replacement, insnbuf);
- add_nops(insnbuf + a->replacementlen,
- a->instrlen - a->replacementlen);
+ if (a->instrlen > a->replacementlen) {
+ add_nops(insnbuf + a->replacementlen,
+ a->instrlen - a->replacementlen);
+ insnbuf_sz += a->instrlen - a->replacementlen;
+ }
+ DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr);
- text_poke_early(instr, insnbuf, a->instrlen);
+ text_poke_early(instr, insnbuf, insnbuf_sz);
}
}
#ifdef CONFIG_SMP
-
static void alternatives_smp_lock(const s32 *start, const s32 *end,
u8 *text, u8 *text_end)
{
@@ -371,8 +488,8 @@ void __init_or_module alternatives_smp_module_add(struct module *mod,
smp->locks_end = locks_end;
smp->text = text;
smp->text_end = text_end;
- DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n",
- __func__, smp->locks, smp->locks_end,
+ DPRINTK("locks %p -> %p, text %p -> %p, name %s\n",
+ smp->locks, smp->locks_end,
smp->text, smp->text_end, smp->name);
list_add_tail(&smp->next, &smp_alt_modules);
@@ -440,7 +557,7 @@ int alternatives_text_reserved(void *start, void *end)
return 0;
}
-#endif
+#endif /* CONFIG_SMP */
#ifdef CONFIG_PARAVIRT
void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
@@ -601,7 +718,7 @@ int poke_int3_handler(struct pt_regs *regs)
if (likely(!bp_patching_in_progress))
return 0;
- if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr)
+ if (user_mode(regs) || regs->ip != (unsigned long)bp_int3_addr)
return 0;
/* set up the specified breakpoint handler */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ad3639ae1b9b..dcb52850a28f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1084,67 +1084,6 @@ void lapic_shutdown(void)
local_irq_restore(flags);
}
-/*
- * This is to verify that we're looking at a real local APIC.
- * Check these against your board if the CPUs aren't getting
- * started for no apparent reason.
- */
-int __init verify_local_APIC(void)
-{
- unsigned int reg0, reg1;
-
- /*
- * The version register is read-only in a real APIC.
- */
- reg0 = apic_read(APIC_LVR);
- apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0);
- apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK);
- reg1 = apic_read(APIC_LVR);
- apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1);
-
- /*
- * The two version reads above should print the same
- * numbers. If the second one is different, then we
- * poke at a non-APIC.
- */
- if (reg1 != reg0)
- return 0;
-
- /*
- * Check if the version looks reasonably.
- */
- reg1 = GET_APIC_VERSION(reg0);
- if (reg1 == 0x00 || reg1 == 0xff)
- return 0;
- reg1 = lapic_get_maxlvt();
- if (reg1 < 0x02 || reg1 == 0xff)
- return 0;
-
- /*
- * The ID register is read/write in a real APIC.
- */
- reg0 = apic_read(APIC_ID);
- apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0);
- apic_write(APIC_ID, reg0 ^ apic->apic_id_mask);
- reg1 = apic_read(APIC_ID);
- apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1);
- apic_write(APIC_ID, reg0);
- if (reg1 != (reg0 ^ apic->apic_id_mask))
- return 0;
-
- /*
- * The next two are just to see if we have sane values.
- * They're only really relevant if we're in Virtual Wire
- * compatibility mode, but most boxes are anymore.
- */
- reg0 = apic_read(APIC_LVT0);
- apic_printk(APIC_DEBUG, "Getting LVT0: %x\n", reg0);
- reg1 = apic_read(APIC_LVT1);
- apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1);
-
- return 1;
-}
-
/**
* sync_Arb_IDs - synchronize APIC bus arbitration IDs
*/
@@ -2283,7 +2222,6 @@ int __init APIC_init_uniprocessor(void)
disable_ioapic_support();
default_setup_apic_routing();
- verify_local_APIC();
apic_bsp_setup(true);
return 0;
}
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index c2fd21fed002..017149cded07 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -37,10 +37,12 @@ static const struct apic apic_numachip;
static unsigned int get_apic_id(unsigned long x)
{
unsigned long value;
- unsigned int id;
+ unsigned int id = (x >> 24) & 0xff;
- rdmsrl(MSR_FAM10H_NODE_ID, value);
- id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
+ if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+ rdmsrl(MSR_FAM10H_NODE_ID, value);
+ id |= (value << 2) & 0xff00;
+ }
return id;
}
@@ -155,10 +157,18 @@ static int __init numachip_probe(void)
static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
{
- if (c->phys_proc_id != node) {
- c->phys_proc_id = node;
- per_cpu(cpu_llc_id, smp_processor_id()) = node;
+ u64 val;
+ u32 nodes = 1;
+
+ this_cpu_write(cpu_llc_id, node);
+
+ /* Account for nodes per socket in multi-core-module processors */
+ if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+ rdmsrl(MSR_FAM10H_NODE_ID, val);
+ nodes = ((val >> 3) & 7) + 1;
}
+
+ c->phys_proc_id = node / nodes;
}
static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index e658f21681c8..d9d0bd2faaf4 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -135,12 +135,12 @@ static void init_x2apic_ldr(void)
per_cpu(x86_cpu_to_logical_apicid, this_cpu) = apic_read(APIC_LDR);
- __cpu_set(this_cpu, per_cpu(cpus_in_cluster, this_cpu));
+ cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, this_cpu));
for_each_online_cpu(cpu) {
if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
continue;
- __cpu_set(this_cpu, per_cpu(cpus_in_cluster, cpu));
- __cpu_set(cpu, per_cpu(cpus_in_cluster, this_cpu));
+ cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
+ cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
}
}
@@ -195,7 +195,7 @@ static int x2apic_init_cpu_notifier(void)
BUG_ON(!per_cpu(cpus_in_cluster, cpu) || !per_cpu(ipi_mask, cpu));
- __cpu_set(cpu, per_cpu(cpus_in_cluster, cpu));
+ cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
register_hotcpu_notifier(&x2apic_cpu_notifier);
return 1;
}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 8e9dcfd630e4..c8d92950bc04 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -144,33 +144,60 @@ static void __init uv_set_apicid_hibit(void)
static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
{
- int pnodeid, is_uv1, is_uv2, is_uv3;
-
- is_uv1 = !strcmp(oem_id, "SGI");
- is_uv2 = !strcmp(oem_id, "SGI2");
- is_uv3 = !strncmp(oem_id, "SGI3", 4); /* there are varieties of UV3 */
- if (is_uv1 || is_uv2 || is_uv3) {
- uv_hub_info->hub_revision =
- (is_uv1 ? UV1_HUB_REVISION_BASE :
- (is_uv2 ? UV2_HUB_REVISION_BASE :
- UV3_HUB_REVISION_BASE));
- pnodeid = early_get_pnodeid();
- early_get_apic_pnode_shift();
- x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
- x86_platform.nmi_init = uv_nmi_init;
- if (!strcmp(oem_table_id, "UVL"))
- uv_system_type = UV_LEGACY_APIC;
- else if (!strcmp(oem_table_id, "UVX"))
- uv_system_type = UV_X2APIC;
- else if (!strcmp(oem_table_id, "UVH")) {
- __this_cpu_write(x2apic_extra_bits,
- pnodeid << uvh_apicid.s.pnode_shift);
- uv_system_type = UV_NON_UNIQUE_APIC;
- uv_set_apicid_hibit();
- return 1;
- }
+ int pnodeid;
+ int uv_apic;
+
+ if (strncmp(oem_id, "SGI", 3) != 0)
+ return 0;
+
+ /*
+ * Determine UV arch type.
+ * SGI: UV100/1000
+ * SGI2: UV2000/3000
+ * SGI3: UV300 (truncated to 4 chars because of different varieties)
+ */
+ uv_hub_info->hub_revision =
+ !strncmp(oem_id, "SGI3", 4) ? UV3_HUB_REVISION_BASE :
+ !strcmp(oem_id, "SGI2") ? UV2_HUB_REVISION_BASE :
+ !strcmp(oem_id, "SGI") ? UV1_HUB_REVISION_BASE : 0;
+
+ if (uv_hub_info->hub_revision == 0)
+ goto badbios;
+
+ pnodeid = early_get_pnodeid();
+ early_get_apic_pnode_shift();
+ x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
+ x86_platform.nmi_init = uv_nmi_init;
+
+ if (!strcmp(oem_table_id, "UVX")) { /* most common */
+ uv_system_type = UV_X2APIC;
+ uv_apic = 0;
+
+ } else if (!strcmp(oem_table_id, "UVH")) { /* only UV1 systems */
+ uv_system_type = UV_NON_UNIQUE_APIC;
+ __this_cpu_write(x2apic_extra_bits,
+ pnodeid << uvh_apicid.s.pnode_shift);
+ uv_set_apicid_hibit();
+ uv_apic = 1;
+
+ } else if (!strcmp(oem_table_id, "UVL")) { /* only used for */
+ uv_system_type = UV_LEGACY_APIC; /* very small systems */
+ uv_apic = 0;
+
+ } else {
+ goto badbios;
}
- return 0;
+
+ pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n",
+ oem_id, oem_table_id, uv_system_type,
+ uv_min_hub_revision_id, uv_apic);
+
+ return uv_apic;
+
+badbios:
+ pr_err("UV: OEM_ID:%s OEM_TABLE_ID:%s\n", oem_id, oem_table_id);
+ pr_err("Current BIOS not supported, update kernel and/or BIOS\n");
+ BUG();
}
enum uv_system_type get_uv_system_type(void)
@@ -854,10 +881,14 @@ void __init uv_system_init(void)
unsigned long mmr_base, present, paddr;
unsigned short pnode_mask;
unsigned char n_lshift;
- char *hub = (is_uv1_hub() ? "UV1" :
- (is_uv2_hub() ? "UV2" :
- "UV3"));
+ char *hub = (is_uv1_hub() ? "UV100/1000" :
+ (is_uv2_hub() ? "UV2000/3000" :
+ (is_uv3_hub() ? "UV300" : NULL)));
+ if (!hub) {
+ pr_err("UV: Unknown/unsupported UV hub\n");
+ return;
+ }
pr_info("UV: Found %s hub\n", hub);
map_low_mmrs();
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 3b3b9d33ac1d..47703aed74cf 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -68,7 +68,7 @@ void foo(void)
/* Offset from the sysenter stack to tss.sp0 */
DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
- sizeof(struct tss_struct));
+ offsetofend(struct tss_struct, SYSENTER_stack));
#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index fdcbb4d27c9f..5ce6f2da8763 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -81,6 +81,7 @@ int main(void)
#undef ENTRY
OFFSET(TSS_ist, tss_struct, x86_tss.ist);
+ OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
BLANK();
DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index a220239cea65..dd9e50500297 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -711,6 +711,11 @@ static void init_amd(struct cpuinfo_x86 *c)
set_cpu_bug(c, X86_BUG_AMD_APIC_C1E);
rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
+
+ /* 3DNow or LM implies PREFETCHW */
+ if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH))
+ if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM))
+ set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2346c95c6ab1..3f70538012e2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -959,38 +959,37 @@ static void identify_cpu(struct cpuinfo_x86 *c)
#endif
}
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_IA32_EMULATION
-/* May not be __init: called during resume */
-static void syscall32_cpu_init(void)
-{
- /* Load these always in case some future AMD CPU supports
- SYSENTER from compat mode too. */
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
-
- wrmsrl(MSR_CSTAR, ia32_cstar_target);
-}
-#endif /* CONFIG_IA32_EMULATION */
-#endif /* CONFIG_X86_64 */
-
+/*
+ * Set up the CPU state needed to execute SYSENTER/SYSEXIT instructions
+ * on 32-bit kernels:
+ */
#ifdef CONFIG_X86_32
void enable_sep_cpu(void)
{
- int cpu = get_cpu();
- struct tss_struct *tss = &per_cpu(init_tss, cpu);
+ struct tss_struct *tss;
+ int cpu;
- if (!boot_cpu_has(X86_FEATURE_SEP)) {
- put_cpu();
- 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.
+ */
tss->x86_tss.ss1 = __KERNEL_CS;
- tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss;
- wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
- wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0);
- wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0);
+ wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
+
+ wrmsr(MSR_IA32_SYSENTER_ESP,
+ (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
+ 0);
+
+ wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0);
+
+out:
put_cpu();
}
#endif
@@ -1118,7 +1117,7 @@ static __init int setup_disablecpuid(char *arg)
__setup("clearcpuid=", setup_disablecpuid);
DEFINE_PER_CPU(unsigned long, kernel_stack) =
- (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+ (unsigned long)&init_thread_union + THREAD_SIZE;
EXPORT_PER_CPU_SYMBOL(kernel_stack);
#ifdef CONFIG_X86_64
@@ -1130,8 +1129,8 @@ DEFINE_PER_CPU_FIRST(union irq_stack_union,
irq_stack_union) __aligned(PAGE_SIZE) __visible;
/*
- * The following four percpu variables are hot. Align current_task to
- * cacheline size such that all four fall in the same cacheline.
+ * The following percpu variables are hot. Align current_task to
+ * cacheline size such that they fall in the same cacheline.
*/
DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
&init_task;
@@ -1171,10 +1170,23 @@ void syscall_init(void)
*/
wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32);
wrmsrl(MSR_LSTAR, system_call);
- wrmsrl(MSR_CSTAR, ignore_sysret);
#ifdef CONFIG_IA32_EMULATION
- syscall32_cpu_init();
+ wrmsrl(MSR_CSTAR, ia32_cstar_target);
+ /*
+ * This only works on Intel CPUs.
+ * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
+ * This does not cause SYSENTER to jump to the wrong location, because
+ * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
+ */
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+#else
+ wrmsrl(MSR_CSTAR, ignore_sysret);
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
#endif
/* Flags to clear on syscall */
@@ -1226,6 +1238,15 @@ DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+/*
+ * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
+ * the top of the kernel stack. Use an extra percpu variable to track the
+ * top of the kernel stack directly.
+ */
+DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
+ (unsigned long)&init_thread_union + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
+
#ifdef CONFIG_CC_STACKPROTECTOR
DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
#endif
@@ -1307,7 +1328,7 @@ void cpu_init(void)
*/
load_ucode_ap();
- t = &per_cpu(init_tss, cpu);
+ t = &per_cpu(cpu_tss, cpu);
oist = &per_cpu(orig_ist, cpu);
#ifdef CONFIG_NUMA
@@ -1391,7 +1412,7 @@ void cpu_init(void)
{
int cpu = smp_processor_id();
struct task_struct *curr = current;
- struct tss_struct *t = &per_cpu(init_tss, cpu);
+ struct tss_struct *t = &per_cpu(cpu_tss, cpu);
struct thread_struct *thread = &curr->thread;
wait_for_master_cpu(cpu);
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index 36d99a337b49..3f20710a5b23 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -6,7 +6,7 @@
IN=$1
OUT=$2
-function dump_array()
+dump_array()
{
ARRAY=$1
SIZE=$2
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index b71a7f86d68a..e2888a3ad1e3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2147,24 +2147,24 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
static unsigned long code_segment_base(struct pt_regs *regs)
{
/*
+ * For IA32 we look at the GDT/LDT segment base to convert the
+ * effective IP to a linear address.
+ */
+
+#ifdef CONFIG_X86_32
+ /*
* If we are in VM86 mode, add the segment offset to convert to a
* linear address.
*/
if (regs->flags & X86_VM_MASK)
return 0x10 * regs->cs;
- /*
- * For IA32 we look at the GDT/LDT segment base to convert the
- * effective IP to a linear address.
- */
-#ifdef CONFIG_X86_32
if (user_mode(regs) && regs->cs != __USER_CS)
return get_segment_base(regs->cs);
#else
- if (test_thread_flag(TIF_IA32)) {
- if (user_mode(regs) && regs->cs != __USER32_CS)
- return get_segment_base(regs->cs);
- }
+ if (user_mode(regs) && !user_64bit_mode(regs) &&
+ regs->cs != __USER32_CS)
+ return get_segment_base(regs->cs);
#endif
return 0;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d967138..258990688a5e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -212,11 +212,11 @@ static struct event_constraint intel_hsw_event_constraints[] = {
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
- INTEL_EVENT_CONSTRAINT(0x08a3, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
/* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
- INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4),
+ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
- INTEL_EVENT_CONSTRAINT(0x04a3, 0xf),
+ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
EVENT_CONSTRAINT_END
};
@@ -1649,11 +1649,11 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
if (c)
return c;
- c = intel_pebs_constraints(event);
+ c = intel_shared_regs_constraints(cpuc, event);
if (c)
return c;
- c = intel_shared_regs_constraints(cpuc, event);
+ c = intel_pebs_constraints(event);
if (c)
return c;
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index aceb2f90c716..c76d3e37c6e1 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -105,7 +105,7 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
#ifdef CONFIG_X86_32
struct pt_regs fixed_regs;
- if (!user_mode_vm(regs)) {
+ if (!user_mode(regs)) {
crash_fixup_ss_esp(&fixed_regs, regs);
regs = &fixed_regs;
}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index cf3df1d8d039..ab3b65639a3e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -278,7 +278,7 @@ int __die(const char *str, struct pt_regs *regs, long err)
print_modules();
show_regs(regs);
#ifdef CONFIG_X86_32
- if (user_mode_vm(regs)) {
+ if (user_mode(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
} else {
@@ -307,7 +307,7 @@ void die(const char *str, struct pt_regs *regs, long err)
unsigned long flags = oops_begin();
int sig = SIGSEGV;
- if (!user_mode_vm(regs))
+ if (!user_mode(regs))
report_bug(regs->ip, regs);
if (__die(str, regs, err))
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 5abd4cd4230c..39891ff50d03 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -123,13 +123,13 @@ void show_regs(struct pt_regs *regs)
int i;
show_regs_print_info(KERN_EMERG);
- __show_regs(regs, !user_mode_vm(regs));
+ __show_regs(regs, !user_mode(regs));
/*
* When in-kernel, we also print out the stack and code at the
* time of the fault..
*/
- if (!user_mode_vm(regs)) {
+ if (!user_mode(regs)) {
unsigned int code_prologue = code_bytes * 43 / 64;
unsigned int code_len = code_bytes;
unsigned char c;
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index a62536a1be88..49ff55ef9b26 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -95,20 +95,6 @@ static unsigned long early_serial_base = 0x3f8; /* ttyS0 */
#define DLL 0 /* Divisor Latch Low */
#define DLH 1 /* Divisor latch High */
-static void mem32_serial_out(unsigned long addr, int offset, int value)
-{
- uint32_t *vaddr = (uint32_t *)addr;
- /* shift implied by pointer type */
- writel(value, vaddr + offset);
-}
-
-static unsigned int mem32_serial_in(unsigned long addr, int offset)
-{
- uint32_t *vaddr = (uint32_t *)addr;
- /* shift implied by pointer type */
- return readl(vaddr + offset);
-}
-
static unsigned int io_serial_in(unsigned long addr, int offset)
{
return inb(addr + offset);
@@ -205,6 +191,20 @@ static __init void early_serial_init(char *s)
}
#ifdef CONFIG_PCI
+static void mem32_serial_out(unsigned long addr, int offset, int value)
+{
+ u32 *vaddr = (u32 *)addr;
+ /* shift implied by pointer type */
+ writel(value, vaddr + offset);
+}
+
+static unsigned int mem32_serial_in(unsigned long addr, int offset)
+{
+ u32 *vaddr = (u32 *)addr;
+ /* shift implied by pointer type */
+ return readl(vaddr + offset);
+}
+
/*
* early_pci_serial_init()
*
@@ -217,8 +217,8 @@ static __init void early_pci_serial_init(char *s)
unsigned divisor;
unsigned long baud = DEFAULT_BAUD;
u8 bus, slot, func;
- uint32_t classcode, bar0;
- uint16_t cmdreg;
+ u32 classcode, bar0;
+ u16 cmdreg;
char *e;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 31e2d5bf3e38..1c309763e321 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -395,10 +395,13 @@ sysenter_past_esp:
/*CFI_REL_OFFSET cs, 0*/
/*
* Push current_thread_info()->sysenter_return to the stack.
- * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
- * pushed above; +8 corresponds to copy_thread's esp0 setting.
+ * A tiny bit of offset fixup is necessary: TI_sysenter_return
+ * is relative to thread_info, which is at the bottom of the
+ * kernel stack page. 4*4 means the 4 words pushed above;
+ * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
+ * and THREAD_SIZE takes us to the bottom.
*/
- pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp)
+ pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
CFI_REL_OFFSET eip, 0
pushl_cfi %eax
@@ -432,7 +435,7 @@ sysenter_after_call:
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
testl $_TIF_ALLWORK_MASK, %ecx
- jne sysexit_audit
+ jnz sysexit_audit
sysenter_exit:
/* if something modifies registers it must also disable sysexit */
movl PT_EIP(%esp), %edx
@@ -460,7 +463,7 @@ sysenter_audit:
sysexit_audit:
testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jne syscall_exit_work
+ jnz syscall_exit_work
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
movl %eax,%edx /* second arg, syscall return value */
@@ -472,7 +475,7 @@ sysexit_audit:
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx
- jne syscall_exit_work
+ jnz syscall_exit_work
movl PT_EAX(%esp),%eax /* reload syscall return value */
jmp sysenter_exit
#endif
@@ -510,7 +513,7 @@ syscall_exit:
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
testl $_TIF_ALLWORK_MASK, %ecx # current->work
- jne syscall_exit_work
+ jnz syscall_exit_work
restore_all:
TRACE_IRQS_IRET
@@ -612,7 +615,7 @@ work_notifysig: # deal with pending signals and
#ifdef CONFIG_VM86
testl $X86_EFLAGS_VM, PT_EFLAGS(%esp)
movl %esp, %eax
- jne work_notifysig_v86 # returning to kernel-space or
+ jnz work_notifysig_v86 # returning to kernel-space or
# vm86-space
1:
#else
@@ -720,43 +723,22 @@ END(sysenter_badsys)
.endm
/*
- * Build the entry stubs and pointer table with some assembler magic.
- * We pack 7 stubs into a single 32-byte chunk, which will fit in a
- * single cache line on all modern x86 implementations.
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
*/
-.section .init.rodata,"a"
-ENTRY(interrupt)
-.section .entry.text, "ax"
- .p2align 5
- .p2align CONFIG_X86_L1_CACHE_SHIFT
+ .align 8
ENTRY(irq_entries_start)
RING0_INT_FRAME
-vector=FIRST_EXTERNAL_VECTOR
-.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
- .balign 32
- .rept 7
- .if vector < FIRST_SYSTEM_VECTOR
- .if vector <> FIRST_EXTERNAL_VECTOR
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
CFI_ADJUST_CFA_OFFSET -4
- .endif
-1: pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */
- .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
- jmp 2f
- .endif
- .previous
- .long 1b
- .section .entry.text, "ax"
-vector=vector+1
- .endif
- .endr
-2: jmp common_interrupt
-.endr
+ .align 8
+ .endr
END(irq_entries_start)
-.previous
-END(interrupt)
-.previous
-
/*
* the CPU automatically disables interrupts when executing an IRQ vector,
* so IRQ-flags tracing has to follow that:
@@ -816,15 +798,9 @@ ENTRY(simd_coprocessor_error)
pushl_cfi $0
#ifdef CONFIG_X86_INVD_BUG
/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-661: pushl_cfi $do_general_protection
-662:
-.section .altinstructions,"a"
- altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f
-.previous
-.section .altinstr_replacement,"ax"
-663: pushl $do_simd_coprocessor_error
-664:
-.previous
+ ALTERNATIVE "pushl_cfi $do_general_protection", \
+ "pushl $do_simd_coprocessor_error", \
+ X86_FEATURE_XMM
#else
pushl_cfi $do_simd_coprocessor_error
#endif
@@ -1240,20 +1216,13 @@ error_code:
/*CFI_REL_OFFSET es, 0*/
pushl_cfi %ds
/*CFI_REL_OFFSET ds, 0*/
- pushl_cfi %eax
- CFI_REL_OFFSET eax, 0
- pushl_cfi %ebp
- CFI_REL_OFFSET ebp, 0
- pushl_cfi %edi
- CFI_REL_OFFSET edi, 0
- pushl_cfi %esi
- CFI_REL_OFFSET esi, 0
- pushl_cfi %edx
- CFI_REL_OFFSET edx, 0
- pushl_cfi %ecx
- CFI_REL_OFFSET ecx, 0
- pushl_cfi %ebx
- CFI_REL_OFFSET ebx, 0
+ pushl_cfi_reg eax
+ pushl_cfi_reg ebp
+ pushl_cfi_reg edi
+ pushl_cfi_reg esi
+ pushl_cfi_reg edx
+ pushl_cfi_reg ecx
+ pushl_cfi_reg ebx
cld
movl $(__KERNEL_PERCPU), %ecx
movl %ecx, %fs
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1d74d161687c..c7b238494b31 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -14,27 +14,14 @@
* NOTE: This code handles signal-recognition, which happens every time
* after an interrupt and after each system call.
*
- * Normal syscalls and interrupts don't save a full stack frame, this is
- * only done for syscall tracing, signals or fork/exec et.al.
- *
* A note on terminology:
- * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
* at the top of the kernel process stack.
- * - partial stack frame: partially saved registers up to R11.
- * - full stack frame: Like partial stack frame, but all register saved.
*
* Some macro usage:
* - CFI macros are used to generate dwarf2 unwind information for better
* backtraces. They don't change any code.
- * - SAVE_ALL/RESTORE_ALL - Save/restore all registers
- * - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify.
- * There are unfortunately lots of special cases where some registers
- * not touched. The macro is a big mess that should be cleaned up.
- * - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS.
- * Gives a full stack frame.
* - ENTRY/END Define functions in the symbol table.
- * - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack
- * frame that is otherwise undefined after a SYSCALL
* - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
* - idtentry - Define exception entry points.
*/
@@ -70,10 +57,6 @@
.section .entry.text, "ax"
-#ifndef CONFIG_PREEMPT
-#define retint_kernel retint_restore_args
-#endif
-
#ifdef CONFIG_PARAVIRT
ENTRY(native_usergs_sysret64)
swapgs
@@ -82,9 +65,9 @@ ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
-.macro TRACE_IRQS_IRETQ offset=ARGOFFSET
+.macro TRACE_IRQS_IRETQ
#ifdef CONFIG_TRACE_IRQFLAGS
- bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
+ bt $9,EFLAGS(%rsp) /* interrupts off? */
jnc 1f
TRACE_IRQS_ON
1:
@@ -116,8 +99,8 @@ ENDPROC(native_usergs_sysret64)
call debug_stack_reset
.endm
-.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET
- bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */
+.macro TRACE_IRQS_IRETQ_DEBUG
+ bt $9,EFLAGS(%rsp) /* interrupts off? */
jnc 1f
TRACE_IRQS_ON_DEBUG
1:
@@ -130,34 +113,7 @@ ENDPROC(native_usergs_sysret64)
#endif
/*
- * C code is not supposed to know about undefined top of stack. Every time
- * a C function with an pt_regs argument is called from the SYSCALL based
- * fast path FIXUP_TOP_OF_STACK is needed.
- * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
- * manipulation.
- */
-
- /* %rsp:at FRAMEEND */
- .macro FIXUP_TOP_OF_STACK tmp offset=0
- movq PER_CPU_VAR(old_rsp),\tmp
- movq \tmp,RSP+\offset(%rsp)
- movq $__USER_DS,SS+\offset(%rsp)
- movq $__USER_CS,CS+\offset(%rsp)
- movq RIP+\offset(%rsp),\tmp /* get rip */
- movq \tmp,RCX+\offset(%rsp) /* copy it to rcx as sysret would do */
- movq R11+\offset(%rsp),\tmp /* get eflags */
- movq \tmp,EFLAGS+\offset(%rsp)
- .endm
-
- .macro RESTORE_TOP_OF_STACK tmp offset=0
- movq RSP+\offset(%rsp),\tmp
- movq \tmp,PER_CPU_VAR(old_rsp)
- movq EFLAGS+\offset(%rsp),\tmp
- movq \tmp,R11+\offset(%rsp)
- .endm
-
-/*
- * initial frame state for interrupts (and exceptions without error code)
+ * empty frame
*/
.macro EMPTY_FRAME start=1 offset=0
.if \start
@@ -173,12 +129,12 @@ ENDPROC(native_usergs_sysret64)
* initial frame state for interrupts (and exceptions without error code)
*/
.macro INTR_FRAME start=1 offset=0
- EMPTY_FRAME \start, SS+8+\offset-RIP
- /*CFI_REL_OFFSET ss, SS+\offset-RIP*/
- CFI_REL_OFFSET rsp, RSP+\offset-RIP
- /*CFI_REL_OFFSET rflags, EFLAGS+\offset-RIP*/
- /*CFI_REL_OFFSET cs, CS+\offset-RIP*/
- CFI_REL_OFFSET rip, RIP+\offset-RIP
+ EMPTY_FRAME \start, 5*8+\offset
+ /*CFI_REL_OFFSET ss, 4*8+\offset*/
+ CFI_REL_OFFSET rsp, 3*8+\offset
+ /*CFI_REL_OFFSET rflags, 2*8+\offset*/
+ /*CFI_REL_OFFSET cs, 1*8+\offset*/
+ CFI_REL_OFFSET rip, 0*8+\offset
.endm
/*
@@ -186,30 +142,23 @@ ENDPROC(native_usergs_sysret64)
* with vector already pushed)
*/
.macro XCPT_FRAME start=1 offset=0
- INTR_FRAME \start, RIP+\offset-ORIG_RAX
- .endm
-
-/*
- * frame that enables calling into C.
- */
- .macro PARTIAL_FRAME start=1 offset=0
- XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
- CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
- CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
- CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET
- CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET
- CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET
- CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET
- CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
- CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
- CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
+ INTR_FRAME \start, 1*8+\offset
.endm
/*
* frame that enables passing a complete pt_regs to a C function.
*/
.macro DEFAULT_FRAME start=1 offset=0
- PARTIAL_FRAME \start, R11+\offset-R15
+ XCPT_FRAME \start, ORIG_RAX+\offset
+ CFI_REL_OFFSET rdi, RDI+\offset
+ CFI_REL_OFFSET rsi, RSI+\offset
+ CFI_REL_OFFSET rdx, RDX+\offset
+ CFI_REL_OFFSET rcx, RCX+\offset
+ CFI_REL_OFFSET rax, RAX+\offset
+ CFI_REL_OFFSET r8, R8+\offset
+ CFI_REL_OFFSET r9, R9+\offset
+ CFI_REL_OFFSET r10, R10+\offset
+ CFI_REL_OFFSET r11, R11+\offset
CFI_REL_OFFSET rbx, RBX+\offset
CFI_REL_OFFSET rbp, RBP+\offset
CFI_REL_OFFSET r12, R12+\offset
@@ -218,105 +167,30 @@ ENDPROC(native_usergs_sysret64)
CFI_REL_OFFSET r15, R15+\offset
.endm
-ENTRY(save_paranoid)
- XCPT_FRAME 1 RDI+8
- cld
- movq %rdi, RDI+8(%rsp)
- movq %rsi, RSI+8(%rsp)
- movq_cfi rdx, RDX+8
- movq_cfi rcx, RCX+8
- movq_cfi rax, RAX+8
- movq %r8, R8+8(%rsp)
- movq %r9, R9+8(%rsp)
- movq %r10, R10+8(%rsp)
- movq %r11, R11+8(%rsp)
- movq_cfi rbx, RBX+8
- movq %rbp, RBP+8(%rsp)
- movq %r12, R12+8(%rsp)
- movq %r13, R13+8(%rsp)
- movq %r14, R14+8(%rsp)
- movq %r15, R15+8(%rsp)
- movl $1,%ebx
- movl $MSR_GS_BASE,%ecx
- rdmsr
- testl %edx,%edx
- js 1f /* negative -> in kernel */
- SWAPGS
- xorl %ebx,%ebx
-1: ret
- CFI_ENDPROC
-END(save_paranoid)
-
/*
- * A newly forked process directly context switches into this address.
+ * 64bit SYSCALL instruction entry. Up to 6 arguments in registers.
*
- * rdi: prev task we switched from
- */
-ENTRY(ret_from_fork)
- DEFAULT_FRAME
-
- LOCK ; btr $TIF_FORK,TI_flags(%r8)
-
- pushq_cfi $0x0002
- popfq_cfi # reset kernel eflags
-
- call schedule_tail # rdi: 'prev' task parameter
-
- GET_THREAD_INFO(%rcx)
-
- RESTORE_REST
-
- testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
- jz 1f
-
- /*
- * By the time we get here, we have no idea whether our pt_regs,
- * ti flags, and ti status came from the 64-bit SYSCALL fast path,
- * the slow path, or one of the ia32entry paths.
- * Use int_ret_from_sys_call to return, since it can safely handle
- * all of the above.
- */
- jmp int_ret_from_sys_call
-
-1:
- subq $REST_SKIP, %rsp # leave space for volatiles
- CFI_ADJUST_CFA_OFFSET REST_SKIP
- movq %rbp, %rdi
- call *%rbx
- movl $0, RAX(%rsp)
- RESTORE_REST
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(ret_from_fork)
-
-/*
- * System call entry. Up to 6 arguments in registers are supported.
+ * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
*
- * SYSCALL does not save anything on the stack and does not change the
- * stack pointer. However, it does mask the flags register for us, so
- * CLD and CLAC are not needed.
- */
-
-/*
- * Register setup:
+ * Registers on entry:
* rax system call number
+ * rcx return address
+ * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
* rdi arg0
- * rcx return address for syscall/sysret, C arg3
* rsi arg1
* rdx arg2
- * r10 arg3 (--> moved to rcx for C)
+ * r10 arg3 (needs to be moved to rcx to conform to C ABI)
* r8 arg4
* r9 arg5
- * r11 eflags for syscall/sysret, temporary for C
- * r12-r15,rbp,rbx saved by C code, not touched.
+ * (note: r12-r15,rbp,rbx are callee-preserved in C ABI)
*
- * Interrupts are off on entry.
* Only called from user space.
*
- * XXX if we had a free scratch register we could save the RSP into the stack frame
- * and report it properly in ps. Unfortunately we haven't.
- *
- * When user can change the frames always force IRET. That is because
+ * When user can change pt_regs->foo always force IRET. That is because
* it deals with uncanonical addresses better. SYSRET has trouble
* with them due to bugs in both AMD and Intel CPUs.
*/
@@ -324,9 +198,15 @@ END(ret_from_fork)
ENTRY(system_call)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
+ CFI_DEF_CFA rsp,0
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
+
+ /*
+ * Interrupts are off on entry.
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
SWAPGS_UNSAFE_STACK
/*
* A hypervisor implementation might want to use a label
@@ -335,18 +215,38 @@ ENTRY(system_call)
*/
GLOBAL(system_call_after_swapgs)
- movq %rsp,PER_CPU_VAR(old_rsp)
+ movq %rsp,PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(kernel_stack),%rsp
+
+ /* Construct struct pt_regs on stack */
+ pushq_cfi $__USER_DS /* pt_regs->ss */
+ pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
/*
- * No need to follow this irqs off/on section - it's straight
- * and short:
+ * Re-enable interrupts.
+ * We use 'rsp_scratch' as a scratch space, hence irq-off block above
+ * must execute atomically in the face of possible interrupt-driven
+ * task preemption. We must enable interrupts only after we're done
+ * with using rsp_scratch:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_ARGS 8, 0, rax_enosys=1
- movq_cfi rax,(ORIG_RAX-ARGOFFSET)
- movq %rcx,RIP-ARGOFFSET(%rsp)
- CFI_REL_OFFSET rip,RIP-ARGOFFSET
- testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+ pushq_cfi %r11 /* pt_regs->flags */
+ pushq_cfi $__USER_CS /* pt_regs->cs */
+ pushq_cfi %rcx /* pt_regs->ip */
+ CFI_REL_OFFSET rip,0
+ pushq_cfi_reg rax /* pt_regs->orig_ax */
+ pushq_cfi_reg rdi /* pt_regs->di */
+ pushq_cfi_reg rsi /* pt_regs->si */
+ pushq_cfi_reg rdx /* pt_regs->dx */
+ pushq_cfi_reg rcx /* pt_regs->cx */
+ pushq_cfi $-ENOSYS /* pt_regs->ax */
+ pushq_cfi_reg r8 /* pt_regs->r8 */
+ pushq_cfi_reg r9 /* pt_regs->r9 */
+ pushq_cfi_reg r10 /* pt_regs->r10 */
+ pushq_cfi_reg r11 /* pt_regs->r11 */
+ sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */
+ CFI_ADJUST_CFA_OFFSET 6*8
+
+ testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
jnz tracesys
system_call_fastpath:
#if __SYSCALL_MASK == ~0
@@ -355,82 +255,96 @@ system_call_fastpath:
andl $__SYSCALL_MASK,%eax
cmpl $__NR_syscall_max,%eax
#endif
- ja ret_from_sys_call /* and return regs->ax */
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
movq %r10,%rcx
- call *sys_call_table(,%rax,8) # XXX: rip relative
- movq %rax,RAX-ARGOFFSET(%rsp)
+ call *sys_call_table(,%rax,8)
+ movq %rax,RAX(%rsp)
+1:
/*
- * Syscall return path ending with SYSRET (fast path)
- * Has incomplete stack frame and undefined top of stack.
+ * Syscall return path ending with SYSRET (fast path).
+ * Has incompletely filled pt_regs.
*/
-ret_from_sys_call:
- testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- jnz int_ret_from_sys_call_fixup /* Go the the slow path */
-
LOCKDEP_SYS_EXIT
+ /*
+ * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
+ * it is too small to ever cause noticeable irq latency.
+ */
DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- CFI_REMEMBER_STATE
+
/*
- * sysretq will re-enable interrupts:
+ * We must check ti flags with interrupts (or at least preemption)
+ * off because we must *never* return to userspace without
+ * processing exit work that is enqueued if we're preempted here.
+ * In particular, returning to userspace with any of the one-shot
+ * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+ * very bad.
*/
- TRACE_IRQS_ON
- movq RIP-ARGOFFSET(%rsp),%rcx
+ testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+ jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */
+
+ CFI_REMEMBER_STATE
+
+ RESTORE_C_REGS_EXCEPT_RCX_R11
+ movq RIP(%rsp),%rcx
CFI_REGISTER rip,rcx
- RESTORE_ARGS 1,-ARG_SKIP,0
+ movq EFLAGS(%rsp),%r11
/*CFI_REGISTER rflags,r11*/
- movq PER_CPU_VAR(old_rsp), %rsp
+ movq RSP(%rsp),%rsp
+ /*
+ * 64bit SYSRET restores rip from rcx,
+ * rflags from r11 (but RF and VM bits are forced to 0),
+ * cs and ss are loaded from MSRs.
+ * Restoration of rflags re-enables interrupts.
+ */
USERGS_SYSRET64
CFI_RESTORE_STATE
-int_ret_from_sys_call_fixup:
- FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
- jmp int_ret_from_sys_call
-
- /* Do syscall tracing */
+ /* Do syscall entry tracing */
tracesys:
- leaq -REST_SKIP(%rsp), %rdi
- movq $AUDIT_ARCH_X86_64, %rsi
+ movq %rsp, %rdi
+ movl $AUDIT_ARCH_X86_64, %esi
call syscall_trace_enter_phase1
test %rax, %rax
jnz tracesys_phase2 /* if needed, run the slow path */
- LOAD_ARGS 0 /* else restore clobbered regs */
+ RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */
+ movq ORIG_RAX(%rsp), %rax
jmp system_call_fastpath /* and return to the fast path */
tracesys_phase2:
- SAVE_REST
- FIXUP_TOP_OF_STACK %rdi
+ SAVE_EXTRA_REGS
movq %rsp, %rdi
- movq $AUDIT_ARCH_X86_64, %rsi
+ movl $AUDIT_ARCH_X86_64, %esi
movq %rax,%rdx
call syscall_trace_enter_phase2
/*
- * Reload arg registers from stack in case ptrace changed them.
+ * Reload registers from stack in case ptrace changed them.
* We don't reload %rax because syscall_trace_entry_phase2() returned
* the value it wants us to use in the table lookup.
*/
- LOAD_ARGS ARGOFFSET, 1
- RESTORE_REST
+ RESTORE_C_REGS_EXCEPT_RAX
+ RESTORE_EXTRA_REGS
#if __SYSCALL_MASK == ~0
cmpq $__NR_syscall_max,%rax
#else
andl $__SYSCALL_MASK,%eax
cmpl $__NR_syscall_max,%eax
#endif
- ja int_ret_from_sys_call /* RAX(%rsp) is already set */
+ ja 1f /* return -ENOSYS (already in pt_regs->ax) */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
- movq %rax,RAX-ARGOFFSET(%rsp)
- /* Use IRET because user could have changed frame */
+ movq %rax,RAX(%rsp)
+1:
+ /* Use IRET because user could have changed pt_regs->foo */
/*
* Syscall return path ending with IRET.
- * Has correct top of stack, but partial stack frame.
+ * Has correct iret frame.
*/
GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
+int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */
TRACE_IRQS_OFF
movl $_TIF_ALLWORK_MASK,%edi
/* edi: mask to check */
@@ -440,8 +354,8 @@ GLOBAL(int_with_check)
movl TI_flags(%rcx),%edx
andl %edi,%edx
jnz int_careful
- andl $~TS_COMPAT,TI_status(%rcx)
- jmp retint_swapgs
+ andl $~TS_COMPAT,TI_status(%rcx)
+ jmp syscall_return
/* Either reschedule or signal or syscall exit tracking needed. */
/* First do a reschedule test. */
@@ -458,12 +372,11 @@ int_careful:
TRACE_IRQS_OFF
jmp int_with_check
- /* handle signals and tracing -- both require a full stack frame */
+ /* handle signals and tracing -- both require a full pt_regs */
int_very_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
-int_check_syscall_exit_work:
- SAVE_REST
+ SAVE_EXTRA_REGS
/* Check for syscall exit trace */
testl $_TIF_WORK_SYSCALL_EXIT,%edx
jz int_signal
@@ -482,86 +395,192 @@ int_signal:
call do_notify_resume
1: movl $_TIF_WORK_MASK,%edi
int_restore_rest:
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
jmp int_with_check
+
+syscall_return:
+ /* The IRETQ could re-enable interrupts: */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_IRETQ
+
+ /*
+ * Try to use SYSRET instead of IRET if we're returning to
+ * a completely clean 64-bit userspace context.
+ */
+ movq RCX(%rsp),%rcx
+ cmpq %rcx,RIP(%rsp) /* RCX == RIP */
+ jne opportunistic_sysret_failed
+
+ /*
+ * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+ * in kernel space. This essentially lets the user take over
+ * the kernel, since userspace controls RSP. It's not worth
+ * testing for canonicalness exactly -- this check detects any
+ * of the 17 high bits set, which is true for non-canonical
+ * or kernel addresses. (This will pessimize vsyscall=native.
+ * Big deal.)
+ *
+ * If virtual addresses ever become wider, this will need
+ * to be updated to remain correct on both old and new CPUs.
+ */
+ .ifne __VIRTUAL_MASK_SHIFT - 47
+ .error "virtual address width changed -- SYSRET checks need update"
+ .endif
+ shr $__VIRTUAL_MASK_SHIFT, %rcx
+ jnz opportunistic_sysret_failed
+
+ cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ movq R11(%rsp),%r11
+ cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */
+ jne opportunistic_sysret_failed
+
+ /*
+ * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
+ * restoring TF results in a trap from userspace immediately after
+ * SYSRET. This would cause an infinite loop whenever #DB happens
+ * with register state that satisfies the opportunistic SYSRET
+ * conditions. For example, single-stepping this user code:
+ *
+ * movq $stuck_here,%rcx
+ * pushfq
+ * popq %r11
+ * stuck_here:
+ *
+ * would never get past 'stuck_here'.
+ */
+ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+ jnz opportunistic_sysret_failed
+
+ /* nothing to check for RSP */
+
+ cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */
+ jne opportunistic_sysret_failed
+
+ /*
+ * We win! This label is here just for ease of understanding
+ * perf profiles. Nothing jumps here.
+ */
+syscall_return_via_sysret:
+ CFI_REMEMBER_STATE
+ /* r11 is already restored (see code above) */
+ RESTORE_C_REGS_EXCEPT_R11
+ movq RSP(%rsp),%rsp
+ USERGS_SYSRET64
+ CFI_RESTORE_STATE
+
+opportunistic_sysret_failed:
+ SWAPGS
+ jmp restore_c_regs_and_iret
CFI_ENDPROC
END(system_call)
+
.macro FORK_LIKE func
ENTRY(stub_\func)
CFI_STARTPROC
- popq %r11 /* save return address */
- PARTIAL_FRAME 0
- SAVE_REST
- pushq %r11 /* put it back on stack */
- FIXUP_TOP_OF_STACK %r11, 8
- DEFAULT_FRAME 0 8 /* offset 8: return address */
- call sys_\func
- RESTORE_TOP_OF_STACK %r11, 8
- ret $REST_SKIP /* pop extended registers */
+ DEFAULT_FRAME 0, 8 /* offset 8: return address */
+ SAVE_EXTRA_REGS 8
+ jmp sys_\func
CFI_ENDPROC
END(stub_\func)
.endm
- .macro FIXED_FRAME label,func
-ENTRY(\label)
- CFI_STARTPROC
- PARTIAL_FRAME 0 8 /* offset 8: return address */
- FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET
- call \func
- RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET
- ret
- CFI_ENDPROC
-END(\label)
- .endm
-
FORK_LIKE clone
FORK_LIKE fork
FORK_LIKE vfork
- FIXED_FRAME stub_iopl, sys_iopl
ENTRY(stub_execve)
CFI_STARTPROC
- addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
- FIXUP_TOP_OF_STACK %r11
- call sys_execve
- movq %rax,RAX(%rsp)
- RESTORE_REST
- jmp int_ret_from_sys_call
+ DEFAULT_FRAME 0, 8
+ call sys_execve
+return_from_execve:
+ testl %eax, %eax
+ jz 1f
+ /* exec failed, can use fast SYSRET code path in this case */
+ ret
+1:
+ /* must use IRET code path (pt_regs->cs may have changed) */
+ addq $8, %rsp
+ CFI_ADJUST_CFA_OFFSET -8
+ ZERO_EXTRA_REGS
+ movq %rax,RAX(%rsp)
+ jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_execve)
-
-ENTRY(stub_execveat)
+/*
+ * Remaining execve stubs are only 7 bytes long.
+ * ENTRY() often aligns to 16 bytes, which in this case has no benefits.
+ */
+ .align 8
+GLOBAL(stub_execveat)
CFI_STARTPROC
- addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
- FIXUP_TOP_OF_STACK %r11
- call sys_execveat
- RESTORE_TOP_OF_STACK %r11
- movq %rax,RAX(%rsp)
- RESTORE_REST
- jmp int_ret_from_sys_call
+ DEFAULT_FRAME 0, 8
+ call sys_execveat
+ jmp return_from_execve
CFI_ENDPROC
END(stub_execveat)
+#ifdef CONFIG_X86_X32_ABI
+ .align 8
+GLOBAL(stub_x32_execve)
+ CFI_STARTPROC
+ DEFAULT_FRAME 0, 8
+ call compat_sys_execve
+ jmp return_from_execve
+ CFI_ENDPROC
+END(stub_x32_execve)
+ .align 8
+GLOBAL(stub_x32_execveat)
+ CFI_STARTPROC
+ DEFAULT_FRAME 0, 8
+ call compat_sys_execveat
+ jmp return_from_execve
+ CFI_ENDPROC
+END(stub_x32_execveat)
+#endif
+
+#ifdef CONFIG_IA32_EMULATION
+ .align 8
+GLOBAL(stub32_execve)
+ CFI_STARTPROC
+ call compat_sys_execve
+ jmp return_from_execve
+ CFI_ENDPROC
+END(stub32_execve)
+ .align 8
+GLOBAL(stub32_execveat)
+ CFI_STARTPROC
+ call compat_sys_execveat
+ jmp return_from_execve
+ CFI_ENDPROC
+END(stub32_execveat)
+#endif
+
/*
* sigreturn is special because it needs to restore all registers on return.
* This cannot be done with SYSRET, so use the IRET return path instead.
*/
ENTRY(stub_rt_sigreturn)
CFI_STARTPROC
- addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
- FIXUP_TOP_OF_STACK %r11
+ DEFAULT_FRAME 0, 8
+ /*
+ * SAVE_EXTRA_REGS result is not normally needed:
+ * sigreturn overwrites all pt_regs->GPREGS.
+ * But sigreturn can fail (!), and there is no easy way to detect that.
+ * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error,
+ * we SAVE_EXTRA_REGS here.
+ */
+ SAVE_EXTRA_REGS 8
call sys_rt_sigreturn
- movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
- RESTORE_REST
+return_from_stub:
+ addq $8, %rsp
+ CFI_ADJUST_CFA_OFFSET -8
+ RESTORE_EXTRA_REGS
+ movq %rax,RAX(%rsp)
jmp int_ret_from_sys_call
CFI_ENDPROC
END(stub_rt_sigreturn)
@@ -569,86 +588,70 @@ END(stub_rt_sigreturn)
#ifdef CONFIG_X86_X32_ABI
ENTRY(stub_x32_rt_sigreturn)
CFI_STARTPROC
- addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
- FIXUP_TOP_OF_STACK %r11
+ DEFAULT_FRAME 0, 8
+ SAVE_EXTRA_REGS 8
call sys32_x32_rt_sigreturn
- movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
- RESTORE_REST
- jmp int_ret_from_sys_call
+ jmp return_from_stub
CFI_ENDPROC
END(stub_x32_rt_sigreturn)
+#endif
-ENTRY(stub_x32_execve)
- CFI_STARTPROC
- addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
- FIXUP_TOP_OF_STACK %r11
- call compat_sys_execve
- RESTORE_TOP_OF_STACK %r11
- movq %rax,RAX(%rsp)
- RESTORE_REST
- jmp int_ret_from_sys_call
- CFI_ENDPROC
-END(stub_x32_execve)
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * rdi: prev task we switched from
+ */
+ENTRY(ret_from_fork)
+ DEFAULT_FRAME
-ENTRY(stub_x32_execveat)
- CFI_STARTPROC
- addq $8, %rsp
- PARTIAL_FRAME 0
- SAVE_REST
- FIXUP_TOP_OF_STACK %r11
- call compat_sys_execveat
- RESTORE_TOP_OF_STACK %r11
- movq %rax,RAX(%rsp)
- RESTORE_REST
+ LOCK ; btr $TIF_FORK,TI_flags(%r8)
+
+ pushq_cfi $0x0002
+ popfq_cfi # reset kernel eflags
+
+ call schedule_tail # rdi: 'prev' task parameter
+
+ RESTORE_EXTRA_REGS
+
+ testl $3,CS(%rsp) # from kernel_thread?
+
+ /*
+ * By the time we get here, we have no idea whether our pt_regs,
+ * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+ * the slow path, or one of the ia32entry paths.
+ * Use IRET code path to return, since it can safely handle
+ * all of the above.
+ */
+ jnz int_ret_from_sys_call
+
+ /* We came from kernel_thread */
+ /* nb: we depend on RESTORE_EXTRA_REGS above */
+ movq %rbp, %rdi
+ call *%rbx
+ movl $0, RAX(%rsp)
+ RESTORE_EXTRA_REGS
jmp int_ret_from_sys_call
CFI_ENDPROC
-END(stub_x32_execveat)
-
-#endif
+END(ret_from_fork)
/*
- * Build the entry stubs and pointer table with some assembler magic.
- * We pack 7 stubs into a single 32-byte chunk, which will fit in a
- * single cache line on all modern x86 implementations.
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
*/
- .section .init.rodata,"a"
-ENTRY(interrupt)
- .section .entry.text
- .p2align 5
- .p2align CONFIG_X86_L1_CACHE_SHIFT
+ .align 8
ENTRY(irq_entries_start)
INTR_FRAME
-vector=FIRST_EXTERNAL_VECTOR
-.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
- .balign 32
- .rept 7
- .if vector < FIRST_SYSTEM_VECTOR
- .if vector <> FIRST_EXTERNAL_VECTOR
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
CFI_ADJUST_CFA_OFFSET -8
- .endif
-1: pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */
- .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
- jmp 2f
- .endif
- .previous
- .quad 1b
- .section .entry.text
-vector=vector+1
- .endif
- .endr
-2: jmp common_interrupt
-.endr
+ .align 8
+ .endr
CFI_ENDPROC
END(irq_entries_start)
-.previous
-END(interrupt)
-.previous
-
/*
* Interrupt entry/exit.
*
@@ -659,47 +662,45 @@ END(interrupt)
/* 0(%rsp): ~(interrupt number) */
.macro interrupt func
- /* reserve pt_regs for scratch regs and rbp */
- subq $ORIG_RAX-RBP, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
cld
- /* start from rbp in pt_regs and jump over */
- movq_cfi rdi, (RDI-RBP)
- movq_cfi rsi, (RSI-RBP)
- movq_cfi rdx, (RDX-RBP)
- movq_cfi rcx, (RCX-RBP)
- movq_cfi rax, (RAX-RBP)
- movq_cfi r8, (R8-RBP)
- movq_cfi r9, (R9-RBP)
- movq_cfi r10, (R10-RBP)
- movq_cfi r11, (R11-RBP)
-
- /* Save rbp so that we can unwind from get_irq_regs() */
- movq_cfi rbp, 0
-
- /* Save previous stack value */
- movq %rsp, %rsi
+ /*
+ * Since nothing in interrupt handling code touches r12...r15 members
+ * of "struct pt_regs", and since interrupts can nest, we can save
+ * four stack slots and simultaneously provide
+ * an unwind-friendly stack layout by saving "truncated" pt_regs
+ * exactly up to rbp slot, without these members.
+ */
+ ALLOC_PT_GPREGS_ON_STACK -RBP
+ SAVE_C_REGS -RBP
+ /* this goes to 0(%rsp) for unwinder, not for saving the value: */
+ SAVE_EXTRA_REGS_RBP -RBP
- leaq -RBP(%rsp),%rdi /* arg1 for handler */
- testl $3, CS-RBP(%rsi)
+ leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */
+
+ testl $3, CS-RBP(%rsp)
je 1f
SWAPGS
+1:
/*
+ * Save previous stack pointer, optionally switch to interrupt stack.
* irq_count is used to check if a CPU is already on an interrupt stack
* or not. While this is essentially redundant with preempt_count it is
* a little cheaper to use a separate counter in the PDA (short of
* moving irq_enter into assembly, which would be too much work)
*/
-1: incl PER_CPU_VAR(irq_count)
+ movq %rsp, %rsi
+ incl PER_CPU_VAR(irq_count)
cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
CFI_DEF_CFA_REGISTER rsi
-
- /* Store previous stack value */
pushq %rsi
+ /*
+ * For debugger:
+ * "CFA (Current Frame Address) is the value on stack + offset"
+ */
CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
- 0x77 /* DW_OP_breg7 */, 0, \
+ 0x77 /* DW_OP_breg7 (rsp) */, 0, \
0x06 /* DW_OP_deref */, \
- 0x08 /* DW_OP_const1u */, SS+8-RBP, \
+ 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \
0x22 /* DW_OP_plus */
/* We entered an interrupt context - irqs are off: */
TRACE_IRQS_OFF
@@ -717,7 +718,7 @@ common_interrupt:
ASM_CLAC
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): old_rsp-ARGOFFSET */
+ /* 0(%rsp): old RSP */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -725,19 +726,18 @@ ret_from_intr:
/* Restore saved previous stack */
popq %rsi
- CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */
- leaq ARGOFFSET-RBP(%rsi), %rsp
+ CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */
+ /* return code expects complete pt_regs - adjust rsp accordingly: */
+ leaq -RBP(%rsi),%rsp
CFI_DEF_CFA_REGISTER rsp
- CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET
+ CFI_ADJUST_CFA_OFFSET RBP
-exit_intr:
- GET_THREAD_INFO(%rcx)
- testl $3,CS-ARGOFFSET(%rsp)
+ testl $3,CS(%rsp)
je retint_kernel
-
/* Interrupt came from user space */
+
+ GET_THREAD_INFO(%rcx)
/*
- * Has a correct top of stack, but a partial stack frame
* %rcx: thread info. Interrupts off.
*/
retint_with_reschedule:
@@ -756,70 +756,34 @@ retint_swapgs: /* return to user-space */
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_IRETQ
- /*
- * Try to use SYSRET instead of IRET if we're returning to
- * a completely clean 64-bit userspace context.
- */
- movq (RCX-R11)(%rsp), %rcx
- cmpq %rcx,(RIP-R11)(%rsp) /* RCX == RIP */
- jne opportunistic_sysret_failed
-
- /*
- * On Intel CPUs, sysret with non-canonical RCX/RIP will #GP
- * in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP. It's not worth
- * testing for canonicalness exactly -- this check detects any
- * of the 17 high bits set, which is true for non-canonical
- * or kernel addresses. (This will pessimize vsyscall=native.
- * Big deal.)
- *
- * If virtual addresses ever become wider, this will need
- * to be updated to remain correct on both old and new CPUs.
- */
- .ifne __VIRTUAL_MASK_SHIFT - 47
- .error "virtual address width changed -- sysret checks need update"
- .endif
- shr $__VIRTUAL_MASK_SHIFT, %rcx
- jnz opportunistic_sysret_failed
-
- cmpq $__USER_CS,(CS-R11)(%rsp) /* CS must match SYSRET */
- jne opportunistic_sysret_failed
-
- movq (R11-ARGOFFSET)(%rsp), %r11
- cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp) /* R11 == RFLAGS */
- jne opportunistic_sysret_failed
-
- testq $X86_EFLAGS_RF,%r11 /* sysret can't restore RF */
- jnz opportunistic_sysret_failed
-
- /* nothing to check for RSP */
-
- cmpq $__USER_DS,(SS-ARGOFFSET)(%rsp) /* SS must match SYSRET */
- jne opportunistic_sysret_failed
-
- /*
- * We win! This label is here just for ease of understanding
- * perf profiles. Nothing jumps here.
- */
-irq_return_via_sysret:
- CFI_REMEMBER_STATE
- RESTORE_ARGS 1,8,1
- movq (RSP-RIP)(%rsp),%rsp
- USERGS_SYSRET64
- CFI_RESTORE_STATE
-
-opportunistic_sysret_failed:
SWAPGS
- jmp restore_args
+ jmp restore_c_regs_and_iret
-retint_restore_args: /* return to kernel space */
- DISABLE_INTERRUPTS(CLBR_ANY)
+/* Returning to kernel space */
+retint_kernel:
+#ifdef CONFIG_PREEMPT
+ /* Interrupts are off */
+ /* Check if we need preemption */
+ bt $9,EFLAGS(%rsp) /* interrupts were off? */
+ jnc 1f
+0: cmpl $0,PER_CPU_VAR(__preempt_count)
+ jnz 1f
+ call preempt_schedule_irq
+ jmp 0b
+1:
+#endif
/*
* The iretq could re-enable interrupts:
*/
TRACE_IRQS_IRETQ
-restore_args:
- RESTORE_ARGS 1,8,1
+
+/*
+ * At this label, code paths which return to kernel and to user,
+ * which come from interrupts/exception and from syscalls, merge.
+ */
+restore_c_regs_and_iret:
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
irq_return:
INTERRUPT_RETURN
@@ -890,28 +854,17 @@ retint_signal:
jz retint_swapgs
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_REST
+ SAVE_EXTRA_REGS
movq $-1,ORIG_RAX(%rsp)
xorl %esi,%esi # oldset
movq %rsp,%rdi # &pt_regs
call do_notify_resume
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
jmp retint_with_reschedule
-#ifdef CONFIG_PREEMPT
- /* Returning to kernel space. Check if we need preemption */
- /* rcx: threadinfo. interrupts off. */
-ENTRY(retint_kernel)
- cmpl $0,PER_CPU_VAR(__preempt_count)
- jnz retint_restore_args
- bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
- jnc retint_restore_args
- call preempt_schedule_irq
- jmp exit_intr
-#endif
CFI_ENDPROC
END(common_interrupt)
@@ -1000,7 +953,7 @@ apicinterrupt IRQ_WORK_VECTOR \
/*
* Exception entry points.
*/
-#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
@@ -1022,8 +975,7 @@ ENTRY(\sym)
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
.endif
- subq $ORIG_RAX-R15, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
+ ALLOC_PT_GPREGS_ON_STACK
.if \paranoid
.if \paranoid == 1
@@ -1031,10 +983,11 @@ ENTRY(\sym)
testl $3, CS(%rsp) /* If coming from userspace, switch */
jnz 1f /* stacks. */
.endif
- call save_paranoid
+ call paranoid_entry
.else
call error_entry
.endif
+ /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
DEFAULT_FRAME 0
@@ -1056,19 +1009,20 @@ ENTRY(\sym)
.endif
.if \shift_ist != -1
- subq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist)
+ subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
.endif
call \do_sym
.if \shift_ist != -1
- addq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist)
+ addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
.endif
+ /* these procedures expect "no swapgs" flag in ebx */
.if \paranoid
- jmp paranoid_exit /* %ebx: no swapgs flag */
+ jmp paranoid_exit
.else
- jmp error_exit /* %ebx: no swapgs flag */
+ jmp error_exit
.endif
.if \paranoid == 1
@@ -1272,7 +1226,9 @@ ENTRY(xen_failsafe_callback)
addq $0x30,%rsp
CFI_ADJUST_CFA_OFFSET -0x30
pushq_cfi $-1 /* orig_ax = -1 => not a system call */
- SAVE_ALL
+ ALLOC_PT_GPREGS_ON_STACK
+ SAVE_C_REGS
+ SAVE_EXTRA_REGS
jmp error_exit
CFI_ENDPROC
END(xen_failsafe_callback)
@@ -1304,59 +1260,66 @@ idtentry async_page_fault do_async_page_fault has_error_code=1
idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip)
#endif
- /*
- * "Paranoid" exit path from exception stack. This is invoked
- * only on return from non-NMI IST interrupts that came
- * from kernel space.
- *
- * We may be returning to very strange contexts (e.g. very early
- * in syscall entry), so checking for preemption here would
- * be complicated. Fortunately, we there's no good reason
- * to try to handle preemption here.
- */
+/*
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Use slow, but surefire "are we in kernel?" check.
+ * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ */
+ENTRY(paranoid_entry)
+ XCPT_FRAME 1 15*8
+ cld
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
+ movl $1,%ebx
+ movl $MSR_GS_BASE,%ecx
+ rdmsr
+ testl %edx,%edx
+ js 1f /* negative -> in kernel */
+ SWAPGS
+ xorl %ebx,%ebx
+1: ret
+ CFI_ENDPROC
+END(paranoid_entry)
- /* ebx: no swapgs flag */
+/*
+ * "Paranoid" exit path from exception stack. This is invoked
+ * only on return from non-NMI IST interrupts that came
+ * from kernel space.
+ *
+ * We may be returning to very strange contexts (e.g. very early
+ * in syscall entry), so checking for preemption here would
+ * be complicated. Fortunately, we there's no good reason
+ * to try to handle preemption here.
+ */
+/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
ENTRY(paranoid_exit)
DEFAULT_FRAME
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF_DEBUG
testl %ebx,%ebx /* swapgs needed? */
- jnz paranoid_restore
- TRACE_IRQS_IRETQ 0
+ jnz paranoid_exit_no_swapgs
+ TRACE_IRQS_IRETQ
SWAPGS_UNSAFE_STACK
- RESTORE_ALL 8
- INTERRUPT_RETURN
-paranoid_restore:
- TRACE_IRQS_IRETQ_DEBUG 0
- RESTORE_ALL 8
+ jmp paranoid_exit_restore
+paranoid_exit_no_swapgs:
+ TRACE_IRQS_IRETQ_DEBUG
+paranoid_exit_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
+ REMOVE_PT_GPREGS_FROM_STACK 8
INTERRUPT_RETURN
CFI_ENDPROC
END(paranoid_exit)
/*
- * Exception entry point. This expects an error code/orig_rax on the stack.
- * returns in "no swapgs flag" in %ebx.
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
*/
ENTRY(error_entry)
- XCPT_FRAME
- CFI_ADJUST_CFA_OFFSET 15*8
- /* oldrax contains error code */
+ XCPT_FRAME 1 15*8
cld
- movq %rdi, RDI+8(%rsp)
- movq %rsi, RSI+8(%rsp)
- movq %rdx, RDX+8(%rsp)
- movq %rcx, RCX+8(%rsp)
- movq %rax, RAX+8(%rsp)
- movq %r8, R8+8(%rsp)
- movq %r9, R9+8(%rsp)
- movq %r10, R10+8(%rsp)
- movq %r11, R11+8(%rsp)
- movq_cfi rbx, RBX+8
- movq %rbp, RBP+8(%rsp)
- movq %r12, R12+8(%rsp)
- movq %r13, R13+8(%rsp)
- movq %r14, R14+8(%rsp)
- movq %r15, R15+8(%rsp)
+ SAVE_C_REGS 8
+ SAVE_EXTRA_REGS 8
xorl %ebx,%ebx
testl $3,CS+8(%rsp)
je error_kernelspace
@@ -1366,12 +1329,12 @@ error_sti:
TRACE_IRQS_OFF
ret
-/*
- * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. B stepping K8s sometimes report a
- * truncated RIP for IRET exceptions returning to compat mode. Check
- * for these here too.
- */
+ /*
+ * There are two places in the kernel that can potentially fault with
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
+ */
error_kernelspace:
CFI_REL_OFFSET rcx, RCX+8
incl %ebx
@@ -1401,11 +1364,11 @@ error_bad_iret:
END(error_entry)
-/* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */
+/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */
ENTRY(error_exit)
DEFAULT_FRAME
movl %ebx,%eax
- RESTORE_REST
+ RESTORE_EXTRA_REGS
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
@@ -1420,19 +1383,7 @@ ENTRY(error_exit)
CFI_ENDPROC
END(error_exit)
-/*
- * Test if a given stack is an NMI stack or not.
- */
- .macro test_in_nmi reg stack nmi_ret normal_ret
- cmpq %\reg, \stack
- ja \normal_ret
- subq $EXCEPTION_STKSZ, %\reg
- cmpq %\reg, \stack
- jb \normal_ret
- jmp \nmi_ret
- .endm
-
- /* runs on exception stack */
+/* Runs on exception stack */
ENTRY(nmi)
INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
@@ -1468,7 +1419,7 @@ ENTRY(nmi)
* NMI.
*/
- /* Use %rdx as out temp variable throughout */
+ /* Use %rdx as our temp variable throughout */
pushq_cfi %rdx
CFI_REL_OFFSET rdx, 0
@@ -1493,8 +1444,17 @@ ENTRY(nmi)
* We check the variable because the first NMI could be in a
* breakpoint routine using a breakpoint stack.
*/
- lea 6*8(%rsp), %rdx
- test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi
+ lea 6*8(%rsp), %rdx
+ /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
+ cmpq %rdx, 4*8(%rsp)
+ /* If the stack pointer is above the NMI stack, this is a normal NMI */
+ ja first_nmi
+ subq $EXCEPTION_STKSZ, %rdx
+ cmpq %rdx, 4*8(%rsp)
+ /* If it is below the NMI stack, it is a normal NMI */
+ jb first_nmi
+ /* Ah, it is within the NMI stack, treat it as nested */
+
CFI_REMEMBER_STATE
nested_nmi:
@@ -1587,7 +1547,7 @@ first_nmi:
.rept 5
pushq_cfi 11*8(%rsp)
.endr
- CFI_DEF_CFA_OFFSET SS+8-RIP
+ CFI_DEF_CFA_OFFSET 5*8
/* Everything up to here is safe from nested NMIs */
@@ -1615,7 +1575,7 @@ repeat_nmi:
pushq_cfi -6*8(%rsp)
.endr
subq $(5*8), %rsp
- CFI_DEF_CFA_OFFSET SS+8-RIP
+ CFI_DEF_CFA_OFFSET 5*8
end_repeat_nmi:
/*
@@ -1624,16 +1584,16 @@ end_repeat_nmi:
* so that we repeat another NMI.
*/
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
- subq $ORIG_RAX-R15, %rsp
- CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
+ ALLOC_PT_GPREGS_ON_STACK
+
/*
- * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit
+ * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
* as we should not be calling schedule in NMI context.
* Even with normal interrupts enabled. An NMI should not be
* setting NEED_RESCHED or anything that normal interrupts and
* exceptions might do.
*/
- call save_paranoid
+ call paranoid_entry
DEFAULT_FRAME 0
/*
@@ -1664,8 +1624,10 @@ end_repeat_nmi:
nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
+ RESTORE_EXTRA_REGS
+ RESTORE_C_REGS
/* Pop the extra iret frame at once */
- RESTORE_ALL 6*8
+ REMOVE_PT_GPREGS_FROM_STACK 6*8
/* Clear the NMI executing stack variable */
movq $0, 5*8(%rsp)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index c4f8d4659070..2b55ee6db053 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -177,9 +177,6 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
*/
load_ucode_bsp();
- if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
- early_printk("Kernel alive\n");
-
clear_page(init_level4_pgt);
/* set init_level4_pgt kernel high mapping*/
init_level4_pgt[511] = early_level4_pgt[511];
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index f36bd42d6f0c..d031bad9e07e 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -22,6 +22,7 @@
#include <asm/cpufeature.h>
#include <asm/percpu.h>
#include <asm/nops.h>
+#include <asm/bootparam.h>
/* Physical address */
#define pa(X) ((X) - __PAGE_OFFSET)
@@ -90,7 +91,7 @@ ENTRY(startup_32)
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
us to not reload segments */
- testb $(1<<6), BP_loadflags(%esi)
+ testb $KEEP_SEGMENTS, BP_loadflags(%esi)
jnz 2f
/*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 6fd514d9f69a..ae6588b301c2 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -1,5 +1,5 @@
/*
- * linux/arch/x86_64/kernel/head.S -- start in 32bit and switch to 64bit
+ * linux/arch/x86/kernel/head_64.S -- start in 32bit and switch to 64bit
*
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
* Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
@@ -56,7 +56,7 @@ startup_64:
* %rsi holds a physical pointer to real_mode_data.
*
* We come here either directly from a 64bit bootloader, or from
- * arch/x86_64/boot/compressed/head.S.
+ * arch/x86/boot/compressed/head_64.S.
*
* We only come here initially at boot nothing else comes here.
*
@@ -146,7 +146,7 @@ startup_64:
leaq level2_kernel_pgt(%rip), %rdi
leaq 4096(%rdi), %r8
/* See if it is a valid page table entry */
-1: testq $1, 0(%rdi)
+1: testb $1, 0(%rdi)
jz 2f
addq %rbp, 0(%rdi)
/* Go to the next page */
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index d5651fce0b71..29c740deafec 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -68,7 +68,7 @@ static inline bool interrupted_kernel_fpu_idle(void)
static inline bool interrupted_user_mode(void)
{
struct pt_regs *regs = get_irq_regs();
- return regs && user_mode_vm(regs);
+ return regs && user_mode(regs);
}
/*
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 4ddaf66ea35f..37dae792dbbe 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -54,7 +54,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
* because the ->io_bitmap_max value must match the bitmap
* contents:
*/
- tss = &per_cpu(init_tss, get_cpu());
+ tss = &per_cpu(cpu_tss, get_cpu());
if (turn_on)
bitmap_clear(t->io_bitmap_ptr, from, num);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 67b1cbe0093a..e5952c225532 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -295,7 +295,7 @@ int check_irq_vectors_for_cpu_disable(void)
this_cpu = smp_processor_id();
cpumask_copy(&online_new, cpu_online_mask);
- cpu_clear(this_cpu, online_new);
+ cpumask_clear_cpu(this_cpu, &online_new);
this_count = 0;
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
@@ -307,7 +307,7 @@ int check_irq_vectors_for_cpu_disable(void)
data = irq_desc_get_irq_data(desc);
cpumask_copy(&affinity_new, data->affinity);
- cpu_clear(this_cpu, affinity_new);
+ cpumask_clear_cpu(this_cpu, &affinity_new);
/* Do not count inactive or per-cpu irqs. */
if (!irq_has_action(irq) || irqd_is_per_cpu(data))
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 28d28f5eb8f4..f9fd86a7fcc7 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -165,7 +165,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs)
if (unlikely(!desc))
return false;
- if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
+ if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
if (unlikely(overflow))
print_stack_overflow();
desc->handle_irq(irq, desc);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index e4b503d5558c..394e643d7830 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -44,7 +44,7 @@ static inline void stack_overflow_check(struct pt_regs *regs)
u64 estack_top, estack_bottom;
u64 curbase = (u64)task_stack_page(current);
- if (user_mode_vm(regs))
+ if (user_mode(regs))
return;
if (regs->sp >= curbase + sizeof(struct thread_info) +
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 70e181ea1eac..cd10a6437264 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -178,7 +178,8 @@ void __init native_init_IRQ(void)
#endif
for_each_clear_bit_from(i, used_vectors, first_system_vector) {
/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
- set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
+ set_intr_gate(i, irq_entries_start +
+ 8 * (i - FIRST_EXTERNAL_VECTOR));
}
#ifdef CONFIG_X86_LOCAL_APIC
for_each_clear_bit_from(i, used_vectors, NR_VECTORS)
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 7ec1d5f8d283..d6178d9791db 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -72,7 +72,7 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
{ "bx", 8, offsetof(struct pt_regs, bx) },
{ "cx", 8, offsetof(struct pt_regs, cx) },
{ "dx", 8, offsetof(struct pt_regs, dx) },
- { "si", 8, offsetof(struct pt_regs, dx) },
+ { "si", 8, offsetof(struct pt_regs, si) },
{ "di", 8, offsetof(struct pt_regs, di) },
{ "bp", 8, offsetof(struct pt_regs, bp) },
{ "sp", 8, offsetof(struct pt_regs, sp) },
@@ -126,11 +126,11 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
#ifdef CONFIG_X86_32
switch (regno) {
case GDB_SS:
- if (!user_mode_vm(regs))
+ if (!user_mode(regs))
*(unsigned long *)mem = __KERNEL_DS;
break;
case GDB_SP:
- if (!user_mode_vm(regs))
+ if (!user_mode(regs))
*(unsigned long *)mem = kernel_stack_pointer(regs);
break;
case GDB_GS:
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 4e3d5a9621fe..24d079604fd5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -602,7 +602,7 @@ int kprobe_int3_handler(struct pt_regs *regs)
struct kprobe *p;
struct kprobe_ctlblk *kcb;
- if (user_mode_vm(regs))
+ if (user_mode(regs))
return 0;
addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
@@ -1007,7 +1007,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
struct die_args *args = data;
int ret = NOTIFY_DONE;
- if (args->regs && user_mode_vm(args->regs))
+ if (args->regs && user_mode(args->regs))
return ret;
if (val == DIE_GPF) {
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 9bbb9b35c144..005c03e93fc5 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -33,6 +33,7 @@
#include <asm/page.h>
#include <asm/pgtable.h>
+#include <asm/setup.h>
#if 0
#define DEBUGP(fmt, ...) \
@@ -53,7 +54,7 @@ static DEFINE_MUTEX(module_kaslr_mutex);
static unsigned long int get_module_load_offset(void)
{
- if (kaslr_enabled) {
+ if (kaslr_enabled()) {
mutex_lock(&module_kaslr_mutex);
/*
* Calculate the module_load_offset the first time this
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 781861cc5ee8..da8cb987b973 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -131,10 +131,11 @@ void perf_get_regs_user(struct perf_regs *regs_user,
}
/*
- * RIP, flags, and the argument registers are usually saved.
- * orig_ax is probably okay, too.
+ * These registers are always saved on 64-bit syscall entry.
+ * On 32-bit entry points, they are saved too except r8..r11.
*/
regs_user_copy->ip = user_regs->ip;
+ regs_user_copy->ax = user_regs->ax;
regs_user_copy->cx = user_regs->cx;
regs_user_copy->dx = user_regs->dx;
regs_user_copy->si = user_regs->si;
@@ -145,9 +146,12 @@ void perf_get_regs_user(struct perf_regs *regs_user,
regs_user_copy->r11 = user_regs->r11;
regs_user_copy->orig_ax = user_regs->orig_ax;
regs_user_copy->flags = user_regs->flags;
+ regs_user_copy->sp = user_regs->sp;
+ regs_user_copy->cs = user_regs->cs;
+ regs_user_copy->ss = user_regs->ss;
/*
- * Don't even try to report the "rest" regs.
+ * Most system calls don't save these registers, don't report them.
*/
regs_user_copy->bx = -1;
regs_user_copy->bp = -1;
@@ -158,37 +162,13 @@ void perf_get_regs_user(struct perf_regs *regs_user,
/*
* For this to be at all useful, we need a reasonable guess for
- * sp and the ABI. Be careful: we're in NMI context, and we're
+ * the ABI. Be careful: we're in NMI context, and we're
* considering current to be the current task, so we should
* be careful not to look at any other percpu variables that might
* change during context switches.
*/
- if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
- task_thread_info(current)->status & TS_COMPAT) {
- /* Easy case: we're in a compat syscall. */
- regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
- regs_user_copy->sp = user_regs->sp;
- regs_user_copy->cs = user_regs->cs;
- regs_user_copy->ss = user_regs->ss;
- } else if (user_regs->orig_ax != -1) {
- /*
- * We're probably in a 64-bit syscall.
- * Warning: this code is severely racy. At least it's better
- * than just blindly copying user_regs.
- */
- regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
- regs_user_copy->sp = this_cpu_read(old_rsp);
- regs_user_copy->cs = __USER_CS;
- regs_user_copy->ss = __USER_DS;
- regs_user_copy->cx = -1; /* usually contains garbage */
- } else {
- /* We're probably in an interrupt or exception. */
- regs_user->abi = user_64bit_mode(user_regs) ?
- PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
- regs_user_copy->sp = user_regs->sp;
- regs_user_copy->cs = user_regs->cs;
- regs_user_copy->ss = user_regs->ss;
- }
+ regs_user->abi = user_64bit_mode(user_regs) ?
+ PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
regs_user->regs = regs_user_copy;
}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 046e2d620bbe..0c8992dbead5 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -9,7 +9,7 @@
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/pm.h>
-#include <linux/clockchips.h>
+#include <linux/tick.h>
#include <linux/random.h>
#include <linux/user-return-notifier.h>
#include <linux/dmi.h>
@@ -24,6 +24,7 @@
#include <asm/syscalls.h>
#include <asm/idle.h>
#include <asm/uaccess.h>
+#include <asm/mwait.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/debugreg.h>
@@ -37,7 +38,26 @@
* section. Since TSS's are completely CPU-local, we want them
* on exact cacheline boundaries, to eliminate cacheline ping-pong.
*/
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+ .x86_tss = {
+ .sp0 = TOP_OF_INIT_STACK,
+#ifdef CONFIG_X86_32
+ .ss0 = __KERNEL_DS,
+ .ss1 = __KERNEL_CS,
+ .io_bitmap_base = INVALID_IO_BITMAP_OFFSET,
+#endif
+ },
+#ifdef CONFIG_X86_32
+ /*
+ * Note that the .io_bitmap member must be extra-big. This is because
+ * the CPU will access an additional byte beyond the end of the IO
+ * permission bitmap. The extra byte must be all 1 bits, and must
+ * be within the limit.
+ */
+ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 },
+#endif
+};
+EXPORT_PER_CPU_SYMBOL_GPL(cpu_tss);
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU(unsigned char, is_idle);
@@ -109,7 +129,7 @@ void exit_thread(void)
unsigned long *bp = t->io_bitmap_ptr;
if (bp) {
- struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
+ struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
t->io_bitmap_ptr = NULL;
clear_thread_flag(TIF_IO_BITMAP);
@@ -377,14 +397,11 @@ static void amd_e400_idle(void)
if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
cpumask_set_cpu(cpu, amd_e400_c1e_mask);
- /*
- * Force broadcast so ACPI can not interfere.
- */
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
- &cpu);
+ /* Force broadcast so ACPI can not interfere. */
+ tick_broadcast_force();
pr_info("Switch to broadcast mode on CPU%d\n", cpu);
}
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+ tick_broadcast_enter();
default_idle();
@@ -393,12 +410,59 @@ static void amd_e400_idle(void)
* called with interrupts disabled.
*/
local_irq_disable();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+ tick_broadcast_exit();
local_irq_enable();
} else
default_idle();
}
+/*
+ * Intel Core2 and older machines prefer MWAIT over HALT for C1.
+ * We can't rely on cpuidle installing MWAIT, because it will not load
+ * on systems that support only C1 -- so the boot default must be MWAIT.
+ *
+ * Some AMD machines are the opposite, they depend on using HALT.
+ *
+ * So for default C1, which is used during boot until cpuidle loads,
+ * use MWAIT-C1 on Intel HW that has it, else use HALT.
+ */
+static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
+{
+ if (c->x86_vendor != X86_VENDOR_INTEL)
+ return 0;
+
+ if (!cpu_has(c, X86_FEATURE_MWAIT))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * MONITOR/MWAIT with no hints, used for default default C1 state.
+ * This invokes MWAIT with interrutps enabled and no flags,
+ * which is backwards compatible with the original MWAIT implementation.
+ */
+
+static void mwait_idle(void)
+{
+ if (!current_set_polling_and_test()) {
+ if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
+ smp_mb(); /* quirk */
+ clflush((void *)&current_thread_info()->flags);
+ smp_mb(); /* quirk */
+ }
+
+ __monitor((void *)&current_thread_info()->flags, 0, 0);
+ if (!need_resched())
+ __sti_mwait(0, 0);
+ else
+ local_irq_enable();
+ } else {
+ local_irq_enable();
+ }
+ __current_clr_polling();
+}
+
void select_idle_routine(const struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
@@ -412,6 +476,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c)
/* E400: APIC timer interrupt does not wake up CPU from C1e */
pr_info("using AMD E400 aware idle routine\n");
x86_idle = amd_e400_idle;
+ } else if (prefer_mwait_c1_over_halt(c)) {
+ pr_info("using mwait in idle threads\n");
+ x86_idle = mwait_idle;
} else
x86_idle = default_idle;
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 603c4f99cb5a..8ed2106b06da 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -73,7 +73,7 @@ void __show_regs(struct pt_regs *regs, int all)
unsigned long sp;
unsigned short ss, gs;
- if (user_mode_vm(regs)) {
+ if (user_mode(regs)) {
sp = regs->sp;
ss = regs->ss & 0xffff;
gs = get_user_gs(regs);
@@ -206,11 +206,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
regs->ip = new_ip;
regs->sp = new_sp;
regs->flags = X86_EFLAGS_IF;
- /*
- * force it to the iret return path by making it look as if there was
- * some work pending.
- */
- set_thread_flag(TIF_NOTIFY_RESUME);
+ force_iret();
}
EXPORT_SYMBOL_GPL(start_thread);
@@ -248,7 +244,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct thread_struct *prev = &prev_p->thread,
*next = &next_p->thread;
int cpu = smp_processor_id();
- struct tss_struct *tss = &per_cpu(init_tss, cpu);
+ struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
fpu_switch_t fpu;
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
@@ -256,11 +252,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
/*
- * Reload esp0.
- */
- load_sp0(tss, next);
-
- /*
* Save away %gs. No need to save %fs, as it was saved on the
* stack on entry. No need to save %es and %ds, as those are
* always kernel segments while inside the kernel. Doing this
@@ -310,9 +301,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
*/
arch_end_context_switch(next_p);
+ /*
+ * Reload esp0, kernel_stack, and current_top_of_stack. This changes
+ * current_thread_info().
+ */
+ load_sp0(tss, next);
this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - KERNEL_STACK_OFFSET);
+ (unsigned long)task_stack_page(next_p) +
+ THREAD_SIZE);
+ this_cpu_write(cpu_current_top_of_stack,
+ (unsigned long)task_stack_page(next_p) +
+ THREAD_SIZE);
/*
* Restore %gs if needed (which is common)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 67fcc43577d2..4baaa972f52a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
asmlinkage extern void ret_from_fork(void);
-__visible DEFINE_PER_CPU(unsigned long, old_rsp);
+__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
@@ -161,7 +161,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
childregs = task_pt_regs(p);
p->thread.sp = (unsigned long) childregs;
- p->thread.usersp = me->thread.usersp;
set_tsk_thread_flag(p, TIF_FORK);
p->thread.io_bitmap_ptr = NULL;
@@ -207,7 +206,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
*/
if (clone_flags & CLONE_SETTLS) {
#ifdef CONFIG_IA32_EMULATION
- if (test_thread_flag(TIF_IA32))
+ if (is_ia32_task())
err = do_set_thread_area(p, -1,
(struct user_desc __user *)childregs->si, 0);
else
@@ -235,13 +234,12 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
loadsegment(es, _ds);
loadsegment(ds, _ds);
load_gs_index(0);
- current->thread.usersp = new_sp;
regs->ip = new_ip;
regs->sp = new_sp;
- this_cpu_write(old_rsp, new_sp);
regs->cs = _cs;
regs->ss = _ss;
regs->flags = X86_EFLAGS_IF;
+ force_iret();
}
void
@@ -277,15 +275,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
struct thread_struct *prev = &prev_p->thread;
struct thread_struct *next = &next_p->thread;
int cpu = smp_processor_id();
- struct tss_struct *tss = &per_cpu(init_tss, cpu);
+ struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
unsigned fsindex, gsindex;
fpu_switch_t fpu;
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
- /* Reload esp0 and ss1. */
- load_sp0(tss, next);
-
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
*
@@ -401,8 +396,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/*
* Switch the PDA and FPU contexts.
*/
- prev->usersp = this_cpu_read(old_rsp);
- this_cpu_write(old_rsp, next->usersp);
this_cpu_write(current_task, next_p);
/*
@@ -413,9 +406,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+ /* Reload esp0 and ss1. This changes current_thread_info(). */
+ load_sp0(tss, next);
+
this_cpu_write(kernel_stack,
- (unsigned long)task_stack_page(next_p) +
- THREAD_SIZE - KERNEL_STACK_OFFSET);
+ (unsigned long)task_stack_page(next_p) + THREAD_SIZE);
/*
* Now maybe reload the debug registers and handle I/O bitmaps
@@ -602,6 +597,5 @@ long sys_arch_prctl(int code, unsigned long addr)
unsigned long KSTK_ESP(struct task_struct *task)
{
- return (test_tsk_thread_flag(task, TIF_IA32)) ?
- (task_pt_regs(task)->sp) : ((task)->thread.usersp);
+ return task_pt_regs(task)->sp;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index e510618b2e91..a7bc79480719 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -364,18 +364,12 @@ static int set_segment_reg(struct task_struct *task,
case offsetof(struct user_regs_struct,cs):
if (unlikely(value == 0))
return -EIO;
-#ifdef CONFIG_IA32_EMULATION
- if (test_tsk_thread_flag(task, TIF_IA32))
- task_pt_regs(task)->cs = value;
-#endif
+ task_pt_regs(task)->cs = value;
break;
case offsetof(struct user_regs_struct,ss):
if (unlikely(value == 0))
return -EIO;
-#ifdef CONFIG_IA32_EMULATION
- if (test_tsk_thread_flag(task, TIF_IA32))
- task_pt_regs(task)->ss = value;
-#endif
+ task_pt_regs(task)->ss = value;
break;
}
@@ -1421,7 +1415,7 @@ static void fill_sigtrap_info(struct task_struct *tsk,
memset(info, 0, sizeof(*info));
info->si_signo = SIGTRAP;
info->si_code = si_code;
- info->si_addr = user_mode_vm(regs) ? (void __user *)regs->ip : NULL;
+ info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL;
}
void user_single_step_siginfo(struct task_struct *tsk,
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d229a58..e5ecd20e72dd 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
+static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
+
+static struct pvclock_vsyscall_time_info *
+pvclock_get_vsyscall_user_time_info(int cpu)
+{
+ if (!pvclock_vdso_info) {
+ BUG();
+ return NULL;
+ }
+
+ return &pvclock_vdso_info[cpu];
+}
+
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
+{
+ return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
+}
+
#ifdef CONFIG_X86_64
+static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
+ void *v)
+{
+ struct task_migration_notifier *mn = v;
+ struct pvclock_vsyscall_time_info *pvti;
+
+ pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
+
+ /* this is NULL when pvclock vsyscall is not initialized */
+ if (unlikely(pvti == NULL))
+ return NOTIFY_DONE;
+
+ pvti->migrate_count++;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block pvclock_migrate = {
+ .notifier_call = pvclock_task_migrate,
+};
+
/*
* Initialize the generic pvclock vsyscall state. This will allocate
* a/some page(s) for the per-vcpu pvclock information, set up a
@@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
+ pvclock_vdso_info = i;
+
for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
__pa(i) + (idx*PAGE_SIZE),
PAGE_KERNEL_VVAR);
}
+
+ register_task_migration_notifier(&pvclock_migrate);
+
return 0;
}
#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index bae6c609888e..86db4bcd7ce5 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -183,6 +183,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
},
},
+ /* ASRock */
+ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */
+ .callback = set_pci_reboot,
+ .ident = "ASRock Q1900DC-ITX",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"),
+ DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"),
+ },
+ },
+
/* ASUS */
{ /* Handle problems with rebooting on ASUS P4S800 */
.callback = set_bios_reboot,
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index e13f8e7c22a6..77630d57e7bf 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -226,23 +226,23 @@ swap_pages:
movl (%ebx), %ecx
addl $4, %ebx
1:
- testl $0x1, %ecx /* is it a destination page */
+ testb $0x1, %cl /* is it a destination page */
jz 2f
movl %ecx, %edi
andl $0xfffff000, %edi
jmp 0b
2:
- testl $0x2, %ecx /* is it an indirection page */
+ testb $0x2, %cl /* is it an indirection page */
jz 2f
movl %ecx, %ebx
andl $0xfffff000, %ebx
jmp 0b
2:
- testl $0x4, %ecx /* is it the done indicator */
+ testb $0x4, %cl /* is it the done indicator */
jz 2f
jmp 3f
2:
- testl $0x8, %ecx /* is it the source indicator */
+ testb $0x8, %cl /* is it the source indicator */
jz 0b /* Ignore it otherwise */
movl %ecx, %esi /* For every source page do a copy */
andl $0xfffff000, %esi
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 3fd2c693e475..98111b38ebfd 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -123,7 +123,7 @@ identity_mapped:
* Set cr4 to a known state:
* - physical address extension enabled
*/
- movq $X86_CR4_PAE, %rax
+ movl $X86_CR4_PAE, %eax
movq %rax, %cr4
jmp 1f
@@ -221,23 +221,23 @@ swap_pages:
movq (%rbx), %rcx
addq $8, %rbx
1:
- testq $0x1, %rcx /* is it a destination page? */
+ testb $0x1, %cl /* is it a destination page? */
jz 2f
movq %rcx, %rdi
andq $0xfffffffffffff000, %rdi
jmp 0b
2:
- testq $0x2, %rcx /* is it an indirection page? */
+ testb $0x2, %cl /* is it an indirection page? */
jz 2f
movq %rcx, %rbx
andq $0xfffffffffffff000, %rbx
jmp 0b
2:
- testq $0x4, %rcx /* is it the done indicator? */
+ testb $0x4, %cl /* is it the done indicator? */
jz 2f
jmp 3f
2:
- testq $0x8, %rcx /* is it the source indicator? */
+ testb $0x8, %cl /* is it the source indicator? */
jz 0b /* Ignore it otherwise */
movq %rcx, %rsi /* For ever source page do a copy */
andq $0xfffffffffffff000, %rsi
@@ -246,17 +246,17 @@ swap_pages:
movq %rsi, %rax
movq %r10, %rdi
- movq $512, %rcx
+ movl $512, %ecx
rep ; movsq
movq %rax, %rdi
movq %rdx, %rsi
- movq $512, %rcx
+ movl $512, %ecx
rep ; movsq
movq %rdx, %rdi
movq %r10, %rsi
- movq $512, %rcx
+ movl $512, %ecx
rep ; movsq
lea PAGE_SIZE(%rax), %rsi
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 98dc9317286e..014466b152b5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -122,8 +122,6 @@
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
-bool __read_mostly kaslr_enabled = false;
-
#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
#endif
@@ -427,11 +425,6 @@ static void __init reserve_initrd(void)
}
#endif /* CONFIG_BLK_DEV_INITRD */
-static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
-{
- kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
-}
-
static void __init parse_setup_data(void)
{
struct setup_data *data;
@@ -457,9 +450,6 @@ static void __init parse_setup_data(void)
case SETUP_EFI:
parse_efi_setup(pa_data, data_len);
break;
- case SETUP_KASLR:
- parse_kaslr_setup(pa_data, data_len);
- break;
default:
break;
}
@@ -842,14 +832,15 @@ static void __init trim_low_memory_range(void)
static int
dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
{
- if (kaslr_enabled)
+ if (kaslr_enabled()) {
pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
(unsigned long)&_text - __START_KERNEL,
__START_KERNEL,
__START_KERNEL_map,
MODULES_VADDR-1);
- else
+ } else {
pr_emerg("Kernel Offset: disabled\n");
+ }
return 0;
}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index e5042463c1bc..53cc4085c3d7 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -61,8 +61,7 @@
regs->seg = GET_SEG(seg) | 3; \
} while (0)
-int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
- unsigned long *pax)
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc)
{
void __user *buf;
unsigned int tmpflags;
@@ -81,7 +80,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
#endif /* CONFIG_X86_32 */
COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
- COPY(dx); COPY(cx); COPY(ip);
+ COPY(dx); COPY(cx); COPY(ip); COPY(ax);
#ifdef CONFIG_X86_64
COPY(r8);
@@ -94,27 +93,20 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
COPY(r15);
#endif /* CONFIG_X86_64 */
-#ifdef CONFIG_X86_32
COPY_SEG_CPL3(cs);
COPY_SEG_CPL3(ss);
-#else /* !CONFIG_X86_32 */
- /* Kernel saves and restores only the CS segment register on signals,
- * which is the bare minimum needed to allow mixed 32/64-bit code.
- * App's signal handler can save/restore other segments if needed. */
- COPY_SEG_CPL3(cs);
-#endif /* CONFIG_X86_32 */
get_user_ex(tmpflags, &sc->flags);
regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
regs->orig_ax = -1; /* disable syscall checks */
get_user_ex(buf, &sc->fpstate);
-
- get_user_ex(*pax, &sc->ax);
} get_user_catch(err);
err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+ force_iret();
+
return err;
}
@@ -162,8 +154,9 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
#else /* !CONFIG_X86_32 */
put_user_ex(regs->flags, &sc->flags);
put_user_ex(regs->cs, &sc->cs);
- put_user_ex(0, &sc->gs);
- put_user_ex(0, &sc->fs);
+ put_user_ex(0, &sc->__pad2);
+ put_user_ex(0, &sc->__pad1);
+ put_user_ex(regs->ss, &sc->ss);
#endif /* CONFIG_X86_32 */
put_user_ex(fpstate, &sc->fpstate);
@@ -457,9 +450,19 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
regs->sp = (unsigned long)frame;
- /* Set up the CS register to run signal handlers in 64-bit mode,
- even if the handler happens to be interrupting 32-bit code. */
+ /*
+ * Set up the CS and SS registers to run signal handlers in
+ * 64-bit mode, even if the handler happens to be interrupting
+ * 32-bit or 16-bit code.
+ *
+ * SS is subtle. In 64-bit mode, we don't need any particular
+ * SS descriptor, but we do need SS to be valid. It's possible
+ * that the old SS is entirely bogus -- this can happen if the
+ * signal we're trying to deliver is #GP or #SS caused by a bad
+ * SS value.
+ */
regs->cs = __USER_CS;
+ regs->ss = __USER_DS;
return 0;
}
@@ -539,7 +542,6 @@ asmlinkage unsigned long sys_sigreturn(void)
{
struct pt_regs *regs = current_pt_regs();
struct sigframe __user *frame;
- unsigned long ax;
sigset_t set;
frame = (struct sigframe __user *)(regs->sp - 8);
@@ -553,9 +555,9 @@ asmlinkage unsigned long sys_sigreturn(void)
set_current_blocked(&set);
- if (restore_sigcontext(regs, &frame->sc, &ax))
+ if (restore_sigcontext(regs, &frame->sc))
goto badframe;
- return ax;
+ return regs->ax;
badframe:
signal_fault(regs, frame, "sigreturn");
@@ -568,7 +570,6 @@ asmlinkage long sys_rt_sigreturn(void)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
- unsigned long ax;
sigset_t set;
frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
@@ -579,13 +580,13 @@ asmlinkage long sys_rt_sigreturn(void)
set_current_blocked(&set);
- if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
- return ax;
+ return regs->ax;
badframe:
signal_fault(regs, frame, "rt_sigreturn");
@@ -780,7 +781,6 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe_x32 __user *frame;
sigset_t set;
- unsigned long ax;
frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
@@ -791,13 +791,13 @@ asmlinkage long sys32_x32_rt_sigreturn(void)
set_current_blocked(&set);
- if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
goto badframe;
if (compat_restore_altstack(&frame->uc.uc_stack))
goto badframe;
- return ax;
+ return regs->ax;
badframe:
signal_fault(regs, frame, "x32 rt_sigreturn");
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index febc6aabc72e..7035f6b21c3f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -779,6 +779,26 @@ out:
return boot_error;
}
+void common_cpu_up(unsigned int cpu, struct task_struct *idle)
+{
+ /* Just in case we booted with a single CPU. */
+ alternatives_enable_smp();
+
+ per_cpu(current_task, cpu) = idle;
+
+#ifdef CONFIG_X86_32
+ /* Stack for startup_32 can be just as for start_secondary onwards */
+ irq_ctx_init(cpu);
+ per_cpu(cpu_current_top_of_stack, cpu) =
+ (unsigned long)task_stack_page(idle) + THREAD_SIZE;
+#else
+ clear_tsk_thread_flag(idle, TIF_FORK);
+ initial_gs = per_cpu_offset(cpu);
+#endif
+ per_cpu(kernel_stack, cpu) =
+ (unsigned long)task_stack_page(idle) + THREAD_SIZE;
+}
+
/*
* NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad
* (ie clustered apic addressing mode), this is a LOGICAL apic ID.
@@ -796,23 +816,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
int cpu0_nmi_registered = 0;
unsigned long timeout;
- /* Just in case we booted with a single CPU. */
- alternatives_enable_smp();
-
idle->thread.sp = (unsigned long) (((struct pt_regs *)
(THREAD_SIZE + task_stack_page(idle))) - 1);
- per_cpu(current_task, cpu) = idle;
-#ifdef CONFIG_X86_32
- /* Stack for startup_32 can be just as for start_secondary onwards */
- irq_ctx_init(cpu);
-#else
- clear_tsk_thread_flag(idle, TIF_FORK);
- initial_gs = per_cpu_offset(cpu);
-#endif
- per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(idle) -
- KERNEL_STACK_OFFSET + THREAD_SIZE;
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
stack_start = idle->thread.sp;
@@ -953,6 +959,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
/* the FPU context is blank, nobody can own it */
__cpu_disable_lazy_restore(cpu);
+ common_cpu_up(cpu, tidle);
+
err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
@@ -1086,8 +1094,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
return SMP_NO_APIC;
}
- verify_local_APIC();
-
/*
* If SMP should be disabled, then really disable it!
*/
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c
index e9bcd57d8a9e..3777189c4a19 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/kernel/syscall_32.c
@@ -5,21 +5,29 @@
#include <linux/cache.h>
#include <asm/asm-offsets.h>
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ;
+#ifdef CONFIG_IA32_EMULATION
+#define SYM(sym, compat) compat
+#else
+#define SYM(sym, compat) sym
+#define ia32_sys_call_table sys_call_table
+#define __NR_ia32_syscall_max __NR_syscall_max
+#endif
+
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
#include <asm/syscalls_32.h>
#undef __SYSCALL_I386
-#define __SYSCALL_I386(nr, sym, compat) [nr] = sym,
+#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
typedef asmlinkage void (*sys_call_ptr_t)(void);
extern asmlinkage void sys_ni_syscall(void);
-__visible const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
*/
- [0 ... __NR_syscall_max] = &sys_ni_syscall,
+ [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall,
#include <asm/syscalls_32.h>
};
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 25adc0e16eaa..d39c09119db6 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -30,7 +30,7 @@ unsigned long profile_pc(struct pt_regs *regs)
{
unsigned long pc = instruction_pointer(regs);
- if (!user_mode_vm(regs) && in_lock_functions(pc)) {
+ if (!user_mode(regs) && in_lock_functions(pc)) {
#ifdef CONFIG_FRAME_POINTER
return *(unsigned long *)(regs->bp + sizeof(long));
#else
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9d2073e2ecc9..6751c5c58eec 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -112,7 +112,7 @@ enum ctx_state ist_enter(struct pt_regs *regs)
{
enum ctx_state prev_state;
- if (user_mode_vm(regs)) {
+ if (user_mode(regs)) {
/* Other than that, we're just an exception. */
prev_state = exception_enter();
} else {
@@ -146,7 +146,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
/* Must be before exception_exit. */
preempt_count_sub(HARDIRQ_OFFSET);
- if (user_mode_vm(regs))
+ if (user_mode(regs))
return exception_exit(prev_state);
else
rcu_nmi_exit();
@@ -158,7 +158,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
*
* IST exception handlers normally cannot schedule. As a special
* exception, if the exception interrupted userspace code (i.e.
- * user_mode_vm(regs) would return true) and the exception was not
+ * user_mode(regs) would return true) and the exception was not
* a double fault, it can be safe to schedule. ist_begin_non_atomic()
* begins a non-atomic section within an ist_enter()/ist_exit() region.
* Callers are responsible for enabling interrupts themselves inside
@@ -167,15 +167,15 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state)
*/
void ist_begin_non_atomic(struct pt_regs *regs)
{
- BUG_ON(!user_mode_vm(regs));
+ BUG_ON(!user_mode(regs));
/*
* Sanity check: we need to be on the normal thread stack. This
* will catch asm bugs and any attempt to use ist_preempt_enable
* from double_fault.
*/
- BUG_ON(((current_stack_pointer() ^ this_cpu_read_stable(kernel_stack))
- & ~(THREAD_SIZE - 1)) != 0);
+ BUG_ON((unsigned long)(current_top_of_stack() -
+ current_stack_pointer()) >= THREAD_SIZE);
preempt_count_sub(HARDIRQ_OFFSET);
}
@@ -194,8 +194,7 @@ static nokprobe_inline int
do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
struct pt_regs *regs, long error_code)
{
-#ifdef CONFIG_X86_32
- if (regs->flags & X86_VM_MASK) {
+ if (v8086_mode(regs)) {
/*
* Traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
* On nmi (interrupt 2), do_trap should not be called.
@@ -207,7 +206,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
}
return -1;
}
-#endif
+
if (!user_mode(regs)) {
if (!fixup_exception(regs)) {
tsk->thread.error_code = error_code;
@@ -462,13 +461,11 @@ do_general_protection(struct pt_regs *regs, long error_code)
prev_state = exception_enter();
conditional_sti(regs);
-#ifdef CONFIG_X86_32
- if (regs->flags & X86_VM_MASK) {
+ if (v8086_mode(regs)) {
local_irq_enable();
handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
goto exit;
}
-#endif
tsk = current;
if (!user_mode(regs)) {
@@ -587,7 +584,7 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
/* Copy the remainder of the stack from the current stack. */
memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
- BUG_ON(!user_mode_vm(&new_stack->regs));
+ BUG_ON(!user_mode(&new_stack->regs));
return new_stack;
}
NOKPROBE_SYMBOL(fixup_bad_iret);
@@ -673,7 +670,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
/* It's safe to allow irq's after DR6 has been saved */
preempt_conditional_sti(regs);
- if (regs->flags & X86_VM_MASK) {
+ if (v8086_mode(regs)) {
handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
X86_TRAP_DB);
preempt_conditional_cli(regs);
@@ -721,7 +718,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
return;
conditional_sti(regs);
- if (!user_mode_vm(regs))
+ if (!user_mode(regs))
{
if (!fixup_exception(regs)) {
task->thread.error_code = error_code;
@@ -925,9 +922,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
/* Set of traps needed for early debugging. */
void __init early_trap_init(void)
{
- set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
+ /*
+ * Don't use IST to set DEBUG_STACK as it doesn't work until TSS
+ * is ready in cpu_init() <-- trap_init(). Before trap_init(),
+ * CPU runs at ring 0 so it is impossible to hit an invalid
+ * stack. Using the original stack works well enough at this
+ * early stage. DEBUG_STACK will be equipped after cpu_init() in
+ * trap_init().
+ *
+ * We don't need to set trace_idt_table like set_intr_gate(),
+ * since we don't have trace_debug and it will be reset to
+ * 'debug' in trap_init() by set_intr_gate_ist().
+ */
+ set_intr_gate_notrace(X86_TRAP_DB, debug);
/* int3 can be called from all */
- set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+ set_system_intr_gate(X86_TRAP_BP, &int3);
#ifdef CONFIG_X86_32
set_intr_gate(X86_TRAP_PF, page_fault);
#endif
@@ -1005,6 +1014,15 @@ void __init trap_init(void)
*/
cpu_init();
+ /*
+ * X86_TRAP_DB and X86_TRAP_BP have been set
+ * in early_trap_init(). However, ITS works only after
+ * cpu_init() loads TSS. See comments in early_trap_init().
+ */
+ set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
+ /* int3 can be called from all */
+ set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+
x86_init.irqs.trap_init();
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 81f8adb0679e..0b81ad67da07 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -912,7 +912,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val,
int ret = NOTIFY_DONE;
/* We are only interested in userspace traps */
- if (regs && !user_mode_vm(regs))
+ if (regs && !user_mode(regs))
return NOTIFY_DONE;
switch (val) {
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index e8edcf52e069..fc9db6ef2a95 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -150,7 +150,7 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs)
do_exit(SIGSEGV);
}
- tss = &per_cpu(init_tss, get_cpu());
+ tss = &per_cpu(cpu_tss, get_cpu());
current->thread.sp0 = current->thread.saved_sp0;
current->thread.sysenter_cs = __KERNEL_CS;
load_sp0(tss, &current->thread);
@@ -318,7 +318,7 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
tsk->thread.saved_fs = info->regs32->fs;
tsk->thread.saved_gs = get_user_gs(info->regs32);
- tss = &per_cpu(init_tss, get_cpu());
+ tss = &per_cpu(cpu_tss, get_cpu());
tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0;
if (cpu_has_sep)
tsk->thread.sysenter_cs = 0;
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index c7d791f32b98..51e330416995 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -31,30 +31,30 @@ void update_vsyscall(struct timekeeper *tk)
gtod_write_begin(vdata);
/* copy vsyscall data */
- vdata->vclock_mode = tk->tkr.clock->archdata.vclock_mode;
- vdata->cycle_last = tk->tkr.cycle_last;
- vdata->mask = tk->tkr.mask;
- vdata->mult = tk->tkr.mult;
- vdata->shift = tk->tkr.shift;
+ vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+ vdata->cycle_last = tk->tkr_mono.cycle_last;
+ vdata->mask = tk->tkr_mono.mask;
+ vdata->mult = tk->tkr_mono.mult;
+ vdata->shift = tk->tkr_mono.shift;
vdata->wall_time_sec = tk->xtime_sec;
- vdata->wall_time_snsec = tk->tkr.xtime_nsec;
+ vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec;
vdata->monotonic_time_sec = tk->xtime_sec
+ tk->wall_to_monotonic.tv_sec;
- vdata->monotonic_time_snsec = tk->tkr.xtime_nsec
+ vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec
+ ((u64)tk->wall_to_monotonic.tv_nsec
- << tk->tkr.shift);
+ << tk->tkr_mono.shift);
while (vdata->monotonic_time_snsec >=
- (((u64)NSEC_PER_SEC) << tk->tkr.shift)) {
+ (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
vdata->monotonic_time_snsec -=
- ((u64)NSEC_PER_SEC) << tk->tkr.shift;
+ ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
vdata->monotonic_time_sec++;
}
vdata->wall_time_coarse_sec = tk->xtime_sec;
- vdata->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >>
- tk->tkr.shift);
+ vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
+ tk->tkr_mono.shift);
vdata->monotonic_time_coarse_sec =
vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 34f66e58a896..cdc6cf903078 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -379,7 +379,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
* thread's fpu state, reconstruct fxstate from the fsave
* header. Sanitize the copied state etc.
*/
- struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
int err = 0;
@@ -393,14 +393,15 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
*/
drop_fpu(tsk);
- if (__copy_from_user(xsave, buf_fx, state_size) ||
+ if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
__copy_from_user(&env, buf, sizeof(env))) {
+ fpu_finit(fpu);
err = -1;
} else {
sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
- set_used_math();
}
+ set_used_math();
if (use_eager_fpu()) {
preempt_disable();
math_state_restore();