select HAVE_ARCH_JUMP_LABEL
select HAVE_TEXT_POKE_SMP
select HAVE_GENERIC_HARDIRQS
- select HAVE_SPARSE_IRQ
select SPARSE_IRQ
select GENERIC_FIND_FIRST_BIT
select GENERIC_IRQ_PROBE
select CLKEVT_I8253
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select GENERIC_IOMAP
+ select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS)
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_HAS_CPU_AUTOPROBE
+ def_bool y
+
config HAVE_SETUP_PER_CPU_AREA
def_bool y
select X86_REBOOTFIXUPS
select OF
select OF_EARLY_FLATTREE
+ select IRQ_DOMAIN
---help---
Select for the Intel CE media processor (CE4100) SOC.
This option compiles in support for the CE4100 SOC for settop
config X86_INTEL_MID
bool
-config X86_MRST
- bool "Moorestown MID platform"
- depends on PCI
- depends on PCI_GOANY
- depends on X86_IO_APIC
- select X86_INTEL_MID
- select SFI
- select DW_APB_TIMER
- select APB_TIMER
- select I2C
- select SPI
- select INTEL_SCU_IPC
- select X86_PLATFORM_DEVICES
- ---help---
- Moorestown is Intel's Low Power Intel Architecture (LPIA) based Moblin
- Internet Device(MID) platform. Moorestown consists of two chips:
- Lincroft (CPU core, graphics, and memory controller) and Langwell IOH.
- Unlike standard x86 PCs, Moorestown does not have many legacy devices
- nor standard legacy replacement devices/features. e.g. Moorestown does
- not contain i8259, i8254, HPET, legacy BIOS, most of the io ports.
-
config X86_MDFLD
bool "Medfield MID platform"
depends on PCI
select SPI
select INTEL_SCU_IPC
select X86_PLATFORM_DEVICES
+ select MFD_INTEL_MSIC
---help---
Medfield is Intel's Low Power Intel Architecture (LPIA) based Moblin
Internet Device(MID) platform.
select GPIOLIB
select OF
select OF_PROMTREE
+ select IRQ_DOMAIN
---help---
Add support for detecting the unique features of the OLPC
XO hardware.
Note: You have to set alix.force=1 for boards with Award BIOS.
+config NET5501
+ bool "Soekris Engineering net5501 System Support (LEDS, GPIO, etc)"
+ select GPIOLIB
+ ---help---
+ This option enables system support for the Soekris Engineering net5501.
+
+config GEOS
+ bool "Traverse Technologies GEOS System Support (LEDS, GPIO, etc)"
+ select GPIOLIB
+ depends on DMI
+ ---help---
+ This option enables system support for the Traverse Technologies GEOS.
+
endif # X86_32
config AMD_NB
depends on X86_64
select COMPAT_BINFMT_ELF
---help---
- Include code to run 32-bit programs under a 64-bit kernel. You should
- likely turn this on, unless you're 100% sure that you don't have any
- 32-bit programs left.
+ Include code to run legacy 32-bit programs under a
+ 64-bit kernel. You should likely turn this on, unless you're
+ 100% sure that you don't have any 32-bit programs left.
config IA32_AOUT
tristate "IA32 a.out support"
---help---
Support old a.out binaries in the 32bit emulation.
+ config X86_X32
+ bool "x32 ABI for 64-bit mode (EXPERIMENTAL)"
+ depends on X86_64 && IA32_EMULATION && EXPERIMENTAL
+ ---help---
+ Include code to run binaries for the x32 native 32-bit ABI
+ for 64-bit processors. An x32 process gets access to the
+ full 64-bit register file and wide data path while leaving
+ pointers at 32 bits for smaller memory footprint.
+
+ You will need a recent binutils (2.22 or later) with
+ elf32_x86_64 support enabled to compile a kernel with this
+ option set.
+
config COMPAT
def_bool y
- depends on IA32_EMULATION
+ depends on IA32_EMULATION || X86_X32
+ select ARCH_WANT_OLD_COMPAT_IPC
config COMPAT_FOR_U64_ALIGNMENT
def_bool COMPAT
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
- #include <linux/signal.h>
#include <linux/errno.h>
#include <linux/wait.h>
- #include <linux/ptrace.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <linux/personality.h>
#include <asm/ucontext.h>
#include <asm/uaccess.h>
#include <asm/i387.h>
+#include <asm/fpu-internal.h>
#include <asm/ptrace.h>
#include <asm/ia32_unistd.h>
#include <asm/user32.h>
#include <asm/proto.h>
#include <asm/vdso.h>
#include <asm/sigframe.h>
+ #include <asm/sighandling.h>
#include <asm/sys_ia32.h>
- #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
- #define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \
- X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
- X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
- X86_EFLAGS_CF)
-
- void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+ #define FIX_EFLAGS __FIX_EFLAGS
int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from)
{
int err = 0;
+ bool ia32 = is_ia32_task();
if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
return -EFAULT;
case __SI_FAULT >> 16:
break;
case __SI_CHLD >> 16:
- put_user_ex(from->si_utime, &to->si_utime);
- put_user_ex(from->si_stime, &to->si_stime);
+ if (ia32) {
+ put_user_ex(from->si_utime, &to->si_utime);
+ put_user_ex(from->si_stime, &to->si_stime);
+ } else {
+ put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime);
+ put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime);
+ }
put_user_ex(from->si_status, &to->si_status);
/* FALL THROUGH */
default:
(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
#include <asm/processor.h>
-#include <asm/system.h>
#ifdef CONFIG_X86_32
#include <asm/desc.h>
#define elf_check_arch(x) \
((x)->e_machine == EM_X86_64)
- #define compat_elf_check_arch(x) elf_check_arch_ia32(x)
+ #define compat_elf_check_arch(x) \
+ (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+
+ #if __USER32_DS != __USER_DS
+ # error "The following code assumes __USER32_DS == __USER_DS"
+ #endif
static inline void elf_common_init(struct thread_struct *t,
struct pt_regs *regs, const u16 ds)
void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
#define compat_start_thread start_thread_ia32
- void set_personality_ia32(void);
- #define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
+ void set_personality_ia32(bool);
+ #define COMPAT_SET_PERSONALITY(ex) \
+ set_personality_ia32((ex).e_machine == EM_X86_64)
#define COMPAT_ELF_PLATFORM ("i686")
#define VDSO_HIGH_BASE 0xffffe000U /* CONFIG_COMPAT_VDSO address */
/* 1GB for 64bit, 8MB for 32bit */
- #define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+ #define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
#define ARCH_DLINFO \
do { \
(unsigned long)current->mm->context.vdso); \
} while (0)
+ #define ARCH_DLINFO_X32 \
+ do { \
+ if (vdso_enabled) \
+ NEW_AUX_ENT(AT_SYSINFO_EHDR, \
+ (unsigned long)current->mm->context.vdso); \
+ } while (0)
+
#define AT_SYSINFO 32
- #define COMPAT_ARCH_DLINFO ARCH_DLINFO_IA32(sysctl_vsyscall32)
+ #define COMPAT_ARCH_DLINFO \
+ if (test_thread_flag(TIF_X32)) \
+ ARCH_DLINFO_X32; \
+ else \
+ ARCH_DLINFO_IA32(sysctl_vsyscall32)
#define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000)
#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
extern int arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp);
+ extern int x32_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
#define compat_arch_setup_additional_pages syscall32_setup_pages
return 1;
#endif
#ifdef CONFIG_IA32_EMULATION
- if (test_thread_flag(TIF_IA32))
+ if (test_thread_flag(TIF_ADDR32))
return 1;
#endif
return 0;
#include <asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeature.h>
-#include <asm/system.h>
#include <asm/page.h>
#include <asm/pgtable_types.h>
#include <asm/percpu.h>
#include <asm/msr.h>
#include <asm/desc_defs.h>
#include <asm/nops.h>
+#include <asm/special_insns.h>
#include <linux/personality.h>
#include <linux/cpumask.h>
#include <linux/math64.h>
#include <linux/init.h>
#include <linux/err.h>
+#include <linux/irqflags.h>
+
+/*
+ * We handle most unaligned accesses in hardware. On the other hand
+ * unaligned DMA can be quite expensive on some Nehalem processors.
+ *
+ * Based on this we disable the IP header alignment in network drivers.
+ */
+#define NET_IP_ALIGN 0
#define HBP_NUM 4
/*
extern void identify_boot_cpu(void);
extern void identify_secondary_cpu(struct cpuinfo_x86 *);
extern void print_cpu_info(struct cpuinfo_x86 *);
+void print_cpu_msr(struct cpuinfo_x86 *);
extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
extern unsigned short num_cache_leaves;
};
struct fpu {
+ unsigned int last_cpu;
+ unsigned int has_fpu;
union thread_xstate *state;
};
unsigned io_bitmap_max;
};
-static inline unsigned long native_get_debugreg(int regno)
-{
- unsigned long val = 0; /* Damn you, gcc! */
-
- switch (regno) {
- case 0:
- asm("mov %%db0, %0" :"=r" (val));
- break;
- case 1:
- asm("mov %%db1, %0" :"=r" (val));
- break;
- case 2:
- asm("mov %%db2, %0" :"=r" (val));
- break;
- case 3:
- asm("mov %%db3, %0" :"=r" (val));
- break;
- case 6:
- asm("mov %%db6, %0" :"=r" (val));
- break;
- case 7:
- asm("mov %%db7, %0" :"=r" (val));
- break;
- default:
- BUG();
- }
- return val;
-}
-
-static inline void native_set_debugreg(int regno, unsigned long value)
-{
- switch (regno) {
- case 0:
- asm("mov %0, %%db0" ::"r" (value));
- break;
- case 1:
- asm("mov %0, %%db1" ::"r" (value));
- break;
- case 2:
- asm("mov %0, %%db2" ::"r" (value));
- break;
- case 3:
- asm("mov %0, %%db3" ::"r" (value));
- break;
- case 6:
- asm("mov %0, %%db6" ::"r" (value));
- break;
- case 7:
- asm("mov %0, %%db7" ::"r" (value));
- break;
- default:
- BUG();
- }
-}
-
/*
* Set IOPL bits in EFLAGS from given mask
*/
#define __cpuid native_cpuid
#define paravirt_enabled() 0
-/*
- * These special macros can be used to get or set a debugging register
- */
-#define get_debugreg(var, register) \
- (var) = native_get_debugreg(register)
-#define set_debugreg(value, register) \
- native_set_debugreg(register, value)
-
static inline void load_sp0(struct tss_struct *tss,
struct thread_struct *thread)
{
#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \
0xc0000000 : 0xFFFFe000)
- #define TASK_SIZE (test_thread_flag(TIF_IA32) ? \
+ #define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
- #define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \
+ #define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define STACK_TOP TASK_SIZE
#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1)
extern unsigned long KSTK_ESP(struct task_struct *task);
+
+ /*
+ * User space RSP while inside the SYSCALL fast path
+ */
+ DECLARE_PER_CPU(unsigned long, old_rsp);
+
#endif /* CONFIG_X86_64 */
extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
#define cpu_has_amd_erratum(x) (false)
#endif /* CONFIG_CPU_SUP_AMD */
+#ifdef CONFIG_X86_32
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+#endif
+
+void disable_hlt(void);
+void enable_hlt(void);
+
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+bool set_pm_idle_to_default(void);
+
+void stop_this_cpu(void *dummy);
+
#endif /* _ASM_X86_PROCESSOR_H */
#define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */
#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
- #define TIF_IA32 17 /* 32bit process */
+ #define TIF_IA32 17 /* IA32 compatibility process */
#define TIF_FORK 18 /* ret_from_fork */
#define TIF_MEMDIE 20 /* is terminating due to OOM killer */
#define TIF_DEBUG 21 /* uses debug registers */
#define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */
#define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */
#define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */
+ #define TIF_ADDR32 29 /* 32-bit address space on 64 bits */
+ #define TIF_X32 30 /* 32-bit native x86-64 binary */
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP)
#define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
+ #define _TIF_ADDR32 (1 << TIF_ADDR32)
+ #define _TIF_X32 (1 << TIF_X32)
/* work to do in syscall_trace_enter() */
#define _TIF_WORK_SYSCALL_ENTRY \
* ever touches our thread-synchronous status, so we don't
* have to worry about atomic accesses.
*/
-#define TS_USEDFPU 0x0001 /* FPU was used by this task
- this quantum (SMP) */
#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
#define TS_POLLING 0x0004 /* idle task polling need_resched,
skip sending interrupt */
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/bitops.h>
+#include <linux/device.h>
#include <asm/apic.h>
#include <asm/stacktrace.h>
#include <asm/nmi.h>
- #include <asm/compat.h>
#include <asm/smp.h>
#include <asm/alternative.h>
+#include <asm/timer.h>
#include "perf_event.h"
return 0;
}
+/*
+ * check that branch_sample_type is compatible with
+ * settings needed for precise_ip > 1 which implies
+ * using the LBR to capture ALL taken branches at the
+ * priv levels of the measurement
+ */
+static inline int precise_br_compat(struct perf_event *event)
+{
+ u64 m = event->attr.branch_sample_type;
+ u64 b = 0;
+
+ /* must capture all branches */
+ if (!(m & PERF_SAMPLE_BRANCH_ANY))
+ return 0;
+
+ m &= PERF_SAMPLE_BRANCH_KERNEL | PERF_SAMPLE_BRANCH_USER;
+
+ if (!event->attr.exclude_user)
+ b |= PERF_SAMPLE_BRANCH_USER;
+
+ if (!event->attr.exclude_kernel)
+ b |= PERF_SAMPLE_BRANCH_KERNEL;
+
+ /*
+ * ignore PERF_SAMPLE_BRANCH_HV, not supported on x86
+ */
+
+ return m == b;
+}
+
int x86_pmu_hw_config(struct perf_event *event)
{
if (event->attr.precise_ip) {
if (event->attr.precise_ip > precise)
return -EOPNOTSUPP;
+ /*
+ * check that PEBS LBR correction does not conflict with
+ * whatever the user is asking with attr->branch_sample_type
+ */
+ if (event->attr.precise_ip > 1) {
+ u64 *br_type = &event->attr.branch_sample_type;
+
+ if (has_branch_stack(event)) {
+ if (!precise_br_compat(event))
+ return -EOPNOTSUPP;
+
+ /* branch_sample_type is compatible */
+
+ } else {
+ /*
+ * user did not specify branch_sample_type
+ *
+ * For PEBS fixups, we capture all
+ * the branches at the priv level of the
+ * event.
+ */
+ *br_type = PERF_SAMPLE_BRANCH_ANY;
+
+ if (!event->attr.exclude_user)
+ *br_type |= PERF_SAMPLE_BRANCH_USER;
+
+ if (!event->attr.exclude_kernel)
+ *br_type |= PERF_SAMPLE_BRANCH_KERNEL;
+ }
+ }
}
/*
/* mark unused */
event->hw.extra_reg.idx = EXTRA_REG_NONE;
+ /* mark not used */
+ event->hw.extra_reg.idx = EXTRA_REG_NONE;
+ event->hw.branch_reg.idx = EXTRA_REG_NONE;
+
return x86_pmu.hw_config(event);
}
/* Prefer fixed purpose counters */
if (x86_pmu.num_counters_fixed) {
idx = X86_PMC_IDX_FIXED;
- for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) {
+ for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_MAX) {
if (!__test_and_set_bit(idx, sched->state.used))
goto done;
}
}
/* Grab the first unused counter starting with idx */
idx = sched->state.counter;
- for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
+ for_each_set_bit_from(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
if (!__test_and_set_bit(idx, sched->state.used))
goto done;
}
break;
case CPU_STARTING:
+ if (x86_pmu.attr_rdpmc)
+ set_in_cr4(X86_CR4_PCE);
if (x86_pmu.cpu_starting)
x86_pmu.cpu_starting(cpu);
break;
}
}
+ x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
+
pr_info("... version: %d\n", x86_pmu.version);
pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
pr_info("... generic registers: %d\n", x86_pmu.num_counters);
return err;
}
+static int x86_pmu_event_idx(struct perf_event *event)
+{
+ int idx = event->hw.idx;
+
+ if (x86_pmu.num_counters_fixed && idx >= X86_PMC_IDX_FIXED) {
+ idx -= X86_PMC_IDX_FIXED;
+ idx |= 1 << 30;
+ }
+
+ return idx + 1;
+}
+
+static ssize_t get_attr_rdpmc(struct device *cdev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return snprintf(buf, 40, "%d\n", x86_pmu.attr_rdpmc);
+}
+
+static void change_rdpmc(void *info)
+{
+ bool enable = !!(unsigned long)info;
+
+ if (enable)
+ set_in_cr4(X86_CR4_PCE);
+ else
+ clear_in_cr4(X86_CR4_PCE);
+}
+
+static ssize_t set_attr_rdpmc(struct device *cdev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ unsigned long val = simple_strtoul(buf, NULL, 0);
+
+ if (!!val != !!x86_pmu.attr_rdpmc) {
+ x86_pmu.attr_rdpmc = !!val;
+ smp_call_function(change_rdpmc, (void *)val, 1);
+ }
+
+ return count;
+}
+
+static DEVICE_ATTR(rdpmc, S_IRUSR | S_IWUSR, get_attr_rdpmc, set_attr_rdpmc);
+
+static struct attribute *x86_pmu_attrs[] = {
+ &dev_attr_rdpmc.attr,
+ NULL,
+};
+
+static struct attribute_group x86_pmu_attr_group = {
+ .attrs = x86_pmu_attrs,
+};
+
+static const struct attribute_group *x86_pmu_attr_groups[] = {
+ &x86_pmu_attr_group,
+ NULL,
+};
+
+static void x86_pmu_flush_branch_stack(void)
+{
+ if (x86_pmu.flush_branch_stack)
+ x86_pmu.flush_branch_stack();
+}
+
static struct pmu pmu = {
- .pmu_enable = x86_pmu_enable,
- .pmu_disable = x86_pmu_disable,
+ .pmu_enable = x86_pmu_enable,
+ .pmu_disable = x86_pmu_disable,
+
+ .attr_groups = x86_pmu_attr_groups,
.event_init = x86_pmu_event_init,
- .add = x86_pmu_add,
- .del = x86_pmu_del,
- .start = x86_pmu_start,
- .stop = x86_pmu_stop,
- .read = x86_pmu_read,
+ .add = x86_pmu_add,
+ .del = x86_pmu_del,
+ .start = x86_pmu_start,
+ .stop = x86_pmu_stop,
+ .read = x86_pmu_read,
.start_txn = x86_pmu_start_txn,
.cancel_txn = x86_pmu_cancel_txn,
.commit_txn = x86_pmu_commit_txn,
+
+ .event_idx = x86_pmu_event_idx,
+ .flush_branch_stack = x86_pmu_flush_branch_stack,
};
+void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+{
+ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+ return;
+
+ userpg->time_mult = this_cpu_read(cyc2ns);
+ userpg->time_shift = CYC2NS_SCALE_FACTOR;
+ userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+}
+
/*
* callchain support
*/
}
#ifdef CONFIG_COMPAT
+
+ #include <asm/compat.h>
+
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
{
movq %rsp, %rsi
leaq -RBP(%rsp),%rdi /* arg1 for handler */
- testl $3, CS(%rdi)
+ testl $3, CS-RBP(%rsi)
je 1f
SWAPGS
/*
* moving irq_enter into assembly, which would be too much work)
*/
1: incl PER_CPU_VAR(irq_count)
- jne 2f
- mov PER_CPU_VAR(irq_stack_ptr),%rsp
+ cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
CFI_DEF_CFA_REGISTER rsi
-2: /* Store previous stack value */
+ /* Store previous stack value */
pushq %rsi
CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
0x77 /* DW_OP_breg7 */, 0, \
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
jnz tracesys
system_call_fastpath:
+ #if __SYSCALL_MASK == ~0
cmpq $__NR_syscall_max,%rax
+ #else
+ andl $__SYSCALL_MASK,%eax
+ cmpl $__NR_syscall_max,%eax
+ #endif
ja badsys
movq %r10,%rcx
call *sys_call_table(,%rax,8) # XXX: rip relative
*/
LOAD_ARGS ARGOFFSET, 1
RESTORE_REST
+ #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) set to -ENOSYS above */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
CFI_ENDPROC
END(stub_rt_sigreturn)
+ #ifdef CONFIG_X86_X32_ABI
+ PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
+
+ ENTRY(stub_x32_rt_sigreturn)
+ CFI_STARTPROC
+ addq $8, %rsp
+ PARTIAL_FRAME 0
+ SAVE_REST
+ movq %rsp,%rdi
+ FIXUP_TOP_OF_STACK %r11
+ 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
+ CFI_ENDPROC
+ END(stub_x32_rt_sigreturn)
+
+ ENTRY(stub_x32_execve)
+ CFI_STARTPROC
+ addq $8, %rsp
+ PARTIAL_FRAME 0
+ SAVE_REST
+ FIXUP_TOP_OF_STACK %r11
+ movq %rsp, %rcx
+ call sys32_execve
+ RESTORE_TOP_OF_STACK %r11
+ movq %rax,RAX(%rsp)
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+ END(stub_x32_execve)
+
+ #endif
+
/*
* 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
/* Restore saved previous stack */
popq %rsi
- CFI_DEF_CFA_REGISTER rsi
+ CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */
leaq ARGOFFSET-RBP(%rsi), %rsp
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET
/* Use %rdx as out temp variable throughout */
pushq_cfi %rdx
+ CFI_REL_OFFSET rdx, 0
+
+ /*
+ * If %cs was not the kernel segment, then the NMI triggered in user
+ * space, which means it is definitely not nested.
+ */
+ cmpl $__KERNEL_CS, 16(%rsp)
+ jne first_nmi
/*
* Check the special variable on the stack to see if NMIs are
* executing.
*/
- cmp $1, -8(%rsp)
+ cmpl $1, -8(%rsp)
je nested_nmi
/*
*/
lea 6*8(%rsp), %rdx
test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi
+ CFI_REMEMBER_STATE
nested_nmi:
/*
nested_nmi_out:
popq_cfi %rdx
+ CFI_RESTORE rdx
/* No need to check faults here */
INTERRUPT_RETURN
+ CFI_RESTORE_STATE
first_nmi:
/*
* Because nested NMIs will use the pushed location that we
* | pt_regs |
* +-------------------------+
*
- * The saved RIP is used to fix up the copied RIP that a nested
- * NMI may zero out. The original stack frame and the temp storage
+ * The saved stack frame is used to fix up the copied stack frame
+ * that a nested NMI may change to make the interrupted NMI iret jump
+ * to the repeat_nmi. The original stack frame and the temp storage
* is also used by nested NMIs and can not be trusted on exit.
*/
+ /* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+ movq (%rsp), %rdx
+ CFI_RESTORE rdx
+
/* Set the NMI executing variable on the stack. */
pushq_cfi $1
.rept 5
pushq_cfi 6*8(%rsp)
.endr
+ CFI_DEF_CFA_OFFSET SS+8-RIP
+
+ /* Everything up to here is safe from nested NMIs */
+
+ /*
+ * If there was a nested NMI, the first NMI's iret will return
+ * here. But NMIs are still enabled and we can take another
+ * nested NMI. The nested NMI checks the interrupted RIP to see
+ * if it is between repeat_nmi and end_repeat_nmi, and if so
+ * it will just return, as we are about to repeat an NMI anyway.
+ * This makes it safe to copy to the stack frame that a nested
+ * NMI will update.
+ */
+repeat_nmi:
+ /*
+ * Update the stack variable to say we are still in NMI (the update
+ * is benign for the non-repeat case, where 1 was pushed just above
+ * to this very stack slot).
+ */
+ movq $1, 5*8(%rsp)
/* Make another copy, this one may be modified by nested NMIs */
.rept 5
pushq_cfi 4*8(%rsp)
.endr
-
- /* Do not pop rdx, nested NMIs will corrupt it */
- movq 11*8(%rsp), %rdx
+ CFI_DEF_CFA_OFFSET SS+8-RIP
+end_repeat_nmi:
/*
* Everything below this point can be preempted by a nested
- * NMI if the first NMI took an exception. Repeated NMIs
- * caused by an exception and nested NMI will start here, and
- * can still be preempted by another NMI.
+ * NMI if the first NMI took an exception and reset our iret stack
+ * so that we repeat another NMI.
*/
-restart_nmi:
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
subq $ORIG_RAX-R15, %rsp
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
CFI_ENDPROC
END(nmi)
- /*
- * If an NMI hit an iret because of an exception or breakpoint,
- * it can lose its NMI context, and a nested NMI may come in.
- * In that case, the nested NMI will change the preempted NMI's
- * stack to jump to here when it does the final iret.
- */
-repeat_nmi:
- INTR_FRAME
- /* Update the stack variable to say we are still in NMI */
- movq $1, 5*8(%rsp)
-
- /* copy the saved stack back to copy stack */
- .rept 5
- pushq_cfi 4*8(%rsp)
- .endr
-
- jmp restart_nmi
- CFI_ENDPROC
-end_repeat_nmi:
-
ENTRY(ignore_sysret)
CFI_STARTPROC
mov $-ENOSYS,%eax
* This file handles the architecture-dependent parts of process handling..
*/
-#include <linux/stackprotector.h>
#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
-#include <linux/tick.h>
#include <linux/prctl.h>
#include <linux/uaccess.h>
#include <linux/io.h>
#include <linux/ftrace.h>
-#include <linux/cpuidle.h>
#include <asm/pgtable.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
+#include <asm/fpu-internal.h>
#include <asm/mmu_context.h>
#include <asm/prctl.h>
#include <asm/desc.h>
#include <asm/idle.h>
#include <asm/syscalls.h>
#include <asm/debugreg.h>
-#include <asm/nmi.h>
+#include <asm/switch_to.h>
asmlinkage extern void ret_from_fork(void);
DEFINE_PER_CPU(unsigned long, old_rsp);
-static DEFINE_PER_CPU(unsigned char, is_idle);
-
-static ATOMIC_NOTIFIER_HEAD(idle_notifier);
-
-void idle_notifier_register(struct notifier_block *n)
-{
- atomic_notifier_chain_register(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_register);
-
-void idle_notifier_unregister(struct notifier_block *n)
-{
- atomic_notifier_chain_unregister(&idle_notifier, n);
-}
-EXPORT_SYMBOL_GPL(idle_notifier_unregister);
-
-void enter_idle(void)
-{
- percpu_write(is_idle, 1);
- atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
-}
-
-static void __exit_idle(void)
-{
- if (x86_test_and_clear_bit_percpu(0, is_idle) == 0)
- return;
- atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
-}
-
-/* Called from interrupts to signify idle end */
-void exit_idle(void)
-{
- /* idle loop has pid 0 */
- if (current->pid)
- return;
- __exit_idle();
-}
-
-#ifndef CONFIG_SMP
-static inline void play_dead(void)
-{
- BUG();
-}
-#endif
-
-/*
- * The idle thread. There's no useful work to be
- * done, so just try to conserve power and have a
- * low exit latency (ie sit in a loop waiting for
- * somebody to say that they'd like to reschedule)
- */
-void cpu_idle(void)
-{
- current_thread_info()->status |= TS_POLLING;
-
- /*
- * If we're the non-boot CPU, nothing set the stack canary up
- * for us. CPU0 already has it initialized but no harm in
- * doing it again. This is a good place for updating it, as
- * we wont ever return from this function (so the invalid
- * canaries already on the stack wont ever trigger).
- */
- boot_init_stack_canary();
-
- /* endless idle loop with no priority at all */
- while (1) {
- tick_nohz_idle_enter();
- while (!need_resched()) {
-
- rmb();
-
- if (cpu_is_offline(smp_processor_id()))
- play_dead();
- /*
- * Idle routines should keep interrupts disabled
- * from here on, until they go to idle.
- * Otherwise, idle callbacks can misfire.
- */
- local_touch_nmi();
- local_irq_disable();
- enter_idle();
- /* Don't trace irqs off for idle */
- stop_critical_timings();
-
- /* enter_idle() needs rcu for notifiers */
- rcu_idle_enter();
-
- if (cpuidle_idle_call())
- pm_idle();
-
- rcu_idle_exit();
- start_critical_timings();
-
- /* In many cases the interrupt that ended idle
- has already called exit_idle. But some idle
- loops can be woken up without interrupt. */
- __exit_idle();
- }
-
- tick_nohz_idle_exit();
- preempt_enable_no_resched();
- schedule();
- preempt_disable();
- }
-}
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
set_tsk_thread_flag(p, TIF_FORK);
+ p->fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
savesegment(gs, p->thread.gsindex);
loadsegment(es, _ds);
loadsegment(ds, _ds);
load_gs_index(0);
+ current->thread.usersp = new_sp;
regs->ip = new_ip;
regs->sp = new_sp;
percpu_write(old_rsp, new_sp);
void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
{
start_thread_common(regs, new_ip, new_sp,
- __USER32_CS, __USER32_DS, __USER32_DS);
+ test_thread_flag(TIF_X32)
+ ? __USER_CS : __USER32_CS,
+ __USER_DS, __USER_DS);
}
#endif
int cpu = smp_processor_id();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
unsigned fsindex, gsindex;
- bool preload_fpu;
+ fpu_switch_t fpu;
- /*
- * If the task has used fpu the last 5 timeslices, just do a full
- * restore of the math state immediately to avoid the trap; the
- * chances of needing FPU soon are obviously high now
- */
- preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
- /* we're going to use this soon, after a few expensive things */
- if (preload_fpu)
- prefetch(next->fpu.state);
+ fpu = switch_fpu_prepare(prev_p, next_p, cpu);
/*
* Reload esp0, LDT and the page table pointer:
load_TLS(next, cpu);
- /* Must be after DS reload */
- __unlazy_fpu(prev_p);
-
- /* Make sure cpu is ready for new context */
- if (preload_fpu)
- clts();
-
/*
* Leave lazy mode, flushing any hypercalls made here.
* This must be done before restoring TLS segments so
wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
prev->gsindex = gsindex;
+ switch_fpu_finish(next_p, fpu);
+
/*
* Switch the PDA and FPU contexts.
*/
task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
__switch_to_xtra(prev_p, next_p, tss);
- /*
- * Preload the FPU context, now that we've determined that the
- * task is likely to be using it.
- */
- if (preload_fpu)
- __math_state_restore();
-
return prev_p;
}
/* Make sure to be in 64bit mode */
clear_thread_flag(TIF_IA32);
+ clear_thread_flag(TIF_ADDR32);
+ clear_thread_flag(TIF_X32);
/* Ensure the corresponding mm is not marked. */
if (current->mm)
current->personality &= ~READ_IMPLIES_EXEC;
}
- void set_personality_ia32(void)
+ void set_personality_ia32(bool x32)
{
/* inherit personality from parent */
/* Make sure to be in 32bit mode */
- set_thread_flag(TIF_IA32);
- current->personality |= force_personality32;
+ set_thread_flag(TIF_ADDR32);
/* Mark the associated mm as containing 32-bit tasks. */
if (current->mm)
current->mm->context.ia32_compat = 1;
- /* Prepare the first "return" to user space */
- current_thread_info()->status |= TS_COMPAT;
+ if (x32) {
+ clear_thread_flag(TIF_IA32);
+ set_thread_flag(TIF_X32);
+ current->personality &= ~READ_IMPLIES_EXEC;
+ /* is_compat_task() uses the presence of the x32
+ syscall bit flag to determine compat status */
+ current_thread_info()->status &= ~TS_COMPAT;
+ } else {
+ set_thread_flag(TIF_IA32);
+ clear_thread_flag(TIF_X32);
+ current->personality |= force_personality32;
+ /* Prepare the first "return" to user space */
+ current_thread_info()->status |= TS_COMPAT;
+ }
}
unsigned long get_wchan(struct task_struct *p)
#include <asm/uaccess.h>
#include <asm/pgtable.h>
-#include <asm/system.h>
#include <asm/processor.h>
#include <asm/i387.h>
+#include <asm/fpu-internal.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>
return ret;
}
+ #ifdef CONFIG_X86_X32_ABI
+ static long x32_arch_ptrace(struct task_struct *child,
+ compat_long_t request, compat_ulong_t caddr,
+ compat_ulong_t cdata)
+ {
+ unsigned long addr = caddr;
+ unsigned long data = cdata;
+ void __user *datap = compat_ptr(data);
+ int ret;
+
+ switch (request) {
+ /* Read 32bits at location addr in the USER area. Only allow
+ to return the lower 32bits of segment and debug registers. */
+ case PTRACE_PEEKUSR: {
+ u32 tmp;
+
+ ret = -EIO;
+ if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+ addr < offsetof(struct user_regs_struct, cs))
+ break;
+
+ tmp = 0; /* Default return condition */
+ if (addr < sizeof(struct user_regs_struct))
+ tmp = getreg(child, addr);
+ else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+ addr <= offsetof(struct user, u_debugreg[7])) {
+ addr -= offsetof(struct user, u_debugreg[0]);
+ tmp = ptrace_get_debugreg(child, addr / sizeof(data));
+ }
+ ret = put_user(tmp, (__u32 __user *)datap);
+ break;
+ }
+
+ /* Write the word at location addr in the USER area. Only allow
+ to update segment and debug registers with the upper 32bits
+ zero-extended. */
+ case PTRACE_POKEUSR:
+ ret = -EIO;
+ if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+ addr < offsetof(struct user_regs_struct, cs))
+ break;
+
+ if (addr < sizeof(struct user_regs_struct))
+ ret = putreg(child, addr, data);
+ else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+ addr <= offsetof(struct user, u_debugreg[7])) {
+ addr -= offsetof(struct user, u_debugreg[0]);
+ ret = ptrace_set_debugreg(child,
+ addr / sizeof(data), data);
+ }
+ break;
+
+ case PTRACE_GETREGS: /* Get all gp regs from the child. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_SETREGS: /* Set all gp regs in the child. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_GENERAL,
+ 0, sizeof(struct user_regs_struct),
+ datap);
+
+ case PTRACE_GETFPREGS: /* Get the child FPU state. */
+ return copy_regset_to_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_i387_struct),
+ datap);
+
+ case PTRACE_SETFPREGS: /* Set the child FPU state. */
+ return copy_regset_from_user(child,
+ task_user_regset_view(current),
+ REGSET_FP,
+ 0, sizeof(struct user_i387_struct),
+ datap);
+
+ /* normal 64bit interface to access TLS data.
+ Works just like arch_prctl, except that the arguments
+ are reversed. */
+ case PTRACE_ARCH_PRCTL:
+ return do_arch_prctl(child, data, addr);
+
+ default:
+ return compat_ptrace_request(child, request, addr, data);
+ }
+
+ return ret;
+ }
+ #endif
+
long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
compat_ulong_t caddr, compat_ulong_t cdata)
{
int ret;
__u32 val;
+ #ifdef CONFIG_X86_X32_ABI
+ if (!is_ia32_task())
+ return x32_arch_ptrace(child, request, caddr, cdata);
+ #endif
+
switch (request) {
case PTRACE_PEEKUSR:
ret = getreg32(child, addr, &val);
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kernel.h>
- #include <linux/signal.h>
#include <linux/errno.h>
#include <linux/wait.h>
- #include <linux/ptrace.h>
#include <linux/tracehook.h>
#include <linux/unistd.h>
#include <linux/stddef.h>
#include <asm/processor.h>
#include <asm/ucontext.h>
#include <asm/i387.h>
+#include <asm/fpu-internal.h>
#include <asm/vdso.h>
#include <asm/mce.h>
+ #include <asm/sighandling.h>
#ifdef CONFIG_X86_64
#include <asm/proto.h>
#include <asm/ia32_unistd.h>
+ #include <asm/sys_ia32.h>
#endif /* CONFIG_X86_64 */
#include <asm/syscall.h>
#include <asm/sigframe.h>
- #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
- #define __FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \
- X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
- X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
- X86_EFLAGS_CF)
-
#ifdef CONFIG_X86_32
# define FIX_EFLAGS (__FIX_EFLAGS | X86_EFLAGS_RF)
#else
regs->seg = GET_SEG(seg) | 3; \
} while (0)
- static 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,
+ unsigned long *pax)
{
void __user *buf;
unsigned int tmpflags;
return err;
}
- static int
- setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
- struct pt_regs *regs, unsigned long mask)
+ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+ struct pt_regs *regs, unsigned long mask)
{
int err = 0;
#define is_ia32 0
#endif /* CONFIG_IA32_EMULATION */
+ #ifdef CONFIG_X86_X32_ABI
+ #define is_x32 test_thread_flag(TIF_X32)
+
+ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+ siginfo_t *info, compat_sigset_t *set,
+ struct pt_regs *regs);
+ #else /* !CONFIG_X86_X32_ABI */
+ #define is_x32 0
+ #endif /* CONFIG_X86_X32_ABI */
+
int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
sigset_t *set, struct pt_regs *regs);
int ia32_setup_frame(int sig, struct k_sigaction *ka,
ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
else
ret = ia32_setup_frame(usig, ka, set, regs);
- } else
+ #ifdef CONFIG_X86_X32_ABI
+ } else if (is_x32) {
+ ret = x32_setup_rt_frame(usig, ka, info,
+ (compat_sigset_t *)set, regs);
+ #endif
+ } else {
ret = __setup_rt_frame(sig, ka, info, set, regs);
+ }
if (ret) {
force_sigsegv(sig, current);
force_sig(SIGSEGV, me);
}
+
+ #ifdef CONFIG_X86_X32_ABI
+ static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+ siginfo_t *info, compat_sigset_t *set,
+ struct pt_regs *regs)
+ {
+ struct rt_sigframe_x32 __user *frame;
+ void __user *restorer;
+ int err = 0;
+ void __user *fpstate = NULL;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ if (copy_siginfo_to_user32(&frame->info, info))
+ return -EFAULT;
+ }
+
+ put_user_try {
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ put_user_ex(0, &frame->uc.uc__pad0);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ restorer = ka->sa.sa_restorer;
+ } else {
+ /* could use a vstub here */
+ restorer = NULL;
+ err |= -EFAULT;
+ }
+ put_user_ex(restorer, &frame->pretcode);
+ } put_user_catch(err);
+
+ if (err)
+ return -EFAULT;
+
+ /* Set up registers for signal handler */
+ regs->sp = (unsigned long) frame;
+ regs->ip = (unsigned long) ka->sa.sa_handler;
+
+ /* We use the x32 calling convention here... */
+ regs->di = sig;
+ regs->si = (unsigned long) &frame->info;
+ regs->dx = (unsigned long) &frame->uc;
+
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+
+ regs->cs = __USER_CS;
+ regs->ss = __USER_DS;
+
+ return 0;
+ }
+
+ asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
+ {
+ struct rt_sigframe_x32 __user *frame;
+ sigset_t set;
+ unsigned long ax;
+ struct pt_regs tregs;
+
+ frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
+
+ if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+ goto badframe;
+ if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+ goto badframe;
+
+ sigdelsetmask(&set, ~_BLOCKABLE);
+ set_current_blocked(&set);
+
+ if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+ goto badframe;
+
+ tregs = *regs;
+ if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+ goto badframe;
+
+ return ax;
+
+ badframe:
+ signal_fault(regs, frame, "x32 rt_sigreturn");
+ return 0;
+ }
+ #endif
static void find_start_end(unsigned long flags, unsigned long *begin,
unsigned long *end)
{
- if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) {
+ if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
unsigned long new_begin;
/* This is usually used needed to map code in small
model, so it needs to be in the first 31bit. Limit
(!vma || addr + len <= vma->vm_start))
return addr;
}
- if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
+ if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
&& len <= mm->cached_hole_size) {
mm->cached_hole_size = 0;
mm->free_area_cache = begin;
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
- unsigned long addr = addr0;
+ unsigned long addr = addr0, start_addr;
/* requested length too big for entire address space */
if (len > TASK_SIZE)
return addr;
/* for MAP_32BIT mappings we force the legact mmap base */
- if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT))
+ if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
goto bottomup;
/* requesting a specific address */
mm->free_area_cache = mm->mmap_base;
}
+try_again:
/* either no address requested or can't fit in requested address hole */
- addr = mm->free_area_cache;
-
- /* make sure it can fit in the remaining address space */
- if (addr > len) {
- unsigned long tmp_addr = align_addr(addr - len, filp,
- ALIGN_TOPDOWN);
-
- vma = find_vma(mm, tmp_addr);
- if (!vma || tmp_addr + len <= vma->vm_start)
- /* remember the address as a hint for next time */
- return mm->free_area_cache = tmp_addr;
- }
-
- if (mm->mmap_base < len)
- goto bottomup;
+ start_addr = addr = mm->free_area_cache;
- addr = mm->mmap_base-len;
+ if (addr < len)
+ goto fail;
+ addr -= len;
do {
addr = align_addr(addr, filp, ALIGN_TOPDOWN);
addr = vma->vm_start-len;
} while (len < vma->vm_start);
+fail:
+ /*
+ * if hint left us with no space for the requested
+ * mapping then try again:
+ */
+ if (start_addr != mm->mmap_base) {
+ mm->free_area_cache = mm->mmap_base;
+ mm->cached_hole_size = 0;
+ goto try_again;
+ }
+
bottomup:
/*
* A failed mmap() very likely causes application failure,
172 i386 prctl sys_prctl
173 i386 rt_sigreturn ptregs_rt_sigreturn stub32_rt_sigreturn
174 i386 rt_sigaction sys_rt_sigaction sys32_rt_sigaction
- 175 i386 rt_sigprocmask sys_rt_sigprocmask sys32_rt_sigprocmask
+ 175 i386 rt_sigprocmask sys_rt_sigprocmask
176 i386 rt_sigpending sys_rt_sigpending sys32_rt_sigpending
177 i386 rt_sigtimedwait sys_rt_sigtimedwait compat_sys_rt_sigtimedwait
178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo sys32_rt_sigqueueinfo
279 i386 mq_timedsend sys_mq_timedsend compat_sys_mq_timedsend
280 i386 mq_timedreceive sys_mq_timedreceive compat_sys_mq_timedreceive
281 i386 mq_notify sys_mq_notify compat_sys_mq_notify
-282 i386 mq_getsetaddr sys_mq_getsetattr compat_sys_mq_getsetattr
+282 i386 mq_getsetattr sys_mq_getsetattr compat_sys_mq_getsetattr
283 i386 kexec_load sys_kexec_load compat_sys_kexec_load
284 i386 waitid sys_waitid compat_sys_waitid
# 285 sys_setaltroot
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
gate_vma.vm_page_prot = __P101;
- /*
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully interpretable later
- * without matching up the same kernel and hardware config to see
- * what PC values meant.
- */
- gate_vma.vm_flags |= VM_ALWAYSDUMP;
+
return 0;
}
int ret = 0;
bool compat;
+ #ifdef CONFIG_X86_X32_ABI
+ if (test_thread_flag(TIF_X32))
+ return x32_setup_additional_pages(bprm, uses_interp);
+ #endif
+
if (vdso_enabled == VDSO_DISABLED)
return 0;
if (compat_uses_vma || !compat) {
/*
* MAYWRITE to allow gdb to COW and set breakpoints
- *
- * Make sure the vDSO gets into every core dump.
- * Dumping its contents makes post-mortem fully
- * interpretable later without matching up the same
- * kernel and hardware config to see what PC values
- * meant.
*/
ret = install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
vdso32_pages);
if (ret)
extern struct page *vdso_pages[];
static unsigned vdso_size;
- static void __init patch_vdso(void *vdso, size_t len)
+ #ifdef CONFIG_X86_X32_ABI
+ extern char vdsox32_start[], vdsox32_end[];
+ extern struct page *vdsox32_pages[];
+ static unsigned vdsox32_size;
+
+ static void __init patch_vdsox32(void *vdso, size_t len)
+ {
+ Elf32_Ehdr *hdr = vdso;
+ Elf32_Shdr *sechdrs, *alt_sec = 0;
+ char *secstrings;
+ void *alt_data;
+ int i;
+
+ BUG_ON(len < sizeof(Elf32_Ehdr));
+ BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0);
+
+ sechdrs = (void *)hdr + hdr->e_shoff;
+ secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+ for (i = 1; i < hdr->e_shnum; i++) {
+ Elf32_Shdr *shdr = &sechdrs[i];
+ if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) {
+ alt_sec = shdr;
+ goto found;
+ }
+ }
+
+ /* If we get here, it's probably a bug. */
+ pr_warning("patch_vdsox32: .altinstructions not found\n");
+ return; /* nothing to patch */
+
+ found:
+ alt_data = (void *)hdr + alt_sec->sh_offset;
+ apply_alternatives(alt_data, alt_data + alt_sec->sh_size);
+ }
+ #endif
+
+ static void __init patch_vdso64(void *vdso, size_t len)
{
Elf64_Ehdr *hdr = vdso;
Elf64_Shdr *sechdrs, *alt_sec = 0;
}
/* If we get here, it's probably a bug. */
- pr_warning("patch_vdso: .altinstructions not found\n");
+ pr_warning("patch_vdso64: .altinstructions not found\n");
return; /* nothing to patch */
found:
int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
int i;
- patch_vdso(vdso_start, vdso_end - vdso_start);
+ patch_vdso64(vdso_start, vdso_end - vdso_start);
vdso_size = npages << PAGE_SHIFT;
for (i = 0; i < npages; i++)
vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE);
+ #ifdef CONFIG_X86_X32_ABI
+ patch_vdsox32(vdsox32_start, vdsox32_end - vdsox32_start);
+ npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE;
+ vdsox32_size = npages << PAGE_SHIFT;
+ for (i = 0; i < npages; i++)
+ vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE);
+ #endif
+
return 0;
}
subsys_initcall(init_vdso);
/* Setup a VMA at program startup for the vsyscall page.
Not called for compat tasks */
- int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+ static int setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp,
+ struct page **pages,
+ unsigned size)
{
struct mm_struct *mm = current->mm;
unsigned long addr;
return 0;
down_write(&mm->mmap_sem);
- addr = vdso_addr(mm->start_stack, vdso_size);
- addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
+ addr = vdso_addr(mm->start_stack, size);
+ addr = get_unmapped_area(NULL, addr, size, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
current->mm->context.vdso = (void *)addr;
- ret = install_special_mapping(mm, addr, vdso_size,
+ ret = install_special_mapping(mm, addr, size,
VM_READ|VM_EXEC|
- VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
- VM_ALWAYSDUMP,
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
- vdso_pages);
+ pages);
if (ret) {
current->mm->context.vdso = NULL;
goto up_fail;
return ret;
}
+ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+ {
+ return setup_additional_pages(bprm, uses_interp, vdso_pages,
+ vdso_size);
+ }
+
+ #ifdef CONFIG_X86_X32_ABI
+ int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+ {
+ return setup_additional_pages(bprm, uses_interp, vdsox32_pages,
+ vdsox32_size);
+ }
+ #endif
+
static __init int vdso_setup(char *s)
{
vdso_enabled = simple_strtoul(s, NULL, 0);
#include <asm/irq.h>
#include <asm/uaccess.h>
-#include <asm/system.h>
/* if you have more than 8 printers, remember to increase LP_NO */
#define LP_NO 8
{
unsigned int minor;
struct timeval par_timeout;
- struct compat_timeval __user *tc;
int ret;
minor = iminor(file->f_path.dentry->d_inode);
mutex_lock(&lp_mutex);
switch (cmd) {
case LPSETTIMEOUT:
- tc = compat_ptr(arg);
- if (get_user(par_timeout.tv_sec, &tc->tv_sec) ||
- get_user(par_timeout.tv_usec, &tc->tv_usec)) {
+ if (compat_get_timeval(&par_timeout, compat_ptr(arg))) {
ret = -EFAULT;
break;
}
static DEFINE_MUTEX(binder_lock);
static DEFINE_MUTEX(binder_deferred_lock);
+static DEFINE_MUTEX(binder_mmap_lock);
static HLIST_HEAD(binder_procs);
static HLIST_HEAD(binder_deferred_list);
BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION;
module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO);
-static int binder_debug_no_lock;
+static bool binder_debug_no_lock;
module_param_named(proc_no_lock, binder_debug_no_lock, bool, S_IWUSR | S_IRUGO);
static DECLARE_WAIT_QUEUE_HEAD(binder_user_error_wait);
};
struct binder_buffer {
- struct list_head entry; /* free and allocated entries by addesss */
+ struct list_head entry; /* free and allocated entries by address */
struct rb_node rb_node; /* free entry by size or allocated entry */
/* by address */
unsigned free:1;
struct rb_root refs_by_node;
int pid;
struct vm_area_struct *vma;
+ struct mm_struct *vma_vm_mm;
struct task_struct *tsk;
struct files_struct *files;
struct hlist_node deferred_work_node;
repeat:
fdt = files_fdtable(files);
- fd = find_next_zero_bit(fdt->open_fds->fds_bits, fdt->max_fds,
- files->next_fd);
+ fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, files->next_fd);
/*
* N.B. For clone tasks sharing a files structure, this test
goto repeat;
}
- FD_SET(fd, fdt->open_fds);
+ __set_open_fd(fd, fdt);
if (flags & O_CLOEXEC)
- FD_SET(fd, fdt->close_on_exec);
+ __set_close_on_exec(fd, fdt);
else
- FD_CLR(fd, fdt->close_on_exec);
+ __clear_close_on_exec(fd, fdt);
files->next_fd = fd + 1;
#if 1
/* Sanity check */
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
struct fdtable *fdt = files_fdtable(files);
- __FD_CLR(fd, fdt->open_fds);
+ __clear_open_fd(fd, fdt);
if (fd < files->next_fd)
files->next_fd = fd;
}
if (!filp)
goto out_unlock;
rcu_assign_pointer(fdt->fd[fd], NULL);
- FD_CLR(fd, fdt->close_on_exec);
+ __clear_close_on_exec(fd, fdt);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
retval = filp_close(filp, files);
if (mm) {
down_write(&mm->mmap_sem);
vma = proc->vma;
+ if (vma && mm != proc->vma_vm_mm) {
+ pr_err("binder: %d: vma mm and task mm mismatch\n",
+ proc->pid);
+ vma = NULL;
+ }
}
if (allocate == 0)
proc->pid, vma->vm_start, vma->vm_end,
(vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
(unsigned long)pgprot_val(vma->vm_page_prot));
- dump_stack();
}
static void binder_vma_close(struct vm_area_struct *vma)
(vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags,
(unsigned long)pgprot_val(vma->vm_page_prot));
proc->vma = NULL;
+ proc->vma_vm_mm = NULL;
binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES);
}
}
vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE;
+ mutex_lock(&binder_mmap_lock);
if (proc->buffer) {
ret = -EBUSY;
failure_string = "already mapped";
}
proc->buffer = area->addr;
proc->user_buffer_offset = vma->vm_start - (uintptr_t)proc->buffer;
+ mutex_unlock(&binder_mmap_lock);
#ifdef CONFIG_CPU_CACHE_VIPT
if (cache_is_vipt_aliasing()) {
binder_insert_free_buffer(proc, buffer);
proc->free_async_space = proc->buffer_size / 2;
barrier();
- proc->files = get_files_struct(current);
+ proc->files = get_files_struct(proc->tsk);
proc->vma = vma;
+ proc->vma_vm_mm = vma->vm_mm;
/*printk(KERN_INFO "binder_mmap: %d %lx-%lx maps %p\n",
proc->pid, vma->vm_start, vma->vm_end, proc->buffer);*/
kfree(proc->pages);
proc->pages = NULL;
err_alloc_pages_failed:
+ mutex_lock(&binder_mmap_lock);
vfree(proc->buffer);
proc->buffer = NULL;
err_get_vm_area_failed:
err_already_mapped:
+ mutex_unlock(&binder_mmap_lock);
err_bad_arg:
printk(KERN_ERR "binder_mmap: %d %lx-%lx %s failed %d\n",
proc->pid, vma->vm_start, vma->vm_end, failure_string, ret);
fdt = files_fdtable(files);
BUG_ON(fdt->fd[fd] != NULL);
rcu_assign_pointer(fdt->fd[fd], file);
- FD_SET(fd, fdt->close_on_exec);
+ __set_close_on_exec(fd, fdt);
spin_unlock(&files->file_lock);
}
sbi->pipefd = pipefd;
sbi->pipe = pipe;
sbi->catatonic = 0;
+ sbi->compat_daemon = is_compat_task();
}
out:
mutex_unlock(&sbi->wq_mutex);
#include <asm/uaccess.h>
#include <asm/param.h>
#include <asm/page.h>
+#include <asm/exec.h>
static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs);
static int load_elf_library(struct file *);
goto out_free_dentry;
/* OK, This is the point of no return */
- current->flags &= ~PF_FORKNOEXEC;
current->mm->def_flags = def_flags;
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
install_exec_creds(bprm);
- current->flags &= ~PF_FORKNOEXEC;
retval = create_elf_tables(bprm, &loc->elf_ex,
load_addr, interp_load_addr);
if (retval < 0) {
* Jeremy Fitzhardinge <jeremy@sw.oz.au>
*/
+/*
+ * The purpose of always_dump_vma() is to make sure that special kernel mappings
+ * that are useful for post-mortem analysis are included in every core dump.
+ * In that way we ensure that the core dump is fully interpretable later
+ * without matching up the same kernel and hardware config to see what PC values
+ * meant. These special mappings include - vDSO, vsyscall, and other
+ * architecture specific mappings
+ */
+static bool always_dump_vma(struct vm_area_struct *vma)
+{
+ /* Any vsyscall mappings? */
+ if (vma == get_gate_vma(vma->vm_mm))
+ return true;
+ /*
+ * arch_vma_name() returns non-NULL for special architecture mappings,
+ * such as vDSO sections.
+ */
+ if (arch_vma_name(vma))
+ return true;
+
+ return false;
+}
+
/*
* Decide what to dump of a segment, part, all or none.
*/
{
#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
- /* The vma can be set up to tell us the answer directly. */
- if (vma->vm_flags & VM_ALWAYSDUMP)
+ /* always dump the vdso and vsyscall sections */
+ if (always_dump_vma(vma))
goto whole;
+ if (vma->vm_flags & VM_NODUMP)
+ return 0;
+
/* Hugetlb memory check */
if (vma->vm_flags & VM_HUGETLB) {
if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
regset->writeback(task, regset, 1);
}
+ #ifndef PR_REG_SIZE
+ #define PR_REG_SIZE(S) sizeof(S)
+ #endif
+
+ #ifndef PRSTATUS_SIZE
+ #define PRSTATUS_SIZE(S) sizeof(S)
+ #endif
+
+ #ifndef PR_REG_PTR
+ #define PR_REG_PTR(S) (&((S)->pr_reg))
+ #endif
+
+ #ifndef SET_PR_FPVALID
+ #define SET_PR_FPVALID(S, V) ((S)->pr_fpvalid = (V))
+ #endif
+
static int fill_thread_core_info(struct elf_thread_core_info *t,
const struct user_regset_view *view,
long signr, size_t *total)
*/
fill_prstatus(&t->prstatus, t->task, signr);
(void) view->regsets[0].get(t->task, &view->regsets[0],
- 0, sizeof(t->prstatus.pr_reg),
- &t->prstatus.pr_reg, NULL);
+ 0, PR_REG_SIZE(t->prstatus.pr_reg),
+ PR_REG_PTR(&t->prstatus), NULL);
fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
- sizeof(t->prstatus), &t->prstatus);
+ PRSTATUS_SIZE(t->prstatus), &t->prstatus);
*total += notesize(&t->notes[0]);
do_thread_regset_writeback(t->task, &view->regsets[0]);
for (i = 1; i < view->n; ++i) {
const struct user_regset *regset = &view->regsets[i];
do_thread_regset_writeback(t->task, regset);
- if (regset->core_note_type &&
+ if (regset->core_note_type && regset->get &&
(!regset->active || regset->active(t->task, regset))) {
int ret;
size_t size = regset->n * regset->size;
regset->core_note_type,
size, data);
else {
- t->prstatus.pr_fpvalid = 1;
+ SET_PR_FPVALID(&t->prstatus, 1);
fill_note(&t->notes[i], "CORE",
NT_PRFPREG, size, data);
}
static int __init init_elf_binfmt(void)
{
- return register_binfmt(&elf_format);
+ register_binfmt(&elf_format);
+ return 0;
}
static void __exit exit_elf_binfmt(void)
#include <linux/nfs4_mount.h>
#include <linux/syscalls.h>
#include <linux/ctype.h>
-#include <linux/module.h>
#include <linux/dirent.h>
#include <linux/fsnotify.h>
#include <linux/highuid.h>
static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
{
- compat_ino_t ino = stat->ino;
- typeof(ubuf->st_uid) uid = 0;
- typeof(ubuf->st_gid) gid = 0;
- int err;
+ struct compat_stat tmp;
- SET_UID(uid, stat->uid);
- SET_GID(gid, stat->gid);
+ if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
+ return -EOVERFLOW;
- if ((u64) stat->size > MAX_NON_LFS ||
- !old_valid_dev(stat->dev) ||
- !old_valid_dev(stat->rdev))
+ memset(&tmp, 0, sizeof(tmp));
+ tmp.st_dev = old_encode_dev(stat->dev);
+ tmp.st_ino = stat->ino;
+ if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
return -EOVERFLOW;
- if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino)
+ tmp.st_mode = stat->mode;
+ tmp.st_nlink = stat->nlink;
+ if (tmp.st_nlink != stat->nlink)
return -EOVERFLOW;
-
- if (clear_user(ubuf, sizeof(*ubuf)))
- return -EFAULT;
-
- err = __put_user(old_encode_dev(stat->dev), &ubuf->st_dev);
- err |= __put_user(ino, &ubuf->st_ino);
- err |= __put_user(stat->mode, &ubuf->st_mode);
- err |= __put_user(stat->nlink, &ubuf->st_nlink);
- err |= __put_user(uid, &ubuf->st_uid);
- err |= __put_user(gid, &ubuf->st_gid);
- err |= __put_user(old_encode_dev(stat->rdev), &ubuf->st_rdev);
- err |= __put_user(stat->size, &ubuf->st_size);
- err |= __put_user(stat->atime.tv_sec, &ubuf->st_atime);
- err |= __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec);
- err |= __put_user(stat->mtime.tv_sec, &ubuf->st_mtime);
- err |= __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec);
- err |= __put_user(stat->ctime.tv_sec, &ubuf->st_ctime);
- err |= __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec);
- err |= __put_user(stat->blksize, &ubuf->st_blksize);
- err |= __put_user(stat->blocks, &ubuf->st_blocks);
- return err;
+ SET_UID(tmp.st_uid, stat->uid);
+ SET_GID(tmp.st_gid, stat->gid);
+ tmp.st_rdev = old_encode_dev(stat->rdev);
+ if ((u64) stat->size > MAX_NON_LFS)
+ return -EOVERFLOW;
+ tmp.st_size = stat->size;
+ tmp.st_atime = stat->atime.tv_sec;
+ tmp.st_atime_nsec = stat->atime.tv_nsec;
+ tmp.st_mtime = stat->mtime.tv_sec;
+ tmp.st_mtime_nsec = stat->mtime.tv_nsec;
+ tmp.st_ctime = stat->ctime.tv_sec;
+ tmp.st_ctime_nsec = stat->ctime.tv_nsec;
+ tmp.st_blocks = stat->blocks;
+ tmp.st_blksize = stat->blksize;
+ return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}
asmlinkage long compat_sys_newstat(const char __user * filename,
}
asmlinkage ssize_t
- compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
- unsigned long vlen, u32 pos_low, u32 pos_high)
+ compat_sys_preadv64(unsigned long fd, const struct compat_iovec __user *vec,
+ unsigned long vlen, loff_t pos)
{
- loff_t pos = ((loff_t)pos_high << 32) | pos_low;
struct file *file;
int fput_needed;
ssize_t ret;
return ret;
}
+ asmlinkage ssize_t
+ compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
+ unsigned long vlen, u32 pos_low, u32 pos_high)
+ {
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+ return compat_sys_preadv64(fd, vec, vlen, pos);
+ }
+
static size_t compat_writev(struct file *file,
const struct compat_iovec __user *vec,
unsigned long vlen, loff_t *pos)
}
asmlinkage ssize_t
- compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
- unsigned long vlen, u32 pos_low, u32 pos_high)
+ compat_sys_pwritev64(unsigned long fd, const struct compat_iovec __user *vec,
+ unsigned long vlen, loff_t pos)
{
- loff_t pos = ((loff_t)pos_high << 32) | pos_low;
struct file *file;
int fput_needed;
ssize_t ret;
return ret;
}
+ asmlinkage ssize_t
+ compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
+ unsigned long vlen, u32 pos_low, u32 pos_high)
+ {
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+ return compat_sys_pwritev64(fd, vec, vlen, pos);
+ }
+
asmlinkage long
compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32,
unsigned int nr_segs, unsigned int flags)
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlb.h>
+#include <asm/exec.h>
#include <trace/events/task.h>
#include "internal.h"
+#include <trace/events/sched.h>
+
int core_uses_pid;
char core_pattern[CORENAME_MAX_SIZE] = "core";
unsigned int core_pipe_limit;
static LIST_HEAD(formats);
static DEFINE_RWLOCK(binfmt_lock);
-int __register_binfmt(struct linux_binfmt * fmt, int insert)
+void __register_binfmt(struct linux_binfmt * fmt, int insert)
{
- if (!fmt)
- return -EINVAL;
+ BUG_ON(!fmt);
write_lock(&binfmt_lock);
insert ? list_add(&fmt->lh, &formats) :
list_add_tail(&fmt->lh, &formats);
write_unlock(&binfmt_lock);
- return 0;
}
EXPORT_SYMBOL(__register_binfmt);
/* Notify parent that we're no longer interested in the old VM */
tsk = current;
old_mm = current->mm;
- sync_mm_rss(tsk, old_mm);
+ sync_mm_rss(old_mm);
mm_release(tsk, old_mm);
if (old_mm) {
if (old_mm) {
up_read(&old_mm->mmap_sem);
BUG_ON(active_mm != old_mm);
+ setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm);
mm_update_next_owner(old_mm);
mmput(old_mm);
return 0;
sig->notify_count = 0;
no_thread_group:
- if (current->mm)
- setmax_mm_hiwater_rss(&sig->maxrss, current->mm);
+ /* we have changed execution domain */
+ tsk->exit_signal = SIGCHLD;
exit_itimers(sig);
flush_itimer_signals();
fdt = files_fdtable(files);
if (i >= fdt->max_fds)
break;
- set = fdt->close_on_exec->fds_bits[j];
+ set = fdt->close_on_exec[j];
if (!set)
continue;
- fdt->close_on_exec->fds_bits[j] = 0;
+ fdt->close_on_exec[j] = 0;
spin_unlock(&files->file_lock);
for ( ; set ; i++,set >>= 1) {
if (set & 1) {
bprm->mm = NULL; /* We're using it now */
set_fs(USER_DS);
- current->flags &= ~(PF_RANDOMIZE | PF_KTHREAD);
+ current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD);
flush_thread();
current->personality &= ~bprm->per_clear;
ret = -EFAULT;
goto out;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
for (; offset < PAGE_SIZE && kaddr[offset];
offset++, bprm->p++)
;
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
put_arg_page(page);
if (offset == PAGE_SIZE)
*/
bprm->recursion_depth = depth;
if (retval >= 0) {
- if (depth == 0)
- ptrace_event(PTRACE_EVENT_EXEC,
- old_pid);
+ if (depth == 0) {
+ trace_sched_process_exec(current, old_pid, bprm);
+ ptrace_event(PTRACE_EVENT_EXEC, old_pid);
+ }
put_binfmt(fmt);
allow_write_access(bprm->file);
if (bprm->file)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
- struct completion *vfork_done;
int core_waiters = -EBUSY;
init_completion(&core_state->startup);
core_waiters = zap_threads(tsk, mm, core_state, exit_code);
up_write(&mm->mmap_sem);
- if (unlikely(core_waiters < 0))
- goto fail;
-
- /*
- * Make sure nobody is waiting for us to release the VM,
- * otherwise we can deadlock when we wait on each other
- */
- vfork_done = tsk->vfork_done;
- if (vfork_done) {
- tsk->vfork_done = NULL;
- complete(vfork_done);
- }
-
- if (core_waiters)
+ if (core_waiters > 0)
wait_for_completion(&core_state->startup);
-fail:
+
return core_waiters;
}
fd_install(0, rp);
spin_lock(&cf->file_lock);
fdt = files_fdtable(cf);
- FD_SET(0, fdt->open_fds);
- FD_CLR(0, fdt->close_on_exec);
+ __set_open_fd(0, fdt);
+ __clear_close_on_exec(0, fdt);
spin_unlock(&cf->file_lock);
/* and disallow core files too */
* Manage the dynamic fd arrays in the process files_struct.
*/
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
*/
static DEFINE_PER_CPU(struct fdtable_defer, fdtable_defer_list);
- static void *alloc_fdmem(unsigned int size)
+ static void *alloc_fdmem(size_t size)
{
/*
* Very large allocations can stress page reclaim, so fall back to
static struct fdtable * alloc_fdtable(unsigned int nr)
{
struct fdtable *fdt;
- char *data;
+ void *data;
/*
* Figure out how many fds we actually want to support in this fdtable.
data = alloc_fdmem(nr * sizeof(struct file *));
if (!data)
goto out_fdt;
- fdt->fd = (struct file **)data;
- data = alloc_fdmem(max_t(unsigned int,
+ fdt->fd = data;
+
+ data = alloc_fdmem(max_t(size_t,
2 * nr / BITS_PER_BYTE, L1_CACHE_BYTES));
if (!data)
goto out_arr;
- fdt->open_fds = (fd_set *)data;
+ fdt->open_fds = data;
data += nr / BITS_PER_BYTE;
- fdt->close_on_exec = (fd_set *)data;
+ fdt->close_on_exec = data;
fdt->next = NULL;
return fdt;
int i;
/* Find the last open fd */
- for (i = size/(8*sizeof(long)); i > 0; ) {
- if (fdt->open_fds->fds_bits[--i])
+ for (i = size / BITS_PER_LONG; i > 0; ) {
+ if (fdt->open_fds[--i])
break;
}
- i = (i+1) * 8 * sizeof(long);
+ i = (i + 1) * BITS_PER_LONG;
return i;
}
newf->next_fd = 0;
new_fdt = &newf->fdtab;
new_fdt->max_fds = NR_OPEN_DEFAULT;
- new_fdt->close_on_exec = (fd_set *)&newf->close_on_exec_init;
- new_fdt->open_fds = (fd_set *)&newf->open_fds_init;
+ new_fdt->close_on_exec = newf->close_on_exec_init;
+ new_fdt->open_fds = newf->open_fds_init;
new_fdt->fd = &newf->fd_array[0];
new_fdt->next = NULL;
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
- memcpy(new_fdt->open_fds->fds_bits,
- old_fdt->open_fds->fds_bits, open_files/8);
- memcpy(new_fdt->close_on_exec->fds_bits,
- old_fdt->close_on_exec->fds_bits, open_files/8);
+ memcpy(new_fdt->open_fds, old_fdt->open_fds, open_files / 8);
+ memcpy(new_fdt->close_on_exec, old_fdt->close_on_exec, open_files / 8);
for (i = open_files; i != 0; i--) {
struct file *f = *old_fds++;
* is partway through open(). So make sure that this
* fd is available to the new process.
*/
- FD_CLR(open_files - i, new_fdt->open_fds);
+ __clear_open_fd(open_files - i, new_fdt);
}
rcu_assign_pointer(*new_fds++, f);
}
memset(new_fds, 0, size);
if (new_fdt->max_fds > open_files) {
- int left = (new_fdt->max_fds-open_files)/8;
- int start = open_files / (8 * sizeof(unsigned long));
+ int left = (new_fdt->max_fds - open_files) / 8;
+ int start = open_files / BITS_PER_LONG;
- memset(&new_fdt->open_fds->fds_bits[start], 0, left);
- memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
+ memset(&new_fdt->open_fds[start], 0, left);
+ memset(&new_fdt->close_on_exec[start], 0, left);
}
rcu_assign_pointer(newf->fdt, new_fdt);
.fdtab = {
.max_fds = NR_OPEN_DEFAULT,
.fd = &init_files.fd_array[0],
- .close_on_exec = (fd_set *)&init_files.close_on_exec_init,
- .open_fds = (fd_set *)&init_files.open_fds_init,
+ .close_on_exec = init_files.close_on_exec_init,
+ .open_fds = init_files.open_fds_init,
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock),
};
fd = files->next_fd;
if (fd < fdt->max_fds)
- fd = find_next_zero_bit(fdt->open_fds->fds_bits,
- fdt->max_fds, fd);
+ fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, fd);
error = expand_files(files, fd);
if (error < 0)
if (start <= files->next_fd)
files->next_fd = fd + 1;
- FD_SET(fd, fdt->open_fds);
+ __set_open_fd(fd, fdt);
if (flags & O_CLOEXEC)
- FD_SET(fd, fdt->close_on_exec);
+ __set_close_on_exec(fd, fdt);
else
- FD_CLR(fd, fdt->close_on_exec);
+ __clear_close_on_exec(fd, fdt);
error = fd;
#if 1
/* Sanity check */
if (!p)
return -ESRCH;
- err = nice;
- err = proc_sched_autogroup_set_nice(p, &err);
+ err = proc_sched_autogroup_set_nice(p, nice);
if (err)
count = err;
fdt = files_fdtable(files);
f_flags = file->f_flags & ~O_CLOEXEC;
- if (FD_ISSET(fd, fdt->close_on_exec))
+ if (close_on_exec(fd, fdt))
f_flags |= O_CLOEXEC;
if (path) {
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tgid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
- REG("maps", S_IRUGO, proc_maps_operations),
+ REG("maps", S_IRUGO, proc_pid_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+ REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations),
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
REG("mountstats", S_IRUSR, proc_mountstats_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
- REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("smaps", S_IRUGO, proc_pid_smaps_operations),
REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
INF("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
- REG("maps", S_IRUGO, proc_maps_operations),
+ REG("maps", S_IRUGO, proc_tid_maps_operations),
#ifdef CONFIG_NUMA
- REG("numa_maps", S_IRUGO, proc_numa_maps_operations),
+ REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations),
#endif
REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations),
LNK("cwd", proc_cwd_link),
REG("mountinfo", S_IRUGO, proc_mountinfo_operations),
#ifdef CONFIG_PROC_PAGE_MONITOR
REG("clear_refs", S_IWUSR, proc_clear_refs_operations),
- REG("smaps", S_IRUGO, proc_smaps_operations),
+ REG("smaps", S_IRUGO, proc_tid_smaps_operations),
REG("pagemap", S_IRUGO, proc_pagemap_operations),
#endif
#ifdef CONFIG_SECURITY
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
get_file(filp);
entry->filp = filp;
entry->wait_address = wait_address;
- entry->key = p->key;
+ entry->key = p->_key;
init_waitqueue_func_entry(&entry->wait, pollwake);
entry->wait.private = pwq;
add_wait_queue(wait_address, &entry->wait);
set = ~(~0UL << (n & (__NFDBITS-1)));
n /= __NFDBITS;
fdt = files_fdtable(current->files);
- open_fds = fdt->open_fds->fds_bits+n;
+ open_fds = fdt->open_fds + n;
max = 0;
if (set) {
set &= BITS(fds, n);
static inline void wait_key_set(poll_table *wait, unsigned long in,
unsigned long out, unsigned long bit)
{
- if (wait) {
- wait->key = POLLEX_SET;
- if (in & bit)
- wait->key |= POLLIN_SET;
- if (out & bit)
- wait->key |= POLLOUT_SET;
- }
+ wait->_key = POLLEX_SET;
+ if (in & bit)
+ wait->_key |= POLLIN_SET;
+ if (out & bit)
+ wait->_key |= POLLOUT_SET;
}
int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
poll_initwait(&table);
wait = &table.pt;
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
- wait = NULL;
+ wait->_qproc = NULL;
timed_out = 1;
}
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
retval++;
- wait = NULL;
+ wait->_qproc = NULL;
}
if ((mask & POLLOUT_SET) && (out & bit)) {
res_out |= bit;
retval++;
- wait = NULL;
+ wait->_qproc = NULL;
}
if ((mask & POLLEX_SET) && (ex & bit)) {
res_ex |= bit;
retval++;
- wait = NULL;
+ wait->_qproc = NULL;
}
}
}
*rexp = res_ex;
cond_resched();
}
- wait = NULL;
+ wait->_qproc = NULL;
if (retval || timed_out || signal_pending(current))
break;
if (table.error) {
* interested in events matching the pollfd->events mask, and the result
* matching that mask is both recorded in pollfd->revents and returned. The
* pwait poll_table will be used by the fd-provided poll handler for waiting,
- * if non-NULL.
+ * if pwait->_qproc is non-NULL.
*/
static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
{
if (file != NULL) {
mask = DEFAULT_POLLMASK;
if (file->f_op && file->f_op->poll) {
- if (pwait)
- pwait->key = pollfd->events |
- POLLERR | POLLHUP;
+ pwait->_key = pollfd->events|POLLERR|POLLHUP;
mask = file->f_op->poll(file, pwait);
}
/* Mask out unneeded events. */
/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
- pt = NULL;
+ pt->_qproc = NULL;
timed_out = 1;
}
for (; pfd != pfd_end; pfd++) {
/*
* Fish for events. If we found one, record it
- * and kill the poll_table, so we don't
+ * and kill poll_table->_qproc, so we don't
* needlessly register any other waiters after
* this. They'll get immediately deregistered
* when we break out and return.
*/
if (do_pollfd(pfd, pt)) {
count++;
- pt = NULL;
+ pt->_qproc = NULL;
}
}
}
/*
* All waiters have already been registered, so don't provide
- * a poll_table to them on the next loop iteration.
+ * a poll_table->_qproc to them on the next loop iteration.
*/
- pt = NULL;
+ pt->_qproc = NULL;
if (!count) {
count = wait->error;
if (signal_pending(current))
}
SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
- long, timeout_msecs)
+ int, timeout_msecs)
{
struct timespec end_time, *to = NULL;
int ret;
header-y += major.h
header-y += map_to_7segment.h
header-y += matroxfb.h
+header-y += mdio.h
header-y += media.h
header-y += mempolicy.h
header-y += meye.h
header-y += posix_types.h
header-y += ppdev.h
header-y += ppp-comp.h
+header-y += ppp-ioctl.h
header-y += ppp_defs.h
header-y += pps.h
header-y += prctl.h
header-y += swab.h
header-y += synclink.h
header-y += sysctl.h
+ header-y += sysinfo.h
header-y += taskstats.h
header-y += tcp.h
header-y += telephony.h
#include <asm/siginfo.h>
#include <asm/signal.h>
+ #ifndef COMPAT_USE_64BIT_TIME
+ #define COMPAT_USE_64BIT_TIME 0
+ #endif
+
#define compat_jiffies_to_clock_t(x) \
(((unsigned long)(x) * COMPAT_USER_HZ) / HZ)
compat_sigset_word sig[_COMPAT_NSIG_WORDS];
} compat_sigset_t;
+ /*
+ * These functions operate strictly on struct compat_time*
+ */
extern int get_compat_timespec(struct timespec *,
const struct compat_timespec __user *);
extern int put_compat_timespec(const struct timespec *,
struct compat_timespec __user *);
+ extern int get_compat_timeval(struct timeval *,
+ const struct compat_timeval __user *);
+ extern int put_compat_timeval(const struct timeval *,
+ struct compat_timeval __user *);
+ /*
+ * These functions operate on 32- or 64-bit specs depending on
+ * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments and the
+ * naming as compat_get/put_ rather than get/put_compat_.
+ */
+ extern int compat_get_timespec(struct timespec *, const void __user *);
+ extern int compat_put_timespec(const struct timespec *, void __user *);
+ extern int compat_get_timeval(struct timeval *, const void __user *);
+ extern int compat_put_timeval(const struct timeval *, void __user *);
struct compat_iovec {
compat_uptr_t iov_base;
struct compat_sysctl_args;
struct compat_kexec_segment;
struct compat_mq_attr;
+struct compat_msgbuf;
extern void compat_exit_robust_list(struct task_struct *curr);
compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
compat_size_t __user *len_ptr);
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
long compat_sys_semctl(int first, int second, int third, void __user *uptr);
long compat_sys_msgsnd(int first, int second, int third, void __user *uptr);
long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
int version, void __user *uptr);
-long compat_sys_msgctl(int first, int second, void __user *uptr);
long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
void __user *uptr);
+#else
+long compat_sys_semctl(int semid, int semnum, int cmd, int arg);
+long compat_sys_msgsnd(int msqid, struct compat_msgbuf __user *msgp,
+ size_t msgsz, int msgflg);
+long compat_sys_msgrcv(int msqid, struct compat_msgbuf __user *msgp,
+ size_t msgsz, long msgtyp, int msgflg);
+long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg);
+#endif
+long compat_sys_msgctl(int first, int second, void __user *uptr);
long compat_sys_shmctl(int first, int second, void __user *uptr);
long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
unsigned nsems, const struct compat_timespec __user *timeout);
unsigned long liovcnt, const struct compat_iovec __user *rvec,
unsigned long riovcnt, unsigned long flags);
+#else
+
+#define is_compat_task() (0)
+
#endif /* CONFIG_COMPAT */
#endif /* _LINUX_COMPAT_H */
#ifndef _LINUX_KERNEL_H
#define _LINUX_KERNEL_H
+ #include <linux/sysinfo.h>
+
/*
* 'kernel.h' contains some often-used function prototypes etc
*/
#include <linux/printk.h>
#include <linux/dynamic_debug.h>
#include <asm/byteorder.h>
-#include <asm/bug.h>
#define USHRT_MAX ((u16)(~0U))
#define SHRT_MAX ((s16)(USHRT_MAX>>1))
} \
)
+/*
+ * Multiplies an integer by a fraction, while avoiding unnecessary
+ * overflow or loss of precision.
+ */
+#define mult_frac(x, numer, denom)( \
+{ \
+ typeof(x) quot = (x) / (denom); \
+ typeof(x) rem = (x) % (denom); \
+ (quot * (numer)) + ((rem * (numer)) / (denom)); \
+} \
+)
+
+
#define _RET_IP_ (unsigned long)__builtin_return_address(0)
#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
#define strict_strtoull kstrtoull
#define strict_strtoll kstrtoll
+extern int num_to_str(char *buf, int size, unsigned long long num);
+
/* lib/printf utilities */
extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...);
char *kasprintf(gfp_t gfp, const char *fmt, ...);
extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
-extern int sscanf(const char *, const char *, ...)
- __attribute__ ((format (scanf, 2, 3)));
-extern int vsscanf(const char *, const char *, va_list)
- __attribute__ ((format (scanf, 2, 0)));
+extern __scanf(2, 3)
+int sscanf(const char *, const char *, ...);
+extern __scanf(2, 0)
+int vsscanf(const char *, const char *, va_list);
extern int get_option(char **str, int *pint);
extern char *get_options(const char *str, int nints, int *ints);
const typeof( ((type *)0)->member ) *__mptr = (ptr); \
(type *)( (char *)__mptr - offsetof(type,member) );})
-#ifdef __CHECKER__
-#define BUILD_BUG_ON_NOT_POWER_OF_2(n)
-#define BUILD_BUG_ON_ZERO(e) (0)
-#define BUILD_BUG_ON_NULL(e) ((void*)0)
-#define BUILD_BUG_ON(condition)
-#define BUILD_BUG() (0)
-#else /* __CHECKER__ */
-
-/* Force a compilation error if a constant expression is not a power of 2 */
-#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \
- BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0))
-
-/* Force a compilation error if condition is true, but also produce a
- result (of value 0 and type size_t), so the expression can be used
- e.g. in a structure initializer (or where-ever else comma expressions
- aren't permitted). */
-#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
-#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
-
-/**
- * BUILD_BUG_ON - break compile if a condition is true.
- * @condition: the condition which the compiler should know is false.
- *
- * If you have some code which relies on certain constants being equal, or
- * other compile-time-evaluated condition, you should use BUILD_BUG_ON to
- * detect if someone changes it.
- *
- * The implementation uses gcc's reluctance to create a negative array, but
- * gcc (as of 4.4) only emits that error for obvious cases (eg. not arguments
- * to inline functions). So as a fallback we use the optimizer; if it can't
- * prove the condition is false, it will cause a link error on the undefined
- * "__build_bug_on_failed". This error message can be harder to track down
- * though, hence the two different methods.
- */
-#ifndef __OPTIMIZE__
-#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
-#else
-extern int __build_bug_on_failed;
-#define BUILD_BUG_ON(condition) \
- do { \
- ((void)sizeof(char[1 - 2*!!(condition)])); \
- if (condition) __build_bug_on_failed = 1; \
- } while(0)
-#endif
-
-/**
- * BUILD_BUG - break compile if used.
- *
- * If you have some code that you expect the compiler to eliminate at
- * build time, you should use BUILD_BUG to detect if it is
- * unexpectedly used.
- */
-#define BUILD_BUG() \
- do { \
- extern void __build_bug_failed(void) \
- __linktime_error("BUILD_BUG failed"); \
- __build_bug_failed(); \
- } while (0)
-
-#endif /* __CHECKER__ */
-
/* Trap pasters of __FUNCTION__ at compile-time */
#define __FUNCTION__ (__func__)
# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
#endif
- struct sysinfo;
extern int do_sysinfo(struct sysinfo *info);
#endif /* __KERNEL__ */
- #define SI_LOAD_SHIFT 16
- struct sysinfo {
- long uptime; /* Seconds since boot */
- unsigned long loads[3]; /* 1, 5, and 15 minute load averages */
- unsigned long totalram; /* Total usable main memory size */
- unsigned long freeram; /* Available memory size */
- unsigned long sharedram; /* Amount of shared memory */
- unsigned long bufferram; /* Memory used by buffers */
- unsigned long totalswap; /* Total swap space size */
- unsigned long freeswap; /* swap space still available */
- unsigned short procs; /* Number of current processes */
- unsigned short pad; /* explicit padding for m68k */
- unsigned long totalhigh; /* Total high memory size */
- unsigned long freehigh; /* Available high memory size */
- unsigned int mem_unit; /* Memory unit size in bytes */
- char _f[20-2*sizeof(long)-sizeof(int)]; /* Padding: libc5 uses this.. */
- };
-
#endif
extern void read_persistent_clock(struct timespec *ts);
extern void read_boot_clock(struct timespec *ts);
extern int update_persistent_clock(struct timespec now);
-extern int no_sync_cmos_clock __read_mostly;
void timekeeping_init(void);
extern int timekeeping_suspended;
a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
a->tv_nsec = ns;
}
+
#endif /* __KERNEL__ */
#define NFDBITS __NFDBITS
#include <linux/hw_breakpoint.h>
#include <linux/oom.h>
#include <linux/writeback.h>
+#include <linux/shm.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
*/
exit_mm(current);
/*
- * We don't want to have TIF_FREEZE set if the system-wide hibernation
+ * We don't want to get frozen, in case system-wide hibernation
* or suspend transition begins right now.
*/
current->flags |= (PF_NOFREEZE | PF_KTHREAD);
i = j * __NFDBITS;
if (i >= fdt->max_fds)
break;
- set = fdt->open_fds->fds_bits[j++];
+ set = fdt->open_fds[j++];
while (set) {
if (set & 1) {
struct file * file = xchg(&fdt->fd[i], NULL);
}
/*
- * When we die, we re-parent all our children.
- * Try to give them to another thread in our thread
- * group, and if no such member exists, give it to
- * the child reaper process (ie "init") in our pid
- * space.
+ * When we die, we re-parent all our children, and try to:
+ * 1. give them to another thread in our thread group, if such a member exists
+ * 2. give it to the first ancestor process which prctl'd itself as a
+ * child_subreaper for its children (like a service manager)
+ * 3. give it to the init process (PID 1) in our pid namespace
*/
static struct task_struct *find_new_reaper(struct task_struct *father)
__releases(&tasklist_lock)
if (unlikely(pid_ns->child_reaper == father)) {
write_unlock_irq(&tasklist_lock);
- if (unlikely(pid_ns == &init_pid_ns))
- panic("Attempted to kill init!");
+ if (unlikely(pid_ns == &init_pid_ns)) {
+ panic("Attempted to kill init! exitcode=0x%08x\n",
+ father->signal->group_exit_code ?:
+ father->exit_code);
+ }
zap_pid_ns_processes(pid_ns);
write_lock_irq(&tasklist_lock);
* forget_original_parent() must move them somewhere.
*/
pid_ns->child_reaper = init_pid_ns.child_reaper;
+ } else if (father->signal->has_child_subreaper) {
+ struct task_struct *reaper;
+
+ /*
+ * Find the first ancestor marked as child_subreaper.
+ * Note that the code below checks same_thread_group(reaper,
+ * pid_ns->child_reaper). This is what we need to DTRT in a
+ * PID namespace. However we still need the check above, see
+ * http://marc.info/?l=linux-kernel&m=131385460420380
+ */
+ for (reaper = father->real_parent;
+ reaper != &init_task;
+ reaper = reaper->real_parent) {
+ if (same_thread_group(reaper, pid_ns->child_reaper))
+ break;
+ if (!reaper->signal->is_child_subreaper)
+ continue;
+ thread = reaper;
+ do {
+ if (!(thread->flags & PF_EXITING))
+ return reaper;
+ } while_each_thread(reaper, thread);
+ }
}
return pid_ns->child_reaper;
if (group_dead)
kill_orphaned_pgrp(tsk->group_leader, NULL);
- /* Let father know we died
- *
- * Thread signals are configurable, but you aren't going to use
- * that to send signals to arbitrary processes.
- * That stops right now.
- *
- * If the parent exec id doesn't match the exec id we saved
- * when we started then we know the parent has changed security
- * domain.
- *
- * If our self_exec id doesn't match our parent_exec_id then
- * we have changed execution domain as these two values started
- * the same after a fork.
- */
- if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
- (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
- tsk->self_exec_id != tsk->parent_exec_id))
- tsk->exit_signal = SIGCHLD;
-
if (unlikely(tsk->ptrace)) {
int sig = thread_group_leader(tsk) &&
thread_group_empty(tsk) &&
schedule();
}
- exit_irq_thread();
-
exit_signals(tsk); /* sets PF_EXITING */
/*
* tsk->flags are checked in the futex code to protect against
smp_mb();
raw_spin_unlock_wait(&tsk->pi_lock);
+ exit_irq_thread();
+
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
current->comm, task_pid_nr(current),
acct_update_integrals(tsk);
/* sync mm's RSS info before statistics gathering */
if (tsk->mm)
- sync_mm_rss(tsk, tsk->mm);
+ sync_mm_rss(tsk->mm);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
#include <linux/ioctl.h>
#include <net/sock.h>
-#include <asm/system.h>
#include <linux/uaccess.h>
#include <asm/unaligned.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci_mon.h>
-static bool enable_mgmt;
+static atomic_t monitor_promisc = ATOMIC_INIT(0);
/* ----- HCI socket interface ----- */
};
/* Send frame to RAW socket */
-void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb,
- struct sock *skip_sk)
+void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb)
{
struct sock *sk;
struct hlist_node *node;
+ struct sk_buff *skb_copy = NULL;
BT_DBG("hdev %p len %d", hdev, skb->len);
read_lock(&hci_sk_list.lock);
+
sk_for_each(sk, node, &hci_sk_list.head) {
struct hci_filter *flt;
struct sk_buff *nskb;
- if (sk == skip_sk)
- continue;
-
if (sk->sk_state != BT_BOUND || hci_pi(sk)->hdev != hdev)
continue;
if (skb->sk == sk)
continue;
- if (bt_cb(skb)->channel != hci_pi(sk)->channel)
+ if (hci_pi(sk)->channel != HCI_CHANNEL_RAW)
continue;
- if (bt_cb(skb)->channel == HCI_CHANNEL_CONTROL)
- goto clone;
-
/* Apply filter */
flt = &hci_pi(sk)->filter;
continue;
}
-clone:
+ if (!skb_copy) {
+ /* Create a private copy with headroom */
+ skb_copy = __pskb_copy(skb, 1, GFP_ATOMIC);
+ if (!skb_copy)
+ continue;
+
+ /* Put type byte before the data */
+ memcpy(skb_push(skb_copy, 1), &bt_cb(skb)->pkt_type, 1);
+ }
+
+ nskb = skb_clone(skb_copy, GFP_ATOMIC);
+ if (!nskb)
+ continue;
+
+ if (sock_queue_rcv_skb(sk, nskb))
+ kfree_skb(nskb);
+ }
+
+ read_unlock(&hci_sk_list.lock);
+
+ kfree_skb(skb_copy);
+}
+
+/* Send frame to control socket */
+void hci_send_to_control(struct sk_buff *skb, struct sock *skip_sk)
+{
+ struct sock *sk;
+ struct hlist_node *node;
+
+ BT_DBG("len %d", skb->len);
+
+ read_lock(&hci_sk_list.lock);
+
+ sk_for_each(sk, node, &hci_sk_list.head) {
+ struct sk_buff *nskb;
+
+ /* Skip the original socket */
+ if (sk == skip_sk)
+ continue;
+
+ if (sk->sk_state != BT_BOUND)
+ continue;
+
+ if (hci_pi(sk)->channel != HCI_CHANNEL_CONTROL)
+ continue;
+
nskb = skb_clone(skb, GFP_ATOMIC);
if (!nskb)
continue;
- /* Put type byte before the data */
- if (bt_cb(skb)->channel == HCI_CHANNEL_RAW)
- memcpy(skb_push(nskb, 1), &bt_cb(nskb)->pkt_type, 1);
+ if (sock_queue_rcv_skb(sk, nskb))
+ kfree_skb(nskb);
+ }
+
+ read_unlock(&hci_sk_list.lock);
+}
+
+/* Send frame to monitor socket */
+void hci_send_to_monitor(struct hci_dev *hdev, struct sk_buff *skb)
+{
+ struct sock *sk;
+ struct hlist_node *node;
+ struct sk_buff *skb_copy = NULL;
+ __le16 opcode;
+
+ if (!atomic_read(&monitor_promisc))
+ return;
+
+ BT_DBG("hdev %p len %d", hdev, skb->len);
+
+ switch (bt_cb(skb)->pkt_type) {
+ case HCI_COMMAND_PKT:
+ opcode = __constant_cpu_to_le16(HCI_MON_COMMAND_PKT);
+ break;
+ case HCI_EVENT_PKT:
+ opcode = __constant_cpu_to_le16(HCI_MON_EVENT_PKT);
+ break;
+ case HCI_ACLDATA_PKT:
+ if (bt_cb(skb)->incoming)
+ opcode = __constant_cpu_to_le16(HCI_MON_ACL_RX_PKT);
+ else
+ opcode = __constant_cpu_to_le16(HCI_MON_ACL_TX_PKT);
+ break;
+ case HCI_SCODATA_PKT:
+ if (bt_cb(skb)->incoming)
+ opcode = __constant_cpu_to_le16(HCI_MON_SCO_RX_PKT);
+ else
+ opcode = __constant_cpu_to_le16(HCI_MON_SCO_TX_PKT);
+ break;
+ default:
+ return;
+ }
+
+ read_lock(&hci_sk_list.lock);
+
+ sk_for_each(sk, node, &hci_sk_list.head) {
+ struct sk_buff *nskb;
+
+ if (sk->sk_state != BT_BOUND)
+ continue;
+
+ if (hci_pi(sk)->channel != HCI_CHANNEL_MONITOR)
+ continue;
+
+ if (!skb_copy) {
+ struct hci_mon_hdr *hdr;
+
+ /* Create a private copy with headroom */
+ skb_copy = __pskb_copy(skb, HCI_MON_HDR_SIZE, GFP_ATOMIC);
+ if (!skb_copy)
+ continue;
+
+ /* Put header before the data */
+ hdr = (void *) skb_push(skb_copy, HCI_MON_HDR_SIZE);
+ hdr->opcode = opcode;
+ hdr->index = cpu_to_le16(hdev->id);
+ hdr->len = cpu_to_le16(skb->len);
+ }
+
+ nskb = skb_clone(skb_copy, GFP_ATOMIC);
+ if (!nskb)
+ continue;
+
+ if (sock_queue_rcv_skb(sk, nskb))
+ kfree_skb(nskb);
+ }
+
+ read_unlock(&hci_sk_list.lock);
+
+ kfree_skb(skb_copy);
+}
+
+static void send_monitor_event(struct sk_buff *skb)
+{
+ struct sock *sk;
+ struct hlist_node *node;
+
+ BT_DBG("len %d", skb->len);
+
+ read_lock(&hci_sk_list.lock);
+
+ sk_for_each(sk, node, &hci_sk_list.head) {
+ struct sk_buff *nskb;
+
+ if (sk->sk_state != BT_BOUND)
+ continue;
+
+ if (hci_pi(sk)->channel != HCI_CHANNEL_MONITOR)
+ continue;
+
+ nskb = skb_clone(skb, GFP_ATOMIC);
+ if (!nskb)
+ continue;
if (sock_queue_rcv_skb(sk, nskb))
kfree_skb(nskb);
}
+
read_unlock(&hci_sk_list.lock);
}
+static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
+{
+ struct hci_mon_hdr *hdr;
+ struct hci_mon_new_index *ni;
+ struct sk_buff *skb;
+ __le16 opcode;
+
+ switch (event) {
+ case HCI_DEV_REG:
+ skb = bt_skb_alloc(HCI_MON_NEW_INDEX_SIZE, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ ni = (void *) skb_put(skb, HCI_MON_NEW_INDEX_SIZE);
+ ni->type = hdev->dev_type;
+ ni->bus = hdev->bus;
+ bacpy(&ni->bdaddr, &hdev->bdaddr);
+ memcpy(ni->name, hdev->name, 8);
+
+ opcode = __constant_cpu_to_le16(HCI_MON_NEW_INDEX);
+ break;
+
+ case HCI_DEV_UNREG:
+ skb = bt_skb_alloc(0, GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ opcode = __constant_cpu_to_le16(HCI_MON_DEL_INDEX);
+ break;
+
+ default:
+ return NULL;
+ }
+
+ __net_timestamp(skb);
+
+ hdr = (void *) skb_push(skb, HCI_MON_HDR_SIZE);
+ hdr->opcode = opcode;
+ hdr->index = cpu_to_le16(hdev->id);
+ hdr->len = cpu_to_le16(skb->len - HCI_MON_HDR_SIZE);
+
+ return skb;
+}
+
+static void send_monitor_replay(struct sock *sk)
+{
+ struct hci_dev *hdev;
+
+ read_lock(&hci_dev_list_lock);
+
+ list_for_each_entry(hdev, &hci_dev_list, list) {
+ struct sk_buff *skb;
+
+ skb = create_monitor_event(hdev, HCI_DEV_REG);
+ if (!skb)
+ continue;
+
+ if (sock_queue_rcv_skb(sk, skb))
+ kfree_skb(skb);
+ }
+
+ read_unlock(&hci_dev_list_lock);
+}
+
+/* Generate internal stack event */
+static void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data)
+{
+ struct hci_event_hdr *hdr;
+ struct hci_ev_stack_internal *ev;
+ struct sk_buff *skb;
+
+ skb = bt_skb_alloc(HCI_EVENT_HDR_SIZE + sizeof(*ev) + dlen, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ hdr = (void *) skb_put(skb, HCI_EVENT_HDR_SIZE);
+ hdr->evt = HCI_EV_STACK_INTERNAL;
+ hdr->plen = sizeof(*ev) + dlen;
+
+ ev = (void *) skb_put(skb, sizeof(*ev) + dlen);
+ ev->type = type;
+ memcpy(ev->data, data, dlen);
+
+ bt_cb(skb)->incoming = 1;
+ __net_timestamp(skb);
+
+ bt_cb(skb)->pkt_type = HCI_EVENT_PKT;
+ skb->dev = (void *) hdev;
+ hci_send_to_sock(hdev, skb);
+ kfree_skb(skb);
+}
+
+void hci_sock_dev_event(struct hci_dev *hdev, int event)
+{
+ struct hci_ev_si_device ev;
+
+ BT_DBG("hdev %s event %d", hdev->name, event);
+
+ /* Send event to monitor */
+ if (atomic_read(&monitor_promisc)) {
+ struct sk_buff *skb;
+
+ skb = create_monitor_event(hdev, event);
+ if (skb) {
+ send_monitor_event(skb);
+ kfree_skb(skb);
+ }
+ }
+
+ /* Send event to sockets */
+ ev.event = event;
+ ev.dev_id = hdev->id;
+ hci_si_event(NULL, HCI_EV_SI_DEVICE, sizeof(ev), &ev);
+
+ if (event == HCI_DEV_UNREG) {
+ struct sock *sk;
+ struct hlist_node *node;
+
+ /* Detach sockets from device */
+ read_lock(&hci_sk_list.lock);
+ sk_for_each(sk, node, &hci_sk_list.head) {
+ bh_lock_sock_nested(sk);
+ if (hci_pi(sk)->hdev == hdev) {
+ hci_pi(sk)->hdev = NULL;
+ sk->sk_err = EPIPE;
+ sk->sk_state = BT_OPEN;
+ sk->sk_state_change(sk);
+
+ hci_dev_put(hdev);
+ }
+ bh_unlock_sock(sk);
+ }
+ read_unlock(&hci_sk_list.lock);
+ }
+}
+
static int hci_sock_release(struct socket *sock)
{
struct sock *sk = sock->sk;
hdev = hci_pi(sk)->hdev;
+ if (hci_pi(sk)->channel == HCI_CHANNEL_MONITOR)
+ atomic_dec(&monitor_promisc);
+
bt_sock_unlink(&hci_sk_list, sk);
if (hdev) {
hci_dev_lock(hdev);
- err = hci_blacklist_add(hdev, &bdaddr);
+ err = hci_blacklist_add(hdev, &bdaddr, 0);
hci_dev_unlock(hdev);
hci_dev_lock(hdev);
- err = hci_blacklist_del(hdev, &bdaddr);
+ err = hci_blacklist_del(hdev, &bdaddr, 0);
hci_dev_unlock(hdev);
if (haddr.hci_family != AF_BLUETOOTH)
return -EINVAL;
- if (haddr.hci_channel > HCI_CHANNEL_CONTROL)
- return -EINVAL;
-
- if (haddr.hci_channel == HCI_CHANNEL_CONTROL) {
- if (!enable_mgmt)
- return -EINVAL;
- set_bit(HCI_PI_MGMT_INIT, &hci_pi(sk)->flags);
- }
-
lock_sock(sk);
- if (sk->sk_state == BT_BOUND || hci_pi(sk)->hdev) {
+ if (sk->sk_state == BT_BOUND) {
err = -EALREADY;
goto done;
}
- if (haddr.hci_dev != HCI_DEV_NONE) {
- hdev = hci_dev_get(haddr.hci_dev);
- if (!hdev) {
- err = -ENODEV;
+ switch (haddr.hci_channel) {
+ case HCI_CHANNEL_RAW:
+ if (hci_pi(sk)->hdev) {
+ err = -EALREADY;
goto done;
}
- atomic_inc(&hdev->promisc);
+ if (haddr.hci_dev != HCI_DEV_NONE) {
+ hdev = hci_dev_get(haddr.hci_dev);
+ if (!hdev) {
+ err = -ENODEV;
+ goto done;
+ }
+
+ atomic_inc(&hdev->promisc);
+ }
+
+ hci_pi(sk)->hdev = hdev;
+ break;
+
+ case HCI_CHANNEL_CONTROL:
+ if (haddr.hci_dev != HCI_DEV_NONE) {
+ err = -EINVAL;
+ goto done;
+ }
+
+ if (!capable(CAP_NET_ADMIN)) {
+ err = -EPERM;
+ goto done;
+ }
+
+ break;
+
+ case HCI_CHANNEL_MONITOR:
+ if (haddr.hci_dev != HCI_DEV_NONE) {
+ err = -EINVAL;
+ goto done;
+ }
+
+ if (!capable(CAP_NET_RAW)) {
+ err = -EPERM;
+ goto done;
+ }
+
+ send_monitor_replay(sk);
+
+ atomic_inc(&monitor_promisc);
+ break;
+
+ default:
+ err = -EINVAL;
+ goto done;
}
+
hci_pi(sk)->channel = haddr.hci_channel;
- hci_pi(sk)->hdev = hdev;
sk->sk_state = BT_BOUND;
done:
data = &tv;
len = sizeof(tv);
#ifdef CONFIG_COMPAT
- if (msg->msg_flags & MSG_CMSG_COMPAT) {
+ if (!COMPAT_USE_64BIT_TIME &&
+ (msg->msg_flags & MSG_CMSG_COMPAT)) {
ctv.tv_sec = tv.tv_sec;
ctv.tv_usec = tv.tv_usec;
data = &ctv;
skb_reset_transport_header(skb);
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
- hci_sock_cmsg(sk, msg, skb);
+ switch (hci_pi(sk)->channel) {
+ case HCI_CHANNEL_RAW:
+ hci_sock_cmsg(sk, msg, skb);
+ break;
+ case HCI_CHANNEL_CONTROL:
+ case HCI_CHANNEL_MONITOR:
+ sock_recv_timestamp(msg, sk, skb);
+ break;
+ }
skb_free_datagram(sk, skb);
case HCI_CHANNEL_CONTROL:
err = mgmt_control(sk, msg, len);
goto done;
+ case HCI_CHANNEL_MONITOR:
+ err = -EOPNOTSUPP;
+ goto done;
default:
err = -EINVAL;
goto done;
lock_sock(sk);
+ if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) {
+ err = -EINVAL;
+ goto done;
+ }
+
switch (optname) {
case HCI_DATA_DIR:
if (get_user(opt, (int __user *)optval)) {
break;
}
+done:
release_sock(sk);
return err;
}
{
struct hci_ufilter uf;
struct sock *sk = sock->sk;
- int len, opt;
+ int len, opt, err = 0;
+
+ BT_DBG("sk %p, opt %d", sk, optname);
if (get_user(len, optlen))
return -EFAULT;
+ lock_sock(sk);
+
+ if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) {
+ err = -EINVAL;
+ goto done;
+ }
+
switch (optname) {
case HCI_DATA_DIR:
if (hci_pi(sk)->cmsg_mask & HCI_CMSG_DIR)
opt = 0;
if (put_user(opt, optval))
- return -EFAULT;
+ err = -EFAULT;
break;
case HCI_TIME_STAMP:
opt = 0;
if (put_user(opt, optval))
- return -EFAULT;
+ err = -EFAULT;
break;
case HCI_FILTER:
len = min_t(unsigned int, len, sizeof(uf));
if (copy_to_user(optval, &uf, len))
- return -EFAULT;
+ err = -EFAULT;
break;
default:
- return -ENOPROTOOPT;
+ err = -ENOPROTOOPT;
break;
}
- return 0;
+done:
+ release_sock(sk);
+ return err;
}
static const struct proto_ops hci_sock_ops = {
return 0;
}
-static int hci_sock_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
-{
- struct hci_dev *hdev = (struct hci_dev *) ptr;
- struct hci_ev_si_device ev;
-
- BT_DBG("hdev %s event %ld", hdev->name, event);
-
- /* Send event to sockets */
- ev.event = event;
- ev.dev_id = hdev->id;
- hci_si_event(NULL, HCI_EV_SI_DEVICE, sizeof(ev), &ev);
-
- if (event == HCI_DEV_UNREG) {
- struct sock *sk;
- struct hlist_node *node;
-
- /* Detach sockets from device */
- read_lock(&hci_sk_list.lock);
- sk_for_each(sk, node, &hci_sk_list.head) {
- bh_lock_sock_nested(sk);
- if (hci_pi(sk)->hdev == hdev) {
- hci_pi(sk)->hdev = NULL;
- sk->sk_err = EPIPE;
- sk->sk_state = BT_OPEN;
- sk->sk_state_change(sk);
-
- hci_dev_put(hdev);
- }
- bh_unlock_sock(sk);
- }
- read_unlock(&hci_sk_list.lock);
- }
-
- return NOTIFY_DONE;
-}
-
static const struct net_proto_family hci_sock_family_ops = {
.family = PF_BLUETOOTH,
.owner = THIS_MODULE,
.create = hci_sock_create,
};
-static struct notifier_block hci_sock_nblock = {
- .notifier_call = hci_sock_dev_event
-};
-
int __init hci_sock_init(void)
{
int err;
if (err < 0)
goto error;
- hci_register_notifier(&hci_sock_nblock);
-
BT_INFO("HCI socket layer initialized");
return 0;
if (bt_sock_unregister(BTPROTO_HCI) < 0)
BT_ERR("HCI socket unregistration failed");
- hci_unregister_notifier(&hci_sock_nblock);
-
proto_unregister(&hci_sk_proto);
}
-
-module_param(enable_mgmt, bool, 0644);
-MODULE_PARM_DESC(enable_mgmt, "Enable Management interface");
/* I've named the args so it is easy to tell whose space the pointers are in. */
int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov,
- struct sockaddr *kern_address, int mode)
+ struct sockaddr_storage *kern_address, int mode)
{
int tot_len;
int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data)
{
- struct compat_timeval ctv;
- struct compat_timespec cts[3];
struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control;
struct compat_cmsghdr cmhdr;
int cmlen;
return 0; /* XXX: return error? check spec. */
}
- if (level == SOL_SOCKET && type == SCM_TIMESTAMP) {
- struct timeval *tv = (struct timeval *)data;
- ctv.tv_sec = tv->tv_sec;
- ctv.tv_usec = tv->tv_usec;
- data = &ctv;
- len = sizeof(ctv);
- }
- if (level == SOL_SOCKET &&
- (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
- int count = type == SCM_TIMESTAMPNS ? 1 : 3;
- int i;
- struct timespec *ts = (struct timespec *)data;
- for (i = 0; i < count; i++) {
- cts[i].tv_sec = ts[i].tv_sec;
- cts[i].tv_nsec = ts[i].tv_nsec;
+ if (!COMPAT_USE_64BIT_TIME) {
+ struct compat_timeval ctv;
+ struct compat_timespec cts[3];
+ if (level == SOL_SOCKET && type == SCM_TIMESTAMP) {
+ struct timeval *tv = (struct timeval *)data;
+ ctv.tv_sec = tv->tv_sec;
+ ctv.tv_usec = tv->tv_usec;
+ data = &ctv;
+ len = sizeof(ctv);
+ }
+ if (level == SOL_SOCKET &&
+ (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) {
+ int count = type == SCM_TIMESTAMPNS ? 1 : 3;
+ int i;
+ struct timespec *ts = (struct timespec *)data;
+ for (i = 0; i < count; i++) {
+ cts[i].tv_sec = ts[i].tv_sec;
+ cts[i].tv_nsec = ts[i].tv_nsec;
+ }
+ data = &cts;
+ len = sizeof(cts[0]) * count;
}
- data = &cts;
- len = sizeof(cts[0]) * count;
}
cmlen = CMSG_COMPAT_LEN(len);
int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{
- struct compat_timeval __user *ctv =
- (struct compat_timeval __user *) userstamp;
- int err = -ENOENT;
+ struct compat_timeval __user *ctv;
+ int err;
struct timeval tv;
+ if (COMPAT_USE_64BIT_TIME)
+ return sock_get_timestamp(sk, userstamp);
+
+ ctv = (struct compat_timeval __user *) userstamp;
+ err = -ENOENT;
if (!sock_flag(sk, SOCK_TIMESTAMP))
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
tv = ktime_to_timeval(sk->sk_stamp);
int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
{
- struct compat_timespec __user *ctv =
- (struct compat_timespec __user *) userstamp;
- int err = -ENOENT;
+ struct compat_timespec __user *ctv;
+ int err;
struct timespec ts;
+ if (COMPAT_USE_64BIT_TIME)
+ return sock_get_timestampns (sk, userstamp);
+
+ ctv = (struct compat_timespec __user *) userstamp;
+ err = -ENOENT;
if (!sock_flag(sk, SOCK_TIMESTAMP))
sock_enable_timestamp(sk, SOCK_TIMESTAMP);
ts = ktime_to_timespec(sk->sk_stamp);
int datagrams;
struct timespec ktspec;
+ if (COMPAT_USE_64BIT_TIME)
+ return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
+ flags | MSG_CMSG_COMPAT,
+ (struct timespec *) timeout);
+
if (timeout == NULL)
return __sys_recvmmsg(fd, (struct mmsghdr __user *)mmsg, vlen,
flags | MSG_CMSG_COMPAT, NULL);
* invalid addresses -EFAULT is returned. On a success 0 is returned.
*/
-int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr)
+int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr)
{
if (ulen < 0 || ulen > sizeof(struct sockaddr_storage))
return -EINVAL;
* specified. Zero is returned for a success.
*/
-static int move_addr_to_user(struct sockaddr *kaddr, int klen,
+static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen,
void __user *uaddr, int __user *ulen)
{
int err;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock) {
- err = move_addr_to_kernel(umyaddr, addrlen, (struct sockaddr *)&address);
+ err = move_addr_to_kernel(umyaddr, addrlen, &address);
if (err >= 0) {
err = security_socket_bind(sock,
(struct sockaddr *)&address,
err = -ECONNABORTED;
goto out_fd;
}
- err = move_addr_to_user((struct sockaddr *)&address,
+ err = move_addr_to_user(&address,
len, upeer_sockaddr, upeer_addrlen);
if (err < 0)
goto out_fd;
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (!sock)
goto out;
- err = move_addr_to_kernel(uservaddr, addrlen, (struct sockaddr *)&address);
+ err = move_addr_to_kernel(uservaddr, addrlen, &address);
if (err < 0)
goto out_put;
err = sock->ops->getname(sock, (struct sockaddr *)&address, &len, 0);
if (err)
goto out_put;
- err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr, usockaddr_len);
+ err = move_addr_to_user(&address, len, usockaddr, usockaddr_len);
out_put:
fput_light(sock->file, fput_needed);
sock->ops->getname(sock, (struct sockaddr *)&address, &len,
1);
if (!err)
- err = move_addr_to_user((struct sockaddr *)&address, len, usockaddr,
+ err = move_addr_to_user(&address, len, usockaddr,
usockaddr_len);
fput_light(sock->file, fput_needed);
}
msg.msg_controllen = 0;
msg.msg_namelen = 0;
if (addr) {
- err = move_addr_to_kernel(addr, addr_len, (struct sockaddr *)&address);
+ err = move_addr_to_kernel(addr, addr_len, &address);
if (err < 0)
goto out_put;
msg.msg_name = (struct sockaddr *)&address;
err = sock_recvmsg(sock, &msg, size, flags);
if (err >= 0 && addr != NULL) {
- err2 = move_addr_to_user((struct sockaddr *)&address,
+ err2 = move_addr_to_user(&address,
msg.msg_namelen, addr, addr_len);
if (err2 < 0)
err = err2;
/* This will also move the address data into kernel space */
if (MSG_CMSG_COMPAT & flags) {
- err = verify_compat_iovec(msg_sys, iov,
- (struct sockaddr *)&address,
- VERIFY_READ);
+ err = verify_compat_iovec(msg_sys, iov, &address, VERIFY_READ);
} else
- err = verify_iovec(msg_sys, iov,
- (struct sockaddr *)&address,
- VERIFY_READ);
+ err = verify_iovec(msg_sys, iov, &address, VERIFY_READ);
if (err < 0)
goto out_freeiov;
total_len = err;
uaddr = (__force void __user *)msg_sys->msg_name;
uaddr_len = COMPAT_NAMELEN(msg);
if (MSG_CMSG_COMPAT & flags) {
- err = verify_compat_iovec(msg_sys, iov,
- (struct sockaddr *)&addr,
- VERIFY_WRITE);
+ err = verify_compat_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
} else
- err = verify_iovec(msg_sys, iov,
- (struct sockaddr *)&addr,
- VERIFY_WRITE);
+ err = verify_iovec(msg_sys, iov, &addr, VERIFY_WRITE);
if (err < 0)
goto out_freeiov;
total_len = err;
len = err;
if (uaddr != NULL) {
- err = move_addr_to_user((struct sockaddr *)&addr,
+ err = move_addr_to_user(&addr,
msg_sys->msg_namelen, uaddr,
uaddr_len);
if (err < 0)
#ifdef CONFIG_COMPAT
static int do_siocgstamp(struct net *net, struct socket *sock,
- unsigned int cmd, struct compat_timeval __user *up)
+ unsigned int cmd, void __user *up)
{
mm_segment_t old_fs = get_fs();
struct timeval ktv;
set_fs(KERNEL_DS);
err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv);
set_fs(old_fs);
- if (!err) {
- err = put_user(ktv.tv_sec, &up->tv_sec);
- err |= __put_user(ktv.tv_usec, &up->tv_usec);
- }
+ if (!err)
+ err = compat_put_timeval(up, &ktv);
+
return err;
}
static int do_siocgstampns(struct net *net, struct socket *sock,
- unsigned int cmd, struct compat_timespec __user *up)
+ unsigned int cmd, void __user *up)
{
mm_segment_t old_fs = get_fs();
struct timespec kts;
set_fs(KERNEL_DS);
err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts);
set_fs(old_fs);
- if (!err) {
- err = put_user(kts.tv_sec, &up->tv_sec);
- err |= __put_user(kts.tv_nsec, &up->tv_nsec);
- }
+ if (!err)
+ err = compat_put_timespec(up, &kts);
+
return err;
}
#include <linux/syslog.h>
#include <linux/user_namespace.h>
#include <linux/export.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
#include "avc.h"
#include "objsec.h"
fdt = files_fdtable(files);
if (i >= fdt->max_fds)
break;
- set = fdt->open_fds->fds_bits[j];
+ set = fdt->open_fds[j];
if (!set)
continue;
spin_unlock(&files->file_lock);