summaryrefslogtreecommitdiffstats
path: root/arch/i386/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/i386/kernel')
-rw-r--r--arch/i386/kernel/acpi/boot.c8
-rw-r--r--arch/i386/kernel/cpu/cpufreq/powernow-k8.c9
-rw-r--r--arch/i386/kernel/cpu/mtrr/main.c13
-rw-r--r--arch/i386/kernel/dmi_scan.c90
-rw-r--r--arch/i386/kernel/efi.c23
-rw-r--r--arch/i386/kernel/kprobes.c253
-rw-r--r--arch/i386/kernel/microcode.c7
-rw-r--r--arch/i386/kernel/process.c8
-rw-r--r--arch/i386/kernel/setup.c8
-rw-r--r--arch/i386/kernel/traps.c17
10 files changed, 303 insertions, 133 deletions
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index f1a21945963..033066176b3 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -668,10 +668,10 @@ unsigned long __init acpi_find_rsdp(void)
unsigned long rsdp_phys = 0;
if (efi_enabled) {
- if (efi.acpi20)
- return __pa(efi.acpi20);
- else if (efi.acpi)
- return __pa(efi.acpi);
+ if (efi.acpi20 != EFI_INVALID_TABLE_ADDR)
+ return efi.acpi20;
+ else if (efi.acpi != EFI_INVALID_TABLE_ADDR)
+ return efi.acpi;
}
/*
* Scan memory looking for the RSDP signature. First search EBDA (low
diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
index e5bc06480ff..1e70823e1cb 100644
--- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
@@ -40,6 +40,7 @@
#ifdef CONFIG_X86_POWERNOW_K8_ACPI
#include <linux/acpi.h>
+#include <linux/mutex.h>
#include <acpi/processor.h>
#endif
@@ -49,7 +50,7 @@
#include "powernow-k8.h"
/* serialize freq changes */
-static DECLARE_MUTEX(fidvid_sem);
+static DEFINE_MUTEX(fidvid_mutex);
static struct powernow_k8_data *powernow_data[NR_CPUS];
@@ -943,17 +944,17 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate))
goto err_out;
- down(&fidvid_sem);
+ mutex_lock(&fidvid_mutex);
powernow_k8_acpi_pst_values(data, newstate);
if (transition_frequency(data, newstate)) {
printk(KERN_ERR PFX "transition frequency failed\n");
ret = 1;
- up(&fidvid_sem);
+ mutex_unlock(&fidvid_mutex);
goto err_out;
}
- up(&fidvid_sem);
+ mutex_unlock(&fidvid_mutex);
pol->cur = find_khz_freq_from_fid(data->currfid);
ret = 0;
diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index 3b4618bed70..fff90bda473 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -36,6 +36,7 @@
#include <linux/pci.h>
#include <linux/smp.h>
#include <linux/cpu.h>
+#include <linux/mutex.h>
#include <asm/mtrr.h>
@@ -47,7 +48,7 @@
u32 num_var_ranges = 0;
unsigned int *usage_table;
-static DECLARE_MUTEX(mtrr_sem);
+static DEFINE_MUTEX(mtrr_mutex);
u32 size_or_mask, size_and_mask;
@@ -333,7 +334,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
/* No CPU hotplug when we change MTRR entries */
lock_cpu_hotplug();
/* Search for existing MTRR */
- down(&mtrr_sem);
+ mutex_lock(&mtrr_mutex);
for (i = 0; i < num_var_ranges; ++i) {
mtrr_if->get(i, &lbase, &lsize, &ltype);
if (base >= lbase + lsize)
@@ -371,7 +372,7 @@ int mtrr_add_page(unsigned long base, unsigned long size,
printk(KERN_INFO "mtrr: no more MTRRs available\n");
error = i;
out:
- up(&mtrr_sem);
+ mutex_unlock(&mtrr_mutex);
unlock_cpu_hotplug();
return error;
}
@@ -464,7 +465,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
max = num_var_ranges;
/* No CPU hotplug when we change MTRR entries */
lock_cpu_hotplug();
- down(&mtrr_sem);
+ mutex_lock(&mtrr_mutex);
if (reg < 0) {
/* Search for existing MTRR */
for (i = 0; i < max; ++i) {
@@ -503,7 +504,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size)
set_mtrr(reg, 0, 0, 0);
error = reg;
out:
- up(&mtrr_sem);
+ mutex_unlock(&mtrr_mutex);
unlock_cpu_hotplug();
return error;
}
@@ -685,7 +686,7 @@ void mtrr_ap_init(void)
if (!mtrr_if || !use_intel())
return;
/*
- * Ideally we should hold mtrr_sem here to avoid mtrr entries changed,
+ * Ideally we should hold mtrr_mutex here to avoid mtrr entries changed,
* but this routine will be called in cpu boot time, holding the lock
* breaks it. This routine is called in two cases: 1.very earily time
* of software resume, when there absolutely isn't mtrr entry changes;
diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c
index ebc8dc116c4..5efceebc48d 100644
--- a/arch/i386/kernel/dmi_scan.c
+++ b/arch/i386/kernel/dmi_scan.c
@@ -3,6 +3,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/dmi.h>
+#include <linux/efi.h>
#include <linux/bootmem.h>
#include <linux/slab.h>
#include <asm/dmi.h>
@@ -185,47 +186,72 @@ static void __init dmi_decode(struct dmi_header *dm)
}
}
-void __init dmi_scan_machine(void)
+static int __init dmi_present(char __iomem *p)
{
u8 buf[15];
- char __iomem *p, *q;
+ memcpy_fromio(buf, p, 15);
+ if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) {
+ u16 num = (buf[13] << 8) | buf[12];
+ u16 len = (buf[7] << 8) | buf[6];
+ u32 base = (buf[11] << 24) | (buf[10] << 16) |
+ (buf[9] << 8) | buf[8];
- /*
- * no iounmap() for that ioremap(); it would be a no-op, but it's
- * so early in setup that sucker gets confused into doing what
- * it shouldn't if we actually call it.
- */
- p = ioremap(0xF0000, 0x10000);
- if (p == NULL)
- goto out;
-
- for (q = p; q < p + 0x10000; q += 16) {
- memcpy_fromio(buf, q, 15);
- if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) {
- u16 num = (buf[13] << 8) | buf[12];
- u16 len = (buf[7] << 8) | buf[6];
- u32 base = (buf[11] << 24) | (buf[10] << 16) |
- (buf[9] << 8) | buf[8];
-
- /*
- * DMI version 0.0 means that the real version is taken from
- * the SMBIOS version, which we don't know at this point.
- */
- if (buf[14] != 0)
- printk(KERN_INFO "DMI %d.%d present.\n",
- buf[14] >> 4, buf[14] & 0xF);
- else
- printk(KERN_INFO "DMI present.\n");
+ /*
+ * DMI version 0.0 means that the real version is taken from
+ * the SMBIOS version, which we don't know at this point.
+ */
+ if (buf[14] != 0)
+ printk(KERN_INFO "DMI %d.%d present.\n",
+ buf[14] >> 4, buf[14] & 0xF);
+ else
+ printk(KERN_INFO "DMI present.\n");
+ if (dmi_table(base,len, num, dmi_decode) == 0)
+ return 0;
+ }
+ return 1;
+}
- if (dmi_table(base,len, num, dmi_decode) == 0)
+void __init dmi_scan_machine(void)
+{
+ char __iomem *p, *q;
+ int rc;
+
+ if (efi_enabled) {
+ if (efi.smbios == EFI_INVALID_TABLE_ADDR)
+ goto out;
+
+ /* This is called as a core_initcall() because it isn't
+ * needed during early boot. This also means we can
+ * iounmap the space when we're done with it.
+ */
+ p = dmi_ioremap(efi.smbios, 32);
+ if (p == NULL)
+ goto out;
+
+ rc = dmi_present(p + 0x10); /* offset of _DMI_ string */
+ dmi_iounmap(p, 32);
+ if (!rc)
+ return;
+ }
+ else {
+ /*
+ * no iounmap() for that ioremap(); it would be a no-op, but
+ * it's so early in setup that sucker gets confused into doing
+ * what it shouldn't if we actually call it.
+ */
+ p = dmi_ioremap(0xF0000, 0x10000);
+ if (p == NULL)
+ goto out;
+
+ for (q = p; q < p + 0x10000; q += 16) {
+ rc = dmi_present(q);
+ if (!rc)
return;
}
}
-
-out: printk(KERN_INFO "DMI not present or invalid.\n");
+ out: printk(KERN_INFO "DMI not present or invalid.\n");
}
-
/**
* dmi_check_system - check system DMI data
* @list: array of dmi_system_id structures to match against
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index 7ec6cfa01fb..9202b67c4b2 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -361,7 +361,7 @@ void __init efi_init(void)
*/
c16 = (efi_char16_t *) boot_ioremap(efi.systab->fw_vendor, 2);
if (c16) {
- for (i = 0; i < sizeof(vendor) && *c16; ++i)
+ for (i = 0; i < (sizeof(vendor) - 1) && *c16; ++i)
vendor[i] = *c16++;
vendor[i] = '\0';
} else
@@ -381,29 +381,38 @@ void __init efi_init(void)
if (config_tables == NULL)
printk(KERN_ERR PFX "Could not map EFI Configuration Table!\n");
+ efi.mps = EFI_INVALID_TABLE_ADDR;
+ efi.acpi = EFI_INVALID_TABLE_ADDR;
+ efi.acpi20 = EFI_INVALID_TABLE_ADDR;
+ efi.smbios = EFI_INVALID_TABLE_ADDR;
+ efi.sal_systab = EFI_INVALID_TABLE_ADDR;
+ efi.boot_info = EFI_INVALID_TABLE_ADDR;
+ efi.hcdp = EFI_INVALID_TABLE_ADDR;
+ efi.uga = EFI_INVALID_TABLE_ADDR;
+
for (i = 0; i < num_config_tables; i++) {
if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) {
- efi.mps = (void *)config_tables[i].table;
+ efi.mps = config_tables[i].table;
printk(KERN_INFO " MPS=0x%lx ", config_tables[i].table);
} else
if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) {
- efi.acpi20 = __va(config_tables[i].table);
+ efi.acpi20 = config_tables[i].table;
printk(KERN_INFO " ACPI 2.0=0x%lx ", config_tables[i].table);
} else
if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) {
- efi.acpi = __va(config_tables[i].table);
+ efi.acpi = config_tables[i].table;
printk(KERN_INFO " ACPI=0x%lx ", config_tables[i].table);
} else
if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) {
- efi.smbios = (void *) config_tables[i].table;
+ efi.smbios = config_tables[i].table;
printk(KERN_INFO " SMBIOS=0x%lx ", config_tables[i].table);
} else
if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) {
- efi.hcdp = (void *)config_tables[i].table;
+ efi.hcdp = config_tables[i].table;
printk(KERN_INFO " HCDP=0x%lx ", config_tables[i].table);
} else
if (efi_guidcmp(config_tables[i].guid, UGA_IO_PROTOCOL_GUID) == 0) {
- efi.uga = (void *)config_tables[i].table;
+ efi.uga = config_tables[i].table;
printk(KERN_INFO " UGA=0x%lx ", config_tables[i].table);
}
}
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 7a59050242a..f19768789e8 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -35,12 +35,56 @@
#include <asm/cacheflush.h>
#include <asm/kdebug.h>
#include <asm/desc.h>
+#include <asm/uaccess.h>
void jprobe_return_end(void);
DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+/* insert a jmp code */
+static inline void set_jmp_op(void *from, void *to)
+{
+ struct __arch_jmp_op {
+ char op;
+ long raddr;
+ } __attribute__((packed)) *jop;
+ jop = (struct __arch_jmp_op *)from;
+ jop->raddr = (long)(to) - ((long)(from) + 5);
+ jop->op = RELATIVEJUMP_INSTRUCTION;
+}
+
+/*
+ * returns non-zero if opcodes can be boosted.
+ */
+static inline int can_boost(kprobe_opcode_t opcode)
+{
+ switch (opcode & 0xf0 ) {
+ case 0x70:
+ return 0; /* can't boost conditional jump */
+ case 0x90:
+ /* can't boost call and pushf */
+ return opcode != 0x9a && opcode != 0x9c;
+ case 0xc0:
+ /* can't boost undefined opcodes and soft-interruptions */
+ return (0xc1 < opcode && opcode < 0xc6) ||
+ (0xc7 < opcode && opcode < 0xcc) || opcode == 0xcf;
+ case 0xd0:
+ /* can boost AA* and XLAT */
+ return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7);
+ case 0xe0:
+ /* can boost in/out and (may be) jmps */
+ return (0xe3 < opcode && opcode != 0xe8);
+ case 0xf0:
+ /* clear and set flags can be boost */
+ return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
+ default:
+ /* currently, can't boost 2 bytes opcodes */
+ return opcode != 0x0f;
+ }
+}
+
+
/*
* returns non-zero if opcode modifies the interrupt flag.
*/
@@ -65,6 +109,11 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
p->opcode = *p->addr;
+ if (can_boost(p->opcode)) {
+ p->ainsn.boostable = 0;
+ } else {
+ p->ainsn.boostable = -1;
+ }
return 0;
}
@@ -155,9 +204,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p;
int ret = 0;
- kprobe_opcode_t *addr = NULL;
- unsigned long *lp;
+ kprobe_opcode_t *addr;
struct kprobe_ctlblk *kcb;
+#ifdef CONFIG_PREEMPT
+ unsigned pre_preempt_count = preempt_count();
+#endif /* CONFIG_PREEMPT */
+
+ addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t));
/*
* We don't want to be preempted for the entire
@@ -166,17 +219,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
preempt_disable();
kcb = get_kprobe_ctlblk();
- /* Check if the application is using LDT entry for its code segment and
- * calculate the address by reading the base address from the LDT entry.
- */
- if ((regs->xcs & 4) && (current->mm)) {
- lp = (unsigned long *) ((unsigned long)((regs->xcs >> 3) * 8)
- + (char *) current->mm->context.ldt);
- addr = (kprobe_opcode_t *) (get_desc_base(lp) + regs->eip -
- sizeof(kprobe_opcode_t));
- } else {
- addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t));
- }
/* Check we're not actually recursing */
if (kprobe_running()) {
p = get_kprobe(addr);
@@ -252,6 +294,21 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
/* handler has already set things up, so skip ss setup */
return 1;
+ if (p->ainsn.boostable == 1 &&
+#ifdef CONFIG_PREEMPT
+ !(pre_preempt_count) && /*
+ * This enables booster when the direct
+ * execution path aren't preempted.
+ */
+#endif /* CONFIG_PREEMPT */
+ !p->post_handler && !p->break_handler ) {
+ /* Boost up -- we can execute copied instructions directly */
+ reset_current_kprobe();
+ regs->eip = (unsigned long)p->ainsn.insn;
+ preempt_enable_no_resched();
+ return 1;
+ }
+
ss_probe:
prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_HIT_SS;
@@ -267,17 +324,44 @@ no_kprobe:
* here. When a retprobed function returns, this probe is hit and
* trampoline_probe_handler() runs, calling the kretprobe's handler.
*/
- void kretprobe_trampoline_holder(void)
+ void __kprobes kretprobe_trampoline_holder(void)
{
- asm volatile ( ".global kretprobe_trampoline\n"
+ asm volatile ( ".global kretprobe_trampoline\n"
"kretprobe_trampoline: \n"
- "nop\n");
- }
+ " pushf\n"
+ /* skip cs, eip, orig_eax, es, ds */
+ " subl $20, %esp\n"
+ " pushl %eax\n"
+ " pushl %ebp\n"
+ " pushl %edi\n"
+ " pushl %esi\n"
+ " pushl %edx\n"
+ " pushl %ecx\n"
+ " pushl %ebx\n"
+ " movl %esp, %eax\n"
+ " call trampoline_handler\n"
+ /* move eflags to cs */
+ " movl 48(%esp), %edx\n"
+ " movl %edx, 44(%esp)\n"
+ /* save true return address on eflags */
+ " movl %eax, 48(%esp)\n"
+ " popl %ebx\n"
+ " popl %ecx\n"
+ " popl %edx\n"
+ " popl %esi\n"
+ " popl %edi\n"
+ " popl %ebp\n"
+ " popl %eax\n"
+ /* skip eip, orig_eax, es, ds */
+ " addl $16, %esp\n"
+ " popf\n"
+ " ret\n");
+}
/*
- * Called when we hit the probe point at kretprobe_trampoline
+ * Called from kretprobe_trampoline
*/
-int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head;
@@ -306,8 +390,11 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
/* another task is sharing our hash bucket */
continue;
- if (ri->rp && ri->rp->handler)
+ if (ri->rp && ri->rp->handler){
+ __get_cpu_var(current_kprobe) = &ri->rp->kp;
ri->rp->handler(ri, regs);
+ __get_cpu_var(current_kprobe) = NULL;
+ }
orig_ret_address = (unsigned long)ri->ret_addr;
recycle_rp_inst(ri);
@@ -322,18 +409,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
}
BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address));
- regs->eip = orig_ret_address;
- reset_current_kprobe();
spin_unlock_irqrestore(&kretprobe_lock, flags);
- preempt_enable_no_resched();
- /*
- * By returning a non-zero value, we are telling
- * kprobe_handler() that we don't want the post_handler
- * to run (and have re-enabled preemption)
- */
- return 1;
+ return (void*)orig_ret_address;
}
/*
@@ -357,15 +436,17 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
* 2) If the single-stepped instruction was a call, the return address
* that is atop the stack is the address following the copied instruction.
* We need to make it the address following the original instruction.
+ *
+ * This function also checks instruction size for preparing direct execution.
*/
static void __kprobes resume_execution(struct kprobe *p,
struct pt_regs *regs, struct kprobe_ctlblk *kcb)
{
unsigned long *tos = (unsigned long *)&regs->esp;
- unsigned long next_eip = 0;
unsigned long copy_eip = (unsigned long)p->ainsn.insn;
unsigned long orig_eip = (unsigned long)p->addr;
+ regs->eflags &= ~TF_MASK;
switch (p->ainsn.insn[0]) {
case 0x9c: /* pushfl */
*tos &= ~(TF_MASK | IF_MASK);
@@ -375,37 +456,51 @@ static void __kprobes resume_execution(struct kprobe *p,
case 0xcb:
case 0xc2:
case 0xca:
- regs->eflags &= ~TF_MASK;
- /* eip is already adjusted, no more changes required*/
- return;
+ case 0xea: /* jmp absolute -- eip is correct */
+ /* eip is already adjusted, no more changes required */
+ p->ainsn.boostable = 1;
+ goto no_change;
case 0xe8: /* call relative - Fix return addr */
*tos = orig_eip + (*tos - copy_eip);
break;
case 0xff:
if ((p->ainsn.insn[1] & 0x30) == 0x10) {
/* call absolute, indirect */
- /* Fix return addr; eip is correct. */
- next_eip = regs->eip;
+ /*
+ * Fix return addr; eip is correct.
+ * But this is not boostable
+ */
*tos = orig_eip + (*tos - copy_eip);
+ goto no_change;
} else if (((p->ainsn.insn[1] & 0x31) == 0x20) || /* jmp near, absolute indirect */
((p->ainsn.insn[1] & 0x31) == 0x21)) { /* jmp far, absolute indirect */
- /* eip is correct. */
- next_eip = regs->eip;
+ /* eip is correct. And this is boostable */
+ p->ainsn.boostable = 1;
+ goto no_change;
}
- break;
- case 0xea: /* jmp absolute -- eip is correct */
- next_eip = regs->eip;
- break;
default:
break;
}
- regs->eflags &= ~TF_MASK;
- if (next_eip) {
- regs->eip = next_eip;
- } else {
- regs->eip = orig_eip + (regs->eip - copy_eip);
+ if (p->ainsn.boostable == 0) {
+ if ((regs->eip > copy_eip) &&
+ (regs->eip - copy_eip) + 5 < MAX_INSN_SIZE) {
+ /*
+ * These instructions can be executed directly if it
+ * jumps back to correct address.
+ */
+ set_jmp_op((void *)regs->eip,
+ (void *)orig_eip + (regs->eip - copy_eip));
+ p->ainsn.boostable = 1;
+ } else {
+ p->ainsn.boostable = -1;
+ }
}
+
+ regs->eip = orig_eip + (regs->eip - copy_eip);
+
+no_change:
+ return;
}
/*
@@ -453,15 +548,57 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
struct kprobe *cur = kprobe_running();
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
- return 1;
-
- if (kcb->kprobe_status & KPROBE_HIT_SS) {
- resume_execution(cur, regs, kcb);
+ switch(kcb->kprobe_status) {
+ case KPROBE_HIT_SS:
+ case KPROBE_REENTER:
+ /*
+ * We are here because the instruction being single
+ * stepped caused a page fault. We reset the current
+ * kprobe and the eip points back to the probe address
+ * and allow the page fault handler to continue as a
+ * normal page fault.
+ */
+ regs->eip = (unsigned long)cur->addr;
regs->eflags |= kcb->kprobe_old_eflags;
-
- reset_current_kprobe();
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ restore_previous_kprobe(kcb);
+ else
+ reset_current_kprobe();
preempt_enable_no_resched();
+ break;
+ case KPROBE_HIT_ACTIVE:
+ case KPROBE_HIT_SSDONE:
+ /*
+ * We increment the nmissed count for accounting,
+ * we can also use npre/npostfault count for accouting
+ * these specific fault cases.
+ */
+ kprobes_inc_nmissed_count(cur);
+
+ /*
+ * We come here because instructions in the pre/post
+ * handler caused the page_fault, this could happen
+ * if handler tries to access user space by
+ * copy_from_user(), get_user() etc. Let the
+ * user-specified handler try to fix it first.
+ */
+ if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
+ return 1;
+
+ /*
+ * In case the user-specified fault handler returned
+ * zero, try to fix up.
+ */
+ if (fixup_exception(regs))
+ return 1;
+
+ /*
+ * fixup_exception() could not handle it,
+ * Let do_page_fault() fix it.
+ */
+ break;
+ default:
+ break;
}
return 0;
}
@@ -475,6 +612,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
struct die_args *args = (struct die_args *)data;
int ret = NOTIFY_DONE;
+ if (args->regs && user_mode(args->regs))
+ return ret;
+
switch (val) {
case DIE_INT3:
if (kprobe_handler(args->regs))
@@ -564,12 +704,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
return 0;
}
-static struct kprobe trampoline_p = {
- .addr = (kprobe_opcode_t *) &kretprobe_trampoline,
- .pre_handler = trampoline_probe_handler
-};
-
int __init arch_init_kprobes(void)
{
- return register_kprobe(&trampoline_p);
+ return 0;
}
diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c
index 55bc365b875..dd780a00553 100644
--- a/arch/i386/kernel/microcode.c
+++ b/arch/i386/kernel/microcode.c
@@ -81,6 +81,7 @@
#include <linux/miscdevice.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
+#include <linux/mutex.h>
#include <asm/msr.h>
#include <asm/uaccess.h>
@@ -114,7 +115,7 @@ MODULE_LICENSE("GPL");
static DEFINE_SPINLOCK(microcode_update_lock);
/* no concurrent ->write()s are allowed on /dev/cpu/microcode */
-static DECLARE_MUTEX(microcode_sem);
+static DEFINE_MUTEX(microcode_mutex);
static void __user *user_buffer; /* user area microcode data buffer */
static unsigned int user_buffer_size; /* it's size */
@@ -444,7 +445,7 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_
return -EINVAL;
}
- down(&microcode_sem);
+ mutex_lock(&microcode_mutex);
user_buffer = (void __user *) buf;
user_buffer_size = (int) len;
@@ -453,7 +454,7 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_
if (!ret)
ret = (ssize_t)len;
- up(&microcode_sem);
+ mutex_unlock(&microcode_mutex);
return ret;
}
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 299e6167408..24b3e745478 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -38,7 +38,6 @@
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/random.h>
-#include <linux/kprobes.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -364,13 +363,6 @@ void exit_thread(void)
struct task_struct *tsk = current;
struct thread_struct *t = &tsk->thread;
- /*
- * Remove function-return probe instances associated with this task
- * and put them back on the free list. Do not insert an exit probe for
- * this function, it will be disabled by kprobe_flush_task if you do.
- */
- kprobe_flush_task(tsk);
-
/* The process may have allocated an io port bitmap... nuke it. */
if (unlikely(NULL != t->io_bitmap_ptr)) {
int cpu = get_cpu();
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index d313a11acaf..6917daa159a 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -1058,10 +1058,10 @@ static int __init
free_available_memory(unsigned long start, unsigned long end, void *arg)
{
/* check max_low_pfn */
- if (start >= ((max_low_pfn + 1) << PAGE_SHIFT))
+ if (start >= (max_low_pfn << PAGE_SHIFT))
return 0;
- if (end >= ((max_low_pfn + 1) << PAGE_SHIFT))
- end = (max_low_pfn + 1) << PAGE_SHIFT;
+ if (end >= (max_low_pfn << PAGE_SHIFT))
+ end = max_low_pfn << PAGE_SHIFT;
if (start < end)
free_bootmem(start, end - start);
@@ -1286,8 +1286,6 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat
probe_roms();
for (i = 0; i < e820.nr_map; i++) {
struct resource *res;
- if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL)
- continue;
res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
switch (e820.map[i].type) {
case E820_RAM: res->name = "System RAM"; break;
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index de5386b01d3..4624f8ca245 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -386,8 +386,12 @@ void die(const char * str, struct pt_regs * regs, long err)
#endif
if (nl)
printk("\n");
- notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV);
- show_registers(regs);
+ if (notify_die(DIE_OOPS, str, regs, err,
+ current->thread.trap_no, SIGSEGV) !=
+ NOTIFY_STOP)
+ show_registers(regs);
+ else
+ regs = NULL;
} else
printk(KERN_EMERG "Recursive die() failure, output suppressed\n");
@@ -395,6 +399,9 @@ void die(const char * str, struct pt_regs * regs, long err)
die.lock_owner = -1;
spin_unlock_irqrestore(&die.lock, flags);
+ if (!regs)
+ return;
+
if (kexec_should_crash(current))
crash_kexec(regs);
@@ -623,7 +630,7 @@ static DEFINE_SPINLOCK(nmi_print_lock);
void die_nmi (struct pt_regs *regs, const char *msg)
{
- if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 0, SIGINT) ==
+ if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) ==
NOTIFY_STOP)
return;
@@ -662,7 +669,7 @@ static void default_do_nmi(struct pt_regs * regs)
reason = get_nmi_reason();
if (!(reason & 0xc0)) {
- if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT)
+ if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
== NOTIFY_STOP)
return;
#ifdef CONFIG_X86_LOCAL_APIC
@@ -678,7 +685,7 @@ static void default_do_nmi(struct pt_regs * regs)
unknown_nmi_error(reason, regs);
return;
}
- if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP)
+ if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
return;
if (reason & 0x80)
mem_parity_error(reason, regs);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-02 04:51:03 +0000