summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/apic/io_apic.c130
-rw-r--r--arch/x86/kernel/cpu/common.c33
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c5
-rw-r--r--arch/x86/kernel/devicetree.c12
-rw-r--r--arch/x86/kernel/early-quirks.c46
-rw-r--r--arch/x86/kernel/entry_32.S17
-rw-r--r--arch/x86/kernel/entry_64.S285
-rw-r--r--arch/x86/kernel/espfix_64.c209
-rw-r--r--arch/x86/kernel/ftrace.c56
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/hpet.c8
-rw-r--r--arch/x86/kernel/irq.c16
-rw-r--r--arch/x86/kernel/ldt.c10
-rw-r--r--arch/x86/kernel/mcount_64.S217
-rw-r--r--arch/x86/kernel/pci-dma.c11
-rw-r--r--arch/x86/kernel/pci-swiotlb.c9
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/signal.c6
-rw-r--r--arch/x86/kernel/smpboot.c12
-rw-r--r--arch/x86/kernel/vsyscall_64.c15
22 files changed, 671 insertions, 434 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f4d96000d33..047f9ff2e36 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -26,9 +26,11 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-y += probe_roms.o
obj-$(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_X86_64) += vsyscall_64.o
obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
obj-y += pci-dma.o quirks.o topology.o kdebugfs.o
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b574b295a2f..8e3842fc8be 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -512,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_addr, struct dma_attrs *attrs)
{
gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
- free_pages((unsigned long)vaddr, get_order(size));
+ dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
}
static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 992060e0989..9d0a9795a0f 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -206,9 +206,6 @@ int __init arch_early_irq_init(void)
count = ARRAY_SIZE(irq_cfgx);
node = cpu_to_node(0);
- /* Make sure the legacy interrupts are marked in the bitmap */
- irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
-
for (i = 0; i < count; i++) {
irq_set_chip_data(i, &cfg[i]);
zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
@@ -281,18 +278,6 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
return cfg;
}
-static int alloc_irqs_from(unsigned int from, unsigned int count, int node)
-{
- return irq_alloc_descs_from(from, count, node);
-}
-
-static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
-{
- free_irq_cfg(at, cfg);
- irq_free_desc(at);
-}
-
-
struct io_apic {
unsigned int index;
unsigned int unused[3];
@@ -2916,98 +2901,39 @@ static int __init ioapic_init_ops(void)
device_initcall(ioapic_init_ops);
/*
- * Dynamic irq allocate and deallocation
+ * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
*/
-unsigned int __create_irqs(unsigned int from, unsigned int count, int node)
+int arch_setup_hwirq(unsigned int irq, int node)
{
- struct irq_cfg **cfg;
+ struct irq_cfg *cfg;
unsigned long flags;
- int irq, i;
-
- if (from < nr_irqs_gsi)
- from = nr_irqs_gsi;
+ int ret;
- cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node);
+ cfg = alloc_irq_cfg(irq, node);
if (!cfg)
- return 0;
-
- irq = alloc_irqs_from(from, count, node);
- if (irq < 0)
- goto out_cfgs;
-
- for (i = 0; i < count; i++) {
- cfg[i] = alloc_irq_cfg(irq + i, node);
- if (!cfg[i])
- goto out_irqs;
- }
+ return -ENOMEM;
raw_spin_lock_irqsave(&vector_lock, flags);
- for (i = 0; i < count; i++)
- if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus()))
- goto out_vecs;
- raw_spin_unlock_irqrestore(&vector_lock, flags);
-
- for (i = 0; i < count; i++) {
- irq_set_chip_data(irq + i, cfg[i]);
- irq_clear_status_flags(irq + i, IRQ_NOREQUEST);
- }
-
- kfree(cfg);
- return irq;
-
-out_vecs:
- for (i--; i >= 0; i--)
- __clear_irq_vector(irq + i, cfg[i]);
+ ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
raw_spin_unlock_irqrestore(&vector_lock, flags);
-out_irqs:
- for (i = 0; i < count; i++)
- free_irq_at(irq + i, cfg[i]);
-out_cfgs:
- kfree(cfg);
- return 0;
-}
-unsigned int create_irq_nr(unsigned int from, int node)
-{
- return __create_irqs(from, 1, node);
-}
-
-int create_irq(void)
-{
- int node = cpu_to_node(0);
- unsigned int irq_want;
- int irq;
-
- irq_want = nr_irqs_gsi;
- irq = create_irq_nr(irq_want, node);
-
- if (irq == 0)
- irq = -1;
-
- return irq;
+ if (!ret)
+ irq_set_chip_data(irq, cfg);
+ else
+ free_irq_cfg(irq, cfg);
+ return ret;
}
-void destroy_irq(unsigned int irq)
+void arch_teardown_hwirq(unsigned int irq)
{
struct irq_cfg *cfg = irq_get_chip_data(irq);
unsigned long flags;
- irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
-
free_remapped_irq(irq);
-
raw_spin_lock_irqsave(&vector_lock, flags);
__clear_irq_vector(irq, cfg);
raw_spin_unlock_irqrestore(&vector_lock, flags);
- free_irq_at(irq, cfg);
-}
-
-void destroy_irqs(unsigned int irq, unsigned int count)
-{
- unsigned int i;
-
- for (i = 0; i < count; i++)
- destroy_irq(irq + i);
+ free_irq_cfg(irq, cfg);
}
/*
@@ -3136,8 +3062,8 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- unsigned int irq, irq_want;
struct msi_desc *msidesc;
+ unsigned int irq;
int node, ret;
/* Multiple MSI vectors only supported with interrupt remapping */
@@ -3145,28 +3071,25 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
return 1;
node = dev_to_node(&dev->dev);
- irq_want = nr_irqs_gsi;
+
list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = create_irq_nr(irq_want, node);
- if (irq == 0)
+ irq = irq_alloc_hwirq(node);
+ if (!irq)
return -ENOSPC;
- irq_want = irq + 1;
-
ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0)
- goto error;
+ if (ret < 0) {
+ irq_free_hwirq(irq);
+ return ret;
+ }
+
}
return 0;
-
-error:
- destroy_irq(irq);
- return ret;
}
void native_teardown_msi_irq(unsigned int irq)
{
- destroy_irq(irq);
+ irq_free_hwirq(irq);
}
#ifdef CONFIG_DMAR_TABLE
@@ -3420,11 +3343,6 @@ static void __init probe_nr_irqs_gsi(void)
printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
}
-int get_nr_irqs_gsi(void)
-{
- return nr_irqs_gsi;
-}
-
unsigned int arch_dynirq_lower_bound(unsigned int from)
{
return from < nr_irqs_gsi ? nr_irqs_gsi : from;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a135239badb..2cbbf88d8f2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -20,6 +20,7 @@
#include <asm/processor.h>
#include <asm/debugreg.h>
#include <asm/sections.h>
+#include <asm/vsyscall.h>
#include <linux/topology.h>
#include <linux/cpumask.h>
#include <asm/pgtable.h>
@@ -953,6 +954,38 @@ static void vgetcpu_set_mode(void)
else
vgetcpu_mode = VGETCPU_LSL;
}
+
+/* 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
+
+#ifdef CONFIG_X86_32
+void enable_sep_cpu(void)
+{
+ int cpu = get_cpu();
+ struct tss_struct *tss = &per_cpu(init_tss, cpu);
+
+ if (!boot_cpu_has(X86_FEATURE_SEP)) {
+ put_cpu();
+ return;
+ }
+
+ 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);
+ put_cpu();
+}
#endif
void __init identify_boot_cpu(void)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 6cc800381d1..bb92f38153b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
#define SPINUNIT 100 /* 100ns */
-atomic_t mce_entry;
-
DEFINE_PER_CPU(unsigned, mce_exception_count);
struct mce_bank *mce_banks __read_mostly;
@@ -1040,8 +1038,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
char *msg = "Unknown";
- atomic_inc(&mce_entry);
-
this_cpu_inc(mce_exception_count);
if (!cfg->banks)
@@ -1171,7 +1167,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_report_event(regs);
mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
out:
- atomic_dec(&mce_entry);
sync_core();
}
EXPORT_SYMBOL_GPL(do_machine_check);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index d35078ea144..7db54b5d5f8 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -206,23 +206,21 @@ static void __init dtb_apic_setup(void)
static void __init x86_flattree_get_config(void)
{
u32 size, map_len;
- struct boot_param_header *dt;
+ void *dt;
if (!initial_dtb)
return;
- map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK),
- (u64)sizeof(struct boot_param_header));
+ map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128);
- dt = early_memremap(initial_dtb, map_len);
- size = be32_to_cpu(dt->totalsize);
+ initial_boot_params = dt = early_memremap(initial_dtb, map_len);
+ size = of_get_flat_dt_size();
if (map_len < size) {
early_iounmap(dt, map_len);
- dt = early_memremap(initial_dtb, size);
+ initial_boot_params = dt = early_memremap(initial_dtb, size);
map_len = size;
}
- initial_boot_params = dt;
unflatten_and_copy_device_tree();
early_iounmap(dt, map_len);
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6cda0baeac9..2e1a6853e00 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -419,7 +419,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
return gmch_ctrl << 25; /* 32 MB units */
}
-static size_t gen8_stolen_size(int num, int slot, int func)
+static size_t __init gen8_stolen_size(int num, int slot, int func)
{
u16 gmch_ctrl;
@@ -429,48 +429,73 @@ static size_t gen8_stolen_size(int num, int slot, int func)
return gmch_ctrl << 25; /* 32 MB units */
}
+static size_t __init chv_stolen_size(int num, int slot, int func)
+{
+ u16 gmch_ctrl;
+
+ gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
+ gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
+ gmch_ctrl &= SNB_GMCH_GMS_MASK;
+
+ /*
+ * 0x0 to 0x10: 32MB increments starting at 0MB
+ * 0x11 to 0x16: 4MB increments starting at 8MB
+ * 0x17 to 0x1d: 4MB increments start at 36MB
+ */
+ if (gmch_ctrl < 0x11)
+ return gmch_ctrl << 25;
+ else if (gmch_ctrl < 0x17)
+ return (gmch_ctrl - 0x11 + 2) << 22;
+ else
+ return (gmch_ctrl - 0x17 + 9) << 22;
+}
struct intel_stolen_funcs {
size_t (*size)(int num, int slot, int func);
u32 (*base)(int num, int slot, int func, size_t size);
};
-static const struct intel_stolen_funcs i830_stolen_funcs = {
+static const struct intel_stolen_funcs i830_stolen_funcs __initconst = {
.base = i830_stolen_base,
.size = i830_stolen_size,
};
-static const struct intel_stolen_funcs i845_stolen_funcs = {
+static const struct intel_stolen_funcs i845_stolen_funcs __initconst = {
.base = i845_stolen_base,
.size = i830_stolen_size,
};
-static const struct intel_stolen_funcs i85x_stolen_funcs = {
+static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = {
.base = i85x_stolen_base,
.size = gen3_stolen_size,
};
-static const struct intel_stolen_funcs i865_stolen_funcs = {
+static const struct intel_stolen_funcs i865_stolen_funcs __initconst = {
.base = i865_stolen_base,
.size = gen3_stolen_size,
};
-static const struct intel_stolen_funcs gen3_stolen_funcs = {
+static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = {
.base = intel_stolen_base,
.size = gen3_stolen_size,
};
-static const struct intel_stolen_funcs gen6_stolen_funcs = {
+static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = {
.base = intel_stolen_base,
.size = gen6_stolen_size,
};
-static const struct intel_stolen_funcs gen8_stolen_funcs = {
+static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = {
.base = intel_stolen_base,
.size = gen8_stolen_size,
};
-static struct pci_device_id intel_stolen_ids[] __initdata = {
+static const struct intel_stolen_funcs chv_stolen_funcs __initconst = {
+ .base = intel_stolen_base,
+ .size = chv_stolen_size,
+};
+
+static const struct pci_device_id intel_stolen_ids[] __initconst = {
INTEL_I830_IDS(&i830_stolen_funcs),
INTEL_I845G_IDS(&i845_stolen_funcs),
INTEL_I85X_IDS(&i85x_stolen_funcs),
@@ -496,7 +521,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = {
INTEL_HSW_D_IDS(&gen6_stolen_funcs),
INTEL_HSW_M_IDS(&gen6_stolen_funcs),
INTEL_BDW_M_IDS(&gen8_stolen_funcs),
- INTEL_BDW_D_IDS(&gen8_stolen_funcs)
+ INTEL_BDW_D_IDS(&gen8_stolen_funcs),
+ INTEL_CHV_IDS(&chv_stolen_funcs),
};
static void __init intel_graphics_stolen(int num, int slot, int func)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index a2a4f469788..98313ffaae6 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -527,6 +527,7 @@ syscall_exit:
restore_all:
TRACE_IRQS_IRET
restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
# are returning to the kernel.
@@ -537,6 +538,7 @@ restore_all_notrace:
cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
CFI_REMEMBER_STATE
je ldt_ss # returning to user-space with LDT SS
+#endif
restore_nocheck:
RESTORE_REGS 4 # skip orig_eax/error_code
irq_return:
@@ -549,13 +551,9 @@ ENTRY(iret_exc)
.previous
_ASM_EXTABLE(irq_return,iret_exc)
+#ifdef CONFIG_X86_ESPFIX32
CFI_RESTORE_STATE
ldt_ss:
- larl PT_OLDSS(%esp), %eax
- jnz restore_nocheck
- testl $0x00400000, %eax # returning to 32bit stack?
- jnz restore_nocheck # allright, normal return
-
#ifdef CONFIG_PARAVIRT
/*
* The kernel can't run on a non-flat stack if paravirt mode
@@ -597,6 +595,7 @@ ldt_ss:
lss (%esp), %esp /* switch to espfix segment */
CFI_ADJUST_CFA_OFFSET -8
jmp restore_nocheck
+#endif
CFI_ENDPROC
ENDPROC(system_call)
@@ -704,6 +703,7 @@ END(syscall_badsys)
* the high word of the segment base from the GDT and swiches to the
* normal stack and adjusts ESP with the matching offset.
*/
+#ifdef CONFIG_X86_ESPFIX32
/* fixup the stack */
mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -713,8 +713,10 @@ END(syscall_badsys)
pushl_cfi %eax
lss (%esp), %esp /* switch to the normal stack segment */
CFI_ADJUST_CFA_OFFSET -8
+#endif
.endm
.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
movl %ss, %eax
/* see if on espfix stack */
cmpw $__ESPFIX_SS, %ax
@@ -725,6 +727,7 @@ END(syscall_badsys)
/* switch to normal stack */
FIXUP_ESPFIX_STACK
27:
+#endif
.endm
/*
@@ -1355,11 +1358,13 @@ END(debug)
ENTRY(nmi)
RING0_INT_FRAME
ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
pushl_cfi %eax
movl %ss, %eax
cmpw $__ESPFIX_SS, %ax
popl_cfi %eax
je nmi_espfix_stack
+#endif
cmpl $ia32_sysenter_target,(%esp)
je nmi_stack_fixup
pushl_cfi %eax
@@ -1399,6 +1404,7 @@ nmi_debug_stack_check:
FIX_STACK 24, nmi_stack_correct, 1
jmp nmi_stack_correct
+#ifdef CONFIG_X86_ESPFIX32
nmi_espfix_stack:
/* We have a RING0_INT_FRAME here.
*
@@ -1420,6 +1426,7 @@ nmi_espfix_stack:
lss 12+4(%esp), %esp # back to espfix stack
CFI_ADJUST_CFA_OFFSET -24
jmp irq_return
+#endif
CFI_ENDPROC
END(nmi)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index be846d2468f..48a2644a082 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -53,11 +53,11 @@
#include <asm/page_types.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
-#include <asm/ftrace.h>
#include <asm/percpu.h>
#include <asm/asm.h>
#include <asm/context_tracking.h>
#include <asm/smap.h>
+#include <asm/pgtable_types.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -69,209 +69,6 @@
.code64
.section .entry.text, "ax"
-#ifdef CONFIG_FUNCTION_TRACER
-
-#ifdef CC_USING_FENTRY
-# define function_hook __fentry__
-#else
-# define function_hook mcount
-#endif
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-
-ENTRY(function_hook)
- retq
-END(function_hook)
-
-/* skip is set if stack has been adjusted */
-.macro ftrace_caller_setup skip=0
- MCOUNT_SAVE_FRAME \skip
-
- /* Load the ftrace_ops into the 3rd parameter */
- movq function_trace_op(%rip), %rdx
-
- /* Load ip into the first parameter */
- movq RIP(%rsp), %rdi
- subq $MCOUNT_INSN_SIZE, %rdi
- /* Load the parent_ip into the second parameter */
-#ifdef CC_USING_FENTRY
- movq SS+16(%rsp), %rsi
-#else
- movq 8(%rbp), %rsi
-#endif
-.endm
-
-ENTRY(ftrace_caller)
- /* Check if tracing was disabled (quick check) */
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
- ftrace_caller_setup
- /* regs go into 4th parameter (but make it NULL) */
- movq $0, %rcx
-
-GLOBAL(ftrace_call)
- call ftrace_stub
-
- MCOUNT_RESTORE_FRAME
-ftrace_return:
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-GLOBAL(ftrace_graph_call)
- jmp ftrace_stub
-#endif
-
-GLOBAL(ftrace_stub)
- retq
-END(ftrace_caller)
-
-ENTRY(ftrace_regs_caller)
- /* Save the current flags before compare (in SS location)*/
- pushfq
-
- /* Check if tracing was disabled (quick check) */
- cmpl $0, function_trace_stop
- jne ftrace_restore_flags
-
- /* skip=8 to skip flags saved in SS */
- ftrace_caller_setup 8
-
- /* Save the rest of pt_regs */
- movq %r15, R15(%rsp)
- movq %r14, R14(%rsp)
- movq %r13, R13(%rsp)
- movq %r12, R12(%rsp)
- movq %r11, R11(%rsp)
- movq %r10, R10(%rsp)
- movq %rbp, RBP(%rsp)
- movq %rbx, RBX(%rsp)
- /* Copy saved flags */
- movq SS(%rsp), %rcx
- movq %rcx, EFLAGS(%rsp)
- /* Kernel segments */
- movq $__KERNEL_DS, %rcx
- movq %rcx, SS(%rsp)
- movq $__KERNEL_CS, %rcx
- movq %rcx, CS(%rsp)
- /* Stack - skipping return address */
- leaq SS+16(%rsp), %rcx
- movq %rcx, RSP(%rsp)
-
- /* regs go into 4th parameter */
- leaq (%rsp), %rcx
-
-GLOBAL(ftrace_regs_call)
- call ftrace_stub
-
- /* Copy flags back to SS, to restore them */
- movq EFLAGS(%rsp), %rax
- movq %rax, SS(%rsp)
-
- /* Handlers can change the RIP */
- movq RIP(%rsp), %rax
- movq %rax, SS+8(%rsp)
-
- /* restore the rest of pt_regs */
- movq R15(%rsp), %r15
- movq R14(%rsp), %r14
- movq R13(%rsp), %r13
- movq R12(%rsp), %r12
- movq R10(%rsp), %r10
- movq RBP(%rsp), %rbp
- movq RBX(%rsp), %rbx
-
- /* skip=8 to skip flags saved in SS */
- MCOUNT_RESTORE_FRAME 8
-
- /* Restore flags */
- popfq
-
- jmp ftrace_return
-ftrace_restore_flags:
- popfq
- jmp ftrace_stub
-
-END(ftrace_regs_caller)
-
-
-#else /* ! CONFIG_DYNAMIC_FTRACE */
-
-ENTRY(function_hook)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
- cmpq $ftrace_stub, ftrace_trace_function
- jnz trace
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- cmpq $ftrace_stub, ftrace_graph_return
- jnz ftrace_graph_caller
-
- cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
- jnz ftrace_graph_caller
-#endif
-
-GLOBAL(ftrace_stub)
- retq
-
-trace:
- MCOUNT_SAVE_FRAME
-
- movq RIP(%rsp), %rdi
-#ifdef CC_USING_FENTRY
- movq SS+16(%rsp), %rsi
-#else
- movq 8(%rbp), %rsi
-#endif
- subq $MCOUNT_INSN_SIZE, %rdi
-
- call *ftrace_trace_function
-
- MCOUNT_RESTORE_FRAME
-
- jmp ftrace_stub
-END(function_hook)
-#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FUNCTION_TRACER */
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-ENTRY(ftrace_graph_caller)
- MCOUNT_SAVE_FRAME
-
-#ifdef CC_USING_FENTRY
- leaq SS+16(%rsp), %rdi
- movq $0, %rdx /* No framepointers needed */
-#else
- leaq 8(%rbp), %rdi
- movq (%rbp), %rdx
-#endif
- movq RIP(%rsp), %rsi
- subq $MCOUNT_INSN_SIZE, %rsi
-
- call prepare_ftrace_return
-
- MCOUNT_RESTORE_FRAME
-
- retq
-END(ftrace_graph_caller)
-
-GLOBAL(return_to_handler)
- subq $24, %rsp
-
- /* Save the return values */
- movq %rax, (%rsp)
- movq %rdx, 8(%rsp)
- movq %rbp, %rdi
-
- call ftrace_return_to_handler
-
- movq %rax, %rdi
- movq 8(%rsp), %rdx
- movq (%rsp), %rax
- addq $24, %rsp
- jmp *%rdi
-#endif
-
#ifndef CONFIG_PREEMPT
#define retint_kernel retint_restore_args
@@ -1040,8 +837,18 @@ restore_args:
RESTORE_ARGS 1,8,1
irq_return:
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4,(SS-RIP)(%rsp)
+ jnz irq_return_ldt
+#endif
+
+irq_return_iret:
INTERRUPT_RETURN
- _ASM_EXTABLE(irq_return, bad_iret)
+ _ASM_EXTABLE(irq_return_iret, bad_iret)
#ifdef CONFIG_PARAVIRT
ENTRY(native_iret)
@@ -1049,6 +856,32 @@ ENTRY(native_iret)
_ASM_EXTABLE(native_iret, bad_iret)
#endif
+#ifdef CONFIG_X86_ESPFIX64
+irq_return_ldt:
+ pushq_cfi %rax
+ pushq_cfi %rdi
+ SWAPGS
+ movq PER_CPU_VAR(espfix_waddr),%rdi
+ movq %rax,(0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp),%rax /* RIP */
+ movq %rax,(1*8)(%rdi)
+ movq (3*8)(%rsp),%rax /* CS */
+ movq %rax,(2*8)(%rdi)
+ movq (4*8)(%rsp),%rax /* RFLAGS */
+ movq %rax,(3*8)(%rdi)
+ movq (6*8)(%rsp),%rax /* SS */
+ movq %rax,(5*8)(%rdi)
+ movq (5*8)(%rsp),%rax /* RSP */
+ movq %rax,(4*8)(%rdi)
+ andl $0xffff0000,%eax
+ popq_cfi %rdi
+ orq PER_CPU_VAR(espfix_stack),%rax
+ SWAPGS
+ movq %rax,%rsp
+ popq_cfi %rax
+ jmp irq_return_iret
+#endif
+
.section .fixup,"ax"
bad_iret:
/*
@@ -1110,9 +943,45 @@ ENTRY(retint_kernel)
call preempt_schedule_irq
jmp exit_intr
#endif
-
CFI_ENDPROC
END(common_interrupt)
+
+ /*
+ * If IRET takes a fault on the espfix stack, then we
+ * end up promoting it to a doublefault. In that case,
+ * modify the stack to make it look like we just entered
+ * the #GP handler from user space, similar to bad_iret.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ ALIGN
+__do_double_fault:
+ XCPT_FRAME 1 RDI+8
+ movq RSP(%rdi),%rax /* Trap on the espfix stack? */
+ sarq $PGDIR_SHIFT,%rax
+ cmpl $ESPFIX_PGD_ENTRY,%eax
+ jne do_double_fault /* No, just deliver the fault */
+ cmpl $__KERNEL_CS,CS(%rdi)
+ jne do_double_fault
+ movq RIP(%rdi),%rax
+ cmpq $irq_return_iret,%rax
+#ifdef CONFIG_PARAVIRT
+ je 1f
+ cmpq $native_iret,%rax
+#endif
+ jne do_double_fault /* This shouldn't happen... */
+1:
+ movq PER_CPU_VAR(kernel_stack),%rax
+ subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */
+ movq %rax,RSP(%rdi)
+ movq $0,(%rax) /* Missing (lost) #GP error code */
+ movq $general_protection,RIP(%rdi)
+ retq
+ CFI_ENDPROC
+END(__do_double_fault)
+#else
+# define __do_double_fault do_double_fault
+#endif
+
/*
* End of kprobes section
*/
@@ -1289,7 +1158,7 @@ idtentry overflow do_overflow has_error_code=0
idtentry bounds do_bounds has_error_code=0
idtentry invalid_op do_invalid_op has_error_code=0
idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=1
+idtentry double_fault __do_double_fault has_error_code=1 paranoid=1
idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
idtentry invalid_TSS do_invalid_TSS has_error_code=1
idtentry segment_not_present do_segment_not_present has_error_code=1
@@ -1576,7 +1445,7 @@ error_sti:
*/
error_kernelspace:
incl %ebx
- leaq irq_return(%rip),%rcx
+ leaq irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
je error_swapgs
movl %ecx,%eax /* zero extend */
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
new file mode 100644
index 00000000000..6afbb16e9b7
--- /dev/null
+++ b/arch/x86/kernel/espfix_64.c
@@ -0,0 +1,209 @@
+/* ----------------------------------------------------------------------- *
+ *
+ * Copyright 2014 Intel Corporation; author: H. Peter Anvin
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The IRET instruction, when returning to a 16-bit segment, only
+ * restores the bottom 16 bits of the user space stack pointer. This
+ * causes some 16-bit software to break, but it also leaks kernel state
+ * to user space.
+ *
+ * This works around this by creating percpu "ministacks", each of which
+ * is mapped 2^16 times 64K apart. When we detect that the return SS is
+ * on the LDT, we copy the IRET frame to the ministack and use the
+ * relevant alias to return to userspace. The ministacks are mapped
+ * readonly, so if the IRET fault we promote #GP to #DF which is an IST
+ * vector and thus has its own stack; we then do the fixup in the #DF
+ * handler.
+ *
+ * This file sets up the ministacks and the related page tables. The
+ * actual ministack invocation is in entry_64.S.
+ */
+
+#include <linux/init.h>
+#include <linux/init_task.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/gfp.h>
+#include <linux/random.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/setup.h>
+#include <asm/espfix.h>
+
+/*
+ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round
+ * it up to a cache line to avoid unnecessary sharing.
+ */
+#define ESPFIX_STACK_SIZE (8*8UL)
+#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE)
+
+/* There is address space for how many espfix pages? */
+#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16))
+
+#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE)
+#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS
+# error "Need more than one PGD for the ESPFIX hack"
+#endif
+
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/* This contains the *bottom* address of the espfix stack */
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+/* Initialization mutex - should this be a spinlock? */
+static DEFINE_MUTEX(espfix_init_mutex);
+
+/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */
+#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE)
+static void *espfix_pages[ESPFIX_MAX_PAGES];
+
+static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD]
+ __aligned(PAGE_SIZE);
+
+static unsigned int page_random, slot_random;
+
+/*
+ * This returns the bottom address of the espfix stack for a specific CPU.
+ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case
+ * we have to account for some amount of padding at the end of each page.
+ */
+static inline unsigned long espfix_base_addr(unsigned int cpu)
+{
+ unsigned long page, slot;
+ unsigned long addr;
+
+ page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random;
+ slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE;
+ addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE);
+ addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16);
+ addr += ESPFIX_BASE_ADDR;
+ return addr;
+}
+
+#define PTE_STRIDE (65536/PAGE_SIZE)
+#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE)
+#define ESPFIX_PMD_CLONES PTRS_PER_PMD
+#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES))
+
+#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX)
+
+static void init_espfix_random(void)
+{
+ unsigned long rand;
+
+ /*
+ * This is run before the entropy pools are initialized,
+ * but this is hopefully better than nothing.
+ */
+ if (!arch_get_random_long(&rand)) {
+ /* The constant is an arbitrary large prime */
+ rdtscll(rand);
+ rand *= 0xc345c6b72fd16123UL;
+ }
+
+ slot_random = rand % ESPFIX_STACKS_PER_PAGE;
+ page_random = (rand / ESPFIX_STACKS_PER_PAGE)
+ & (ESPFIX_PAGE_SPACE - 1);
+}
+
+void __init init_espfix_bsp(void)
+{
+ pgd_t *pgd_p;
+ pteval_t ptemask;
+
+ ptemask = __supported_pte_mask;
+
+ /* Install the espfix pud into the kernel page directory */
+ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
+ pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
+
+ /* Randomize the locations */
+ init_espfix_random();
+
+ /* The rest is the same as for any other processor */
+ init_espfix_ap();
+}
+
+void init_espfix_ap(void)
+{
+ unsigned int cpu, page;
+ unsigned long addr;
+ pud_t pud, *pud_p;
+ pmd_t pmd, *pmd_p;
+ pte_t pte, *pte_p;
+ int n;
+ void *stack_page;
+ pteval_t ptemask;
+
+ /* We only have to do this once... */
+ if (likely(this_cpu_read(espfix_stack)))
+ return; /* Already initialized */
+
+ cpu = smp_processor_id();
+ addr = espfix_base_addr(cpu);
+ page = cpu/ESPFIX_STACKS_PER_PAGE;
+
+ /* Did another CPU already set this up? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (likely(stack_page))
+ goto done;
+
+ mutex_lock(&espfix_init_mutex);
+
+ /* Did we race on the lock? */
+ stack_page = ACCESS_ONCE(espfix_pages[page]);
+ if (stack_page)
+ goto unlock_done;
+
+ ptemask = __supported_pte_mask;
+
+ pud_p = &espfix_pud_page[pud_index(addr)];
+ pud = *pud_p;
+ if (!pud_present(pud)) {
+ pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+ pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PUD_CLONES; n++)
+ set_pud(&pud_p[n], pud);
+ }
+
+ pmd_p = pmd_offset(&pud, addr);
+ pmd = *pmd_p;
+ if (!pmd_present(pmd)) {
+ pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+ pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
+ paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PMD_CLONES; n++)
+ set_pmd(&pmd_p[n], pmd);
+ }
+
+ pte_p = pte_offset_kernel(&pmd, addr);
+ stack_page = (void *)__get_free_page(GFP_KERNEL);
+ pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
+ paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT);
+ for (n = 0; n < ESPFIX_PTE_CLONES; n++)
+ set_pte(&pte_p[n*PTE_STRIDE], pte);
+
+ /* Job is done for this CPU and any CPU which shares this page */
+ ACCESS_ONCE(espfix_pages[page]) = stack_page;
+
+unlock_done:
+ mutex_unlock(&espfix_init_mutex);
+done:
+ this_cpu_write(espfix_stack, addr);
+ this_cpu_write(espfix_waddr, (unsigned long)stack_page
+ + (addr & ~PAGE_MASK));
+}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 52819e816f8..cbc4a91b131 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -297,16 +297,7 @@ int ftrace_int3_handler(struct pt_regs *regs)
static int ftrace_write(unsigned long ip, const char *val, int size)
{
- /*
- * On x86_64, kernel text mappings are mapped read-only with
- * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
- * of the kernel text mapping to modify the kernel text.
- *
- * For 32bit kernels, these mappings are same and we can use
- * kernel identity mapping to modify code.
- */
- if (within(ip, (unsigned long)_text, (unsigned long)_etext))
- ip = (unsigned long)__va(__pa_symbol(ip));
+ ip = text_ip_addr(ip);
if (probe_kernel_write((void *)ip, val, size))
return -EPERM;
@@ -349,40 +340,14 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
return add_break(rec->ip, old);
}
-/*
- * If the record has the FTRACE_FL_REGS set, that means that it
- * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
- * is not not set, then it wants to convert to the normal callback.
- */
-static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
-{
- if (rec->flags & FTRACE_FL_REGS)
- return (unsigned long)FTRACE_REGS_ADDR;
- else
- return (unsigned long)FTRACE_ADDR;
-}
-
-/*
- * The FTRACE_FL_REGS_EN is set when the record already points to
- * a function that saves all the regs. Basically the '_EN' version
- * represents the current state of the function.
- */
-static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
-{
- if (rec->flags & FTRACE_FL_REGS_EN)
- return (unsigned long)FTRACE_REGS_ADDR;
- else
- return (unsigned long)FTRACE_ADDR;
-}
-
static int add_breakpoints(struct dyn_ftrace *rec, int enable)
{
unsigned long ftrace_addr;
int ret;
- ret = ftrace_test_record(rec, enable);
+ ftrace_addr = ftrace_get_addr_curr(rec);
- ftrace_addr = get_ftrace_addr(rec);
+ ret = ftrace_test_record(rec, enable);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
@@ -392,10 +357,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
/* converting nop to call */
return add_brk_on_nop(rec);
- case FTRACE_UPDATE_MODIFY_CALL_REGS:
case FTRACE_UPDATE_MODIFY_CALL:
- ftrace_addr = get_ftrace_old_addr(rec);
- /* fall through */
case FTRACE_UPDATE_MAKE_NOP:
/* converting a call to a nop */
return add_brk_on_call(rec, ftrace_addr);
@@ -440,14 +402,14 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
* If not, don't touch the breakpoint, we make just create
* a disaster.
*/
- ftrace_addr = get_ftrace_addr(rec);
+ ftrace_addr = ftrace_get_addr_new(rec);
nop = ftrace_call_replace(ip, ftrace_addr);
if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
goto update;
/* Check both ftrace_addr and ftrace_old_addr */
- ftrace_addr = get_ftrace_old_addr(rec);
+ ftrace_addr = ftrace_get_addr_curr(rec);
nop = ftrace_call_replace(ip, ftrace_addr);
if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
@@ -491,13 +453,12 @@ static int add_update(struct dyn_ftrace *rec, int enable)
ret = ftrace_test_record(rec, enable);
- ftrace_addr = get_ftrace_addr(rec);
+ ftrace_addr = ftrace_get_addr_new(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
- case FTRACE_UPDATE_MODIFY_CALL_REGS:
case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
@@ -538,13 +499,12 @@ static int finish_update(struct dyn_ftrace *rec, int enable)
ret = ftrace_update_record(rec, enable);
- ftrace_addr = get_ftrace_addr(rec);
+ ftrace_addr = ftrace_get_addr_new(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
- case FTRACE_UPDATE_MODIFY_CALL_REGS:
case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
@@ -621,8 +581,8 @@ void ftrace_replace_code(int enable)
return;
remove_breakpoints:
+ pr_warn("Failed on %s (%d):\n", report, count);
ftrace_bug(ret, rec ? rec->ip : 0);
- printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
for_ftrace_rec_iter(iter) {
rec = ftrace_rec_iter_record(iter);
/*
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 068054f4bf2..eda1a865641 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -172,7 +172,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
*/
load_ucode_bsp();
- if (console_loglevel == 10)
+ if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
early_printk("Kernel alive\n");
clear_page(init_level4_pgt);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 4177bfbc80b..319bcb9372f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -74,9 +74,6 @@ static inline void hpet_writel(unsigned int d, unsigned int a)
static inline void hpet_set_mapping(void)
{
hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
-#ifdef CONFIG_X86_64
- __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE);
-#endif
}
static inline void hpet_clear_mapping(void)
@@ -479,7 +476,7 @@ static int hpet_msi_next_event(unsigned long delta,
static int hpet_setup_msi_irq(unsigned int irq)
{
if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
- destroy_irq(irq);
+ irq_free_hwirq(irq);
return -EINVAL;
}
return 0;
@@ -487,9 +484,8 @@ static int hpet_setup_msi_irq(unsigned int irq)
static int hpet_assign_irq(struct hpet_dev *dev)
{
- unsigned int irq;
+ unsigned int irq = irq_alloc_hwirq(-1);
- irq = create_irq_nr(0, -1);
if (!irq)
return -EINVAL;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 283a76a9cc4..11ccfb0a63e 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -17,6 +17,7 @@
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>
+#include <asm/desc.h>
#define CREATE_TRACE_POINTS
#include <asm/trace/irq_vectors.h>
@@ -334,10 +335,17 @@ int check_irq_vectors_for_cpu_disable(void)
for_each_online_cpu(cpu) {
if (cpu == this_cpu)
continue;
- for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
- vector++) {
- if (per_cpu(vector_irq, cpu)[vector] < 0)
- count++;
+ /*
+ * We scan from FIRST_EXTERNAL_VECTOR to first system
+ * vector. If the vector is marked in the used vectors
+ * bitmap or an irq is assigned to it, we don't count
+ * it as available.
+ */
+ for (vector = FIRST_EXTERNAL_VECTOR;
+ vector < first_system_vector; vector++) {
+ if (!test_bit(vector, used_vectors) &&
+ per_cpu(vector_irq, cpu)[vector] < 0)
+ count++;
}
}
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index dcbbaa165bd..c37886d759c 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,8 +20,6 @@
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
-int sysctl_ldt16 = 0;
-
#ifdef CONFIG_SMP
static void flush_ldt(void *current_mm)
{
@@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
}
}
- /*
- * On x86-64 we do not support 16-bit segments due to
- * IRET leaking the high bits of the kernel stack address.
- */
-#ifdef CONFIG_X86_64
- if (!ldt_info.seg_32bit && !sysctl_ldt16) {
+ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
error = -EINVAL;
goto out_unlock;
}
-#endif
fill_ldt(&ldt, &ldt_info);
if (oldmode)
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
new file mode 100644
index 00000000000..c050a015316
--- /dev/null
+++ b/arch/x86/kernel/mcount_64.S
@@ -0,0 +1,217 @@
+/*
+ * linux/arch/x86_64/mcount_64.S
+ *
+ * Copyright (C) 2014 Steven Rostedt, Red Hat Inc
+ */
+
+#include <linux/linkage.h>
+#include <asm/ptrace.h>
+#include <asm/ftrace.h>
+
+
+ .code64
+ .section .entry.text, "ax"
+
+
+#ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CC_USING_FENTRY
+# define function_hook __fentry__
+#else
+# define function_hook mcount
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(function_hook)
+ retq
+END(function_hook)
+
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+ MCOUNT_SAVE_FRAME \skip
+
+ /* Load the ftrace_ops into the 3rd parameter */
+ movq function_trace_op(%rip), %rdx
+
+ /* Load ip into the first parameter */
+ movq RIP(%rsp), %rdi
+ subq $MCOUNT_INSN_SIZE, %rdi
+ /* Load the parent_ip into the second parameter */
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
+ movq 8(%rbp), %rsi
+#endif
+.endm
+
+ENTRY(ftrace_caller)
+ /* Check if tracing was disabled (quick check) */
+ cmpl $0, function_trace_stop
+ jne ftrace_stub
+
+ ftrace_caller_setup
+ /* regs go into 4th parameter (but make it NULL) */
+ movq $0, %rcx
+
+GLOBAL(ftrace_call)
+ call ftrace_stub
+
+ MCOUNT_RESTORE_FRAME
+ftrace_return:
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+GLOBAL(ftrace_graph_call)
+ jmp ftrace_stub
+#endif
+
+GLOBAL(ftrace_stub)
+ retq
+END(ftrace_caller)
+
+ENTRY(ftrace_regs_caller)
+ /* Save the current flags before compare (in SS location)*/
+ pushfq
+
+ /* Check if tracing was disabled (quick check) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /* skip=8 to skip flags saved in SS */
+ ftrace_caller_setup 8
+
+ /* Save the rest of pt_regs */
+ movq %r15, R15(%rsp)
+ movq %r14, R14(%rsp)
+ movq %r13, R13(%rsp)
+ movq %r12, R12(%rsp)
+ movq %r11, R11(%rsp)
+ movq %r10, R10(%rsp)
+ movq %rbp, RBP(%rsp)
+ movq %rbx, RBX(%rsp)
+ /* Copy saved flags */
+ movq SS(%rsp), %rcx
+ movq %rcx, EFLAGS(%rsp)
+ /* Kernel segments */
+ movq $__KERNEL_DS, %rcx
+ movq %rcx, SS(%rsp)
+ movq $__KERNEL_CS, %rcx
+ movq %rcx, CS(%rsp)
+ /* Stack - skipping return address */
+ leaq SS+16(%rsp), %rcx
+ movq %rcx, RSP(%rsp)
+
+ /* regs go into 4th parameter */
+ leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ /* Copy flags back to SS, to restore them */
+ movq EFLAGS(%rsp), %rax
+ movq %rax, SS(%rsp)
+
+ /* Handlers can change the RIP */
+ movq RIP(%rsp), %rax
+ movq %rax, SS+8(%rsp)
+
+ /* restore the rest of pt_regs */
+ movq R15(%rsp), %r15
+ movq R14(%rsp), %r14
+ movq R13(%rsp), %r13
+ movq R12(%rsp), %r12
+ movq R10(%rsp), %r10
+ movq RBP(%rsp), %rbp
+ movq RBX(%rsp), %rbx
+
+ /* skip=8 to skip flags saved in SS */
+ MCOUNT_RESTORE_FRAME 8
+
+ /* Restore flags */
+ popfq
+
+ jmp ftrace_return
+ftrace_restore_flags:
+ popfq
+ jmp ftrace_stub
+
+END(ftrace_regs_caller)
+
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(function_hook)
+ cmpl $0, function_trace_stop
+ jne ftrace_stub
+
+ cmpq $ftrace_stub, ftrace_trace_function
+ jnz trace
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ cmpq $ftrace_stub, ftrace_graph_return
+ jnz ftrace_graph_caller
+
+ cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
+ jnz ftrace_graph_caller
+#endif
+
+GLOBAL(ftrace_stub)
+ retq
+
+trace:
+ MCOUNT_SAVE_FRAME
+
+ movq RIP(%rsp), %rdi
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
+ movq 8(%rbp), %rsi
+#endif
+ subq $MCOUNT_INSN_SIZE, %rdi
+
+ call *ftrace_trace_function
+
+ MCOUNT_RESTORE_FRAME
+
+ jmp ftrace_stub
+END(function_hook)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ENTRY(ftrace_graph_caller)
+ MCOUNT_SAVE_FRAME
+
+#ifdef CC_USING_FENTRY
+ leaq SS+16(%rsp), %rdi
+ movq $0, %rdx /* No framepointers needed */
+#else
+ leaq 8(%rbp), %rdi
+ movq (%rbp), %rdx
+#endif
+ movq RIP(%rsp), %rsi
+ subq $MCOUNT_INSN_SIZE, %rsi
+
+ call prepare_ftrace_return
+
+ MCOUNT_RESTORE_FRAME
+
+ retq
+END(ftrace_graph_caller)
+
+GLOBAL(return_to_handler)
+ subq $24, %rsp
+
+ /* Save the return values */
+ movq %rax, (%rsp)
+ movq %rdx, 8(%rsp)
+ movq %rbp, %rdi
+
+ call ftrace_return_to_handler
+
+ movq %rax, %rdi
+ movq 8(%rsp), %rdx
+ movq (%rsp), %rax
+ addq $24, %rsp
+ jmp *%rdi
+#endif
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index f7d0672481f..a25e202bb31 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -97,12 +97,17 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_mask = dma_alloc_coherent_mask(dev, flag);
- flag |= __GFP_ZERO;
+ flag &= ~__GFP_ZERO;
again:
page = NULL;
/* CMA can be used only in the context which permits sleeping */
- if (flag & __GFP_WAIT)
+ if (flag & __GFP_WAIT) {
page = dma_alloc_from_contiguous(dev, count, get_order(size));
+ if (page && page_to_phys(page) + size > dma_mask) {
+ dma_release_from_contiguous(dev, page, count);
+ page = NULL;
+ }
+ }
/* fallback */
if (!page)
page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
@@ -120,7 +125,7 @@ again:
return NULL;
}
-
+ memset(page_address(page), 0, size);
*dma_addr = addr;
return page_address(page);
}
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 6c483ba98b9..77dd0ad58be 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -14,7 +14,7 @@
#include <asm/iommu_table.h>
int swiotlb __read_mostly;
-static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
struct dma_attrs *attrs)
{
@@ -28,11 +28,14 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
}
-static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+void x86_swiotlb_free_coherent(struct device *dev, size_t size,
void *vaddr, dma_addr_t dma_addr,
struct dma_attrs *attrs)
{
- swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+ if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr)))
+ swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+ else
+ dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs);
}
static struct dma_map_ops swiotlb_dma_ops = {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 09c76d26555..78a0e629892 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p)
setup_real_mode();
memblock_set_current_limit(get_max_mapped());
- dma_contiguous_reserve(0);
+ dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 9e5de6813e1..a0da58db43a 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -298,7 +298,8 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
}
if (current->mm->context.vdso)
- restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn);
+ restorer = current->mm->context.vdso +
+ selected_vdso32->sym___kernel_sigreturn;
else
restorer = &frame->retcode;
if (ksig->ka.sa.sa_flags & SA_RESTORER)
@@ -361,7 +362,8 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
save_altstack_ex(&frame->uc.uc_stack, regs->sp);
/* Set up to return from userspace. */
- restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
+ restorer = current->mm->context.vdso +
+ selected_vdso32->sym___kernel_sigreturn;
if (ksig->ka.sa.sa_flags & SA_RESTORER)
restorer = ksig->ka.sa.sa_restorer;
put_user_ex(restorer, &frame->pretcode);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 34826934d4a..5492798930e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -244,6 +244,13 @@ static void notrace start_secondary(void *unused)
check_tsc_sync_target();
/*
+ * Enable the espfix hack for this CPU
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ init_espfix_ap();
+#endif
+
+ /*
* We need to hold vector_lock so there the set of online cpus
* does not change while we are assigning vectors to cpus. Holding
* this lock ensures we don't half assign or remove an irq from a cpu.
@@ -859,9 +866,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
/* was set by cpu_init() */
cpumask_clear_cpu(cpu, cpu_initialized_mask);
-
- set_cpu_present(cpu, false);
- per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
}
/* mark "stuck" area as not stuck */
@@ -921,7 +925,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
- pr_debug("do_boot_cpu failed %d\n", err);
+ pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
return -EIO;
}
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 8b3b3eb3cea..ea5b5709aa7 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -91,7 +91,7 @@ static int addr_to_vsyscall_nr(unsigned long addr)
{
int nr;
- if ((addr & ~0xC00UL) != VSYSCALL_START)
+ if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
return -EINVAL;
nr = (addr & 0xC00UL) >> 10;
@@ -330,24 +330,17 @@ void __init map_vsyscall(void)
{
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page);
- __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall,
+ __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
vsyscall_mode == NATIVE
? PAGE_KERNEL_VSYSCALL
: PAGE_KERNEL_VVAR);
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) !=
- (unsigned long)VSYSCALL_START);
-
- __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR);
- BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) !=
- (unsigned long)VVAR_ADDRESS);
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
+ (unsigned long)VSYSCALL_ADDR);
}
static int __init vsyscall_init(void)
{
- BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
-
cpu_notifier_register_begin();
on_each_cpu(cpu_vsyscall_init, NULL, 1);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-06-01 16:44:13 +0000