smart2= [HW]
Format: <io1>[,<io2>[,...,<io8>]]
- smp-alt-once [X86-32,SMP] On a hotplug CPU system, only
- attempt to substitute SMP alternatives once at boot.
-
smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices
smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port
smsc-ircc2.ircc_sir= [HW] SIR base I/O port
W: http://www.native-instruments.com
F: sound/usb/caiaq/
+NATIVE LINUX KVM TOOL
+M: Pekka Enberg <penberg@kernel.org>
+M: Sasha Levin <levinsasha928@gmail.com>
+M: Asias He <asias.hejun@gmail.com>
+L: kvm@vger.kernel.org
+S: Maintained
+F: tools/kvm/
+
NCP FILESYSTEM
M: Petr Vandrovec <petr@vandrovec.name>
S: Odd Fixes
endif
ifdef CONFIG_FUNCTION_TRACER
-KBUILD_CFLAGS += -pg
+ifdef CONFIG_HAVE_FENTRY
+CC_USING_FENTRY := $(call cc-option, -mfentry -DCC_USING_FENTRY)
+endif
+KBUILD_CFLAGS += -pg $(CC_USING_FENTRY)
+KBUILD_AFLAGS += $(CC_USING_FENTRY)
ifdef CONFIG_DYNAMIC_FTRACE
ifdef CONFIG_HAVE_C_RECORDMCOUNT
BUILD_C_RECORDMCOUNT := y
subsystem. Also has support for calculating CPU cycle events
to determine how many clock cycles in a given period.
+config HAVE_PERF_REGS
+ bool
+ help
+ Support selective register dumps for perf events. This includes
+ bit-mapping of each registers and a unique architecture id.
+
+config HAVE_PERF_USER_STACK_DUMP
+ bool
+ help
+ Support user stack dumps for perf event samples. This needs
+ access to the user stack pointer which is not unified across
+ architectures.
+
config HAVE_ARCH_JUMP_LABEL
bool
Modules only use ELF REL relocations. Modules with ELF RELA
relocations will give an error.
+config HAVE_VIRT_CPU_ACCOUNTING
+ bool
+
source "kernel/gcov/Kconfig"
select HAVE_GENERIC_HARDIRQS
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
+ select HAVE_VIRT_CPU_ACCOUNTING
select ARCH_DISCARD_MEMBLOCK
select GENERIC_IRQ_PROBE
select GENERIC_PENDING_IRQ if SMP
default "17" if HUGETLB_PAGE
default "11"
-config VIRT_CPU_ACCOUNTING
- bool "Deterministic task and CPU time accounting"
- default n
- help
- Select this option to enable more accurate task and CPU time
- accounting. This is done by reading a CPU counter on each
- kernel entry and exit and on transitions within the kernel
- between system, softirq and hardirq state, so there is a
- small performance impact.
- If in doubt, say N here.
-
config SMP
bool "Symmetric multi-processing support"
select USE_GENERIC_SMP_HELPERS
extern void ia64_save_extra (struct task_struct *task);
extern void ia64_load_extra (struct task_struct *task);
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next);
-# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n)
-#else
-# define IA64_ACCOUNT_ON_SWITCH(p,n)
-#endif
-
#ifdef CONFIG_PERFMON
DECLARE_PER_CPU(unsigned long, pfm_syst_info);
# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
|| PERFMON_IS_SYSWIDE())
#define __switch_to(prev,next,last) do { \
- IA64_ACCOUNT_ON_SWITCH(prev, next); \
if (IA64_HAS_EXTRA_STATE(prev)) \
ia64_save_extra(prev); \
if (IA64_HAS_EXTRA_STATE(next)) \
* accumulated times to the current process, and to prepare accounting on
* the next process.
*/
-void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
+void account_switch_vtime(struct task_struct *prev)
{
struct thread_info *pi = task_thread_info(prev);
- struct thread_info *ni = task_thread_info(next);
+ struct thread_info *ni = task_thread_info(current);
cputime_t delta_stime, delta_utime;
__u64 now;
DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING)
-#define account_process_vtime(tsk) account_process_tick(tsk, 0)
-#else
-#define account_process_vtime(tsk) do { } while (0)
-#endif
-
extern void secondary_cpu_time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
local_irq_save(flags);
- account_system_vtime(current);
- account_process_vtime(current);
-
/*
* We can't take a PMU exception inside _switch() since there is a
* window where the kernel stack SLB and the kernel stack are out
account_user_time(tsk, utime, utimescaled);
}
+void account_switch_vtime(struct task_struct *prev)
+{
+ account_system_vtime(prev);
+ account_process_tick(prev, 0);
+}
+
#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
#define calc_cputime_factors()
#endif
config PPC64
bool "64-bit kernel"
default n
+ select HAVE_VIRT_CPU_ACCOUNTING
help
This option selects whether a 32-bit or a 64-bit kernel
will be built.
default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
default n
-config VIRT_CPU_ACCOUNTING
- bool "Deterministic task and CPU time accounting"
- depends on PPC64
- default y
- help
- Select this option to enable more accurate task and CPU time
- accounting. This is done by reading a CPU counter on each
- kernel entry and exit and on transitions within the kernel
- between system, softirq and hardirq state, so there is a
- small performance impact. This also enables accounting of
- stolen time on logically-partitioned systems running on
- IBM POWER5-based machines.
-
- If in doubt, say Y here.
-
config PPC_HAVE_PMU_SUPPORT
bool
config PGSTE
def_bool y if KVM
-config VIRT_CPU_ACCOUNTING
- def_bool y
-
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_CMPXCHG_LOCAL
+ select HAVE_VIRT_CPU_ACCOUNTING
+ select VIRT_CPU_ACCOUNTING
select ARCH_DISCARD_MEMBLOCK
select BUILDTIME_EXTABLE_SORT
select ARCH_INLINE_SPIN_TRYLOCK
prev = __switch_to(prev,next); \
} while (0)
-extern void account_vtime(struct task_struct *, struct task_struct *);
-extern void account_tick_vtime(struct task_struct *);
-
#define finish_arch_switch(prev) do { \
set_fs(current->thread.mm_segment); \
- account_vtime(prev, current); \
} while (0)
#endif /* __ASM_SWITCH_TO_H */
return virt_timer_forward(user + system);
}
-void account_vtime(struct task_struct *prev, struct task_struct *next)
+void account_switch_vtime(struct task_struct *prev)
{
struct thread_info *ti;
ti = task_thread_info(prev);
ti->user_timer = S390_lowcore.user_timer;
ti->system_timer = S390_lowcore.system_timer;
- ti = task_thread_info(next);
+ ti = task_thread_info(current);
S390_lowcore.user_timer = ti->user_timer;
S390_lowcore.system_timer = ti->system_timer;
}
| 1*SD_BALANCE_FORK \
| 0*SD_BALANCE_WAKE \
| 0*SD_WAKE_AFFINE \
- | 0*SD_PREFER_LOCAL \
| 0*SD_SHARE_CPUPOWER \
| 0*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
select HAVE_KRETPROBES
select HAVE_OPTPROBES
select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FENTRY if X86_64
select HAVE_C_RECORDMCOUNT
select HAVE_DYNAMIC_FTRACE
select HAVE_FUNCTION_TRACER
select HAVE_MIXED_BREAKPOINTS_REGS
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
+ select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
select ANON_INODES
select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
select HAVE_CMPXCHG_LOCAL if !M386
If in doubt, say "Y".
+config KVMTOOL_TEST_ENABLE
+ bool "Enable options to create a bootable tools/kvm/ kernel"
+ select NET
+ select NETDEVICES
+ select PCI
+ select BLOCK
+ select BLK_DEV
+ select NETWORK_FILESYSTEMS
+ select INET
+ select EXPERIMENTAL
+ select SERIAL_8250
+ select SERIAL_8250_CONSOLE
+ select IP_PNP
+ select IP_PNP_DHCP
+ select BINFMT_ELF
+ select PCI_MSI
+ select HAVE_ARCH_KGDB
+ select DEBUG_KERNEL
+ select KGDB
+ select KGDB_SERIAL_CONSOLE
+ select VIRTUALIZATION
+ select VIRTIO
+ select VIRTIO_RING
+ select VIRTIO_PCI
+ select VIRTIO_BLK
+ select VIRTIO_CONSOLE
+ select VIRTIO_NET
+ select 9P_FS
+ select NET_9P
+ select NET_9P_VIRTIO
+
menuconfig PARAVIRT_GUEST
bool "Paravirtualized guest support"
---help---
Say N otherwise.
config MICROCODE
- tristate "/dev/cpu/microcode - microcode support"
+ tristate "CPU microcode loading support"
select FW_LOADER
---help---
+
If you say Y here, you will be able to update the microcode on
certain Intel and AMD processors. The Intel support is for the
- IA32 family, e.g. Pentium Pro, Pentium II, Pentium III,
- Pentium 4, Xeon etc. The AMD support is for family 0x10 and
- 0x11 processors, e.g. Opteron, Phenom and Turion 64 Ultra.
- You will obviously need the actual microcode binary data itself
- which is not shipped with the Linux kernel.
+ IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4,
+ Xeon etc. The AMD support is for families 0x10 and later. You will
+ obviously need the actual microcode binary data itself which is not
+ shipped with the Linux kernel.
This option selects the general module only, you need to select
at least one vendor specific module as well.
- To compile this driver as a module, choose M here: the
- module will be called microcode.
+ To compile this driver as a module, choose M here: the module
+ will be called microcode.
config MICROCODE_INTEL
- bool "Intel microcode patch loading support"
+ bool "Intel microcode loading support"
depends on MICROCODE
default MICROCODE
select FW_LOADER
<http://www.urbanmyth.org/microcode/>.
config MICROCODE_AMD
- bool "AMD microcode patch loading support"
+ bool "AMD microcode loading support"
depends on MICROCODE
select FW_LOADER
---help---
#define SVGA_MODE ASK_VGA
#endif
-#ifndef RAMDISK
-#define RAMDISK 0
-#endif
-
#ifndef ROOT_RDONLY
#define ROOT_RDONLY 1
#endif
void *locks, void *locks_end,
void *text, void *text_end);
extern void alternatives_smp_module_del(struct module *mod);
-extern void alternatives_smp_switch(int smp);
+extern void alternatives_enable_smp(void);
extern int alternatives_text_reserved(void *start, void *end);
extern bool skip_smp_alternatives;
#else
void *locks, void *locks_end,
void *text, void *text_end) {}
static inline void alternatives_smp_module_del(struct module *mod) {}
-static inline void alternatives_smp_switch(int smp) {}
+static inline void alternatives_enable_smp(void) {}
static inline int alternatives_text_reserved(void *start, void *end)
{
return 0;
#ifdef __ASSEMBLY__
- .macro MCOUNT_SAVE_FRAME
- /* taken from glibc */
- subq $0x38, %rsp
- movq %rax, (%rsp)
- movq %rcx, 8(%rsp)
- movq %rdx, 16(%rsp)
- movq %rsi, 24(%rsp)
- movq %rdi, 32(%rsp)
- movq %r8, 40(%rsp)
- movq %r9, 48(%rsp)
+ /* skip is set if the stack was already partially adjusted */
+ .macro MCOUNT_SAVE_FRAME skip=0
+ /*
+ * We add enough stack to save all regs.
+ */
+ subq $(SS+8-\skip), %rsp
+ movq %rax, RAX(%rsp)
+ movq %rcx, RCX(%rsp)
+ movq %rdx, RDX(%rsp)
+ movq %rsi, RSI(%rsp)
+ movq %rdi, RDI(%rsp)
+ movq %r8, R8(%rsp)
+ movq %r9, R9(%rsp)
+ /* Move RIP to its proper location */
+ movq SS+8(%rsp), %rdx
+ movq %rdx, RIP(%rsp)
.endm
- .macro MCOUNT_RESTORE_FRAME
- movq 48(%rsp), %r9
- movq 40(%rsp), %r8
- movq 32(%rsp), %rdi
- movq 24(%rsp), %rsi
- movq 16(%rsp), %rdx
- movq 8(%rsp), %rcx
- movq (%rsp), %rax
- addq $0x38, %rsp
+ .macro MCOUNT_RESTORE_FRAME skip=0
+ movq R9(%rsp), %r9
+ movq R8(%rsp), %r8
+ movq RDI(%rsp), %rdi
+ movq RSI(%rsp), %rsi
+ movq RDX(%rsp), %rdx
+ movq RCX(%rsp), %rcx
+ movq RAX(%rsp), %rax
+ addq $(SS+8-\skip), %rsp
.endm
#endif
#ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR ((long)(mcount))
+#ifdef CC_USING_FENTRY
+# define MCOUNT_ADDR ((long)(__fentry__))
+#else
+# define MCOUNT_ADDR ((long)(mcount))
+#endif
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#endif
+
#ifndef __ASSEMBLY__
extern void mcount(void);
extern atomic_t modifying_ftrace_code;
+extern void __fentry__(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
#include <asm/insn.h>
#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define ARCH_SUPPORTS_KPROBES_ON_FTRACE
struct pt_regs;
struct kprobe;
enum ucode_state (*request_microcode_user) (int cpu,
const void __user *buf, size_t size);
- enum ucode_state (*request_microcode_fw) (int cpu,
- struct device *device);
+ enum ucode_state (*request_microcode_fw) (int cpu, struct device *,
+ bool refresh_fw);
void (*microcode_fini_cpu) (int cpu);
#ifdef CONFIG_MICROCODE_AMD
extern struct microcode_ops * __init init_amd_microcode(void);
extern void __exit exit_amd_microcode(void);
-
-static inline void get_ucode_data(void *to, const u8 *from, size_t n)
-{
- memcpy(to, from, n);
-}
-
#else
static inline struct microcode_ops * __init init_amd_microcode(void)
{
static inline void amd_pmu_disable_virt(void) { }
#endif
+#define arch_perf_out_copy_user copy_from_user_nmi
+
#endif /* _ASM_X86_PERF_EVENT_H */
--- /dev/null
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+enum perf_event_x86_regs {
+ PERF_REG_X86_AX,
+ PERF_REG_X86_BX,
+ PERF_REG_X86_CX,
+ PERF_REG_X86_DX,
+ PERF_REG_X86_SI,
+ PERF_REG_X86_DI,
+ PERF_REG_X86_BP,
+ PERF_REG_X86_SP,
+ PERF_REG_X86_IP,
+ PERF_REG_X86_FLAGS,
+ PERF_REG_X86_CS,
+ PERF_REG_X86_SS,
+ PERF_REG_X86_DS,
+ PERF_REG_X86_ES,
+ PERF_REG_X86_FS,
+ PERF_REG_X86_GS,
+ PERF_REG_X86_R8,
+ PERF_REG_X86_R9,
+ PERF_REG_X86_R10,
+ PERF_REG_X86_R11,
+ PERF_REG_X86_R12,
+ PERF_REG_X86_R13,
+ PERF_REG_X86_R14,
+ PERF_REG_X86_R15,
+
+ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
+ PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+};
+#endif /* _ASM_X86_PERF_REGS_H */
obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
#define MAX_PATCH_LEN (255-1)
-#ifdef CONFIG_HOTPLUG_CPU
-static int smp_alt_once;
-
-static int __init bootonly(char *str)
-{
- smp_alt_once = 1;
- return 1;
-}
-__setup("smp-alt-boot", bootonly);
-#else
-#define smp_alt_once 1
-#endif
-
static int __initdata_or_module debug_alternative;
static int __init debug_alt(char *str)
{
const s32 *poff;
- if (noreplace_smp)
- return;
-
mutex_lock(&text_mutex);
for (poff = start; poff < end; poff++) {
u8 *ptr = (u8 *)poff + *poff;
};
static LIST_HEAD(smp_alt_modules);
static DEFINE_MUTEX(smp_alt);
-static int smp_mode = 1; /* protected by smp_alt */
+static bool uniproc_patched = false; /* protected by smp_alt */
void __init_or_module alternatives_smp_module_add(struct module *mod,
char *name,
{
struct smp_alt_module *smp;
- if (noreplace_smp)
- return;
+ mutex_lock(&smp_alt);
+ if (!uniproc_patched)
+ goto unlock;
- if (smp_alt_once) {
- if (boot_cpu_has(X86_FEATURE_UP))
- alternatives_smp_unlock(locks, locks_end,
- text, text_end);
- return;
- }
+ if (num_possible_cpus() == 1)
+ /* Don't bother remembering, we'll never have to undo it. */
+ goto smp_unlock;
smp = kzalloc(sizeof(*smp), GFP_KERNEL);
if (NULL == smp)
- return; /* we'll run the (safe but slow) SMP code then ... */
+ /* we'll run the (safe but slow) SMP code then ... */
+ goto unlock;
smp->mod = mod;
smp->name = name;
__func__, smp->locks, smp->locks_end,
smp->text, smp->text_end, smp->name);
- mutex_lock(&smp_alt);
list_add_tail(&smp->next, &smp_alt_modules);
- if (boot_cpu_has(X86_FEATURE_UP))
- alternatives_smp_unlock(smp->locks, smp->locks_end,
- smp->text, smp->text_end);
+smp_unlock:
+ alternatives_smp_unlock(locks, locks_end, text, text_end);
+unlock:
mutex_unlock(&smp_alt);
}
{
struct smp_alt_module *item;
- if (smp_alt_once || noreplace_smp)
- return;
-
mutex_lock(&smp_alt);
list_for_each_entry(item, &smp_alt_modules, next) {
if (mod != item->mod)
continue;
list_del(&item->next);
- mutex_unlock(&smp_alt);
- DPRINTK("%s: %s\n", __func__, item->name);
kfree(item);
- return;
+ break;
}
mutex_unlock(&smp_alt);
}
-bool skip_smp_alternatives;
-void alternatives_smp_switch(int smp)
+void alternatives_enable_smp(void)
{
struct smp_alt_module *mod;
pr_info("lockdep: fixing up alternatives\n");
#endif
- if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
- return;
- BUG_ON(!smp && (num_online_cpus() > 1));
+ /* Why bother if there are no other CPUs? */
+ BUG_ON(num_possible_cpus() == 1);
mutex_lock(&smp_alt);
- /*
- * Avoid unnecessary switches because it forces JIT based VMs to
- * throw away all cached translations, which can be quite costly.
- */
- if (smp == smp_mode) {
- /* nothing */
- } else if (smp) {
+ if (uniproc_patched) {
pr_info("switching to SMP code\n");
+ BUG_ON(num_online_cpus() != 1);
clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
list_for_each_entry(mod, &smp_alt_modules, next)
alternatives_smp_lock(mod->locks, mod->locks_end,
mod->text, mod->text_end);
- } else {
- pr_info("switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
- list_for_each_entry(mod, &smp_alt_modules, next)
- alternatives_smp_unlock(mod->locks, mod->locks_end,
- mod->text, mod->text_end);
+ uniproc_patched = false;
}
- smp_mode = smp;
mutex_unlock(&smp_alt);
}
apply_alternatives(__alt_instructions, __alt_instructions_end);
- /* switch to patch-once-at-boottime-only mode and free the
- * tables in case we know the number of CPUs will never ever
- * change */
-#ifdef CONFIG_HOTPLUG_CPU
- if (num_possible_cpus() < 2)
- smp_alt_once = 1;
-#endif
-
#ifdef CONFIG_SMP
- if (smp_alt_once) {
- if (1 == num_possible_cpus()) {
- pr_info("switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
-
- alternatives_smp_unlock(__smp_locks, __smp_locks_end,
- _text, _etext);
- }
- } else {
+ /* Patch to UP if other cpus not imminent. */
+ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
+ uniproc_patched = true;
alternatives_smp_module_add(NULL, "core kernel",
__smp_locks, __smp_locks_end,
_text, _etext);
-
- /* Only switch to UP mode if we don't immediately boot others */
- if (num_present_cpus() == 1 || setup_max_cpus <= 1)
- alternatives_smp_switch(0);
}
-#endif
- apply_paravirt(__parainstructions, __parainstructions_end);
- if (smp_alt_once)
+ if (!uniproc_patched || num_possible_cpus() == 1)
free_init_pages("SMP alternatives",
(unsigned long)__smp_locks,
(unsigned long)__smp_locks_end);
+#endif
+
+ apply_paravirt(__parainstructions, __parainstructions_end);
restart_nmi();
}
}
#endif
+static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has_invlpg)
+ return;
+
+ tlb_flushall_shift = 5;
+
+ if (c->x86 <= 0x11)
+ tlb_flushall_shift = 4;
+}
+
+static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
+{
+ u32 ebx, eax, ecx, edx;
+ u16 mask = 0xfff;
+
+ if (c->x86 < 0xf)
+ return;
+
+ if (c->extended_cpuid_level < 0x80000006)
+ return;
+
+ cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
+
+ tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
+ tlb_lli_4k[ENTRIES] = ebx & mask;
+
+ /*
+ * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
+ * characteristics from the CPUID function 0x80000005 instead.
+ */
+ if (c->x86 == 0xf) {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ mask = 0xff;
+ }
+
+ /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!((eax >> 16) & mask)) {
+ u32 a, b, c, d;
+
+ cpuid(0x80000005, &a, &b, &c, &d);
+ tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff;
+ } else {
+ tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+ }
+
+ /* a 4M entry uses two 2M entries */
+ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+
+ /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!(eax & mask)) {
+ /* Erratum 658 */
+ if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
+ tlb_lli_2m[ENTRIES] = 1024;
+ } else {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ tlb_lli_2m[ENTRIES] = eax & 0xff;
+ }
+ } else
+ tlb_lli_2m[ENTRIES] = eax & mask;
+
+ tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+
+ cpu_set_tlb_flushall_shift(c);
+}
+
static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
.c_vendor = "AMD",
.c_ident = { "AuthenticAMD" },
.c_size_cache = amd_size_cache,
#endif
.c_early_init = early_init_amd,
+ .c_detect_tlb = cpu_detect_tlb_amd,
.c_bsp_init = bsp_init_amd,
.c_init = init_amd,
.c_x86_vendor = X86_VENDOR_AMD,
printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
- "tlb_flushall_shift is 0x%x\n",
+ "tlb_flushall_shift: %d\n",
tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
#else
vgetcpu_set_mode();
#endif
- if (boot_cpu_data.cpuid_level >= 2)
- cpu_detect_tlb(&boot_cpu_data);
+ cpu_detect_tlb(&boot_cpu_data);
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
int i, j, n;
unsigned int regs[4];
unsigned char *desc = (unsigned char *)regs;
+
+ if (c->cpuid_level < 2)
+ return;
+
/* Number of times to iterate */
n = cpuid_eax(2) & 0xFF;
}
static cpumask_var_t mce_inject_cpumask;
+static DEFINE_MUTEX(mce_inject_mutex);
static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
{
put_online_cpus();
} else
#endif
+ {
+ preempt_disable();
raise_local();
+ preempt_enable();
+ }
}
/* Error injection interface */
* so do it a jiffie or two later everywhere.
*/
schedule_timeout(2);
+
+ mutex_lock(&mce_inject_mutex);
raise_mce(&m);
+ mutex_unlock(&mce_inject_mutex);
return usize;
}
extern struct mce_bank *mce_banks;
+#ifdef CONFIG_X86_MCE_INTEL
+unsigned long mce_intel_adjust_timer(unsigned long interval);
+void mce_intel_cmci_poll(void);
+void mce_intel_hcpu_update(unsigned long cpu);
+#else
+# define mce_intel_adjust_timer mce_adjust_timer_default
+static inline void mce_intel_cmci_poll(void) { }
+static inline void mce_intel_hcpu_update(unsigned long cpu) { }
+#endif
+
+void mce_timer_kick(unsigned long interval);
+
#ifdef CONFIG_ACPI_APEI
int apei_write_mce(struct mce *m);
ssize_t apei_read_mce(struct mce *m, u64 *record_id);
static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
+static unsigned long mce_adjust_timer_default(unsigned long interval)
+{
+ return interval;
+}
+
+static unsigned long (*mce_adjust_timer)(unsigned long interval) =
+ mce_adjust_timer_default;
+
static void mce_timer_fn(unsigned long data)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
if (mce_available(__this_cpu_ptr(&cpu_info))) {
machine_check_poll(MCP_TIMESTAMP,
&__get_cpu_var(mce_poll_banks));
+ mce_intel_cmci_poll();
}
/*
* polling interval, otherwise increase the polling interval.
*/
iv = __this_cpu_read(mce_next_interval);
- if (mce_notify_irq())
+ if (mce_notify_irq()) {
iv = max(iv / 2, (unsigned long) HZ/100);
- else
+ } else {
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
+ iv = mce_adjust_timer(iv);
+ }
__this_cpu_write(mce_next_interval, iv);
+ /* Might have become 0 after CMCI storm subsided */
+ if (iv) {
+ t->expires = jiffies + iv;
+ add_timer_on(t, smp_processor_id());
+ }
+}
- t->expires = jiffies + iv;
- add_timer_on(t, smp_processor_id());
+/*
+ * Ensure that the timer is firing in @interval from now.
+ */
+void mce_timer_kick(unsigned long interval)
+{
+ struct timer_list *t = &__get_cpu_var(mce_timer);
+ unsigned long when = jiffies + interval;
+ unsigned long iv = __this_cpu_read(mce_next_interval);
+
+ if (timer_pending(t)) {
+ if (time_before(when, t->expires))
+ mod_timer_pinned(t, when);
+ } else {
+ t->expires = round_jiffies(when);
+ add_timer_on(t, smp_processor_id());
+ }
+ if (interval < iv)
+ __this_cpu_write(mce_next_interval, interval);
}
/* Must not be called in IRQ context where del_timer_sync() can deadlock */
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
mce_intel_feature_init(c);
+ mce_adjust_timer = mce_intel_adjust_timer;
break;
case X86_VENDOR_AMD:
mce_amd_feature_init(c);
}
}
-static void __mcheck_cpu_init_timer(void)
+static void mce_start_timer(unsigned int cpu, struct timer_list *t)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
- unsigned long iv = check_interval * HZ;
+ unsigned long iv = mce_adjust_timer(check_interval * HZ);
- setup_timer(t, mce_timer_fn, smp_processor_id());
+ __this_cpu_write(mce_next_interval, iv);
- if (mce_ignore_ce)
+ if (mce_ignore_ce || !iv)
return;
- __this_cpu_write(mce_next_interval, iv);
- if (!iv)
- return;
t->expires = round_jiffies(jiffies + iv);
add_timer_on(t, smp_processor_id());
}
+static void __mcheck_cpu_init_timer(void)
+{
+ struct timer_list *t = &__get_cpu_var(mce_timer);
+ unsigned int cpu = smp_processor_id();
+
+ setup_timer(t, mce_timer_fn, cpu);
+ mce_start_timer(cpu, t);
+}
+
/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
unsigned int cpu = (unsigned long)hcpu;
struct timer_list *t = &per_cpu(mce_timer, cpu);
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
mce_device_create(cpu);
if (threshold_cpu_callback)
threshold_cpu_callback(action, cpu);
break;
case CPU_DEAD:
- case CPU_DEAD_FROZEN:
if (threshold_cpu_callback)
threshold_cpu_callback(action, cpu);
mce_device_remove(cpu);
+ mce_intel_hcpu_update(cpu);
break;
case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- del_timer_sync(t);
smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
+ del_timer_sync(t);
break;
case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- if (!mce_ignore_ce && check_interval) {
- t->expires = round_jiffies(jiffies +
- per_cpu(mce_next_interval, cpu));
- add_timer_on(t, cpu);
- }
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
+ mce_start_timer(cpu, t);
break;
- case CPU_POST_DEAD:
+ }
+
+ if (action == CPU_POST_DEAD) {
/* intentionally ignoring frozen here */
cmci_rediscover(cpu);
- break;
}
+
return NOTIFY_OK;
}
#include <asm/msr.h>
#include <asm/mce.h>
+#include "mce-internal.h"
+
/*
* Support for Intel Correct Machine Check Interrupts. This allows
* the CPU to raise an interrupt when a corrected machine check happened.
*/
static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
-#define CMCI_THRESHOLD 1
+#define CMCI_THRESHOLD 1
+#define CMCI_POLL_INTERVAL (30 * HZ)
+#define CMCI_STORM_INTERVAL (1 * HZ)
+#define CMCI_STORM_THRESHOLD 15
+
+static DEFINE_PER_CPU(unsigned long, cmci_time_stamp);
+static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt);
+static DEFINE_PER_CPU(unsigned int, cmci_storm_state);
+
+enum {
+ CMCI_STORM_NONE,
+ CMCI_STORM_ACTIVE,
+ CMCI_STORM_SUBSIDED,
+};
+
+static atomic_t cmci_storm_on_cpus;
static int cmci_supported(int *banks)
{
return !!(cap & MCG_CMCI_P);
}
+void mce_intel_cmci_poll(void)
+{
+ if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
+ return;
+ machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+}
+
+void mce_intel_hcpu_update(unsigned long cpu)
+{
+ if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE)
+ atomic_dec(&cmci_storm_on_cpus);
+
+ per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
+}
+
+unsigned long mce_intel_adjust_timer(unsigned long interval)
+{
+ int r;
+
+ if (interval < CMCI_POLL_INTERVAL)
+ return interval;
+
+ switch (__this_cpu_read(cmci_storm_state)) {
+ case CMCI_STORM_ACTIVE:
+ /*
+ * We switch back to interrupt mode once the poll timer has
+ * silenced itself. That means no events recorded and the
+ * timer interval is back to our poll interval.
+ */
+ __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED);
+ r = atomic_sub_return(1, &cmci_storm_on_cpus);
+ if (r == 0)
+ pr_notice("CMCI storm subsided: switching to interrupt mode\n");
+ /* FALLTHROUGH */
+
+ case CMCI_STORM_SUBSIDED:
+ /*
+ * We wait for all cpus to go back to SUBSIDED
+ * state. When that happens we switch back to
+ * interrupt mode.
+ */
+ if (!atomic_read(&cmci_storm_on_cpus)) {
+ __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
+ cmci_reenable();
+ cmci_recheck();
+ }
+ return CMCI_POLL_INTERVAL;
+ default:
+ /*
+ * We have shiny weather. Let the poll do whatever it
+ * thinks.
+ */
+ return interval;
+ }
+}
+
+static bool cmci_storm_detect(void)
+{
+ unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
+ unsigned long ts = __this_cpu_read(cmci_time_stamp);
+ unsigned long now = jiffies;
+ int r;
+
+ if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE)
+ return true;
+
+ if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) {
+ cnt++;
+ } else {
+ cnt = 1;
+ __this_cpu_write(cmci_time_stamp, now);
+ }
+ __this_cpu_write(cmci_storm_cnt, cnt);
+
+ if (cnt <= CMCI_STORM_THRESHOLD)
+ return false;
+
+ cmci_clear();
+ __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
+ r = atomic_add_return(1, &cmci_storm_on_cpus);
+ mce_timer_kick(CMCI_POLL_INTERVAL);
+
+ if (r == 1)
+ pr_notice("CMCI storm detected: switching to poll mode\n");
+ return true;
+}
+
/*
* The interrupt handler. This is called on every event.
* Just call the poller directly to log any events.
*/
static void intel_threshold_interrupt(void)
{
+ if (cmci_storm_detect())
+ return;
machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
mce_notify_irq();
}
-static void print_update(char *type, int *hdr, int num)
-{
- if (*hdr == 0)
- printk(KERN_INFO "CPU %d MCA banks", smp_processor_id());
- *hdr = 1;
- printk(KERN_CONT " %s:%d", type, num);
-}
-
/*
* Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
* on this CPU. Use the algorithm recommended in the SDM to discover shared
* banks.
*/
-static void cmci_discover(int banks, int boot)
+static void cmci_discover(int banks)
{
unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
unsigned long flags;
- int hdr = 0;
int i;
raw_spin_lock_irqsave(&cmci_discover_lock, flags);
/* Already owned by someone else? */
if (val & MCI_CTL2_CMCI_EN) {
- if (test_and_clear_bit(i, owned) && !boot)
- print_update("SHD", &hdr, i);
+ clear_bit(i, owned);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
continue;
}
/* Did the enable bit stick? -- the bank supports CMCI */
if (val & MCI_CTL2_CMCI_EN) {
- if (!test_and_set_bit(i, owned) && !boot)
- print_update("CMCI", &hdr, i);
+ set_bit(i, owned);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
} else {
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
- if (hdr)
- printk(KERN_CONT "\n");
}
/*
continue;
/* Recheck banks in case CPUs don't all have the same */
if (cmci_supported(&banks))
- cmci_discover(banks, 0);
+ cmci_discover(banks);
}
set_cpus_allowed_ptr(current, old);
{
int banks;
if (cmci_supported(&banks))
- cmci_discover(banks, 0);
+ cmci_discover(banks);
}
static void intel_init_cmci(void)
return;
mce_threshold_vector = intel_threshold_interrupt;
- cmci_discover(banks, 1);
+ cmci_discover(banks);
/*
* For CPU #0 this runs with still disabled APIC, but that's
* ok because only the vector is set up. We still do another
break;
case 28: /* Atom */
+ case 54: /* Cedariew */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
* to have an operational LBR which can freeze
* on PMU interrupt
*/
- if (boot_cpu_data.x86_mask < 10) {
+ if (boot_cpu_data.x86_model == 28
+ && boot_cpu_data.x86_mask < 10) {
pr_cont("LBR disabled due to erratum");
return;
}
.xlate = ioapic_xlate,
};
+static void dt_add_ioapic_domain(unsigned int ioapic_num,
+ struct device_node *np)
+{
+ struct irq_domain *id;
+ struct mp_ioapic_gsi *gsi_cfg;
+ int ret;
+ int num;
+
+ gsi_cfg = mp_ioapic_gsi_routing(ioapic_num);
+ num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
+
+ id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops,
+ (void *)ioapic_num);
+ BUG_ON(!id);
+ if (gsi_cfg->gsi_base == 0) {
+ /*
+ * The first NR_IRQS_LEGACY irq descs are allocated in
+ * early_irq_init() and need just a mapping. The
+ * remaining irqs need both. All of them are preallocated
+ * and assigned so we can keep the 1:1 mapping which the ioapic
+ * is having.
+ */
+ ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY);
+ if (ret)
+ pr_err("Error mapping legacy IRQs: %d\n", ret);
+
+ if (num > NR_IRQS_LEGACY) {
+ ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY,
+ NR_IRQS_LEGACY, num - NR_IRQS_LEGACY);
+ if (ret)
+ pr_err("Error creating mapping for the "
+ "remaining IRQs: %d\n", ret);
+ }
+ irq_set_default_host(id);
+ } else {
+ ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num);
+ if (ret)
+ pr_err("Error creating IRQ mapping: %d\n", ret);
+ }
+}
+
static void __init ioapic_add_ofnode(struct device_node *np)
{
struct resource r;
for (i = 0; i < nr_ioapics; i++) {
if (r.start == mpc_ioapic_addr(i)) {
- struct irq_domain *id;
- struct mp_ioapic_gsi *gsi_cfg;
-
- gsi_cfg = mp_ioapic_gsi_routing(i);
-
- id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0,
- &ioapic_irq_domain_ops,
- (void*)i);
- BUG_ON(!id);
+ dt_add_ioapic_domain(i, np);
return;
}
}
pushl %eax
pushl %ecx
pushl %edx
- movl 0xc(%esp), %eax
+ pushl $0 /* Pass NULL as regs pointer */
+ movl 4*4(%esp), %eax
movl 0x4(%ebp), %edx
+ leal function_trace_op, %ecx
subl $MCOUNT_INSN_SIZE, %eax
.globl ftrace_call
ftrace_call:
call ftrace_stub
+ addl $4,%esp /* skip NULL pointer */
popl %edx
popl %ecx
popl %eax
+ftrace_ret:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
ret
END(ftrace_caller)
+ENTRY(ftrace_regs_caller)
+ pushf /* push flags before compare (in cs location) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /*
+ * i386 does not save SS and ESP when coming from kernel.
+ * Instead, to get sp, ®s->sp is used (see ptrace.h).
+ * Unfortunately, that means eflags must be at the same location
+ * as the current return ip is. We move the return ip into the
+ * ip location, and move flags into the return ip location.
+ */
+ pushl 4(%esp) /* save return ip into ip slot */
+ subl $MCOUNT_INSN_SIZE, (%esp) /* Adjust ip */
+
+ pushl $0 /* Load 0 into orig_ax */
+ pushl %gs
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+
+ movl 13*4(%esp), %eax /* Get the saved flags */
+ movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
+ /* clobbering return ip */
+ movl $__KERNEL_CS,13*4(%esp)
+
+ movl 12*4(%esp), %eax /* Load ip (1st parameter) */
+ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
+ leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ pushl %esp /* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ addl $4, %esp /* Skip pt_regs */
+ movl 14*4(%esp), %eax /* Move flags back into cs */
+ movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
+ movl 12*4(%esp), %eax /* Get return ip from regs->ip */
+ addl $MCOUNT_INSN_SIZE, %eax
+ movl %eax, 14*4(%esp) /* Put return ip back for ret */
+
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ popl %ds
+ popl %es
+ popl %fs
+ popl %gs
+ addl $8, %esp /* Skip orig_ax and ip */
+ popf /* Pop flags at end (no addl to corrupt flags) */
+ jmp ftrace_ret
+
+ftrace_restore_flags:
+ popf
+ jmp ftrace_stub
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(mcount)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
pushl %eax
pushl %ecx
pushl %edx
.section .entry.text, "ax"
#ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CC_USING_FENTRY
+# define function_hook __fentry__
+#else
+# define function_hook mcount
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(mcount)
+
+ENTRY(function_hook)
retq
-END(mcount)
+END(function_hook)
+
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+ MCOUNT_SAVE_FRAME \skip
+
+ /* Load the ftrace_ops into the 3rd parameter */
+ leaq function_trace_op, %rdx
+
+ /* Load ip into the first parameter */
+ movq RIP(%rsp), %rdi
+ subq $MCOUNT_INSN_SIZE, %rdi
+ /* Load the parent_ip into the second parameter */
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
+ movq 8(%rbp), %rsi
+#endif
+.endm
ENTRY(ftrace_caller)
+ /* Check if tracing was disabled (quick check) */
cmpl $0, function_trace_stop
jne ftrace_stub
- MCOUNT_SAVE_FRAME
-
- movq 0x38(%rsp), %rdi
- movq 8(%rbp), %rsi
- subq $MCOUNT_INSN_SIZE, %rdi
+ ftrace_caller_setup
+ /* regs go into 4th parameter (but make it NULL) */
+ movq $0, %rcx
GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
+ftrace_return:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
GLOBAL(ftrace_graph_call)
retq
END(ftrace_caller)
+ENTRY(ftrace_regs_caller)
+ /* Save the current flags before compare (in SS location)*/
+ pushfq
+
+ /* Check if tracing was disabled (quick check) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /* skip=8 to skip flags saved in SS */
+ ftrace_caller_setup 8
+
+ /* Save the rest of pt_regs */
+ movq %r15, R15(%rsp)
+ movq %r14, R14(%rsp)
+ movq %r13, R13(%rsp)
+ movq %r12, R12(%rsp)
+ movq %r11, R11(%rsp)
+ movq %r10, R10(%rsp)
+ movq %rbp, RBP(%rsp)
+ movq %rbx, RBX(%rsp)
+ /* Copy saved flags */
+ movq SS(%rsp), %rcx
+ movq %rcx, EFLAGS(%rsp)
+ /* Kernel segments */
+ movq $__KERNEL_DS, %rcx
+ movq %rcx, SS(%rsp)
+ movq $__KERNEL_CS, %rcx
+ movq %rcx, CS(%rsp)
+ /* Stack - skipping return address */
+ leaq SS+16(%rsp), %rcx
+ movq %rcx, RSP(%rsp)
+
+ /* regs go into 4th parameter */
+ leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ /* Copy flags back to SS, to restore them */
+ movq EFLAGS(%rsp), %rax
+ movq %rax, SS(%rsp)
+
+ /* restore the rest of pt_regs */
+ movq R15(%rsp), %r15
+ movq R14(%rsp), %r14
+ movq R13(%rsp), %r13
+ movq R12(%rsp), %r12
+ movq R10(%rsp), %r10
+ movq RBP(%rsp), %rbp
+ movq RBX(%rsp), %rbx
+
+ /* skip=8 to skip flags saved in SS */
+ MCOUNT_RESTORE_FRAME 8
+
+ /* Restore flags */
+ popfq
+
+ jmp ftrace_return
+ftrace_restore_flags:
+ popfq
+ jmp ftrace_stub
+
+END(ftrace_regs_caller)
+
+
#else /* ! CONFIG_DYNAMIC_FTRACE */
-ENTRY(mcount)
+
+ENTRY(function_hook)
cmpl $0, function_trace_stop
jne ftrace_stub
trace:
MCOUNT_SAVE_FRAME
- movq 0x38(%rsp), %rdi
+ movq RIP(%rsp), %rdi
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
movq 8(%rbp), %rsi
+#endif
subq $MCOUNT_INSN_SIZE, %rdi
call *ftrace_trace_function
MCOUNT_RESTORE_FRAME
jmp ftrace_stub
-END(mcount)
+END(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
MCOUNT_SAVE_FRAME
+#ifdef CC_USING_FENTRY
+ leaq SS+16(%rsp), %rdi
+ movq $0, %rdx /* No framepointers needed */
+#else
leaq 8(%rbp), %rdi
- movq 0x38(%rsp), %rsi
movq (%rbp), %rdx
+#endif
+ movq RIP(%rsp), %rsi
subq $MCOUNT_INSN_SIZE, %rsi
call prepare_ftrace_return
ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
unsigned const char *new_code);
+/*
+ * Should never be called:
+ * As it is only called by __ftrace_replace_code() which is called by
+ * ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
+ * which is called to turn mcount into nops or nops into function calls
+ * but not to convert a function from not using regs to one that uses
+ * regs, which ftrace_modify_call() is for.
+ */
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ WARN_ON(1);
+ return -EINVAL;
+}
+
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
ret = ftrace_modify_code(ip, old, new);
+ /* Also update the regs callback function */
+ if (!ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
atomic_dec(&modifying_ftrace_code);
return ret;
return add_break(rec->ip, old);
}
+/*
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ */
+static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_REGS)
+ return (unsigned long)FTRACE_REGS_ADDR;
+ else
+ return (unsigned long)FTRACE_ADDR;
+}
+
+/*
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ */
+static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_REGS_EN)
+ return (unsigned long)FTRACE_REGS_ADDR;
+ else
+ return (unsigned long)FTRACE_ADDR;
+}
+
static int add_breakpoints(struct dyn_ftrace *rec, int enable)
{
unsigned long ftrace_addr;
ret = ftrace_test_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
/* converting nop to call */
return add_brk_on_nop(rec);
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
+ ftrace_addr = get_ftrace_old_addr(rec);
+ /* fall through */
case FTRACE_UPDATE_MAKE_NOP:
/* converting a call to a nop */
return add_brk_on_call(rec, ftrace_addr);
* If not, don't touch the breakpoint, we make just create
* a disaster.
*/
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
+ nop = ftrace_call_replace(ip, ftrace_addr);
+
+ if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
+ goto update;
+
+ /* Check both ftrace_addr and ftrace_old_addr */
+ ftrace_addr = get_ftrace_old_addr(rec);
nop = ftrace_call_replace(ip, ftrace_addr);
if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
return -EINVAL;
}
+ update:
return probe_kernel_write((void *)ip, &nop[0], 1);
}
ret = ftrace_test_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
return add_update_call(rec, ftrace_addr);
ret = ftrace_update_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
return finish_update_call(rec, ftrace_addr);
* out of.
*/
outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
- outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */
+ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */
}
static struct syscore_ops i8259_syscore_ops = {
return 0;
}
+#ifdef KPROBES_CAN_USE_FTRACE
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct pt_regs *regs)
+{
+ struct kprobe *p;
+ struct kprobe_ctlblk *kcb;
+ unsigned long flags;
+
+ /* Disable irq for emulating a breakpoint and avoiding preempt */
+ local_irq_save(flags);
+
+ p = get_kprobe((kprobe_opcode_t *)ip);
+ if (unlikely(!p) || kprobe_disabled(p))
+ goto end;
+
+ kcb = get_kprobe_ctlblk();
+ if (kprobe_running()) {
+ kprobes_inc_nmissed_count(p);
+ } else {
+ regs->ip += sizeof(kprobe_opcode_t);
+
+ __this_cpu_write(current_kprobe, p);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ if (p->pre_handler)
+ p->pre_handler(p, regs);
+
+ if (unlikely(p->post_handler)) {
+ /* Emulate singlestep as if there is a 5byte nop */
+ regs->ip = ip + MCOUNT_INSN_SIZE;
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
+ __this_cpu_write(current_kprobe, NULL);
+ regs->ip = ip; /* Recover for next callback */
+ }
+end:
+ local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+ p->ainsn.insn = NULL;
+ p->ainsn.boostable = -1;
+ return 0;
+}
+#endif
+
int __init arch_init_kprobes(void)
{
return arch_init_optprobes();
static struct equiv_cpu_entry *equiv_cpu_table;
-/* page-sized ucode patch buffer */
-void *patch;
+struct ucode_patch {
+ struct list_head plist;
+ void *data;
+ u32 patch_id;
+ u16 equiv_cpu;
+};
+
+static LIST_HEAD(pcache);
+
+static u16 find_equiv_id(unsigned int cpu)
+{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ int i = 0;
+
+ if (!equiv_cpu_table)
+ return 0;
+
+ while (equiv_cpu_table[i].installed_cpu != 0) {
+ if (uci->cpu_sig.sig == equiv_cpu_table[i].installed_cpu)
+ return equiv_cpu_table[i].equiv_cpu;
+
+ i++;
+ }
+ return 0;
+}
+
+static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu)
+{
+ int i = 0;
+
+ BUG_ON(!equiv_cpu_table);
+
+ while (equiv_cpu_table[i].equiv_cpu != 0) {
+ if (equiv_cpu == equiv_cpu_table[i].equiv_cpu)
+ return equiv_cpu_table[i].installed_cpu;
+ i++;
+ }
+ return 0;
+}
+
+/*
+ * a small, trivial cache of per-family ucode patches
+ */
+static struct ucode_patch *cache_find_patch(u16 equiv_cpu)
+{
+ struct ucode_patch *p;
+
+ list_for_each_entry(p, &pcache, plist)
+ if (p->equiv_cpu == equiv_cpu)
+ return p;
+ return NULL;
+}
+
+static void update_cache(struct ucode_patch *new_patch)
+{
+ struct ucode_patch *p;
+
+ list_for_each_entry(p, &pcache, plist) {
+ if (p->equiv_cpu == new_patch->equiv_cpu) {
+ if (p->patch_id >= new_patch->patch_id)
+ /* we already have the latest patch */
+ return;
+
+ list_replace(&p->plist, &new_patch->plist);
+ kfree(p->data);
+ kfree(p);
+ return;
+ }
+ }
+ /* no patch found, add it */
+ list_add_tail(&new_patch->plist, &pcache);
+}
+
+static void free_cache(void)
+{
+ struct ucode_patch *p;
+
+ list_for_each_entry_reverse(p, &pcache, plist) {
+ __list_del(p->plist.prev, p->plist.next);
+ kfree(p->data);
+ kfree(p);
+ }
+}
+
+static struct ucode_patch *find_patch(unsigned int cpu)
+{
+ u16 equiv_id;
+
+ equiv_id = find_equiv_id(cpu);
+ if (!equiv_id)
+ return NULL;
+
+ return cache_find_patch(equiv_id);
+}
static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ csig->sig = cpuid_eax(0x00000001);
csig->rev = c->microcode;
pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
return 0;
}
-static unsigned int verify_ucode_size(int cpu, u32 patch_size,
+static unsigned int verify_patch_size(int cpu, u32 patch_size,
unsigned int size)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
return patch_size;
}
-static u16 find_equiv_id(void)
+static int apply_microcode_amd(int cpu)
{
- unsigned int current_cpu_id, i = 0;
-
- BUG_ON(equiv_cpu_table == NULL);
-
- current_cpu_id = cpuid_eax(0x00000001);
-
- while (equiv_cpu_table[i].installed_cpu != 0) {
- if (current_cpu_id == equiv_cpu_table[i].installed_cpu)
- return equiv_cpu_table[i].equiv_cpu;
-
- i++;
- }
- return 0;
-}
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct microcode_amd *mc_amd;
+ struct ucode_cpu_info *uci;
+ struct ucode_patch *p;
+ u32 rev, dummy;
-/*
- * we signal a good patch is found by returning its size > 0
- */
-static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
- unsigned int leftover_size, int rev,
- unsigned int *current_size)
-{
- struct microcode_header_amd *mc_hdr;
- unsigned int actual_size, patch_size;
- u16 equiv_cpu_id;
+ BUG_ON(raw_smp_processor_id() != cpu);
- /* size of the current patch we're staring at */
- patch_size = *(u32 *)(ucode_ptr + 4);
- *current_size = patch_size + SECTION_HDR_SIZE;
+ uci = ucode_cpu_info + cpu;
- equiv_cpu_id = find_equiv_id();
- if (!equiv_cpu_id)
+ p = find_patch(cpu);
+ if (!p)
return 0;
- /*
- * let's look at the patch header itself now
- */
- mc_hdr = (struct microcode_header_amd *)(ucode_ptr + SECTION_HDR_SIZE);
+ mc_amd = p->data;
+ uci->mc = p->data;
- if (mc_hdr->processor_rev_id != equiv_cpu_id)
- return 0;
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- /* ucode might be chipset specific -- currently we don't support this */
- if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
- pr_err("CPU%d: chipset specific code not yet supported\n",
- cpu);
+ /* need to apply patch? */
+ if (rev >= mc_amd->hdr.patch_id) {
+ c->microcode = rev;
return 0;
}
- if (mc_hdr->patch_id <= rev)
- return 0;
-
- /*
- * now that the header looks sane, verify its size
- */
- actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
- if (!actual_size)
- return 0;
-
- /* clear the patch buffer */
- memset(patch, 0, PAGE_SIZE);
-
- /* all looks ok, get the binary patch */
- get_ucode_data(patch, ucode_ptr + SECTION_HDR_SIZE, actual_size);
-
- return actual_size;
-}
-
-static int apply_microcode_amd(int cpu)
-{
- u32 rev, dummy;
- int cpu_num = raw_smp_processor_id();
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num;
- struct microcode_amd *mc_amd = uci->mc;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-
- /* We should bind the task to the CPU */
- BUG_ON(cpu_num != cpu);
-
- if (mc_amd == NULL)
- return 0;
-
wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
- /* get patch id after patching */
- rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- /* check current patch id and patch's id for match */
+ /* verify patch application was successful */
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
if (rev != mc_amd->hdr.patch_id) {
pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
return -ENOMEM;
}
- get_ucode_data(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
+ memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
/* add header length */
return size + CONTAINER_HDR_SZ;
equiv_cpu_table = NULL;
}
-static enum ucode_state
-generic_load_microcode(int cpu, const u8 *data, size_t size)
+static void cleanup(void)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- struct microcode_header_amd *mc_hdr = NULL;
- unsigned int mc_size, leftover, current_size = 0;
+ free_equiv_cpu_table();
+ free_cache();
+}
+
+/*
+ * We return the current size even if some of the checks failed so that
+ * we can skip over the next patch. If we return a negative value, we
+ * signal a grave error like a memory allocation has failed and the
+ * driver cannot continue functioning normally. In such cases, we tear
+ * down everything we've used up so far and exit.
+ */
+static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
+{
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct microcode_header_amd *mc_hdr;
+ struct ucode_patch *patch;
+ unsigned int patch_size, crnt_size, ret;
+ u32 proc_fam;
+ u16 proc_id;
+
+ patch_size = *(u32 *)(fw + 4);
+ crnt_size = patch_size + SECTION_HDR_SIZE;
+ mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
+ proc_id = mc_hdr->processor_rev_id;
+
+ proc_fam = find_cpu_family_by_equiv_cpu(proc_id);
+ if (!proc_fam) {
+ pr_err("No patch family for equiv ID: 0x%04x\n", proc_id);
+ return crnt_size;
+ }
+
+ /* check if patch is for the current family */
+ proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
+ if (proc_fam != c->x86)
+ return crnt_size;
+
+ if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+ pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n",
+ mc_hdr->patch_id);
+ return crnt_size;
+ }
+
+ ret = verify_patch_size(cpu, patch_size, leftover);
+ if (!ret) {
+ pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
+ return crnt_size;
+ }
+
+ patch = kzalloc(sizeof(*patch), GFP_KERNEL);
+ if (!patch) {
+ pr_err("Patch allocation failure.\n");
+ return -EINVAL;
+ }
+
+ patch->data = kzalloc(patch_size, GFP_KERNEL);
+ if (!patch->data) {
+ pr_err("Patch data allocation failure.\n");
+ kfree(patch);
+ return -EINVAL;
+ }
+
+ /* All looks ok, copy patch... */
+ memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size);
+ INIT_LIST_HEAD(&patch->plist);
+ patch->patch_id = mc_hdr->patch_id;
+ patch->equiv_cpu = proc_id;
+
+ /* ... and add to cache. */
+ update_cache(patch);
+
+ return crnt_size;
+}
+
+static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size)
+{
+ enum ucode_state ret = UCODE_ERROR;
+ unsigned int leftover;
+ u8 *fw = (u8 *)data;
+ int crnt_size = 0;
int offset;
- const u8 *ucode_ptr = data;
- void *new_mc = NULL;
- unsigned int new_rev = uci->cpu_sig.rev;
- enum ucode_state state = UCODE_ERROR;
- offset = install_equiv_cpu_table(ucode_ptr);
+ offset = install_equiv_cpu_table(data);
if (offset < 0) {
pr_err("failed to create equivalent cpu table\n");
- goto out;
+ return ret;
}
- ucode_ptr += offset;
+ fw += offset;
leftover = size - offset;
- if (*(u32 *)ucode_ptr != UCODE_UCODE_TYPE) {
+ if (*(u32 *)fw != UCODE_UCODE_TYPE) {
pr_err("invalid type field in container file section header\n");
- goto free_table;
+ free_equiv_cpu_table();
+ return ret;
}
while (leftover) {
- mc_size = get_matching_microcode(cpu, ucode_ptr, leftover,
- new_rev, ¤t_size);
- if (mc_size) {
- mc_hdr = patch;
- new_mc = patch;
- new_rev = mc_hdr->patch_id;
- goto out_ok;
- }
-
- ucode_ptr += current_size;
- leftover -= current_size;
- }
+ crnt_size = verify_and_add_patch(cpu, fw, leftover);
+ if (crnt_size < 0)
+ return ret;
- if (!new_mc) {
- state = UCODE_NFOUND;
- goto free_table;
+ fw += crnt_size;
+ leftover -= crnt_size;
}
-out_ok:
- uci->mc = new_mc;
- state = UCODE_OK;
- pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n",
- cpu, uci->cpu_sig.rev, new_rev);
-
-free_table:
- free_equiv_cpu_table();
-
-out:
- return state;
+ return UCODE_OK;
}
/*
*
* This legacy file is always smaller than 2K in size.
*
- * Starting at family 15h they are in family specific firmware files:
+ * Beginning with family 15h, they are in family-specific firmware files:
*
* amd-ucode/microcode_amd_fam15h.bin
* amd-ucode/microcode_amd_fam16h.bin
*
* These might be larger than 2K.
*/
-static enum ucode_state request_microcode_amd(int cpu, struct device *device)
+static enum ucode_state request_microcode_amd(int cpu, struct device *device,
+ bool refresh_fw)
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
- const struct firmware *fw;
- enum ucode_state ret = UCODE_NFOUND;
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ enum ucode_state ret = UCODE_NFOUND;
+ const struct firmware *fw;
+
+ /* reload ucode container only on the boot cpu */
+ if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+ return UCODE_OK;
if (c->x86 >= 0x15)
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
goto fw_release;
}
- ret = generic_load_microcode(cpu, fw->data, fw->size);
+ /* free old equiv table */
+ free_equiv_cpu_table();
+
+ ret = load_microcode_amd(cpu, fw->data, fw->size);
+ if (ret != UCODE_OK)
+ cleanup();
-fw_release:
+ fw_release:
release_firmware(fw);
-out:
+ out:
return ret;
}
return NULL;
}
- patch = (void *)get_zeroed_page(GFP_KERNEL);
- if (!patch)
- return NULL;
-
return µcode_amd_ops;
}
void __exit exit_amd_microcode(void)
{
- free_page((unsigned long)patch);
+ cleanup();
}
if (do_microcode_update(buf, len) == 0)
ret = (ssize_t)len;
+ if (ret > 0)
+ perf_check_microcode();
+
mutex_unlock(µcode_mutex);
put_online_cpus();
static int reload_for_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ enum ucode_state ustate;
int err = 0;
- if (uci->valid) {
- enum ucode_state ustate;
-
- ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev);
- if (ustate == UCODE_OK)
- apply_microcode_on_target(cpu);
- else
- if (ustate == UCODE_ERROR)
- err = -EINVAL;
- }
+ if (!uci->valid)
+ return err;
+ ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, true);
+ if (ustate == UCODE_OK)
+ apply_microcode_on_target(cpu);
+ else
+ if (ustate == UCODE_ERROR)
+ err = -EINVAL;
return err;
}
static enum ucode_state microcode_resume_cpu(int cpu)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
- if (!uci->mc)
- return UCODE_NFOUND;
-
pr_debug("CPU%d updated upon resume\n", cpu);
- apply_microcode_on_target(cpu);
+
+ if (apply_microcode_on_target(cpu))
+ return UCODE_ERROR;
return UCODE_OK;
}
-static enum ucode_state microcode_init_cpu(int cpu)
+static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
{
enum ucode_state ustate;
if (system_state != SYSTEM_RUNNING)
return UCODE_NFOUND;
- ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev);
+ ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev,
+ refresh_fw);
if (ustate == UCODE_OK) {
pr_debug("CPU%d updated upon init\n", cpu);
static enum ucode_state microcode_update_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- enum ucode_state ustate;
if (uci->valid)
- ustate = microcode_resume_cpu(cpu);
- else
- ustate = microcode_init_cpu(cpu);
+ return microcode_resume_cpu(cpu);
- return ustate;
+ return microcode_init_cpu(cpu, false);
}
static int mc_device_add(struct device *dev, struct subsys_interface *sif)
if (err)
return err;
- if (microcode_init_cpu(cpu) == UCODE_ERROR)
+ if (microcode_init_cpu(cpu, true) == UCODE_ERROR)
return -EINVAL;
return err;
struct device *dev;
dev = get_cpu_device(cpu);
- switch (action) {
+
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
microcode_update_cpu(cpu);
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
pr_debug("CPU%d added\n", cpu);
+ /*
+ * "break" is missing on purpose here because we want to fall
+ * through in order to create the sysfs group.
+ */
+
+ case CPU_DOWN_FAILED:
if (sysfs_create_group(&dev->kobj, &mc_attr_group))
pr_err("Failed to create group for CPU%d\n", cpu);
break;
+
case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
/* Suspend is in progress, only remove the interface */
sysfs_remove_group(&dev->kobj, &mc_attr_group);
pr_debug("CPU%d removed\n", cpu);
break;
/*
+ * case CPU_DEAD:
+ *
* When a CPU goes offline, don't free up or invalidate the copy of
* the microcode in kernel memory, so that we can reuse it when the
* CPU comes back online without unnecessarily requesting the userspace
* for it again.
*/
- case CPU_UP_CANCELED_FROZEN:
- /* The CPU refused to come up during a system resume */
- microcode_fini_cpu(cpu);
- break;
}
+
+ /* The CPU refused to come up during a system resume */
+ if (action == CPU_UP_CANCELED_FROZEN)
+ microcode_fini_cpu(cpu);
+
return NOTIFY_OK;
}
return 0;
}
-static enum ucode_state request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device,
+ bool refresh_fw)
{
char name[30];
struct cpuinfo_x86 *c = &cpu_data(cpu);
--- /dev/null
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <linux/stddef.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_X86_32
+#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX
+#else
+#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX
+#endif
+
+#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
+
+static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
+ PT_REGS_OFFSET(PERF_REG_X86_AX, ax),
+ PT_REGS_OFFSET(PERF_REG_X86_BX, bx),
+ PT_REGS_OFFSET(PERF_REG_X86_CX, cx),
+ PT_REGS_OFFSET(PERF_REG_X86_DX, dx),
+ PT_REGS_OFFSET(PERF_REG_X86_SI, si),
+ PT_REGS_OFFSET(PERF_REG_X86_DI, di),
+ PT_REGS_OFFSET(PERF_REG_X86_BP, bp),
+ PT_REGS_OFFSET(PERF_REG_X86_SP, sp),
+ PT_REGS_OFFSET(PERF_REG_X86_IP, ip),
+ PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags),
+ PT_REGS_OFFSET(PERF_REG_X86_CS, cs),
+ PT_REGS_OFFSET(PERF_REG_X86_SS, ss),
+#ifdef CONFIG_X86_32
+ PT_REGS_OFFSET(PERF_REG_X86_DS, ds),
+ PT_REGS_OFFSET(PERF_REG_X86_ES, es),
+ PT_REGS_OFFSET(PERF_REG_X86_FS, fs),
+ PT_REGS_OFFSET(PERF_REG_X86_GS, gs),
+#else
+ /*
+ * The pt_regs struct does not store
+ * ds, es, fs, gs in 64 bit mode.
+ */
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+#endif
+#ifdef CONFIG_X86_64
+ PT_REGS_OFFSET(PERF_REG_X86_R8, r8),
+ PT_REGS_OFFSET(PERF_REG_X86_R9, r9),
+ PT_REGS_OFFSET(PERF_REG_X86_R10, r10),
+ PT_REGS_OFFSET(PERF_REG_X86_R11, r11),
+ PT_REGS_OFFSET(PERF_REG_X86_R12, r12),
+ PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
+ PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
+ PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
+#endif
+};
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ if (WARN_ON_ONCE(idx > ARRAY_SIZE(pt_regs_offset)))
+ return 0;
+
+ return regs_get_register(regs, pt_regs_offset[idx]);
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
+
+#ifdef CONFIG_X86_32
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_32;
+}
+#else /* CONFIG_X86_64 */
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ if (mask & REG_NOSUPPORT)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ if (test_tsk_thread_flag(task, TIF_IA32))
+ return PERF_SAMPLE_REGS_ABI_32;
+ else
+ return PERF_SAMPLE_REGS_ABI_64;
+}
+#endif /* CONFIG_X86_32 */
unsigned long boot_error = 0;
int timeout;
- alternatives_smp_switch(1);
+ /* Just in case we booted with a single CPU. */
+ alternatives_enable_smp();
idle->thread.sp = (unsigned long) (((struct pt_regs *)
(THREAD_SIZE + task_stack_page(idle))) - 1);
preempt_enable();
}
-void arch_disable_nonboot_cpus_begin(void)
-{
- /*
- * Avoid the smp alternatives switch during the disable_nonboot_cpus().
- * In the suspend path, we will be back in the SMP mode shortly anyways.
- */
- skip_smp_alternatives = true;
-}
-
-void arch_disable_nonboot_cpus_end(void)
-{
- skip_smp_alternatives = false;
-}
-
void arch_enable_nonboot_cpus_begin(void)
{
set_mtrr_aps_delayed_init();
if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
if (system_state == SYSTEM_RUNNING)
pr_info("CPU %u is now offline\n", cpu);
-
- if (1 == num_online_cpus())
- alternatives_smp_switch(0);
return;
}
msleep(100);
#include <asm/ftrace.h>
#ifdef CONFIG_FUNCTION_TRACER
-/* mcount is defined in assembly */
+/* mcount and __fentry__ are defined in assembly */
+#ifdef CC_USING_FENTRY
+EXPORT_SYMBOL(__fentry__);
+#else
EXPORT_SYMBOL(mcount);
#endif
+#endif
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
return rc;
if (num_online_cpus() == 1)
- alternatives_smp_switch(1);
+ /* Just in case we booted with a single CPU. */
+ alternatives_enable_smp();
rc = xen_smp_intr_init(cpu);
if (rc)
unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
-
- if (num_online_cpus() == 1)
- alternatives_smp_switch(0);
}
static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
*/
#include <linux/slab.h>
+#include <linux/smpboot.h>
#include "ehca_classes.h"
#include "ehca_irq.h"
ehca_process_eq((struct ehca_shca*)data, 1);
}
-static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
+static int find_next_online_cpu(struct ehca_comp_pool *pool)
{
int cpu;
unsigned long flags;
ehca_dmp(cpu_online_mask, cpumask_size(), "");
spin_lock_irqsave(&pool->last_cpu_lock, flags);
- cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
- if (cpu >= nr_cpu_ids)
- cpu = cpumask_first(cpu_online_mask);
- pool->last_cpu = cpu;
+ do {
+ cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
+ if (cpu >= nr_cpu_ids)
+ cpu = cpumask_first(cpu_online_mask);
+ pool->last_cpu = cpu;
+ } while (!per_cpu_ptr(pool->cpu_comp_tasks, cpu)->active);
spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
return cpu;
}
static void __queue_comp_task(struct ehca_cq *__cq,
- struct ehca_cpu_comp_task *cct)
+ struct ehca_cpu_comp_task *cct,
+ struct task_struct *thread)
{
unsigned long flags;
__cq->nr_callbacks++;
list_add_tail(&__cq->entry, &cct->cq_list);
cct->cq_jobs++;
- wake_up(&cct->wait_queue);
+ wake_up_process(thread);
} else
__cq->nr_callbacks++;
{
int cpu_id;
struct ehca_cpu_comp_task *cct;
+ struct task_struct *thread;
int cq_jobs;
unsigned long flags;
BUG_ON(!cpu_online(cpu_id));
cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
- BUG_ON(!cct);
+ thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+ BUG_ON(!cct || !thread);
spin_lock_irqsave(&cct->task_lock, flags);
cq_jobs = cct->cq_jobs;
if (cq_jobs > 0) {
cpu_id = find_next_online_cpu(pool);
cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu_id);
- BUG_ON(!cct);
+ thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu_id);
+ BUG_ON(!cct || !thread);
}
-
- __queue_comp_task(__cq, cct);
+ __queue_comp_task(__cq, cct, thread);
}
static void run_comp_task(struct ehca_cpu_comp_task *cct)
{
struct ehca_cq *cq;
- unsigned long flags;
-
- spin_lock_irqsave(&cct->task_lock, flags);
while (!list_empty(&cct->cq_list)) {
cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
- spin_unlock_irqrestore(&cct->task_lock, flags);
+ spin_unlock_irq(&cct->task_lock);
comp_event_callback(cq);
if (atomic_dec_and_test(&cq->nr_events))
wake_up(&cq->wait_completion);
- spin_lock_irqsave(&cct->task_lock, flags);
+ spin_lock_irq(&cct->task_lock);
spin_lock(&cq->task_lock);
cq->nr_callbacks--;
if (!cq->nr_callbacks) {
}
spin_unlock(&cq->task_lock);
}
-
- spin_unlock_irqrestore(&cct->task_lock, flags);
}
-static int comp_task(void *__cct)
+static void comp_task_park(unsigned int cpu)
{
- struct ehca_cpu_comp_task *cct = __cct;
- int cql_empty;
- DECLARE_WAITQUEUE(wait, current);
-
- set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
- add_wait_queue(&cct->wait_queue, &wait);
-
- spin_lock_irq(&cct->task_lock);
- cql_empty = list_empty(&cct->cq_list);
- spin_unlock_irq(&cct->task_lock);
- if (cql_empty)
- schedule();
- else
- __set_current_state(TASK_RUNNING);
-
- remove_wait_queue(&cct->wait_queue, &wait);
+ struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+ struct ehca_cpu_comp_task *target;
+ struct task_struct *thread;
+ struct ehca_cq *cq, *tmp;
+ LIST_HEAD(list);
- spin_lock_irq(&cct->task_lock);
- cql_empty = list_empty(&cct->cq_list);
- spin_unlock_irq(&cct->task_lock);
- if (!cql_empty)
- run_comp_task(__cct);
+ spin_lock_irq(&cct->task_lock);
+ cct->cq_jobs = 0;
+ cct->active = 0;
+ list_splice_init(&cct->cq_list, &list);
+ spin_unlock_irq(&cct->task_lock);
- set_current_state(TASK_INTERRUPTIBLE);
+ cpu = find_next_online_cpu(pool);
+ target = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+ thread = *per_cpu_ptr(pool->cpu_comp_threads, cpu);
+ spin_lock_irq(&target->task_lock);
+ list_for_each_entry_safe(cq, tmp, &list, entry) {
+ list_del(&cq->entry);
+ __queue_comp_task(cq, target, thread);
}
- __set_current_state(TASK_RUNNING);
-
- return 0;
-}
-
-static struct task_struct *create_comp_task(struct ehca_comp_pool *pool,
- int cpu)
-{
- struct ehca_cpu_comp_task *cct;
-
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- spin_lock_init(&cct->task_lock);
- INIT_LIST_HEAD(&cct->cq_list);
- init_waitqueue_head(&cct->wait_queue);
- cct->task = kthread_create_on_node(comp_task, cct, cpu_to_node(cpu),
- "ehca_comp/%d", cpu);
-
- return cct->task;
+ spin_unlock_irq(&target->task_lock);
}
-static void destroy_comp_task(struct ehca_comp_pool *pool,
- int cpu)
+static void comp_task_stop(unsigned int cpu, bool online)
{
- struct ehca_cpu_comp_task *cct;
- struct task_struct *task;
- unsigned long flags_cct;
-
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-
- spin_lock_irqsave(&cct->task_lock, flags_cct);
+ struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- task = cct->task;
- cct->task = NULL;
+ spin_lock_irq(&cct->task_lock);
cct->cq_jobs = 0;
-
- spin_unlock_irqrestore(&cct->task_lock, flags_cct);
-
- if (task)
- kthread_stop(task);
+ cct->active = 0;
+ WARN_ON(!list_empty(&cct->cq_list));
+ spin_unlock_irq(&cct->task_lock);
}
-static void __cpuinit take_over_work(struct ehca_comp_pool *pool, int cpu)
+static int comp_task_should_run(unsigned int cpu)
{
struct ehca_cpu_comp_task *cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- LIST_HEAD(list);
- struct ehca_cq *cq;
- unsigned long flags_cct;
-
- spin_lock_irqsave(&cct->task_lock, flags_cct);
-
- list_splice_init(&cct->cq_list, &list);
-
- while (!list_empty(&list)) {
- cq = list_entry(cct->cq_list.next, struct ehca_cq, entry);
-
- list_del(&cq->entry);
- __queue_comp_task(cq, this_cpu_ptr(pool->cpu_comp_tasks));
- }
-
- spin_unlock_irqrestore(&cct->task_lock, flags_cct);
+ return cct->cq_jobs;
}
-static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static void comp_task(unsigned int cpu)
{
- unsigned int cpu = (unsigned long)hcpu;
- struct ehca_cpu_comp_task *cct;
+ struct ehca_cpu_comp_task *cct = this_cpu_ptr(pool->cpu_comp_tasks);
+ int cql_empty;
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_PREPARE)", cpu);
- if (!create_comp_task(pool, cpu)) {
- ehca_gen_err("Can't create comp_task for cpu: %x", cpu);
- return notifier_from_errno(-ENOMEM);
- }
- break;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- kthread_bind(cct->task, cpumask_any(cpu_online_mask));
- destroy_comp_task(pool, cpu);
- break;
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_ONLINE)", cpu);
- cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
- kthread_bind(cct->task, cpu);
- wake_up_process(cct->task);
- break;
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_DOWN_PREPARE)", cpu);
- break;
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_DOWN_FAILED)", cpu);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- ehca_gen_dbg("CPU: %x (CPU_DEAD)", cpu);
- destroy_comp_task(pool, cpu);
- take_over_work(pool, cpu);
- break;
+ spin_lock_irq(&cct->task_lock);
+ cql_empty = list_empty(&cct->cq_list);
+ if (!cql_empty) {
+ __set_current_state(TASK_RUNNING);
+ run_comp_task(cct);
}
-
- return NOTIFY_OK;
+ spin_unlock_irq(&cct->task_lock);
}
-static struct notifier_block comp_pool_callback_nb __cpuinitdata = {
- .notifier_call = comp_pool_callback,
- .priority = 0,
+static struct smp_hotplug_thread comp_pool_threads = {
+ .thread_should_run = comp_task_should_run,
+ .thread_fn = comp_task,
+ .thread_comm = "ehca_comp/%u",
+ .cleanup = comp_task_stop,
+ .park = comp_task_park,
};
int ehca_create_comp_pool(void)
{
- int cpu;
- struct task_struct *task;
+ int cpu, ret = -ENOMEM;
if (!ehca_scaling_code)
return 0;
pool->last_cpu = cpumask_any(cpu_online_mask);
pool->cpu_comp_tasks = alloc_percpu(struct ehca_cpu_comp_task);
- if (pool->cpu_comp_tasks == NULL) {
- kfree(pool);
- return -EINVAL;
- }
+ if (!pool->cpu_comp_tasks)
+ goto out_pool;
- for_each_online_cpu(cpu) {
- task = create_comp_task(pool, cpu);
- if (task) {
- kthread_bind(task, cpu);
- wake_up_process(task);
- }
+ pool->cpu_comp_threads = alloc_percpu(struct task_struct *);
+ if (!pool->cpu_comp_threads)
+ goto out_tasks;
+
+ for_each_present_cpu(cpu) {
+ struct ehca_cpu_comp_task *cct;
+
+ cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
+ spin_lock_init(&cct->task_lock);
+ INIT_LIST_HEAD(&cct->cq_list);
}
- register_hotcpu_notifier(&comp_pool_callback_nb);
+ comp_pool_threads.store = pool->cpu_comp_threads;
+ ret = smpboot_register_percpu_thread(&comp_pool_threads);
+ if (ret)
+ goto out_threads;
- printk(KERN_INFO "eHCA scaling code enabled\n");
+ pr_info("eHCA scaling code enabled\n");
+ return ret;
- return 0;
+out_threads:
+ free_percpu(pool->cpu_comp_threads);
+out_tasks:
+ free_percpu(pool->cpu_comp_tasks);
+out_pool:
+ kfree(pool);
+ return ret;
}
void ehca_destroy_comp_pool(void)
{
- int i;
-
if (!ehca_scaling_code)
return;
- unregister_hotcpu_notifier(&comp_pool_callback_nb);
-
- for_each_online_cpu(i)
- destroy_comp_task(pool, i);
+ smpboot_unregister_percpu_thread(&comp_pool_threads);
+ free_percpu(pool->cpu_comp_threads);
free_percpu(pool->cpu_comp_tasks);
kfree(pool);
}
void ehca_process_eq(struct ehca_shca *shca, int is_irq);
struct ehca_cpu_comp_task {
- wait_queue_head_t wait_queue;
struct list_head cq_list;
- struct task_struct *task;
spinlock_t task_lock;
int cq_jobs;
+ int active;
};
struct ehca_comp_pool {
- struct ehca_cpu_comp_task *cpu_comp_tasks;
+ struct ehca_cpu_comp_task __percpu *cpu_comp_tasks;
+ struct task_struct * __percpu *cpu_comp_threads;
int last_cpu;
spinlock_t last_cpu_lock;
};
#include <linux/kallsyms.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
+#include <linux/ptrace.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <asm/ftrace.h>
+/*
+ * If the arch supports passing the variable contents of
+ * function_trace_op as the third parameter back from the
+ * mcount call, then the arch should define this as 1.
+ */
+#ifndef ARCH_SUPPORTS_FTRACE_OPS
+#define ARCH_SUPPORTS_FTRACE_OPS 0
+#endif
+
+/*
+ * If the arch's mcount caller does not support all of ftrace's
+ * features, then it must call an indirect function that
+ * does. Or at least does enough to prevent any unwelcomed side effects.
+ */
+#if !defined(CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST) || \
+ !ARCH_SUPPORTS_FTRACE_OPS
+# define FTRACE_FORCE_LIST_FUNC 1
+#else
+# define FTRACE_FORCE_LIST_FUNC 0
+#endif
+
+
struct module;
struct ftrace_hash;
void __user *buffer, size_t *lenp,
loff_t *ppos);
-typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
+struct ftrace_ops;
+
+typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs);
/*
* FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
* could be controled by following calls:
* ftrace_function_local_enable
* ftrace_function_local_disable
+ * SAVE_REGS - The ftrace_ops wants regs saved at each function called
+ * and passed to the callback. If this flag is set, but the
+ * architecture does not support passing regs
+ * (ARCH_SUPPORTS_FTRACE_SAVE_REGS is not defined), then the
+ * ftrace_ops will fail to register, unless the next flag
+ * is set.
+ * SAVE_REGS_IF_SUPPORTED - This is the same as SAVE_REGS, but if the
+ * handler can handle an arch that does not save regs
+ * (the handler tests if regs == NULL), then it can set
+ * this flag instead. It will not fail registering the ftrace_ops
+ * but, the regs field will be NULL if the arch does not support
+ * passing regs to the handler.
+ * Note, if this flag is set, the SAVE_REGS flag will automatically
+ * get set upon registering the ftrace_ops, if the arch supports it.
+ * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure
+ * that the call back has its own recursion protection. If it does
+ * not set this, then the ftrace infrastructure will add recursion
+ * protection for the caller.
*/
enum {
- FTRACE_OPS_FL_ENABLED = 1 << 0,
- FTRACE_OPS_FL_GLOBAL = 1 << 1,
- FTRACE_OPS_FL_DYNAMIC = 1 << 2,
- FTRACE_OPS_FL_CONTROL = 1 << 3,
+ FTRACE_OPS_FL_ENABLED = 1 << 0,
+ FTRACE_OPS_FL_GLOBAL = 1 << 1,
+ FTRACE_OPS_FL_DYNAMIC = 1 << 2,
+ FTRACE_OPS_FL_CONTROL = 1 << 3,
+ FTRACE_OPS_FL_SAVE_REGS = 1 << 4,
+ FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 5,
+ FTRACE_OPS_FL_RECURSION_SAFE = 1 << 6,
};
struct ftrace_ops {
return *this_cpu_ptr(ops->disabled);
}
-extern void ftrace_stub(unsigned long a0, unsigned long a1);
+extern void ftrace_stub(unsigned long a0, unsigned long a1,
+ struct ftrace_ops *op, struct pt_regs *regs);
#else /* !CONFIG_FUNCTION_TRACER */
/*
*/
#define register_ftrace_function(ops) ({ 0; })
#define unregister_ftrace_function(ops) ({ 0; })
+static inline int ftrace_nr_registered_ops(void)
+{
+ return 0;
+}
static inline void clear_ftrace_function(void) { }
static inline void ftrace_kill(void) { }
static inline void ftrace_stop(void) { }
extern int ftrace_text_reserved(void *start, void *end);
+extern int ftrace_nr_registered_ops(void);
+
+/*
+ * The dyn_ftrace record's flags field is split into two parts.
+ * the first part which is '0-FTRACE_REF_MAX' is a counter of
+ * the number of callbacks that have registered the function that
+ * the dyn_ftrace descriptor represents.
+ *
+ * The second part is a mask:
+ * ENABLED - the function is being traced
+ * REGS - the record wants the function to save regs
+ * REGS_EN - the function is set up to save regs.
+ *
+ * When a new ftrace_ops is registered and wants a function to save
+ * pt_regs, the rec->flag REGS is set. When the function has been
+ * set up to save regs, the REG_EN flag is set. Once a function
+ * starts saving regs it will do so until all ftrace_ops are removed
+ * from tracing that function.
+ */
enum {
- FTRACE_FL_ENABLED = (1 << 30),
+ FTRACE_FL_ENABLED = (1UL << 29),
+ FTRACE_FL_REGS = (1UL << 30),
+ FTRACE_FL_REGS_EN = (1UL << 31)
};
-#define FTRACE_FL_MASK (0x3UL << 30)
-#define FTRACE_REF_MAX ((1 << 30) - 1)
+#define FTRACE_FL_MASK (0x7UL << 29)
+#define FTRACE_REF_MAX ((1UL << 29) - 1)
struct dyn_ftrace {
union {
};
int ftrace_force_update(void);
+int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
+ int remove, int reset);
int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset);
int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
FTRACE_STOP_FUNC_RET = (1 << 4),
};
+/*
+ * The FTRACE_UPDATE_* enum is used to pass information back
+ * from the ftrace_update_record() and ftrace_test_record()
+ * functions. These are called by the code update routines
+ * to find out what is to be done for a given function.
+ *
+ * IGNORE - The function is already what we want it to be
+ * MAKE_CALL - Start tracing the function
+ * MODIFY_CALL - Stop saving regs for the function
+ * MODIFY_CALL_REGS - Start saving regs for the function
+ * MAKE_NOP - Stop tracing the function
+ */
enum {
FTRACE_UPDATE_IGNORE,
FTRACE_UPDATE_MAKE_CALL,
+ FTRACE_UPDATE_MODIFY_CALL,
+ FTRACE_UPDATE_MODIFY_CALL_REGS,
FTRACE_UPDATE_MAKE_NOP,
};
extern void ftrace_replace_code(int enable);
extern int ftrace_update_ftrace_func(ftrace_func_t func);
extern void ftrace_caller(void);
+extern void ftrace_regs_caller(void);
extern void ftrace_call(void);
+extern void ftrace_regs_call(void);
extern void mcount_call(void);
void ftrace_modify_all_code(int command);
#ifndef FTRACE_ADDR
#define FTRACE_ADDR ((unsigned long)ftrace_caller)
#endif
+
+#ifndef FTRACE_REGS_ADDR
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+# define FTRACE_REGS_ADDR ((unsigned long)ftrace_regs_caller)
+#else
+# define FTRACE_REGS_ADDR FTRACE_ADDR
+#endif
+#endif
+
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
extern void ftrace_graph_caller(void);
extern int ftrace_enable_ftrace_graph_caller(void);
*/
extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+/**
+ * ftrace_modify_call - convert from one addr to another (no nop)
+ * @rec: the mcount call site record
+ * @old_addr: the address expected to be currently called to
+ * @addr: the address to change to
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch. The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should be a caller to @old_addr
+ *
+ * Return must be:
+ * 0 on success
+ * -EFAULT on error reading the location
+ * -EINVAL on a failed compare of the contents
+ * -EPERM on error writing to the location
+ * Any other value will be considered a failure.
+ */
+extern int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr);
+#else
+/* Should never be called */
+static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ return -EINVAL;
+}
+#endif
+
/* May be defined in arch */
extern int ftrace_arch_read_dyn_info(char *buf, int size);
extern void ftrace_disable_daemon(void);
extern void ftrace_enable_daemon(void);
-#else
+#else /* CONFIG_DYNAMIC_FTRACE */
static inline int skip_trace(unsigned long ip) { return 0; }
static inline int ftrace_force_update(void) { return 0; }
static inline void ftrace_disable_daemon(void) { }
{
return 0;
}
+static inline unsigned long ftrace_location(unsigned long ip)
+{
+ return 0;
+}
/*
* Again users of functions that have ftrace_ops may not
*/
#define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; })
#define ftrace_set_early_filter(ops, buf, enable) do { } while (0)
+#define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; })
#define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; })
#define ftrace_free_filter(ops) do { } while (0)
extern void account_steal_ticks(unsigned long ticks);
extern void account_idle_ticks(unsigned long ticks);
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void account_switch_vtime(struct task_struct *prev);
+#else
+static inline void account_switch_vtime(struct task_struct *prev) { }
+#endif
+
#endif /* _LINUX_KERNEL_STAT_H */
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>
+#include <linux/ftrace.h>
#ifdef CONFIG_KPROBES
#include <asm/kprobes.h>
#define KPROBE_REENTER 0x00000004
#define KPROBE_HIT_SSDONE 0x00000008
+/*
+ * If function tracer is enabled and the arch supports full
+ * passing of pt_regs to function tracing, then kprobes can
+ * optimize on top of function tracing.
+ */
+#if defined(CONFIG_FUNCTION_TRACER) && defined(ARCH_SUPPORTS_FTRACE_SAVE_REGS) \
+ && defined(ARCH_SUPPORTS_KPROBES_ON_FTRACE)
+# define KPROBES_CAN_USE_FTRACE
+#endif
+
/* Attach to insert probes on any functions which should be ignored*/
#define __kprobes __attribute__((__section__(".kprobes.text")))
+
#else /* CONFIG_KPROBES */
typedef int kprobe_opcode_t;
struct arch_specific_insn {
int dummy;
};
#define __kprobes
+
#endif /* CONFIG_KPROBES */
struct kprobe;
* NOTE:
* this flag is only for optimized_kprobe.
*/
+#define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */
/* Has this kprobe gone ? */
static inline int kprobe_gone(struct kprobe *p)
{
return p->flags & KPROBE_FLAG_OPTIMIZED;
}
+
+/* Is this kprobe uses ftrace ? */
+static inline int kprobe_ftrace(struct kprobe *p)
+{
+ return p->flags & KPROBE_FLAG_FTRACE;
+}
+
/*
* Special probe type that uses setjmp-longjmp type tricks to resume
* execution at a specified entry with a matching prototype corresponding
#endif
#endif /* CONFIG_OPTPROBES */
+#ifdef KPROBES_CAN_USE_FTRACE
+extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct pt_regs *regs);
+extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
+#endif
+
/* Get the kprobe at this addr (if any) - called with preemption disabled */
struct kprobe *get_kprobe(void *addr);
kthread_create_on_node(threadfn, data, -1, namefmt, ##arg)
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+ void *data,
+ unsigned int cpu,
+ const char *namefmt);
+
/**
* kthread_run - create and wake a thread.
* @threadfn: the function to run until signal_pending(current).
void kthread_bind(struct task_struct *k, unsigned int cpu);
int kthread_stop(struct task_struct *k);
-int kthread_should_stop(void);
+bool kthread_should_stop(void);
+bool kthread_should_park(void);
bool kthread_freezable_should_stop(bool *was_frozen);
void *kthread_data(struct task_struct *k);
+int kthread_park(struct task_struct *k);
+void kthread_unpark(struct task_struct *k);
+void kthread_parkme(void);
int kthreadd(void *unused);
extern struct task_struct *kthreadd_task;
PERF_SAMPLE_STREAM_ID = 1U << 9,
PERF_SAMPLE_RAW = 1U << 10,
PERF_SAMPLE_BRANCH_STACK = 1U << 11,
+ PERF_SAMPLE_REGS_USER = 1U << 12,
+ PERF_SAMPLE_STACK_USER = 1U << 13,
- PERF_SAMPLE_MAX = 1U << 12, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 14, /* non-ABI */
};
/*
PERF_SAMPLE_BRANCH_KERNEL|\
PERF_SAMPLE_BRANCH_HV)
+/*
+ * Values to determine ABI of the registers dump.
+ */
+enum perf_sample_regs_abi {
+ PERF_SAMPLE_REGS_ABI_NONE = 0,
+ PERF_SAMPLE_REGS_ABI_32 = 1,
+ PERF_SAMPLE_REGS_ABI_64 = 2,
+};
+
/*
* The format of the data returned by read() on a perf event fd,
* as specified by attr.read_format:
#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */
#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */
#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */
+#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */
+ /* add: sample_stack_user */
/*
* Hardware event_id to monitor via a performance monitoring event:
exclude_host : 1, /* don't count in host */
exclude_guest : 1, /* don't count in guest */
- __reserved_1 : 43;
+ exclude_callchain_kernel : 1, /* exclude kernel callchains */
+ exclude_callchain_user : 1, /* exclude user callchains */
+
+ __reserved_1 : 41;
union {
__u32 wakeup_events; /* wakeup every n events */
__u64 bp_len;
__u64 config2; /* extension of config1 */
};
- __u64 branch_sample_type; /* enum branch_sample_type */
+ __u64 branch_sample_type; /* enum perf_branch_sample_type */
+
+ /*
+ * Defines set of user regs to dump on samples.
+ * See asm/perf_regs.h for details.
+ */
+ __u64 sample_regs_user;
+
+ /*
+ * Defines size of the user stack to dump on samples.
+ */
+ __u32 sample_stack_user;
+
+ /* Align to u64. */
+ __u32 __reserved_2;
};
/*
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
+ *
+ * { u64 abi; # enum perf_sample_regs_abi
+ * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER
+ *
+ * { u64 size;
+ * char data[size];
+ * u64 dyn_size; } && PERF_SAMPLE_STACK_USER
* };
*/
PERF_RECORD_SAMPLE = 9,
#include <linux/static_key.h>
#include <linux/atomic.h>
#include <linux/sysfs.h>
+#include <linux/perf_regs.h>
#include <asm/local.h>
struct perf_callchain_entry {
struct perf_branch_entry entries[0];
};
+struct perf_regs_user {
+ __u64 abi;
+ struct pt_regs *regs;
+};
+
struct task_struct;
/*
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
+ struct perf_regs_user regs_user;
+ u64 stack_user_size;
};
static inline void perf_sample_data_init(struct perf_sample_data *data,
data->addr = addr;
data->raw = NULL;
data->br_stack = NULL;
- data->period = period;
+ data->period = period;
+ data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
+ data->regs_user.regs = NULL;
+ data->stack_user_size = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
extern int perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size);
extern void perf_output_end(struct perf_output_handle *handle);
-extern void perf_output_copy(struct perf_output_handle *handle,
+extern unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len);
+extern unsigned int perf_output_skip(struct perf_output_handle *handle,
+ unsigned int len);
extern int perf_swevent_get_recursion_context(void);
extern void perf_swevent_put_recursion_context(int rctx);
extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
+extern int __perf_event_disable(void *info);
extern void perf_event_task_tick(void);
#else
static inline void
static inline void perf_swevent_put_recursion_context(int rctx) { }
static inline void perf_event_enable(struct perf_event *event) { }
static inline void perf_event_disable(struct perf_event *event) { }
+static inline int __perf_event_disable(void *info) { return -1; }
static inline void perf_event_task_tick(void) { }
#endif
--- /dev/null
+#ifndef _LINUX_PERF_REGS_H
+#define _LINUX_PERF_REGS_H
+
+#ifdef CONFIG_HAVE_PERF_REGS
+#include <asm/perf_regs.h>
+u64 perf_reg_value(struct pt_regs *regs, int idx);
+int perf_reg_validate(u64 mask);
+u64 perf_reg_abi(struct task_struct *task);
+#else
+static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ return 0;
+}
+
+static inline int perf_reg_validate(u64 mask)
+{
+ return mask ? -ENOSYS : 0;
+}
+
+static inline u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_NONE;
+}
+#endif /* CONFIG_HAVE_PERF_REGS */
+#endif /* _LINUX_PERF_REGS_H */
#define MMF_VM_HUGEPAGE 17 /* set when VM_HUGEPAGE is set on vma */
#define MMF_EXE_FILE_CHANGED 18 /* see prctl_set_mm_exe_file() */
+#define MMF_HAS_UPROBES 19 /* might have uprobes */
+
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
struct sighand_struct {
#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
-#define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */
#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
--- /dev/null
+#ifndef _LINUX_SMPBOOT_H
+#define _LINUX_SMPBOOT_H
+
+#include <linux/types.h>
+
+struct task_struct;
+/* Cookie handed to the thread_fn*/
+struct smpboot_thread_data;
+
+/**
+ * struct smp_hotplug_thread - CPU hotplug related thread descriptor
+ * @store: Pointer to per cpu storage for the task pointers
+ * @list: List head for core management
+ * @thread_should_run: Check whether the thread should run or not. Called with
+ * preemption disabled.
+ * @thread_fn: The associated thread function
+ * @setup: Optional setup function, called when the thread gets
+ * operational the first time
+ * @cleanup: Optional cleanup function, called when the thread
+ * should stop (module exit)
+ * @park: Optional park function, called when the thread is
+ * parked (cpu offline)
+ * @unpark: Optional unpark function, called when the thread is
+ * unparked (cpu online)
+ * @thread_comm: The base name of the thread
+ */
+struct smp_hotplug_thread {
+ struct task_struct __percpu **store;
+ struct list_head list;
+ int (*thread_should_run)(unsigned int cpu);
+ void (*thread_fn)(unsigned int cpu);
+ void (*setup)(unsigned int cpu);
+ void (*cleanup)(unsigned int cpu, bool online);
+ void (*park)(unsigned int cpu);
+ void (*unpark)(unsigned int cpu);
+ const char *thread_comm;
+};
+
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
+void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
+int smpboot_thread_schedule(void);
+
+#endif
#endif
/*
- * Note that all tvec_bases are 2 byte aligned and lower bit of
- * base in timer_list is guaranteed to be zero. Use the LSB to
- * indicate whether the timer is deferrable.
+ * Note that all tvec_bases are at least 4 byte aligned and lower two bits
+ * of base in timer_list is guaranteed to be zero. Use them for flags.
*
* A deferrable timer will work normally when the system is busy, but
* will not cause a CPU to come out of idle just to service it; instead,
* the timer will be serviced when the CPU eventually wakes up with a
* subsequent non-deferrable timer.
+ *
+ * An irqsafe timer is executed with IRQ disabled and it's safe to wait for
+ * the completion of the running instance from IRQ handlers, for example,
+ * by calling del_timer_sync().
+ *
+ * Note: The irq disabled callback execution is a special case for
+ * workqueue locking issues. It's not meant for executing random crap
+ * with interrupts disabled. Abuse is monitored!
*/
-#define TBASE_DEFERRABLE_FLAG (0x1)
+#define TIMER_DEFERRABLE 0x1LU
+#define TIMER_IRQSAFE 0x2LU
-#define TIMER_INITIALIZER(_function, _expires, _data) { \
+#define TIMER_FLAG_MASK 0x3LU
+
+#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \
.entry = { .prev = TIMER_ENTRY_STATIC }, \
.function = (_function), \
.expires = (_expires), \
.data = (_data), \
- .base = &boot_tvec_bases, \
+ .base = (void *)((unsigned long)&boot_tvec_bases + (_flags)), \
.slack = -1, \
__TIMER_LOCKDEP_MAP_INITIALIZER( \
__FILE__ ":" __stringify(__LINE__)) \
}
-#define TBASE_MAKE_DEFERRED(ptr) ((struct tvec_base *) \
- ((unsigned char *)(ptr) + TBASE_DEFERRABLE_FLAG))
+#define TIMER_INITIALIZER(_function, _expires, _data) \
+ __TIMER_INITIALIZER((_function), (_expires), (_data), 0)
-#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) {\
- .entry = { .prev = TIMER_ENTRY_STATIC }, \
- .function = (_function), \
- .expires = (_expires), \
- .data = (_data), \
- .base = TBASE_MAKE_DEFERRED(&boot_tvec_bases), \
- __TIMER_LOCKDEP_MAP_INITIALIZER( \
- __FILE__ ":" __stringify(__LINE__)) \
- }
+#define TIMER_DEFERRED_INITIALIZER(_function, _expires, _data) \
+ __TIMER_INITIALIZER((_function), (_expires), (_data), TIMER_DEFERRABLE)
#define DEFINE_TIMER(_name, _function, _expires, _data) \
struct timer_list _name = \
TIMER_INITIALIZER(_function, _expires, _data)
-void init_timer_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key);
-void init_timer_deferrable_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key);
+void init_timer_key(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key);
+
+#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
+extern void init_timer_on_stack_key(struct timer_list *timer,
+ unsigned int flags, const char *name,
+ struct lock_class_key *key);
+extern void destroy_timer_on_stack(struct timer_list *timer);
+#else
+static inline void destroy_timer_on_stack(struct timer_list *timer) { }
+static inline void init_timer_on_stack_key(struct timer_list *timer,
+ unsigned int flags, const char *name,
+ struct lock_class_key *key)
+{
+ init_timer_key(timer, flags, name, key);
+}
+#endif
#ifdef CONFIG_LOCKDEP
-#define init_timer(timer) \
+#define __init_timer(_timer, _flags) \
do { \
static struct lock_class_key __key; \
- init_timer_key((timer), #timer, &__key); \
+ init_timer_key((_timer), (_flags), #_timer, &__key); \
} while (0)
-#define init_timer_deferrable(timer) \
+#define __init_timer_on_stack(_timer, _flags) \
do { \
static struct lock_class_key __key; \
- init_timer_deferrable_key((timer), #timer, &__key); \
+ init_timer_on_stack_key((_timer), (_flags), #_timer, &__key); \
} while (0)
+#else
+#define __init_timer(_timer, _flags) \
+ init_timer_key((_timer), (_flags), NULL, NULL)
+#define __init_timer_on_stack(_timer, _flags) \
+ init_timer_on_stack_key((_timer), (_flags), NULL, NULL)
+#endif
+#define init_timer(timer) \
+ __init_timer((timer), 0)
+#define init_timer_deferrable(timer) \
+ __init_timer((timer), TIMER_DEFERRABLE)
#define init_timer_on_stack(timer) \
+ __init_timer_on_stack((timer), 0)
+
+#define __setup_timer(_timer, _fn, _data, _flags) \
do { \
- static struct lock_class_key __key; \
- init_timer_on_stack_key((timer), #timer, &__key); \
+ __init_timer((_timer), (_flags)); \
+ (_timer)->function = (_fn); \
+ (_timer)->data = (_data); \
} while (0)
-#define setup_timer(timer, fn, data) \
+#define __setup_timer_on_stack(_timer, _fn, _data, _flags) \
do { \
- static struct lock_class_key __key; \
- setup_timer_key((timer), #timer, &__key, (fn), (data));\
+ __init_timer_on_stack((_timer), (_flags)); \
+ (_timer)->function = (_fn); \
+ (_timer)->data = (_data); \
} while (0)
+#define setup_timer(timer, fn, data) \
+ __setup_timer((timer), (fn), (data), 0)
#define setup_timer_on_stack(timer, fn, data) \
- do { \
- static struct lock_class_key __key; \
- setup_timer_on_stack_key((timer), #timer, &__key, \
- (fn), (data)); \
- } while (0)
+ __setup_timer_on_stack((timer), (fn), (data), 0)
#define setup_deferrable_timer_on_stack(timer, fn, data) \
- do { \
- static struct lock_class_key __key; \
- setup_deferrable_timer_on_stack_key((timer), #timer, \
- &__key, (fn), \
- (data)); \
- } while (0)
-#else
-#define init_timer(timer)\
- init_timer_key((timer), NULL, NULL)
-#define init_timer_deferrable(timer)\
- init_timer_deferrable_key((timer), NULL, NULL)
-#define init_timer_on_stack(timer)\
- init_timer_on_stack_key((timer), NULL, NULL)
-#define setup_timer(timer, fn, data)\
- setup_timer_key((timer), NULL, NULL, (fn), (data))
-#define setup_timer_on_stack(timer, fn, data)\
- setup_timer_on_stack_key((timer), NULL, NULL, (fn), (data))
-#define setup_deferrable_timer_on_stack(timer, fn, data)\
- setup_deferrable_timer_on_stack_key((timer), NULL, NULL, (fn), (data))
-#endif
-
-#ifdef CONFIG_DEBUG_OBJECTS_TIMERS
-extern void init_timer_on_stack_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key);
-extern void destroy_timer_on_stack(struct timer_list *timer);
-#else
-static inline void destroy_timer_on_stack(struct timer_list *timer) { }
-static inline void init_timer_on_stack_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key)
-{
- init_timer_key(timer, name, key);
-}
-#endif
-
-static inline void setup_timer_key(struct timer_list * timer,
- const char *name,
- struct lock_class_key *key,
- void (*function)(unsigned long),
- unsigned long data)
-{
- timer->function = function;
- timer->data = data;
- init_timer_key(timer, name, key);
-}
-
-static inline void setup_timer_on_stack_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key,
- void (*function)(unsigned long),
- unsigned long data)
-{
- timer->function = function;
- timer->data = data;
- init_timer_on_stack_key(timer, name, key);
-}
-
-extern void setup_deferrable_timer_on_stack_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key,
- void (*function)(unsigned long),
- unsigned long data);
+ __setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE)
/**
* timer_pending - is a timer pending?
| 1*SD_BALANCE_FORK \
| 0*SD_BALANCE_WAKE \
| 1*SD_WAKE_AFFINE \
- | 0*SD_PREFER_LOCAL \
| 0*SD_SHARE_CPUPOWER \
| 1*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
| 1*SD_BALANCE_FORK \
| 0*SD_BALANCE_WAKE \
| 1*SD_WAKE_AFFINE \
- | 0*SD_PREFER_LOCAL \
| 0*SD_SHARE_CPUPOWER \
| 0*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
struct uprobes_state {
struct xol_area *xol_area;
- atomic_t count;
};
+
extern int __weak set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
-extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr, bool verify);
+extern int __weak set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
extern bool __weak is_swbp_insn(uprobe_opcode_t *insn);
extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
extern int uprobe_mmap(struct vm_area_struct *vma);
extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+extern void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm);
extern void uprobe_free_utask(struct task_struct *t);
extern void uprobe_copy_process(struct task_struct *t);
extern unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs);
extern bool uprobe_deny_signal(void);
extern bool __weak arch_uprobe_skip_sstep(struct arch_uprobe *aup, struct pt_regs *regs);
extern void uprobe_clear_state(struct mm_struct *mm);
-extern void uprobe_reset_state(struct mm_struct *mm);
#else /* !CONFIG_UPROBES */
struct uprobes_state {
};
uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
}
+static inline void
+uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+}
static inline void uprobe_notify_resume(struct pt_regs *regs)
{
}
static inline void uprobe_clear_state(struct mm_struct *mm)
{
}
-static inline void uprobe_reset_state(struct mm_struct *mm)
-{
-}
#endif /* !CONFIG_UPROBES */
#endif /* _LINUX_UPROBES_H */
depends on SYSCTL
default y
+config VIRT_CPU_ACCOUNTING
+ bool "Deterministic task and CPU time accounting"
+ depends on HAVE_VIRT_CPU_ACCOUNTING
+ default y if PPC64
+ help
+ Select this option to enable more accurate task and CPU time
+ accounting. This is done by reading a CPU counter on each
+ kernel entry and exit and on transitions within the kernel
+ between system, softirq and hardirq state, so there is a
+ small performance impact. In the case of s390 or IBM POWER > 5,
+ this also enables accounting of stolen time on logically-partitioned
+ systems.
+
config BSD_PROCESS_ACCT
bool "BSD Process Accounting"
help
kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
notifier.o ksysfs.o cred.o \
- async.o range.o groups.o lglock.o
+ async.o range.o groups.o lglock.o smpboot.o
ifdef CONFIG_FUNCTION_TRACER
# Do not trace debug files and internal ftrace files
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
obj-$(CONFIG_SMP) += smp.o
-obj-$(CONFIG_SMP) += smpboot.o
ifneq ($(CONFIG_SMP),y)
obj-y += up.o
endif
__func__, cpu);
goto out_release;
}
+ smpboot_park_threads(cpu);
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
+ smpboot_unpark_threads(cpu);
cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
-
goto out_release;
}
BUG_ON(cpu_online(cpu));
goto out;
}
+ ret = smpboot_create_threads(cpu);
+ if (ret)
+ goto out;
+
ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
if (ret) {
nr_calls--;
goto out_notify;
BUG_ON(!cpu_online(cpu));
+ /* Wake the per cpu threads */
+ smpboot_unpark_threads(cpu);
+
/* Now call notifier in preparation. */
cpu_notify(CPU_ONLINE | mod, hcpu);
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
-void __weak arch_disable_nonboot_cpus_begin(void)
-{
-}
-
-void __weak arch_disable_nonboot_cpus_end(void)
-{
-}
-
int disable_nonboot_cpus(void)
{
int cpu, first_cpu, error = 0;
* with the userspace trying to use the CPU hotplug at the same time
*/
cpumask_clear(frozen_cpus);
- arch_disable_nonboot_cpus_begin();
printk("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
}
}
- arch_disable_nonboot_cpus_end();
-
if (!error) {
BUG_ON(num_online_cpus() > 1);
/* Make sure the CPUs won't be enabled by someone else */
int rctx;
struct perf_callchain_entry *entry;
+ int kernel = !event->attr.exclude_callchain_kernel;
+ int user = !event->attr.exclude_callchain_user;
+
+ if (!kernel && !user)
+ return NULL;
entry = get_callchain_entry(&rctx);
if (rctx == -1)
entry->nr = 0;
- if (!user_mode(regs)) {
+ if (kernel && !user_mode(regs)) {
perf_callchain_store(entry, PERF_CONTEXT_KERNEL);
perf_callchain_kernel(entry, regs);
- if (current->mm)
- regs = task_pt_regs(current);
- else
- regs = NULL;
}
- if (regs) {
- /*
- * Disallow cross-task user callchains.
- */
- if (event->ctx->task && event->ctx->task != current)
- goto exit_put;
-
- perf_callchain_store(entry, PERF_CONTEXT_USER);
- perf_callchain_user(entry, regs);
+ if (user) {
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ if (regs) {
+ /*
+ * Disallow cross-task user callchains.
+ */
+ if (event->ctx->task && event->ctx->task != current)
+ goto exit_put;
+
+ perf_callchain_store(entry, PERF_CONTEXT_USER);
+ perf_callchain_user(entry, regs);
+ }
}
exit_put:
#include <linux/perf_event.h>
#include <linux/ftrace_event.h>
#include <linux/hw_breakpoint.h>
+#include <linux/mm_types.h>
#include "internal.h"
/*
* Cross CPU call to disable a performance event
*/
-static int __perf_event_disable(void *info)
+int __perf_event_disable(void *info)
{
struct perf_event *event = info;
struct perf_event_context *ctx = event->ctx;
}
EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks);
+static void
+perf_output_sample_regs(struct perf_output_handle *handle,
+ struct pt_regs *regs, u64 mask)
+{
+ int bit;
+
+ for_each_set_bit(bit, (const unsigned long *) &mask,
+ sizeof(mask) * BITS_PER_BYTE) {
+ u64 val;
+
+ val = perf_reg_value(regs, bit);
+ perf_output_put(handle, val);
+ }
+}
+
+static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+ struct pt_regs *regs)
+{
+ if (!user_mode(regs)) {
+ if (current->mm)
+ regs = task_pt_regs(current);
+ else
+ regs = NULL;
+ }
+
+ if (regs) {
+ regs_user->regs = regs;
+ regs_user->abi = perf_reg_abi(current);
+ }
+}
+
+/*
+ * Get remaining task size from user stack pointer.
+ *
+ * It'd be better to take stack vma map and limit this more
+ * precisly, but there's no way to get it safely under interrupt,
+ * so using TASK_SIZE as limit.
+ */
+static u64 perf_ustack_task_size(struct pt_regs *regs)
+{
+ unsigned long addr = perf_user_stack_pointer(regs);
+
+ if (!addr || addr >= TASK_SIZE)
+ return 0;
+
+ return TASK_SIZE - addr;
+}
+
+static u16
+perf_sample_ustack_size(u16 stack_size, u16 header_size,
+ struct pt_regs *regs)
+{
+ u64 task_size;
+
+ /* No regs, no stack pointer, no dump. */
+ if (!regs)
+ return 0;
+
+ /*
+ * Check if we fit in with the requested stack size into the:
+ * - TASK_SIZE
+ * If we don't, we limit the size to the TASK_SIZE.
+ *
+ * - remaining sample size
+ * If we don't, we customize the stack size to
+ * fit in to the remaining sample size.
+ */
+
+ task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs));
+ stack_size = min(stack_size, (u16) task_size);
+
+ /* Current header size plus static size and dynamic size. */
+ header_size += 2 * sizeof(u64);
+
+ /* Do we fit in with the current stack dump size? */
+ if ((u16) (header_size + stack_size) < header_size) {
+ /*
+ * If we overflow the maximum size for the sample,
+ * we customize the stack dump size to fit in.
+ */
+ stack_size = USHRT_MAX - header_size - sizeof(u64);
+ stack_size = round_up(stack_size, sizeof(u64));
+ }
+
+ return stack_size;
+}
+
+static void
+perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
+ struct pt_regs *regs)
+{
+ /* Case of a kernel thread, nothing to dump */
+ if (!regs) {
+ u64 size = 0;
+ perf_output_put(handle, size);
+ } else {
+ unsigned long sp;
+ unsigned int rem;
+ u64 dyn_size;
+
+ /*
+ * We dump:
+ * static size
+ * - the size requested by user or the best one we can fit
+ * in to the sample max size
+ * data
+ * - user stack dump data
+ * dynamic size
+ * - the actual dumped size
+ */
+
+ /* Static size. */
+ perf_output_put(handle, dump_size);
+
+ /* Data. */
+ sp = perf_user_stack_pointer(regs);
+ rem = __output_copy_user(handle, (void *) sp, dump_size);
+ dyn_size = dump_size - rem;
+
+ perf_output_skip(handle, rem);
+
+ /* Dynamic size. */
+ perf_output_put(handle, dyn_size);
+ }
+}
+
static void __perf_event_header__init_id(struct perf_event_header *header,
struct perf_sample_data *data,
struct perf_event *event)
perf_output_put(handle, nr);
}
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ u64 abi = data->regs_user.abi;
+
+ /*
+ * If there are no regs to dump, notice it through
+ * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+ */
+ perf_output_put(handle, abi);
+
+ if (abi) {
+ u64 mask = event->attr.sample_regs_user;
+ perf_output_sample_regs(handle,
+ data->regs_user.regs,
+ mask);
+ }
+ }
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ perf_output_sample_ustack(handle,
+ data->stack_user_size,
+ data->regs_user.regs);
}
void perf_prepare_sample(struct perf_event_header *header,
}
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_REGS_USER) {
+ /* regs dump ABI info */
+ int size = sizeof(u64);
+
+ perf_sample_regs_user(&data->regs_user, regs);
+
+ if (data->regs_user.regs) {
+ u64 mask = event->attr.sample_regs_user;
+ size += hweight64(mask) * sizeof(u64);
+ }
+
+ header->size += size;
+ }
+
+ if (sample_type & PERF_SAMPLE_STACK_USER) {
+ /*
+ * Either we need PERF_SAMPLE_STACK_USER bit to be allways
+ * processed as the last one or have additional check added
+ * in case new sample type is added, because we could eat
+ * up the rest of the sample size.
+ */
+ struct perf_regs_user *uregs = &data->regs_user;
+ u16 stack_size = event->attr.sample_stack_user;
+ u16 size = sizeof(u64);
+
+ if (!uregs->abi)
+ perf_sample_regs_user(uregs, regs);
+
+ stack_size = perf_sample_ustack_size(stack_size, header->size,
+ uregs->regs);
+
+ /*
+ * If there is something to dump, add space for the dump
+ * itself and for the field that tells the dynamic size,
+ * which is how many have been actually dumped.
+ */
+ if (stack_size)
+ size += sizeof(u64) + stack_size;
+
+ data->stack_user_size = stack_size;
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
attr->branch_sample_type = mask;
}
}
+
+ if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
+ ret = perf_reg_validate(attr->sample_regs_user);
+ if (ret)
+ return ret;
+ }
+
+ if (attr->sample_type & PERF_SAMPLE_STACK_USER) {
+ if (!arch_perf_have_user_stack_dump())
+ return -ENOSYS;
+
+ /*
+ * We have __u32 type for the size, but so far
+ * we can only use __u16 as maximum due to the
+ * __u16 sample size limit.
+ */
+ if (attr->sample_stack_user >= USHRT_MAX)
+ ret = -EINVAL;
+ else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64)))
+ ret = -EINVAL;
+ }
+
out:
return ret;
int old_type = bp->attr.bp_type;
int err = 0;
- perf_event_disable(bp);
+ /*
+ * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it
+ * will not be possible to raise IPIs that invoke __perf_event_disable.
+ * So call the function directly after making sure we are targeting the
+ * current task.
+ */
+ if (irqs_disabled() && bp->ctx && bp->ctx->task == current)
+ __perf_event_disable(bp);
+ else
+ perf_event_disable(bp);
bp->attr.bp_addr = attr->bp_addr;
bp->attr.bp_type = attr->bp_type;
#define _KERNEL_EVENTS_INTERNAL_H
#include <linux/hardirq.h>
+#include <linux/uaccess.h>
/* Buffer handling */
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
}
-static inline void
-__output_copy(struct perf_output_handle *handle,
- const void *buf, unsigned int len)
+#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \
+static inline unsigned int \
+func_name(struct perf_output_handle *handle, \
+ const void *buf, unsigned int len) \
+{ \
+ unsigned long size, written; \
+ \
+ do { \
+ size = min_t(unsigned long, handle->size, len); \
+ \
+ written = memcpy_func(handle->addr, buf, size); \
+ \
+ len -= written; \
+ handle->addr += written; \
+ buf += written; \
+ handle->size -= written; \
+ if (!handle->size) { \
+ struct ring_buffer *rb = handle->rb; \
+ \
+ handle->page++; \
+ handle->page &= rb->nr_pages - 1; \
+ handle->addr = rb->data_pages[handle->page]; \
+ handle->size = PAGE_SIZE << page_order(rb); \
+ } \
+ } while (len && written == size); \
+ \
+ return len; \
+}
+
+static inline int memcpy_common(void *dst, const void *src, size_t n)
{
- do {
- unsigned long size = min_t(unsigned long, handle->size, len);
-
- memcpy(handle->addr, buf, size);
-
- len -= size;
- handle->addr += size;
- buf += size;
- handle->size -= size;
- if (!handle->size) {
- struct ring_buffer *rb = handle->rb;
-
- handle->page++;
- handle->page &= rb->nr_pages - 1;
- handle->addr = rb->data_pages[handle->page];
- handle->size = PAGE_SIZE << page_order(rb);
- }
- } while (len);
+ memcpy(dst, src, n);
+ return n;
}
+DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
+
+#define MEMCPY_SKIP(dst, src, n) (n)
+
+DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP)
+
+#ifndef arch_perf_out_copy_user
+#define arch_perf_out_copy_user __copy_from_user_inatomic
+#endif
+
+DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
+
/* Callchain handling */
extern struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs);
recursion[rctx]--;
}
+#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+ return true;
+}
+
+#define perf_user_stack_pointer(regs) user_stack_pointer(regs)
+#else
+static inline bool arch_perf_have_user_stack_dump(void)
+{
+ return false;
+}
+
+#define perf_user_stack_pointer(regs) 0
+#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */
+
#endif /* _KERNEL_EVENTS_INTERNAL_H */
return -ENOSPC;
}
-void perf_output_copy(struct perf_output_handle *handle,
+unsigned int perf_output_copy(struct perf_output_handle *handle,
const void *buf, unsigned int len)
{
- __output_copy(handle, buf, len);
+ return __output_copy(handle, buf, len);
+}
+
+unsigned int perf_output_skip(struct perf_output_handle *handle,
+ unsigned int len)
+{
+ return __output_skip(handle, NULL, len);
}
void perf_output_end(struct perf_output_handle *handle)
if (ret <= 0)
return ret;
- lock_page(page);
vaddr_new = kmap_atomic(page);
vaddr &= ~PAGE_MASK;
memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE);
kunmap_atomic(vaddr_new);
- unlock_page(page);
put_page(page);
*/
result = is_swbp_at_addr(mm, vaddr);
if (result == 1)
- return -EEXIST;
+ return 0;
if (result)
return result;
* @mm: the probed process address space.
* @auprobe: arch specific probepoint information.
* @vaddr: the virtual address to insert the opcode.
- * @verify: if true, verify existance of breakpoint instruction.
*
* For mm @mm, restore the original opcode (opcode) at @vaddr.
* Return 0 (success) or a negative errno.
*/
int __weak
-set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, bool verify)
+set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr)
{
- if (verify) {
- int result;
+ int result;
- result = is_swbp_at_addr(mm, vaddr);
- if (!result)
- return -EINVAL;
+ result = is_swbp_at_addr(mm, vaddr);
+ if (!result)
+ return -EINVAL;
+
+ if (result != 1)
+ return result;
- if (result != 1)
- return result;
- }
return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn);
}
install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long vaddr)
{
+ bool first_uprobe;
int ret;
/*
* Hence behave as if probe already existed.
*/
if (!uprobe->consumers)
- return -EEXIST;
+ return 0;
if (!(uprobe->flags & UPROBE_COPY_INSN)) {
ret = copy_insn(uprobe, vma->vm_file);
}
/*
- * Ideally, should be updating the probe count after the breakpoint
- * has been successfully inserted. However a thread could hit the
- * breakpoint we just inserted even before the probe count is
- * incremented. If this is the first breakpoint placed, breakpoint
- * notifier might ignore uprobes and pass the trap to the thread.
- * Hence increment before and decrement on failure.
+ * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(),
+ * the task can hit this breakpoint right after __replace_page().
*/
- atomic_inc(&mm->uprobes_state.count);
+ first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags);
+ if (first_uprobe)
+ set_bit(MMF_HAS_UPROBES, &mm->flags);
+
ret = set_swbp(&uprobe->arch, mm, vaddr);
- if (ret)
- atomic_dec(&mm->uprobes_state.count);
+ if (ret && first_uprobe)
+ clear_bit(MMF_HAS_UPROBES, &mm->flags);
return ret;
}
static void
remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr)
{
- if (!set_orig_insn(&uprobe->arch, mm, vaddr, true))
- atomic_dec(&mm->uprobes_state.count);
+ set_orig_insn(&uprobe->arch, mm, vaddr);
}
/*
vaddr_to_offset(vma, info->vaddr) != uprobe->offset)
goto unlock;
- if (is_register) {
+ if (is_register)
err = install_breakpoint(uprobe, mm, vma, info->vaddr);
- /*
- * We can race against uprobe_mmap(), see the
- * comment near uprobe_hash().
- */
- if (err == -EEXIST)
- err = 0;
- } else {
+ else
remove_breakpoint(uprobe, mm, info->vaddr);
- }
+
unlock:
up_write(&mm->mmap_sem);
free:
}
/*
- * Called from mmap_region.
- * called with mm->mmap_sem acquired.
- *
- * Return -ve no if we fail to insert probes and we cannot
- * bail-out.
- * Return 0 otherwise. i.e:
+ * Called from mmap_region/vma_adjust with mm->mmap_sem acquired.
*
- * - successful insertion of probes
- * - (or) no possible probes to be inserted.
- * - (or) insertion of probes failed but we can bail-out.
+ * Currently we ignore all errors and always return 0, the callers
+ * can't handle the failure anyway.
*/
int uprobe_mmap(struct vm_area_struct *vma)
{
struct list_head tmp_list;
struct uprobe *uprobe, *u;
struct inode *inode;
- int ret, count;
if (!atomic_read(&uprobe_events) || !valid_vma(vma, true))
return 0;
mutex_lock(uprobes_mmap_hash(inode));
build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list);
- ret = 0;
- count = 0;
-
list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
- if (!ret) {
+ if (!fatal_signal_pending(current)) {
unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
-
- ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
- /*
- * We can race against uprobe_register(), see the
- * comment near uprobe_hash().
- */
- if (ret == -EEXIST) {
- ret = 0;
-
- if (!is_swbp_at_addr(vma->vm_mm, vaddr))
- continue;
-
- /*
- * Unable to insert a breakpoint, but
- * breakpoint lies underneath. Increment the
- * probe count.
- */
- atomic_inc(&vma->vm_mm->uprobes_state.count);
- }
-
- if (!ret)
- count++;
+ install_breakpoint(uprobe, vma->vm_mm, vma, vaddr);
}
put_uprobe(uprobe);
}
-
mutex_unlock(uprobes_mmap_hash(inode));
- if (ret)
- atomic_sub(count, &vma->vm_mm->uprobes_state.count);
-
- return ret;
+ return 0;
}
/*
*/
void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
- struct list_head tmp_list;
- struct uprobe *uprobe, *u;
- struct inode *inode;
-
if (!atomic_read(&uprobe_events) || !valid_vma(vma, false))
return;
if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */
return;
- if (!atomic_read(&vma->vm_mm->uprobes_state.count))
- return;
-
- inode = vma->vm_file->f_mapping->host;
- if (!inode)
+ if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags))
return;
- mutex_lock(uprobes_mmap_hash(inode));
- build_probe_list(inode, vma, start, end, &tmp_list);
-
- list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) {
- unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset);
- /*
- * An unregister could have removed the probe before
- * unmap. So check before we decrement the count.
- */
- if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1)
- atomic_dec(&vma->vm_mm->uprobes_state.count);
- put_uprobe(uprobe);
- }
- mutex_unlock(uprobes_mmap_hash(inode));
+ /* TODO: unmapping uprobe(s) will need more work */
}
/* Slot allocation for XOL */
kfree(area);
}
-/*
- * uprobe_reset_state - Free the area allocated for slots.
- */
-void uprobe_reset_state(struct mm_struct *mm)
+void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm)
{
- mm->uprobes_state.xol_area = NULL;
- atomic_set(&mm->uprobes_state.count, 0);
+ newmm->uprobes_state.xol_area = NULL;
+
+ if (test_bit(MMF_HAS_UPROBES, &oldmm->flags))
+ set_bit(MMF_HAS_UPROBES, &newmm->flags);
}
/*
utask->active_uprobe = NULL;
utask->state = UTASK_RUNNING;
}
- if (uprobe) {
- if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
+ if (!(uprobe->flags & UPROBE_SKIP_SSTEP))
- /*
- * cannot singlestep; cannot skip instruction;
- * re-execute the instruction.
- */
- instruction_pointer_set(regs, bp_vaddr);
+ /*
+ * cannot singlestep; cannot skip instruction;
+ * re-execute the instruction.
+ */
+ instruction_pointer_set(regs, bp_vaddr);
- put_uprobe(uprobe);
- }
+ put_uprobe(uprobe);
}
/*
{
struct uprobe_task *utask;
- if (!current->mm || !atomic_read(¤t->mm->uprobes_state.count))
- /* task is currently not uprobed */
+ if (!current->mm || !test_bit(MMF_HAS_UPROBES, ¤t->mm->flags))
return 0;
utask = current->utask;
down_write(&oldmm->mmap_sem);
flush_cache_dup_mm(oldmm);
+ uprobe_dup_mmap(oldmm, mm);
/*
* Not linked in yet - no deadlock potential:
*/
if (retval)
goto out;
-
- if (file)
- uprobe_mmap(tmp);
}
/* a new mm has just been created */
arch_dup_mmap(oldmm, mm);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
mm->pmd_huge_pte = NULL;
#endif
- uprobe_reset_state(mm);
-
if (!mm_init(mm, tsk))
goto fail_nomem;
irq_set_chip(irq, chip);
__irq_set_handler(irq, handle, 0, name);
}
+EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name);
void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
{
*/
#include <linux/interrupt.h>
#include <linux/irq.h>
+#include <linux/export.h>
#include "internals.h"
.irq_mask = noop,
.irq_unmask = noop,
};
+EXPORT_SYMBOL_GPL(dummy_irq_chip);
{
LIST_HEAD(free_list);
+ mutex_lock(&kprobe_mutex);
/* Lock modules while optimizing kprobes */
mutex_lock(&module_mutex);
- mutex_lock(&kprobe_mutex);
/*
* Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
/* Step 4: Free cleaned kprobes after quiesence period */
do_free_cleaned_kprobes(&free_list);
- mutex_unlock(&kprobe_mutex);
mutex_unlock(&module_mutex);
+ mutex_unlock(&kprobe_mutex);
/* Step 5: Kick optimizer again if needed */
if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
struct kprobe *ap;
struct optimized_kprobe *op;
+ /* Impossible to optimize ftrace-based kprobe */
+ if (kprobe_ftrace(p))
+ return;
+
+ /* For preparing optimization, jump_label_text_reserved() is called */
+ jump_label_lock();
+ mutex_lock(&text_mutex);
+
ap = alloc_aggr_kprobe(p);
if (!ap)
- return;
+ goto out;
op = container_of(ap, struct optimized_kprobe, kp);
if (!arch_prepared_optinsn(&op->optinsn)) {
/* If failed to setup optimizing, fallback to kprobe */
arch_remove_optimized_kprobe(op);
kfree(op);
- return;
+ goto out;
}
init_aggr_kprobe(ap, p);
- optimize_kprobe(ap);
+ optimize_kprobe(ap); /* This just kicks optimizer thread */
+
+out:
+ mutex_unlock(&text_mutex);
+ jump_label_unlock();
}
#ifdef CONFIG_SYSCTL
}
#endif /* CONFIG_OPTPROBES */
+#ifdef KPROBES_CAN_USE_FTRACE
+static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
+ .func = kprobe_ftrace_handler,
+ .flags = FTRACE_OPS_FL_SAVE_REGS,
+};
+static int kprobe_ftrace_enabled;
+
+/* Must ensure p->addr is really on ftrace */
+static int __kprobes prepare_kprobe(struct kprobe *p)
+{
+ if (!kprobe_ftrace(p))
+ return arch_prepare_kprobe(p);
+
+ return arch_prepare_kprobe_ftrace(p);
+}
+
+/* Caller must lock kprobe_mutex */
+static void __kprobes arm_kprobe_ftrace(struct kprobe *p)
+{
+ int ret;
+
+ ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
+ (unsigned long)p->addr, 0, 0);
+ WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+ kprobe_ftrace_enabled++;
+ if (kprobe_ftrace_enabled == 1) {
+ ret = register_ftrace_function(&kprobe_ftrace_ops);
+ WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret);
+ }
+}
+
+/* Caller must lock kprobe_mutex */
+static void __kprobes disarm_kprobe_ftrace(struct kprobe *p)
+{
+ int ret;
+
+ kprobe_ftrace_enabled--;
+ if (kprobe_ftrace_enabled == 0) {
+ ret = unregister_ftrace_function(&kprobe_ftrace_ops);
+ WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret);
+ }
+ ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
+ (unsigned long)p->addr, 1, 0);
+ WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+}
+#else /* !KPROBES_CAN_USE_FTRACE */
+#define prepare_kprobe(p) arch_prepare_kprobe(p)
+#define arm_kprobe_ftrace(p) do {} while (0)
+#define disarm_kprobe_ftrace(p) do {} while (0)
+#endif
+
/* Arm a kprobe with text_mutex */
static void __kprobes arm_kprobe(struct kprobe *kp)
{
+ if (unlikely(kprobe_ftrace(kp))) {
+ arm_kprobe_ftrace(kp);
+ return;
+ }
/*
* Here, since __arm_kprobe() doesn't use stop_machine(),
* this doesn't cause deadlock on text_mutex. So, we don't
}
/* Disarm a kprobe with text_mutex */
-static void __kprobes disarm_kprobe(struct kprobe *kp)
+static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt)
{
+ if (unlikely(kprobe_ftrace(kp))) {
+ disarm_kprobe_ftrace(kp);
+ return;
+ }
/* Ditto */
mutex_lock(&text_mutex);
- __disarm_kprobe(kp, true);
+ __disarm_kprobe(kp, reopt);
mutex_unlock(&text_mutex);
}
if (p->post_handler && !ap->post_handler)
ap->post_handler = aggr_post_handler;
- if (kprobe_disabled(ap) && !kprobe_disabled(p)) {
- ap->flags &= ~KPROBE_FLAG_DISABLED;
- if (!kprobes_all_disarmed)
- /* Arm the breakpoint again. */
- __arm_kprobe(ap);
- }
return 0;
}
int ret = 0;
struct kprobe *ap = orig_p;
+ /* For preparing optimization, jump_label_text_reserved() is called */
+ jump_label_lock();
+ /*
+ * Get online CPUs to avoid text_mutex deadlock.with stop machine,
+ * which is invoked by unoptimize_kprobe() in add_new_kprobe()
+ */
+ get_online_cpus();
+ mutex_lock(&text_mutex);
+
if (!kprobe_aggrprobe(orig_p)) {
/* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */
ap = alloc_aggr_kprobe(orig_p);
- if (!ap)
- return -ENOMEM;
+ if (!ap) {
+ ret = -ENOMEM;
+ goto out;
+ }
init_aggr_kprobe(ap, orig_p);
} else if (kprobe_unused(ap))
/* This probe is going to die. Rescue it */
* free aggr_probe. It will be used next time, or
* freed by unregister_kprobe.
*/
- return ret;
+ goto out;
/* Prepare optimized instructions if possible. */
prepare_optimized_kprobe(ap);
/* Copy ap's insn slot to p */
copy_kprobe(ap, p);
- return add_new_kprobe(ap, p);
+ ret = add_new_kprobe(ap, p);
+
+out:
+ mutex_unlock(&text_mutex);
+ put_online_cpus();
+ jump_label_unlock();
+
+ if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) {
+ ap->flags &= ~KPROBE_FLAG_DISABLED;
+ if (!kprobes_all_disarmed)
+ /* Arm the breakpoint again. */
+ arm_kprobe(ap);
+ }
+ return ret;
}
static int __kprobes in_kprobes_functions(unsigned long addr)
return ret;
}
-int __kprobes register_kprobe(struct kprobe *p)
+static __kprobes int check_kprobe_address_safe(struct kprobe *p,
+ struct module **probed_mod)
{
int ret = 0;
- struct kprobe *old_p;
- struct module *probed_mod;
- kprobe_opcode_t *addr;
-
- addr = kprobe_addr(p);
- if (IS_ERR(addr))
- return PTR_ERR(addr);
- p->addr = addr;
+ unsigned long ftrace_addr;
- ret = check_kprobe_rereg(p);
- if (ret)
- return ret;
+ /*
+ * If the address is located on a ftrace nop, set the
+ * breakpoint to the following instruction.
+ */
+ ftrace_addr = ftrace_location((unsigned long)p->addr);
+ if (ftrace_addr) {
+#ifdef KPROBES_CAN_USE_FTRACE
+ /* Given address is not on the instruction boundary */
+ if ((unsigned long)p->addr != ftrace_addr)
+ return -EILSEQ;
+ /* break_handler (jprobe) can not work with ftrace */
+ if (p->break_handler)
+ return -EINVAL;
+ p->flags |= KPROBE_FLAG_FTRACE;
+#else /* !KPROBES_CAN_USE_FTRACE */
+ return -EINVAL;
+#endif
+ }
jump_label_lock();
preempt_disable();
+
+ /* Ensure it is not in reserved area nor out of text */
if (!kernel_text_address((unsigned long) p->addr) ||
in_kprobes_functions((unsigned long) p->addr) ||
- ftrace_text_reserved(p->addr, p->addr) ||
jump_label_text_reserved(p->addr, p->addr)) {
ret = -EINVAL;
- goto cannot_probe;
+ goto out;
}
- /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
- p->flags &= KPROBE_FLAG_DISABLED;
-
- /*
- * Check if are we probing a module.
- */
- probed_mod = __module_text_address((unsigned long) p->addr);
- if (probed_mod) {
- /* Return -ENOENT if fail. */
- ret = -ENOENT;
+ /* Check if are we probing a module */
+ *probed_mod = __module_text_address((unsigned long) p->addr);
+ if (*probed_mod) {
/*
* We must hold a refcount of the probed module while updating
* its code to prohibit unexpected unloading.
*/
- if (unlikely(!try_module_get(probed_mod)))
- goto cannot_probe;
+ if (unlikely(!try_module_get(*probed_mod))) {
+ ret = -ENOENT;
+ goto out;
+ }
/*
* If the module freed .init.text, we couldn't insert
* kprobes in there.
*/
- if (within_module_init((unsigned long)p->addr, probed_mod) &&
- probed_mod->state != MODULE_STATE_COMING) {
- module_put(probed_mod);
- goto cannot_probe;
+ if (within_module_init((unsigned long)p->addr, *probed_mod) &&
+ (*probed_mod)->state != MODULE_STATE_COMING) {
+ module_put(*probed_mod);
+ *probed_mod = NULL;
+ ret = -ENOENT;
}
- /* ret will be updated by following code */
}
+out:
preempt_enable();
jump_label_unlock();
+ return ret;
+}
+
+int __kprobes register_kprobe(struct kprobe *p)
+{
+ int ret;
+ struct kprobe *old_p;
+ struct module *probed_mod;
+ kprobe_opcode_t *addr;
+
+ /* Adjust probe address from symbol */
+ addr = kprobe_addr(p);
+ if (IS_ERR(addr))
+ return PTR_ERR(addr);
+ p->addr = addr;
+
+ ret = check_kprobe_rereg(p);
+ if (ret)
+ return ret;
+
+ /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */
+ p->flags &= KPROBE_FLAG_DISABLED;
p->nmissed = 0;
INIT_LIST_HEAD(&p->list);
- mutex_lock(&kprobe_mutex);
- jump_label_lock(); /* needed to call jump_label_text_reserved() */
+ ret = check_kprobe_address_safe(p, &probed_mod);
+ if (ret)
+ return ret;
- get_online_cpus(); /* For avoiding text_mutex deadlock. */
- mutex_lock(&text_mutex);
+ mutex_lock(&kprobe_mutex);
old_p = get_kprobe(p->addr);
if (old_p) {
goto out;
}
- ret = arch_prepare_kprobe(p);
+ mutex_lock(&text_mutex); /* Avoiding text modification */
+ ret = prepare_kprobe(p);
+ mutex_unlock(&text_mutex);
if (ret)
goto out;
&kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
if (!kprobes_all_disarmed && !kprobe_disabled(p))
- __arm_kprobe(p);
+ arm_kprobe(p);
/* Try to optimize kprobe */
try_to_optimize_kprobe(p);
out:
- mutex_unlock(&text_mutex);
- put_online_cpus();
- jump_label_unlock();
mutex_unlock(&kprobe_mutex);
if (probed_mod)
module_put(probed_mod);
return ret;
-
-cannot_probe:
- preempt_enable();
- jump_label_unlock();
- return ret;
}
EXPORT_SYMBOL_GPL(register_kprobe);
/* Try to disarm and disable this/parent probe */
if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
- disarm_kprobe(orig_p);
+ disarm_kprobe(orig_p, true);
orig_p->flags |= KPROBE_FLAG_DISABLED;
}
}
if (!pp)
pp = p;
- seq_printf(pi, "%s%s%s\n",
+ seq_printf(pi, "%s%s%s%s\n",
(kprobe_gone(p) ? "[GONE]" : ""),
((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""),
- (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""));
+ (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""),
+ (kprobe_ftrace(pp) ? "[FTRACE]" : ""));
}
static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
goto already_enabled;
/* Arming kprobes doesn't optimize kprobe itself */
- mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist)
if (!kprobe_disabled(p))
- __arm_kprobe(p);
+ arm_kprobe(p);
}
- mutex_unlock(&text_mutex);
kprobes_all_disarmed = false;
printk(KERN_INFO "Kprobes globally enabled\n");
kprobes_all_disarmed = true;
printk(KERN_INFO "Kprobes globally disabled\n");
- mutex_lock(&text_mutex);
for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
head = &kprobe_table[i];
hlist_for_each_entry_rcu(p, node, head, hlist) {
if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
- __disarm_kprobe(p, false);
+ disarm_kprobe(p, false);
}
}
- mutex_unlock(&text_mutex);
mutex_unlock(&kprobe_mutex);
/* Wait for disarming all kprobes by optimizer */
};
struct kthread {
- int should_stop;
+ unsigned long flags;
+ unsigned int cpu;
void *data;
+ struct completion parked;
struct completion exited;
};
+enum KTHREAD_BITS {
+ KTHREAD_IS_PER_CPU = 0,
+ KTHREAD_SHOULD_STOP,
+ KTHREAD_SHOULD_PARK,
+ KTHREAD_IS_PARKED,
+};
+
#define to_kthread(tsk) \
container_of((tsk)->vfork_done, struct kthread, exited)
* and this will return true. You should then return, and your return
* value will be passed through to kthread_stop().
*/
-int kthread_should_stop(void)
+bool kthread_should_stop(void)
{
- return to_kthread(current)->should_stop;
+ return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
}
EXPORT_SYMBOL(kthread_should_stop);
+/**
+ * kthread_should_park - should this kthread park now?
+ *
+ * When someone calls kthread_park() on your kthread, it will be woken
+ * and this will return true. You should then do the necessary
+ * cleanup and call kthread_parkme()
+ *
+ * Similar to kthread_should_stop(), but this keeps the thread alive
+ * and in a park position. kthread_unpark() "restarts" the thread and
+ * calls the thread function again.
+ */
+bool kthread_should_park(void)
+{
+ return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
+}
+
/**
* kthread_freezable_should_stop - should this freezable kthread return now?
* @was_frozen: optional out parameter, indicates whether %current was frozen
return to_kthread(task)->data;
}
+static void __kthread_parkme(struct kthread *self)
+{
+ __set_current_state(TASK_INTERRUPTIBLE);
+ while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
+ if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
+ complete(&self->parked);
+ schedule();
+ __set_current_state(TASK_INTERRUPTIBLE);
+ }
+ clear_bit(KTHREAD_IS_PARKED, &self->flags);
+ __set_current_state(TASK_RUNNING);
+}
+
+void kthread_parkme(void)
+{
+ __kthread_parkme(to_kthread(current));
+}
+
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
struct kthread self;
int ret;
- self.should_stop = 0;
+ self.flags = 0;
self.data = data;
init_completion(&self.exited);
+ init_completion(&self.parked);
current->vfork_done = &self.exited;
/* OK, tell user we're spawned, wait for stop or wakeup */
schedule();
ret = -EINTR;
- if (!self.should_stop)
- ret = threadfn(data);
+ if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) {
+ __kthread_parkme(&self);
+ ret = threadfn(data);
+ }
/* we can't just return, we must preserve "self" on stack */
do_exit(ret);
}
* Returns a task_struct or ERR_PTR(-ENOMEM).
*/
struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
- void *data,
- int node,
+ void *data, int node,
const char namefmt[],
...)
{
}
EXPORT_SYMBOL(kthread_create_on_node);
+static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+ /* It's safe because the task is inactive. */
+ do_set_cpus_allowed(p, cpumask_of(cpu));
+ p->flags |= PF_THREAD_BOUND;
+}
+
/**
* kthread_bind - bind a just-created kthread to a cpu.
* @p: thread created by kthread_create().
WARN_ON(1);
return;
}
-
- /* It's safe because the task is inactive. */
- do_set_cpus_allowed(p, cpumask_of(cpu));
- p->flags |= PF_THREAD_BOUND;
+ __kthread_bind(p, cpu);
}
EXPORT_SYMBOL(kthread_bind);
+/**
+ * kthread_create_on_cpu - Create a cpu bound kthread
+ * @threadfn: the function to run until signal_pending(current).
+ * @data: data ptr for @threadfn.
+ * @cpu: The cpu on which the thread should be bound,
+ * @namefmt: printf-style name for the thread. Format is restricted
+ * to "name.*%u". Code fills in cpu number.
+ *
+ * Description: This helper function creates and names a kernel thread
+ * The thread will be woken and put into park mode.
+ */
+struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
+ void *data, unsigned int cpu,
+ const char *namefmt)
+{
+ struct task_struct *p;
+
+ p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
+ cpu);
+ if (IS_ERR(p))
+ return p;
+ set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
+ to_kthread(p)->cpu = cpu;
+ /* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */
+ kthread_park(p);
+ return p;
+}
+
+static struct kthread *task_get_live_kthread(struct task_struct *k)
+{
+ struct kthread *kthread;
+
+ get_task_struct(k);
+ kthread = to_kthread(k);
+ /* It might have exited */
+ barrier();
+ if (k->vfork_done != NULL)
+ return kthread;
+ return NULL;
+}
+
+/**
+ * kthread_unpark - unpark a thread created by kthread_create().
+ * @k: thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return false, wakes it, and
+ * waits for it to return. If the thread is marked percpu then its
+ * bound to the cpu again.
+ */
+void kthread_unpark(struct task_struct *k)
+{
+ struct kthread *kthread = task_get_live_kthread(k);
+
+ if (kthread) {
+ clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ /*
+ * We clear the IS_PARKED bit here as we don't wait
+ * until the task has left the park code. So if we'd
+ * park before that happens we'd see the IS_PARKED bit
+ * which might be about to be cleared.
+ */
+ if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+ __kthread_bind(k, kthread->cpu);
+ wake_up_process(k);
+ }
+ }
+ put_task_struct(k);
+}
+
+/**
+ * kthread_park - park a thread created by kthread_create().
+ * @k: thread created by kthread_create().
+ *
+ * Sets kthread_should_park() for @k to return true, wakes it, and
+ * waits for it to return. This can also be called after kthread_create()
+ * instead of calling wake_up_process(): the thread will park without
+ * calling threadfn().
+ *
+ * Returns 0 if the thread is parked, -ENOSYS if the thread exited.
+ * If called by the kthread itself just the park bit is set.
+ */
+int kthread_park(struct task_struct *k)
+{
+ struct kthread *kthread = task_get_live_kthread(k);
+ int ret = -ENOSYS;
+
+ if (kthread) {
+ if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+ set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ if (k != current) {
+ wake_up_process(k);
+ wait_for_completion(&kthread->parked);
+ }
+ }
+ ret = 0;
+ }
+ put_task_struct(k);
+ return ret;
+}
+
/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*/
int kthread_stop(struct task_struct *k)
{
- struct kthread *kthread;
+ struct kthread *kthread = task_get_live_kthread(k);
int ret;
trace_sched_kthread_stop(k);
- get_task_struct(k);
-
- kthread = to_kthread(k);
- barrier(); /* it might have exited */
- if (k->vfork_done != NULL) {
- kthread->should_stop = 1;
+ if (kthread) {
+ set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
+ clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
wake_up_process(k);
wait_for_completion(&kthread->exited);
}
*/
static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
-DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
DEFINE_PER_CPU(char, rcu_cpu_has_work);
#endif /* #ifdef CONFIG_RCU_BOOST */
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
static void invoke_rcu_core(void);
static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */
/* Adjust any no-longer-needed kthreads. */
- rcu_stop_cpu_kthread(cpu);
- rcu_node_kthread_setaffinity(rnp, -1);
+ rcu_boost_kthread_setaffinity(rnp, -1);
/* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */
break;
case CPU_ONLINE:
case CPU_DOWN_FAILED:
- rcu_node_kthread_setaffinity(rnp, -1);
- rcu_cpu_kthread_setrt(cpu, 1);
+ rcu_boost_kthread_setaffinity(rnp, -1);
break;
case CPU_DOWN_PREPARE:
- rcu_node_kthread_setaffinity(rnp, cpu);
- rcu_cpu_kthread_setrt(cpu, 0);
+ rcu_boost_kthread_setaffinity(rnp, cpu);
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
/* Refused to boost: not sure why, though. */
/* This can happen due to race conditions. */
#endif /* #ifdef CONFIG_RCU_BOOST */
- struct task_struct *node_kthread_task;
- /* kthread that takes care of this rcu_node */
- /* structure, for example, awakening the */
- /* per-CPU kthreads as needed. */
- unsigned int node_kthread_status;
- /* State of node_kthread_task for tracing. */
} ____cacheline_internodealigned_in_smp;
/*
#ifdef CONFIG_HOTPLUG_CPU
static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
unsigned long flags);
-static void rcu_stop_cpu_kthread(int cpu);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static void rcu_print_detail_task_stall(struct rcu_state *rsp);
static int rcu_print_task_stall(struct rcu_node *rnp);
static bool rcu_is_callbacks_kthread(void);
#ifdef CONFIG_RCU_BOOST
static void rcu_preempt_do_callbacks(void);
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
- cpumask_var_t cm);
static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
- struct rcu_node *rnp,
- int rnp_index);
-static void invoke_rcu_node_kthread(struct rcu_node *rnp);
-static void rcu_yield(void (*f)(unsigned long), unsigned long arg);
+ struct rcu_node *rnp);
#endif /* #ifdef CONFIG_RCU_BOOST */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt);
static void __cpuinit rcu_prepare_kthreads(int cpu);
static void rcu_prepare_for_idle_init(int cpu);
static void rcu_cleanup_after_idle(int cpu);
*/
#include <linux/delay.h>
+#include <linux/smpboot.h>
#define RCU_KTHREAD_PRIO 1
#endif /* #else #ifdef CONFIG_RCU_TRACE */
+static void rcu_wake_cond(struct task_struct *t, int status)
+{
+ /*
+ * If the thread is yielding, only wake it when this
+ * is invoked from idle
+ */
+ if (status != RCU_KTHREAD_YIELDING || is_idle_task(current))
+ wake_up_process(t);
+}
+
/*
* Carry out RCU priority boosting on the task indicated by ->exp_tasks
* or ->boost_tasks, advancing the pointer to the next task in the
ACCESS_ONCE(rnp->boost_tasks) != NULL;
}
-/*
- * Timer handler to initiate waking up of boost kthreads that
- * have yielded the CPU due to excessive numbers of tasks to
- * boost. We wake up the per-rcu_node kthread, which in turn
- * will wake up the booster kthread.
- */
-static void rcu_boost_kthread_timer(unsigned long arg)
-{
- invoke_rcu_node_kthread((struct rcu_node *)arg);
-}
-
/*
* Priority-boosting kthread. One per leaf rcu_node and one for the
* root rcu_node.
else
spincnt = 0;
if (spincnt > 10) {
+ rnp->boost_kthread_status = RCU_KTHREAD_YIELDING;
trace_rcu_utilization("End boost kthread@rcu_yield");
- rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp);
+ schedule_timeout_interruptible(2);
trace_rcu_utilization("Start boost kthread@rcu_yield");
spincnt = 0;
}
rnp->boost_tasks = rnp->gp_tasks;
raw_spin_unlock_irqrestore(&rnp->lock, flags);
t = rnp->boost_kthread_task;
- if (t != NULL)
- wake_up_process(t);
+ if (t)
+ rcu_wake_cond(t, rnp->boost_kthread_status);
} else {
rcu_initiate_boost_trace(rnp);
raw_spin_unlock_irqrestore(&rnp->lock, flags);
local_irq_save(flags);
__this_cpu_write(rcu_cpu_has_work, 1);
if (__this_cpu_read(rcu_cpu_kthread_task) != NULL &&
- current != __this_cpu_read(rcu_cpu_kthread_task))
- wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
+ current != __this_cpu_read(rcu_cpu_kthread_task)) {
+ rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task),
+ __this_cpu_read(rcu_cpu_kthread_status));
+ }
local_irq_restore(flags);
}
return __get_cpu_var(rcu_cpu_kthread_task) == current;
}
-/*
- * Set the affinity of the boost kthread. The CPU-hotplug locks are
- * held, so no one should be messing with the existence of the boost
- * kthread.
- */
-static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
- cpumask_var_t cm)
-{
- struct task_struct *t;
-
- t = rnp->boost_kthread_task;
- if (t != NULL)
- set_cpus_allowed_ptr(rnp->boost_kthread_task, cm);
-}
-
#define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
/*
* Returns zero if all is well, a negated errno otherwise.
*/
static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
- struct rcu_node *rnp,
- int rnp_index)
+ struct rcu_node *rnp)
{
+ int rnp_index = rnp - &rsp->node[0];
unsigned long flags;
struct sched_param sp;
struct task_struct *t;
if (&rcu_preempt_state != rsp)
return 0;
+
+ if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0)
+ return 0;
+
rsp->boost = 1;
if (rnp->boost_kthread_task != NULL)
return 0;
return 0;
}
-#ifdef CONFIG_HOTPLUG_CPU
-
-/*
- * Stop the RCU's per-CPU kthread when its CPU goes offline,.
- */
-static void rcu_stop_cpu_kthread(int cpu)
-{
- struct task_struct *t;
-
- /* Stop the CPU's kthread. */
- t = per_cpu(rcu_cpu_kthread_task, cpu);
- if (t != NULL) {
- per_cpu(rcu_cpu_kthread_task, cpu) = NULL;
- kthread_stop(t);
- }
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
static void rcu_kthread_do_work(void)
{
rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
rcu_preempt_do_callbacks();
}
-/*
- * Wake up the specified per-rcu_node-structure kthread.
- * Because the per-rcu_node kthreads are immortal, we don't need
- * to do anything to keep them alive.
- */
-static void invoke_rcu_node_kthread(struct rcu_node *rnp)
+static void rcu_cpu_kthread_setup(unsigned int cpu)
{
- struct task_struct *t;
-
- t = rnp->node_kthread_task;
- if (t != NULL)
- wake_up_process(t);
-}
-
-/*
- * Set the specified CPU's kthread to run RT or not, as specified by
- * the to_rt argument. The CPU-hotplug locks are held, so the task
- * is not going away.
- */
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
-{
- int policy;
struct sched_param sp;
- struct task_struct *t;
-
- t = per_cpu(rcu_cpu_kthread_task, cpu);
- if (t == NULL)
- return;
- if (to_rt) {
- policy = SCHED_FIFO;
- sp.sched_priority = RCU_KTHREAD_PRIO;
- } else {
- policy = SCHED_NORMAL;
- sp.sched_priority = 0;
- }
- sched_setscheduler_nocheck(t, policy, &sp);
-}
-
-/*
- * Timer handler to initiate the waking up of per-CPU kthreads that
- * have yielded the CPU due to excess numbers of RCU callbacks.
- * We wake up the per-rcu_node kthread, which in turn will wake up
- * the booster kthread.
- */
-static void rcu_cpu_kthread_timer(unsigned long arg)
-{
- struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
- struct rcu_node *rnp = rdp->mynode;
- atomic_or(rdp->grpmask, &rnp->wakemask);
- invoke_rcu_node_kthread(rnp);
+ sp.sched_priority = RCU_KTHREAD_PRIO;
+ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
}
-/*
- * Drop to non-real-time priority and yield, but only after posting a
- * timer that will cause us to regain our real-time priority if we
- * remain preempted. Either way, we restore our real-time priority
- * before returning.
- */
-static void rcu_yield(void (*f)(unsigned long), unsigned long arg)
+static void rcu_cpu_kthread_park(unsigned int cpu)
{
- struct sched_param sp;
- struct timer_list yield_timer;
- int prio = current->rt_priority;
-
- setup_timer_on_stack(&yield_timer, f, arg);
- mod_timer(&yield_timer, jiffies + 2);
- sp.sched_priority = 0;
- sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp);
- set_user_nice(current, 19);
- schedule();
- set_user_nice(current, 0);
- sp.sched_priority = prio;
- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp);
- del_timer(&yield_timer);
+ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
}
-/*
- * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU.
- * This can happen while the corresponding CPU is either coming online
- * or going offline. We cannot wait until the CPU is fully online
- * before starting the kthread, because the various notifier functions
- * can wait for RCU grace periods. So we park rcu_cpu_kthread() until
- * the corresponding CPU is online.
- *
- * Return 1 if the kthread needs to stop, 0 otherwise.
- *
- * Caller must disable bh. This function can momentarily enable it.
- */
-static int rcu_cpu_kthread_should_stop(int cpu)
+static int rcu_cpu_kthread_should_run(unsigned int cpu)
{
- while (cpu_is_offline(cpu) ||
- !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) ||
- smp_processor_id() != cpu) {
- if (kthread_should_stop())
- return 1;
- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU;
- per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id();
- local_bh_enable();
- schedule_timeout_uninterruptible(1);
- if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)))
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
- local_bh_disable();
- }
- per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
- return 0;
+ return __get_cpu_var(rcu_cpu_has_work);
}
/*
* RCU softirq used in flavors and configurations of RCU that do not
* support RCU priority boosting.
*/
-static int rcu_cpu_kthread(void *arg)
+static void rcu_cpu_kthread(unsigned int cpu)
{
- int cpu = (int)(long)arg;
- unsigned long flags;
- int spincnt = 0;
- unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
- char work;
- char *workp = &per_cpu(rcu_cpu_has_work, cpu);
+ unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status);
+ char work, *workp = &__get_cpu_var(rcu_cpu_has_work);
+ int spincnt;
- trace_rcu_utilization("Start CPU kthread@init");
- for (;;) {
- *statusp = RCU_KTHREAD_WAITING;
- trace_rcu_utilization("End CPU kthread@rcu_wait");
- rcu_wait(*workp != 0 || kthread_should_stop());
+ for (spincnt = 0; spincnt < 10; spincnt++) {
trace_rcu_utilization("Start CPU kthread@rcu_wait");
local_bh_disable();
- if (rcu_cpu_kthread_should_stop(cpu)) {
- local_bh_enable();
- break;
- }
*statusp = RCU_KTHREAD_RUNNING;
- per_cpu(rcu_cpu_kthread_loops, cpu)++;
- local_irq_save(flags);
+ this_cpu_inc(rcu_cpu_kthread_loops);
+ local_irq_disable();
work = *workp;
*workp = 0;
- local_irq_restore(flags);
+ local_irq_enable();
if (work)
rcu_kthread_do_work();
local_bh_enable();
- if (*workp != 0)
- spincnt++;
- else
- spincnt = 0;
- if (spincnt > 10) {
- *statusp = RCU_KTHREAD_YIELDING;
- trace_rcu_utilization("End CPU kthread@rcu_yield");
- rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu);
- trace_rcu_utilization("Start CPU kthread@rcu_yield");
- spincnt = 0;
- }
- }
- *statusp = RCU_KTHREAD_STOPPED;
- trace_rcu_utilization("End CPU kthread@term");
- return 0;
-}
-
-/*
- * Spawn a per-CPU kthread, setting up affinity and priority.
- * Because the CPU hotplug lock is held, no other CPU will be attempting
- * to manipulate rcu_cpu_kthread_task. There might be another CPU
- * attempting to access it during boot, but the locking in kthread_bind()
- * will enforce sufficient ordering.
- *
- * Please note that we cannot simply refuse to wake up the per-CPU
- * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state,
- * which can result in softlockup complaints if the task ends up being
- * idle for more than a couple of minutes.
- *
- * However, please note also that we cannot bind the per-CPU kthread to its
- * CPU until that CPU is fully online. We also cannot wait until the
- * CPU is fully online before we create its per-CPU kthread, as this would
- * deadlock the system when CPU notifiers tried waiting for grace
- * periods. So we bind the per-CPU kthread to its CPU only if the CPU
- * is online. If its CPU is not yet fully online, then the code in
- * rcu_cpu_kthread() will wait until it is fully online, and then do
- * the binding.
- */
-static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
-{
- struct sched_param sp;
- struct task_struct *t;
-
- if (!rcu_scheduler_fully_active ||
- per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
- return 0;
- t = kthread_create_on_node(rcu_cpu_kthread,
- (void *)(long)cpu,
- cpu_to_node(cpu),
- "rcuc/%d", cpu);
- if (IS_ERR(t))
- return PTR_ERR(t);
- if (cpu_online(cpu))
- kthread_bind(t, cpu);
- per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
- WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
- sp.sched_priority = RCU_KTHREAD_PRIO;
- sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
- per_cpu(rcu_cpu_kthread_task, cpu) = t;
- wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */
- return 0;
-}
-
-/*
- * Per-rcu_node kthread, which is in charge of waking up the per-CPU
- * kthreads when needed. We ignore requests to wake up kthreads
- * for offline CPUs, which is OK because force_quiescent_state()
- * takes care of this case.
- */
-static int rcu_node_kthread(void *arg)
-{
- int cpu;
- unsigned long flags;
- unsigned long mask;
- struct rcu_node *rnp = (struct rcu_node *)arg;
- struct sched_param sp;
- struct task_struct *t;
-
- for (;;) {
- rnp->node_kthread_status = RCU_KTHREAD_WAITING;
- rcu_wait(atomic_read(&rnp->wakemask) != 0);
- rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
- raw_spin_lock_irqsave(&rnp->lock, flags);
- mask = atomic_xchg(&rnp->wakemask, 0);
- rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
- for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
- if ((mask & 0x1) == 0)
- continue;
- preempt_disable();
- t = per_cpu(rcu_cpu_kthread_task, cpu);
- if (!cpu_online(cpu) || t == NULL) {
- preempt_enable();
- continue;
- }
- per_cpu(rcu_cpu_has_work, cpu) = 1;
- sp.sched_priority = RCU_KTHREAD_PRIO;
- sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
- preempt_enable();
+ if (*workp == 0) {
+ trace_rcu_utilization("End CPU kthread@rcu_wait");
+ *statusp = RCU_KTHREAD_WAITING;
+ return;
}
}
- /* NOTREACHED */
- rnp->node_kthread_status = RCU_KTHREAD_STOPPED;
- return 0;
+ *statusp = RCU_KTHREAD_YIELDING;
+ trace_rcu_utilization("Start CPU kthread@rcu_yield");
+ schedule_timeout_interruptible(2);
+ trace_rcu_utilization("End CPU kthread@rcu_yield");
+ *statusp = RCU_KTHREAD_WAITING;
}
/*
* no outgoing CPU. If there are no CPUs left in the affinity set,
* this function allows the kthread to execute on any CPU.
*/
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
{
+ struct task_struct *t = rnp->boost_kthread_task;
+ unsigned long mask = rnp->qsmaskinit;
cpumask_var_t cm;
int cpu;
- unsigned long mask = rnp->qsmaskinit;
- if (rnp->node_kthread_task == NULL)
+ if (!t)
return;
- if (!alloc_cpumask_var(&cm, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
return;
- cpumask_clear(cm);
for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1)
if ((mask & 0x1) && cpu != outgoingcpu)
cpumask_set_cpu(cpu, cm);
cpumask_clear_cpu(cpu, cm);
WARN_ON_ONCE(cpumask_weight(cm) == 0);
}
- set_cpus_allowed_ptr(rnp->node_kthread_task, cm);
- rcu_boost_kthread_setaffinity(rnp, cm);
+ set_cpus_allowed_ptr(t, cm);
free_cpumask_var(cm);
}
-/*
- * Spawn a per-rcu_node kthread, setting priority and affinity.
- * Called during boot before online/offline can happen, or, if
- * during runtime, with the main CPU-hotplug locks held. So only
- * one of these can be executing at a time.
- */
-static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
- struct rcu_node *rnp)
-{
- unsigned long flags;
- int rnp_index = rnp - &rsp->node[0];
- struct sched_param sp;
- struct task_struct *t;
-
- if (!rcu_scheduler_fully_active ||
- rnp->qsmaskinit == 0)
- return 0;
- if (rnp->node_kthread_task == NULL) {
- t = kthread_create(rcu_node_kthread, (void *)rnp,
- "rcun/%d", rnp_index);
- if (IS_ERR(t))
- return PTR_ERR(t);
- raw_spin_lock_irqsave(&rnp->lock, flags);
- rnp->node_kthread_task = t;
- raw_spin_unlock_irqrestore(&rnp->lock, flags);
- sp.sched_priority = 99;
- sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
- wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
- }
- return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
-}
+static struct smp_hotplug_thread rcu_cpu_thread_spec = {
+ .store = &rcu_cpu_kthread_task,
+ .thread_should_run = rcu_cpu_kthread_should_run,
+ .thread_fn = rcu_cpu_kthread,
+ .thread_comm = "rcuc/%u",
+ .setup = rcu_cpu_kthread_setup,
+ .park = rcu_cpu_kthread_park,
+};
/*
* Spawn all kthreads -- called as soon as the scheduler is running.
*/
static int __init rcu_spawn_kthreads(void)
{
- int cpu;
struct rcu_node *rnp;
+ int cpu;
rcu_scheduler_fully_active = 1;
- for_each_possible_cpu(cpu) {
+ for_each_possible_cpu(cpu)
per_cpu(rcu_cpu_has_work, cpu) = 0;
- if (cpu_online(cpu))
- (void)rcu_spawn_one_cpu_kthread(cpu);
- }
+ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec));
rnp = rcu_get_root(rcu_state);
- (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+ (void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
if (NUM_RCU_NODES > 1) {
rcu_for_each_leaf_node(rcu_state, rnp)
- (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+ (void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
}
return 0;
}
struct rcu_node *rnp = rdp->mynode;
/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
- if (rcu_scheduler_fully_active) {
- (void)rcu_spawn_one_cpu_kthread(cpu);
- if (rnp->node_kthread_task == NULL)
- (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
- }
+ if (rcu_scheduler_fully_active)
+ (void)rcu_spawn_one_boost_kthread(rcu_state, rnp);
}
#else /* #ifdef CONFIG_RCU_BOOST */
{
}
-#ifdef CONFIG_HOTPLUG_CPU
-
-static void rcu_stop_cpu_kthread(int cpu)
-{
-}
-
-#endif /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
-{
-}
-
-static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
+static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
{
}
rdp->nxttail[RCU_WAIT_TAIL]],
".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
#ifdef CONFIG_RCU_BOOST
- seq_printf(m, " kt=%d/%c/%d ktl=%x",
+ seq_printf(m, " kt=%d/%c ktl=%x",
per_cpu(rcu_cpu_has_work, rdp->cpu),
convert_kthread_status(per_cpu(rcu_cpu_kthread_status,
rdp->cpu)),
- per_cpu(rcu_cpu_kthread_cpu, rdp->cpu),
per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff);
#endif /* #ifdef CONFIG_RCU_BOOST */
seq_printf(m, " b=%ld", rdp->blimit);
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
obj-$(CONFIG_SMP) += cpupri.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
dequeue_task(rq, p, flags);
}
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-
-/*
- * There are no locks covering percpu hardirq/softirq time.
- * They are only modified in account_system_vtime, on corresponding CPU
- * with interrupts disabled. So, writes are safe.
- * They are read and saved off onto struct rq in update_rq_clock().
- * This may result in other CPU reading this CPU's irq time and can
- * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value with a side effect of accounting a slice of irq time to wrong
- * task when irq is in progress while we read rq->clock. That is a worthy
- * compromise in place of having locks on each irq in account_system_time.
- */
-static DEFINE_PER_CPU(u64, cpu_hardirq_time);
-static DEFINE_PER_CPU(u64, cpu_softirq_time);
-
-static DEFINE_PER_CPU(u64, irq_start_time);
-static int sched_clock_irqtime;
-
-void enable_sched_clock_irqtime(void)
-{
- sched_clock_irqtime = 1;
-}
-
-void disable_sched_clock_irqtime(void)
-{
- sched_clock_irqtime = 0;
-}
-
-#ifndef CONFIG_64BIT
-static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
-
-static inline void irq_time_write_begin(void)
-{
- __this_cpu_inc(irq_time_seq.sequence);
- smp_wmb();
-}
-
-static inline void irq_time_write_end(void)
-{
- smp_wmb();
- __this_cpu_inc(irq_time_seq.sequence);
-}
-
-static inline u64 irq_time_read(int cpu)
-{
- u64 irq_time;
- unsigned seq;
-
- do {
- seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
- irq_time = per_cpu(cpu_softirq_time, cpu) +
- per_cpu(cpu_hardirq_time, cpu);
- } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
-
- return irq_time;
-}
-#else /* CONFIG_64BIT */
-static inline void irq_time_write_begin(void)
-{
-}
-
-static inline void irq_time_write_end(void)
-{
-}
-
-static inline u64 irq_time_read(int cpu)
-{
- return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
-}
-#endif /* CONFIG_64BIT */
-
-/*
- * Called before incrementing preempt_count on {soft,}irq_enter
- * and before decrementing preempt_count on {soft,}irq_exit.
- */
-void account_system_vtime(struct task_struct *curr)
-{
- unsigned long flags;
- s64 delta;
- int cpu;
-
- if (!sched_clock_irqtime)
- return;
-
- local_irq_save(flags);
-
- cpu = smp_processor_id();
- delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
- __this_cpu_add(irq_start_time, delta);
-
- irq_time_write_begin();
- /*
- * We do not account for softirq time from ksoftirqd here.
- * We want to continue accounting softirq time to ksoftirqd thread
- * in that case, so as not to confuse scheduler with a special task
- * that do not consume any time, but still wants to run.
- */
- if (hardirq_count())
- __this_cpu_add(cpu_hardirq_time, delta);
- else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
- __this_cpu_add(cpu_softirq_time, delta);
-
- irq_time_write_end();
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(account_system_vtime);
-
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
-{
- if (unlikely(steal > NSEC_PER_SEC))
- return div_u64(steal, TICK_NSEC);
-
- return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
-
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
/*
#endif
}
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-static int irqtime_account_hi_update(void)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
- unsigned long flags;
- u64 latest_ns;
- int ret = 0;
-
- local_irq_save(flags);
- latest_ns = this_cpu_read(cpu_hardirq_time);
- if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
- ret = 1;
- local_irq_restore(flags);
- return ret;
-}
-
-static int irqtime_account_si_update(void)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
- unsigned long flags;
- u64 latest_ns;
- int ret = 0;
-
- local_irq_save(flags);
- latest_ns = this_cpu_read(cpu_softirq_time);
- if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
- ret = 1;
- local_irq_restore(flags);
- return ret;
-}
-
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#define sched_clock_irqtime (0)
-
-#endif
-
void sched_set_stop_task(int cpu, struct task_struct *stop)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
* Manfred Spraul <manfred@colorfullife.com>
*/
prev_state = prev->state;
+ account_switch_vtime(prev);
finish_arch_switch(prev);
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
local_irq_disable();
return ns;
}
-#ifdef CONFIG_CGROUP_CPUACCT
-struct cgroup_subsys cpuacct_subsys;
-struct cpuacct root_cpuacct;
-#endif
-
-static inline void task_group_account_field(struct task_struct *p, int index,
- u64 tmp)
-{
-#ifdef CONFIG_CGROUP_CPUACCT
- struct kernel_cpustat *kcpustat;
- struct cpuacct *ca;
-#endif
- /*
- * Since all updates are sure to touch the root cgroup, we
- * get ourselves ahead and touch it first. If the root cgroup
- * is the only cgroup, then nothing else should be necessary.
- *
- */
- __get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
-
-#ifdef CONFIG_CGROUP_CPUACCT
- if (unlikely(!cpuacct_subsys.active))
- return;
-
- rcu_read_lock();
- ca = task_ca(p);
- while (ca && (ca != &root_cpuacct)) {
- kcpustat = this_cpu_ptr(ca->cpustat);
- kcpustat->cpustat[index] += tmp;
- ca = parent_ca(ca);
- }
- rcu_read_unlock();
-#endif
-}
-
-
-/*
- * Account user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- */
-void account_user_time(struct task_struct *p, cputime_t cputime,
- cputime_t cputime_scaled)
-{
- int index;
-
- /* Add user time to process. */
- p->utime += cputime;
- p->utimescaled += cputime_scaled;
- account_group_user_time(p, cputime);
-
- index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
-
- /* Add user time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
-
- /* Account for user time used */
- acct_update_integrals(p);
-}
-
-/*
- * Account guest cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in virtual machine since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- */
-static void account_guest_time(struct task_struct *p, cputime_t cputime,
- cputime_t cputime_scaled)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
-
- /* Add guest time to process. */
- p->utime += cputime;
- p->utimescaled += cputime_scaled;
- account_group_user_time(p, cputime);
- p->gtime += cputime;
-
- /* Add guest time to cpustat. */
- if (TASK_NICE(p) > 0) {
- cpustat[CPUTIME_NICE] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
- } else {
- cpustat[CPUTIME_USER] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST] += (__force u64) cputime;
- }
-}
-
-/*
- * Account system cpu time to a process and desired cpustat field
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in kernel space since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- * @target_cputime64: pointer to cpustat field that has to be updated
- */
-static inline
-void __account_system_time(struct task_struct *p, cputime_t cputime,
- cputime_t cputime_scaled, int index)
-{
- /* Add system time to process. */
- p->stime += cputime;
- p->stimescaled += cputime_scaled;
- account_group_system_time(p, cputime);
-
- /* Add system time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
-
- /* Account for system time used */
- acct_update_integrals(p);
-}
-
-/*
- * Account system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- */
-void account_system_time(struct task_struct *p, int hardirq_offset,
- cputime_t cputime, cputime_t cputime_scaled)
-{
- int index;
-
- if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
- account_guest_time(p, cputime, cputime_scaled);
- return;
- }
-
- if (hardirq_count() - hardirq_offset)
- index = CPUTIME_IRQ;
- else if (in_serving_softirq())
- index = CPUTIME_SOFTIRQ;
- else
- index = CPUTIME_SYSTEM;
-
- __account_system_time(p, cputime, cputime_scaled, index);
-}
-
-/*
- * Account for involuntary wait time.
- * @cputime: the cpu time spent in involuntary wait
- */
-void account_steal_time(cputime_t cputime)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
-
- cpustat[CPUTIME_STEAL] += (__force u64) cputime;
-}
-
-/*
- * Account for idle time.
- * @cputime: the cpu time spent in idle wait
- */
-void account_idle_time(cputime_t cputime)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
- struct rq *rq = this_rq();
-
- if (atomic_read(&rq->nr_iowait) > 0)
- cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
- else
- cpustat[CPUTIME_IDLE] += (__force u64) cputime;
-}
-
-static __always_inline bool steal_account_process_tick(void)
-{
-#ifdef CONFIG_PARAVIRT
- if (static_key_false(¶virt_steal_enabled)) {
- u64 steal, st = 0;
-
- steal = paravirt_steal_clock(smp_processor_id());
- steal -= this_rq()->prev_steal_time;
-
- st = steal_ticks(steal);
- this_rq()->prev_steal_time += st * TICK_NSEC;
-
- account_steal_time(st);
- return st;
- }
-#endif
- return false;
-}
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-/*
- * Account a tick to a process and cpustat
- * @p: the process that the cpu time gets accounted to
- * @user_tick: is the tick from userspace
- * @rq: the pointer to rq
- *
- * Tick demultiplexing follows the order
- * - pending hardirq update
- * - pending softirq update
- * - user_time
- * - idle_time
- * - system time
- * - check for guest_time
- * - else account as system_time
- *
- * Check for hardirq is done both for system and user time as there is
- * no timer going off while we are on hardirq and hence we may never get an
- * opportunity to update it solely in system time.
- * p->stime and friends are only updated on system time and not on irq
- * softirq as those do not count in task exec_runtime any more.
- */
-static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
- struct rq *rq)
-{
- cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
- u64 *cpustat = kcpustat_this_cpu->cpustat;
-
- if (steal_account_process_tick())
- return;
-
- if (irqtime_account_hi_update()) {
- cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
- } else if (irqtime_account_si_update()) {
- cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
- } else if (this_cpu_ksoftirqd() == p) {
- /*
- * ksoftirqd time do not get accounted in cpu_softirq_time.
- * So, we have to handle it separately here.
- * Also, p->stime needs to be updated for ksoftirqd.
- */
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SOFTIRQ);
- } else if (user_tick) {
- account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
- } else if (p == rq->idle) {
- account_idle_time(cputime_one_jiffy);
- } else if (p->flags & PF_VCPU) { /* System time or guest time */
- account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
- } else {
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SYSTEM);
- }
-}
-
-static void irqtime_account_idle_ticks(int ticks)
-{
- int i;
- struct rq *rq = this_rq();
-
- for (i = 0; i < ticks; i++)
- irqtime_account_process_tick(current, 0, rq);
-}
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static void irqtime_account_idle_ticks(int ticks) {}
-static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
- struct rq *rq) {}
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-/*
- * Account a single tick of cpu time.
- * @p: the process that the cpu time gets accounted to
- * @user_tick: indicates if the tick is a user or a system tick
- */
-void account_process_tick(struct task_struct *p, int user_tick)
-{
- cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
- struct rq *rq = this_rq();
-
- if (sched_clock_irqtime) {
- irqtime_account_process_tick(p, user_tick, rq);
- return;
- }
-
- if (steal_account_process_tick())
- return;
-
- if (user_tick)
- account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
- else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
- account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
- one_jiffy_scaled);
- else
- account_idle_time(cputime_one_jiffy);
-}
-
-/*
- * Account multiple ticks of steal time.
- * @p: the process from which the cpu time has been stolen
- * @ticks: number of stolen ticks
- */
-void account_steal_ticks(unsigned long ticks)
-{
- account_steal_time(jiffies_to_cputime(ticks));
-}
-
-/*
- * Account multiple ticks of idle time.
- * @ticks: number of stolen ticks
- */
-void account_idle_ticks(unsigned long ticks)
-{
-
- if (sched_clock_irqtime) {
- irqtime_account_idle_ticks(ticks);
- return;
- }
-
- account_idle_time(jiffies_to_cputime(ticks));
-}
-
-#endif
-
-/*
- * Use precise platform statistics if available:
- */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- *ut = p->utime;
- *st = p->stime;
-}
-
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- struct task_cputime cputime;
-
- thread_group_cputime(p, &cputime);
-
- *ut = cputime.utime;
- *st = cputime.stime;
-}
-#else
-
-#ifndef nsecs_to_cputime
-# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
-#endif
-
-static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
-{
- u64 temp = (__force u64) rtime;
-
- temp *= (__force u64) utime;
-
- if (sizeof(cputime_t) == 4)
- temp = div_u64(temp, (__force u32) total);
- else
- temp = div64_u64(temp, (__force u64) total);
-
- return (__force cputime_t) temp;
-}
-
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- cputime_t rtime, utime = p->utime, total = utime + p->stime;
-
- /*
- * Use CFS's precise accounting:
- */
- rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
-
- if (total)
- utime = scale_utime(utime, rtime, total);
- else
- utime = rtime;
-
- /*
- * Compare with previous values, to keep monotonicity:
- */
- p->prev_utime = max(p->prev_utime, utime);
- p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
-
- *ut = p->prev_utime;
- *st = p->prev_stime;
-}
-
-/*
- * Must be called with siglock held.
- */
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- struct signal_struct *sig = p->signal;
- struct task_cputime cputime;
- cputime_t rtime, utime, total;
-
- thread_group_cputime(p, &cputime);
-
- total = cputime.utime + cputime.stime;
- rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
-
- if (total)
- utime = scale_utime(cputime.utime, rtime, total);
- else
- utime = rtime;
-
- sig->prev_utime = max(sig->prev_utime, utime);
- sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
-
- *ut = sig->prev_utime;
- *st = sig->prev_stime;
-}
-#endif
-
/*
* This function gets called by the timer code, with HZ frequency.
* We call it with interrupts disabled.
/*
* __schedule() is the main scheduler function.
+ *
+ * The main means of driving the scheduler and thus entering this function are:
+ *
+ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
+ *
+ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
+ * paths. For example, see arch/x86/entry_64.S.
+ *
+ * To drive preemption between tasks, the scheduler sets the flag in timer
+ * interrupt handler scheduler_tick().
+ *
+ * 3. Wakeups don't really cause entry into schedule(). They add a
+ * task to the run-queue and that's it.
+ *
+ * Now, if the new task added to the run-queue preempts the current
+ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
+ * called on the nearest possible occasion:
+ *
+ * - If the kernel is preemptible (CONFIG_PREEMPT=y):
+ *
+ * - in syscall or exception context, at the next outmost
+ * preempt_enable(). (this might be as soon as the wake_up()'s
+ * spin_unlock()!)
+ *
+ * - in IRQ context, return from interrupt-handler to
+ * preemptible context
+ *
+ * - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
+ * then at the next:
+ *
+ * - cond_resched() call
+ * - explicit schedule() call
+ * - return from syscall or exception to user-space
+ * - return from interrupt-handler to user-space
*/
static void __sched __schedule(void)
{
*/
if (preempt && rq != p_rq)
resched_task(p_rq->curr);
- } else {
- /*
- * We might have set it in task_yield_fair(), but are
- * not going to schedule(), so don't want to skip
- * the next update.
- */
- rq->skip_clock_update = 0;
}
out:
}
/*
- * While a dead CPU has no uninterruptible tasks queued at this point,
- * it might still have a nonzero ->nr_uninterruptible counter, because
- * for performance reasons the counter is not stricly tracking tasks to
- * their home CPUs. So we just add the counter to another CPU's counter,
- * to keep the global sum constant after CPU-down:
- */
-static void migrate_nr_uninterruptible(struct rq *rq_src)
-{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
-
- rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
- rq_src->nr_uninterruptible = 0;
-}
-
-/*
- * remove the tasks which were accounted by rq from calc_load_tasks.
+ * Since this CPU is going 'away' for a while, fold any nr_active delta
+ * we might have. Assumes we're called after migrate_tasks() so that the
+ * nr_active count is stable.
+ *
+ * Also see the comment "Global load-average calculations".
*/
-static void calc_global_load_remove(struct rq *rq)
+static void calc_load_migrate(struct rq *rq)
{
- atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
- rq->calc_load_active = 0;
+ long delta = calc_load_fold_active(rq);
+ if (delta)
+ atomic_long_add(delta, &calc_load_tasks);
}
/*
*/
rq->stop = NULL;
- /* Ensure any throttled groups are reachable by pick_next_task */
- unthrottle_offline_cfs_rqs(rq);
-
for ( ; ; ) {
/*
* There's this thread running, bail when that's the only
*tablep = NULL;
}
+static int min_load_idx = 0;
+static int max_load_idx = CPU_LOAD_IDX_MAX;
+
static void
set_table_entry(struct ctl_table *entry,
const char *procname, void *data, int maxlen,
- umode_t mode, proc_handler *proc_handler)
+ umode_t mode, proc_handler *proc_handler,
+ bool load_idx)
{
entry->procname = procname;
entry->data = data;
entry->maxlen = maxlen;
entry->mode = mode;
entry->proc_handler = proc_handler;
+
+ if (load_idx) {
+ entry->extra1 = &min_load_idx;
+ entry->extra2 = &max_load_idx;
+ }
}
static struct ctl_table *
return NULL;
set_table_entry(&table[0], "min_interval", &sd->min_interval,
- sizeof(long), 0644, proc_doulongvec_minmax);
+ sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[1], "max_interval", &sd->max_interval,
- sizeof(long), 0644, proc_doulongvec_minmax);
+ sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, true);
set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[9], "cache_nice_tries",
&sd->cache_nice_tries,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[10], "flags", &sd->flags,
- sizeof(int), 0644, proc_dointvec_minmax);
+ sizeof(int), 0644, proc_dointvec_minmax, false);
set_table_entry(&table[11], "name", sd->name,
- CORENAME_MAX_SIZE, 0444, proc_dostring);
+ CORENAME_MAX_SIZE, 0444, proc_dostring, false);
/* &table[12] is terminator */
return table;
BUG_ON(rq->nr_running != 1); /* the migration thread */
raw_spin_unlock_irqrestore(&rq->lock, flags);
- migrate_nr_uninterruptible(rq);
- calc_global_load_remove(rq);
+ calc_load_migrate(rq);
break;
#endif
}
| 0*SD_BALANCE_FORK
| 0*SD_BALANCE_WAKE
| 0*SD_WAKE_AFFINE
- | 0*SD_PREFER_LOCAL
| 0*SD_SHARE_CPUPOWER
| 0*SD_SHARE_PKG_RESOURCES
| 1*SD_SERIALIZE
* (balbir@in.ibm.com).
*/
+struct cpuacct root_cpuacct;
+
/* create a new cpu accounting group */
static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
{
--- /dev/null
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/tsacct_kern.h>
+#include <linux/kernel_stat.h>
+#include <linux/static_key.h>
+#include "sched.h"
+
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
+ */
+DEFINE_PER_CPU(u64, cpu_hardirq_time);
+DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+static DEFINE_PER_CPU(u64, irq_start_time);
+static int sched_clock_irqtime;
+
+void enable_sched_clock_irqtime(void)
+{
+ sched_clock_irqtime = 1;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+ sched_clock_irqtime = 0;
+}
+
+#ifndef CONFIG_64BIT
+DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+#endif /* CONFIG_64BIT */
+
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
+void account_system_vtime(struct task_struct *curr)
+{
+ unsigned long flags;
+ s64 delta;
+ int cpu;
+
+ if (!sched_clock_irqtime)
+ return;
+
+ local_irq_save(flags);
+
+ cpu = smp_processor_id();
+ delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+ __this_cpu_add(irq_start_time, delta);
+
+ irq_time_write_begin();
+ /*
+ * We do not account for softirq time from ksoftirqd here.
+ * We want to continue accounting softirq time to ksoftirqd thread
+ * in that case, so as not to confuse scheduler with a special task
+ * that do not consume any time, but still wants to run.
+ */
+ if (hardirq_count())
+ __this_cpu_add(cpu_hardirq_time, delta);
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ __this_cpu_add(cpu_softirq_time, delta);
+
+ irq_time_write_end();
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(account_system_vtime);
+
+static int irqtime_account_hi_update(void)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_hardirq_time);
+ if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_softirq_time);
+ if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#define sched_clock_irqtime (0)
+
+#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
+
+static inline void task_group_account_field(struct task_struct *p, int index,
+ u64 tmp)
+{
+#ifdef CONFIG_CGROUP_CPUACCT
+ struct kernel_cpustat *kcpustat;
+ struct cpuacct *ca;
+#endif
+ /*
+ * Since all updates are sure to touch the root cgroup, we
+ * get ourselves ahead and touch it first. If the root cgroup
+ * is the only cgroup, then nothing else should be necessary.
+ *
+ */
+ __get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
+
+#ifdef CONFIG_CGROUP_CPUACCT
+ if (unlikely(!cpuacct_subsys.active))
+ return;
+
+ rcu_read_lock();
+ ca = task_ca(p);
+ while (ca && (ca != &root_cpuacct)) {
+ kcpustat = this_cpu_ptr(ca->cpustat);
+ kcpustat->cpustat[index] += tmp;
+ ca = parent_ca(ca);
+ }
+ rcu_read_unlock();
+#endif
+}
+
+/*
+ * Account user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_user_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
+{
+ int index;
+
+ /* Add user time to process. */
+ p->utime += cputime;
+ p->utimescaled += cputime_scaled;
+ account_group_user_time(p, cputime);
+
+ index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+
+ /* Add user time to cpustat. */
+ task_group_account_field(p, index, (__force u64) cputime);
+
+ /* Account for user time used */
+ acct_update_integrals(p);
+}
+
+/*
+ * Account guest cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ /* Add guest time to process. */
+ p->utime += cputime;
+ p->utimescaled += cputime_scaled;
+ account_group_user_time(p, cputime);
+ p->gtime += cputime;
+
+ /* Add guest time to cpustat. */
+ if (TASK_NICE(p) > 0) {
+ cpustat[CPUTIME_NICE] += (__force u64) cputime;
+ cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
+ } else {
+ cpustat[CPUTIME_USER] += (__force u64) cputime;
+ cpustat[CPUTIME_GUEST] += (__force u64) cputime;
+ }
+}
+
+/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled, int index)
+{
+ /* Add system time to process. */
+ p->stime += cputime;
+ p->stimescaled += cputime_scaled;
+ account_group_system_time(p, cputime);
+
+ /* Add system time to cpustat. */
+ task_group_account_field(p, index, (__force u64) cputime);
+
+ /* Account for system time used */
+ acct_update_integrals(p);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+ cputime_t cputime, cputime_t cputime_scaled)
+{
+ int index;
+
+ if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
+ account_guest_time(p, cputime, cputime_scaled);
+ return;
+ }
+
+ if (hardirq_count() - hardirq_offset)
+ index = CPUTIME_IRQ;
+ else if (in_serving_softirq())
+ index = CPUTIME_SOFTIRQ;
+ else
+ index = CPUTIME_SYSTEM;
+
+ __account_system_time(p, cputime, cputime_scaled, index);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @cputime: the cpu time spent in involuntary wait
+ */
+void account_steal_time(cputime_t cputime)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ cpustat[CPUTIME_STEAL] += (__force u64) cputime;
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+void account_idle_time(cputime_t cputime)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+ struct rq *rq = this_rq();
+
+ if (atomic_read(&rq->nr_iowait) > 0)
+ cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+ else
+ cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+}
+
+static __always_inline bool steal_account_process_tick(void)
+{
+#ifdef CONFIG_PARAVIRT
+ if (static_key_false(¶virt_steal_enabled)) {
+ u64 steal, st = 0;
+
+ steal = paravirt_steal_clock(smp_processor_id());
+ steal -= this_rq()->prev_steal_time;
+
+ st = steal_ticks(steal);
+ this_rq()->prev_steal_time += st * TICK_NSEC;
+
+ account_steal_time(st);
+ return st;
+ }
+#endif
+ return false;
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ * - check for guest_time
+ * - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq)
+{
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ if (steal_account_process_tick())
+ return;
+
+ if (irqtime_account_hi_update()) {
+ cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+ } else if (irqtime_account_si_update()) {
+ cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+ } else if (this_cpu_ksoftirqd() == p) {
+ /*
+ * ksoftirqd time do not get accounted in cpu_softirq_time.
+ * So, we have to handle it separately here.
+ * Also, p->stime needs to be updated for ksoftirqd.
+ */
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ CPUTIME_SOFTIRQ);
+ } else if (user_tick) {
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else if (p == rq->idle) {
+ account_idle_time(cputime_one_jiffy);
+ } else if (p->flags & PF_VCPU) { /* System time or guest time */
+ account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else {
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ CPUTIME_SYSTEM);
+ }
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+ int i;
+ struct rq *rq = this_rq();
+
+ for (i = 0; i < ticks; i++)
+ irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ struct rq *rq = this_rq();
+
+ if (sched_clock_irqtime) {
+ irqtime_account_process_tick(p, user_tick, rq);
+ return;
+ }
+
+ if (steal_account_process_tick())
+ return;
+
+ if (user_tick)
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+ account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
+ one_jiffy_scaled);
+ else
+ account_idle_time(cputime_one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+ account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+
+ if (sched_clock_irqtime) {
+ irqtime_account_idle_ticks(ticks);
+ return;
+ }
+
+ account_idle_time(jiffies_to_cputime(ticks));
+}
+
+#endif
+
+/*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ *ut = p->utime;
+ *st = p->stime;
+}
+
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ struct task_cputime cputime;
+
+ thread_group_cputime(p, &cputime);
+
+ *ut = cputime.utime;
+ *st = cputime.stime;
+}
+#else
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
+#endif
+
+static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total)
+{
+ u64 temp = (__force u64) rtime;
+
+ temp *= (__force u64) utime;
+
+ if (sizeof(cputime_t) == 4)
+ temp = div_u64(temp, (__force u32) total);
+ else
+ temp = div64_u64(temp, (__force u64) total);
+
+ return (__force cputime_t) temp;
+}
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ cputime_t rtime, utime = p->utime, total = utime + p->stime;
+
+ /*
+ * Use CFS's precise accounting:
+ */
+ rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
+
+ if (total)
+ utime = scale_utime(utime, rtime, total);
+ else
+ utime = rtime;
+
+ /*
+ * Compare with previous values, to keep monotonicity:
+ */
+ p->prev_utime = max(p->prev_utime, utime);
+ p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
+
+ *ut = p->prev_utime;
+ *st = p->prev_stime;
+}
+
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ struct signal_struct *sig = p->signal;
+ struct task_cputime cputime;
+ cputime_t rtime, utime, total;
+
+ thread_group_cputime(p, &cputime);
+
+ total = cputime.utime + cputime.stime;
+ rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
+
+ if (total)
+ utime = scale_utime(cputime.utime, rtime, total);
+ else
+ utime = rtime;
+
+ sig->prev_utime = max(sig->prev_utime, utime);
+ sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
+
+ *ut = sig->prev_utime;
+ *st = sig->prev_stime;
+}
+#endif
/*
* The idea is to set a period in which each task runs once.
*
- * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
+ * When there are too many tasks (sched_nr_latency) we have to stretch
* this period because otherwise the slices get too small.
*
* p = (nr <= nl) ? l : l*nr/nl
hrtimer_cancel(&cfs_b->slack_timer);
}
-void unthrottle_offline_cfs_rqs(struct rq *rq)
+static void unthrottle_offline_cfs_rqs(struct rq *rq)
{
struct cfs_rq *cfs_rq;
return NULL;
}
static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {}
-void unthrottle_offline_cfs_rqs(struct rq *rq) {}
+static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
#endif /* CONFIG_CFS_BANDWIDTH */
int prev_cpu = task_cpu(p);
int new_cpu = cpu;
int want_affine = 0;
- int want_sd = 1;
int sync = wake_flags & WF_SYNC;
if (p->nr_cpus_allowed == 1)
if (!(tmp->flags & SD_LOAD_BALANCE))
continue;
- /*
- * If power savings logic is enabled for a domain, see if we
- * are not overloaded, if so, don't balance wider.
- */
- if (tmp->flags & (SD_PREFER_LOCAL)) {
- unsigned long power = 0;
- unsigned long nr_running = 0;
- unsigned long capacity;
- int i;
-
- for_each_cpu(i, sched_domain_span(tmp)) {
- power += power_of(i);
- nr_running += cpu_rq(i)->cfs.nr_running;
- }
-
- capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE);
-
- if (nr_running < capacity)
- want_sd = 0;
- }
-
/*
* If both cpu and prev_cpu are part of this domain,
* cpu is a valid SD_WAKE_AFFINE target.
if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
affine_sd = tmp;
- want_affine = 0;
- }
-
- if (!want_sd && !want_affine)
break;
+ }
- if (!(tmp->flags & sd_flag))
- continue;
-
- if (want_sd)
+ if (tmp->flags & sd_flag)
sd = tmp;
}
if (affine_sd) {
- if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+ if (cpu != prev_cpu && wake_affine(affine_sd, p, sync))
prev_cpu = cpu;
new_cpu = select_idle_sibling(p, prev_cpu);
* @group: sched_group whose statistics are to be updated.
* @load_idx: Load index of sched_domain of this_cpu for load calc.
* @local_group: Does group contain this_cpu.
- * @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sgs: variable to hold the statistics for this group.
*/
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
- * @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
goto out_balanced;
}
- BUG_ON(busiest == this_rq);
+ BUG_ON(busiest == env.dst_rq);
schedstat_add(sd, lb_imbalance[idle], env.imbalance);
update_h_load(env.src_cpu);
more_balance:
local_irq_save(flags);
- double_rq_lock(this_rq, busiest);
+ double_rq_lock(env.dst_rq, busiest);
/*
* cur_ld_moved - load moved in current iteration
*/
cur_ld_moved = move_tasks(&env);
ld_moved += cur_ld_moved;
- double_rq_unlock(this_rq, busiest);
+ double_rq_unlock(env.dst_rq, busiest);
local_irq_restore(flags);
if (env.flags & LBF_NEED_BREAK) {
if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 &&
lb_iterations++ < max_lb_iterations) {
- this_rq = cpu_rq(env.new_dst_cpu);
- env.dst_rq = this_rq;
+ env.dst_rq = cpu_rq(env.new_dst_cpu);
env.dst_cpu = env.new_dst_cpu;
env.flags &= ~LBF_SOME_PINNED;
env.loop = 0;
static void rq_offline_fair(struct rq *rq)
{
update_sysctl();
+
+ /* Ensure any throttled groups are reachable by pick_next_task */
+ unthrottle_offline_cfs_rqs(rq);
}
#endif /* CONFIG_SMP */
*/
SCHED_FEAT(START_DEBIT, true)
-/*
- * Based on load and program behaviour, see if it makes sense to place
- * a newly woken task on the same cpu as the task that woke it --
- * improve cache locality. Typically used with SYNC wakeups as
- * generated by pipes and the like, see also SYNC_WAKEUPS.
- */
-SCHED_FEAT(AFFINE_WAKEUPS, true)
-
/*
* Prefer to schedule the task we woke last (assuming it failed
* wakeup-preemption), since its likely going to consume data we
* runtime - in which case borrowing doesn't make sense.
*/
rt_rq->rt_runtime = RUNTIME_INF;
+ rt_rq->rt_throttled = 0;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
struct kernel_cpustat __percpu *cpustat;
};
+extern struct cgroup_subsys cpuacct_subsys;
+extern struct cpuacct root_cpuacct;
+
/* return cpu accounting group corresponding to this container */
static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
{
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#endif
+#ifdef CONFIG_PARAVIRT
+static inline u64 steal_ticks(u64 steal)
+{
+ if (unlikely(steal > NSEC_PER_SEC))
+ return div_u64(steal, TICK_NSEC);
+
+ return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
+}
+#endif
+
static inline void inc_nr_running(struct rq *rq)
{
rq->nr_running++;
extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
-extern void unthrottle_offline_cfs_rqs(struct rq *rq);
extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
#endif
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+DECLARE_PER_CPU(u64, cpu_hardirq_time);
+DECLARE_PER_CPU(u64, cpu_softirq_time);
+
+#ifndef CONFIG_64BIT
+DECLARE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
+{
+ __this_cpu_inc(irq_time_seq.sequence);
+ smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+ smp_wmb();
+ __this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+ u64 irq_time;
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+ irq_time = per_cpu(cpu_softirq_time, cpu) +
+ per_cpu(cpu_hardirq_time, cpu);
+ } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+ return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+ return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+#endif /* CONFIG_64BIT */
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
/*
* Common SMP CPU bringup/teardown functions
*/
+#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/smp.h>
#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/slab.h>
#include <linux/sched.h>
+#include <linux/export.h>
#include <linux/percpu.h>
+#include <linux/kthread.h>
+#include <linux/smpboot.h>
#include "smpboot.h"
+#ifdef CONFIG_SMP
+
#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD
/*
* For the hotplug case we keep the task structs around and reuse
}
}
#endif
+
+#endif /* #ifdef CONFIG_SMP */
+
+static LIST_HEAD(hotplug_threads);
+static DEFINE_MUTEX(smpboot_threads_lock);
+
+struct smpboot_thread_data {
+ unsigned int cpu;
+ unsigned int status;
+ struct smp_hotplug_thread *ht;
+};
+
+enum {
+ HP_THREAD_NONE = 0,
+ HP_THREAD_ACTIVE,
+ HP_THREAD_PARKED,
+};
+
+/**
+ * smpboot_thread_fn - percpu hotplug thread loop function
+ * @data: thread data pointer
+ *
+ * Checks for thread stop and park conditions. Calls the necessary
+ * setup, cleanup, park and unpark functions for the registered
+ * thread.
+ *
+ * Returns 1 when the thread should exit, 0 otherwise.
+ */
+static int smpboot_thread_fn(void *data)
+{
+ struct smpboot_thread_data *td = data;
+ struct smp_hotplug_thread *ht = td->ht;
+
+ while (1) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ preempt_disable();
+ if (kthread_should_stop()) {
+ set_current_state(TASK_RUNNING);
+ preempt_enable();
+ if (ht->cleanup)
+ ht->cleanup(td->cpu, cpu_online(td->cpu));
+ kfree(td);
+ return 0;
+ }
+
+ if (kthread_should_park()) {
+ __set_current_state(TASK_RUNNING);
+ preempt_enable();
+ if (ht->park && td->status == HP_THREAD_ACTIVE) {
+ BUG_ON(td->cpu != smp_processor_id());
+ ht->park(td->cpu);
+ td->status = HP_THREAD_PARKED;
+ }
+ kthread_parkme();
+ /* We might have been woken for stop */
+ continue;
+ }
+
+ BUG_ON(td->cpu != smp_processor_id());
+
+ /* Check for state change setup */
+ switch (td->status) {
+ case HP_THREAD_NONE:
+ preempt_enable();
+ if (ht->setup)
+ ht->setup(td->cpu);
+ td->status = HP_THREAD_ACTIVE;
+ preempt_disable();
+ break;
+ case HP_THREAD_PARKED:
+ preempt_enable();
+ if (ht->unpark)
+ ht->unpark(td->cpu);
+ td->status = HP_THREAD_ACTIVE;
+ preempt_disable();
+ break;
+ }
+
+ if (!ht->thread_should_run(td->cpu)) {
+ preempt_enable();
+ schedule();
+ } else {
+ set_current_state(TASK_RUNNING);
+ preempt_enable();
+ ht->thread_fn(td->cpu);
+ }
+ }
+}
+
+static int
+__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+ struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+ struct smpboot_thread_data *td;
+
+ if (tsk)
+ return 0;
+
+ td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu));
+ if (!td)
+ return -ENOMEM;
+ td->cpu = cpu;
+ td->ht = ht;
+
+ tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu,
+ ht->thread_comm);
+ if (IS_ERR(tsk)) {
+ kfree(td);
+ return PTR_ERR(tsk);
+ }
+
+ get_task_struct(tsk);
+ *per_cpu_ptr(ht->store, cpu) = tsk;
+ return 0;
+}
+
+int smpboot_create_threads(unsigned int cpu)
+{
+ struct smp_hotplug_thread *cur;
+ int ret = 0;
+
+ mutex_lock(&smpboot_threads_lock);
+ list_for_each_entry(cur, &hotplug_threads, list) {
+ ret = __smpboot_create_thread(cur, cpu);
+ if (ret)
+ break;
+ }
+ mutex_unlock(&smpboot_threads_lock);
+ return ret;
+}
+
+static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+ struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+ kthread_unpark(tsk);
+}
+
+void smpboot_unpark_threads(unsigned int cpu)
+{
+ struct smp_hotplug_thread *cur;
+
+ mutex_lock(&smpboot_threads_lock);
+ list_for_each_entry(cur, &hotplug_threads, list)
+ smpboot_unpark_thread(cur, cpu);
+ mutex_unlock(&smpboot_threads_lock);
+}
+
+static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
+{
+ struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+ if (tsk)
+ kthread_park(tsk);
+}
+
+void smpboot_park_threads(unsigned int cpu)
+{
+ struct smp_hotplug_thread *cur;
+
+ mutex_lock(&smpboot_threads_lock);
+ list_for_each_entry_reverse(cur, &hotplug_threads, list)
+ smpboot_park_thread(cur, cpu);
+ mutex_unlock(&smpboot_threads_lock);
+}
+
+static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
+{
+ unsigned int cpu;
+
+ /* We need to destroy also the parked threads of offline cpus */
+ for_each_possible_cpu(cpu) {
+ struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
+
+ if (tsk) {
+ kthread_stop(tsk);
+ put_task_struct(tsk);
+ *per_cpu_ptr(ht->store, cpu) = NULL;
+ }
+ }
+}
+
+/**
+ * smpboot_register_percpu_thread - Register a per_cpu thread related to hotplug
+ * @plug_thread: Hotplug thread descriptor
+ *
+ * Creates and starts the threads on all online cpus.
+ */
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
+{
+ unsigned int cpu;
+ int ret = 0;
+
+ mutex_lock(&smpboot_threads_lock);
+ for_each_online_cpu(cpu) {
+ ret = __smpboot_create_thread(plug_thread, cpu);
+ if (ret) {
+ smpboot_destroy_threads(plug_thread);
+ goto out;
+ }
+ smpboot_unpark_thread(plug_thread, cpu);
+ }
+ list_add(&plug_thread->list, &hotplug_threads);
+out:
+ mutex_unlock(&smpboot_threads_lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
+
+/**
+ * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
+ * @plug_thread: Hotplug thread descriptor
+ *
+ * Stops all threads on all possible cpus.
+ */
+void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
+{
+ get_online_cpus();
+ mutex_lock(&smpboot_threads_lock);
+ list_del(&plug_thread->list);
+ smpboot_destroy_threads(plug_thread);
+ mutex_unlock(&smpboot_threads_lock);
+ put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
static inline void idle_threads_init(void) { }
#endif
+int smpboot_create_threads(unsigned int cpu);
+void smpboot_park_threads(unsigned int cpu);
+void smpboot_unpark_threads(unsigned int cpu);
+
#endif
#include <linux/rcupdate.h>
#include <linux/ftrace.h>
#include <linux/smp.h>
+#include <linux/smpboot.h>
#include <linux/tick.h>
#define CREATE_TRACE_POINTS
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
-static int run_ksoftirqd(void * __bind_cpu)
+static int ksoftirqd_should_run(unsigned int cpu)
{
- set_current_state(TASK_INTERRUPTIBLE);
-
- while (!kthread_should_stop()) {
- preempt_disable();
- if (!local_softirq_pending()) {
- schedule_preempt_disabled();
- }
-
- __set_current_state(TASK_RUNNING);
-
- while (local_softirq_pending()) {
- /* Preempt disable stops cpu going offline.
- If already offline, we'll be on wrong CPU:
- don't process */
- if (cpu_is_offline((long)__bind_cpu))
- goto wait_to_die;
- local_irq_disable();
- if (local_softirq_pending())
- __do_softirq();
- local_irq_enable();
- sched_preempt_enable_no_resched();
- cond_resched();
- preempt_disable();
- rcu_note_context_switch((long)__bind_cpu);
- }
- preempt_enable();
- set_current_state(TASK_INTERRUPTIBLE);
- }
- __set_current_state(TASK_RUNNING);
- return 0;
+ return local_softirq_pending();
+}
-wait_to_die:
- preempt_enable();
- /* Wait for kthread_stop */
- set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
- schedule();
- set_current_state(TASK_INTERRUPTIBLE);
+static void run_ksoftirqd(unsigned int cpu)
+{
+ local_irq_disable();
+ if (local_softirq_pending()) {
+ __do_softirq();
+ rcu_note_context_switch(cpu);
+ local_irq_enable();
+ cond_resched();
+ return;
}
- __set_current_state(TASK_RUNNING);
- return 0;
+ local_irq_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
unsigned long action,
void *hcpu)
{
- int hotcpu = (unsigned long)hcpu;
- struct task_struct *p;
-
switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- p = kthread_create_on_node(run_ksoftirqd,
- hcpu,
- cpu_to_node(hotcpu),
- "ksoftirqd/%d", hotcpu);
- if (IS_ERR(p)) {
- printk("ksoftirqd for %i failed\n", hotcpu);
- return notifier_from_errno(PTR_ERR(p));
- }
- kthread_bind(p, hotcpu);
- per_cpu(ksoftirqd, hotcpu) = p;
- break;
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- wake_up_process(per_cpu(ksoftirqd, hotcpu));
- break;
#ifdef CONFIG_HOTPLUG_CPU
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- if (!per_cpu(ksoftirqd, hotcpu))
- break;
- /* Unbind so it can run. Fall thru. */
- kthread_bind(per_cpu(ksoftirqd, hotcpu),
- cpumask_any(cpu_online_mask));
case CPU_DEAD:
- case CPU_DEAD_FROZEN: {
- static const struct sched_param param = {
- .sched_priority = MAX_RT_PRIO-1
- };
-
- p = per_cpu(ksoftirqd, hotcpu);
- per_cpu(ksoftirqd, hotcpu) = NULL;
- sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
- kthread_stop(p);
- takeover_tasklets(hotcpu);
+ case CPU_DEAD_FROZEN:
+ takeover_tasklets((unsigned long)hcpu);
break;
- }
#endif /* CONFIG_HOTPLUG_CPU */
- }
+ }
return NOTIFY_OK;
}
.notifier_call = cpu_callback
};
+static struct smp_hotplug_thread softirq_threads = {
+ .store = &ksoftirqd,
+ .thread_should_run = ksoftirqd_should_run,
+ .thread_fn = run_ksoftirqd,
+ .thread_comm = "ksoftirqd/%u",
+};
+
static __init int spawn_ksoftirqd(void)
{
- void *cpu = (void *)(long)smp_processor_id();
- int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
-
- BUG_ON(err != NOTIFY_OK);
- cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
register_cpu_notifier(&cpu_nfb);
+
+ BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
+
return 0;
}
early_initcall(spawn_ksoftirqd);
.extra2 = &max_sched_tunable_scaling,
},
{
- .procname = "sched_migration_cost",
+ .procname = "sched_migration_cost_ns",
.data = &sysctl_sched_migration_cost,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .procname = "sched_time_avg",
+ .procname = "sched_time_avg_ms",
.data = &sysctl_sched_time_avg,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .procname = "sched_shares_window",
+ .procname = "sched_shares_window_ns",
.data = &sysctl_sched_shares_window,
.maxlen = sizeof(unsigned int),
.mode = 0644,
tick_do_update_jiffies64(now);
update_cpu_load_nohz();
+ calc_load_exit_idle();
touch_softlockup_watchdog();
/*
* Cancel the scheduled timer and restore the tick
/* Functions below help us manage 'deferrable' flag */
static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
{
- return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG);
+ return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE);
}
-static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
+static inline unsigned int tbase_get_irqsafe(struct tvec_base *base)
{
- return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG));
+ return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE);
}
-static inline void timer_set_deferrable(struct timer_list *timer)
+static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
{
- timer->base = TBASE_MAKE_DEFERRED(timer->base);
+ return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK));
}
static inline void
timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
{
- timer->base = (struct tvec_base *)((unsigned long)(new_base) |
- tbase_get_deferrable(timer->base));
+ unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK;
+
+ timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags);
}
static unsigned long round_jiffies_common(unsigned long j, int cpu,
debug_object_assert_init(timer, &timer_debug_descr);
}
-static void __init_timer(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key);
+static void do_init_timer(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key);
-void init_timer_on_stack_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key)
+void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key)
{
debug_object_init_on_stack(timer, &timer_debug_descr);
- __init_timer(timer, name, key);
+ do_init_timer(timer, flags, name, key);
}
EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
debug_timer_assert_init(timer);
}
-static void __init_timer(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key)
+static void do_init_timer(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key)
{
+ struct tvec_base *base = __raw_get_cpu_var(tvec_bases);
+
timer->entry.next = NULL;
- timer->base = __raw_get_cpu_var(tvec_bases);
+ timer->base = (void *)((unsigned long)base | flags);
timer->slack = -1;
#ifdef CONFIG_TIMER_STATS
timer->start_site = NULL;
lockdep_init_map(&timer->lockdep_map, name, key, 0);
}
-void setup_deferrable_timer_on_stack_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key,
- void (*function)(unsigned long),
- unsigned long data)
-{
- timer->function = function;
- timer->data = data;
- init_timer_on_stack_key(timer, name, key);
- timer_set_deferrable(timer);
-}
-EXPORT_SYMBOL_GPL(setup_deferrable_timer_on_stack_key);
-
/**
* init_timer_key - initialize a timer
* @timer: the timer to be initialized
+ * @flags: timer flags
* @name: name of the timer
* @key: lockdep class key of the fake lock used for tracking timer
* sync lock dependencies
* init_timer_key() must be done to a timer prior calling *any* of the
* other timer functions.
*/
-void init_timer_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key)
+void init_timer_key(struct timer_list *timer, unsigned int flags,
+ const char *name, struct lock_class_key *key)
{
debug_init(timer);
- __init_timer(timer, name, key);
+ do_init_timer(timer, flags, name, key);
}
EXPORT_SYMBOL(init_timer_key);
-void init_timer_deferrable_key(struct timer_list *timer,
- const char *name,
- struct lock_class_key *key)
-{
- init_timer_key(timer, name, key);
- timer_set_deferrable(timer);
-}
-EXPORT_SYMBOL(init_timer_deferrable_key);
-
static inline void detach_timer(struct timer_list *timer, bool clear_pending)
{
struct list_head *entry = &timer->entry;
{
detach_timer(timer, true);
if (!tbase_get_deferrable(timer->base))
- timer->base->active_timers--;
+ base->active_timers--;
}
static int detach_if_pending(struct timer_list *timer, struct tvec_base *base,
detach_timer(timer, clear_pending);
if (!tbase_get_deferrable(timer->base)) {
- timer->base->active_timers--;
+ base->active_timers--;
if (timer->expires == base->next_timer)
base->next_timer = base->timer_jiffies;
}
*
* Synchronization rules: Callers must prevent restarting of the timer,
* otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which would prevent
- * completion of the timer's handler. The timer's handler must not call
- * add_timer_on(). Upon exit the timer is not queued and the handler is
- * not running on any CPU.
+ * interrupt contexts unless the timer is an irqsafe one. The caller must
+ * not hold locks which would prevent completion of the timer's
+ * handler. The timer's handler must not call add_timer_on(). Upon exit the
+ * timer is not queued and the handler is not running on any CPU.
*
- * Note: You must not hold locks that are held in interrupt context
- * while calling this function. Even if the lock has nothing to do
- * with the timer in question. Here's why:
+ * Note: For !irqsafe timers, you must not hold locks that are held in
+ * interrupt context while calling this function. Even if the lock has
+ * nothing to do with the timer in question. Here's why:
*
* CPU0 CPU1
* ---- ----
* don't use it in hardirq context, because it
* could lead to deadlock.
*/
- WARN_ON(in_irq());
+ WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base));
for (;;) {
int ret = try_to_del_timer_sync(timer);
if (ret >= 0)
while (!list_empty(head)) {
void (*fn)(unsigned long);
unsigned long data;
+ bool irqsafe;
timer = list_first_entry(head, struct timer_list,entry);
fn = timer->function;
data = timer->data;
+ irqsafe = tbase_get_irqsafe(timer->base);
timer_stats_account_timer(timer);
base->running_timer = timer;
detach_expired_timer(timer, base);
- spin_unlock_irq(&base->lock);
- call_timer_fn(timer, fn, data);
- spin_lock_irq(&base->lock);
+ if (irqsafe) {
+ spin_unlock(&base->lock);
+ call_timer_fn(timer, fn, data);
+ spin_lock(&base->lock);
+ } else {
+ spin_unlock_irq(&base->lock);
+ call_timer_fn(timer, fn, data);
+ spin_lock_irq(&base->lock);
+ }
}
}
base->running_timer = NULL;
void __init init_timers(void)
{
- int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
- (void *)(long)smp_processor_id());
+ int err;
+
+ /* ensure there are enough low bits for flags in timer->base pointer */
+ BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK);
+ err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
+ (void *)(long)smp_processor_id());
init_timer_stats();
BUG_ON(err != NOTIFY_OK);
help
See Documentation/trace/ftrace-design.txt
+config HAVE_FENTRY
+ bool
+ help
+ Arch supports the gcc options -pg with -mfentry
+
config HAVE_C_RECORDMCOUNT
bool
help
ORIG_CFLAGS := $(KBUILD_CFLAGS)
KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS))
+ifdef CONFIG_FTRACE_SELFTEST
# selftest needs instrumentation
CFLAGS_trace_selftest_dynamic.o = -pg
obj-y += trace_selftest_dynamic.o
endif
+endif
# If unlikely tracing is enabled, do not trace these files
ifdef CONFIG_TRACING_BRANCHES
#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
+static struct ftrace_ops ftrace_list_end __read_mostly = {
+ .func = ftrace_stub,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
/* ftrace_enabled is a method to turn ftrace on or off */
int ftrace_enabled __read_mostly;
static int last_ftrace_enabled;
/* Quick disabling of function tracer. */
-int function_trace_stop;
+int function_trace_stop __read_mostly;
+
+/* Current function tracing op */
+struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
static DEFINE_MUTEX(ftrace_lock);
-static struct ftrace_ops ftrace_list_end __read_mostly = {
- .func = ftrace_stub,
-};
-
static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
-static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
-ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
static struct ftrace_ops global_ops;
static struct ftrace_ops control_ops;
-static void
-ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
+#if ARCH_SUPPORTS_FTRACE_OPS
+static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs);
+#else
+/* See comment below, where ftrace_ops_list_func is defined */
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
+#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
+#endif
+
+/**
+ * ftrace_nr_registered_ops - return number of ops registered
+ *
+ * Returns the number of ftrace_ops registered and tracing functions
+ */
+int ftrace_nr_registered_ops(void)
+{
+ struct ftrace_ops *ops;
+ int cnt = 0;
+
+ mutex_lock(&ftrace_lock);
+
+ for (ops = ftrace_ops_list;
+ ops != &ftrace_list_end; ops = ops->next)
+ cnt++;
+
+ mutex_unlock(&ftrace_lock);
+
+ return cnt;
+}
/*
* Traverse the ftrace_global_list, invoking all entries. The reason that we
*
* Silly Alpha and silly pointer-speculation compiler optimizations!
*/
-static void ftrace_global_list_func(unsigned long ip,
- unsigned long parent_ip)
+static void
+ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs)
{
- struct ftrace_ops *op;
-
if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
return;
trace_recursion_set(TRACE_GLOBAL_BIT);
op = rcu_dereference_raw(ftrace_global_list); /*see above*/
while (op != &ftrace_list_end) {
- op->func(ip, parent_ip);
+ op->func(ip, parent_ip, op, regs);
op = rcu_dereference_raw(op->next); /*see above*/
};
trace_recursion_clear(TRACE_GLOBAL_BIT);
}
-static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
+static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs)
{
if (!test_tsk_trace_trace(current))
return;
- ftrace_pid_function(ip, parent_ip);
+ ftrace_pid_function(ip, parent_ip, op, regs);
}
static void set_ftrace_pid_function(ftrace_func_t func)
void clear_ftrace_function(void)
{
ftrace_trace_function = ftrace_stub;
- __ftrace_trace_function = ftrace_stub;
- __ftrace_trace_function_delay = ftrace_stub;
ftrace_pid_function = ftrace_stub;
}
-#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
-/*
- * For those archs that do not test ftrace_trace_stop in their
- * mcount call site, we need to do it from C.
- */
-static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
-{
- if (function_trace_stop)
- return;
-
- __ftrace_trace_function(ip, parent_ip);
-}
-#endif
-
static void control_ops_disable_all(struct ftrace_ops *ops)
{
int cpu;
/*
* If we are at the end of the list and this ops is
- * not dynamic, then have the mcount trampoline call
- * the function directly
+ * recursion safe and not dynamic and the arch supports passing ops,
+ * then have the mcount trampoline call the function directly.
*/
if (ftrace_ops_list == &ftrace_list_end ||
(ftrace_ops_list->next == &ftrace_list_end &&
- !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC)))
+ !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) &&
+ (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) &&
+ !FTRACE_FORCE_LIST_FUNC)) {
+ /* Set the ftrace_ops that the arch callback uses */
+ if (ftrace_ops_list == &global_ops)
+ function_trace_op = ftrace_global_list;
+ else
+ function_trace_op = ftrace_ops_list;
func = ftrace_ops_list->func;
- else
+ } else {
+ /* Just use the default ftrace_ops */
+ function_trace_op = &ftrace_list_end;
func = ftrace_ops_list_func;
+ }
-#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
ftrace_trace_function = func;
-#else
-#ifdef CONFIG_DYNAMIC_FTRACE
- /* do not update till all functions have been modified */
- __ftrace_trace_function_delay = func;
-#else
- __ftrace_trace_function = func;
-#endif
- ftrace_trace_function =
- (func == ftrace_stub) ? func : ftrace_test_stop_func;
-#endif
}
static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
return -EINVAL;
+#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+ /*
+ * If the ftrace_ops specifies SAVE_REGS, then it only can be used
+ * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set.
+ * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant.
+ */
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS &&
+ !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED))
+ return -EINVAL;
+
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)
+ ops->flags |= FTRACE_OPS_FL_SAVE_REGS;
+#endif
+
if (!core_kernel_data((unsigned long)ops))
ops->flags |= FTRACE_OPS_FL_DYNAMIC;
}
static void
-function_profile_call(unsigned long ip, unsigned long parent_ip)
+function_profile_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct pt_regs *regs)
{
struct ftrace_profile_stat *stat;
struct ftrace_profile *rec;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int profile_graph_entry(struct ftrace_graph_ent *trace)
{
- function_profile_call(trace->func, 0);
+ function_profile_call(trace->func, 0, NULL, NULL);
return 1;
}
#else
static struct ftrace_ops ftrace_profile_ops __read_mostly = {
.func = function_profile_call,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static int register_ftrace_profiler(void)
.func = ftrace_stub,
.notrace_hash = EMPTY_HASH,
.filter_hash = EMPTY_HASH,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static DEFINE_MUTEX(ftrace_regex_lock);
rec->flags++;
if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX))
return;
+ /*
+ * If any ops wants regs saved for this function
+ * then all ops will get saved regs.
+ */
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+ rec->flags |= FTRACE_FL_REGS;
} else {
if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0))
return;
if (enable && (rec->flags & ~FTRACE_FL_MASK))
flag = FTRACE_FL_ENABLED;
+ /*
+ * If enabling and the REGS flag does not match the REGS_EN, then
+ * do not ignore this record. Set flags to fail the compare against
+ * ENABLED.
+ */
+ if (flag &&
+ (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)))
+ flag |= FTRACE_FL_REGS;
+
/* If the state of this record hasn't changed, then do nothing */
if ((rec->flags & FTRACE_FL_ENABLED) == flag)
return FTRACE_UPDATE_IGNORE;
if (flag) {
- if (update)
+ /* Save off if rec is being enabled (for return value) */
+ flag ^= rec->flags & FTRACE_FL_ENABLED;
+
+ if (update) {
rec->flags |= FTRACE_FL_ENABLED;
- return FTRACE_UPDATE_MAKE_CALL;
+ if (flag & FTRACE_FL_REGS) {
+ if (rec->flags & FTRACE_FL_REGS)
+ rec->flags |= FTRACE_FL_REGS_EN;
+ else
+ rec->flags &= ~FTRACE_FL_REGS_EN;
+ }
+ }
+
+ /*
+ * If this record is being updated from a nop, then
+ * return UPDATE_MAKE_CALL.
+ * Otherwise, if the EN flag is set, then return
+ * UPDATE_MODIFY_CALL_REGS to tell the caller to convert
+ * from the non-save regs, to a save regs function.
+ * Otherwise,
+ * return UPDATE_MODIFY_CALL to tell the caller to convert
+ * from the save regs, to a non-save regs function.
+ */
+ if (flag & FTRACE_FL_ENABLED)
+ return FTRACE_UPDATE_MAKE_CALL;
+ else if (rec->flags & FTRACE_FL_REGS_EN)
+ return FTRACE_UPDATE_MODIFY_CALL_REGS;
+ else
+ return FTRACE_UPDATE_MODIFY_CALL;
}
- if (update)
- rec->flags &= ~FTRACE_FL_ENABLED;
+ if (update) {
+ /* If there's no more users, clear all flags */
+ if (!(rec->flags & ~FTRACE_FL_MASK))
+ rec->flags = 0;
+ else
+ /* Just disable the record (keep REGS state) */
+ rec->flags &= ~FTRACE_FL_ENABLED;
+ }
return FTRACE_UPDATE_MAKE_NOP;
}
static int
__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
{
+ unsigned long ftrace_old_addr;
unsigned long ftrace_addr;
int ret;
- ftrace_addr = (unsigned long)FTRACE_ADDR;
-
ret = ftrace_update_record(rec, enable);
+ if (rec->flags & FTRACE_FL_REGS)
+ ftrace_addr = (unsigned long)FTRACE_REGS_ADDR;
+ else
+ ftrace_addr = (unsigned long)FTRACE_ADDR;
+
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
case FTRACE_UPDATE_MAKE_NOP:
return ftrace_make_nop(NULL, rec, ftrace_addr);
+
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
+ if (rec->flags & FTRACE_FL_REGS)
+ ftrace_old_addr = (unsigned long)FTRACE_ADDR;
+ else
+ ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR;
+
+ return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
}
return -1; /* unknow ftrace bug */
*/
arch_ftrace_update_code(command);
-#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
- /*
- * For archs that call ftrace_test_stop_func(), we must
- * wait till after we update all the function callers
- * before we update the callback. This keeps different
- * ops that record different functions from corrupting
- * each other.
- */
- __ftrace_trace_function = __ftrace_trace_function_delay;
-#endif
function_trace_stop--;
ret = ftrace_arch_code_modify_post_process();
seq_printf(m, "%ps", (void *)rec->ip);
if (iter->flags & FTRACE_ITER_ENABLED)
- seq_printf(m, " (%ld)",
- rec->flags & ~FTRACE_FL_MASK);
+ seq_printf(m, " (%ld)%s",
+ rec->flags & ~FTRACE_FL_MASK,
+ rec->flags & FTRACE_FL_REGS ? " R" : "");
seq_printf(m, "\n");
return 0;
}
device_initcall(ftrace_mod_cmd_init);
-static void
-function_trace_probe_call(unsigned long ip, unsigned long parent_ip)
+static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct ftrace_func_probe *entry;
struct hlist_head *hhd;
}
static int
-ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
- int reset, int enable)
+ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
+{
+ struct ftrace_func_entry *entry;
+
+ if (!ftrace_location(ip))
+ return -EINVAL;
+
+ if (remove) {
+ entry = ftrace_lookup_ip(hash, ip);
+ if (!entry)
+ return -ENOENT;
+ free_hash_entry(hash, entry);
+ return 0;
+ }
+
+ return add_hash_entry(hash, ip);
+}
+
+static int
+ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
+ unsigned long ip, int remove, int reset, int enable)
{
struct ftrace_hash **orig_hash;
struct ftrace_hash *hash;
ret = -EINVAL;
goto out_regex_unlock;
}
+ if (ip) {
+ ret = ftrace_match_addr(hash, ip, remove);
+ if (ret < 0)
+ goto out_regex_unlock;
+ }
mutex_lock(&ftrace_lock);
ret = ftrace_hash_move(ops, enable, orig_hash, hash);
return ret;
}
+static int
+ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove,
+ int reset, int enable)
+{
+ return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable);
+}
+
+/**
+ * ftrace_set_filter_ip - set a function to filter on in ftrace by address
+ * @ops - the ops to set the filter with
+ * @ip - the address to add to or remove from the filter.
+ * @remove - non zero to remove the ip from the filter
+ * @reset - non zero to reset all filters before applying this filter.
+ *
+ * Filters denote which functions should be enabled when tracing is enabled
+ * If @ip is NULL, it failes to update filter.
+ */
+int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip,
+ int remove, int reset)
+{
+ return ftrace_set_addr(ops, ip, remove, reset, 1);
+}
+EXPORT_SYMBOL_GPL(ftrace_set_filter_ip);
+
+static int
+ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
+ int reset, int enable)
+{
+ return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable);
+}
+
/**
* ftrace_set_filter - set a function to filter on in ftrace
* @ops - the ops to set the filter with
static struct ftrace_ops global_ops = {
.func = ftrace_stub,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static int __init ftrace_nodyn_init(void)
#endif /* CONFIG_DYNAMIC_FTRACE */
static void
-ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
+ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs)
{
- struct ftrace_ops *op;
-
if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
return;
while (op != &ftrace_list_end) {
if (!ftrace_function_local_disabled(op) &&
ftrace_ops_test(op, ip))
- op->func(ip, parent_ip);
+ op->func(ip, parent_ip, op, regs);
op = rcu_dereference_raw(op->next);
};
static struct ftrace_ops control_ops = {
.func = ftrace_ops_control_func,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
-static void
-ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
+static inline void
+__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ignored, struct pt_regs *regs)
{
struct ftrace_ops *op;
+ if (function_trace_stop)
+ return;
+
if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
return;
op = rcu_dereference_raw(ftrace_ops_list);
while (op != &ftrace_list_end) {
if (ftrace_ops_test(op, ip))
- op->func(ip, parent_ip);
+ op->func(ip, parent_ip, op, regs);
op = rcu_dereference_raw(op->next);
};
preempt_enable_notrace();
trace_recursion_clear(TRACE_INTERNAL_BIT);
}
+/*
+ * Some archs only support passing ip and parent_ip. Even though
+ * the list function ignores the op parameter, we do not want any
+ * C side effects, where a function is called without the caller
+ * sending a third parameter.
+ * Archs are to support both the regs and ftrace_ops at the same time.
+ * If they support ftrace_ops, it is assumed they support regs.
+ * If call backs want to use regs, they must either check for regs
+ * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS.
+ * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved.
+ * An architecture can pass partial regs with ftrace_ops and still
+ * set the ARCH_SUPPORT_FTARCE_OPS.
+ */
+#if ARCH_SUPPORTS_FTRACE_OPS
+static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *regs)
+{
+ __ftrace_ops_list_func(ip, parent_ip, NULL, regs);
+}
+#else
+static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
+{
+ __ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
+}
+#endif
+
static void clear_ftrace_swapper(void)
{
struct task_struct *p;
* to the buffer after this will fail and return NULL.
*
* This is different than ring_buffer_record_disable() as
- * it works like an on/off switch, where as the disable() verison
+ * it works like an on/off switch, where as the disable() version
* must be paired with a enable().
*/
void ring_buffer_record_off(struct ring_buffer *buffer)
* ring_buffer_record_off().
*
* This is different than ring_buffer_record_enable() as
- * it works like an on/off switch, where as the enable() verison
+ * it works like an on/off switch, where as the enable() version
* must be paired with a disable().
*/
void ring_buffer_record_on(struct ring_buffer *buffer)
static int __init set_tracing_thresh(char *str)
{
- unsigned long threshhold;
+ unsigned long threshold;
int ret;
if (!str)
return 0;
- ret = strict_strtoul(str, 0, &threshhold);
+ ret = strict_strtoul(str, 0, &threshold);
if (ret < 0)
return 0;
- tracing_thresh = threshhold * 1000;
+ tracing_thresh = threshold * 1000;
return 1;
}
__setup("tracing_thresh=", set_tracing_thresh);
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
+#endif
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
extern int DYN_FTRACE_TEST_NAME(void);
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
-#endif
extern int ring_buffer_expanded;
extern bool tracing_selftest_disabled;
#ifdef CONFIG_FUNCTION_TRACER
static void
-perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct pt_regs *pt_regs)
{
struct ftrace_entry *entry;
struct hlist_head *head;
static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
static void
-function_test_events_call(unsigned long ip, unsigned long parent_ip)
+function_test_events_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct ring_buffer_event *event;
struct ring_buffer *buffer;
static struct ftrace_ops trace_ops __initdata =
{
.func = function_test_events_call,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static __init void event_trace_self_test_with_function(void)
static int __ftrace_function_set_filter(int filter, char *buf, int len,
struct function_filter_data *data)
{
- int i, re_cnt, ret;
+ int i, re_cnt, ret = -EINVAL;
int *reset;
char **re;
}
static void
-function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
+function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = func_trace;
struct trace_array_cpu *data;
static struct tracer_flags func_flags;
static void
-function_trace_call(unsigned long ip, unsigned long parent_ip)
+function_trace_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
+
{
struct trace_array *tr = func_trace;
struct trace_array_cpu *data;
}
static void
-function_stack_trace_call(unsigned long ip, unsigned long parent_ip)
+function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = func_trace;
struct trace_array_cpu *data;
static struct ftrace_ops trace_ops __read_mostly =
{
.func = function_trace_call,
- .flags = FTRACE_OPS_FL_GLOBAL,
+ .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
};
static struct ftrace_ops trace_stack_ops __read_mostly =
{
.func = function_stack_trace_call,
- .flags = FTRACE_OPS_FL_GLOBAL,
+ .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
};
static struct tracer_opt func_opts[] = {
return;
}
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST
+#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY)
/*
* The arch may choose to record the frame pointer used
* and check it here to make sure that it is what we expect it
*
* Currently, x86_32 with optimize for size (-Os) makes the latest
* gcc do the above.
+ *
+ * Note, -mfentry does not use frame pointers, and this test
+ * is not needed if CC_USING_FENTRY is set.
*/
if (unlikely(current->ret_stack[index].fp != frame_pointer)) {
ftrace_graph_stop();
* irqsoff uses its own tracer function to keep the overhead down:
*/
static void
-irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = irqsoff_trace;
struct trace_array_cpu *data;
static struct ftrace_ops trace_ops __read_mostly =
{
.func = irqsoff_tracer_call,
- .flags = FTRACE_OPS_FL_GLOBAL,
+ .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
};
#endif /* CONFIG_FUNCTION_TRACER */
* wakeup uses its own tracer function to keep the overhead down:
*/
static void
-wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = wakeup_trace;
struct trace_array_cpu *data;
static struct ftrace_ops trace_ops __read_mostly =
{
.func = wakeup_tracer_call,
- .flags = FTRACE_OPS_FL_GLOBAL,
+ .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
};
#endif /* CONFIG_FUNCTION_TRACER */
static int trace_selftest_test_probe1_cnt;
static void trace_selftest_test_probe1_func(unsigned long ip,
- unsigned long pip)
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_probe1_cnt++;
}
static int trace_selftest_test_probe2_cnt;
static void trace_selftest_test_probe2_func(unsigned long ip,
- unsigned long pip)
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_probe2_cnt++;
}
static int trace_selftest_test_probe3_cnt;
static void trace_selftest_test_probe3_func(unsigned long ip,
- unsigned long pip)
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_probe3_cnt++;
}
static int trace_selftest_test_global_cnt;
static void trace_selftest_test_global_func(unsigned long ip,
- unsigned long pip)
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_global_cnt++;
}
static int trace_selftest_test_dyn_cnt;
static void trace_selftest_test_dyn_func(unsigned long ip,
- unsigned long pip)
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_dyn_cnt++;
}
static struct ftrace_ops test_probe1 = {
.func = trace_selftest_test_probe1_func,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static struct ftrace_ops test_probe2 = {
.func = trace_selftest_test_probe2_func,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static struct ftrace_ops test_probe3 = {
.func = trace_selftest_test_probe3_func,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static struct ftrace_ops test_global = {
- .func = trace_selftest_test_global_func,
- .flags = FTRACE_OPS_FL_GLOBAL,
+ .func = trace_selftest_test_global_func,
+ .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE,
};
static void print_counts(void)
return ret;
}
+
+static int trace_selftest_recursion_cnt;
+static void trace_selftest_test_recursion_func(unsigned long ip,
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
+{
+ /*
+ * This function is registered without the recursion safe flag.
+ * The ftrace infrastructure should provide the recursion
+ * protection. If not, this will crash the kernel!
+ */
+ trace_selftest_recursion_cnt++;
+ DYN_FTRACE_TEST_NAME();
+}
+
+static void trace_selftest_test_recursion_safe_func(unsigned long ip,
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
+{
+ /*
+ * We said we would provide our own recursion. By calling
+ * this function again, we should recurse back into this function
+ * and count again. But this only happens if the arch supports
+ * all of ftrace features and nothing else is using the function
+ * tracing utility.
+ */
+ if (trace_selftest_recursion_cnt++)
+ return;
+ DYN_FTRACE_TEST_NAME();
+}
+
+static struct ftrace_ops test_rec_probe = {
+ .func = trace_selftest_test_recursion_func,
+};
+
+static struct ftrace_ops test_recsafe_probe = {
+ .func = trace_selftest_test_recursion_safe_func,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
+};
+
+static int
+trace_selftest_function_recursion(void)
+{
+ int save_ftrace_enabled = ftrace_enabled;
+ int save_tracer_enabled = tracer_enabled;
+ char *func_name;
+ int len;
+ int ret;
+ int cnt;
+
+ /* The previous test PASSED */
+ pr_cont("PASSED\n");
+ pr_info("Testing ftrace recursion: ");
+
+
+ /* enable tracing, and record the filter function */
+ ftrace_enabled = 1;
+ tracer_enabled = 1;
+
+ /* Handle PPC64 '.' name */
+ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+ len = strlen(func_name);
+
+ ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1);
+ if (ret) {
+ pr_cont("*Could not set filter* ");
+ goto out;
+ }
+
+ ret = register_ftrace_function(&test_rec_probe);
+ if (ret) {
+ pr_cont("*could not register callback* ");
+ goto out;
+ }
+
+ DYN_FTRACE_TEST_NAME();
+
+ unregister_ftrace_function(&test_rec_probe);
+
+ ret = -1;
+ if (trace_selftest_recursion_cnt != 1) {
+ pr_cont("*callback not called once (%d)* ",
+ trace_selftest_recursion_cnt);
+ goto out;
+ }
+
+ trace_selftest_recursion_cnt = 1;
+
+ pr_cont("PASSED\n");
+ pr_info("Testing ftrace recursion safe: ");
+
+ ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1);
+ if (ret) {
+ pr_cont("*Could not set filter* ");
+ goto out;
+ }
+
+ ret = register_ftrace_function(&test_recsafe_probe);
+ if (ret) {
+ pr_cont("*could not register callback* ");
+ goto out;
+ }
+
+ DYN_FTRACE_TEST_NAME();
+
+ unregister_ftrace_function(&test_recsafe_probe);
+
+ /*
+ * If arch supports all ftrace features, and no other task
+ * was on the list, we should be fine.
+ */
+ if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC)
+ cnt = 2; /* Should have recursed */
+ else
+ cnt = 1;
+
+ ret = -1;
+ if (trace_selftest_recursion_cnt != cnt) {
+ pr_cont("*callback not called expected %d times (%d)* ",
+ cnt, trace_selftest_recursion_cnt);
+ goto out;
+ }
+
+ ret = 0;
+out:
+ ftrace_enabled = save_ftrace_enabled;
+ tracer_enabled = save_tracer_enabled;
+
+ return ret;
+}
#else
# define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; })
+# define trace_selftest_function_recursion() ({ 0; })
#endif /* CONFIG_DYNAMIC_FTRACE */
+static enum {
+ TRACE_SELFTEST_REGS_START,
+ TRACE_SELFTEST_REGS_FOUND,
+ TRACE_SELFTEST_REGS_NOT_FOUND,
+} trace_selftest_regs_stat;
+
+static void trace_selftest_test_regs_func(unsigned long ip,
+ unsigned long pip,
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
+{
+ if (pt_regs)
+ trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND;
+ else
+ trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND;
+}
+
+static struct ftrace_ops test_regs_probe = {
+ .func = trace_selftest_test_regs_func,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS,
+};
+
+static int
+trace_selftest_function_regs(void)
+{
+ int save_ftrace_enabled = ftrace_enabled;
+ int save_tracer_enabled = tracer_enabled;
+ char *func_name;
+ int len;
+ int ret;
+ int supported = 0;
+
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+ supported = 1;
+#endif
+
+ /* The previous test PASSED */
+ pr_cont("PASSED\n");
+ pr_info("Testing ftrace regs%s: ",
+ !supported ? "(no arch support)" : "");
+
+ /* enable tracing, and record the filter function */
+ ftrace_enabled = 1;
+ tracer_enabled = 1;
+
+ /* Handle PPC64 '.' name */
+ func_name = "*" __stringify(DYN_FTRACE_TEST_NAME);
+ len = strlen(func_name);
+
+ ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1);
+ /*
+ * If DYNAMIC_FTRACE is not set, then we just trace all functions.
+ * This test really doesn't care.
+ */
+ if (ret && ret != -ENODEV) {
+ pr_cont("*Could not set filter* ");
+ goto out;
+ }
+
+ ret = register_ftrace_function(&test_regs_probe);
+ /*
+ * Now if the arch does not support passing regs, then this should
+ * have failed.
+ */
+ if (!supported) {
+ if (!ret) {
+ pr_cont("*registered save-regs without arch support* ");
+ goto out;
+ }
+ test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED;
+ ret = register_ftrace_function(&test_regs_probe);
+ }
+ if (ret) {
+ pr_cont("*could not register callback* ");
+ goto out;
+ }
+
+
+ DYN_FTRACE_TEST_NAME();
+
+ unregister_ftrace_function(&test_regs_probe);
+
+ ret = -1;
+
+ switch (trace_selftest_regs_stat) {
+ case TRACE_SELFTEST_REGS_START:
+ pr_cont("*callback never called* ");
+ goto out;
+
+ case TRACE_SELFTEST_REGS_FOUND:
+ if (supported)
+ break;
+ pr_cont("*callback received regs without arch support* ");
+ goto out;
+
+ case TRACE_SELFTEST_REGS_NOT_FOUND:
+ if (!supported)
+ break;
+ pr_cont("*callback received NULL regs* ");
+ goto out;
+ }
+
+ ret = 0;
+out:
+ ftrace_enabled = save_ftrace_enabled;
+ tracer_enabled = save_tracer_enabled;
+
+ return ret;
+}
+
/*
* Simple verification test of ftrace function tracer.
* Enable ftrace, sleep 1/10 second, and then read the trace
ret = trace_selftest_startup_dynamic_tracing(trace, tr,
DYN_FTRACE_TEST_NAME);
+ if (ret)
+ goto out;
+ ret = trace_selftest_function_recursion();
+ if (ret)
+ goto out;
+
+ ret = trace_selftest_function_regs();
out:
ftrace_enabled = save_ftrace_enabled;
tracer_enabled = save_tracer_enabled;
set_current_state(TASK_INTERRUPTIBLE);
schedule();
+ complete(x);
+
/* we are awake, now wait to disappear */
while (!kthread_should_stop()) {
/*
/* reset the max latency */
tracing_max_latency = 0;
- /* sleep to let the RT thread sleep too */
- msleep(100);
+ while (p->on_rq) {
+ /*
+ * Sleep to make sure the RT thread is asleep too.
+ * On virtual machines we can't rely on timings,
+ * but we want to make sure this test still works.
+ */
+ msleep(100);
+ }
- /*
- * Yes this is slightly racy. It is possible that for some
- * strange reason that the RT thread we created, did not
- * call schedule for 100ms after doing the completion,
- * and we do a wakeup on a task that already is awake.
- * But that is extremely unlikely, and the worst thing that
- * happens in such a case, is that we disable tracing.
- * Honestly, if this race does happen something is horrible
- * wrong with the system.
- */
+ init_completion(&isrt);
wake_up_process(p);
- /* give a little time to let the thread wake up */
- msleep(100);
+ /* Wait for the task to wake up */
+ wait_for_completion(&isrt);
/* stop the tracing. */
tracing_stop();
}
static void
-stack_trace_call(unsigned long ip, unsigned long parent_ip)
+stack_trace_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
int cpu;
static struct ftrace_ops trace_ops __read_mostly =
{
.func = stack_trace_call,
+ .flags = FTRACE_OPS_FL_RECURSION_SAFE,
};
static ssize_t
#include <linux/notifier.h>
#include <linux/module.h>
#include <linux/sysctl.h>
+#include <linux/smpboot.h>
#include <asm/irq_regs.h>
#include <linux/kvm_para.h>
int watchdog_enabled = 1;
int __read_mostly watchdog_thresh = 10;
+static int __read_mostly watchdog_disabled;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
static DEFINE_PER_CPU(bool, soft_watchdog_warn);
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
+static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
#ifdef CONFIG_HARDLOCKUP_DETECTOR
static DEFINE_PER_CPU(bool, hard_watchdog_warn);
static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
#endif
__this_cpu_write(hard_watchdog_warn, false);
return;
}
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+
static void watchdog_interrupt_count(void)
{
__this_cpu_inc(hrtimer_interrupts);
}
-#else
-static inline void watchdog_interrupt_count(void) { return; }
-#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+
+static int watchdog_nmi_enable(unsigned int cpu);
+static void watchdog_nmi_disable(unsigned int cpu);
/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
return HRTIMER_RESTART;
}
+static void watchdog_set_prio(unsigned int policy, unsigned int prio)
+{
+ struct sched_param param = { .sched_priority = prio };
-/*
- * The watchdog thread - touches the timestamp.
- */
-static int watchdog(void *unused)
+ sched_setscheduler(current, policy, ¶m);
+}
+
+static void watchdog_enable(unsigned int cpu)
{
- struct sched_param param = { .sched_priority = 0 };
struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
- /* initialize timestamp */
- __touch_watchdog();
+ if (!watchdog_enabled) {
+ kthread_park(current);
+ return;
+ }
+
+ /* Enable the perf event */
+ watchdog_nmi_enable(cpu);
/* kick off the timer for the hardlockup detector */
+ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer->function = watchdog_timer_fn;
+
/* done here because hrtimer_start can only pin to smp_processor_id() */
hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()),
HRTIMER_MODE_REL_PINNED);
- set_current_state(TASK_INTERRUPTIBLE);
- /*
- * Run briefly (kicked by the hrtimer callback function) once every
- * get_sample_period() seconds (4 seconds by default) to reset the
- * softlockup timestamp. If this gets delayed for more than
- * 2*watchdog_thresh seconds then the debug-printout triggers in
- * watchdog_timer_fn().
- */
- while (!kthread_should_stop()) {
- __touch_watchdog();
- schedule();
+ /* initialize timestamp */
+ watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
+ __touch_watchdog();
+}
- if (kthread_should_stop())
- break;
+static void watchdog_disable(unsigned int cpu)
+{
+ struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
- set_current_state(TASK_INTERRUPTIBLE);
- }
- /*
- * Drop the policy/priority elevation during thread exit to avoid a
- * scheduling latency spike.
- */
- __set_current_state(TASK_RUNNING);
- sched_setscheduler(current, SCHED_NORMAL, ¶m);
- return 0;
+ watchdog_set_prio(SCHED_NORMAL, 0);
+ hrtimer_cancel(hrtimer);
+ /* disable the perf event */
+ watchdog_nmi_disable(cpu);
}
+static int watchdog_should_run(unsigned int cpu)
+{
+ return __this_cpu_read(hrtimer_interrupts) !=
+ __this_cpu_read(soft_lockup_hrtimer_cnt);
+}
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every get_sample_period() seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static void watchdog(unsigned int cpu)
+{
+ __this_cpu_write(soft_lockup_hrtimer_cnt,
+ __this_cpu_read(hrtimer_interrupts));
+ __touch_watchdog();
+}
#ifdef CONFIG_HARDLOCKUP_DETECTOR
/*
*/
static unsigned long cpu0_err;
-static int watchdog_nmi_enable(int cpu)
+static int watchdog_nmi_enable(unsigned int cpu)
{
struct perf_event_attr *wd_attr;
struct perf_event *event = per_cpu(watchdog_ev, cpu);
return 0;
}
-static void watchdog_nmi_disable(int cpu)
+static void watchdog_nmi_disable(unsigned int cpu)
{
struct perf_event *event = per_cpu(watchdog_ev, cpu);
return;
}
#else
-static int watchdog_nmi_enable(int cpu) { return 0; }
-static void watchdog_nmi_disable(int cpu) { return; }
+static int watchdog_nmi_enable(unsigned int cpu) { return 0; }
+static void watchdog_nmi_disable(unsigned int cpu) { return; }
#endif /* CONFIG_HARDLOCKUP_DETECTOR */
/* prepare/enable/disable routines */
-static void watchdog_prepare_cpu(int cpu)
-{
- struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
-
- WARN_ON(per_cpu(softlockup_watchdog, cpu));
- hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
- hrtimer->function = watchdog_timer_fn;
-}
-
-static int watchdog_enable(int cpu)
-{
- struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
- int err = 0;
-
- /* enable the perf event */
- err = watchdog_nmi_enable(cpu);
-
- /* Regardless of err above, fall through and start softlockup */
-
- /* create the watchdog thread */
- if (!p) {
- struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
- p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu);
- if (IS_ERR(p)) {
- pr_err("softlockup watchdog for %i failed\n", cpu);
- if (!err) {
- /* if hardlockup hasn't already set this */
- err = PTR_ERR(p);
- /* and disable the perf event */
- watchdog_nmi_disable(cpu);
- }
- goto out;
- }
- sched_setscheduler(p, SCHED_FIFO, ¶m);
- kthread_bind(p, cpu);
- per_cpu(watchdog_touch_ts, cpu) = 0;
- per_cpu(softlockup_watchdog, cpu) = p;
- wake_up_process(p);
- }
-
-out:
- return err;
-}
-
-static void watchdog_disable(int cpu)
-{
- struct task_struct *p = per_cpu(softlockup_watchdog, cpu);
- struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
-
- /*
- * cancel the timer first to stop incrementing the stats
- * and waking up the kthread
- */
- hrtimer_cancel(hrtimer);
-
- /* disable the perf event */
- watchdog_nmi_disable(cpu);
-
- /* stop the watchdog thread */
- if (p) {
- per_cpu(softlockup_watchdog, cpu) = NULL;
- kthread_stop(p);
- }
-}
-
/* sysctl functions */
#ifdef CONFIG_SYSCTL
static void watchdog_enable_all_cpus(void)
{
- int cpu;
-
- watchdog_enabled = 0;
-
- for_each_online_cpu(cpu)
- if (!watchdog_enable(cpu))
- /* if any cpu succeeds, watchdog is considered
- enabled for the system */
- watchdog_enabled = 1;
-
- if (!watchdog_enabled)
- pr_err("failed to be enabled on some cpus\n");
+ unsigned int cpu;
+ if (watchdog_disabled) {
+ watchdog_disabled = 0;
+ for_each_online_cpu(cpu)
+ kthread_unpark(per_cpu(softlockup_watchdog, cpu));
+ }
}
static void watchdog_disable_all_cpus(void)
{
- int cpu;
-
- for_each_online_cpu(cpu)
- watchdog_disable(cpu);
+ unsigned int cpu;
- /* if all watchdogs are disabled, then they are disabled for the system */
- watchdog_enabled = 0;
+ if (!watchdog_disabled) {
+ watchdog_disabled = 1;
+ for_each_online_cpu(cpu)
+ kthread_park(per_cpu(softlockup_watchdog, cpu));
+ }
}
-
/*
* proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh
*/
{
int ret;
+ if (watchdog_disabled < 0)
+ return -ENODEV;
+
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write)
- goto out;
+ return ret;
if (watchdog_enabled && watchdog_thresh)
watchdog_enable_all_cpus();
else
watchdog_disable_all_cpus();
-out:
return ret;
}
#endif /* CONFIG_SYSCTL */
-
-/*
- * Create/destroy watchdog threads as CPUs come and go:
- */
-static int __cpuinit
-cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
- int hotcpu = (unsigned long)hcpu;
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- watchdog_prepare_cpu(hotcpu);
- break;
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- if (watchdog_enabled)
- watchdog_enable(hotcpu);
- break;
-#ifdef CONFIG_HOTPLUG_CPU
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- watchdog_disable(hotcpu);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- watchdog_disable(hotcpu);
- break;
-#endif /* CONFIG_HOTPLUG_CPU */
- }
-
- /*
- * hardlockup and softlockup are not important enough
- * to block cpu bring up. Just always succeed and
- * rely on printk output to flag problems.
- */
- return NOTIFY_OK;
-}
-
-static struct notifier_block __cpuinitdata cpu_nfb = {
- .notifier_call = cpu_callback
+static struct smp_hotplug_thread watchdog_threads = {
+ .store = &softlockup_watchdog,
+ .thread_should_run = watchdog_should_run,
+ .thread_fn = watchdog,
+ .thread_comm = "watchdog/%u",
+ .setup = watchdog_enable,
+ .park = watchdog_disable,
+ .unpark = watchdog_enable,
};
void __init lockup_detector_init(void)
{
- void *cpu = (void *)(long)smp_processor_id();
- int err;
-
- err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
- WARN_ON(notifier_to_errno(err));
-
- cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
- register_cpu_notifier(&cpu_nfb);
-
- return;
+ if (smpboot_register_percpu_thread(&watchdog_threads)) {
+ pr_err("Failed to create watchdog threads, disabled\n");
+ watchdog_disabled = -ENODEV;
+ }
}
# These targets are used from top-level makefile
PHONY += oldconfig xconfig gconfig menuconfig config silentoldconfig update-po-config \
- localmodconfig localyesconfig
+ localmodconfig localyesconfig kvmconfig
ifdef KBUILD_KCONFIG
Kconfig := $(KBUILD_KCONFIG)
$(Q)mkdir -p include/generated
$< --$@ $(Kconfig)
+kvmconfig:
+ $(Q)$(CONFIG_SHELL) $(srctree)/scripts/config -e KVMTOOL_TEST_ENABLE
+ $(Q)yes "" | make oldconfig > /dev/null
+ @echo 'Kernel configuration modified to run as KVM guest.'
+
localyesconfig localmodconfig: $(obj)/streamline_config.pl $(obj)/conf
$(Q)mkdir -p include/generated
$(Q)perl $< --$@ $(srctree) $(Kconfig) > .tmp.config
&sym0[Elf_r_sym(relp)];
char const *symname = &str0[w(symp->st_name)];
char const *mcount = gpfx == '_' ? "_mcount" : "mcount";
+ char const *fentry = "__fentry__";
if (symname[0] == '.')
++symname; /* ppc64 hack */
if (strcmp(mcount, symname) == 0 ||
- (altmcount && strcmp(altmcount, symname) == 0))
+ (altmcount && strcmp(altmcount, symname) == 0) ||
+ (strcmp(fentry, symname) == 0))
mcountsym = Elf_r_sym(relp);
return mcountsym;
--- /dev/null
+/lkvm
+/vm
+*.o
+*.d
+.cscope
+tags
+include/common-cmds.h
+tests/boot/boot_test.iso
+tests/boot/rootfs/
+guest/init
+guest/init_stage2
+KVMTOOLS-VERSION-FILE
--- /dev/null
+Most of the infrastructure that 'perf' uses here has been reused
+from the Git project, as of version:
+
+ 66996ec: Sync with 1.6.2.4
+
+Here is an (incomplete!) list of main contributors to those files
+in util/* and elsewhere:
+
+ Alex Riesen
+ Christian Couder
+ Dmitry Potapov
+ Jeff King
+ Johannes Schindelin
+ Johannes Sixt
+ Junio C Hamano
+ Linus Torvalds
+ Matthias Kestenholz
+ Michal Ostrowski
+ Miklos Vajna
+ Petr Baudis
+ Pierre Habouzit
+ René Scharfe
+ Samuel Tardieu
+ Shawn O. Pearce
+ Steffen Prohaska
+ Steve Haslam
+
+Thanks guys!
+
+The full history of the files can be found in the upstream Git commits.
--- /dev/null
+This document explains how to debug a guests' kernel using KGDB.
+
+1. Run the guest:
+ 'lkvm run -k [vmlinuz] -p "kgdboc=ttyS1 kgdbwait" --tty 1'
+
+And see which PTY got assigned to ttyS1 (you'll see:
+' Info: Assigned terminal 1 to pty /dev/pts/X').
+
+2. Run GDB on the host:
+ 'gdb [vmlinuz]'
+
+3. Connect to the guest (from within GDB):
+ 'target remote /dev/pty/X'
+
+4. Start debugging! (enter 'continue' to continue boot).
--- /dev/null
+lkvm-balloon(1)
+================
+
+NAME
+----
+lkvm-balloon - Inflate or deflate the virtio balloon
+
+SYNOPSIS
+--------
+[verse]
+'lkvm balloon [command] [size] [instance]'
+
+DESCRIPTION
+-----------
+The command inflates or deflates the virtio balloon located in the
+specified instance.
+For a list of running instances see 'lkvm list'.
+
+Command can be either 'inflate' or 'deflate'. Inflate increases the
+size of the balloon, thus decreasing the amount of virtual RAM available
+for the guest. Deflation returns previously inflated memory back to the
+guest.
+
+size is specified in Mb.
--- /dev/null
+lkvm-debug(1)
+================
+
+NAME
+----
+lkvm-debug - Print debug information from a running instance
+
+SYNOPSIS
+--------
+[verse]
+'lkvm debug [instance]'
+
+DESCRIPTION
+-----------
+The command prints debug information from a running instance.
+For a list of running instances see 'lkvm list'.
--- /dev/null
+lkvm-list(1)
+================
+
+NAME
+----
+lkvm-list - Print a list of running instances on the host.
+
+SYNOPSIS
+--------
+[verse]
+'lkvm list'
+
+DESCRIPTION
+-----------
+This command prints a list of running instances on the host which
+belong to the user who currently ran 'lkvm list'.
--- /dev/null
+lkvm-pause(1)
+================
+
+NAME
+----
+lkvm-pause - Pause the virtual machine
+
+SYNOPSIS
+--------
+[verse]
+'lkvm pause [instance]'
+
+DESCRIPTION
+-----------
+The command pauses a virtual machine.
+For a list of running instances see 'lkvm list'.
--- /dev/null
+lkvm-resume(1)
+================
+
+NAME
+----
+lkvm-resume - Resume the virtual machine
+
+SYNOPSIS
+--------
+[verse]
+'lkvm resume [instance]'
+
+DESCRIPTION
+-----------
+The command resumes a virtual machine.
+For a list of running instances see 'lkvm list'.
--- /dev/null
+lkvm-run(1)
+================
+
+NAME
+----
+lkvm-run - Start the virtual machine
+
+SYNOPSIS
+--------
+[verse]
+'lkvm run' [-k <kernel image> | --kernel <kernel image>]
+
+DESCRIPTION
+-----------
+The command starts a virtual machine.
+
+OPTIONS
+-------
+-m::
+--mem=::
+ Virtual machine memory size in MiB.
+
+-p::
+--params::
+ Additional kernel command line arguments.
+
+-r::
+--initrd=::
+ Initial RAM disk image.
+
+-k::
+--kernel=::
+ The virtual machine kernel.
+
+--dev=::
+ KVM device file.
+
+-i::
+--image=::
+ A disk image file.
+
+-s::
+--single-step::
+ Enable single stepping.
+
+-g::
+--ioport-debug::
+ Enable ioport debugging.
+
+-c::
+--enable-virtio-console::
+ Enable the virtual IO console.
+
+--cpus::
+ The number of virtual CPUs to run.
+
+--debug::
+ Enable debug messages.
+
+SEE ALSO
+--------
+linkkvm:
--- /dev/null
+lkvm-sandbox(1)
+================
+
+NAME
+----
+lkvm-sandbox - Run a command in a sandboxed guest
+
+SYNOPSIS
+--------
+[verse]
+'lkvm sandbox ['lkvm run' arguments] -- [sandboxed command]'
+
+DESCRIPTION
+-----------
+The sandboxed command will run in a guest as part of it's init
+command.
--- /dev/null
+lkvm-setup(1)
+================
+
+NAME
+----
+lkvm-setup - Setup a new virtual machine
+
+SYNOPSIS
+--------
+[verse]
+'lkvm setup <name>'
+
+DESCRIPTION
+-----------
+The command setups a virtual machine.
--- /dev/null
+lkvm-stat(1)
+================
+
+NAME
+----
+lkvm-stat - Print statistics about a running instance
+
+SYNOPSIS
+--------
+[verse]
+'lkvm [command] [-n instance] [-p instance pid] [--all]'
+
+DESCRIPTION
+-----------
+The command prints statistics about a running instance.
+For a list of running instances see 'lkvm list'.
+
+Commands:
+ --memory, -m Display memory statistics
--- /dev/null
+lkvm-stop(1)
+================
+
+NAME
+----
+lkvm-stop - Stop a running instance
+
+SYNOPSIS
+--------
+[verse]
+'lkvm stop [instance]'
+
+DESCRIPTION
+-----------
+The command stops a running instance.
+For a list of running instances see 'lkvm list'.
--- /dev/null
+lkvm-version(1)
+================
+
+NAME
+----
+lkvm-version - Print the version of the kernel tree kvm tools
+was built on.
+
+SYNOPSIS
+--------
+[verse]
+'lkvm version'
+
+DESCRIPTION
+-----------
+The command prints the version of the kernel that was used to build
+kvm tools.
+
+Note that the version is not the version of the kernel which is currently
+running on the host, but is the version of the kernel tree from which kvm
+tools was built.
--- /dev/null
+General
+--------
+
+virtio-console as the name implies is a console over virtio transport. Here is
+a simple head to head comparison of the virtio-console vs regular 8250 console:
+
+8250 serial console:
+
+ - Requires CONFIG_SERIAL_8250=y and CONFIG_SERIAL_8250_CONSOLE=y kernel configs,
+which are enabled almost everywhere.
+ - Doesn't require guest-side changes.
+ - Compatible with older guests.
+
+virtio-console:
+
+ - Requires CONFIG_VIRTIO_CONSOLE=y (along with all other virtio dependencies),
+which got enabled only in recent kernels (but not all of them).
+ - Much faster.
+ - Consumes less processing resources.
+ - Requires guest-side changes.
+
+Enabling virtio-console
+------------------------
+
+First, make sure guest kernel is built with CONFIG_VIRTIO_CONSOLE=y. Once this
+is done, the following has to be done inside guest image:
+
+ - Add the following line to /etc/inittab:
+ 'hvc0:2345:respawn:/sbin/agetty -L 9600 hvc0'
+ - Add 'hvc0' to /etc/securetty (so you could actually log on)
+ - Start the guest with '--console virtio'
+
+Common errors
+--------------
+
+Q: I don't see anything on the screen!
+A: Make sure CONFIG_VIRTIO_CONSOLE=y is enabled in the *guest* kernel, also
+make sure you've updated /etc/inittab
+
+Q: It won't accept my username/password, but I enter them correctly!
+A: You didn't add 'hvc0' to /etc/securetty
--- /dev/null
+#
+# Define WERROR=0 to disable -Werror.
+#
+
+ifeq ($(strip $(V)),)
+ E = @echo
+ Q = @
+else
+ E = @\#
+ Q =
+endif
+ifneq ($(I), )
+ KINCL_PATH=$(I)
+else
+ KINCL_PATH=../..
+endif
+export E Q KINCL_PATH
+
+include config/utilities.mak
+include config/feature-tests.mak
+
+CC := $(CROSS_COMPILE)$(CC)
+LD := $(CROSS_COMPILE)$(LD)
+
+FIND := find
+CSCOPE := cscope
+TAGS := ctags
+INSTALL := install
+
+prefix = $(HOME)
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+
+DESTDIR_SQ = $(subst ','\'',$(DESTDIR))
+bindir_SQ = $(subst ','\'',$(bindir))
+
+PROGRAM := lkvm
+PROGRAM_ALIAS := vm
+
+GUEST_INIT := guest/init
+
+OBJS += builtin-balloon.o
+OBJS += builtin-debug.o
+OBJS += builtin-help.o
+OBJS += builtin-list.o
+OBJS += builtin-stat.o
+OBJS += builtin-pause.o
+OBJS += builtin-resume.o
+OBJS += builtin-run.o
+OBJS += builtin-setup.o
+OBJS += builtin-stop.o
+OBJS += builtin-version.o
+OBJS += disk/core.o
+OBJS += framebuffer.o
+OBJS += guest_compat.o
+OBJS += hw/rtc.o
+OBJS += hw/serial.o
+OBJS += ioport.o
+OBJS += kvm-cpu.o
+OBJS += kvm.o
+OBJS += main.o
+OBJS += mmio.o
+OBJS += pci.o
+OBJS += term.o
+OBJS += virtio/blk.o
+OBJS += virtio/scsi.o
+OBJS += virtio/console.o
+OBJS += virtio/core.o
+OBJS += virtio/net.o
+OBJS += virtio/rng.o
+OBJS += virtio/balloon.o
+OBJS += virtio/pci.o
+OBJS += disk/blk.o
+OBJS += disk/qcow.o
+OBJS += disk/raw.o
+OBJS += ioeventfd.o
+OBJS += net/uip/core.o
+OBJS += net/uip/arp.o
+OBJS += net/uip/icmp.o
+OBJS += net/uip/ipv4.o
+OBJS += net/uip/tcp.o
+OBJS += net/uip/udp.o
+OBJS += net/uip/buf.o
+OBJS += net/uip/csum.o
+OBJS += net/uip/dhcp.o
+OBJS += kvm-cmd.o
+OBJS += util/rbtree.o
+OBJS += util/threadpool.o
+OBJS += util/parse-options.o
+OBJS += util/rbtree-interval.o
+OBJS += util/strbuf.o
+OBJS += util/read-write.o
+OBJS += util/util.o
+OBJS += virtio/9p.o
+OBJS += virtio/9p-pdu.o
+OBJS += hw/vesa.o
+OBJS += hw/pci-shmem.o
+OBJS += kvm-ipc.o
+OBJS += builtin-sandbox.o
+OBJS += virtio/mmio.o
+
+# Translate uname -m into ARCH string
+ARCH ?= $(shell uname -m | sed -e s/i.86/i386/ -e s/ppc.*/powerpc/)
+
+ifeq ($(ARCH),i386)
+ ARCH := x86
+ DEFINES += -DCONFIG_X86_32
+endif
+ifeq ($(ARCH),x86_64)
+ ARCH := x86
+ DEFINES += -DCONFIG_X86_64
+endif
+
+LIBFDT_SRC = fdt.o fdt_ro.o fdt_wip.o fdt_sw.o fdt_rw.o fdt_strerror.o
+LIBFDT_OBJS = $(patsubst %,../../scripts/dtc/libfdt/%,$(LIBFDT_SRC))
+
+### Arch-specific stuff
+
+#x86
+ifeq ($(ARCH),x86)
+ DEFINES += -DCONFIG_X86
+ OBJS += x86/boot.o
+ OBJS += x86/cpuid.o
+ OBJS += x86/interrupt.o
+ OBJS += x86/ioport.o
+ OBJS += x86/irq.o
+ OBJS += x86/kvm.o
+ OBJS += x86/kvm-cpu.o
+ OBJS += x86/mptable.o
+ OBJS += hw/i8042.o
+# Exclude BIOS object files from header dependencies.
+ OTHEROBJS += x86/bios.o
+ OTHEROBJS += x86/bios/bios-rom.o
+ ARCH_INCLUDE := x86/include
+endif
+# POWER/ppc: Actually only support ppc64 currently.
+ifeq ($(ARCH), powerpc)
+ DEFINES += -DCONFIG_PPC
+ OBJS += powerpc/boot.o
+ OBJS += powerpc/ioport.o
+ OBJS += powerpc/irq.o
+ OBJS += powerpc/kvm.o
+ OBJS += powerpc/cpu_info.o
+ OBJS += powerpc/kvm-cpu.o
+ OBJS += powerpc/spapr_hcall.o
+ OBJS += powerpc/spapr_rtas.o
+ OBJS += powerpc/spapr_hvcons.o
+ OBJS += powerpc/spapr_pci.o
+ OBJS += powerpc/xics.o
+# We use libfdt, but it's sometimes not packaged 64bit. It's small too,
+# so just build it in:
+ CFLAGS += -I../../scripts/dtc/libfdt
+ OTHEROBJS += $(LIBFDT_OBJS)
+ ARCH_INCLUDE := powerpc/include
+ CFLAGS += -m64
+endif
+
+###
+
+ifeq (,$(ARCH_INCLUDE))
+ UNSUPP_ERR = @echo "This architecture is not supported in kvmtool." && exit 1
+else
+ UNSUPP_ERR =
+endif
+
+###
+
+# Detect optional features.
+# On a given system, some libs may link statically, some may not; so, check
+# both and only build those that link!
+
+FLAGS_BFD := $(CFLAGS) -lbfd
+ifeq ($(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD)),y)
+ CFLAGS_DYNOPT += -DCONFIG_HAS_BFD
+ OBJS_DYNOPT += symbol.o
+ LIBS_DYNOPT += -lbfd
+endif
+ifeq ($(call try-cc,$(SOURCE_BFD),$(FLAGS_BFD) -static),y)
+ CFLAGS_STATOPT += -DCONFIG_HAS_BFD
+ OBJS_STATOPT += symbol.o
+ LIBS_STATOPT += -lbfd
+endif
+
+FLAGS_VNCSERVER := $(CFLAGS) -lvncserver
+ifeq ($(call try-cc,$(SOURCE_VNCSERVER),$(FLAGS_VNCSERVER)),y)
+ OBJS_DYNOPT += ui/vnc.o
+ CFLAGS_DYNOPT += -DCONFIG_HAS_VNCSERVER
+ LIBS_DYNOPT += -lvncserver
+endif
+ifeq ($(call try-cc,$(SOURCE_VNCSERVER),$(FLAGS_VNCSERVER) -static),y)
+ OBJS_STATOPT += ui/vnc.o
+ CFLAGS_STATOPT += -DCONFIG_HAS_VNCSERVER
+ LIBS_STATOPT += -lvncserver
+endif
+
+FLAGS_SDL := $(CFLAGS) -lSDL
+ifeq ($(call try-cc,$(SOURCE_SDL),$(FLAGS_SDL)),y)
+ OBJS_DYNOPT += ui/sdl.o
+ CFLAGS_DYNOPT += -DCONFIG_HAS_SDL
+ LIBS_DYNOPT += -lSDL
+endif
+ifeq ($(call try-cc,$(SOURCE_SDL),$(FLAGS_SDL) -static), y)
+ OBJS_STATOPT += ui/sdl.o
+ CFLAGS_STATOPT += -DCONFIG_HAS_SDL
+ LIBS_STATOPT += -lSDL
+endif
+
+FLAGS_ZLIB := $(CFLAGS) -lz
+ifeq ($(call try-cc,$(SOURCE_ZLIB),$(FLAGS_ZLIB)),y)
+ CFLAGS_DYNOPT += -DCONFIG_HAS_ZLIB
+ LIBS_DYNOPT += -lz
+endif
+ifeq ($(call try-cc,$(SOURCE_ZLIB),$(FLAGS_ZLIB) -static),y)
+ CFLAGS_STATOPT += -DCONFIG_HAS_ZLIB
+ LIBS_STATOPT += -lz
+endif
+
+FLAGS_AIO := $(CFLAGS) -laio
+ifeq ($(call try-cc,$(SOURCE_AIO),$(FLAGS_AIO)),y)
+ CFLAGS_DYNOPT += -DCONFIG_HAS_AIO
+ LIBS_DYNOPT += -laio
+endif
+ifeq ($(call try-cc,$(SOURCE_AIO),$(FLAGS_AIO) -static),y)
+ CFLAGS_STATOPT += -DCONFIG_HAS_AIO
+ LIBS_STATOPT += -laio
+endif
+
+ifneq ($(call try-build,$(SOURCE_STATIC),-static,),y)
+$(error No static libc found. Please install glibc-static package.)
+endif
+###
+
+LIBS += -lrt
+LIBS += -lpthread
+LIBS += -lutil
+
+
+DEPS := $(patsubst %.o,%.d,$(OBJS))
+
+DEFINES += -D_FILE_OFFSET_BITS=64
+DEFINES += -D_GNU_SOURCE
+DEFINES += -DKVMTOOLS_VERSION='"$(KVMTOOLS_VERSION)"'
+DEFINES += -DBUILD_ARCH='"$(ARCH)"'
+
+KVM_INCLUDE := include
+CFLAGS += $(CPPFLAGS) $(DEFINES) -I$(KVM_INCLUDE) -I$(ARCH_INCLUDE) -I$(KINCL_PATH)/include -I$(KINCL_PATH)/arch/$(ARCH)/include/ -O2 -fno-strict-aliasing -g -flto
+
+WARNINGS += -Wall
+WARNINGS += -Wcast-align
+WARNINGS += -Wformat=2
+WARNINGS += -Winit-self
+WARNINGS += -Wmissing-declarations
+WARNINGS += -Wmissing-prototypes
+WARNINGS += -Wnested-externs
+WARNINGS += -Wno-system-headers
+WARNINGS += -Wold-style-definition
+WARNINGS += -Wredundant-decls
+WARNINGS += -Wsign-compare
+WARNINGS += -Wstrict-prototypes
+WARNINGS += -Wundef
+WARNINGS += -Wvolatile-register-var
+WARNINGS += -Wwrite-strings
+
+CFLAGS += $(WARNINGS)
+
+# Some targets may use 'external' sources that don't build totally cleanly.
+CFLAGS_EASYGOING := $(CFLAGS)
+
+ifneq ($(WERROR),0)
+ CFLAGS += -Werror
+endif
+
+all: arch_support_check $(PROGRAM) $(PROGRAM_ALIAS) $(GUEST_INIT)
+
+arch_support_check:
+ $(UNSUPP_ERR)
+
+KVMTOOLS-VERSION-FILE:
+ @$(SHELL_PATH) util/KVMTOOLS-VERSION-GEN $(OUTPUT)
+-include $(OUTPUT)KVMTOOLS-VERSION-FILE
+
+# When building -static all objects are built with appropriate flags, which
+# may differ between static & dynamic .o. The objects are separated into
+# .o and .static.o. See the %.o: %.c rules below.
+#
+# $(OTHEROBJS) are things that do not get substituted like this.
+#
+STATIC_OBJS = $(patsubst %.o,%.static.o,$(OBJS) $(OBJS_STATOPT))
+GUEST_OBJS = guest/guest_init.o
+
+$(PROGRAM)-static: $(DEPS) $(STATIC_OBJS) $(OTHEROBJS) $(GUEST_INIT)
+ $(E) " LINK " $@
+ $(Q) $(CC) -static $(CFLAGS) $(STATIC_OBJS) $(OTHEROBJS) $(GUEST_OBJS) $(LIBS) $(LIBS_STATOPT) -o $@
+
+$(PROGRAM): $(DEPS) $(OBJS) $(OBJS_DYNOPT) $(OTHEROBJS) $(GUEST_INIT)
+ $(E) " LINK " $@
+ $(Q) $(CC) $(CFLAGS) $(OBJS) $(OBJS_DYNOPT) $(OTHEROBJS) $(GUEST_OBJS) $(LIBS) $(LIBS_DYNOPT) -o $@
+
+$(PROGRAM_ALIAS): $(PROGRAM)
+ $(E) " LN " $@
+ $(Q) ln -f $(PROGRAM) $@
+
+$(GUEST_INIT): guest/init.c
+ $(E) " LINK " $@
+ $(Q) $(CC) -static guest/init.c -o $@
+ $(Q) $(LD) -r -b binary -o guest/guest_init.o $(GUEST_INIT)
+
+$(DEPS):
+
+util/rbtree.d: ../../lib/rbtree.c
+ $(Q) $(CC) -M -MT util/rbtree.o $(CFLAGS) $< -o $@
+
+%.d: %.c
+ $(Q) $(CC) -M -MT $(patsubst %.d,%.o,$@) $(CFLAGS) $< -o $@
+
+# The header file common-cmds.h is needed for compilation of builtin-help.c.
+builtin-help.d: $(KVM_INCLUDE)/common-cmds.h
+
+$(OBJS):
+
+# This rule relaxes the -Werror on libfdt, since for now it still has
+# a bunch of warnings. :(
+../../scripts/dtc/libfdt/%.o: ../../scripts/dtc/libfdt/%.c
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(CFLAGS_EASYGOING) $< -o $@
+
+util/rbtree.static.o util/rbtree.o: ../../lib/rbtree.c
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(CFLAGS) $< -o $@
+
+%.static.o: %.c
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(CFLAGS) $(CFLAGS_STATOPT) $< -o $@
+
+%.o: %.c
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(CFLAGS) $(CFLAGS_DYNOPT) $< -o $@
+
+
+$(KVM_INCLUDE)/common-cmds.h: util/generate-cmdlist.sh command-list.txt
+
+$(KVM_INCLUDE)/common-cmds.h: $(wildcard Documentation/kvm-*.txt)
+ $(E) " GEN " $@
+ $(Q) util/generate-cmdlist.sh > $@+ && mv $@+ $@
+
+#
+# BIOS assembly weirdness
+#
+BIOS_CFLAGS += -m32
+BIOS_CFLAGS += -march=i386
+BIOS_CFLAGS += -mregparm=3
+
+BIOS_CFLAGS += -fno-stack-protector
+BIOS_CFLAGS += -I../../arch/$(ARCH)
+
+x86/bios.o: x86/bios/bios.bin x86/bios/bios-rom.h
+
+x86/bios/bios.bin.elf: x86/bios/entry.S x86/bios/e820.c x86/bios/int10.c x86/bios/int15.c x86/bios/rom.ld.S
+ $(E) " CC x86/bios/memcpy.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c -s x86/bios/memcpy.c -o x86/bios/memcpy.o
+ $(E) " CC x86/bios/e820.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c -s x86/bios/e820.c -o x86/bios/e820.o
+ $(E) " CC x86/bios/int10.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c -s x86/bios/int10.c -o x86/bios/int10.o
+ $(E) " CC x86/bios/int15.o"
+ $(Q) $(CC) -include code16gcc.h $(CFLAGS) $(BIOS_CFLAGS) -c -s x86/bios/int15.c -o x86/bios/int15.o
+ $(E) " CC x86/bios/entry.o"
+ $(Q) $(CC) $(CFLAGS) $(BIOS_CFLAGS) -c -s x86/bios/entry.S -o x86/bios/entry.o
+ $(E) " LD " $@
+ $(Q) $(LD) -T x86/bios/rom.ld.S -o x86/bios/bios.bin.elf x86/bios/memcpy.o x86/bios/entry.o x86/bios/e820.o x86/bios/int10.o x86/bios/int15.o
+
+x86/bios/bios.bin: x86/bios/bios.bin.elf
+ $(E) " OBJCOPY " $@
+ $(Q) objcopy -O binary -j .text x86/bios/bios.bin.elf x86/bios/bios.bin
+
+x86/bios/bios-rom.o: x86/bios/bios-rom.S x86/bios/bios.bin x86/bios/bios-rom.h
+ $(E) " CC " $@
+ $(Q) $(CC) -c $(CFLAGS) x86/bios/bios-rom.S -o x86/bios/bios-rom.o
+
+x86/bios/bios-rom.h: x86/bios/bios.bin.elf
+ $(E) " NM " $@
+ $(Q) cd x86/bios && sh gen-offsets.sh > bios-rom.h && cd ..
+
+check: all
+ $(MAKE) -C tests
+ ./$(PROGRAM) run tests/pit/tick.bin
+ ./$(PROGRAM) run -d tests/boot/boot_test.iso -p "init=init"
+.PHONY: check
+
+install: all
+ $(E) " INSTALL"
+ $(Q) $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
+ $(Q) $(INSTALL) $(PROGRAM) '$(DESTDIR_SQ)$(bindir_SQ)'
+.PHONY: install
+
+clean:
+ $(E) " CLEAN"
+ $(Q) rm -f x86/bios/*.bin
+ $(Q) rm -f x86/bios/*.elf
+ $(Q) rm -f x86/bios/*.o
+ $(Q) rm -f x86/bios/bios-rom.h
+ $(Q) rm -f tests/boot/boot_test.iso
+ $(Q) rm -rf tests/boot/rootfs/
+ $(Q) rm -f $(DEPS) $(OBJS) $(OTHEROBJS) $(OBJS_DYNOPT) $(STATIC_OBJS) $(PROGRAM) $(PROGRAM_ALIAS) $(PROGRAM)-static $(GUEST_INIT) $(GUEST_OBJS)
+ $(Q) rm -f cscope.*
+ $(Q) rm -f tags
+ $(Q) rm -f TAGS
+ $(Q) rm -f $(KVM_INCLUDE)/common-cmds.h
+ $(Q) rm -f KVMTOOLS-VERSION-FILE
+.PHONY: clean
+
+KVM_DEV ?= /dev/kvm
+
+$(KVM_DEV):
+ $(E) " MKNOD " $@
+ $(Q) mknod $@ char 10 232
+
+devices: $(KVM_DEV)
+.PHONY: devices
+
+TAGS:
+ $(E) " GEN" $@
+ $(Q) $(RM) -f TAGS
+ $(Q) $(FIND) . -name '*.[hcS]' -print | xargs etags -a
+.PHONY: TAGS
+
+tags:
+ $(E) " GEN" $@
+ $(Q) $(RM) -f tags
+ $(Q) $(FIND) . -name '*.[hcS]' -print | xargs ctags -a
+.PHONY: tags
+
+cscope:
+ $(E) " GEN" $@
+ $(Q) $(FIND) . -name '*.[hcS]' -print > cscope.files
+ $(Q) $(CSCOPE) -bkqu
+.PHONY: cscope
+
+# Deps
+-include $(DEPS)
--- /dev/null
+Native Linux KVM tool
+=====================
+The goal of this tool is to provide a clean, from-scratch, lightweight
+KVM host tool implementation that can boot Linux guest images (just a
+hobby, won't be big and professional like QEMU) with no BIOS
+dependencies and with only the minimal amount of legacy device
+emulation.
+
+It's great as a learning tool if you want to get your feet wet in
+virtualization land: it's only 5 KLOC of clean C code that can already
+boot a guest Linux image.
+
+Right now it can boot a Linux image and provide you output via a serial
+console, over the host terminal, i.e. you can use it to boot a guest
+Linux image in a terminal or over ssh and log into the guest without
+much guest or host side setup work needed.
+
+1. To try out the tool, clone the git repository:
+
+ git clone git://github.com/penberg/linux-kvm.git
+
+or alternatively, if you already have a kernel source tree:
+
+ git remote add kvm-tool git://github.com/penberg/linux-kvm.git
+ git remote update
+ git checkout -b kvm-tool/master kvm-tool
+
+2. Compile the tool:
+
+ cd tools/kvm && make
+
+3. Download a raw userspace image:
+
+ wget http://wiki.qemu.org/download/linux-0.2.img.bz2 && bunzip2
+linux-0.2.img.bz2
+
+4. The guest kernel has to be built with the following configuration:
+
+ - For the default console output:
+ CONFIG_SERIAL_8250=y
+ CONFIG_SERIAL_8250_CONSOLE=y
+
+ - For running 32bit images on 64bit hosts:
+ CONFIG_IA32_EMULATION=y
+
+ - Proper FS options according to image FS (e.g. CONFIG_EXT2_FS, CONFIG_EXT4_FS).
+
+ - For all virtio devices listed below:
+ CONFIG_VIRTIO=y
+ CONFIG_VIRTIO_RING=y
+ CONFIG_VIRTIO_PCI=y
+
+ - For virtio-blk devices (--disk, -d):
+ CONFIG_VIRTIO_BLK=y
+
+ - For virtio-net devices ([--network, -n] virtio):
+ CONFIG_VIRTIO_NET=y
+
+ - For virtio-9p devices (--virtio-9p):
+ CONFIG_NET_9P=y
+ CONFIG_NET_9P_VIRTIO=y
+ CONFIG_9P_FS=y
+
+ - For virtio-balloon device (--balloon):
+ CONFIG_VIRTIO_BALLOON=y
+
+ - For virtio-console device (--console virtio):
+ CONFIG_VIRTIO_CONSOLE=y
+
+ - For virtio-rng device (--rng):
+ CONFIG_HW_RANDOM_VIRTIO=y
+
+ - For vesa device (--sdl or --vnc):
+ CONFIG_FB_VESA=y
+
+
+5. And finally, launch the hypervisor:
+
+ ./lkvm run --disk linux-0.2.img \
+ --kernel ../../arch/x86/boot/bzImage \
+or
+
+ sudo ./lkvm run --disk linux-0.2.img \
+ --kernel ../../arch/x86/boot/bzImage \
+ --network virtio
+
+The tool has been written by Pekka Enberg, Cyrill Gorcunov, Asias He,
+Sasha Levin and Prasad Joshi. Special thanks to Avi Kivity for his help
+on KVM internals and Ingo Molnar for all-around support and encouragement!
+
+See the following thread for original discussion for motivation of this
+project:
+
+http://thread.gmane.org/gmane.linux.kernel/962051/focus=962620
+
+Build dependencies
+=====================
+For deb based systems:
+32-bit:
+sudo apt-get install build-essential
+64-bit:
+sudo apt-get install build-essential libc6-dev-i386
+
+For rpm based systems:
+32-bit:
+yum install glibc-devel
+64-bit:
+yum install glibc-devel glibc-static
+
+On 64-bit Arch Linux make sure the multilib repository is enabled in your
+/etc/pacman.conf and run
+pacman -Sy lib32-glibc
--- /dev/null
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-balloon.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm.h>
+#include <kvm/kvm-ipc.h>
+
+static const char *instance_name;
+static u64 inflate;
+static u64 deflate;
+
+static const char * const balloon_usage[] = {
+ "lkvm balloon [-n name] [-p pid] [-i amount] [-d amount]",
+ NULL
+};
+
+static const struct option balloon_options[] = {
+ OPT_GROUP("Instance options:"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_GROUP("Balloon options:"),
+ OPT_U64('i', "inflate", &inflate, "Amount to inflate"),
+ OPT_U64('d', "deflate", &deflate, "Amount to deflate"),
+ OPT_END(),
+};
+
+void kvm_balloon_help(void)
+{
+ usage_with_options(balloon_usage, balloon_options);
+}
+
+static void parse_balloon_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, balloon_options, balloon_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_balloon_help();
+ }
+}
+
+int kvm_cmd_balloon(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+ int amount;
+
+ parse_balloon_options(argc, argv);
+
+ if (inflate == 0 && deflate == 0)
+ kvm_balloon_help();
+
+ if (instance_name == NULL)
+ kvm_balloon_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ if (inflate)
+ amount = inflate;
+ else if (deflate)
+ amount = -deflate;
+ else
+ kvm_balloon_help();
+
+ r = kvm_ipc__send_msg(instance, KVM_IPC_BALLOON,
+ sizeof(amount), (u8 *)&amount);
+
+ close(instance);
+
+ if (r < 0)
+ return -1;
+
+ return 0;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-debug.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+#include <kvm/read-write.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+#define BUFFER_SIZE 100
+
+static bool all;
+static int nmi = -1;
+static bool dump;
+static const char *instance_name;
+static const char *sysrq;
+
+static const char * const debug_usage[] = {
+ "lkvm debug [--all] [-n name] [-d] [-m vcpu]",
+ NULL
+};
+
+static const struct option debug_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('d', "dump", &dump, "Generate a debug dump from guest"),
+ OPT_INTEGER('m', "nmi", &nmi, "Generate NMI on VCPU"),
+ OPT_STRING('s', "sysrq", &sysrq, "sysrq", "Inject a sysrq"),
+ OPT_GROUP("Instance options:"),
+ OPT_BOOLEAN('a', "all", &all, "Debug all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_debug_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, debug_options, debug_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_debug_help();
+ }
+}
+
+void kvm_debug_help(void)
+{
+ usage_with_options(debug_usage, debug_options);
+}
+
+static int do_debug(const char *name, int sock)
+{
+ char buff[BUFFER_SIZE];
+ struct debug_cmd_params cmd = {.dbg_type = 0};
+ int r;
+
+ if (dump)
+ cmd.dbg_type |= KVM_DEBUG_CMD_TYPE_DUMP;
+
+ if (nmi != -1) {
+ cmd.dbg_type |= KVM_DEBUG_CMD_TYPE_NMI;
+ cmd.cpu = nmi;
+ }
+
+ if (sysrq) {
+ cmd.dbg_type |= KVM_DEBUG_CMD_TYPE_SYSRQ;
+ cmd.sysrq = sysrq[0];
+ }
+
+ r = kvm_ipc__send_msg(sock, KVM_IPC_DEBUG, sizeof(cmd), (u8 *)&cmd);
+ if (r < 0)
+ return r;
+
+ if (!dump)
+ return 0;
+
+ do {
+ r = xread(sock, buff, BUFFER_SIZE);
+ if (r < 0)
+ return 0;
+ printf("%.*s", r, buff);
+ } while (r > 0);
+
+ return 0;
+}
+
+int kvm_cmd_debug(int argc, const char **argv, const char *prefix)
+{
+ parse_debug_options(argc, argv);
+ int instance;
+ int r;
+
+ if (all)
+ return kvm__enumerate_instances(do_debug);
+
+ if (instance_name == NULL)
+ kvm_debug_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_debug(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
--- /dev/null
+#include <stdio.h>
+#include <string.h>
+
+/* user defined headers */
+#include <common-cmds.h>
+
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-help.h>
+#include <kvm/kvm.h>
+
+
+const char kvm_usage_string[] =
+ "lkvm COMMAND [ARGS]";
+
+const char kvm_more_info_string[] =
+ "See 'lkvm help COMMAND' for more information on a specific command.";
+
+
+static void list_common_cmds_help(void)
+{
+ unsigned int i, longest = 0;
+
+ for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
+ if (longest < strlen(common_cmds[i].name))
+ longest = strlen(common_cmds[i].name);
+ }
+
+ puts(" The most commonly used lkvm commands are:");
+ for (i = 0; i < ARRAY_SIZE(common_cmds); i++) {
+ printf(" %-*s ", longest, common_cmds[i].name);
+ puts(common_cmds[i].help);
+ }
+}
+
+static void kvm_help(void)
+{
+ printf("\n To start a simple non-privileged shell run '%s run'\n\n"
+ "usage: %s\n\n", KVM_BINARY_NAME, kvm_usage_string);
+ list_common_cmds_help();
+ printf("\n %s\n\n", kvm_more_info_string);
+}
+
+
+static void help_cmd(const char *cmd)
+{
+ struct cmd_struct *p;
+ p = kvm_get_command(kvm_commands, cmd);
+ if (!p)
+ kvm_help();
+ else if (p->help)
+ p->help();
+}
+
+int kvm_cmd_help(int argc, const char **argv, const char *prefix)
+{
+ if (!argv || !*argv) {
+ kvm_help();
+ return 0;
+ }
+ help_cmd(argv[0]);
+ return 0;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-list.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <dirent.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+#include <fcntl.h>
+
+static bool run;
+static bool rootfs;
+
+static const char * const list_usage[] = {
+ "lkvm list",
+ NULL
+};
+
+static const struct option list_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('i', "run", &run, "List running instances"),
+ OPT_BOOLEAN('r', "rootfs", &rootfs, "List rootfs instances"),
+ OPT_END()
+};
+
+#define KVM_INSTANCE_RUNNING "running"
+#define KVM_INSTANCE_PAUSED "paused"
+#define KVM_INSTANCE_SHUTOFF "shut off"
+
+void kvm_list_help(void)
+{
+ usage_with_options(list_usage, list_options);
+}
+
+static pid_t get_pid(int sock)
+{
+ pid_t pid;
+ int r;
+
+ r = kvm_ipc__send(sock, KVM_IPC_PID);
+ if (r < 0)
+ return r;
+
+ r = read(sock, &pid, sizeof(pid));
+ if (r < 0)
+ return r;
+
+ return pid;
+}
+
+int get_vmstate(int sock)
+{
+ int vmstate;
+ int r;
+
+ r = kvm_ipc__send(sock, KVM_IPC_VMSTATE);
+ if (r < 0)
+ return r;
+
+ r = read(sock, &vmstate, sizeof(vmstate));
+ if (r < 0)
+ return r;
+
+ return vmstate;
+
+}
+
+static int print_guest(const char *name, int sock)
+{
+ pid_t pid;
+ int vmstate;
+
+ pid = get_pid(sock);
+ vmstate = get_vmstate(sock);
+
+ if ((int)pid < 0 || vmstate < 0)
+ return -1;
+
+ if (vmstate == KVM_VMSTATE_PAUSED)
+ printf("%5d %-20s %s\n", pid, name, KVM_INSTANCE_PAUSED);
+ else
+ printf("%5d %-20s %s\n", pid, name, KVM_INSTANCE_RUNNING);
+
+ return 0;
+}
+
+static int kvm_list_running_instances(void)
+{
+ return kvm__enumerate_instances(print_guest);
+}
+
+static int kvm_list_rootfs(void)
+{
+ DIR *dir;
+ struct dirent *dirent;
+
+ dir = opendir(kvm__get_dir());
+ if (dir == NULL)
+ return -1;
+
+ while ((dirent = readdir(dir))) {
+ if (dirent->d_type == DT_DIR &&
+ strcmp(dirent->d_name, ".") &&
+ strcmp(dirent->d_name, ".."))
+ printf("%5s %-20s %s\n", "", dirent->d_name, KVM_INSTANCE_SHUTOFF);
+ }
+
+ return 0;
+}
+
+static void parse_setup_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, list_options, list_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_list_help();
+ }
+}
+
+int kvm_cmd_list(int argc, const char **argv, const char *prefix)
+{
+ int r;
+
+ parse_setup_options(argc, argv);
+
+ if (!run && !rootfs)
+ run = rootfs = true;
+
+ printf("%6s %-20s %s\n", "PID", "NAME", "STATE");
+ printf("------------------------------------\n");
+
+ if (run) {
+ r = kvm_list_running_instances();
+ if (r < 0)
+ perror("Error listing instances");
+ }
+
+ if (rootfs) {
+ r = kvm_list_rootfs();
+ if (r < 0)
+ perror("Error listing rootfs");
+ }
+
+ return 0;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-pause.h>
+#include <kvm/builtin-list.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+static bool all;
+static const char *instance_name;
+
+static const char * const pause_usage[] = {
+ "lkvm pause [--all] [-n name]",
+ NULL
+};
+
+static const struct option pause_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('a', "all", &all, "Pause all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_pause_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, pause_options, pause_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_pause_help();
+ }
+}
+
+void kvm_pause_help(void)
+{
+ usage_with_options(pause_usage, pause_options);
+}
+
+static int do_pause(const char *name, int sock)
+{
+ int r;
+ int vmstate;
+
+ vmstate = get_vmstate(sock);
+ if (vmstate < 0)
+ return vmstate;
+ if (vmstate == KVM_VMSTATE_PAUSED) {
+ printf("Guest %s is already paused.\n", name);
+ return 0;
+ }
+
+ r = kvm_ipc__send(sock, KVM_IPC_PAUSE);
+ if (r)
+ return r;
+
+ printf("Guest %s paused\n", name);
+
+ return 0;
+}
+
+int kvm_cmd_pause(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+
+ parse_pause_options(argc, argv);
+
+ if (all)
+ return kvm__enumerate_instances(do_pause);
+
+ if (instance_name == NULL)
+ kvm_pause_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_pause(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-resume.h>
+#include <kvm/builtin-list.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+static bool all;
+static const char *instance_name;
+
+static const char * const resume_usage[] = {
+ "lkvm resume [--all] [-n name]",
+ NULL
+};
+
+static const struct option resume_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('a', "all", &all, "Resume all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_resume_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, resume_options, resume_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_resume_help();
+ }
+}
+
+void kvm_resume_help(void)
+{
+ usage_with_options(resume_usage, resume_options);
+}
+
+static int do_resume(const char *name, int sock)
+{
+ int r;
+ int vmstate;
+
+ vmstate = get_vmstate(sock);
+ if (vmstate < 0)
+ return vmstate;
+ if (vmstate == KVM_VMSTATE_RUNNING) {
+ printf("Guest %s is still running.\n", name);
+ return 0;
+ }
+
+ r = kvm_ipc__send(sock, KVM_IPC_RESUME);
+ if (r)
+ return r;
+
+ printf("Guest %s resumed\n", name);
+
+ return 0;
+}
+
+int kvm_cmd_resume(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+
+ parse_resume_options(argc, argv);
+
+ if (all)
+ return kvm__enumerate_instances(do_resume);
+
+ if (instance_name == NULL)
+ kvm_resume_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_resume(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
--- /dev/null
+#include "kvm/builtin-run.h"
+
+#include "kvm/builtin-setup.h"
+#include "kvm/virtio-balloon.h"
+#include "kvm/virtio-console.h"
+#include "kvm/parse-options.h"
+#include "kvm/8250-serial.h"
+#include "kvm/framebuffer.h"
+#include "kvm/disk-image.h"
+#include "kvm/threadpool.h"
+#include "kvm/virtio-scsi.h"
+#include "kvm/virtio-blk.h"
+#include "kvm/virtio-net.h"
+#include "kvm/virtio-rng.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/virtio-9p.h"
+#include "kvm/barrier.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/ioport.h"
+#include "kvm/symbol.h"
+#include "kvm/i8042.h"
+#include "kvm/mutex.h"
+#include "kvm/term.h"
+#include "kvm/util.h"
+#include "kvm/strbuf.h"
+#include "kvm/vesa.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/rtc.h"
+#include "kvm/sdl.h"
+#include "kvm/vnc.h"
+#include "kvm/guest_compat.h"
+#include "kvm/pci-shmem.h"
+#include "kvm/kvm-ipc.h"
+#include "kvm/builtin-debug.h"
+
+#include <linux/types.h>
+#include <linux/err.h>
+
+#include <sys/utsname.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <termios.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <stdio.h>
+
+#define DEFAULT_KVM_DEV "/dev/kvm"
+#define DEFAULT_CONSOLE "serial"
+#define DEFAULT_NETWORK "user"
+#define DEFAULT_HOST_ADDR "192.168.33.1"
+#define DEFAULT_GUEST_ADDR "192.168.33.15"
+#define DEFAULT_GUEST_MAC "02:15:15:15:15:15"
+#define DEFAULT_HOST_MAC "02:01:01:01:01:01"
+#define DEFAULT_SCRIPT "none"
+const char *DEFAULT_SANDBOX_FILENAME = "guest/sandbox.sh";
+
+#define MB_SHIFT (20)
+#define KB_SHIFT (10)
+#define GB_SHIFT (30)
+#define MIN_RAM_SIZE_MB (64ULL)
+#define MIN_RAM_SIZE_BYTE (MIN_RAM_SIZE_MB << MB_SHIFT)
+
+struct kvm *kvm;
+struct kvm_cpu **kvm_cpus;
+__thread struct kvm_cpu *current_kvm_cpu;
+
+static struct disk_image_params disk_image[MAX_DISK_IMAGES];
+static u64 ram_size;
+static u8 image_count;
+static u8 num_net_devices;
+static bool virtio_rng;
+static const char *kernel_cmdline;
+static const char *kernel_filename;
+static const char *vmlinux_filename;
+static const char *initrd_filename;
+static const char *firmware_filename;
+static const char *console;
+static const char *dev;
+static const char *network;
+static const char *host_ip;
+static const char *guest_ip;
+static const char *guest_mac;
+static const char *host_mac;
+static const char *script;
+static const char *guest_name;
+static const char *sandbox;
+static const char *hugetlbfs_path;
+static const char *custom_rootfs_name = "default";
+static struct virtio_net_params *net_params;
+static bool single_step;
+static bool vnc;
+static bool sdl;
+static bool balloon;
+static bool using_rootfs;
+static bool custom_rootfs;
+static bool no_net;
+static bool no_dhcp;
+extern bool ioport_debug;
+extern bool mmio_debug;
+static int kvm_run_wrapper;
+extern int active_console;
+extern int debug_iodelay;
+
+bool do_debug_print = false;
+
+static int nrcpus;
+static int vidmode = -1;
+
+extern char _binary_guest_init_start;
+extern char _binary_guest_init_size;
+
+static const char * const run_usage[] = {
+ "lkvm run [<options>] [<kernel image>]",
+ NULL
+};
+
+enum {
+ KVM_RUN_DEFAULT,
+ KVM_RUN_SANDBOX,
+};
+
+void kvm_run_set_wrapper_sandbox(void)
+{
+ kvm_run_wrapper = KVM_RUN_SANDBOX;
+}
+
+static int img_name_parser(const struct option *opt, const char *arg, int unset)
+{
+ char path[PATH_MAX];
+ const char *cur;
+ struct stat st;
+ char *sep;
+
+ if (stat(arg, &st) == 0 &&
+ S_ISDIR(st.st_mode)) {
+ char tmp[PATH_MAX];
+
+ if (using_rootfs)
+ die("Please use only one rootfs directory atmost");
+
+ if (realpath(arg, tmp) == 0 ||
+ virtio_9p__register(kvm, tmp, "/dev/root") < 0)
+ die("Unable to initialize virtio 9p");
+ using_rootfs = 1;
+ return 0;
+ }
+
+ snprintf(path, PATH_MAX, "%s%s", kvm__get_dir(), arg);
+
+ if (stat(path, &st) == 0 &&
+ S_ISDIR(st.st_mode)) {
+ char tmp[PATH_MAX];
+
+ if (using_rootfs)
+ die("Please use only one rootfs directory atmost");
+
+ if (realpath(path, tmp) == 0 ||
+ virtio_9p__register(kvm, tmp, "/dev/root") < 0)
+ die("Unable to initialize virtio 9p");
+ if (virtio_9p__register(kvm, "/", "hostfs") < 0)
+ die("Unable to initialize virtio 9p");
+ kvm_setup_resolv(arg);
+ using_rootfs = custom_rootfs = 1;
+ custom_rootfs_name = arg;
+ return 0;
+ }
+
+ if (image_count >= MAX_DISK_IMAGES)
+ die("Currently only 4 images are supported");
+
+ disk_image[image_count].filename = arg;
+ cur = arg;
+
+ if (strncmp(arg, "scsi:", 5) == 0) {
+ sep = strstr(arg, ":");
+ if (sep)
+ disk_image[image_count].wwpn = sep + 1;
+ sep = strstr(sep + 1, ":");
+ if (sep) {
+ *sep = 0;
+ disk_image[image_count].tpgt = sep + 1;
+ }
+ cur = sep + 1;
+ }
+
+ do {
+ sep = strstr(cur, ",");
+ if (sep) {
+ if (strncmp(sep + 1, "ro", 2) == 0)
+ disk_image[image_count].readonly = true;
+ else if (strncmp(sep + 1, "direct", 6) == 0)
+ disk_image[image_count].direct = true;
+ *sep = 0;
+ cur = sep + 1;
+ }
+ } while (sep);
+
+ image_count++;
+
+ return 0;
+}
+
+static int virtio_9p_rootdir_parser(const struct option *opt, const char *arg, int unset)
+{
+ char *tag_name;
+ char tmp[PATH_MAX];
+
+ /*
+ * 9p dir can be of the form dirname,tag_name or
+ * just dirname. In the later case we use the
+ * default tag name
+ */
+ tag_name = strstr(arg, ",");
+ if (tag_name) {
+ *tag_name = '\0';
+ tag_name++;
+ }
+ if (realpath(arg, tmp)) {
+ if (virtio_9p__register(kvm, tmp, tag_name) < 0)
+ die("Unable to initialize virtio 9p");
+ } else
+ die("Failed resolving 9p path");
+ return 0;
+}
+
+static int tty_parser(const struct option *opt, const char *arg, int unset)
+{
+ int tty = atoi(arg);
+
+ term_set_tty(tty);
+
+ return 0;
+}
+
+static inline void str_to_mac(const char *str, char *mac)
+{
+ sscanf(str, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+ mac, mac+1, mac+2, mac+3, mac+4, mac+5);
+}
+static int set_net_param(struct virtio_net_params *p, const char *param,
+ const char *val)
+{
+ if (strcmp(param, "guest_mac") == 0) {
+ str_to_mac(val, p->guest_mac);
+ } else if (strcmp(param, "mode") == 0) {
+ if (!strncmp(val, "user", 4)) {
+ int i;
+
+ for (i = 0; i < num_net_devices; i++)
+ if (net_params[i].mode == NET_MODE_USER)
+ die("Only one usermode network device allowed at a time");
+ p->mode = NET_MODE_USER;
+ } else if (!strncmp(val, "tap", 3)) {
+ p->mode = NET_MODE_TAP;
+ } else if (!strncmp(val, "none", 4)) {
+ no_net = 1;
+ return -1;
+ } else
+ die("Unkown network mode %s, please use user, tap or none", network);
+ } else if (strcmp(param, "script") == 0) {
+ p->script = strdup(val);
+ } else if (strcmp(param, "guest_ip") == 0) {
+ p->guest_ip = strdup(val);
+ } else if (strcmp(param, "host_ip") == 0) {
+ p->host_ip = strdup(val);
+ } else if (strcmp(param, "trans") == 0) {
+ p->trans = strdup(val);
+ } else if (strcmp(param, "vhost") == 0) {
+ p->vhost = atoi(val);
+ } else if (strcmp(param, "fd") == 0) {
+ p->fd = atoi(val);
+ } else
+ die("Unknown network parameter %s", param);
+
+ return 0;
+}
+
+static int netdev_parser(const struct option *opt, const char *arg, int unset)
+{
+ struct virtio_net_params p;
+ char *buf = NULL, *cmd = NULL, *cur = NULL;
+ bool on_cmd = true;
+
+ if (arg) {
+ buf = strdup(arg);
+ if (buf == NULL)
+ die("Failed allocating new net buffer");
+ cur = strtok(buf, ",=");
+ }
+
+ p = (struct virtio_net_params) {
+ .guest_ip = DEFAULT_GUEST_ADDR,
+ .host_ip = DEFAULT_HOST_ADDR,
+ .script = DEFAULT_SCRIPT,
+ .mode = NET_MODE_TAP,
+ };
+
+ str_to_mac(DEFAULT_GUEST_MAC, p.guest_mac);
+ p.guest_mac[5] += num_net_devices;
+
+ while (cur) {
+ if (on_cmd) {
+ cmd = cur;
+ } else {
+ if (set_net_param(&p, cmd, cur) < 0)
+ goto done;
+ }
+ on_cmd = !on_cmd;
+
+ cur = strtok(NULL, ",=");
+ };
+
+ num_net_devices++;
+
+ net_params = realloc(net_params, num_net_devices * sizeof(*net_params));
+ if (net_params == NULL)
+ die("Failed adding new network device");
+
+ net_params[num_net_devices - 1] = p;
+
+done:
+ free(buf);
+ return 0;
+}
+
+static int shmem_parser(const struct option *opt, const char *arg, int unset)
+{
+ const u64 default_size = SHMEM_DEFAULT_SIZE;
+ const u64 default_phys_addr = SHMEM_DEFAULT_ADDR;
+ const char *default_handle = SHMEM_DEFAULT_HANDLE;
+ struct shmem_info *si = malloc(sizeof(struct shmem_info));
+ u64 phys_addr;
+ u64 size;
+ char *handle = NULL;
+ int create = 0;
+ const char *p = arg;
+ char *next;
+ int base = 10;
+ int verbose = 0;
+
+ const int skip_pci = strlen("pci:");
+ if (verbose)
+ pr_info("shmem_parser(%p,%s,%d)", opt, arg, unset);
+ /* parse out optional addr family */
+ if (strcasestr(p, "pci:")) {
+ p += skip_pci;
+ } else if (strcasestr(p, "mem:")) {
+ die("I can't add to E820 map yet.\n");
+ }
+ /* parse out physical addr */
+ base = 10;
+ if (strcasestr(p, "0x"))
+ base = 16;
+ phys_addr = strtoll(p, &next, base);
+ if (next == p && phys_addr == 0) {
+ pr_info("shmem: no physical addr specified, using default.");
+ phys_addr = default_phys_addr;
+ }
+ if (*next != ':' && *next != '\0')
+ die("shmem: unexpected chars after phys addr.\n");
+ if (*next == '\0')
+ p = next;
+ else
+ p = next + 1;
+ /* parse out size */
+ base = 10;
+ if (strcasestr(p, "0x"))
+ base = 16;
+ size = strtoll(p, &next, base);
+ if (next == p && size == 0) {
+ pr_info("shmem: no size specified, using default.");
+ size = default_size;
+ }
+ /* look for [KMGkmg][Bb]* uses base 2. */
+ int skip_B = 0;
+ if (strspn(next, "KMGkmg")) { /* might have a prefix */
+ if (*(next + 1) == 'B' || *(next + 1) == 'b')
+ skip_B = 1;
+ switch (*next) {
+ case 'K':
+ case 'k':
+ size = size << KB_SHIFT;
+ break;
+ case 'M':
+ case 'm':
+ size = size << MB_SHIFT;
+ break;
+ case 'G':
+ case 'g':
+ size = size << GB_SHIFT;
+ break;
+ default:
+ die("shmem: bug in detecting size prefix.");
+ break;
+ }
+ next += 1 + skip_B;
+ }
+ if (*next != ':' && *next != '\0') {
+ die("shmem: unexpected chars after phys size. <%c><%c>\n",
+ *next, *p);
+ }
+ if (*next == '\0')
+ p = next;
+ else
+ p = next + 1;
+ /* parse out optional shmem handle */
+ const int skip_handle = strlen("handle=");
+ next = strcasestr(p, "handle=");
+ if (*p && next) {
+ if (p != next)
+ die("unexpected chars before handle\n");
+ p += skip_handle;
+ next = strchrnul(p, ':');
+ if (next - p) {
+ handle = malloc(next - p + 1);
+ strncpy(handle, p, next - p);
+ handle[next - p] = '\0'; /* just in case. */
+ }
+ if (*next == '\0')
+ p = next;
+ else
+ p = next + 1;
+ }
+ /* parse optional create flag to see if we should create shm seg. */
+ if (*p && strcasestr(p, "create")) {
+ create = 1;
+ p += strlen("create");
+ }
+ if (*p != '\0')
+ die("shmem: unexpected trailing chars\n");
+ if (handle == NULL) {
+ handle = malloc(strlen(default_handle) + 1);
+ strcpy(handle, default_handle);
+ }
+ if (verbose) {
+ pr_info("shmem: phys_addr = %llx", phys_addr);
+ pr_info("shmem: size = %llx", size);
+ pr_info("shmem: handle = %s", handle);
+ pr_info("shmem: create = %d", create);
+ }
+
+ si->phys_addr = phys_addr;
+ si->size = size;
+ si->handle = handle;
+ si->create = create;
+ pci_shmem__register_mem(si); /* ownership of si, etc. passed on. */
+ return 0;
+}
+
+static const struct option options[] = {
+ OPT_GROUP("Basic options:"),
+ OPT_STRING('\0', "name", &guest_name, "guest name",
+ "A name for the guest"),
+ OPT_INTEGER('c', "cpus", &nrcpus, "Number of CPUs"),
+ OPT_U64('m', "mem", &ram_size, "Virtual machine memory size in MiB."),
+ OPT_CALLBACK('\0', "shmem", NULL,
+ "[pci:]<addr>:<size>[:handle=<handle>][:create]",
+ "Share host shmem with guest via pci device",
+ shmem_parser),
+ OPT_CALLBACK('d', "disk", NULL, "image or rootfs_dir", "Disk image or rootfs directory", img_name_parser),
+ OPT_BOOLEAN('\0', "balloon", &balloon, "Enable virtio balloon"),
+ OPT_BOOLEAN('\0', "vnc", &vnc, "Enable VNC framebuffer"),
+ OPT_BOOLEAN('\0', "sdl", &sdl, "Enable SDL framebuffer"),
+ OPT_BOOLEAN('\0', "rng", &virtio_rng, "Enable virtio Random Number Generator"),
+ OPT_CALLBACK('\0', "9p", NULL, "dir_to_share,tag_name",
+ "Enable virtio 9p to share files between host and guest", virtio_9p_rootdir_parser),
+ OPT_STRING('\0', "console", &console, "serial, virtio or hv",
+ "Console to use"),
+ OPT_STRING('\0', "dev", &dev, "device_file", "KVM device file"),
+ OPT_CALLBACK('\0', "tty", NULL, "tty id",
+ "Remap guest TTY into a pty on the host",
+ tty_parser),
+ OPT_STRING('\0', "sandbox", &sandbox, "script",
+ "Run this script when booting into custom rootfs"),
+ OPT_STRING('\0', "hugetlbfs", &hugetlbfs_path, "path", "Hugetlbfs path"),
+
+ OPT_GROUP("Kernel options:"),
+ OPT_STRING('k', "kernel", &kernel_filename, "kernel",
+ "Kernel to boot in virtual machine"),
+ OPT_STRING('i', "initrd", &initrd_filename, "initrd",
+ "Initial RAM disk image"),
+ OPT_STRING('p', "params", &kernel_cmdline, "params",
+ "Kernel command line arguments"),
+ OPT_STRING('f', "firmware", &firmware_filename, "firmware",
+ "Firmware image to boot in virtual machine"),
+
+ OPT_GROUP("Networking options:"),
+ OPT_CALLBACK_DEFAULT('n', "network", NULL, "network params",
+ "Create a new guest NIC",
+ netdev_parser, NULL),
+ OPT_BOOLEAN('\0', "no-dhcp", &no_dhcp, "Disable kernel DHCP in rootfs mode"),
+
+ OPT_GROUP("BIOS options:"),
+ OPT_INTEGER('\0', "vidmode", &vidmode,
+ "Video mode"),
+
+ OPT_GROUP("Debug options:"),
+ OPT_BOOLEAN('\0', "debug", &do_debug_print,
+ "Enable debug messages"),
+ OPT_BOOLEAN('\0', "debug-single-step", &single_step,
+ "Enable single stepping"),
+ OPT_BOOLEAN('\0', "debug-ioport", &ioport_debug,
+ "Enable ioport debugging"),
+ OPT_BOOLEAN('\0', "debug-mmio", &mmio_debug,
+ "Enable MMIO debugging"),
+ OPT_INTEGER('\0', "debug-iodelay", &debug_iodelay,
+ "Delay IO by millisecond"),
+ OPT_END()
+};
+
+/*
+ * Serialize debug printout so that the output of multiple vcpus does not
+ * get mixed up:
+ */
+static int printout_done;
+
+static void handle_sigusr1(int sig)
+{
+ struct kvm_cpu *cpu = current_kvm_cpu;
+ int fd = kvm_cpu__get_debug_fd();
+
+ if (!cpu || cpu->needs_nmi)
+ return;
+
+ dprintf(fd, "\n #\n # vCPU #%ld's dump:\n #\n", cpu->cpu_id);
+ kvm_cpu__show_registers(cpu);
+ kvm_cpu__show_code(cpu);
+ kvm_cpu__show_page_tables(cpu);
+ fflush(stdout);
+ printout_done = 1;
+ mb();
+}
+
+/* Pause/resume the guest using SIGUSR2 */
+static int is_paused;
+
+static void handle_pause(int fd, u32 type, u32 len, u8 *msg)
+{
+ if (WARN_ON(len))
+ return;
+
+ if (type == KVM_IPC_RESUME && is_paused) {
+ kvm->vm_state = KVM_VMSTATE_RUNNING;
+ kvm__continue();
+ } else if (type == KVM_IPC_PAUSE && !is_paused) {
+ kvm->vm_state = KVM_VMSTATE_PAUSED;
+ ioctl(kvm->vm_fd, KVM_KVMCLOCK_CTRL);
+ kvm__pause();
+ } else {
+ return;
+ }
+
+ is_paused = !is_paused;
+}
+
+static void handle_vmstate(int fd, u32 type, u32 len, u8 *msg)
+{
+ int r = 0;
+
+ if (type == KVM_IPC_VMSTATE)
+ r = write(fd, &kvm->vm_state, sizeof(kvm->vm_state));
+
+ if (r < 0)
+ pr_warning("Failed sending VMSTATE");
+}
+
+static void handle_debug(int fd, u32 type, u32 len, u8 *msg)
+{
+ int i;
+ struct debug_cmd_params *params;
+ u32 dbg_type;
+ u32 vcpu;
+
+ if (WARN_ON(type != KVM_IPC_DEBUG || len != sizeof(*params)))
+ return;
+
+ params = (void *)msg;
+ dbg_type = params->dbg_type;
+ vcpu = params->cpu;
+
+ if (dbg_type & KVM_DEBUG_CMD_TYPE_SYSRQ)
+ serial8250__inject_sysrq(kvm, params->sysrq);
+
+ if (dbg_type & KVM_DEBUG_CMD_TYPE_NMI) {
+ if ((int)vcpu >= kvm->nrcpus)
+ return;
+
+ kvm_cpus[vcpu]->needs_nmi = 1;
+ pthread_kill(kvm_cpus[vcpu]->thread, SIGUSR1);
+ }
+
+ if (!(dbg_type & KVM_DEBUG_CMD_TYPE_DUMP))
+ return;
+
+ for (i = 0; i < nrcpus; i++) {
+ struct kvm_cpu *cpu = kvm_cpus[i];
+
+ if (!cpu)
+ continue;
+
+ printout_done = 0;
+
+ kvm_cpu__set_debug_fd(fd);
+ pthread_kill(cpu->thread, SIGUSR1);
+ /*
+ * Wait for the vCPU to dump state before signalling
+ * the next thread. Since this is debug code it does
+ * not matter that we are burning CPU time a bit:
+ */
+ while (!printout_done)
+ mb();
+ }
+
+ close(fd);
+
+ serial8250__inject_sysrq(kvm, 'p');
+}
+
+static void handle_sigalrm(int sig)
+{
+ kvm__arch_periodic_poll(kvm);
+}
+
+static void handle_stop(int fd, u32 type, u32 len, u8 *msg)
+{
+ if (WARN_ON(type != KVM_IPC_STOP || len))
+ return;
+
+ kvm_cpu__reboot();
+}
+
+static void *kvm_cpu_thread(void *arg)
+{
+ current_kvm_cpu = arg;
+
+ if (kvm_cpu__start(current_kvm_cpu))
+ goto panic_kvm;
+
+ return (void *) (intptr_t) 0;
+
+panic_kvm:
+ fprintf(stderr, "KVM exit reason: %u (\"%s\")\n",
+ current_kvm_cpu->kvm_run->exit_reason,
+ kvm_exit_reasons[current_kvm_cpu->kvm_run->exit_reason]);
+ if (current_kvm_cpu->kvm_run->exit_reason == KVM_EXIT_UNKNOWN)
+ fprintf(stderr, "KVM exit code: 0x%Lu\n",
+ current_kvm_cpu->kvm_run->hw.hardware_exit_reason);
+
+ kvm_cpu__set_debug_fd(STDOUT_FILENO);
+ kvm_cpu__show_registers(current_kvm_cpu);
+ kvm_cpu__show_code(current_kvm_cpu);
+ kvm_cpu__show_page_tables(current_kvm_cpu);
+
+ return (void *) (intptr_t) 1;
+}
+
+static char kernel[PATH_MAX];
+
+static const char *host_kernels[] = {
+ "/boot/vmlinuz",
+ "/boot/bzImage",
+ NULL
+};
+
+static const char *default_kernels[] = {
+ "./bzImage",
+ "arch/" BUILD_ARCH "/boot/bzImage",
+ "../../arch/" BUILD_ARCH "/boot/bzImage",
+ NULL
+};
+
+static const char *default_vmlinux[] = {
+ "vmlinux",
+ "../../../vmlinux",
+ "../../vmlinux",
+ NULL
+};
+
+static void kernel_usage_with_options(void)
+{
+ const char **k;
+ struct utsname uts;
+
+ fprintf(stderr, "Fatal: could not find default kernel image in:\n");
+ k = &default_kernels[0];
+ while (*k) {
+ fprintf(stderr, "\t%s\n", *k);
+ k++;
+ }
+
+ if (uname(&uts) < 0)
+ return;
+
+ k = &host_kernels[0];
+ while (*k) {
+ if (snprintf(kernel, PATH_MAX, "%s-%s", *k, uts.release) < 0)
+ return;
+ fprintf(stderr, "\t%s\n", kernel);
+ k++;
+ }
+ fprintf(stderr, "\nPlease see '%s run --help' for more options.\n\n",
+ KVM_BINARY_NAME);
+}
+
+static u64 host_ram_size(void)
+{
+ long page_size;
+ long nr_pages;
+
+ nr_pages = sysconf(_SC_PHYS_PAGES);
+ if (nr_pages < 0) {
+ pr_warning("sysconf(_SC_PHYS_PAGES) failed");
+ return 0;
+ }
+
+ page_size = sysconf(_SC_PAGE_SIZE);
+ if (page_size < 0) {
+ pr_warning("sysconf(_SC_PAGE_SIZE) failed");
+ return 0;
+ }
+
+ return (nr_pages * page_size) >> MB_SHIFT;
+}
+
+/*
+ * If user didn't specify how much memory it wants to allocate for the guest,
+ * avoid filling the whole host RAM.
+ */
+#define RAM_SIZE_RATIO 0.8
+
+static u64 get_ram_size(int nr_cpus)
+{
+ u64 available;
+ u64 ram_size;
+
+ ram_size = 64 * (nr_cpus + 3);
+
+ available = host_ram_size() * RAM_SIZE_RATIO;
+ if (!available)
+ available = MIN_RAM_SIZE_MB;
+
+ if (ram_size > available)
+ ram_size = available;
+
+ return ram_size;
+}
+
+static const char *find_kernel(void)
+{
+ const char **k;
+ struct stat st;
+ struct utsname uts;
+
+ k = &default_kernels[0];
+ while (*k) {
+ if (stat(*k, &st) < 0 || !S_ISREG(st.st_mode)) {
+ k++;
+ continue;
+ }
+ strncpy(kernel, *k, PATH_MAX);
+ return kernel;
+ }
+
+ if (uname(&uts) < 0)
+ return NULL;
+
+ k = &host_kernels[0];
+ while (*k) {
+ if (snprintf(kernel, PATH_MAX, "%s-%s", *k, uts.release) < 0)
+ return NULL;
+
+ if (stat(kernel, &st) < 0 || !S_ISREG(st.st_mode)) {
+ k++;
+ continue;
+ }
+ return kernel;
+
+ }
+ return NULL;
+}
+
+static const char *find_vmlinux(void)
+{
+ const char **vmlinux;
+
+ vmlinux = &default_vmlinux[0];
+ while (*vmlinux) {
+ struct stat st;
+
+ if (stat(*vmlinux, &st) < 0 || !S_ISREG(st.st_mode)) {
+ vmlinux++;
+ continue;
+ }
+ return *vmlinux;
+ }
+ return NULL;
+}
+
+void kvm_run_help(void)
+{
+ usage_with_options(run_usage, options);
+}
+
+static int kvm_setup_guest_init(void)
+{
+ const char *rootfs = custom_rootfs_name;
+ char tmp[PATH_MAX];
+ size_t size;
+ int fd, ret;
+ char *data;
+
+ /* Setup /virt/init */
+ size = (size_t)&_binary_guest_init_size;
+ data = (char *)&_binary_guest_init_start;
+ snprintf(tmp, PATH_MAX, "%s%s/virt/init", kvm__get_dir(), rootfs);
+ remove(tmp);
+ fd = open(tmp, O_CREAT | O_WRONLY, 0755);
+ if (fd < 0)
+ die("Fail to setup %s", tmp);
+ ret = xwrite(fd, data, size);
+ if (ret < 0)
+ die("Fail to setup %s", tmp);
+ close(fd);
+
+ return 0;
+}
+
+static int kvm_run_set_sandbox(void)
+{
+ const char *guestfs_name = custom_rootfs_name;
+ char path[PATH_MAX], script[PATH_MAX], *tmp;
+
+ snprintf(path, PATH_MAX, "%s%s/virt/sandbox.sh", kvm__get_dir(), guestfs_name);
+
+ remove(path);
+
+ if (sandbox == NULL)
+ return 0;
+
+ tmp = realpath(sandbox, NULL);
+ if (tmp == NULL)
+ return -ENOMEM;
+
+ snprintf(script, PATH_MAX, "/host/%s", tmp);
+ free(tmp);
+
+ return symlink(script, path);
+}
+
+static void kvm_write_sandbox_cmd_exactly(int fd, const char *arg)
+{
+ const char *single_quote;
+
+ if (!*arg) { /* zero length string */
+ if (write(fd, "''", 2) <= 0)
+ die("Failed writing sandbox script");
+ return;
+ }
+
+ while (*arg) {
+ single_quote = strchrnul(arg, '\'');
+
+ /* write non-single-quote string as #('string') */
+ if (arg != single_quote) {
+ if (write(fd, "'", 1) <= 0 ||
+ write(fd, arg, single_quote - arg) <= 0 ||
+ write(fd, "'", 1) <= 0)
+ die("Failed writing sandbox script");
+ }
+
+ /* write single quote as #("'") */
+ if (*single_quote) {
+ if (write(fd, "\"'\"", 3) <= 0)
+ die("Failed writing sandbox script");
+ } else
+ break;
+
+ arg = single_quote + 1;
+ }
+}
+
+static void resolve_program(const char *src, char *dst, size_t len)
+{
+ struct stat st;
+ int err;
+
+ err = stat(src, &st);
+
+ if (!err && S_ISREG(st.st_mode)) {
+ char resolved_path[PATH_MAX];
+
+ if (!realpath(src, resolved_path))
+ die("Unable to resolve program %s: %s\n", src, strerror(errno));
+
+ snprintf(dst, len, "/host%s", resolved_path);
+ } else
+ strncpy(dst, src, len);
+}
+
+static void kvm_run_write_sandbox_cmd(const char **argv, int argc)
+{
+ const char script_hdr[] = "#! /bin/bash\n\n";
+ char program[PATH_MAX];
+ int fd;
+
+ remove(sandbox);
+
+ fd = open(sandbox, O_RDWR | O_CREAT, 0777);
+ if (fd < 0)
+ die("Failed creating sandbox script");
+
+ if (write(fd, script_hdr, sizeof(script_hdr) - 1) <= 0)
+ die("Failed writing sandbox script");
+
+ resolve_program(argv[0], program, PATH_MAX);
+ kvm_write_sandbox_cmd_exactly(fd, program);
+
+ argv++;
+ argc--;
+
+ while (argc) {
+ if (write(fd, " ", 1) <= 0)
+ die("Failed writing sandbox script");
+
+ kvm_write_sandbox_cmd_exactly(fd, argv[0]);
+ argv++;
+ argc--;
+ }
+ if (write(fd, "\n", 1) <= 0)
+ die("Failed writing sandbox script");
+
+ close(fd);
+}
+
+static int kvm_cmd_run_init(int argc, const char **argv)
+{
+ static char real_cmdline[2048], default_name[20];
+ struct framebuffer *fb = NULL;
+ unsigned int nr_online_cpus;
+ int max_cpus, recommended_cpus;
+ int i, r;
+
+ signal(SIGALRM, handle_sigalrm);
+ kvm_ipc__register_handler(KVM_IPC_DEBUG, handle_debug);
+ signal(SIGUSR1, handle_sigusr1);
+ kvm_ipc__register_handler(KVM_IPC_PAUSE, handle_pause);
+ kvm_ipc__register_handler(KVM_IPC_RESUME, handle_pause);
+ kvm_ipc__register_handler(KVM_IPC_STOP, handle_stop);
+ kvm_ipc__register_handler(KVM_IPC_VMSTATE, handle_vmstate);
+
+ nr_online_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+ while (argc != 0) {
+ argc = parse_options(argc, argv, options, run_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION |
+ PARSE_OPT_KEEP_DASHDASH);
+ if (argc != 0) {
+ /* Cusrom options, should have been handled elsewhere */
+ if (strcmp(argv[0], "--") == 0) {
+ if (kvm_run_wrapper == KVM_RUN_SANDBOX) {
+ sandbox = DEFAULT_SANDBOX_FILENAME;
+ kvm_run_write_sandbox_cmd(argv+1, argc-1);
+ break;
+ }
+ }
+
+ if ((kvm_run_wrapper == KVM_RUN_DEFAULT && kernel_filename) ||
+ (kvm_run_wrapper == KVM_RUN_SANDBOX && sandbox)) {
+ fprintf(stderr, "Cannot handle parameter: "
+ "%s\n", argv[0]);
+ usage_with_options(run_usage, options);
+ return -EINVAL;
+ }
+ if (kvm_run_wrapper == KVM_RUN_SANDBOX) {
+ /*
+ * first unhandled parameter is treated as
+ * sandbox command
+ */
+ sandbox = DEFAULT_SANDBOX_FILENAME;
+ kvm_run_write_sandbox_cmd(argv, argc);
+ } else {
+ /*
+ * first unhandled parameter is treated as a kernel
+ * image
+ */
+ kernel_filename = argv[0];
+ }
+ argv++;
+ argc--;
+ }
+
+ }
+
+ if (!kernel_filename)
+ kernel_filename = find_kernel();
+
+ if (!kernel_filename) {
+ kernel_usage_with_options();
+ return -EINVAL;
+ }
+
+ vmlinux_filename = find_vmlinux();
+
+ if (nrcpus == 0)
+ nrcpus = nr_online_cpus;
+
+ if (!ram_size)
+ ram_size = get_ram_size(nrcpus);
+
+ if (ram_size < MIN_RAM_SIZE_MB)
+ die("Not enough memory specified: %lluMB (min %lluMB)", ram_size, MIN_RAM_SIZE_MB);
+
+ if (ram_size > host_ram_size())
+ pr_warning("Guest memory size %lluMB exceeds host physical RAM size %lluMB", ram_size, host_ram_size());
+
+ ram_size <<= MB_SHIFT;
+
+ if (!dev)
+ dev = DEFAULT_KVM_DEV;
+
+ if (!console)
+ console = DEFAULT_CONSOLE;
+
+ if (!strncmp(console, "virtio", 6))
+ active_console = CONSOLE_VIRTIO;
+ else if (!strncmp(console, "serial", 6))
+ active_console = CONSOLE_8250;
+ else if (!strncmp(console, "hv", 2))
+ active_console = CONSOLE_HV;
+ else
+ pr_warning("No console!");
+
+ if (!host_ip)
+ host_ip = DEFAULT_HOST_ADDR;
+
+ if (!guest_ip)
+ guest_ip = DEFAULT_GUEST_ADDR;
+
+ if (!guest_mac)
+ guest_mac = DEFAULT_GUEST_MAC;
+
+ if (!host_mac)
+ host_mac = DEFAULT_HOST_MAC;
+
+ if (!script)
+ script = DEFAULT_SCRIPT;
+
+ term_init();
+
+ if (!guest_name) {
+ if (custom_rootfs) {
+ guest_name = custom_rootfs_name;
+ } else {
+ sprintf(default_name, "guest-%u", getpid());
+ guest_name = default_name;
+ }
+ }
+
+ kvm = kvm__init(dev, hugetlbfs_path, ram_size, guest_name);
+ if (IS_ERR(kvm)) {
+ r = PTR_ERR(kvm);
+ goto fail;
+ }
+
+ kvm->single_step = single_step;
+
+ r = ioeventfd__init(kvm);
+ if (r < 0) {
+ pr_err("ioeventfd__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ max_cpus = kvm__max_cpus(kvm);
+ recommended_cpus = kvm__recommended_cpus(kvm);
+
+ if (nrcpus > max_cpus) {
+ printf(" # Limit the number of CPUs to %d\n", max_cpus);
+ nrcpus = max_cpus;
+ } else if (nrcpus > recommended_cpus) {
+ printf(" # Warning: The maximum recommended amount of VCPUs"
+ " is %d\n", recommended_cpus);
+ }
+
+ kvm->nrcpus = nrcpus;
+
+ /* Alloc one pointer too many, so array ends up 0-terminated */
+ kvm_cpus = calloc(nrcpus + 1, sizeof(void *));
+ if (!kvm_cpus)
+ die("Couldn't allocate array for %d CPUs", nrcpus);
+
+ r = irq__init(kvm);
+ if (r < 0) {
+ pr_err("irq__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ r = pci__init(kvm);
+ if (r < 0) {
+ pr_err("pci__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ r = ioport__init(kvm);
+ if (r < 0) {
+ pr_err("ioport__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ /*
+ * vidmode should be either specified
+ * either set by default
+ */
+ if (vnc || sdl) {
+ if (vidmode == -1)
+ vidmode = 0x312;
+ } else {
+ vidmode = 0;
+ }
+
+ memset(real_cmdline, 0, sizeof(real_cmdline));
+ kvm__arch_set_cmdline(real_cmdline, vnc || sdl);
+
+ if (strlen(real_cmdline) > 0)
+ strcat(real_cmdline, " ");
+
+ if (kernel_cmdline)
+ strlcat(real_cmdline, kernel_cmdline, sizeof(real_cmdline));
+
+ if (!using_rootfs && !disk_image[0].filename && !initrd_filename) {
+ char tmp[PATH_MAX];
+
+ kvm_setup_create_new(custom_rootfs_name);
+ kvm_setup_resolv(custom_rootfs_name);
+
+ snprintf(tmp, PATH_MAX, "%s%s", kvm__get_dir(), "default");
+ if (virtio_9p__register(kvm, tmp, "/dev/root") < 0)
+ die("Unable to initialize virtio 9p");
+ if (virtio_9p__register(kvm, "/", "hostfs") < 0)
+ die("Unable to initialize virtio 9p");
+ using_rootfs = custom_rootfs = 1;
+ }
+
+ if (using_rootfs) {
+ strcat(real_cmdline, " root=/dev/root rw rootflags=rw,trans=virtio,version=9p2000.L rootfstype=9p");
+ if (custom_rootfs) {
+ kvm_run_set_sandbox();
+
+ strcat(real_cmdline, " init=/virt/init");
+
+ if (!no_dhcp)
+ strcat(real_cmdline, " ip=dhcp");
+ if (kvm_setup_guest_init())
+ die("Failed to setup init for guest.");
+ }
+ } else if (!strstr(real_cmdline, "root=")) {
+ strlcat(real_cmdline, " root=/dev/vda rw ", sizeof(real_cmdline));
+ }
+
+ if (image_count) {
+ kvm->nr_disks = image_count;
+ kvm->disks = disk_image__open_all((struct disk_image_params *)&disk_image, image_count);
+ if (IS_ERR(kvm->disks)) {
+ r = PTR_ERR(kvm->disks);
+ pr_err("disk_image__open_all() failed with error %ld\n",
+ PTR_ERR(kvm->disks));
+ goto fail;
+ }
+ }
+
+ printf(" # %s run -k %s -m %Lu -c %d --name %s\n", KVM_BINARY_NAME,
+ kernel_filename, ram_size / 1024 / 1024, nrcpus, guest_name);
+
+ if (!firmware_filename) {
+ if (!kvm__load_kernel(kvm, kernel_filename,
+ initrd_filename, real_cmdline, vidmode))
+ die("unable to load kernel %s", kernel_filename);
+
+ kvm->vmlinux = vmlinux_filename;
+ r = symbol_init(kvm);
+ if (r < 0)
+ pr_debug("symbol_init() failed with error %d\n", r);
+ }
+
+ ioport__setup_arch();
+
+ r = rtc__init(kvm);
+ if (r < 0) {
+ pr_err("rtc__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ r = serial8250__init(kvm);
+ if (r < 0) {
+ pr_err("serial__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ r = virtio_blk__init(kvm);
+ if (r < 0) {
+ pr_err("virtio_blk__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ r = virtio_scsi_init(kvm);
+ if (r < 0) {
+ pr_err("virtio_scsi_init() failed with error %d\n", r);
+ goto fail;
+ }
+
+
+ if (active_console == CONSOLE_VIRTIO)
+ virtio_console__init(kvm);
+
+ if (virtio_rng)
+ virtio_rng__init(kvm);
+
+ if (balloon)
+ virtio_bln__init(kvm);
+
+ if (!network)
+ network = DEFAULT_NETWORK;
+
+ virtio_9p__init(kvm);
+
+ for (i = 0; i < num_net_devices; i++) {
+ net_params[i].kvm = kvm;
+ virtio_net__init(&net_params[i]);
+ }
+
+ if (num_net_devices == 0 && no_net == 0) {
+ struct virtio_net_params net_params;
+
+ net_params = (struct virtio_net_params) {
+ .guest_ip = guest_ip,
+ .host_ip = host_ip,
+ .kvm = kvm,
+ .script = script,
+ .mode = NET_MODE_USER,
+ };
+ str_to_mac(guest_mac, net_params.guest_mac);
+ str_to_mac(host_mac, net_params.host_mac);
+
+ virtio_net__init(&net_params);
+ }
+
+ kvm__init_ram(kvm);
+
+#ifdef CONFIG_X86
+ kbd__init(kvm);
+#endif
+
+ pci_shmem__init(kvm);
+
+ if (vnc || sdl) {
+ fb = vesa__init(kvm);
+ if (IS_ERR(fb)) {
+ pr_err("vesa__init() failed with error %ld\n", PTR_ERR(fb));
+ goto fail;
+ }
+ }
+
+ if (vnc && fb) {
+ r = vnc__init(fb);
+ if (r < 0) {
+ pr_err("vnc__init() failed with error %d\n", r);
+ goto fail;
+ }
+ }
+
+ if (sdl && fb) {
+ sdl__init(fb);
+ if (r < 0) {
+ pr_err("sdl__init() failed with error %d\n", r);
+ goto fail;
+ }
+ }
+
+ r = fb__start();
+ if (r < 0) {
+ pr_err("fb__init() failed with error %d\n", r);
+ goto fail;
+ }
+
+ /* Device init all done; firmware init must
+ * come after this (it may set up device trees etc.)
+ */
+
+ kvm__start_timer(kvm);
+
+ if (firmware_filename) {
+ if (!kvm__load_firmware(kvm, firmware_filename))
+ die("unable to load firmware image %s: %s", firmware_filename, strerror(errno));
+ } else {
+ kvm__arch_setup_firmware(kvm);
+ if (r < 0) {
+ pr_err("kvm__arch_setup_firmware() failed with error %d\n", r);
+ goto fail;
+ }
+ }
+
+ for (i = 0; i < nrcpus; i++) {
+ kvm_cpus[i] = kvm_cpu__init(kvm, i);
+ if (!kvm_cpus[i])
+ die("unable to initialize KVM VCPU");
+ }
+
+ thread_pool__init(nr_online_cpus);
+fail:
+ return r;
+}
+
+static int kvm_cmd_run_work(void)
+{
+ int i, r = -1;
+ void *ret = NULL;
+
+ for (i = 0; i < nrcpus; i++) {
+ if (pthread_create(&kvm_cpus[i]->thread, NULL, kvm_cpu_thread, kvm_cpus[i]) != 0)
+ die("unable to create KVM VCPU thread");
+ }
+
+ /* Only VCPU #0 is going to exit by itself when shutting down */
+ if (pthread_join(kvm_cpus[0]->thread, &ret) != 0)
+ r = 0;
+
+ kvm_cpu__delete(kvm_cpus[0]);
+ kvm_cpus[0] = NULL;
+
+ for (i = 1; i < nrcpus; i++) {
+ if (kvm_cpus[i]->is_running) {
+ pthread_kill(kvm_cpus[i]->thread, SIGKVMEXIT);
+ if (pthread_join(kvm_cpus[i]->thread, &ret) != 0)
+ die("pthread_join");
+ kvm_cpu__delete(kvm_cpus[i]);
+ }
+ if (ret == NULL)
+ r = 0;
+ }
+
+ return r;
+}
+
+static void kvm_cmd_run_exit(int guest_ret)
+{
+ int r = 0;
+
+ compat__print_all_messages();
+
+ r = symbol_exit(kvm);
+ if (r < 0)
+ pr_warning("symbol_exit() failed with error %d\n", r);
+
+ r = irq__exit(kvm);
+ if (r < 0)
+ pr_warning("irq__exit() failed with error %d\n", r);
+
+ fb__stop();
+
+ r = virtio_scsi_exit(kvm);
+ if (r < 0)
+ pr_warning("virtio_scsi_exit() failed with error %d\n", r);
+
+ r = virtio_blk__exit(kvm);
+ if (r < 0)
+ pr_warning("virtio_blk__exit() failed with error %d\n", r);
+
+ r = virtio_rng__exit(kvm);
+ if (r < 0)
+ pr_warning("virtio_rng__exit() failed with error %d\n", r);
+
+ r = disk_image__close_all(kvm->disks, image_count);
+ if (r < 0)
+ pr_warning("disk_image__close_all() failed with error %d\n", r);
+
+ r = serial8250__exit(kvm);
+ if (r < 0)
+ pr_warning("serial8250__exit() failed with error %d\n", r);
+
+ r = rtc__exit(kvm);
+ if (r < 0)
+ pr_warning("rtc__exit() failed with error %d\n", r);
+
+ r = kvm__arch_free_firmware(kvm);
+ if (r < 0)
+ pr_warning("kvm__arch_free_firmware() failed with error %d\n", r);
+
+ r = ioport__exit(kvm);
+ if (r < 0)
+ pr_warning("ioport__exit() failed with error %d\n", r);
+
+ r = ioeventfd__exit(kvm);
+ if (r < 0)
+ pr_warning("ioeventfd__exit() failed with error %d\n", r);
+
+ r = pci__exit(kvm);
+ if (r < 0)
+ pr_warning("pci__exit() failed with error %d\n", r);
+
+ r = kvm__exit(kvm);
+ if (r < 0)
+ pr_warning("pci__exit() failed with error %d\n", r);
+
+ free(kvm_cpus);
+
+ if (guest_ret == 0)
+ printf("\n # KVM session ended normally.\n");
+}
+
+int kvm_cmd_run(int argc, const char **argv, const char *prefix)
+{
+ int r, ret = -EFAULT;
+
+ r = kvm_cmd_run_init(argc, argv);
+ if (r < 0)
+ return r;
+
+ ret = kvm_cmd_run_work();
+ kvm_cmd_run_exit(ret);
+
+ return ret;
+}
--- /dev/null
+#include "kvm/builtin-sandbox.h"
+#include "kvm/builtin-run.h"
+
+int kvm_cmd_sandbox(int argc, const char **argv, const char *prefix)
+{
+ kvm_run_set_wrapper_sandbox();
+
+ return kvm_cmd_run(argc, argv, prefix);
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-setup.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/read-write.h>
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <limits.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+extern char _binary_guest_init_start;
+extern char _binary_guest_init_size;
+
+static const char *instance_name;
+
+static const char * const setup_usage[] = {
+ "lkvm setup [name]",
+ NULL
+};
+
+static const struct option setup_options[] = {
+ OPT_END()
+};
+
+static void parse_setup_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, setup_options, setup_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0 && instance_name)
+ kvm_setup_help();
+ else
+ instance_name = argv[0];
+ argv++;
+ argc--;
+ }
+}
+
+void kvm_setup_help(void)
+{
+ printf("\n%s setup creates a new rootfs under %s.\n"
+ "This can be used later by the '-d' parameter of '%s run'.\n",
+ KVM_BINARY_NAME, kvm__get_dir(), KVM_BINARY_NAME);
+ usage_with_options(setup_usage, setup_options);
+}
+
+static int copy_file(const char *from, const char *to)
+{
+ int in_fd, out_fd;
+ void *src, *dst;
+ struct stat st;
+ int err = -1;
+
+ in_fd = open(from, O_RDONLY);
+ if (in_fd < 0)
+ return err;
+
+ if (fstat(in_fd, &st) < 0)
+ goto error_close_in;
+
+ out_fd = open(to, O_RDWR | O_CREAT | O_TRUNC, st.st_mode & (S_IRWXU|S_IRWXG|S_IRWXO));
+ if (out_fd < 0)
+ goto error_close_in;
+
+ src = mmap(NULL, st.st_size, PROT_READ, MAP_SHARED, in_fd, 0);
+ if (src == MAP_FAILED)
+ goto error_close_out;
+
+ if (ftruncate(out_fd, st.st_size) < 0)
+ goto error_munmap_src;
+
+ dst = mmap(NULL, st.st_size, PROT_READ|PROT_WRITE, MAP_SHARED, out_fd, 0);
+ if (dst == MAP_FAILED)
+ goto error_munmap_src;
+
+ memcpy(dst, src, st.st_size);
+
+ if (fsync(out_fd) < 0)
+ goto error_munmap_dst;
+
+ err = 0;
+
+error_munmap_dst:
+ munmap(dst, st.st_size);
+error_munmap_src:
+ munmap(src, st.st_size);
+error_close_out:
+ close(out_fd);
+error_close_in:
+ close(in_fd);
+
+ return err;
+}
+
+static const char *guestfs_dirs[] = {
+ "/dev",
+ "/etc",
+ "/home",
+ "/host",
+ "/proc",
+ "/root",
+ "/sys",
+ "/tmp",
+ "/var",
+ "/var/lib",
+ "/virt",
+ "/virt/home",
+};
+
+static const char *guestfs_symlinks[] = {
+ "/bin",
+ "/lib",
+ "/lib64",
+ "/sbin",
+ "/usr",
+ "/etc/ld.so.conf",
+};
+
+static int copy_init(const char *guestfs_name)
+{
+ char path[PATH_MAX];
+ size_t size;
+ int fd, ret;
+ char *data;
+
+ size = (size_t)&_binary_guest_init_size;
+ data = (char *)&_binary_guest_init_start;
+ snprintf(path, PATH_MAX, "%s%s/virt/init", kvm__get_dir(), guestfs_name);
+ remove(path);
+ fd = open(path, O_CREAT | O_WRONLY, 0755);
+ if (fd < 0)
+ die("Fail to setup %s", path);
+ ret = xwrite(fd, data, size);
+ if (ret < 0)
+ die("Fail to setup %s", path);
+ close(fd);
+
+ return 0;
+}
+
+static int copy_passwd(const char *guestfs_name)
+{
+ char path[PATH_MAX];
+ FILE *file;
+ int ret;
+
+ snprintf(path, PATH_MAX, "%s%s/etc/passwd", kvm__get_dir(), guestfs_name);
+
+ file = fopen(path, "w");
+ if (!file)
+ return -1;
+
+ ret = fprintf(file, "root:x:0:0:root:/root:/bin/sh\n");
+ if (ret < 0)
+ return ret;
+
+ fclose(file);
+
+ return 0;
+}
+
+static int make_guestfs_symlink(const char *guestfs_name, const char *path)
+{
+ char target[PATH_MAX];
+ char name[PATH_MAX];
+
+ snprintf(name, PATH_MAX, "%s%s%s", kvm__get_dir(), guestfs_name, path);
+
+ snprintf(target, PATH_MAX, "/host%s", path);
+
+ return symlink(target, name);
+}
+
+static int make_dir(const char *dir)
+{
+ char name[PATH_MAX];
+
+ snprintf(name, PATH_MAX, "%s%s", kvm__get_dir(), dir);
+
+ return mkdir(name, 0777);
+}
+
+static void make_guestfs_dir(const char *guestfs_name, const char *dir)
+{
+ char name[PATH_MAX];
+
+ snprintf(name, PATH_MAX, "%s%s", guestfs_name, dir);
+
+ make_dir(name);
+}
+
+void kvm_setup_resolv(const char *guestfs_name)
+{
+ char path[PATH_MAX];
+
+ snprintf(path, PATH_MAX, "%s%s/etc/resolv.conf", kvm__get_dir(), guestfs_name);
+
+ copy_file("/etc/resolv.conf", path);
+}
+
+static int do_setup(const char *guestfs_name)
+{
+ unsigned int i;
+ int ret;
+
+ ret = make_dir(guestfs_name);
+ if (ret < 0)
+ return ret;
+
+ for (i = 0; i < ARRAY_SIZE(guestfs_dirs); i++)
+ make_guestfs_dir(guestfs_name, guestfs_dirs[i]);
+
+ for (i = 0; i < ARRAY_SIZE(guestfs_symlinks); i++) {
+ make_guestfs_symlink(guestfs_name, guestfs_symlinks[i]);
+ }
+
+ ret = copy_init(guestfs_name);
+ if (ret < 0)
+ return ret;
+
+ return copy_passwd(guestfs_name);
+}
+
+int kvm_setup_create_new(const char *guestfs_name)
+{
+ return do_setup(guestfs_name);
+}
+
+int kvm_cmd_setup(int argc, const char **argv, const char *prefix)
+{
+ int r;
+
+ parse_setup_options(argc, argv);
+
+ if (instance_name == NULL)
+ kvm_setup_help();
+
+ r = do_setup(instance_name);
+ if (r == 0)
+ printf("A new rootfs '%s' has been created in '%s%s'.\n\n"
+ "You can now start it by running the following command:\n\n"
+ " %s run -d %s\n",
+ instance_name, kvm__get_dir(), instance_name,
+ KVM_BINARY_NAME,instance_name);
+ else
+ printf("Unable to create rootfs in %s%s: %s\n",
+ kvm__get_dir(), instance_name, strerror(errno));
+
+ return r;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-stat.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <sys/select.h>
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+#include <linux/virtio_balloon.h>
+
+static bool mem;
+static bool all;
+static const char *instance_name;
+
+static const char * const stat_usage[] = {
+ "lkvm stat [command] [--all] [-n name]",
+ NULL
+};
+
+static const struct option stat_options[] = {
+ OPT_GROUP("Commands options:"),
+ OPT_BOOLEAN('m', "memory", &mem, "Display memory statistics"),
+ OPT_GROUP("Instance options:"),
+ OPT_BOOLEAN('a', "all", &all, "All instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_stat_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, stat_options, stat_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_stat_help();
+ }
+}
+
+void kvm_stat_help(void)
+{
+ usage_with_options(stat_usage, stat_options);
+}
+
+static int do_memstat(const char *name, int sock)
+{
+ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+ fd_set fdset;
+ struct timeval t = { .tv_sec = 1 };
+ int r;
+ u8 i;
+
+ FD_ZERO(&fdset);
+ FD_SET(sock, &fdset);
+ r = kvm_ipc__send(sock, KVM_IPC_STAT);
+ if (r < 0)
+ return r;
+
+ r = select(1, &fdset, NULL, NULL, &t);
+ if (r < 0) {
+ pr_err("Could not retrieve mem stats from %s", name);
+ return r;
+ }
+ r = read(sock, &stats, sizeof(stats));
+ if (r < 0)
+ return r;
+
+ printf("\n\n\t*** Guest memory statistics ***\n\n");
+ for (i = 0; i < VIRTIO_BALLOON_S_NR; i++) {
+ switch (stats[i].tag) {
+ case VIRTIO_BALLOON_S_SWAP_IN:
+ printf("The amount of memory that has been swapped in (in bytes):");
+ break;
+ case VIRTIO_BALLOON_S_SWAP_OUT:
+ printf("The amount of memory that has been swapped out to disk (in bytes):");
+ break;
+ case VIRTIO_BALLOON_S_MAJFLT:
+ printf("The number of major page faults that have occurred:");
+ break;
+ case VIRTIO_BALLOON_S_MINFLT:
+ printf("The number of minor page faults that have occurred:");
+ break;
+ case VIRTIO_BALLOON_S_MEMFREE:
+ printf("The amount of memory not being used for any purpose (in bytes):");
+ break;
+ case VIRTIO_BALLOON_S_MEMTOT:
+ printf("The total amount of memory available (in bytes):");
+ break;
+ }
+ printf("%llu\n", stats[i].val);
+ }
+ printf("\n");
+
+ return 0;
+}
+
+int kvm_cmd_stat(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r = 0;
+
+ parse_stat_options(argc, argv);
+
+ if (!mem)
+ usage_with_options(stat_usage, stat_options);
+
+ if (mem && all)
+ return kvm__enumerate_instances(do_memstat);
+
+ if (instance_name == NULL)
+ kvm_stat_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ if (mem)
+ r = do_memstat(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-stop.h>
+#include <kvm/kvm.h>
+#include <kvm/parse-options.h>
+#include <kvm/kvm-ipc.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+static bool all;
+static const char *instance_name;
+
+static const char * const stop_usage[] = {
+ "lkvm stop [--all] [-n name]",
+ NULL
+};
+
+static const struct option stop_options[] = {
+ OPT_GROUP("General options:"),
+ OPT_BOOLEAN('a', "all", &all, "Stop all instances"),
+ OPT_STRING('n', "name", &instance_name, "name", "Instance name"),
+ OPT_END()
+};
+
+static void parse_stop_options(int argc, const char **argv)
+{
+ while (argc != 0) {
+ argc = parse_options(argc, argv, stop_options, stop_usage,
+ PARSE_OPT_STOP_AT_NON_OPTION);
+ if (argc != 0)
+ kvm_stop_help();
+ }
+}
+
+void kvm_stop_help(void)
+{
+ usage_with_options(stop_usage, stop_options);
+}
+
+static int do_stop(const char *name, int sock)
+{
+ return kvm_ipc__send(sock, KVM_IPC_STOP);
+}
+
+int kvm_cmd_stop(int argc, const char **argv, const char *prefix)
+{
+ int instance;
+ int r;
+
+ parse_stop_options(argc, argv);
+
+ if (all)
+ return kvm__enumerate_instances(do_stop);
+
+ if (instance_name == NULL)
+ kvm_stop_help();
+
+ instance = kvm__get_sock_by_instance(instance_name);
+
+ if (instance <= 0)
+ die("Failed locating instance");
+
+ r = do_stop(instance_name, instance);
+
+ close(instance);
+
+ return r;
+}
--- /dev/null
+#include <kvm/util.h>
+#include <kvm/kvm-cmd.h>
+#include <kvm/builtin-version.h>
+#include <kvm/kvm.h>
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+
+int kvm_cmd_version(int argc, const char **argv, const char *prefix)
+{
+ printf("kvm tool %s\n", KVMTOOLS_VERSION);
+
+ return 0;
+}
--- /dev/null
+/*
+ * code16gcc.h
+ *
+ * This file is -include'd when compiling 16-bit C code.
+ * Note: this asm() needs to be emitted before gcc emits any code.
+ * Depending on gcc version, this requires -fno-unit-at-a-time or
+ * -fno-toplevel-reorder.
+ *
+ * Hopefully gcc will eventually have a real -m16 option so we can
+ * drop this hack long term.
+ */
+
+#ifndef __ASSEMBLY__
+asm(".code16gcc");
+#endif
--- /dev/null
+#
+# List of known perf commands.
+# command name category [deprecated] [common]
+#
+lkvm-run mainporcelain common
+lkvm-setup mainporcelain common
+lkvm-pause common
+lkvm-resume common
+lkvm-version common
+lkvm-list common
+lkvm-debug common
+lkvm-balloon common
+lkvm-stop common
+lkvm-stat common
+lkvm-sandbox common
--- /dev/null
+define SOURCE_HELLO
+#include <stdio.h>
+int main(void)
+{
+ return puts(\"hi\");
+}
+endef
+
+ifndef NO_DWARF
+define SOURCE_DWARF
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/version.h>
+#ifndef _ELFUTILS_PREREQ
+#error
+#endif
+
+int main(void)
+{
+ Dwarf *dbg = dwarf_begin(0, DWARF_C_READ);
+ return (long)dbg;
+}
+endef
+endif
+
+define SOURCE_LIBELF
+#include <libelf.h>
+
+int main(void)
+{
+ Elf *elf = elf_begin(0, ELF_C_READ, 0);
+ return (long)elf;
+}
+endef
+
+define SOURCE_GLIBC
+#include <gnu/libc-version.h>
+
+int main(void)
+{
+ const char *version = gnu_get_libc_version();
+ return (long)version;
+}
+endef
+
+define SOURCE_ELF_MMAP
+#include <libelf.h>
+int main(void)
+{
+ Elf *elf = elf_begin(0, ELF_C_READ_MMAP, 0);
+ return (long)elf;
+}
+endef
+
+ifndef NO_NEWT
+define SOURCE_NEWT
+#include <newt.h>
+
+int main(void)
+{
+ newtInit();
+ newtCls();
+ return newtFinished();
+}
+endef
+endif
+
+ifndef NO_LIBPERL
+define SOURCE_PERL_EMBED
+#include <EXTERN.h>
+#include <perl.h>
+
+int main(void)
+{
+perl_alloc();
+return 0;
+}
+endef
+endif
+
+ifndef NO_LIBPYTHON
+define SOURCE_PYTHON_VERSION
+#include <Python.h>
+#if PY_VERSION_HEX >= 0x03000000
+ #error
+#endif
+int main(void){}
+endef
+define SOURCE_PYTHON_EMBED
+#include <Python.h>
+int main(void)
+{
+ Py_Initialize();
+ return 0;
+}
+endef
+endif
+
+define SOURCE_BFD
+#include <bfd.h>
+
+int main(void)
+{
+ bfd_demangle(0, 0, 0);
+ return 0;
+}
+endef
+
+define SOURCE_CPLUS_DEMANGLE
+extern char *cplus_demangle(const char *, int);
+
+int main(void)
+{
+ cplus_demangle(0, 0);
+ return 0;
+}
+endef
+
+define SOURCE_STRLCPY
+#include <stdlib.h>
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+int main(void)
+{
+ strlcpy(NULL, NULL, 0);
+ return 0;
+}
+endef
+
+define SOURCE_VNCSERVER
+#include <rfb/rfb.h>
+
+int main(void)
+{
+ rfbIsActive((void *)0);
+ return 0;
+}
+endef
+
+define SOURCE_SDL
+#include <SDL/SDL.h>
+
+int main(void)
+{
+ SDL_Init(SDL_INIT_VIDEO);
+ return 0;
+}
+endef
+
+define SOURCE_ZLIB
+#include <zlib.h>
+
+int main(void)
+{
+ inflateInit2(NULL, 0);
+ return 0;
+}
+endef
+
+define SOURCE_AIO
+#include <libaio.h>
+
+int main(void)
+{
+ io_setup(0, NULL);
+ return 0;
+}
+endef
+
+define SOURCE_STATIC
+#include <stdlib.h>
+
+int main(void)
+{
+ return 0;
+}
+endef
--- /dev/null
+# This allows us to work with the newline character:
+define newline
+
+
+endef
+newline := $(newline)
+
+# nl-escape
+#
+# Usage: escape = $(call nl-escape[,escape])
+#
+# This is used as the common way to specify
+# what should replace a newline when escaping
+# newlines; the default is a bizarre string.
+#
+nl-escape = $(or $(1),m822df3020w6a44id34bt574ctac44eb9f4n)
+
+# escape-nl
+#
+# Usage: escaped-text = $(call escape-nl,text[,escape])
+#
+# GNU make's $(shell ...) function converts to a
+# single space each newline character in the output
+# produced during the expansion; this may not be
+# desirable.
+#
+# The only solution is to change each newline into
+# something that won't be converted, so that the
+# information can be recovered later with
+# $(call unescape-nl...)
+#
+escape-nl = $(subst $(newline),$(call nl-escape,$(2)),$(1))
+
+# unescape-nl
+#
+# Usage: text = $(call unescape-nl,escaped-text[,escape])
+#
+# See escape-nl.
+#
+unescape-nl = $(subst $(call nl-escape,$(2)),$(newline),$(1))
+
+# shell-escape-nl
+#
+# Usage: $(shell some-command | $(call shell-escape-nl[,escape]))
+#
+# Use this to escape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as a string constant
+# in an `awk' program that is delimited by shell
+# single-quotes, so be wary of the characters
+# that are chosen.
+#
+define shell-escape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "$(nl-escape)" $$0} END {printf t}'
+endef
+
+# shell-unescape-nl
+#
+# Usage: $(shell some-command | $(call shell-unescape-nl[,escape]))
+#
+# Use this to unescape newlines from within a shell call;
+# the default escape is a bizarre string.
+#
+# NOTE: The escape is used directly as an extended regular
+# expression constant in an `awk' program that is
+# delimited by shell single-quotes, so be wary
+# of the characters that are chosen.
+#
+# (The bash shell has a bug where `{gsub(...),...}' is
+# misinterpreted as a brace expansion; this can be
+# overcome by putting a space between `{' and `gsub').
+#
+define shell-unescape-nl
+awk 'NR==1 {t=$$0} NR>1 {t=t "\n" $$0} END { gsub(/$(nl-escape)/,"\n",t); printf t }'
+endef
+
+# escape-for-shell-sq
+#
+# Usage: embeddable-text = $(call escape-for-shell-sq,text)
+#
+# This function produces text that is suitable for
+# embedding in a shell string that is delimited by
+# single-quotes.
+#
+escape-for-shell-sq = $(subst ','\'',$(1))
+
+# shell-sq
+#
+# Usage: single-quoted-and-escaped-text = $(call shell-sq,text)
+#
+shell-sq = '$(escape-for-shell-sq)'
+
+# shell-wordify
+#
+# Usage: wordified-text = $(call shell-wordify,text)
+#
+# For instance:
+#
+# |define text
+# |hello
+# |world
+# |endef
+# |
+# |target:
+# | echo $(call shell-wordify,$(text))
+#
+# At least GNU make gets confused by expanding a newline
+# within the context of a command line of a makefile rule
+# (this is in constrast to a `$(shell ...)' function call,
+# which can handle it just fine).
+#
+# This function avoids the problem by producing a string
+# that works as a shell word, regardless of whether or
+# not it contains a newline.
+#
+# If the text to be wordified contains a newline, then
+# an intrictate shell command substitution is constructed
+# to render the text as a single line; when the shell
+# processes the resulting escaped text, it transforms
+# it into the original unescaped text.
+#
+# If the text does not contain a newline, then this function
+# produces the same results as the `$(shell-sq)' function.
+#
+shell-wordify = $(if $(findstring $(newline),$(1)),$(_sw-esc-nl),$(shell-sq))
+define _sw-esc-nl
+"$$(echo $(call escape-nl,$(shell-sq),$(2)) | $(call shell-unescape-nl,$(2)))"
+endef
+
+# is-absolute
+#
+# Usage: bool-value = $(call is-absolute,path)
+#
+is-absolute = $(shell echo $(shell-sq) | grep ^/ -q && echo y)
+
+# lookup
+#
+# Usage: absolute-executable-path-or-empty = $(call lookup,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+# trying too hard and getting things wrong).
+#
+lookup = $(call unescape-nl,$(shell sh -c $(_l-sh)))
+_l-sh = $(call shell-sq,command -v $(shell-sq) | $(call shell-escape-nl,))
+
+# is-executable
+#
+# Usage: bool-value = $(call is-executable,path)
+#
+# (It's necessary to use `sh -c' because GNU make messes up by
+# trying too hard and getting things wrong).
+#
+is-executable = $(call _is-executable-helper,$(shell-sq))
+_is-executable-helper = $(shell sh -c $(_is-executable-sh))
+_is-executable-sh = $(call shell-sq,test -f $(1) -a -x $(1) && echo y)
+
+# get-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable,path)
+#
+# The goal is to get an absolute path for an executable;
+# the `command -v' is defined by POSIX, but it's not
+# necessarily very portable, so it's only used if
+# relative path resolution is requested, as determined
+# by the presence of a leading `/'.
+#
+get-executable = $(if $(1),$(if $(is-absolute),$(_ge-abspath),$(lookup)))
+_ge-abspath = $(if $(is-executable),$(1))
+
+# get-supplied-or-default-executable
+#
+# Usage: absolute-executable-path-or-empty = $(call get-executable-or-default,variable,default)
+#
+define get-executable-or-default
+$(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
+endef
+_ge_attempt = $(or $(get-executable),$(_gea_warn),$(call _gea_err,$(2)))
+_gea_warn = $(warning The path '$(1)' is not executable.)
+_gea_err = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-cc
+# Usage: option = $(call try-cc, source-to-build, cc-options)
+try-cc = $(shell sh -c \
+ 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \
+ echo "$(1)" | \
+ $(CC) -x c - $(2) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+ rm -f "$$TMP"')
+
+# try-build
+# Usage: option = $(call try-build, source-to-build, cc-options, link-options)
+try-build = $(shell sh -c \
+ 'TMP="$(OUTPUT)$(TMPOUT).$$$$"; \
+ echo "$(1)" | \
+ $(CC) -x c - $(2) $(3) -o "$$TMP" > /dev/null 2>&1 && echo y; \
+ rm -f "$$TMP"')
--- /dev/null
+#include "kvm/disk-image.h"
+
+#include <linux/err.h>
+#include <mntent.h>
+
+/*
+ * raw image and blk dev are similar, so reuse raw image ops.
+ */
+static struct disk_image_operations blk_dev_ops = {
+ .read = raw_image__read,
+ .write = raw_image__write,
+};
+
+static bool is_mounted(struct stat *st)
+{
+ struct stat st_buf;
+ struct mntent *mnt;
+ FILE *f;
+
+ f = setmntent("/proc/mounts", "r");
+ if (!f)
+ return false;
+
+ while ((mnt = getmntent(f)) != NULL) {
+ if (stat(mnt->mnt_fsname, &st_buf) == 0 &&
+ S_ISBLK(st_buf.st_mode) && st->st_rdev == st_buf.st_rdev) {
+ fclose(f);
+ return true;
+ }
+ }
+
+ fclose(f);
+ return false;
+}
+
+struct disk_image *blkdev__probe(const char *filename, int flags, struct stat *st)
+{
+ struct disk_image *disk;
+ int fd, r;
+ u64 size;
+
+ if (!S_ISBLK(st->st_mode))
+ return ERR_PTR(-EINVAL);
+
+ if (is_mounted(st)) {
+ pr_err("Block device %s is already mounted! Unmount before use.",
+ filename);
+ return ERR_PTR(-EINVAL);
+ }
+
+ /*
+ * Be careful! We are opening host block device!
+ * Open it readonly since we do not want to break user's data on disk.
+ */
+ fd = open(filename, flags);
+ if (fd < 0)
+ return ERR_PTR(fd);
+
+ if (ioctl(fd, BLKGETSIZE64, &size) < 0) {
+ r = -errno;
+ close(fd);
+ return ERR_PTR(r);
+ }
+
+ /*
+ * FIXME: This will not work on 32-bit host because we can not
+ * mmap large disk. There is not enough virtual address space
+ * in 32-bit host. However, this works on 64-bit host.
+ */
+ disk = disk_image__new(fd, size, &blk_dev_ops, DISK_IMAGE_REGULAR);
+#ifdef CONFIG_HAS_AIO
+ if (!IS_ERR_OR_NULL(disk))
+ disk->async = 1;
+#endif
+ return disk;
+}
--- /dev/null
+#include "kvm/disk-image.h"
+#include "kvm/qcow.h"
+#include "kvm/virtio-blk.h"
+
+#include <linux/err.h>
+#include <sys/eventfd.h>
+#include <sys/poll.h>
+
+#define AIO_MAX 256
+
+int debug_iodelay;
+
+#ifdef CONFIG_HAS_AIO
+static void *disk_image__thread(void *param)
+{
+ struct disk_image *disk = param;
+ struct io_event event[AIO_MAX];
+ struct timespec notime = {0};
+ int nr, i;
+ u64 dummy;
+
+ while (read(disk->evt, &dummy, sizeof(dummy)) > 0) {
+ nr = io_getevents(disk->ctx, 1, ARRAY_SIZE(event), event, ¬ime);
+ for (i = 0; i < nr; i++)
+ disk->disk_req_cb(event[i].data, event[i].res);
+ }
+
+ return NULL;
+}
+#endif
+
+struct disk_image *disk_image__new(int fd, u64 size,
+ struct disk_image_operations *ops,
+ int use_mmap)
+{
+ struct disk_image *disk;
+ int r;
+
+ disk = malloc(sizeof *disk);
+ if (!disk)
+ return ERR_PTR(-ENOMEM);
+
+ *disk = (struct disk_image) {
+ .fd = fd,
+ .size = size,
+ .ops = ops,
+ };
+
+ if (use_mmap == DISK_IMAGE_MMAP) {
+ /*
+ * The write to disk image will be discarded
+ */
+ disk->priv = mmap(NULL, size, PROT_RW, MAP_PRIVATE | MAP_NORESERVE, fd, 0);
+ if (disk->priv == MAP_FAILED) {
+ r = -errno;
+ free(disk);
+ return ERR_PTR(r);
+ }
+ }
+
+#ifdef CONFIG_HAS_AIO
+ if (disk) {
+ pthread_t thread;
+
+ disk->evt = eventfd(0, 0);
+ io_setup(AIO_MAX, &disk->ctx);
+ r = pthread_create(&thread, NULL, disk_image__thread, disk);
+ if (r) {
+ r = -errno;
+ free(disk);
+ return ERR_PTR(r);
+ }
+ }
+#endif
+ return disk;
+}
+
+struct disk_image *disk_image__open(const char *filename, bool readonly, bool direct)
+{
+ struct disk_image *disk;
+ struct stat st;
+ int fd, flags;
+
+ if (readonly)
+ flags = O_RDONLY;
+ else
+ flags = O_RDWR;
+ if (direct)
+ flags |= O_DIRECT;
+
+ if (stat(filename, &st) < 0)
+ return ERR_PTR(-errno);
+
+ /* blk device ?*/
+ disk = blkdev__probe(filename, flags, &st);
+ if (!IS_ERR_OR_NULL(disk))
+ return disk;
+
+ fd = open(filename, flags);
+ if (fd < 0)
+ return ERR_PTR(fd);
+
+ /* qcow image ?*/
+ disk = qcow_probe(fd, true);
+ if (!IS_ERR_OR_NULL(disk)) {
+ pr_warning("Forcing read-only support for QCOW");
+ return disk;
+ }
+
+ /* raw image ?*/
+ disk = raw_image__probe(fd, &st, readonly);
+ if (!IS_ERR_OR_NULL(disk))
+ return disk;
+
+ if (close(fd) < 0)
+ pr_warning("close() failed");
+
+ return ERR_PTR(-ENOSYS);
+}
+
+struct disk_image **disk_image__open_all(struct disk_image_params *params, int count)
+{
+ struct disk_image **disks;
+ const char *filename;
+ const char *wwpn;
+ const char *tpgt;
+ bool readonly;
+ bool direct;
+ void *err;
+ int i;
+
+ if (!count)
+ return ERR_PTR(-EINVAL);
+ if (count > MAX_DISK_IMAGES)
+ return ERR_PTR(-ENOSPC);
+
+ disks = calloc(count, sizeof(*disks));
+ if (!disks)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < count; i++) {
+ filename = params[i].filename;
+ readonly = params[i].readonly;
+ direct = params[i].direct;
+ wwpn = params[i].wwpn;
+ tpgt = params[i].tpgt;
+
+ if (wwpn) {
+ disks[i] = malloc(sizeof(struct disk_image));
+ if (!disks[i])
+ return ERR_PTR(-ENOMEM);
+ disks[i]->wwpn = wwpn;
+ disks[i]->tpgt = tpgt;
+ continue;
+ }
+
+ if (!filename)
+ continue;
+
+ disks[i] = disk_image__open(filename, readonly, direct);
+ if (IS_ERR_OR_NULL(disks[i])) {
+ pr_err("Loading disk image '%s' failed", filename);
+ err = disks[i];
+ goto error;
+ }
+ }
+
+ return disks;
+error:
+ for (i = 0; i < count; i++)
+ if (!IS_ERR_OR_NULL(disks[i]))
+ disk_image__close(disks[i]);
+
+ free(disks);
+ return err;
+}
+
+int disk_image__flush(struct disk_image *disk)
+{
+ if (disk->ops->flush)
+ return disk->ops->flush(disk);
+
+ return fsync(disk->fd);
+}
+
+int disk_image__close(struct disk_image *disk)
+{
+ /* If there was no disk image then there's nothing to do: */
+ if (!disk)
+ return 0;
+
+ if (disk->ops->close)
+ return disk->ops->close(disk);
+
+ if (close(disk->fd) < 0)
+ pr_warning("close() failed");
+
+ free(disk);
+
+ return 0;
+}
+
+int disk_image__close_all(struct disk_image **disks, int count)
+{
+ while (count)
+ disk_image__close(disks[--count]);
+
+ free(disks);
+
+ return 0;
+}
+
+/*
+ * Fill iov with disk data, starting from sector 'sector'.
+ * Return amount of bytes read.
+ */
+ssize_t disk_image__read(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t total = 0;
+
+ if (debug_iodelay)
+ msleep(debug_iodelay);
+
+ if (disk->ops->read) {
+ total = disk->ops->read(disk, sector, iov, iovcount, param);
+ if (total < 0) {
+ pr_info("disk_image__read error: total=%ld\n", (long)total);
+ return total;
+ }
+ }
+
+ if (!disk->async && disk->disk_req_cb)
+ disk->disk_req_cb(param, total);
+
+ return total;
+}
+
+/*
+ * Write iov to disk, starting from sector 'sector'.
+ * Return amount of bytes written.
+ */
+ssize_t disk_image__write(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t total = 0;
+
+ if (debug_iodelay)
+ msleep(debug_iodelay);
+
+ if (disk->ops->write) {
+ /*
+ * Try writev based operation first
+ */
+
+ total = disk->ops->write(disk, sector, iov, iovcount, param);
+ if (total < 0) {
+ pr_info("disk_image__write error: total=%ld\n", (long)total);
+ return total;
+ }
+ } else {
+ /* Do nothing */
+ }
+
+ if (!disk->async && disk->disk_req_cb)
+ disk->disk_req_cb(param, total);
+
+ return total;
+}
+
+ssize_t disk_image__get_serial(struct disk_image *disk, void *buffer, ssize_t *len)
+{
+ struct stat st;
+ int r;
+
+ r = fstat(disk->fd, &st);
+ if (r)
+ return r;
+
+ *len = snprintf(buffer, *len, "%llu%llu%llu",
+ (u64)st.st_dev, (u64)st.st_rdev, (u64)st.st_ino);
+ return *len;
+}
+
+void disk_image__set_callback(struct disk_image *disk,
+ void (*disk_req_cb)(void *param, long len))
+{
+ disk->disk_req_cb = disk_req_cb;
+}
--- /dev/null
+#include "kvm/qcow.h"
+
+#include "kvm/disk-image.h"
+#include "kvm/read-write.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <errno.h>
+#ifdef CONFIG_HAS_ZLIB
+#include <zlib.h>
+#endif
+
+#include <linux/err.h>
+#include <linux/byteorder.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+static int update_cluster_refcount(struct qcow *q, u64 clust_idx, u16 append);
+static int qcow_write_refcount_table(struct qcow *q);
+static u64 qcow_alloc_clusters(struct qcow *q, u64 size, int update_ref);
+static void qcow_free_clusters(struct qcow *q, u64 clust_start, u64 size);
+
+static inline int qcow_pwrite_sync(int fd,
+ void *buf, size_t count, off_t offset)
+{
+ if (pwrite_in_full(fd, buf, count, offset) < 0)
+ return -1;
+
+ return fdatasync(fd);
+}
+
+static int l2_table_insert(struct rb_root *root, struct qcow_l2_table *new)
+{
+ struct rb_node **link = &(root->rb_node), *parent = NULL;
+ u64 offset = new->offset;
+
+ /* search the tree */
+ while (*link) {
+ struct qcow_l2_table *t;
+
+ t = rb_entry(*link, struct qcow_l2_table, node);
+ if (!t)
+ goto error;
+
+ parent = *link;
+
+ if (t->offset > offset)
+ link = &(*link)->rb_left;
+ else if (t->offset < offset)
+ link = &(*link)->rb_right;
+ else
+ goto out;
+ }
+
+ /* add new node */
+ rb_link_node(&new->node, parent, link);
+ rb_insert_color(&new->node, root);
+out:
+ return 0;
+error:
+ return -1;
+}
+
+static struct qcow_l2_table *l2_table_lookup(struct rb_root *root, u64 offset)
+{
+ struct rb_node *link = root->rb_node;
+
+ while (link) {
+ struct qcow_l2_table *t;
+
+ t = rb_entry(link, struct qcow_l2_table, node);
+ if (!t)
+ goto out;
+
+ if (t->offset > offset)
+ link = link->rb_left;
+ else if (t->offset < offset)
+ link = link->rb_right;
+ else
+ return t;
+ }
+out:
+ return NULL;
+}
+
+static void l1_table_free_cache(struct qcow_l1_table *l1t)
+{
+ struct rb_root *r = &l1t->root;
+ struct list_head *pos, *n;
+ struct qcow_l2_table *t;
+
+ list_for_each_safe(pos, n, &l1t->lru_list) {
+ /* Remove cache table from the list and RB tree */
+ list_del(pos);
+ t = list_entry(pos, struct qcow_l2_table, list);
+ rb_erase(&t->node, r);
+
+ /* Free the cached node */
+ free(t);
+ }
+}
+
+static int qcow_l2_cache_write(struct qcow *q, struct qcow_l2_table *c)
+{
+ struct qcow_header *header = q->header;
+ u64 size;
+
+ if (!c->dirty)
+ return 0;
+
+ size = 1 << header->l2_bits;
+
+ if (qcow_pwrite_sync(q->fd, c->table,
+ size * sizeof(u64), c->offset) < 0)
+ return -1;
+
+ c->dirty = 0;
+
+ return 0;
+}
+
+static int cache_table(struct qcow *q, struct qcow_l2_table *c)
+{
+ struct qcow_l1_table *l1t = &q->table;
+ struct rb_root *r = &l1t->root;
+ struct qcow_l2_table *lru;
+
+ if (l1t->nr_cached == MAX_CACHE_NODES) {
+ /*
+ * The node at the head of the list is least recently used
+ * node. Remove it from the list and replaced with a new node.
+ */
+ lru = list_first_entry(&l1t->lru_list, struct qcow_l2_table, list);
+
+ /* Remove the node from the cache */
+ rb_erase(&lru->node, r);
+ list_del_init(&lru->list);
+ l1t->nr_cached--;
+
+ /* Free the LRUed node */
+ free(lru);
+ }
+
+ /* Add new node in RB Tree: Helps in searching faster */
+ if (l2_table_insert(r, c) < 0)
+ goto error;
+
+ /* Add in LRU replacement list */
+ list_add_tail(&c->list, &l1t->lru_list);
+ l1t->nr_cached++;
+
+ return 0;
+error:
+ return -1;
+}
+
+static struct qcow_l2_table *l2_table_search(struct qcow *q, u64 offset)
+{
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+
+ l2t = l2_table_lookup(&l1t->root, offset);
+ if (!l2t)
+ return NULL;
+
+ /* Update the LRU state, by moving the searched node to list tail */
+ list_move_tail(&l2t->list, &l1t->lru_list);
+
+ return l2t;
+}
+
+/* Allocates a new node for caching L2 table */
+static struct qcow_l2_table *new_cache_table(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l2_table *c;
+ u64 l2t_sz;
+ u64 size;
+
+ l2t_sz = 1 << header->l2_bits;
+ size = sizeof(*c) + l2t_sz * sizeof(u64);
+ c = calloc(1, size);
+ if (!c)
+ goto out;
+
+ c->offset = offset;
+ RB_CLEAR_NODE(&c->node);
+ INIT_LIST_HEAD(&c->list);
+out:
+ return c;
+}
+
+static inline u64 get_l1_index(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+
+ return offset >> (header->l2_bits + header->cluster_bits);
+}
+
+static inline u64 get_l2_index(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+
+ return (offset >> (header->cluster_bits)) & ((1 << header->l2_bits)-1);
+}
+
+static inline u64 get_cluster_offset(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+
+ return offset & ((1 << header->cluster_bits)-1);
+}
+
+static struct qcow_l2_table *qcow_read_l2_table(struct qcow *q, u64 offset)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l2_table *l2t;
+ u64 size;
+
+ size = 1 << header->l2_bits;
+
+ /* search an entry for offset in cache */
+ l2t = l2_table_search(q, offset);
+ if (l2t)
+ return l2t;
+
+ /* allocate new node for caching l2 table */
+ l2t = new_cache_table(q, offset);
+ if (!l2t)
+ goto error;
+
+ /* table not cached: read from the disk */
+ if (pread_in_full(q->fd, l2t->table, size * sizeof(u64), offset) < 0)
+ goto error;
+
+ /* cache the table */
+ if (cache_table(q, l2t) < 0)
+ goto error;
+
+ return l2t;
+error:
+ free(l2t);
+ return NULL;
+}
+
+static int qcow_decompress_buffer(u8 *out_buf, int out_buf_size,
+ const u8 *buf, int buf_size)
+{
+#ifdef CONFIG_HAS_ZLIB
+ z_stream strm1, *strm = &strm1;
+ int ret, out_len;
+
+ memset(strm, 0, sizeof(*strm));
+
+ strm->next_in = (u8 *)buf;
+ strm->avail_in = buf_size;
+ strm->next_out = out_buf;
+ strm->avail_out = out_buf_size;
+
+ ret = inflateInit2(strm, -12);
+ if (ret != Z_OK)
+ return -1;
+
+ ret = inflate(strm, Z_FINISH);
+ out_len = strm->next_out - out_buf;
+ if ((ret != Z_STREAM_END && ret != Z_BUF_ERROR) ||
+ out_len != out_buf_size) {
+ inflateEnd(strm);
+ return -1;
+ }
+
+ inflateEnd(strm);
+ return 0;
+#else
+ return -1;
+#endif
+}
+
+static ssize_t qcow1_read_cluster(struct qcow *q, u64 offset,
+ void *dst, u32 dst_len)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+ u64 clust_offset;
+ u64 clust_start;
+ u64 l2t_offset;
+ size_t length;
+ u64 l2t_size;
+ u64 l1_idx;
+ u64 l2_idx;
+ int coffset;
+ int csize;
+
+ l1_idx = get_l1_index(q, offset);
+ if (l1_idx >= l1t->table_size)
+ return -1;
+
+ clust_offset = get_cluster_offset(q, offset);
+ if (clust_offset >= q->cluster_size)
+ return -1;
+
+ length = q->cluster_size - clust_offset;
+ if (length > dst_len)
+ length = dst_len;
+
+ mutex_lock(&q->mutex);
+
+ l2t_offset = be64_to_cpu(l1t->l1_table[l1_idx]);
+ if (!l2t_offset)
+ goto zero_cluster;
+
+ l2t_size = 1 << header->l2_bits;
+
+ /* read and cache level 2 table */
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto out_error;
+
+ l2_idx = get_l2_index(q, offset);
+ if (l2_idx >= l2t_size)
+ goto out_error;
+
+ clust_start = be64_to_cpu(l2t->table[l2_idx]);
+ if (clust_start & QCOW1_OFLAG_COMPRESSED) {
+ coffset = clust_start & q->cluster_offset_mask;
+ csize = clust_start >> (63 - q->header->cluster_bits);
+ csize &= (q->cluster_size - 1);
+
+ if (pread_in_full(q->fd, q->cluster_data, csize,
+ coffset) < 0)
+ goto out_error;
+
+ if (qcow_decompress_buffer(q->cluster_cache, q->cluster_size,
+ q->cluster_data, csize) < 0)
+ goto out_error;
+
+ memcpy(dst, q->cluster_cache + clust_offset, length);
+ mutex_unlock(&q->mutex);
+ } else {
+ if (!clust_start)
+ goto zero_cluster;
+
+ mutex_unlock(&q->mutex);
+
+ if (pread_in_full(q->fd, dst, length,
+ clust_start + clust_offset) < 0)
+ return -1;
+ }
+
+ return length;
+
+zero_cluster:
+ mutex_unlock(&q->mutex);
+ memset(dst, 0, length);
+ return length;
+
+out_error:
+ mutex_unlock(&q->mutex);
+ length = -1;
+ return -1;
+}
+
+static ssize_t qcow2_read_cluster(struct qcow *q, u64 offset,
+ void *dst, u32 dst_len)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+ u64 clust_offset;
+ u64 clust_start;
+ u64 l2t_offset;
+ size_t length;
+ u64 l2t_size;
+ u64 l1_idx;
+ u64 l2_idx;
+ int coffset;
+ int sector_offset;
+ int nb_csectors;
+ int csize;
+
+ l1_idx = get_l1_index(q, offset);
+ if (l1_idx >= l1t->table_size)
+ return -1;
+
+ clust_offset = get_cluster_offset(q, offset);
+ if (clust_offset >= q->cluster_size)
+ return -1;
+
+ length = q->cluster_size - clust_offset;
+ if (length > dst_len)
+ length = dst_len;
+
+ mutex_lock(&q->mutex);
+
+ l2t_offset = be64_to_cpu(l1t->l1_table[l1_idx]);
+
+ l2t_offset &= ~QCOW2_OFLAG_COPIED;
+ if (!l2t_offset)
+ goto zero_cluster;
+
+ l2t_size = 1 << header->l2_bits;
+
+ /* read and cache level 2 table */
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto out_error;
+
+ l2_idx = get_l2_index(q, offset);
+ if (l2_idx >= l2t_size)
+ goto out_error;
+
+ clust_start = be64_to_cpu(l2t->table[l2_idx]);
+ if (clust_start & QCOW2_OFLAG_COMPRESSED) {
+ coffset = clust_start & q->cluster_offset_mask;
+ nb_csectors = ((clust_start >> q->csize_shift)
+ & q->csize_mask) + 1;
+ sector_offset = coffset & (SECTOR_SIZE - 1);
+ csize = nb_csectors * SECTOR_SIZE - sector_offset;
+
+ if (pread_in_full(q->fd, q->cluster_data,
+ nb_csectors * SECTOR_SIZE,
+ coffset & ~(SECTOR_SIZE - 1)) < 0) {
+ goto out_error;
+ }
+
+ if (qcow_decompress_buffer(q->cluster_cache, q->cluster_size,
+ q->cluster_data + sector_offset,
+ csize) < 0) {
+ goto out_error;
+ }
+
+ memcpy(dst, q->cluster_cache + clust_offset, length);
+ mutex_unlock(&q->mutex);
+ } else {
+ clust_start &= QCOW2_OFFSET_MASK;
+ if (!clust_start)
+ goto zero_cluster;
+
+ mutex_unlock(&q->mutex);
+
+ if (pread_in_full(q->fd, dst, length,
+ clust_start + clust_offset) < 0)
+ return -1;
+ }
+
+ return length;
+
+zero_cluster:
+ mutex_unlock(&q->mutex);
+ memset(dst, 0, length);
+ return length;
+
+out_error:
+ mutex_unlock(&q->mutex);
+ length = -1;
+ return -1;
+}
+
+static ssize_t qcow_read_sector_single(struct disk_image *disk, u64 sector,
+ void *dst, u32 dst_len)
+{
+ struct qcow *q = disk->priv;
+ struct qcow_header *header = q->header;
+ u32 nr_read;
+ u64 offset;
+ char *buf;
+ u32 nr;
+
+ buf = dst;
+ nr_read = 0;
+
+ while (nr_read < dst_len) {
+ offset = sector << SECTOR_SHIFT;
+ if (offset >= header->size)
+ return -1;
+
+ if (q->version == QCOW1_VERSION)
+ nr = qcow1_read_cluster(q, offset, buf,
+ dst_len - nr_read);
+ else
+ nr = qcow2_read_cluster(q, offset, buf,
+ dst_len - nr_read);
+
+ if (nr <= 0)
+ return -1;
+
+ nr_read += nr;
+ buf += nr;
+ sector += (nr >> SECTOR_SHIFT);
+ }
+
+ return dst_len;
+}
+
+static ssize_t qcow_read_sector(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t nr, total = 0;
+
+ while (iovcount--) {
+ nr = qcow_read_sector_single(disk, sector, iov->iov_base, iov->iov_len);
+ if (nr != (ssize_t)iov->iov_len) {
+ pr_info("qcow_read_sector error: nr=%ld iov_len=%ld\n", (long)nr, (long)iov->iov_len);
+ return -1;
+ }
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ total += nr;
+ iov++;
+ }
+
+ return total;
+}
+
+static void refcount_table_free_cache(struct qcow_refcount_table *rft)
+{
+ struct rb_root *r = &rft->root;
+ struct list_head *pos, *n;
+ struct qcow_refcount_block *t;
+
+ list_for_each_safe(pos, n, &rft->lru_list) {
+ list_del(pos);
+ t = list_entry(pos, struct qcow_refcount_block, list);
+ rb_erase(&t->node, r);
+
+ free(t);
+ }
+}
+
+static int refcount_block_insert(struct rb_root *root, struct qcow_refcount_block *new)
+{
+ struct rb_node **link = &(root->rb_node), *parent = NULL;
+ u64 offset = new->offset;
+
+ /* search the tree */
+ while (*link) {
+ struct qcow_refcount_block *t;
+
+ t = rb_entry(*link, struct qcow_refcount_block, node);
+ if (!t)
+ goto error;
+
+ parent = *link;
+
+ if (t->offset > offset)
+ link = &(*link)->rb_left;
+ else if (t->offset < offset)
+ link = &(*link)->rb_right;
+ else
+ goto out;
+ }
+
+ /* add new node */
+ rb_link_node(&new->node, parent, link);
+ rb_insert_color(&new->node, root);
+out:
+ return 0;
+error:
+ return -1;
+}
+
+static int write_refcount_block(struct qcow *q, struct qcow_refcount_block *rfb)
+{
+ if (!rfb->dirty)
+ return 0;
+
+ if (qcow_pwrite_sync(q->fd, rfb->entries,
+ rfb->size * sizeof(u16), rfb->offset) < 0)
+ return -1;
+
+ rfb->dirty = 0;
+
+ return 0;
+}
+
+static int cache_refcount_block(struct qcow *q, struct qcow_refcount_block *c)
+{
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct rb_root *r = &rft->root;
+ struct qcow_refcount_block *lru;
+
+ if (rft->nr_cached == MAX_CACHE_NODES) {
+ lru = list_first_entry(&rft->lru_list, struct qcow_refcount_block, list);
+
+ rb_erase(&lru->node, r);
+ list_del_init(&lru->list);
+ rft->nr_cached--;
+
+ free(lru);
+ }
+
+ if (refcount_block_insert(r, c) < 0)
+ goto error;
+
+ list_add_tail(&c->list, &rft->lru_list);
+ rft->nr_cached++;
+
+ return 0;
+error:
+ return -1;
+}
+
+static struct qcow_refcount_block *new_refcount_block(struct qcow *q, u64 rfb_offset)
+{
+ struct qcow_refcount_block *rfb;
+
+ rfb = malloc(sizeof *rfb + q->cluster_size);
+ if (!rfb)
+ return NULL;
+
+ rfb->offset = rfb_offset;
+ rfb->size = q->cluster_size / sizeof(u16);
+ RB_CLEAR_NODE(&rfb->node);
+ INIT_LIST_HEAD(&rfb->list);
+
+ return rfb;
+}
+
+static struct qcow_refcount_block *refcount_block_lookup(struct rb_root *root, u64 offset)
+{
+ struct rb_node *link = root->rb_node;
+
+ while (link) {
+ struct qcow_refcount_block *t;
+
+ t = rb_entry(link, struct qcow_refcount_block, node);
+ if (!t)
+ goto out;
+
+ if (t->offset > offset)
+ link = link->rb_left;
+ else if (t->offset < offset)
+ link = link->rb_right;
+ else
+ return t;
+ }
+out:
+ return NULL;
+}
+
+static struct qcow_refcount_block *refcount_block_search(struct qcow *q, u64 offset)
+{
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct qcow_refcount_block *rfb;
+
+ rfb = refcount_block_lookup(&rft->root, offset);
+ if (!rfb)
+ return NULL;
+
+ /* Update the LRU state, by moving the searched node to list tail */
+ list_move_tail(&rfb->list, &rft->lru_list);
+
+ return rfb;
+}
+
+static struct qcow_refcount_block *qcow_grow_refcount_block(struct qcow *q,
+ u64 clust_idx)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct qcow_refcount_block *rfb;
+ u64 new_block_offset;
+ u64 rft_idx;
+
+ rft_idx = clust_idx >> (header->cluster_bits -
+ QCOW_REFCOUNT_BLOCK_SHIFT);
+
+ if (rft_idx >= rft->rf_size) {
+ pr_warning("Don't support grow refcount block table");
+ return NULL;
+ }
+
+ new_block_offset = qcow_alloc_clusters(q, q->cluster_size, 0);
+ if (new_block_offset < 0)
+ return NULL;
+
+ rfb = new_refcount_block(q, new_block_offset);
+ if (!rfb)
+ return NULL;
+
+ memset(rfb->entries, 0x00, q->cluster_size);
+ rfb->dirty = 1;
+
+ /* write refcount block */
+ if (write_refcount_block(q, rfb) < 0)
+ goto free_rfb;
+
+ if (cache_refcount_block(q, rfb) < 0)
+ goto free_rfb;
+
+ rft->rf_table[rft_idx] = cpu_to_be64(new_block_offset);
+ if (update_cluster_refcount(q, new_block_offset >>
+ header->cluster_bits, 1) < 0)
+ goto recover_rft;
+
+ if (qcow_write_refcount_table(q) < 0)
+ goto recover_rft;
+
+ return rfb;
+
+recover_rft:
+ rft->rf_table[rft_idx] = 0;
+free_rfb:
+ free(rfb);
+ return NULL;
+}
+
+static struct qcow_refcount_block *qcow_read_refcount_block(struct qcow *q, u64 clust_idx)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+ struct qcow_refcount_block *rfb;
+ u64 rfb_offset;
+ u64 rft_idx;
+
+ rft_idx = clust_idx >> (header->cluster_bits - QCOW_REFCOUNT_BLOCK_SHIFT);
+ if (rft_idx >= rft->rf_size)
+ return ERR_PTR(-ENOSPC);
+
+ rfb_offset = be64_to_cpu(rft->rf_table[rft_idx]);
+ if (!rfb_offset)
+ return ERR_PTR(-ENOSPC);
+
+ rfb = refcount_block_search(q, rfb_offset);
+ if (rfb)
+ return rfb;
+
+ rfb = new_refcount_block(q, rfb_offset);
+ if (!rfb)
+ return NULL;
+
+ if (pread_in_full(q->fd, rfb->entries, rfb->size * sizeof(u16), rfb_offset) < 0)
+ goto error_free_rfb;
+
+ if (cache_refcount_block(q, rfb) < 0)
+ goto error_free_rfb;
+
+ return rfb;
+
+error_free_rfb:
+ free(rfb);
+
+ return NULL;
+}
+
+static u16 qcow_get_refcount(struct qcow *q, u64 clust_idx)
+{
+ struct qcow_refcount_block *rfb = NULL;
+ struct qcow_header *header = q->header;
+ u64 rfb_idx;
+
+ rfb = qcow_read_refcount_block(q, clust_idx);
+ if (PTR_ERR(rfb) == -ENOSPC)
+ return 0;
+ else if (IS_ERR_OR_NULL(rfb)) {
+ pr_warning("Error while reading refcount table");
+ return -1;
+ }
+
+ rfb_idx = clust_idx & (((1ULL <<
+ (header->cluster_bits - QCOW_REFCOUNT_BLOCK_SHIFT)) - 1));
+
+ if (rfb_idx >= rfb->size) {
+ pr_warning("L1: refcount block index out of bounds");
+ return -1;
+ }
+
+ return be16_to_cpu(rfb->entries[rfb_idx]);
+}
+
+static int update_cluster_refcount(struct qcow *q, u64 clust_idx, u16 append)
+{
+ struct qcow_refcount_block *rfb = NULL;
+ struct qcow_header *header = q->header;
+ u16 refcount;
+ u64 rfb_idx;
+
+ rfb = qcow_read_refcount_block(q, clust_idx);
+ if (PTR_ERR(rfb) == -ENOSPC) {
+ rfb = qcow_grow_refcount_block(q, clust_idx);
+ if (!rfb) {
+ pr_warning("error while growing refcount table");
+ return -1;
+ }
+ } else if (IS_ERR_OR_NULL(rfb)) {
+ pr_warning("error while reading refcount table");
+ return -1;
+ }
+
+ rfb_idx = clust_idx & (((1ULL <<
+ (header->cluster_bits - QCOW_REFCOUNT_BLOCK_SHIFT)) - 1));
+ if (rfb_idx >= rfb->size) {
+ pr_warning("refcount block index out of bounds");
+ return -1;
+ }
+
+ refcount = be16_to_cpu(rfb->entries[rfb_idx]) + append;
+ rfb->entries[rfb_idx] = cpu_to_be16(refcount);
+ rfb->dirty = 1;
+
+ /* write refcount block */
+ if (write_refcount_block(q, rfb) < 0) {
+ pr_warning("refcount block index out of bounds");
+ return -1;
+ }
+
+ /* update free_clust_idx since refcount becomes zero */
+ if (!refcount && clust_idx < q->free_clust_idx)
+ q->free_clust_idx = clust_idx;
+
+ return 0;
+}
+
+static void qcow_free_clusters(struct qcow *q, u64 clust_start, u64 size)
+{
+ struct qcow_header *header = q->header;
+ u64 start, end, offset;
+
+ start = clust_start & ~(q->cluster_size - 1);
+ end = (clust_start + size - 1) & ~(q->cluster_size - 1);
+ for (offset = start; offset <= end; offset += q->cluster_size)
+ update_cluster_refcount(q, offset >> header->cluster_bits, -1);
+}
+
+/*
+ * Allocate clusters according to the size. Find a postion that
+ * can satisfy the size. free_clust_idx is initialized to zero and
+ * Record last position.
+ */
+static u64 qcow_alloc_clusters(struct qcow *q, u64 size, int update_ref)
+{
+ struct qcow_header *header = q->header;
+ u16 clust_refcount;
+ u32 clust_idx = 0, i;
+ u64 clust_num;
+
+ clust_num = (size + (q->cluster_size - 1)) >> header->cluster_bits;
+
+again:
+ for (i = 0; i < clust_num; i++) {
+ clust_idx = q->free_clust_idx++;
+ clust_refcount = qcow_get_refcount(q, clust_idx);
+ if (clust_refcount < 0)
+ return -1;
+ else if (clust_refcount > 0)
+ goto again;
+ }
+
+ clust_idx++;
+
+ if (update_ref)
+ for (i = 0; i < clust_num; i++)
+ if (update_cluster_refcount(q,
+ clust_idx - clust_num + i, 1))
+ return -1;
+
+ return (clust_idx - clust_num) << header->cluster_bits;
+}
+
+static int qcow_write_l1_table(struct qcow *q)
+{
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_header *header = q->header;
+
+ if (qcow_pwrite_sync(q->fd, l1t->l1_table,
+ l1t->table_size * sizeof(u64),
+ header->l1_table_offset) < 0)
+ return -1;
+
+ return 0;
+}
+
+/*
+ * Get l2 table. If the table has been copied, read table directly.
+ * If the table exists, allocate a new cluster and copy the table
+ * to the new cluster.
+ */
+static int get_cluster_table(struct qcow *q, u64 offset,
+ struct qcow_l2_table **result_l2t, u64 *result_l2_index)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *l1t = &q->table;
+ struct qcow_l2_table *l2t;
+ u64 l1t_idx;
+ u64 l2t_offset;
+ u64 l2t_idx;
+ u64 l2t_size;
+ u64 l2t_new_offset;
+
+ l2t_size = 1 << header->l2_bits;
+
+ l1t_idx = get_l1_index(q, offset);
+ if (l1t_idx >= l1t->table_size)
+ return -1;
+
+ l2t_idx = get_l2_index(q, offset);
+ if (l2t_idx >= l2t_size)
+ return -1;
+
+ l2t_offset = be64_to_cpu(l1t->l1_table[l1t_idx]);
+ if (l2t_offset & QCOW2_OFLAG_COPIED) {
+ l2t_offset &= ~QCOW2_OFLAG_COPIED;
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto error;
+ } else {
+ l2t_new_offset = qcow_alloc_clusters(q,
+ l2t_size*sizeof(u64), 1);
+
+ if (l2t_new_offset < 0)
+ goto error;
+
+ l2t = new_cache_table(q, l2t_new_offset);
+ if (!l2t)
+ goto free_cluster;
+
+ if (l2t_offset) {
+ l2t = qcow_read_l2_table(q, l2t_offset);
+ if (!l2t)
+ goto free_cache;
+ } else
+ memset(l2t->table, 0x00, l2t_size * sizeof(u64));
+
+ /* write l2 table */
+ l2t->dirty = 1;
+ if (qcow_l2_cache_write(q, l2t) < 0)
+ goto free_cache;
+
+ /* cache l2 table */
+ if (cache_table(q, l2t))
+ goto free_cache;
+
+ /* update the l1 talble */
+ l1t->l1_table[l1t_idx] = cpu_to_be64(l2t_new_offset
+ | QCOW2_OFLAG_COPIED);
+ if (qcow_write_l1_table(q)) {
+ pr_warning("Update l1 table error");
+ goto free_cache;
+ }
+
+ /* free old cluster */
+ qcow_free_clusters(q, l2t_offset, q->cluster_size);
+ }
+
+ *result_l2t = l2t;
+ *result_l2_index = l2t_idx;
+
+ return 0;
+
+free_cache:
+ free(l2t);
+
+free_cluster:
+ qcow_free_clusters(q, l2t_new_offset, q->cluster_size);
+
+error:
+ return -1;
+}
+
+/*
+ * If the cluster has been copied, write data directly. If not,
+ * read the original data and write it to the new cluster with
+ * modification.
+ */
+static ssize_t qcow_write_cluster(struct qcow *q, u64 offset,
+ void *buf, u32 src_len)
+{
+ struct qcow_l2_table *l2t;
+ u64 clust_new_start;
+ u64 clust_start;
+ u64 clust_flags;
+ u64 clust_off;
+ u64 l2t_idx;
+ u64 len;
+
+ l2t = NULL;
+
+ clust_off = get_cluster_offset(q, offset);
+ if (clust_off >= q->cluster_size)
+ return -1;
+
+ len = q->cluster_size - clust_off;
+ if (len > src_len)
+ len = src_len;
+
+ mutex_lock(&q->mutex);
+
+ if (get_cluster_table(q, offset, &l2t, &l2t_idx)) {
+ pr_warning("Get l2 table error");
+ goto error;
+ }
+
+ clust_start = be64_to_cpu(l2t->table[l2t_idx]);
+ clust_flags = clust_start & QCOW2_OFLAGS_MASK;
+
+ clust_start &= QCOW2_OFFSET_MASK;
+ if (!(clust_flags & QCOW2_OFLAG_COPIED)) {
+ clust_new_start = qcow_alloc_clusters(q, q->cluster_size, 1);
+ if (clust_new_start < 0) {
+ pr_warning("Cluster alloc error");
+ goto error;
+ }
+
+ offset &= ~(q->cluster_size - 1);
+
+ /* if clust_start is not zero, read the original data*/
+ if (clust_start) {
+ mutex_unlock(&q->mutex);
+ if (qcow2_read_cluster(q, offset, q->copy_buff,
+ q->cluster_size) < 0) {
+ pr_warning("Read copy cluster error");
+ qcow_free_clusters(q, clust_new_start,
+ q->cluster_size);
+ return -1;
+ }
+ mutex_lock(&q->mutex);
+ } else
+ memset(q->copy_buff, 0x00, q->cluster_size);
+
+ memcpy(q->copy_buff + clust_off, buf, len);
+
+ /* Write actual data */
+ if (pwrite_in_full(q->fd, q->copy_buff, q->cluster_size,
+ clust_new_start) < 0)
+ goto free_cluster;
+
+ /* update l2 table*/
+ l2t->table[l2t_idx] = cpu_to_be64(clust_new_start
+ | QCOW2_OFLAG_COPIED);
+ l2t->dirty = 1;
+
+ if (qcow_l2_cache_write(q, l2t))
+ goto free_cluster;
+
+ /* free old cluster*/
+ if (clust_flags & QCOW2_OFLAG_COMPRESSED) {
+ int size;
+ size = ((clust_start >> q->csize_shift) &
+ q->csize_mask) + 1;
+ size *= 512;
+ clust_start &= q->cluster_offset_mask;
+ clust_start &= ~511;
+
+ qcow_free_clusters(q, clust_start, size);
+ } else if (clust_start)
+ qcow_free_clusters(q, clust_start, q->cluster_size);
+
+ } else {
+ /* Write actual data */
+ if (pwrite_in_full(q->fd, buf, len,
+ clust_start + clust_off) < 0)
+ goto error;
+ }
+ mutex_unlock(&q->mutex);
+ return len;
+
+free_cluster:
+ qcow_free_clusters(q, clust_new_start, q->cluster_size);
+
+error:
+ mutex_unlock(&q->mutex);
+ return -1;
+}
+
+static ssize_t qcow_write_sector_single(struct disk_image *disk, u64 sector, void *src, u32 src_len)
+{
+ struct qcow *q = disk->priv;
+ struct qcow_header *header = q->header;
+ u32 nr_written;
+ char *buf;
+ u64 offset;
+ ssize_t nr;
+
+ buf = src;
+ nr_written = 0;
+ offset = sector << SECTOR_SHIFT;
+
+ while (nr_written < src_len) {
+ if (offset >= header->size)
+ return -1;
+
+ nr = qcow_write_cluster(q, offset, buf, src_len - nr_written);
+ if (nr < 0)
+ return -1;
+
+ nr_written += nr;
+ buf += nr;
+ offset += nr;
+ }
+
+ return nr_written;
+}
+
+static ssize_t qcow_write_sector(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param)
+{
+ ssize_t nr, total = 0;
+
+ while (iovcount--) {
+ nr = qcow_write_sector_single(disk, sector, iov->iov_base, iov->iov_len);
+ if (nr != (ssize_t)iov->iov_len) {
+ pr_info("qcow_write_sector error: nr=%ld iov_len=%ld\n", (long)nr, (long)iov->iov_len);
+ return -1;
+ }
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ iov++;
+ total += nr;
+ }
+
+ return total;
+}
+
+static int qcow_disk_flush(struct disk_image *disk)
+{
+ struct qcow *q = disk->priv;
+ struct qcow_refcount_table *rft;
+ struct list_head *pos, *n;
+ struct qcow_l1_table *l1t;
+
+ l1t = &q->table;
+ rft = &q->refcount_table;
+
+ mutex_lock(&q->mutex);
+
+ list_for_each_safe(pos, n, &rft->lru_list) {
+ struct qcow_refcount_block *c = list_entry(pos, struct qcow_refcount_block, list);
+
+ if (write_refcount_block(q, c) < 0)
+ goto error_unlock;
+ }
+
+ list_for_each_safe(pos, n, &l1t->lru_list) {
+ struct qcow_l2_table *c = list_entry(pos, struct qcow_l2_table, list);
+
+ if (qcow_l2_cache_write(q, c) < 0)
+ goto error_unlock;
+ }
+
+ if (qcow_write_l1_table < 0)
+ goto error_unlock;
+
+ mutex_unlock(&q->mutex);
+
+ return fsync(disk->fd);
+
+error_unlock:
+ mutex_unlock(&q->mutex);
+ return -1;
+}
+
+static int qcow_disk_close(struct disk_image *disk)
+{
+ struct qcow *q;
+
+ if (!disk)
+ return 0;
+
+ q = disk->priv;
+
+ refcount_table_free_cache(&q->refcount_table);
+ l1_table_free_cache(&q->table);
+ free(q->copy_buff);
+ free(q->cluster_data);
+ free(q->cluster_cache);
+ free(q->refcount_table.rf_table);
+ free(q->table.l1_table);
+ free(q->header);
+ free(q);
+
+ return 0;
+}
+
+static struct disk_image_operations qcow_disk_readonly_ops = {
+ .read = qcow_read_sector,
+ .close = qcow_disk_close,
+};
+
+static struct disk_image_operations qcow_disk_ops = {
+ .read = qcow_read_sector,
+ .write = qcow_write_sector,
+ .flush = qcow_disk_flush,
+ .close = qcow_disk_close,
+};
+
+static int qcow_read_refcount_table(struct qcow *q)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+
+ rft->rf_size = (header->refcount_table_size * q->cluster_size)
+ / sizeof(u64);
+
+ rft->rf_table = calloc(rft->rf_size, sizeof(u64));
+ if (!rft->rf_table)
+ return -1;
+
+ rft->root = RB_ROOT;
+ INIT_LIST_HEAD(&rft->lru_list);
+
+ return pread_in_full(q->fd, rft->rf_table, sizeof(u64) * rft->rf_size, header->refcount_table_offset);
+}
+
+static int qcow_write_refcount_table(struct qcow *q)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_refcount_table *rft = &q->refcount_table;
+
+ return qcow_pwrite_sync(q->fd, rft->rf_table,
+ rft->rf_size * sizeof(u64), header->refcount_table_offset);
+}
+
+static int qcow_read_l1_table(struct qcow *q)
+{
+ struct qcow_header *header = q->header;
+ struct qcow_l1_table *table = &q->table;
+
+ table->table_size = header->l1_size;
+
+ table->l1_table = calloc(table->table_size, sizeof(u64));
+ if (!table->l1_table)
+ return -1;
+
+ return pread_in_full(q->fd, table->l1_table, sizeof(u64) * table->table_size, header->l1_table_offset);
+}
+
+static void *qcow2_read_header(int fd)
+{
+ struct qcow2_header_disk f_header;
+ struct qcow_header *header;
+
+ header = malloc(sizeof(struct qcow_header));
+ if (!header)
+ return NULL;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow2_header_disk), 0) < 0) {
+ free(header);
+ return NULL;
+ }
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+ be64_to_cpus(&f_header.backing_file_offset);
+ be32_to_cpus(&f_header.backing_file_size);
+ be32_to_cpus(&f_header.cluster_bits);
+ be64_to_cpus(&f_header.size);
+ be32_to_cpus(&f_header.crypt_method);
+ be32_to_cpus(&f_header.l1_size);
+ be64_to_cpus(&f_header.l1_table_offset);
+ be64_to_cpus(&f_header.refcount_table_offset);
+ be32_to_cpus(&f_header.refcount_table_clusters);
+ be32_to_cpus(&f_header.nb_snapshots);
+ be64_to_cpus(&f_header.snapshots_offset);
+
+ *header = (struct qcow_header) {
+ .size = f_header.size,
+ .l1_table_offset = f_header.l1_table_offset,
+ .l1_size = f_header.l1_size,
+ .cluster_bits = f_header.cluster_bits,
+ .l2_bits = f_header.cluster_bits - 3,
+ .refcount_table_offset = f_header.refcount_table_offset,
+ .refcount_table_size = f_header.refcount_table_clusters,
+ };
+
+ return header;
+}
+
+static struct disk_image *qcow2_probe(int fd, bool readonly)
+{
+ struct disk_image *disk_image;
+ struct qcow_l1_table *l1t;
+ struct qcow_header *h;
+ struct qcow *q;
+
+ q = calloc(1, sizeof(struct qcow));
+ if (!q)
+ return NULL;
+
+ mutex_init(&q->mutex);
+ q->fd = fd;
+
+ l1t = &q->table;
+
+ l1t->root = RB_ROOT;
+ INIT_LIST_HEAD(&l1t->lru_list);
+
+ h = q->header = qcow2_read_header(fd);
+ if (!h)
+ goto free_qcow;
+
+ q->version = QCOW2_VERSION;
+ q->csize_shift = (62 - (q->header->cluster_bits - 8));
+ q->csize_mask = (1 << (q->header->cluster_bits - 8)) - 1;
+ q->cluster_offset_mask = (1LL << q->csize_shift) - 1;
+ q->cluster_size = 1 << q->header->cluster_bits;
+
+ q->copy_buff = malloc(q->cluster_size);
+ if (!q->copy_buff) {
+ pr_warning("copy buff malloc error");
+ goto free_header;
+ }
+
+ q->cluster_data = malloc(q->cluster_size);
+ if (!q->cluster_data) {
+ pr_warning("cluster data malloc error");
+ goto free_copy_buff;
+ }
+
+ q->cluster_cache = malloc(q->cluster_size);
+ if (!q->cluster_cache) {
+ pr_warning("cluster cache malloc error");
+ goto free_cluster_data;
+ }
+
+ if (qcow_read_l1_table(q) < 0)
+ goto free_cluster_cache;
+
+ if (qcow_read_refcount_table(q) < 0)
+ goto free_l1_table;
+
+ /*
+ * Do not use mmap use read/write instead
+ */
+ if (readonly)
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_readonly_ops, DISK_IMAGE_REGULAR);
+ else
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_ops, DISK_IMAGE_REGULAR);
+
+ if (IS_ERR_OR_NULL(disk_image))
+ goto free_refcount_table;
+
+ disk_image->async = 0;
+ disk_image->priv = q;
+
+ return disk_image;
+
+free_refcount_table:
+ if (q->refcount_table.rf_table)
+ free(q->refcount_table.rf_table);
+free_l1_table:
+ if (q->table.l1_table)
+ free(q->table.l1_table);
+free_cluster_cache:
+ if (q->cluster_cache)
+ free(q->cluster_cache);
+free_cluster_data:
+ if (q->cluster_data)
+ free(q->cluster_data);
+free_copy_buff:
+ if (q->copy_buff)
+ free(q->copy_buff);
+free_header:
+ if (q->header)
+ free(q->header);
+free_qcow:
+ if (q)
+ free(q);
+
+ return NULL;
+}
+
+static bool qcow2_check_image(int fd)
+{
+ struct qcow2_header_disk f_header;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow2_header_disk), 0) < 0)
+ return false;
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+
+ if (f_header.magic != QCOW_MAGIC)
+ return false;
+
+ if (f_header.version != QCOW2_VERSION)
+ return false;
+
+ return true;
+}
+
+static void *qcow1_read_header(int fd)
+{
+ struct qcow1_header_disk f_header;
+ struct qcow_header *header;
+
+ header = malloc(sizeof(struct qcow_header));
+ if (!header)
+ return NULL;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow1_header_disk), 0) < 0) {
+ free(header);
+ return NULL;
+ }
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+ be64_to_cpus(&f_header.backing_file_offset);
+ be32_to_cpus(&f_header.backing_file_size);
+ be32_to_cpus(&f_header.mtime);
+ be64_to_cpus(&f_header.size);
+ be32_to_cpus(&f_header.crypt_method);
+ be64_to_cpus(&f_header.l1_table_offset);
+
+ *header = (struct qcow_header) {
+ .size = f_header.size,
+ .l1_table_offset = f_header.l1_table_offset,
+ .l1_size = f_header.size / ((1 << f_header.l2_bits) * (1 << f_header.cluster_bits)),
+ .cluster_bits = f_header.cluster_bits,
+ .l2_bits = f_header.l2_bits,
+ };
+
+ return header;
+}
+
+static struct disk_image *qcow1_probe(int fd, bool readonly)
+{
+ struct disk_image *disk_image;
+ struct qcow_l1_table *l1t;
+ struct qcow_header *h;
+ struct qcow *q;
+
+ q = calloc(1, sizeof(struct qcow));
+ if (!q)
+ return NULL;
+
+ mutex_init(&q->mutex);
+ q->fd = fd;
+
+ l1t = &q->table;
+
+ l1t->root = RB_ROOT;
+ INIT_LIST_HEAD(&l1t->lru_list);
+
+ h = q->header = qcow1_read_header(fd);
+ if (!h)
+ goto free_qcow;
+
+ q->version = QCOW1_VERSION;
+ q->cluster_size = 1 << q->header->cluster_bits;
+ q->cluster_offset_mask = (1LL << (63 - q->header->cluster_bits)) - 1;
+ q->free_clust_idx = 0;
+
+ q->cluster_data = malloc(q->cluster_size);
+ if (!q->cluster_data) {
+ pr_warning("cluster data malloc error");
+ goto free_header;
+ }
+
+ q->cluster_cache = malloc(q->cluster_size);
+ if (!q->cluster_cache) {
+ pr_warning("cluster cache malloc error");
+ goto free_cluster_data;
+ }
+
+ if (qcow_read_l1_table(q) < 0)
+ goto free_cluster_cache;
+
+ /*
+ * Do not use mmap use read/write instead
+ */
+ if (readonly)
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_readonly_ops, DISK_IMAGE_REGULAR);
+ else
+ disk_image = disk_image__new(fd, h->size, &qcow_disk_ops, DISK_IMAGE_REGULAR);
+
+ if (!disk_image)
+ goto free_l1_table;
+
+ disk_image->async = 1;
+ disk_image->priv = q;
+
+ return disk_image;
+
+free_l1_table:
+ if (q->table.l1_table)
+ free(q->table.l1_table);
+free_cluster_cache:
+ if (q->cluster_cache)
+ free(q->cluster_cache);
+free_cluster_data:
+ if (q->cluster_data)
+ free(q->cluster_data);
+free_header:
+ if (q->header)
+ free(q->header);
+free_qcow:
+ if (q)
+ free(q);
+
+ return NULL;
+}
+
+static bool qcow1_check_image(int fd)
+{
+ struct qcow1_header_disk f_header;
+
+ if (pread_in_full(fd, &f_header, sizeof(struct qcow1_header_disk), 0) < 0)
+ return false;
+
+ be32_to_cpus(&f_header.magic);
+ be32_to_cpus(&f_header.version);
+
+ if (f_header.magic != QCOW_MAGIC)
+ return false;
+
+ if (f_header.version != QCOW1_VERSION)
+ return false;
+
+ return true;
+}
+
+struct disk_image *qcow_probe(int fd, bool readonly)
+{
+ if (qcow1_check_image(fd))
+ return qcow1_probe(fd, readonly);
+
+ if (qcow2_check_image(fd))
+ return qcow2_probe(fd, readonly);
+
+ return NULL;
+}
--- /dev/null
+#include "kvm/disk-image.h"
+
+#include <linux/err.h>
+
+#ifdef CONFIG_HAS_AIO
+#include <libaio.h>
+#endif
+
+ssize_t raw_image__read(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ u64 offset = sector << SECTOR_SHIFT;
+
+#ifdef CONFIG_HAS_AIO
+ struct iocb iocb;
+
+ return aio_preadv(disk->ctx, &iocb, disk->fd, iov, iovcount, offset,
+ disk->evt, param);
+#else
+ return preadv_in_full(disk->fd, iov, iovcount, offset);
+#endif
+}
+
+ssize_t raw_image__write(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ u64 offset = sector << SECTOR_SHIFT;
+
+#ifdef CONFIG_HAS_AIO
+ struct iocb iocb;
+
+ return aio_pwritev(disk->ctx, &iocb, disk->fd, iov, iovcount, offset,
+ disk->evt, param);
+#else
+ return pwritev_in_full(disk->fd, iov, iovcount, offset);
+#endif
+}
+
+ssize_t raw_image__read_mmap(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ u64 offset = sector << SECTOR_SHIFT;
+ ssize_t total = 0;
+
+ while (iovcount--) {
+ memcpy(iov->iov_base, disk->priv + offset, iov->iov_len);
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ offset += iov->iov_len;
+ total += iov->iov_len;
+ iov++;
+ }
+
+ return total;
+}
+
+ssize_t raw_image__write_mmap(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param)
+{
+ u64 offset = sector << SECTOR_SHIFT;
+ ssize_t total = 0;
+
+ while (iovcount--) {
+ memcpy(disk->priv + offset, iov->iov_base, iov->iov_len);
+
+ sector += iov->iov_len >> SECTOR_SHIFT;
+ offset += iov->iov_len;
+ total += iov->iov_len;
+ iov++;
+ }
+
+ return total;
+}
+
+int raw_image__close(struct disk_image *disk)
+{
+ int ret = 0;
+
+ if (disk->priv != MAP_FAILED)
+ ret = munmap(disk->priv, disk->size);
+
+ close(disk->evt);
+
+#ifdef CONFIG_HAS_VIRTIO
+ io_destroy(disk->ctx);
+#endif
+
+ return ret;
+}
+
+/*
+ * multiple buffer based disk image operations
+ */
+static struct disk_image_operations raw_image_regular_ops = {
+ .read = raw_image__read,
+ .write = raw_image__write,
+};
+
+struct disk_image_operations ro_ops = {
+ .read = raw_image__read_mmap,
+ .write = raw_image__write_mmap,
+ .close = raw_image__close,
+};
+
+struct disk_image_operations ro_ops_nowrite = {
+ .read = raw_image__read,
+};
+
+struct disk_image *raw_image__probe(int fd, struct stat *st, bool readonly)
+{
+ struct disk_image *disk;
+
+ if (readonly) {
+ /*
+ * Use mmap's MAP_PRIVATE to implement non-persistent write
+ * FIXME: This does not work on 32-bit host.
+ */
+ struct disk_image *disk;
+
+ disk = disk_image__new(fd, st->st_size, &ro_ops, DISK_IMAGE_MMAP);
+ if (IS_ERR_OR_NULL(disk)) {
+ disk = disk_image__new(fd, st->st_size, &ro_ops_nowrite, DISK_IMAGE_REGULAR);
+#ifdef CONFIG_HAS_AIO
+ if (!IS_ERR_OR_NULL(disk))
+ disk->async = 1;
+#endif
+ }
+
+ return disk;
+ } else {
+ /*
+ * Use read/write instead of mmap
+ */
+ disk = disk_image__new(fd, st->st_size, &raw_image_regular_ops, DISK_IMAGE_REGULAR);
+#ifdef CONFIG_HAS_AIO
+ if (!IS_ERR_OR_NULL(disk))
+ disk->async = 1;
+#endif
+ return disk;
+ }
+}
--- /dev/null
+#include "kvm/framebuffer.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <errno.h>
+
+static LIST_HEAD(framebuffers);
+
+struct framebuffer *fb__register(struct framebuffer *fb)
+{
+ INIT_LIST_HEAD(&fb->node);
+ list_add(&fb->node, &framebuffers);
+
+ return fb;
+}
+
+int fb__attach(struct framebuffer *fb, struct fb_target_operations *ops)
+{
+ if (fb->nr_targets >= FB_MAX_TARGETS)
+ return -ENOSPC;
+
+ fb->targets[fb->nr_targets++] = ops;
+
+ return 0;
+}
+
+static int start_targets(struct framebuffer *fb)
+{
+ unsigned long i;
+
+ for (i = 0; i < fb->nr_targets; i++) {
+ struct fb_target_operations *ops = fb->targets[i];
+ int err = 0;
+
+ if (ops->start)
+ err = ops->start(fb);
+
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+int fb__start(void)
+{
+ struct framebuffer *fb;
+
+ list_for_each_entry(fb, &framebuffers, node) {
+ int err;
+
+ err = start_targets(fb);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+void fb__stop(void)
+{
+ struct framebuffer *fb;
+
+ list_for_each_entry(fb, &framebuffers, node) {
+ u32 i;
+
+ for (i = 0; i < fb->nr_targets; i++)
+ if (fb->targets[i]->stop)
+ fb->targets[i]->stop(fb);
+
+ munmap(fb->mem, fb->mem_size);
+ }
+}
--- /dev/null
+/*
+ * This is a simple init for shared rootfs guests. This part should be limited
+ * to doing mounts and running stage 2 of the init process.
+ */
+#include <sys/mount.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <errno.h>
+#include <linux/reboot.h>
+
+static int run_process(char *filename)
+{
+ char *new_argv[] = { filename, NULL };
+ char *new_env[] = { "TERM=linux", "DISPLAY=192.168.33.1:0",
+ "HOME=/virt/home", NULL };
+
+ return execve(filename, new_argv, new_env);
+}
+
+static int run_process_sandbox(char *filename)
+{
+ char *new_argv[] = { filename, "/virt/sandbox.sh", NULL };
+ char *new_env[] = { "TERM=linux", "HOME=/virt/home", NULL };
+
+ return execve(filename, new_argv, new_env);
+}
+
+static void do_mounts(void)
+{
+ mount("hostfs", "/host", "9p", MS_RDONLY, "trans=virtio,version=9p2000.L");
+ mount("", "/sys", "sysfs", 0, NULL);
+ mount("proc", "/proc", "proc", 0, NULL);
+ mount("devtmpfs", "/dev", "devtmpfs", 0, NULL);
+ mkdir("/dev/pts", 0755);
+ mount("devpts", "/dev/pts", "devpts", 0, NULL);
+}
+
+int main(int argc, char *argv[])
+{
+ pid_t child;
+ int status;
+
+ puts("Mounting...");
+
+ do_mounts();
+
+ /* get session leader */
+ setsid();
+
+ /* set controlling terminal */
+ ioctl(0, TIOCSCTTY, 1);
+
+ child = fork();
+ if (child < 0) {
+ printf("Fatal: fork() failed with %d\n", child);
+ return 0;
+ } else if (child == 0) {
+ if (access("/virt/sandbox.sh", R_OK) == 0)
+ run_process_sandbox("/bin/sh");
+ else
+ run_process("/bin/sh");
+ } else {
+ waitpid(child, &status, 0);
+ }
+
+ reboot(LINUX_REBOOT_CMD_RESTART);
+
+ printf("Init failed: %s\n", strerror(errno));
+
+ return 0;
+}
--- /dev/null
+#include "kvm/guest_compat.h"
+
+#include "kvm/mutex.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+struct compat_message {
+ int id;
+ char *title;
+ char *desc;
+
+ struct list_head list;
+};
+
+static int id;
+static DEFINE_MUTEX(compat_mtx);
+static LIST_HEAD(messages);
+
+static void compat__free(struct compat_message *msg)
+{
+ free(msg->title);
+ free(msg->desc);
+ free(msg);
+}
+
+int compat__add_message(const char *title, const char *desc)
+{
+ struct compat_message *msg;
+ int msg_id;
+
+ msg = malloc(sizeof(*msg));
+ if (msg == NULL)
+ goto cleanup;
+
+ msg->title = strdup(title);
+ msg->desc = strdup(desc);
+
+ if (msg->title == NULL || msg->desc == NULL)
+ goto cleanup;
+
+ mutex_lock(&compat_mtx);
+
+ msg->id = msg_id = id++;
+ list_add_tail(&msg->list, &messages);
+
+ mutex_unlock(&compat_mtx);
+
+ return msg_id;
+
+cleanup:
+ if (msg)
+ compat__free(msg);
+
+ return -ENOMEM;
+}
+
+int compat__remove_message(int id)
+{
+ struct compat_message *pos, *n;
+
+ mutex_lock(&compat_mtx);
+
+ list_for_each_entry_safe(pos, n, &messages, list) {
+ if (pos->id == id) {
+ list_del(&pos->list);
+ compat__free(pos);
+
+ mutex_unlock(&compat_mtx);
+
+ return 0;
+ }
+ }
+
+ mutex_unlock(&compat_mtx);
+
+ return -ENOENT;
+}
+
+int compat__print_all_messages(void)
+{
+ mutex_lock(&compat_mtx);
+
+ while (!list_empty(&messages)) {
+ struct compat_message *msg;
+
+ msg = list_first_entry(&messages, struct compat_message, list);
+
+ printf("\n # KVM compatibility warning.\n\t%s\n\t%s\n",
+ msg->title, msg->desc);
+
+ list_del(&msg->list);
+ compat__free(msg);
+ }
+
+ mutex_unlock(&compat_mtx);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/read-write.h"
+#include "kvm/ioport.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "kvm/kvm.h"
+#include "kvm/i8042.h"
+#include "kvm/kvm-cpu.h"
+
+#include <stdint.h>
+
+/*
+ * IRQs
+ */
+#define KBD_IRQ 1
+#define AUX_IRQ 12
+
+/*
+ * Registers
+ */
+#define I8042_DATA_REG 0x60
+#define I8042_COMMAND_REG 0x64
+
+/*
+ * Commands
+ */
+#define I8042_CMD_CTL_RCTR 0x20
+#define I8042_CMD_CTL_WCTR 0x60
+#define I8042_CMD_AUX_LOOP 0xD3
+#define I8042_CMD_AUX_SEND 0xD4
+#define I8042_CMD_AUX_TEST 0xA9
+#define I8042_CMD_AUX_DISABLE 0xA7
+#define I8042_CMD_AUX_ENABLE 0xA8
+#define I8042_CMD_SYSTEM_RESET 0xFE
+
+#define RESPONSE_ACK 0xFA
+
+#define MODE_DISABLE_AUX 0x20
+
+#define AUX_ENABLE_REPORTING 0x20
+#define AUX_SCALING_FLAG 0x10
+#define AUX_DEFAULT_RESOLUTION 0x2
+#define AUX_DEFAULT_SAMPLE 100
+
+/*
+ * Status register bits
+ */
+#define I8042_STR_AUXDATA 0x20
+#define I8042_STR_KEYLOCK 0x10
+#define I8042_STR_CMDDAT 0x08
+#define I8042_STR_MUXERR 0x04
+#define I8042_STR_OBF 0x01
+
+#define KBD_MODE_KBD_INT 0x01
+#define KBD_MODE_SYS 0x02
+
+#define QUEUE_SIZE 128
+
+/*
+ * This represents the current state of the PS/2 keyboard system,
+ * including the AUX device (the mouse)
+ */
+struct kbd_state {
+ struct kvm *kvm;
+
+ char kq[QUEUE_SIZE]; /* Keyboard queue */
+ int kread, kwrite; /* Indexes into the queue */
+ int kcount; /* number of elements in queue */
+
+ char mq[QUEUE_SIZE];
+ int mread, mwrite;
+ int mcount;
+
+ u8 mstatus; /* Mouse status byte */
+ u8 mres; /* Current mouse resolution */
+ u8 msample; /* Current mouse samples/second */
+
+ u8 mode; /* i8042 mode register */
+ u8 status; /* i8042 status register */
+ /*
+ * Some commands (on port 0x64) have arguments;
+ * we store the command here while we wait for the argument
+ */
+ u32 write_cmd;
+};
+
+static struct kbd_state state;
+
+/*
+ * If there are packets to be read, set the appropriate IRQs high
+ */
+static void kbd_update_irq(void)
+{
+ u8 klevel = 0;
+ u8 mlevel = 0;
+
+ /* First, clear the kbd and aux output buffer full bits */
+ state.status &= ~(I8042_STR_OBF | I8042_STR_AUXDATA);
+
+ if (state.kcount > 0) {
+ state.status |= I8042_STR_OBF;
+ klevel = 1;
+ }
+
+ /* Keyboard has higher priority than mouse */
+ if (klevel == 0 && state.mcount != 0) {
+ state.status |= I8042_STR_OBF | I8042_STR_AUXDATA;
+ mlevel = 1;
+ }
+
+ kvm__irq_line(state.kvm, KBD_IRQ, klevel);
+ kvm__irq_line(state.kvm, AUX_IRQ, mlevel);
+}
+
+/*
+ * Add a byte to the mouse queue, then set IRQs
+ */
+void mouse_queue(u8 c)
+{
+ if (state.mcount >= QUEUE_SIZE)
+ return;
+
+ state.mq[state.mwrite++ % QUEUE_SIZE] = c;
+
+ state.mcount++;
+ kbd_update_irq();
+}
+
+/*
+ * Add a byte to the keyboard queue, then set IRQs
+ */
+void kbd_queue(u8 c)
+{
+ if (state.kcount >= QUEUE_SIZE)
+ return;
+
+ state.kq[state.kwrite++ % QUEUE_SIZE] = c;
+
+ state.kcount++;
+ kbd_update_irq();
+}
+
+static void kbd_write_command(struct kvm *kvm, u8 val)
+{
+ switch (val) {
+ case I8042_CMD_CTL_RCTR:
+ kbd_queue(state.mode);
+ break;
+ case I8042_CMD_CTL_WCTR:
+ case I8042_CMD_AUX_SEND:
+ case I8042_CMD_AUX_LOOP:
+ state.write_cmd = val;
+ break;
+ case I8042_CMD_AUX_TEST:
+ /* 0 means we're a normal PS/2 mouse */
+ mouse_queue(0);
+ break;
+ case I8042_CMD_AUX_DISABLE:
+ state.mode |= MODE_DISABLE_AUX;
+ break;
+ case I8042_CMD_AUX_ENABLE:
+ state.mode &= ~MODE_DISABLE_AUX;
+ break;
+ case I8042_CMD_SYSTEM_RESET:
+ kvm_cpu__reboot();
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * Called when the OS reads from port 0x60 (PS/2 data)
+ */
+static u32 kbd_read_data(void)
+{
+ u32 ret;
+ int i;
+
+ if (state.kcount != 0) {
+ /* Keyboard data gets read first */
+ ret = state.kq[state.kread++ % QUEUE_SIZE];
+ state.kcount--;
+ kvm__irq_line(state.kvm, KBD_IRQ, 0);
+ kbd_update_irq();
+ } else if (state.mcount > 0) {
+ /* Followed by the mouse */
+ ret = state.mq[state.mread++ % QUEUE_SIZE];
+ state.mcount--;
+ kvm__irq_line(state.kvm, AUX_IRQ, 0);
+ kbd_update_irq();
+ } else if (state.kcount == 0) {
+ i = state.kread - 1;
+ if (i < 0)
+ i = QUEUE_SIZE;
+ ret = state.kq[i];
+ }
+ return ret;
+}
+
+/*
+ * Called when the OS read from port 0x64, the command port
+ */
+static u32 kbd_read_status(void)
+{
+ return (u32)state.status;
+}
+
+/*
+ * Called when the OS writes to port 0x60 (data port)
+ * Things written here are generally arguments to commands previously
+ * written to port 0x64 and stored in state.write_cmd
+ */
+static void kbd_write_data(u32 val)
+{
+ switch (state.write_cmd) {
+ case I8042_CMD_CTL_WCTR:
+ state.mode = val;
+ kbd_update_irq();
+ break;
+ case I8042_CMD_AUX_LOOP:
+ mouse_queue(val);
+ mouse_queue(RESPONSE_ACK);
+ break;
+ case I8042_CMD_AUX_SEND:
+ /* The OS wants to send a command to the mouse */
+ mouse_queue(RESPONSE_ACK);
+ switch (val) {
+ case 0xe6:
+ /* set scaling = 1:1 */
+ state.mstatus &= ~AUX_SCALING_FLAG;
+ break;
+ case 0xe8:
+ /* set resolution */
+ state.mres = val;
+ break;
+ case 0xe9:
+ /* Report mouse status/config */
+ mouse_queue(state.mstatus);
+ mouse_queue(state.mres);
+ mouse_queue(state.msample);
+ break;
+ case 0xf2:
+ /* send ID */
+ mouse_queue(0); /* normal mouse */
+ break;
+ case 0xf3:
+ /* set sample rate */
+ state.msample = val;
+ break;
+ case 0xf4:
+ /* enable reporting */
+ state.mstatus |= AUX_ENABLE_REPORTING;
+ break;
+ case 0xf5:
+ state.mstatus &= ~AUX_ENABLE_REPORTING;
+ break;
+ case 0xf6:
+ /* set defaults, just fall through to reset */
+ case 0xff:
+ /* reset */
+ state.mstatus = 0x0;
+ state.mres = AUX_DEFAULT_RESOLUTION;
+ state.msample = AUX_DEFAULT_SAMPLE;
+ break;
+ default:
+ break;
+ }
+ break;
+ case 0:
+ /* Just send the ID */
+ kbd_queue(RESPONSE_ACK);
+ kbd_queue(0xab);
+ kbd_queue(0x41);
+ kbd_update_irq();
+ break;
+ default:
+ /* Yeah whatever */
+ break;
+ }
+ state.write_cmd = 0;
+}
+
+static void kbd_reset(void)
+{
+ state = (struct kbd_state) {
+ .status = I8042_STR_MUXERR | I8042_STR_CMDDAT | I8042_STR_KEYLOCK, /* 0x1c */
+ .mode = KBD_MODE_KBD_INT | KBD_MODE_SYS, /* 0x3 */
+ .mres = AUX_DEFAULT_RESOLUTION,
+ .msample = AUX_DEFAULT_SAMPLE,
+ };
+}
+
+/*
+ * Called when the OS has written to one of the keyboard's ports (0x60 or 0x64)
+ */
+static bool kbd_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ switch (port) {
+ case I8042_COMMAND_REG: {
+ u8 value = kbd_read_status();
+ ioport__write8(data, value);
+ break;
+ }
+ case I8042_DATA_REG: {
+ u32 value = kbd_read_data();
+ ioport__write32(data, value);
+ break;
+ }
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static bool kbd_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ switch (port) {
+ case I8042_COMMAND_REG: {
+ u8 value = ioport__read8(data);
+ kbd_write_command(kvm, value);
+ break;
+ }
+ case I8042_DATA_REG: {
+ u32 value = ioport__read32(data);
+ kbd_write_data(value);
+ break;
+ }
+ default:
+ return false;
+ }
+
+ return true;
+}
+
+static struct ioport_operations kbd_ops = {
+ .io_in = kbd_in,
+ .io_out = kbd_out,
+};
+
+void kbd__init(struct kvm *kvm)
+{
+ kbd_reset();
+ state.kvm = kvm;
+ ioport__register(I8042_DATA_REG, &kbd_ops, 2, NULL);
+ ioport__register(I8042_COMMAND_REG, &kbd_ops, 2, NULL);
+}
--- /dev/null
+#include "kvm/pci-shmem.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/util.h"
+#include "kvm/ioport.h"
+#include "kvm/ioeventfd.h"
+
+#include <linux/kvm.h>
+#include <linux/byteorder.h>
+#include <sys/ioctl.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+
+static struct pci_device_header pci_shmem_pci_device = {
+ .vendor_id = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET),
+ .device_id = cpu_to_le16(0x1110),
+ .header_type = PCI_HEADER_TYPE_NORMAL,
+ .class[2] = 0xFF, /* misc pci device */
+ .status = cpu_to_le16(PCI_STATUS_CAP_LIST),
+ .capabilities = (void *)&pci_shmem_pci_device.msix - (void *)&pci_shmem_pci_device,
+ .msix.cap = PCI_CAP_ID_MSIX,
+ .msix.ctrl = cpu_to_le16(1),
+ .msix.table_offset = cpu_to_le32(1), /* Use BAR 1 */
+ .msix.pba_offset = cpu_to_le32(0x1001), /* Use BAR 1 */
+};
+
+/* registers for the Inter-VM shared memory device */
+enum ivshmem_registers {
+ INTRMASK = 0,
+ INTRSTATUS = 4,
+ IVPOSITION = 8,
+ DOORBELL = 12,
+};
+
+static struct shmem_info *shmem_region;
+static u16 ivshmem_registers;
+static int local_fd;
+static u32 local_id;
+static u64 msix_block;
+static u64 msix_pba;
+static struct msix_table msix_table[2];
+
+int pci_shmem__register_mem(struct shmem_info *si)
+{
+ if (shmem_region == NULL) {
+ shmem_region = si;
+ } else {
+ pr_warning("only single shmem currently avail. ignoring.\n");
+ free(si);
+ }
+ return 0;
+}
+
+static bool shmem_pci__io_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ u16 offset = port - ivshmem_registers;
+
+ switch (offset) {
+ case INTRMASK:
+ break;
+ case INTRSTATUS:
+ break;
+ case IVPOSITION:
+ ioport__write32(data, local_id);
+ break;
+ case DOORBELL:
+ break;
+ };
+
+ return true;
+}
+
+static bool shmem_pci__io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ u16 offset = port - ivshmem_registers;
+
+ switch (offset) {
+ case INTRMASK:
+ break;
+ case INTRSTATUS:
+ break;
+ case IVPOSITION:
+ break;
+ case DOORBELL:
+ break;
+ };
+
+ return true;
+}
+
+static struct ioport_operations shmem_pci__io_ops = {
+ .io_in = shmem_pci__io_in,
+ .io_out = shmem_pci__io_out,
+};
+
+static void callback_mmio_msix(u64 addr, u8 *data, u32 len, u8 is_write, void *ptr)
+{
+ void *mem;
+
+ if (addr - msix_block < 0x1000)
+ mem = &msix_table;
+ else
+ mem = &msix_pba;
+
+ if (is_write)
+ memcpy(mem + addr - msix_block, data, len);
+ else
+ memcpy(data, mem + addr - msix_block, len);
+}
+
+/*
+ * Return an irqfd which can be used by other guests to signal this guest
+ * whenever they need to poke it
+ */
+int pci_shmem__get_local_irqfd(struct kvm *kvm)
+{
+ int fd, gsi, r;
+ struct kvm_irqfd irqfd;
+
+ if (local_fd == 0) {
+ fd = eventfd(0, 0);
+ if (fd < 0)
+ return fd;
+
+ if (pci_shmem_pci_device.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_ENABLE)) {
+ gsi = irq__add_msix_route(kvm, &msix_table[0].msg);
+ } else {
+ gsi = pci_shmem_pci_device.irq_line;
+ }
+
+ irqfd = (struct kvm_irqfd) {
+ .fd = fd,
+ .gsi = gsi,
+ };
+
+ r = ioctl(kvm->vm_fd, KVM_IRQFD, &irqfd);
+ if (r < 0)
+ return r;
+
+ local_fd = fd;
+ }
+
+ return local_fd;
+}
+
+/*
+ * Connect a new client to ivshmem by adding the appropriate datamatch
+ * to the DOORBELL
+ */
+int pci_shmem__add_client(struct kvm *kvm, u32 id, int fd)
+{
+ struct kvm_ioeventfd ioevent;
+
+ ioevent = (struct kvm_ioeventfd) {
+ .addr = ivshmem_registers + DOORBELL,
+ .len = sizeof(u32),
+ .datamatch = id,
+ .fd = fd,
+ .flags = KVM_IOEVENTFD_FLAG_PIO | KVM_IOEVENTFD_FLAG_DATAMATCH,
+ };
+
+ return ioctl(kvm->vm_fd, KVM_IOEVENTFD, &ioevent);
+}
+
+/*
+ * Remove a client connected to ivshmem by removing the appropriate datamatch
+ * from the DOORBELL
+ */
+int pci_shmem__remove_client(struct kvm *kvm, u32 id)
+{
+ struct kvm_ioeventfd ioevent;
+
+ ioevent = (struct kvm_ioeventfd) {
+ .addr = ivshmem_registers + DOORBELL,
+ .len = sizeof(u32),
+ .datamatch = id,
+ .flags = KVM_IOEVENTFD_FLAG_PIO
+ | KVM_IOEVENTFD_FLAG_DATAMATCH
+ | KVM_IOEVENTFD_FLAG_DEASSIGN,
+ };
+
+ return ioctl(kvm->vm_fd, KVM_IOEVENTFD, &ioevent);
+}
+
+static void *setup_shmem(const char *key, size_t len, int creating)
+{
+ int fd;
+ int rtn;
+ void *mem;
+ int flag = O_RDWR;
+
+ if (creating)
+ flag |= O_CREAT;
+
+ fd = shm_open(key, flag, S_IRUSR | S_IWUSR);
+ if (fd < 0) {
+ pr_warning("Failed to open shared memory file %s\n", key);
+ return NULL;
+ }
+
+ if (creating) {
+ rtn = ftruncate(fd, (off_t) len);
+ if (rtn < 0)
+ pr_warning("Can't ftruncate(fd,%zu)\n", len);
+ }
+ mem = mmap(NULL, len,
+ PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE, fd, 0);
+ if (mem == MAP_FAILED) {
+ pr_warning("Failed to mmap shared memory file");
+ mem = NULL;
+ }
+ close(fd);
+
+ return mem;
+}
+
+int pci_shmem__init(struct kvm *kvm)
+{
+ u8 dev, line, pin;
+ char *mem;
+ int r;
+
+ if (shmem_region == 0)
+ return 0;
+
+ /* Register good old INTx */
+ if (irq__register_device(PCI_DEVICE_ID_PCI_SHMEM, &dev, &pin, &line) < 0)
+ return 0;
+
+ pci_shmem_pci_device.irq_pin = pin;
+ pci_shmem_pci_device.irq_line = line;
+
+ /* Register MMIO space for MSI-X */
+ r = ioport__register(IOPORT_EMPTY, &shmem_pci__io_ops, IOPORT_SIZE, NULL);
+ if (r < 0)
+ return r;
+ ivshmem_registers = (u16)r;
+
+ msix_block = pci_get_io_space_block(0x1010);
+ kvm__register_mmio(kvm, msix_block, 0x1010, false, callback_mmio_msix, NULL);
+
+ /*
+ * This registers 3 BARs:
+ *
+ * 0 - ivshmem registers
+ * 1 - MSI-X MMIO space
+ * 2 - Shared memory block
+ */
+ pci_shmem_pci_device.bar[0] = cpu_to_le32(ivshmem_registers | PCI_BASE_ADDRESS_SPACE_IO);
+ pci_shmem_pci_device.bar_size[0] = shmem_region->size;
+ pci_shmem_pci_device.bar[1] = cpu_to_le32(msix_block | PCI_BASE_ADDRESS_SPACE_MEMORY);
+ pci_shmem_pci_device.bar_size[1] = 0x1010;
+ pci_shmem_pci_device.bar[2] = cpu_to_le32(shmem_region->phys_addr | PCI_BASE_ADDRESS_SPACE_MEMORY);
+ pci_shmem_pci_device.bar_size[2] = shmem_region->size;
+
+ pci__register(&pci_shmem_pci_device, dev);
+
+ /* Open shared memory and plug it into the guest */
+ mem = setup_shmem(shmem_region->handle, shmem_region->size,
+ shmem_region->create);
+ if (mem == NULL)
+ return 0;
+ kvm__register_mem(kvm, shmem_region->phys_addr, shmem_region->size,
+ mem);
+ return 1;
+}
--- /dev/null
+#include "kvm/rtc.h"
+
+#include "kvm/ioport.h"
+#include "kvm/kvm.h"
+
+#include <time.h>
+
+/*
+ * MC146818 RTC registers
+ */
+#define RTC_SECONDS 0x00
+#define RTC_SECONDS_ALARM 0x01
+#define RTC_MINUTES 0x02
+#define RTC_MINUTES_ALARM 0x03
+#define RTC_HOURS 0x04
+#define RTC_HOURS_ALARM 0x05
+#define RTC_DAY_OF_WEEK 0x06
+#define RTC_DAY_OF_MONTH 0x07
+#define RTC_MONTH 0x08
+#define RTC_YEAR 0x09
+
+#define RTC_REG_A 0x0A
+#define RTC_REG_B 0x0B
+#define RTC_REG_C 0x0C
+#define RTC_REG_D 0x0D
+
+struct rtc_device {
+ u8 cmos_idx;
+ u8 cmos_data[128];
+};
+
+static struct rtc_device rtc;
+
+static inline unsigned char bin2bcd(unsigned val)
+{
+ return ((val / 10) << 4) + val % 10;
+}
+
+static bool cmos_ram_data_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ struct tm *tm;
+ time_t ti;
+
+ time(&ti);
+
+ tm = gmtime(&ti);
+
+ switch (rtc.cmos_idx) {
+ case RTC_SECONDS:
+ ioport__write8(data, bin2bcd(tm->tm_sec));
+ break;
+ case RTC_MINUTES:
+ ioport__write8(data, bin2bcd(tm->tm_min));
+ break;
+ case RTC_HOURS:
+ ioport__write8(data, bin2bcd(tm->tm_hour));
+ break;
+ case RTC_DAY_OF_WEEK:
+ ioport__write8(data, bin2bcd(tm->tm_wday + 1));
+ break;
+ case RTC_DAY_OF_MONTH:
+ ioport__write8(data, bin2bcd(tm->tm_mday));
+ break;
+ case RTC_MONTH:
+ ioport__write8(data, bin2bcd(tm->tm_mon + 1));
+ break;
+ case RTC_YEAR:
+ ioport__write8(data, bin2bcd(tm->tm_year));
+ break;
+ default:
+ ioport__write8(data, rtc.cmos_data[rtc.cmos_idx]);
+ break;
+ }
+
+ return true;
+}
+
+static bool cmos_ram_data_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ switch (rtc.cmos_idx) {
+ case RTC_REG_C:
+ case RTC_REG_D:
+ /* Read-only */
+ break;
+ default:
+ rtc.cmos_data[rtc.cmos_idx] = ioport__read8(data);
+ break;
+ }
+
+ return true;
+}
+
+static struct ioport_operations cmos_ram_data_ioport_ops = {
+ .io_out = cmos_ram_data_out,
+ .io_in = cmos_ram_data_in,
+};
+
+static bool cmos_ram_index_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ u8 value = ioport__read8(data);
+
+ kvm->nmi_disabled = value & (1UL << 7);
+ rtc.cmos_idx = value & ~(1UL << 7);
+
+ return true;
+}
+
+static struct ioport_operations cmos_ram_index_ioport_ops = {
+ .io_out = cmos_ram_index_out,
+};
+
+int rtc__init(struct kvm *kvm)
+{
+ int r = 0;
+
+ /* PORT 0070-007F - CMOS RAM/RTC (REAL TIME CLOCK) */
+ r = ioport__register(0x0070, &cmos_ram_index_ioport_ops, 1, NULL);
+ if (r < 0)
+ return r;
+
+ r = ioport__register(0x0071, &cmos_ram_data_ioport_ops, 1, NULL);
+ if (r < 0) {
+ ioport__unregister(0x0071);
+ return r;
+ }
+
+ return r;
+}
+
+int rtc__exit(struct kvm *kvm)
+{
+ /* PORT 0070-007F - CMOS RAM/RTC (REAL TIME CLOCK) */
+ ioport__unregister(0x0070);
+ ioport__unregister(0x0071);
+
+ return 0;
+}
\ No newline at end of file
--- /dev/null
+#include "kvm/8250-serial.h"
+
+#include "kvm/read-write.h"
+#include "kvm/ioport.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "kvm/kvm.h"
+
+#include <linux/types.h>
+#include <linux/serial_reg.h>
+
+#include <pthread.h>
+
+/*
+ * This fakes a U6_16550A. The fifo len needs to be 64 as the kernel
+ * expects that for autodetection.
+ */
+#define FIFO_LEN 64
+#define FIFO_MASK (FIFO_LEN - 1)
+
+#define UART_IIR_TYPE_BITS 0xc0
+
+struct serial8250_device {
+ pthread_mutex_t mutex;
+ u8 id;
+
+ u16 iobase;
+ u8 irq;
+ u8 irq_state;
+ int txcnt;
+ int rxcnt;
+ int rxdone;
+ char txbuf[FIFO_LEN];
+ char rxbuf[FIFO_LEN];
+
+ u8 dll;
+ u8 dlm;
+ u8 iir;
+ u8 ier;
+ u8 fcr;
+ u8 lcr;
+ u8 mcr;
+ u8 lsr;
+ u8 msr;
+ u8 scr;
+};
+
+#define SERIAL_REGS_SETTING \
+ .iir = UART_IIR_NO_INT, \
+ .lsr = UART_LSR_TEMT | UART_LSR_THRE, \
+ .msr = UART_MSR_DCD | UART_MSR_DSR | UART_MSR_CTS, \
+ .mcr = UART_MCR_OUT2,
+
+static struct serial8250_device devices[] = {
+ /* ttyS0 */
+ [0] = {
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+
+ .id = 0,
+ .iobase = 0x3f8,
+ .irq = 4,
+
+ SERIAL_REGS_SETTING
+ },
+ /* ttyS1 */
+ [1] = {
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+
+ .id = 1,
+ .iobase = 0x2f8,
+ .irq = 3,
+
+ SERIAL_REGS_SETTING
+ },
+ /* ttyS2 */
+ [2] = {
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+
+ .id = 2,
+ .iobase = 0x3e8,
+ .irq = 4,
+
+ SERIAL_REGS_SETTING
+ },
+ /* ttyS3 */
+ [3] = {
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+
+ .id = 3,
+ .iobase = 0x2e8,
+ .irq = 3,
+
+ SERIAL_REGS_SETTING
+ },
+};
+
+static void serial8250_flush_tx(struct serial8250_device *dev)
+{
+ dev->lsr |= UART_LSR_TEMT | UART_LSR_THRE;
+
+ if (dev->txcnt) {
+ term_putc(CONSOLE_8250, dev->txbuf, dev->txcnt, dev->id);
+ dev->txcnt = 0;
+ }
+}
+
+static void serial8250_update_irq(struct kvm *kvm, struct serial8250_device *dev)
+{
+ u8 iir = 0;
+
+ /* Handle clear rx */
+ if (dev->lcr & UART_FCR_CLEAR_RCVR) {
+ dev->lcr &= ~UART_FCR_CLEAR_RCVR;
+ dev->rxcnt = dev->rxdone = 0;
+ dev->lsr &= ~UART_LSR_DR;
+ }
+
+ /* Handle clear tx */
+ if (dev->lcr & UART_FCR_CLEAR_XMIT) {
+ dev->lcr &= ~UART_FCR_CLEAR_XMIT;
+ dev->txcnt = 0;
+ dev->lsr |= UART_LSR_TEMT | UART_LSR_THRE;
+ }
+
+ /* Data ready and rcv interrupt enabled ? */
+ if ((dev->ier & UART_IER_RDI) && (dev->lsr & UART_LSR_DR))
+ iir |= UART_IIR_RDI;
+
+ /* Transmitter empty and interrupt enabled ? */
+ if ((dev->ier & UART_IER_THRI) && (dev->lsr & UART_LSR_TEMT))
+ iir |= UART_IIR_THRI;
+
+ /* Now update the irq line, if necessary */
+ if (!iir) {
+ dev->iir = UART_IIR_NO_INT;
+ if (dev->irq_state)
+ kvm__irq_line(kvm, dev->irq, 0);
+ } else {
+ dev->iir = iir;
+ if (!dev->irq_state)
+ kvm__irq_line(kvm, dev->irq, 1);
+ }
+ dev->irq_state = iir;
+
+ /*
+ * If the kernel disabled the tx interrupt, we know that there
+ * is nothing more to transmit, so we can reset our tx logic
+ * here.
+ */
+ if (!(dev->ier & UART_IER_THRI))
+ serial8250_flush_tx(dev);
+}
+
+#define SYSRQ_PENDING_NONE 0
+
+static int sysrq_pending;
+
+static void serial8250__sysrq(struct kvm *kvm, struct serial8250_device *dev)
+{
+ dev->lsr |= UART_LSR_DR | UART_LSR_BI;
+ dev->rxbuf[dev->rxcnt++] = sysrq_pending;
+ sysrq_pending = SYSRQ_PENDING_NONE;
+}
+
+static void serial8250__receive(struct kvm *kvm, struct serial8250_device *dev,
+ bool handle_sysrq)
+{
+ int c;
+
+ /*
+ * If the guest transmitted a full fifo, we clear the
+ * TEMT/THRE bits to let the kernel escape from the 8250
+ * interrupt handler. We come here only once a ms, so that
+ * should give the kernel the desired pause. That also flushes
+ * the tx fifo to the terminal.
+ */
+ serial8250_flush_tx(dev);
+
+ if (dev->mcr & UART_MCR_LOOP)
+ return;
+
+ if ((dev->lsr & UART_LSR_DR) || dev->rxcnt)
+ return;
+
+ if (handle_sysrq && sysrq_pending) {
+ serial8250__sysrq(kvm, dev);
+ return;
+ }
+
+ while (term_readable(CONSOLE_8250, dev->id) &&
+ dev->rxcnt < FIFO_LEN) {
+
+ c = term_getc(CONSOLE_8250, dev->id);
+
+ if (c < 0)
+ break;
+ dev->rxbuf[dev->rxcnt++] = c;
+ dev->lsr |= UART_LSR_DR;
+ }
+}
+
+void serial8250__update_consoles(struct kvm *kvm)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ mutex_lock(&dev->mutex);
+
+ /* Restrict sysrq injection to the first port */
+ serial8250__receive(kvm, dev, i == 0);
+
+ serial8250_update_irq(kvm, dev);
+
+ mutex_unlock(&dev->mutex);
+ }
+}
+
+void serial8250__inject_sysrq(struct kvm *kvm, char sysrq)
+{
+ sysrq_pending = sysrq;
+}
+
+static struct serial8250_device *find_device(u16 port)
+{
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ if (dev->iobase == (port & ~0x7))
+ return dev;
+ }
+ return NULL;
+}
+
+static bool serial8250_out(struct ioport *ioport, struct kvm *kvm, u16 port,
+ void *data, int size)
+{
+ struct serial8250_device *dev;
+ u16 offset;
+ bool ret = true;
+ char *addr = data;
+
+ dev = find_device(port);
+ if (!dev)
+ return false;
+
+ mutex_lock(&dev->mutex);
+
+ offset = port - dev->iobase;
+
+ switch (offset) {
+ case UART_TX:
+ if (dev->lcr & UART_LCR_DLAB) {
+ dev->dll = ioport__read8(data);
+ break;
+ }
+
+ /* Loopback mode */
+ if (dev->mcr & UART_MCR_LOOP) {
+ if (dev->rxcnt < FIFO_LEN) {
+ dev->rxbuf[dev->rxcnt++] = *addr;
+ dev->lsr |= UART_LSR_DR;
+ }
+ break;
+ }
+
+ if (dev->txcnt < FIFO_LEN) {
+ dev->txbuf[dev->txcnt++] = *addr;
+ dev->lsr &= ~UART_LSR_TEMT;
+ if (dev->txcnt == FIFO_LEN / 2)
+ dev->lsr &= ~UART_LSR_THRE;
+ } else {
+ /* Should never happpen */
+ dev->lsr &= ~(UART_LSR_TEMT | UART_LSR_THRE);
+ }
+ break;
+ case UART_IER:
+ if (!(dev->lcr & UART_LCR_DLAB))
+ dev->ier = ioport__read8(data) & 0x0f;
+ else
+ dev->dlm = ioport__read8(data);
+ break;
+ case UART_FCR:
+ dev->fcr = ioport__read8(data);
+ break;
+ case UART_LCR:
+ dev->lcr = ioport__read8(data);
+ break;
+ case UART_MCR:
+ dev->mcr = ioport__read8(data);
+ break;
+ case UART_LSR:
+ /* Factory test */
+ break;
+ case UART_MSR:
+ /* Not used */
+ break;
+ case UART_SCR:
+ dev->scr = ioport__read8(data);
+ break;
+ default:
+ ret = false;
+ break;
+ }
+
+ serial8250_update_irq(kvm, dev);
+
+ mutex_unlock(&dev->mutex);
+
+ return ret;
+}
+
+static void serial8250_rx(struct serial8250_device *dev, void *data)
+{
+ if (dev->rxdone == dev->rxcnt)
+ return;
+
+ /* Break issued ? */
+ if (dev->lsr & UART_LSR_BI) {
+ dev->lsr &= ~UART_LSR_BI;
+ ioport__write8(data, 0);
+ return;
+ }
+
+ ioport__write8(data, dev->rxbuf[dev->rxdone++]);
+ if (dev->rxcnt == dev->rxdone) {
+ dev->lsr &= ~UART_LSR_DR;
+ dev->rxcnt = dev->rxdone = 0;
+ }
+}
+
+static bool serial8250_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ struct serial8250_device *dev;
+ u16 offset;
+ bool ret = true;
+
+ dev = find_device(port);
+ if (!dev)
+ return false;
+
+ mutex_lock(&dev->mutex);
+
+ offset = port - dev->iobase;
+
+ switch (offset) {
+ case UART_RX:
+ if (dev->lcr & UART_LCR_DLAB)
+ ioport__write8(data, dev->dll);
+ else
+ serial8250_rx(dev, data);
+ break;
+ case UART_IER:
+ if (dev->lcr & UART_LCR_DLAB)
+ ioport__write8(data, dev->dlm);
+ else
+ ioport__write8(data, dev->ier);
+ break;
+ case UART_IIR:
+ ioport__write8(data, dev->iir | UART_IIR_TYPE_BITS);
+ break;
+ case UART_LCR:
+ ioport__write8(data, dev->lcr);
+ break;
+ case UART_MCR:
+ ioport__write8(data, dev->mcr);
+ break;
+ case UART_LSR:
+ ioport__write8(data, dev->lsr);
+ break;
+ case UART_MSR:
+ ioport__write8(data, dev->msr);
+ break;
+ case UART_SCR:
+ ioport__write8(data, dev->scr);
+ break;
+ default:
+ ret = false;
+ break;
+ }
+
+ serial8250_update_irq(kvm, dev);
+
+ mutex_unlock(&dev->mutex);
+
+ return ret;
+}
+
+static struct ioport_operations serial8250_ops = {
+ .io_in = serial8250_in,
+ .io_out = serial8250_out,
+};
+
+static int serial8250__device_init(struct kvm *kvm, struct serial8250_device *dev)
+{
+ int r;
+
+ r = ioport__register(dev->iobase, &serial8250_ops, 8, NULL);
+ kvm__irq_line(kvm, dev->irq, 0);
+
+ return r;
+}
+
+int serial8250__init(struct kvm *kvm)
+{
+ unsigned int i, j;
+ int r = 0;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ r = serial8250__device_init(kvm, dev);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return r;
+cleanup:
+ for (j = 0; j <= i; j++) {
+ struct serial8250_device *dev = &devices[j];
+
+ ioport__unregister(dev->iobase);
+ }
+
+ return r;
+}
+
+int serial8250__exit(struct kvm *kvm)
+{
+ unsigned int i;
+ int r;
+
+ for (i = 0; i < ARRAY_SIZE(devices); i++) {
+ struct serial8250_device *dev = &devices[i];
+
+ r = ioport__unregister(dev->iobase);
+ if (r < 0)
+ return r;
+ }
+
+ return 0;
+}
--- /dev/null
+#include "kvm/vesa.h"
+
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/framebuffer.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+
+#include <linux/byteorder.h>
+#include <sys/mman.h>
+#include <linux/err.h>
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <inttypes.h>
+#include <unistd.h>
+
+static bool vesa_pci_io_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static bool vesa_pci_io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static struct ioport_operations vesa_io_ops = {
+ .io_in = vesa_pci_io_in,
+ .io_out = vesa_pci_io_out,
+};
+
+static struct pci_device_header vesa_pci_device = {
+ .vendor_id = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET),
+ .device_id = cpu_to_le16(PCI_DEVICE_ID_VESA),
+ .header_type = PCI_HEADER_TYPE_NORMAL,
+ .revision_id = 0,
+ .class[2] = 0x03,
+ .subsys_vendor_id = cpu_to_le16(PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET),
+ .subsys_id = cpu_to_le16(PCI_SUBSYSTEM_ID_VESA),
+ .bar[1] = cpu_to_le32(VESA_MEM_ADDR | PCI_BASE_ADDRESS_SPACE_MEMORY),
+ .bar_size[1] = VESA_MEM_SIZE,
+};
+
+static struct framebuffer vesafb;
+
+struct framebuffer *vesa__init(struct kvm *kvm)
+{
+ u16 vesa_base_addr;
+ u8 dev, line, pin;
+ char *mem;
+ int r;
+
+ r = irq__register_device(PCI_DEVICE_ID_VESA, &dev, &pin, &line);
+ if (r < 0)
+ return ERR_PTR(r);
+
+ r = ioport__register(IOPORT_EMPTY, &vesa_io_ops, IOPORT_SIZE, NULL);
+ if (r < 0)
+ return ERR_PTR(r);
+
+ vesa_pci_device.irq_pin = pin;
+ vesa_pci_device.irq_line = line;
+ vesa_base_addr = (u16)r;
+ vesa_pci_device.bar[0] = cpu_to_le32(vesa_base_addr | PCI_BASE_ADDRESS_SPACE_IO);
+ pci__register(&vesa_pci_device, dev);
+
+ mem = mmap(NULL, VESA_MEM_SIZE, PROT_RW, MAP_ANON_NORESERVE, -1, 0);
+ if (mem == MAP_FAILED)
+ ERR_PTR(-errno);
+
+ kvm__register_mem(kvm, VESA_MEM_ADDR, VESA_MEM_SIZE, mem);
+
+ vesafb = (struct framebuffer) {
+ .width = VESA_WIDTH,
+ .height = VESA_HEIGHT,
+ .depth = VESA_BPP,
+ .mem = mem,
+ .mem_addr = VESA_MEM_ADDR,
+ .mem_size = VESA_MEM_SIZE,
+ };
+ return fb__register(&vesafb);
+}
--- /dev/null
+#ifndef _KVM_ASM_HWEIGHT_H_
+#define _KVM_ASM_HWEIGHT_H_
+
+#include <linux/types.h>
+unsigned int hweight32(unsigned int w);
+unsigned long hweight64(__u64 w);
+
+#endif /* _KVM_ASM_HWEIGHT_H_ */
--- /dev/null
+#ifndef KVM_BIOS_MEMCPY_H
+#define KVM_BIOS_MEMCPY_H
+
+#include <linux/types.h>
+#include <stddef.h>
+
+void memcpy16(u16 dst_seg, void *dst, u16 src_seg, const void *src, size_t len);
+
+#endif /* KVM_BIOS_MEMCPY_H */
--- /dev/null
+#ifndef KVM__8250_SERIAL_H
+#define KVM__8250_SERIAL_H
+
+struct kvm;
+
+int serial8250__init(struct kvm *kvm);
+int serial8250__exit(struct kvm *kvm);
+void serial8250__update_consoles(struct kvm *kvm);
+void serial8250__inject_sysrq(struct kvm *kvm, char sysrq);
+
+#endif /* KVM__8250_SERIAL_H */
--- /dev/null
+#ifndef KVM_APIC_H_
+#define KVM_APIC_H_
+
+#include <asm/apicdef.h>
+
+/*
+ * APIC, IOAPIC stuff
+ */
+#define APIC_BASE_ADDR_STEP 0x00400000
+#define IOAPIC_BASE_ADDR_STEP 0x00100000
+
+#define APIC_ADDR(apic) (APIC_DEFAULT_PHYS_BASE + apic * APIC_BASE_ADDR_STEP)
+#define IOAPIC_ADDR(ioapic) (IO_APIC_DEFAULT_PHYS_BASE + ioapic * IOAPIC_BASE_ADDR_STEP)
+
+#define KVM_APIC_VERSION 0x14 /* xAPIC */
+
+#endif /* KVM_APIC_H_ */
--- /dev/null
+#ifndef KVM__BRLOCK_H
+#define KVM__BRLOCK_H
+
+#include "kvm/kvm.h"
+#include "kvm/barrier.h"
+
+/*
+ * brlock is a lock which is very cheap for reads, but very expensive
+ * for writes.
+ * This lock will be used when updates are very rare and reads are common.
+ * This lock is currently implemented by stopping the guest while
+ * performing the updates. We assume that the only threads whichread from
+ * the locked data are VCPU threads, and the only writer isn't a VCPU thread.
+ */
+
+#ifndef barrier
+#define barrier() __asm__ __volatile__("": : :"memory")
+#endif
+
+#ifdef KVM_BRLOCK_DEBUG
+
+#include "kvm/rwsem.h"
+
+DECLARE_RWSEM(brlock_sem);
+
+#define br_read_lock() down_read(&brlock_sem);
+#define br_read_unlock() up_read(&brlock_sem);
+
+#define br_write_lock() down_write(&brlock_sem);
+#define br_write_unlock() up_write(&brlock_sem);
+
+#else
+
+#define br_read_lock() barrier()
+#define br_read_unlock() barrier()
+
+#define br_write_lock() kvm__pause()
+#define br_write_unlock() kvm__continue()
+#endif
+
+#endif
--- /dev/null
+#ifndef KVM__BALLOON_H
+#define KVM__BALLOON_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_balloon(int argc, const char **argv, const char *prefix);
+void kvm_balloon_help(void) NORETURN;
+
+#endif
--- /dev/null
+#ifndef KVM__DEBUG_H
+#define KVM__DEBUG_H
+
+#include <kvm/util.h>
+#include <linux/types.h>
+
+#define KVM_DEBUG_CMD_TYPE_DUMP (1 << 0)
+#define KVM_DEBUG_CMD_TYPE_NMI (1 << 1)
+#define KVM_DEBUG_CMD_TYPE_SYSRQ (1 << 2)
+
+struct debug_cmd_params {
+ u32 dbg_type;
+ u32 cpu;
+ char sysrq;
+};
+
+int kvm_cmd_debug(int argc, const char **argv, const char *prefix);
+void kvm_debug_help(void) NORETURN;
+
+#endif
--- /dev/null
+#ifndef __KVM_HELP_H__
+#define __KVM_HELP_H__
+
+int kvm_cmd_help(int argc, const char **argv, const char *prefix);
+
+#endif
--- /dev/null
+#ifndef KVM__LIST_H
+#define KVM__LIST_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_list(int argc, const char **argv, const char *prefix);
+void kvm_list_help(void) NORETURN;
+int get_vmstate(int sock);
+
+#endif
--- /dev/null
+#ifndef KVM__PAUSE_H
+#define KVM__PAUSE_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_pause(int argc, const char **argv, const char *prefix);
+void kvm_pause_help(void) NORETURN;
+
+#endif
--- /dev/null
+#ifndef KVM__RESUME_H
+#define KVM__RESUME_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_resume(int argc, const char **argv, const char *prefix);
+void kvm_resume_help(void) NORETURN;
+
+#endif
--- /dev/null
+#ifndef __KVM_RUN_H__
+#define __KVM_RUN_H__
+
+#include <kvm/util.h>
+
+int kvm_cmd_run(int argc, const char **argv, const char *prefix);
+void kvm_run_help(void) NORETURN;
+
+void kvm_run_set_wrapper_sandbox(void);
+
+#endif
--- /dev/null
+#ifndef KVM__SANDBOX_H
+#define KVM__SANDBOX_H
+
+int kvm_cmd_sandbox(int argc, const char **argv, const char *prefix);
+
+#endif
--- /dev/null
+#ifndef KVM__SETUP_H
+#define KVM__SETUP_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_setup(int argc, const char **argv, const char *prefix);
+void kvm_setup_help(void) NORETURN;
+int kvm_setup_create_new(const char *guestfs_name);
+void kvm_setup_resolv(const char *guestfs_name);
+
+#endif
--- /dev/null
+#ifndef KVM__STAT_H
+#define KVM__STAT_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_stat(int argc, const char **argv, const char *prefix);
+void kvm_stat_help(void) NORETURN;
+
+#endif
--- /dev/null
+#ifndef KVM__STOP_H
+#define KVM__STOP_H
+
+#include <kvm/util.h>
+
+int kvm_cmd_stop(int argc, const char **argv, const char *prefix);
+void kvm_stop_help(void) NORETURN;
+
+#endif
--- /dev/null
+#ifndef KVM__VERSION_H
+#define KVM__VERSION_H
+
+int kvm_cmd_version(int argc, const char **argv, const char *prefix);
+
+#endif
--- /dev/null
+#ifndef KVM_COMPILER_H_
+#define KVM_COMPILER_H_
+
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
+#define notrace __attribute__((no_instrument_function))
+
+#endif /* KVM_COMPILER_H_ */
--- /dev/null
+#ifndef KVM__DISK_IMAGE_H
+#define KVM__DISK_IMAGE_H
+
+#include "kvm/read-write.h"
+#include "kvm/util.h"
+
+#include <linux/types.h>
+#include <linux/fs.h> /* for BLKGETSIZE64 */
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <sys/uio.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+#define SECTOR_SHIFT 9
+#define SECTOR_SIZE (1UL << SECTOR_SHIFT)
+
+enum {
+ DISK_IMAGE_REGULAR,
+ DISK_IMAGE_MMAP,
+};
+
+#define MAX_DISK_IMAGES 4
+
+struct disk_image;
+
+struct disk_image_operations {
+ ssize_t (*read)(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ ssize_t (*write)(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ int (*flush)(struct disk_image *disk);
+ int (*close)(struct disk_image *disk);
+};
+
+struct disk_image_params {
+ const char *filename;
+ /*
+ * wwpn == World Wide Port Number
+ * tpgt == Target Portal Group Tag
+ */
+ const char *wwpn;
+ const char *tpgt;
+ bool readonly;
+ bool direct;
+};
+
+struct disk_image {
+ int fd;
+ u64 size;
+ struct disk_image_operations *ops;
+ void *priv;
+ void *disk_req_cb_param;
+ void (*disk_req_cb)(void *param, long len);
+ bool async;
+ int evt;
+#ifdef CONFIG_HAS_AIO
+ io_context_t ctx;
+#endif
+ const char *wwpn;
+ const char *tpgt;
+};
+
+struct disk_image *disk_image__open(const char *filename, bool readonly, bool direct);
+struct disk_image **disk_image__open_all(struct disk_image_params *params, int count);
+struct disk_image *disk_image__new(int fd, u64 size, struct disk_image_operations *ops, int mmap);
+int disk_image__close(struct disk_image *disk);
+int disk_image__close_all(struct disk_image **disks, int count);
+int disk_image__flush(struct disk_image *disk);
+ssize_t disk_image__read(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ssize_t disk_image__write(struct disk_image *disk, u64 sector, const struct iovec *iov,
+ int iovcount, void *param);
+ssize_t disk_image__get_serial(struct disk_image *disk, void *buffer, ssize_t *len);
+
+struct disk_image *raw_image__probe(int fd, struct stat *st, bool readonly);
+struct disk_image *blkdev__probe(const char *filename, int flags, struct stat *st);
+
+ssize_t raw_image__read(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__write(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__read_mmap(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+ssize_t raw_image__write_mmap(struct disk_image *disk, u64 sector,
+ const struct iovec *iov, int iovcount, void *param);
+int raw_image__close(struct disk_image *disk);
+void disk_image__set_callback(struct disk_image *disk, void (*disk_req_cb)(void *param, long len));
+#endif /* KVM__DISK_IMAGE_H */
--- /dev/null
+#ifndef KVM_E820_H
+#define KVM_E820_H
+
+#include <linux/types.h>
+#include <kvm/bios.h>
+
+#define SMAP 0x534d4150 /* ASCII "SMAP" */
+
+struct biosregs;
+
+extern bioscall void e820_query_map(struct biosregs *regs);
+
+#endif /* KVM_E820_H */
--- /dev/null
+#ifndef KVM__FRAMEBUFFER_H
+#define KVM__FRAMEBUFFER_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+struct framebuffer;
+
+struct fb_target_operations {
+ int (*start)(struct framebuffer *fb);
+ int (*stop)(struct framebuffer *fb);
+};
+
+#define FB_MAX_TARGETS 2
+
+struct framebuffer {
+ struct list_head node;
+
+ u32 width;
+ u32 height;
+ u8 depth;
+ char *mem;
+ u64 mem_addr;
+ u64 mem_size;
+
+ unsigned long nr_targets;
+ struct fb_target_operations *targets[FB_MAX_TARGETS];
+};
+
+struct framebuffer *fb__register(struct framebuffer *fb);
+int fb__attach(struct framebuffer *fb, struct fb_target_operations *ops);
+int fb__start(void);
+void fb__stop(void);
+
+#endif /* KVM__FRAMEBUFFER_H */
--- /dev/null
+#ifndef KVM__GUEST_COMPAT_H
+#define KVM__GUEST_COMPAT_H
+
+int compat__print_all_messages(void);
+int compat__remove_message(int id);
+int compat__add_message(const char *title, const char *description);
+
+
+#endif
\ No newline at end of file
--- /dev/null
+#ifndef KVM__PCKBD_H
+#define KVM__PCKBD_H
+
+#include <linux/types.h>
+
+struct kvm;
+
+void mouse_queue(u8 c);
+void kbd_queue(u8 c);
+void kbd__init(struct kvm *kvm);
+
+#endif
--- /dev/null
+#ifndef KVM__IOEVENTFD_H
+#define KVM__IOEVENTFD_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <sys/eventfd.h>
+#include "kvm/util.h"
+
+struct kvm;
+
+struct ioevent {
+ u64 io_addr;
+ u8 io_len;
+ void (*fn)(struct kvm *kvm, void *ptr);
+ struct kvm *fn_kvm;
+ void *fn_ptr;
+ int fd;
+ u64 datamatch;
+
+ struct list_head list;
+};
+
+int ioeventfd__init(struct kvm *kvm);
+int ioeventfd__exit(struct kvm *kvm);
+int ioeventfd__add_event(struct ioevent *ioevent, bool is_pio, bool poll_in_userspace);
+int ioeventfd__del_event(u64 addr, u64 datamatch);
+
+#endif
--- /dev/null
+#ifndef KVM__IOPORT_H
+#define KVM__IOPORT_H
+
+#include "kvm/rbtree-interval.h"
+
+#include <stdbool.h>
+#include <limits.h>
+#include <asm/types.h>
+#include <linux/types.h>
+#include <linux/byteorder.h>
+
+/* some ports we reserve for own use */
+#define IOPORT_DBG 0xe0
+#define IOPORT_START 0x6200
+#define IOPORT_SIZE 0x400
+
+#define IOPORT_EMPTY USHRT_MAX
+
+struct kvm;
+
+struct ioport {
+ struct rb_int_node node;
+ struct ioport_operations *ops;
+ void *priv;
+};
+
+struct ioport_operations {
+ bool (*io_in)(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size);
+ bool (*io_out)(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size);
+};
+
+void ioport__setup_arch(void);
+
+int ioport__register(u16 port, struct ioport_operations *ops, int count, void *param);
+int ioport__unregister(u16 port);
+int ioport__init(struct kvm *kvm);
+int ioport__exit(struct kvm *kvm);
+
+static inline u8 ioport__read8(u8 *data)
+{
+ return *data;
+}
+/* On BE platforms, PCI I/O is byteswapped, i.e. LE, so swap back. */
+static inline u16 ioport__read16(u16 *data)
+{
+ return le16_to_cpu(*data);
+}
+
+static inline u32 ioport__read32(u32 *data)
+{
+ return le32_to_cpu(*data);
+}
+
+static inline void ioport__write8(u8 *data, u8 value)
+{
+ *data = value;
+}
+
+static inline void ioport__write16(u16 *data, u16 value)
+{
+ *data = cpu_to_le16(value);
+}
+
+static inline void ioport__write32(u32 *data, u32 value)
+{
+ *data = cpu_to_le32(value);
+}
+
+#endif /* KVM__IOPORT_H */
--- /dev/null
+#ifndef KVM__IRQ_H
+#define KVM__IRQ_H
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/kvm.h>
+
+#include "kvm/msi.h"
+
+struct kvm;
+
+struct irq_line {
+ u8 line;
+ struct list_head node;
+};
+
+struct pci_dev {
+ struct rb_node node;
+ u32 id;
+ u8 pin;
+ struct list_head lines;
+};
+
+int irq__register_device(u32 dev, u8 *num, u8 *pin, u8 *line);
+
+struct rb_node *irq__get_pci_tree(void);
+
+int irq__init(struct kvm *kvm);
+int irq__exit(struct kvm *kvm);
+int irq__add_msix_route(struct kvm *kvm, struct msi_msg *msg);
+
+#endif
--- /dev/null
+#ifndef __KVM_CMD_H__
+#define __KVM_CMD_H__
+
+struct cmd_struct {
+ const char *cmd;
+ int (*fn)(int, const char **, const char *);
+ void (*help)(void);
+ int option;
+};
+
+extern struct cmd_struct kvm_commands[];
+struct cmd_struct *kvm_get_command(struct cmd_struct *command,
+ const char *cmd);
+
+int handle_command(struct cmd_struct *command, int argc, const char **argv);
+
+#endif
--- /dev/null
+#ifndef KVM__KVM_CPU_H
+#define KVM__KVM_CPU_H
+
+#include "kvm/kvm-cpu-arch.h"
+#include <stdbool.h>
+
+struct kvm_cpu *kvm_cpu__init(struct kvm *kvm, unsigned long cpu_id);
+void kvm_cpu__delete(struct kvm_cpu *vcpu);
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu);
+void kvm_cpu__setup_cpuid(struct kvm_cpu *vcpu);
+void kvm_cpu__enable_singlestep(struct kvm_cpu *vcpu);
+void kvm_cpu__run(struct kvm_cpu *vcpu);
+void kvm_cpu__reboot(void);
+int kvm_cpu__start(struct kvm_cpu *cpu);
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu);
+
+int kvm_cpu__get_debug_fd(void);
+void kvm_cpu__set_debug_fd(int fd);
+void kvm_cpu__show_code(struct kvm_cpu *vcpu);
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu);
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu);
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu);
+
+#endif /* KVM__KVM_CPU_H */
--- /dev/null
+#ifndef KVM__IPC_H_
+#define KVM__IPC_H_
+
+#include <linux/types.h>
+
+enum {
+ KVM_IPC_BALLOON = 1,
+ KVM_IPC_DEBUG = 2,
+ KVM_IPC_STAT = 3,
+ KVM_IPC_PAUSE = 4,
+ KVM_IPC_RESUME = 5,
+ KVM_IPC_STOP = 6,
+ KVM_IPC_PID = 7,
+ KVM_IPC_VMSTATE = 8,
+};
+
+int kvm_ipc__register_handler(u32 type, void (*cb)(int fd, u32 type, u32 len, u8 *msg));
+int kvm_ipc__start(int sock);
+int kvm_ipc__stop(void);
+
+int kvm_ipc__send(int fd, u32 type);
+int kvm_ipc__send_msg(int fd, u32 type, u32 len, u8 *msg);
+
+#endif
--- /dev/null
+#ifndef KVM__KVM_H
+#define KVM__KVM_H
+
+#include "kvm/kvm-arch.h"
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <time.h>
+#include <signal.h>
+
+#define SIGKVMEXIT (SIGRTMIN + 0)
+#define SIGKVMPAUSE (SIGRTMIN + 1)
+
+#define KVM_PID_FILE_PATH "/.lkvm/"
+#define HOME_DIR getenv("HOME")
+#define KVM_BINARY_NAME "lkvm"
+
+#define PAGE_SIZE (sysconf(_SC_PAGE_SIZE))
+
+#define DEFINE_KVM_EXT(ext) \
+ .name = #ext, \
+ .code = ext
+
+enum {
+ KVM_VMSTATE_RUNNING,
+ KVM_VMSTATE_PAUSED,
+};
+
+struct kvm_ext {
+ const char *name;
+ int code;
+};
+
+void kvm__set_dir(const char *fmt, ...);
+const char *kvm__get_dir(void);
+
+struct kvm *kvm__init(const char *kvm_dev, const char *hugetlbfs_path, u64 ram_size, const char *name);
+int kvm__recommended_cpus(struct kvm *kvm);
+int kvm__max_cpus(struct kvm *kvm);
+void kvm__init_ram(struct kvm *kvm);
+int kvm__exit(struct kvm *kvm);
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename);
+bool kvm__load_kernel(struct kvm *kvm, const char *kernel_filename,
+ const char *initrd_filename, const char *kernel_cmdline, u16 vidmode);
+void kvm__start_timer(struct kvm *kvm);
+void kvm__stop_timer(struct kvm *kvm);
+void kvm__irq_line(struct kvm *kvm, int irq, int level);
+void kvm__irq_trigger(struct kvm *kvm, int irq);
+bool kvm__emulate_io(struct kvm *kvm, u16 port, void *data, int direction, int size, u32 count);
+bool kvm__emulate_mmio(struct kvm *kvm, u64 phys_addr, u8 *data, u32 len, u8 is_write);
+int kvm__register_mem(struct kvm *kvm, u64 guest_phys, u64 size, void *userspace_addr);
+int kvm__register_mmio(struct kvm *kvm, u64 phys_addr, u64 phys_addr_len, bool coalesce,
+ void (*mmio_fn)(u64 addr, u8 *data, u32 len, u8 is_write, void *ptr),
+ void *ptr);
+bool kvm__deregister_mmio(struct kvm *kvm, u64 phys_addr);
+void kvm__pause(void);
+void kvm__continue(void);
+void kvm__notify_paused(void);
+int kvm__get_sock_by_instance(const char *name);
+int kvm__enumerate_instances(int (*callback)(const char *name, int pid));
+void kvm__remove_socket(const char *name);
+
+void kvm__arch_set_cmdline(char *cmdline, bool video);
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size);
+void kvm__arch_delete_ram(struct kvm *kvm);
+int kvm__arch_setup_firmware(struct kvm *kvm);
+int kvm__arch_free_firmware(struct kvm *kvm);
+bool kvm__arch_cpu_supports_vm(void);
+void kvm__arch_periodic_poll(struct kvm *kvm);
+
+int load_flat_binary(struct kvm *kvm, int fd_kernel, int fd_initrd, const char *kernel_cmdline);
+bool load_bzimage(struct kvm *kvm, int fd_kernel, int fd_initrd, const char *kernel_cmdline, u16 vidmode);
+
+/*
+ * Debugging
+ */
+void kvm__dump_mem(struct kvm *kvm, unsigned long addr, unsigned long size);
+
+extern const char *kvm_exit_reasons[];
+
+static inline bool host_ptr_in_ram(struct kvm *kvm, void *p)
+{
+ return kvm->ram_start <= p && p < (kvm->ram_start + kvm->ram_size);
+}
+
+static inline void *guest_flat_to_host(struct kvm *kvm, unsigned long offset)
+{
+ return kvm->ram_start + offset;
+}
+
+bool kvm__supports_extension(struct kvm *kvm, unsigned int extension);
+
+#endif /* KVM__KVM_H */
--- /dev/null
+#ifndef LKVM_MSI_H
+#define LKVM_MSI_H
+
+struct msi_msg {
+ u32 address_lo; /* low 32 bits of msi message address */
+ u32 address_hi; /* high 32 bits of msi message address */
+ u32 data; /* 16 bits of msi message data */
+};
+
+#endif /* LKVM_MSI_H */
--- /dev/null
+#ifndef KVM__MUTEX_H
+#define KVM__MUTEX_H
+
+#include <pthread.h>
+
+#include "kvm/util.h"
+
+/*
+ * Kernel-alike mutex API - to make it easier for kernel developers
+ * to write user-space code! :-)
+ */
+
+#define DEFINE_MUTEX(mutex) pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER
+
+static inline void mutex_init(pthread_mutex_t *mutex)
+{
+ if (pthread_mutex_init(mutex, NULL) != 0)
+ die("unexpected pthread_mutex_init() failure!");
+}
+
+static inline void mutex_lock(pthread_mutex_t *mutex)
+{
+ if (pthread_mutex_lock(mutex) != 0)
+ die("unexpected pthread_mutex_lock() failure!");
+}
+
+static inline void mutex_unlock(pthread_mutex_t *mutex)
+{
+ if (pthread_mutex_unlock(mutex) != 0)
+ die("unexpected pthread_mutex_unlock() failure!");
+}
+
+#endif /* KVM__MUTEX_H */
--- /dev/null
+#ifndef __PARSE_OPTIONS_H__
+#define __PARSE_OPTIONS_H__
+
+#include <inttypes.h>
+#include <kvm/util.h>
+
+enum parse_opt_type {
+ /* special types */
+ OPTION_END,
+ OPTION_ARGUMENT,
+ OPTION_GROUP,
+ /* options with no arguments */
+ OPTION_BIT,
+ OPTION_BOOLEAN,
+ OPTION_INCR,
+ OPTION_SET_UINT,
+ OPTION_SET_PTR,
+ /* options with arguments (usually) */
+ OPTION_STRING,
+ OPTION_INTEGER,
+ OPTION_LONG,
+ OPTION_CALLBACK,
+ OPTION_U64,
+ OPTION_UINTEGER,
+};
+
+enum parse_opt_flags {
+ PARSE_OPT_KEEP_DASHDASH = 1,
+ PARSE_OPT_STOP_AT_NON_OPTION = 2,
+ PARSE_OPT_KEEP_ARGV0 = 4,
+ PARSE_OPT_KEEP_UNKNOWN = 8,
+ PARSE_OPT_NO_INTERNAL_HELP = 16,
+};
+
+enum parse_opt_option_flags {
+ PARSE_OPT_OPTARG = 1,
+ PARSE_OPT_NOARG = 2,
+ PARSE_OPT_NONEG = 4,
+ PARSE_OPT_HIDDEN = 8,
+ PARSE_OPT_LASTARG_DEFAULT = 16,
+};
+
+struct option;
+typedef int parse_opt_cb(const struct option *, const char *arg, int unset);
+/*
+ * `type`::
+ * holds the type of the option, you must have an OPTION_END last in your
+ * array.
+ *
+ * `short_name`::
+ * the character to use as a short option name, '\0' if none.
+ *
+ * `long_name`::
+ * the long option name, without the leading dashes, NULL if none.
+ *
+ * `value`::
+ * stores pointers to the values to be filled.
+ *
+ * `argh`::
+ * token to explain the kind of argument this option wants. Keep it
+ * homogenous across the repository.
+ *
+ * `help`::
+ * the short help associated to what the option does.
+ * Must never be NULL (except for OPTION_END).
+ * OPTION_GROUP uses this pointer to store the group header.
+ *
+ * `flags`::
+ * mask of parse_opt_option_flags.
+ * PARSE_OPT_OPTARG: says that the argument is optionnal (not for BOOLEANs)
+ * PARSE_OPT_NOARG: says that this option takes no argument, for CALLBACKs
+ * PARSE_OPT_NONEG: says that this option cannot be negated
+ * PARSE_OPT_HIDDEN this option is skipped in the default usage, showed in
+ * the long one.
+ *
+ * `callback`::
+ * pointer to the callback to use for OPTION_CALLBACK.
+ *
+ * `defval`::
+ * default value to fill (*->value) with for PARSE_OPT_OPTARG.
+ * OPTION_{BIT,SET_UINT,SET_PTR} store the {mask,integer,pointer} to put in
+ * the value when met.
+ * CALLBACKS can use it like they want.
+ */
+struct option {
+enum parse_opt_type type;
+int short_name;
+const char *long_name;
+void *value;
+const char *argh;
+const char *help;
+
+int flags;
+parse_opt_cb *callback;
+intptr_t defval;
+};
+
+#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
+#define check_vtype(v, type) \
+ (BUILD_BUG_ON_ZERO(!__builtin_types_compatible_p(typeof(v), type)) + v)
+
+#define OPT_INTEGER(s, l, v, h) \
+{ \
+ .type = OPTION_INTEGER, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, int *), \
+ .help = (h) \
+}
+
+#define OPT_U64(s, l, v, h) \
+{ \
+ .type = OPTION_U64, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, u64 *), \
+ .help = (h) \
+}
+
+#define OPT_STRING(s, l, v, a, h) \
+{ \
+ .type = OPTION_STRING, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, const char **), (a), \
+ .help = (h) \
+}
+
+#define OPT_BOOLEAN(s, l, v, h) \
+{ \
+ .type = OPTION_BOOLEAN, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, bool *), \
+ .help = (h) \
+}
+
+#define OPT_INCR(s, l, v, h) \
+{ \
+ .type = OPTION_INCR, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = check_vtype(v, int *), \
+ .help = (h) \
+}
+
+#define OPT_GROUP(h) \
+{ \
+ .type = OPTION_GROUP, \
+ .help = (h) \
+}
+
+#define OPT_CALLBACK(s, l, v, a, h, f) \
+{ \
+ .type = OPTION_CALLBACK, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = (v), \
+ (a), \
+ .help = (h), \
+ .callback = (f) \
+}
+
+#define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
+{ \
+ .type = OPTION_CALLBACK, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = (v), \
+ (a), \
+ .help = (h), \
+ .callback = (f), \
+ .flags = PARSE_OPT_NOARG \
+}
+
+#define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
+{ \
+ .type = OPTION_CALLBACK, \
+ .short_name = (s), \
+ .long_name = (l), \
+ .value = (v), (a), \
+ .help = (h), \
+ .callback = (f), \
+ .defval = (intptr_t)d, \
+ .flags = PARSE_OPT_LASTARG_DEFAULT \
+}
+
+#define OPT_END() { .type = OPTION_END }
+
+enum {
+ PARSE_OPT_HELP = -1,
+ PARSE_OPT_DONE,
+ PARSE_OPT_UNKNOWN,
+};
+
+/*
+ * It's okay for the caller to consume argv/argc in the usual way.
+ * Other fields of that structure are private to parse-options and should not
+ * be modified in any way.
+ **/
+struct parse_opt_ctx_t {
+ const char **argv;
+ const char **out;
+ int argc, cpidx;
+ const char *opt;
+ int flags;
+};
+
+/* global functions */
+void usage_with_options(const char * const *usagestr,
+ const struct option *opts) NORETURN;
+int parse_options(int argc, const char **argv, const struct option *options,
+ const char * const usagestr[], int flags);
+#endif
--- /dev/null
+#ifndef KVM__PCI_SHMEM_H
+#define KVM__PCI_SHMEM_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+#define SHMEM_DEFAULT_SIZE (16 << MB_SHIFT)
+#define SHMEM_DEFAULT_ADDR (0xc8000000)
+#define SHMEM_DEFAULT_HANDLE "/kvm_shmem"
+
+struct kvm;
+struct shmem_info;
+
+struct shmem_info {
+ u64 phys_addr;
+ u64 size;
+ char *handle;
+ int create;
+};
+
+int pci_shmem__init(struct kvm *self);
+int pci_shmem__register_mem(struct shmem_info *si);
+
+int pci_shmem__get_local_irqfd(struct kvm *kvm);
+int pci_shmem__add_client(struct kvm *kvm, u32 id, int fd);
+int pci_shmem__remove_client(struct kvm *kvm, u32 id);
+
+#endif
--- /dev/null
+#ifndef KVM__PCI_H
+#define KVM__PCI_H
+
+#include <linux/types.h>
+#include <linux/kvm.h>
+#include <linux/pci_regs.h>
+#include <endian.h>
+
+#include "kvm/kvm.h"
+#include "kvm/msi.h"
+
+#define PCI_MAX_DEVICES 256
+/*
+ * PCI Configuration Mechanism #1 I/O ports. See Section 3.7.4.1.
+ * ("Configuration Mechanism #1") of the PCI Local Bus Specification 2.1 for
+ * details.
+ */
+#define PCI_CONFIG_ADDRESS 0xcf8
+#define PCI_CONFIG_DATA 0xcfc
+#define PCI_CONFIG_BUS_FORWARD 0xcfa
+#define PCI_IO_SIZE 0x100
+
+union pci_config_address {
+ struct {
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+ unsigned reg_offset : 2; /* 1 .. 0 */
+ unsigned register_number : 6; /* 7 .. 2 */
+ unsigned function_number : 3; /* 10 .. 8 */
+ unsigned device_number : 5; /* 15 .. 11 */
+ unsigned bus_number : 8; /* 23 .. 16 */
+ unsigned reserved : 7; /* 30 .. 24 */
+ unsigned enable_bit : 1; /* 31 */
+#else
+ unsigned enable_bit : 1; /* 31 */
+ unsigned reserved : 7; /* 30 .. 24 */
+ unsigned bus_number : 8; /* 23 .. 16 */
+ unsigned device_number : 5; /* 15 .. 11 */
+ unsigned function_number : 3; /* 10 .. 8 */
+ unsigned register_number : 6; /* 7 .. 2 */
+ unsigned reg_offset : 2; /* 1 .. 0 */
+#endif
+ };
+ u32 w;
+};
+
+struct msix_table {
+ struct msi_msg msg;
+ u32 ctrl;
+};
+
+struct msix_cap {
+ u8 cap;
+ u8 next;
+ u16 ctrl;
+ u32 table_offset;
+ u32 pba_offset;
+};
+
+struct pci_device_header {
+ u16 vendor_id;
+ u16 device_id;
+ u16 command;
+ u16 status;
+ u8 revision_id;
+ u8 class[3];
+ u8 cacheline_size;
+ u8 latency_timer;
+ u8 header_type;
+ u8 bist;
+ u32 bar[6];
+ u32 card_bus;
+ u16 subsys_vendor_id;
+ u16 subsys_id;
+ u32 exp_rom_bar;
+ u8 capabilities;
+ u8 reserved1[3];
+ u32 reserved2;
+ u8 irq_line;
+ u8 irq_pin;
+ u8 min_gnt;
+ u8 max_lat;
+ struct msix_cap msix;
+ u8 empty[136]; /* Rest of PCI config space */
+ u32 bar_size[6];
+} __attribute__((packed));
+
+int pci__init(struct kvm *kvm);
+int pci__exit(struct kvm *kvm);
+int pci__register(struct pci_device_header *dev, u8 dev_num);
+struct pci_device_header *pci__find_dev(u8 dev_num);
+u32 pci_get_io_space_block(u32 size);
+void pci__config_wr(struct kvm *kvm, union pci_config_address addr, void *data, int size);
+void pci__config_rd(struct kvm *kvm, union pci_config_address addr, void *data, int size);
+
+#endif /* KVM__PCI_H */
--- /dev/null
+#ifndef KVM__QCOW_H
+#define KVM__QCOW_H
+
+#include "kvm/mutex.h"
+
+#include <linux/types.h>
+#include <stdbool.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+
+#define QCOW_MAGIC (('Q' << 24) | ('F' << 16) | ('I' << 8) | 0xfb)
+
+#define QCOW1_VERSION 1
+#define QCOW2_VERSION 2
+
+#define QCOW1_OFLAG_COMPRESSED (1ULL << 63)
+
+#define QCOW2_OFLAG_COPIED (1ULL << 63)
+#define QCOW2_OFLAG_COMPRESSED (1ULL << 62)
+
+#define QCOW2_OFLAGS_MASK (QCOW2_OFLAG_COPIED|QCOW2_OFLAG_COMPRESSED)
+
+#define QCOW2_OFFSET_MASK (~QCOW2_OFLAGS_MASK)
+
+#define MAX_CACHE_NODES 32
+
+struct qcow_l2_table {
+ u64 offset;
+ struct rb_node node;
+ struct list_head list;
+ u8 dirty;
+ u64 table[];
+};
+
+struct qcow_l1_table {
+ u32 table_size;
+ u64 *l1_table;
+
+ /* Level2 caching data structures */
+ struct rb_root root;
+ struct list_head lru_list;
+ int nr_cached;
+};
+
+#define QCOW_REFCOUNT_BLOCK_SHIFT 1
+
+struct qcow_refcount_block {
+ u64 offset;
+ struct rb_node node;
+ struct list_head list;
+ u64 size;
+ u8 dirty;
+ u16 entries[];
+};
+
+struct qcow_refcount_table {
+ u32 rf_size;
+ u64 *rf_table;
+
+ /* Refcount block caching data structures */
+ struct rb_root root;
+ struct list_head lru_list;
+ int nr_cached;
+};
+
+struct qcow_header {
+ u64 size; /* in bytes */
+ u64 l1_table_offset;
+ u32 l1_size;
+ u8 cluster_bits;
+ u8 l2_bits;
+ u64 refcount_table_offset;
+ u32 refcount_table_size;
+};
+
+struct qcow {
+ pthread_mutex_t mutex;
+ struct qcow_header *header;
+ struct qcow_l1_table table;
+ struct qcow_refcount_table refcount_table;
+ int fd;
+ int csize_shift;
+ int csize_mask;
+ u32 version;
+ u64 cluster_size;
+ u64 cluster_offset_mask;
+ u64 free_clust_idx;
+ void *cluster_cache;
+ void *cluster_data;
+ void *copy_buff;
+};
+
+struct qcow1_header_disk {
+ u32 magic;
+ u32 version;
+
+ u64 backing_file_offset;
+ u32 backing_file_size;
+ u32 mtime;
+
+ u64 size; /* in bytes */
+
+ u8 cluster_bits;
+ u8 l2_bits;
+ u32 crypt_method;
+
+ u64 l1_table_offset;
+};
+
+struct qcow2_header_disk {
+ u32 magic;
+ u32 version;
+
+ u64 backing_file_offset;
+ u32 backing_file_size;
+
+ u32 cluster_bits;
+ u64 size; /* in bytes */
+ u32 crypt_method;
+
+ u32 l1_size;
+ u64 l1_table_offset;
+
+ u64 refcount_table_offset;
+ u32 refcount_table_clusters;
+
+ u32 nb_snapshots;
+ u64 snapshots_offset;
+};
+
+struct disk_image *qcow_probe(int fd, bool readonly);
+
+#endif /* KVM__QCOW_H */
--- /dev/null
+#ifndef KVM__INTERVAL_RBTREE_H
+#define KVM__INTERVAL_RBTREE_H
+
+#include <linux/rbtree.h>
+#include <linux/types.h>
+
+#define RB_INT_INIT(l, h) (struct rb_int_node){.low = l, .high = h}
+#define rb_int(n) rb_entry(n, struct rb_int_node, node)
+
+struct rb_int_node {
+ struct rb_node node;
+ u64 low;
+ u64 high;
+
+ /* max_high will store the highest high of it's 2 children. */
+ u64 max_high;
+};
+
+/* Return the rb_int_node interval in which 'point' is located. */
+struct rb_int_node *rb_int_search_single(struct rb_root *root, u64 point);
+
+/* Return the rb_int_node in which start:len is located. */
+struct rb_int_node *rb_int_search_range(struct rb_root *root, u64 low, u64 high);
+
+int rb_int_insert(struct rb_root *root, struct rb_int_node *data);
+void rb_int_erase(struct rb_root *root, struct rb_int_node *node);
+
+#endif
--- /dev/null
+#ifndef KVM_READ_WRITE_H
+#define KVM_READ_WRITE_H
+
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+
+#ifdef CONFIG_HAS_AIO
+#include <libaio.h>
+#endif
+
+ssize_t xread(int fd, void *buf, size_t count);
+ssize_t xwrite(int fd, const void *buf, size_t count);
+
+ssize_t read_in_full(int fd, void *buf, size_t count);
+ssize_t write_in_full(int fd, const void *buf, size_t count);
+
+ssize_t xpread(int fd, void *buf, size_t count, off_t offset);
+ssize_t xpwrite(int fd, const void *buf, size_t count, off_t offset);
+
+ssize_t pread_in_full(int fd, void *buf, size_t count, off_t offset);
+ssize_t pwrite_in_full(int fd, const void *buf, size_t count, off_t offset);
+
+ssize_t xreadv(int fd, const struct iovec *iov, int iovcnt);
+ssize_t xwritev(int fd, const struct iovec *iov, int iovcnt);
+
+ssize_t readv_in_full(int fd, const struct iovec *iov, int iovcnt);
+ssize_t writev_in_full(int fd, const struct iovec *iov, int iovcnt);
+
+ssize_t xpreadv(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+ssize_t xpwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+
+ssize_t preadv_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+ssize_t pwritev_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset);
+
+#ifdef CONFIG_HAS_AIO
+int aio_preadv(io_context_t ctx, struct iocb *iocb, int fd, const struct iovec *iov, int iovcnt,
+ off_t offset, int ev, void *param);
+int aio_pwritev(io_context_t ctx, struct iocb *iocb, int fd, const struct iovec *iov, int iovcnt,
+ off_t offset, int ev, void *param);
+#endif
+
+#endif /* KVM_READ_WRITE_H */
--- /dev/null
+#ifndef KVM__RTC_H
+#define KVM__RTC_H
+
+struct kvm;
+
+int rtc__init(struct kvm *kvm);
+int rtc__exit(struct kvm *kvm);
+
+#endif /* KVM__RTC_H */
--- /dev/null
+#ifndef KVM__RWSEM_H
+#define KVM__RWSEM_H
+
+#include <pthread.h>
+
+#include "kvm/util.h"
+
+/*
+ * Kernel-alike rwsem API - to make it easier for kernel developers
+ * to write user-space code! :-)
+ */
+
+#define DECLARE_RWSEM(sem) pthread_rwlock_t sem = PTHREAD_RWLOCK_INITIALIZER
+
+static inline void down_read(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_rdlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_rdlock() failure!");
+}
+
+static inline void down_write(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_wrlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_wrlock() failure!");
+}
+
+static inline void up_read(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_unlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_unlock() failure!");
+}
+
+static inline void up_write(pthread_rwlock_t *rwsem)
+{
+ if (pthread_rwlock_unlock(rwsem) != 0)
+ die("unexpected pthread_rwlock_unlock() failure!");
+}
+
+#endif /* KVM__RWSEM_H */
--- /dev/null
+#ifndef KVM__SDL_H
+#define KVM__SDL_H
+
+#include "kvm/util.h"
+
+struct framebuffer;
+
+#ifdef CONFIG_HAS_SDL
+int sdl__init(struct framebuffer *fb);
+int sdl__exit(struct framebuffer *fb);
+#else
+static inline void sdl__init(struct framebuffer *fb)
+{
+ die("SDL support not compiled in. (install the SDL-dev[el] package)");
+}
+static inline void sdl__exit(struct framebuffer *fb)
+{
+ die("SDL support not compiled in. (install the SDL-dev[el] package)");
+}
+#endif
+
+#endif /* KVM__SDL_H */
--- /dev/null
+#ifndef KVM_SEGMENT_H
+#define KVM_SEGMENT_H
+
+#include <linux/types.h>
+
+static inline u32 segment_to_flat(u16 selector, u16 offset)
+{
+ return ((u32)selector << 4) + (u32) offset;
+}
+
+static inline u16 flat_to_seg16(u32 address)
+{
+ return address >> 4;
+}
+
+static inline u16 flat_to_off16(u32 address, u32 segment)
+{
+ return address - (segment << 4);
+}
+
+#endif /* KVM_SEGMENT_H */
--- /dev/null
+#ifndef __STRBUF_H__
+#define __STRBUF_H__
+
+#include <sys/types.h>
+#include <string.h>
+
+int prefixcmp(const char *str, const char *prefix);
+
+extern size_t strlcat(char *dest, const char *src, size_t count);
+extern size_t strlcpy(char *dest, const char *src, size_t size);
+
+/* some inline functions */
+
+static inline const char *skip_prefix(const char *str, const char *prefix)
+{
+ size_t len = strlen(prefix);
+ return strncmp(str, prefix, len) ? NULL : str + len;
+}
+
+#endif
--- /dev/null
+#ifndef KVM__SYMBOL_H
+#define KVM__SYMBOL_H
+
+#include <stddef.h>
+#include <string.h>
+
+struct kvm;
+
+#define SYMBOL_DEFAULT_UNKNOWN "<unknown>"
+
+#ifdef CONFIG_HAS_BFD
+
+int symbol_init(struct kvm *kvm);
+int symbol_exit(struct kvm *kvm);
+char *symbol_lookup(struct kvm *kvm, unsigned long addr, char *sym, size_t size);
+
+#else
+
+static inline int symbol_init(struct kvm *kvm) { return 0; }
+static inline char *symbol_lookup(struct kvm *kvm, unsigned long addr, char *sym, size_t size)
+{
+ char *s = strncpy(sym, SYMBOL_DEFAULT_UNKNOWN, size);
+ sym[size - 1] = '\0';
+ return s;
+}
+static inline int symbol_exit(struct kvm *kvm) { return 0; }
+
+#endif
+
+#endif /* KVM__SYMBOL_H */
--- /dev/null
+#ifndef KVM__TERM_H
+#define KVM__TERM_H
+
+#include <sys/uio.h>
+#include <stdbool.h>
+
+#define CONSOLE_8250 1
+#define CONSOLE_VIRTIO 2
+#define CONSOLE_HV 3
+
+int term_putc_iov(int who, struct iovec *iov, int iovcnt, int term);
+int term_getc_iov(int who, struct iovec *iov, int iovcnt, int term);
+int term_putc(int who, char *addr, int cnt, int term);
+int term_getc(int who, int term);
+
+bool term_readable(int who, int term);
+void term_set_tty(int term);
+void term_init(void);
+
+#endif /* KVM__TERM_H */
--- /dev/null
+#ifndef KVM__THREADPOOL_H
+#define KVM__THREADPOOL_H
+
+#include "kvm/mutex.h"
+
+#include <linux/list.h>
+
+struct kvm;
+
+typedef void (*kvm_thread_callback_fn_t)(struct kvm *kvm, void *data);
+
+struct thread_pool__job {
+ kvm_thread_callback_fn_t callback;
+ struct kvm *kvm;
+ void *data;
+
+ int signalcount;
+ pthread_mutex_t mutex;
+
+ struct list_head queue;
+};
+
+static inline void thread_pool__init_job(struct thread_pool__job *job, struct kvm *kvm, kvm_thread_callback_fn_t callback, void *data)
+{
+ *job = (struct thread_pool__job) {
+ .kvm = kvm,
+ .callback = callback,
+ .data = data,
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+ };
+}
+
+int thread_pool__init(unsigned long thread_count);
+
+void thread_pool__do_job(struct thread_pool__job *job);
+
+#endif
--- /dev/null
+#ifndef KVM_TYPES_H
+#define KVM_TYPES_H
+
+/* FIXME: include/linux/if_tun.h and include/linux/if_ether.h complains */
+#define __be16 u16
+
+#endif /* KVM_TYPES_H */
--- /dev/null
+#ifndef KVM__UIP_H
+#define KVM__UIP_H
+
+#include "linux/types.h"
+#include "kvm/mutex.h"
+
+#include <netinet/in.h>
+#include <sys/uio.h>
+
+#define UIP_BUF_STATUS_FREE 0
+#define UIP_BUF_STATUS_INUSE 1
+#define UIP_BUF_STATUS_USED 2
+
+#define UIP_ETH_P_IP 0X0800
+#define UIP_ETH_P_ARP 0X0806
+
+#define UIP_IP_VER_4 0X40
+#define UIP_IP_HDR_LEN 0X05
+#define UIP_IP_TTL 0X40
+#define UIP_IP_P_UDP 0X11
+#define UIP_IP_P_TCP 0X06
+#define UIP_IP_P_ICMP 0X01
+
+#define UIP_TCP_HDR_LEN 0x50
+#define UIP_TCP_WIN_SIZE 14600
+#define UIP_TCP_FLAG_FIN 1
+#define UIP_TCP_FLAG_SYN 2
+#define UIP_TCP_FLAG_RST 4
+#define UIP_TCP_FLAG_PSH 8
+#define UIP_TCP_FLAG_ACK 16
+#define UIP_TCP_FLAG_URG 32
+
+#define UIP_BOOTP_VENDOR_SPECIFIC_LEN 64
+#define UIP_BOOTP_MAX_PAYLOAD_LEN 300
+#define UIP_DHCP_VENDOR_SPECIFIC_LEN 312
+#define UIP_DHCP_PORT_SERVER 67
+#define UIP_DHCP_PORT_CLIENT 68
+#define UIP_DHCP_MACPAD_LEN 10
+#define UIP_DHCP_HOSTNAME_LEN 64
+#define UIP_DHCP_FILENAME_LEN 128
+#define UIP_DHCP_MAGIC_COOKIE 0x63825363
+#define UIP_DHCP_MAGIC_COOKIE_LEN 4
+#define UIP_DHCP_LEASE_TIME 0x00003840
+#define UIP_DHCP_MAX_PAYLOAD_LEN (UIP_BOOTP_MAX_PAYLOAD_LEN - UIP_BOOTP_VENDOR_SPECIFIC_LEN + UIP_DHCP_VENDOR_SPECIFIC_LEN)
+#define UIP_DHCP_OPTION_LEN (UIP_DHCP_VENDOR_SPECIFIC_LEN - UIP_DHCP_MAGIC_COOKIE_LEN)
+#define UIP_DHCP_DISCOVER 1
+#define UIP_DHCP_OFFER 2
+#define UIP_DHCP_REQUEST 3
+#define UIP_DHCP_ACK 5
+#define UIP_DHCP_MAX_DNS_SERVER_NR 3
+#define UIP_DHCP_MAX_DOMAIN_NAME_LEN 256
+#define UIP_DHCP_TAG_MSG_TYPE 53
+#define UIP_DHCP_TAG_MSG_TYPE_LEN 1
+#define UIP_DHCP_TAG_SERVER_ID 54
+#define UIP_DHCP_TAG_SERVER_ID_LEN 4
+#define UIP_DHCP_TAG_LEASE_TIME 51
+#define UIP_DHCP_TAG_LEASE_TIME_LEN 4
+#define UIP_DHCP_TAG_SUBMASK 1
+#define UIP_DHCP_TAG_SUBMASK_LEN 4
+#define UIP_DHCP_TAG_ROUTER 3
+#define UIP_DHCP_TAG_ROUTER_LEN 4
+#define UIP_DHCP_TAG_ROOT 17
+#define UIP_DHCP_TAG_ROOT_LEN 4
+#define UIP_DHCP_TAG_DNS_SERVER 6
+#define UIP_DHCP_TAG_DNS_SERVER_LEN 4
+#define UIP_DHCP_TAG_DOMAIN_NAME 15
+#define UIP_DHCP_TAG_END 255
+
+/*
+ * IP package maxium len == 64 KBytes
+ * IP header == 20 Bytes
+ * TCP header == 20 Bytes
+ * UDP header == 8 Bytes
+ */
+#define UIP_MAX_TCP_PAYLOAD (64*1024 - 20 - 20 - 1)
+#define UIP_MAX_UDP_PAYLOAD (64*1024 - 20 - 8 - 1)
+
+struct uip_eth_addr {
+ u8 addr[6];
+};
+
+struct uip_eth {
+ struct uip_eth_addr dst;
+ struct uip_eth_addr src;
+ u16 type;
+} __attribute__((packed));
+
+struct uip_arp {
+ struct uip_eth eth;
+ u16 hwtype;
+ u16 proto;
+ u8 hwlen;
+ u8 protolen;
+ u16 op;
+ struct uip_eth_addr smac;
+ u32 sip;
+ struct uip_eth_addr dmac;
+ u32 dip;
+} __attribute__((packed));
+
+struct uip_ip {
+ struct uip_eth eth;
+ u8 vhl;
+ u8 tos;
+ /*
+ * len = IP hdr + IP payload
+ */
+ u16 len;
+ u16 id;
+ u16 flgfrag;
+ u8 ttl;
+ u8 proto;
+ u16 csum;
+ u32 sip;
+ u32 dip;
+} __attribute__((packed));
+
+struct uip_icmp {
+ struct uip_ip ip;
+ u8 type;
+ u8 code;
+ u16 csum;
+ u16 id;
+ u16 seq;
+} __attribute__((packed));
+
+struct uip_udp {
+ /*
+ * FIXME: IP Options (IP hdr len > 20 bytes) are not supported
+ */
+ struct uip_ip ip;
+ u16 sport;
+ u16 dport;
+ /*
+ * len = UDP hdr + UDP payload
+ */
+ u16 len;
+ u16 csum;
+ u8 payload[0];
+} __attribute__((packed));
+
+struct uip_tcp {
+ /*
+ * FIXME: IP Options (IP hdr len > 20 bytes) are not supported
+ */
+ struct uip_ip ip;
+ u16 sport;
+ u16 dport;
+ u32 seq;
+ u32 ack;
+ u8 off;
+ u8 flg;
+ u16 win;
+ u16 csum;
+ u16 urgent;
+} __attribute__((packed));
+
+struct uip_pseudo_hdr {
+ u32 sip;
+ u32 dip;
+ u8 zero;
+ u8 proto;
+ u16 len;
+} __attribute__((packed));
+
+struct uip_dhcp {
+ struct uip_udp udp;
+ u8 msg_type;
+ u8 hardware_type;
+ u8 hardware_len;
+ u8 hops;
+ u32 id;
+ u16 time;
+ u16 flg;
+ u32 client_ip;
+ u32 your_ip;
+ u32 server_ip;
+ u32 agent_ip;
+ struct uip_eth_addr client_mac;
+ u8 pad[UIP_DHCP_MACPAD_LEN];
+ u8 server_hostname[UIP_DHCP_HOSTNAME_LEN];
+ u8 boot_filename[UIP_DHCP_FILENAME_LEN];
+ u32 magic_cookie;
+ u8 option[UIP_DHCP_OPTION_LEN];
+} __attribute__((packed));
+
+struct uip_info {
+ struct list_head udp_socket_head;
+ struct list_head tcp_socket_head;
+ pthread_mutex_t udp_socket_lock;
+ pthread_mutex_t tcp_socket_lock;
+ struct uip_eth_addr guest_mac;
+ struct uip_eth_addr host_mac;
+ pthread_cond_t buf_free_cond;
+ pthread_cond_t buf_used_cond;
+ struct list_head buf_head;
+ pthread_mutex_t buf_lock;
+ pthread_t udp_thread;
+ int udp_epollfd;
+ int buf_free_nr;
+ int buf_used_nr;
+ u32 guest_ip;
+ u32 guest_netmask;
+ u32 host_ip;
+ u32 dns_ip[UIP_DHCP_MAX_DNS_SERVER_NR];
+ char *domain_name;
+ u32 buf_nr;
+};
+
+struct uip_buf {
+ struct list_head list;
+ struct uip_info *info;
+ int vnet_len;
+ int eth_len;
+ int status;
+ char *vnet;
+ char *eth;
+ int id;
+};
+
+struct uip_udp_socket {
+ struct sockaddr_in addr;
+ struct list_head list;
+ pthread_mutex_t *lock;
+ u32 dport, sport;
+ u32 dip, sip;
+ int fd;
+};
+
+struct uip_tcp_socket {
+ struct sockaddr_in addr;
+ struct list_head list;
+ struct uip_info *info;
+ pthread_cond_t cond;
+ pthread_mutex_t *lock;
+ pthread_t thread;
+ u32 dport, sport;
+ u32 guest_acked;
+ u16 window_size;
+ /*
+ * Initial Sequence Number
+ */
+ u32 isn_server;
+ u32 isn_guest;
+ u32 ack_server;
+ u32 seq_server;
+ int write_done;
+ int read_done;
+ u32 dip, sip;
+ u8 *payload;
+ int fd;
+};
+
+struct uip_tx_arg {
+ struct virtio_net_hdr *vnet;
+ struct uip_info *info;
+ struct uip_eth *eth;
+ int vnet_len;
+ int eth_len;
+};
+
+static inline u16 uip_ip_hdrlen(struct uip_ip *ip)
+{
+ return (ip->vhl & 0x0f) * 4;
+}
+
+static inline u16 uip_ip_len(struct uip_ip *ip)
+{
+ return htons(ip->len);
+}
+
+static inline u16 uip_udp_hdrlen(struct uip_udp *udp)
+{
+ return 8;
+}
+
+static inline u16 uip_udp_len(struct uip_udp *udp)
+{
+ return ntohs(udp->len);
+}
+
+static inline u16 uip_tcp_hdrlen(struct uip_tcp *tcp)
+{
+ return (tcp->off >> 4) * 4;
+}
+
+static inline u16 uip_tcp_len(struct uip_tcp *tcp)
+{
+ struct uip_ip *ip;
+
+ ip = &tcp->ip;
+
+ return uip_ip_len(ip) - uip_ip_hdrlen(ip);
+}
+
+static inline u16 uip_tcp_payloadlen(struct uip_tcp *tcp)
+{
+ return uip_tcp_len(tcp) - uip_tcp_hdrlen(tcp);
+}
+
+static inline u8 *uip_tcp_payload(struct uip_tcp *tcp)
+{
+ return (u8 *)&tcp->sport + uip_tcp_hdrlen(tcp);
+}
+
+static inline bool uip_tcp_is_syn(struct uip_tcp *tcp)
+{
+ return (tcp->flg & UIP_TCP_FLAG_SYN) != 0;
+}
+
+static inline bool uip_tcp_is_fin(struct uip_tcp *tcp)
+{
+ return (tcp->flg & UIP_TCP_FLAG_FIN) != 0;
+}
+
+static inline u32 uip_tcp_isn(struct uip_tcp *tcp)
+{
+ return ntohl(tcp->seq);
+}
+
+static inline u32 uip_tcp_isn_alloc(void)
+{
+ /*
+ * FIXME: should increase every 4ms
+ */
+ return 10000000;
+}
+
+static inline u16 uip_eth_hdrlen(struct uip_eth *eth)
+{
+ return sizeof(*eth);
+}
+
+int uip_tx(struct iovec *iov, u16 out, struct uip_info *info);
+int uip_rx(struct iovec *iov, u16 in, struct uip_info *info);
+int uip_init(struct uip_info *info);
+
+int uip_tx_do_ipv4_udp_dhcp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4_icmp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4_tcp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4_udp(struct uip_tx_arg *arg);
+int uip_tx_do_ipv4(struct uip_tx_arg *arg);
+int uip_tx_do_arp(struct uip_tx_arg *arg);
+
+u16 uip_csum_icmp(struct uip_icmp *icmp);
+u16 uip_csum_udp(struct uip_udp *udp);
+u16 uip_csum_tcp(struct uip_tcp *tcp);
+u16 uip_csum_ip(struct uip_ip *ip);
+
+struct uip_buf *uip_buf_set_used(struct uip_info *info, struct uip_buf *buf);
+struct uip_buf *uip_buf_set_free(struct uip_info *info, struct uip_buf *buf);
+struct uip_buf *uip_buf_get_used(struct uip_info *info);
+struct uip_buf *uip_buf_get_free(struct uip_info *info);
+struct uip_buf *uip_buf_clone(struct uip_tx_arg *arg);
+
+int uip_udp_make_pkg(struct uip_info *info, struct uip_udp_socket *sk, struct uip_buf *buf, u8 *payload, int payload_len);
+bool uip_udp_is_dhcp(struct uip_udp *udp);
+
+int uip_dhcp_get_dns(struct uip_info *info);
+#endif /* KVM__UIP_H */
--- /dev/null
+#include <linux/stringify.h>
+
+#ifndef KVM__UTIL_H
+#define KVM__UTIL_H
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+/*
+ * Some bits are stolen from perf tool :)
+ */
+
+#include <unistd.h>
+#include <stdio.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <errno.h>
+#include <limits.h>
+#include <sys/param.h>
+#include <sys/types.h>
+#include <linux/types.h>
+
+#ifdef __GNUC__
+#define NORETURN __attribute__((__noreturn__))
+#else
+#define NORETURN
+#ifndef __attribute__
+#define __attribute__(x)
+#endif
+#endif
+
+extern bool do_debug_print;
+
+#define PROT_RW (PROT_READ|PROT_WRITE)
+#define MAP_ANON_NORESERVE (MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE)
+
+extern void die(const char *err, ...) NORETURN __attribute__((format (printf, 1, 2)));
+extern void die_perror(const char *s) NORETURN;
+extern int pr_err(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void pr_warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void pr_info(const char *err, ...) __attribute__((format (printf, 1, 2)));
+extern void set_die_routine(void (*routine)(const char *err, va_list params) NORETURN);
+
+#define pr_debug(fmt, ...) \
+ do { \
+ if (do_debug_print) \
+ pr_info("(%s) %s:%d: " fmt, __FILE__, \
+ __func__, __LINE__, ##__VA_ARGS__); \
+ } while (0)
+
+
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+
+#ifndef BUG_ON_HANDLER
+# define BUG_ON_HANDLER(condition) \
+ do { \
+ if ((condition)) { \
+ pr_err("BUG at %s:%d", __FILE__, __LINE__); \
+ raise(SIGABRT); \
+ } \
+ } while (0)
+#endif
+
+#define BUG_ON(condition) BUG_ON_HANDLER((condition))
+
+#define DIE_IF(cnd) \
+do { \
+ if (cnd) \
+ die(" at (" __FILE__ ":" __stringify(__LINE__) "): " \
+ __stringify(cnd) "\n"); \
+} while (0)
+
+#define WARN_ON(condition) ({ \
+ int __ret_warn_on = !!(condition); \
+ if (__ret_warn_on) \
+ pr_warning("(%s) %s:%d: failed condition: %s", \
+ __FILE__, __func__, __LINE__, \
+ __stringify(condition)); \
+ __ret_warn_on; \
+})
+
+#define MSECS_TO_USECS(s) ((s) * 1000)
+
+/* Millisecond sleep */
+static inline void msleep(unsigned int msecs)
+{
+ usleep(MSECS_TO_USECS(msecs));
+}
+
+struct kvm;
+void *mmap_hugetlbfs(struct kvm *kvm, const char *htlbfs_path, u64 size);
+void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size);
+
+#endif /* KVM__UTIL_H */
--- /dev/null
+#ifndef KVM__VESA_H
+#define KVM__VESA_H
+
+#include <linux/types.h>
+
+#define VESA_WIDTH 640
+#define VESA_HEIGHT 480
+
+#define VESA_MEM_ADDR 0xd0000000
+#define VESA_MEM_SIZE (4*VESA_WIDTH*VESA_HEIGHT)
+#define VESA_BPP 32
+
+struct kvm;
+struct biosregs;
+
+struct framebuffer *vesa__init(struct kvm *self);
+
+#endif
--- /dev/null
+#ifndef KVM__VIRTIO_9P_H
+#define KVM__VIRTIO_9P_H
+#include "kvm/virtio.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+
+#include <sys/types.h>
+#include <dirent.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+
+#define NUM_VIRT_QUEUES 1
+#define VIRTQUEUE_NUM 128
+#define VIRTIO_9P_DEFAULT_TAG "kvm_9p"
+#define VIRTIO_9P_HDR_LEN (sizeof(u32)+sizeof(u8)+sizeof(u16))
+#define VIRTIO_9P_VERSION_DOTL "9P2000.L"
+#define MAX_TAG_LEN 32
+
+struct p9_msg {
+ u32 size;
+ u8 cmd;
+ u16 tag;
+ u8 msg[0];
+} __attribute__((packed));
+
+struct p9_fid {
+ u32 fid;
+ u32 uid;
+ char abs_path[PATH_MAX];
+ char *path;
+ DIR *dir;
+ int fd;
+ struct rb_node node;
+};
+
+struct p9_dev_job {
+ struct virt_queue *vq;
+ struct p9_dev *p9dev;
+ struct thread_pool__job job_id;
+};
+
+struct p9_dev {
+ struct list_head list;
+ struct virtio_device vdev;
+ struct rb_root fids;
+
+ struct virtio_9p_config *config;
+ u32 features;
+
+ /* virtio queue */
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct p9_dev_job jobs[NUM_VIRT_QUEUES];
+ char root_dir[PATH_MAX];
+};
+
+struct p9_pdu {
+ u32 queue_head;
+ size_t read_offset;
+ size_t write_offset;
+ u16 out_iov_cnt;
+ u16 in_iov_cnt;
+ struct iovec in_iov[VIRTQUEUE_NUM];
+ struct iovec out_iov[VIRTQUEUE_NUM];
+};
+
+struct kvm;
+
+int virtio_9p__register(struct kvm *kvm, const char *root, const char *tag_name);
+int virtio_9p__init(struct kvm *kvm);
+int virtio_p9_pdu_readf(struct p9_pdu *pdu, const char *fmt, ...);
+int virtio_p9_pdu_writef(struct p9_pdu *pdu, const char *fmt, ...);
+
+#endif
--- /dev/null
+#ifndef KVM__BLN_VIRTIO_H
+#define KVM__BLN_VIRTIO_H
+
+struct kvm;
+
+void virtio_bln__init(struct kvm *kvm);
+
+#endif /* KVM__BLN_VIRTIO_H */
--- /dev/null
+#ifndef KVM__BLK_VIRTIO_H
+#define KVM__BLK_VIRTIO_H
+
+#include "kvm/disk-image.h"
+
+struct kvm;
+
+int virtio_blk__init(struct kvm *kvm);
+int virtio_blk__exit(struct kvm *kvm);
+void virtio_blk_complete(void *param, long len);
+
+#endif /* KVM__BLK_VIRTIO_H */
--- /dev/null
+#ifndef KVM__CONSOLE_VIRTIO_H
+#define KVM__CONSOLE_VIRTIO_H
+
+struct kvm;
+
+void virtio_console__init(struct kvm *kvm);
+void virtio_console__inject_interrupt(struct kvm *kvm);
+
+#endif /* KVM__CONSOLE_VIRTIO_H */
--- /dev/null
+#ifndef KVM__VIRTIO_MMIO_H
+#define KVM__VIRTIO_MMIO_H
+
+#include <linux/types.h>
+#include <linux/virtio_mmio.h>
+
+#define VIRTIO_MMIO_MAX_VQ 3
+#define VIRTIO_MMIO_MAX_CONFIG 1
+#define VIRTIO_MMIO_IO_SIZE 0x200
+
+struct kvm;
+
+struct virtio_mmio_ioevent_param {
+ struct virtio_device *vdev;
+ u32 vq;
+};
+
+struct virtio_mmio_hdr {
+ char magic[4];
+ u32 version;
+ u32 device_id;
+ u32 vendor_id;
+ u32 host_features;
+ u32 host_features_sel;
+ u32 reserved_1[2];
+ u32 guest_features;
+ u32 guest_features_sel;
+ u32 guest_page_size;
+ u32 reserved_2;
+ u32 queue_sel;
+ u32 queue_num_max;
+ u32 queue_num;
+ u32 queue_align;
+ u32 queue_pfn;
+ u32 reserved_3[3];
+ u32 queue_notify;
+ u32 reserved_4[3];
+ u32 interrupt_state;
+ u32 interrupt_ack;
+ u32 reserved_5[2];
+ u32 status;
+} __attribute__((packed));
+
+struct virtio_mmio {
+ u32 addr;
+ void *dev;
+ struct kvm *kvm;
+ u8 irq;
+ struct virtio_mmio_hdr hdr;
+ struct virtio_mmio_ioevent_param ioeventfds[VIRTIO_MMIO_MAX_VQ];
+};
+
+int virtio_mmio_signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq);
+int virtio_mmio_signal_config(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_mmio_exit(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_mmio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class);
+#endif
--- /dev/null
+#ifndef KVM__VIRTIO_NET_H
+#define KVM__VIRTIO_NET_H
+
+struct kvm;
+
+struct virtio_net_params {
+ const char *guest_ip;
+ const char *host_ip;
+ const char *script;
+ const char *trans;
+ char guest_mac[6];
+ char host_mac[6];
+ struct kvm *kvm;
+ int mode;
+ int vhost;
+ int fd;
+};
+
+void virtio_net__init(const struct virtio_net_params *params);
+
+enum {
+ NET_MODE_USER,
+ NET_MODE_TAP
+};
+
+#endif /* KVM__VIRTIO_NET_H */
--- /dev/null
+#ifndef VIRTIO_PCI_DEV_H_
+#define VIRTIO_PCI_DEV_H_
+
+#include <linux/virtio_ids.h>
+
+/*
+ * Virtio PCI device constants and resources
+ * they do use (such as irqs and pins).
+ */
+
+#define PCI_DEVICE_ID_VIRTIO_NET 0x1000
+#define PCI_DEVICE_ID_VIRTIO_BLK 0x1001
+#define PCI_DEVICE_ID_VIRTIO_CONSOLE 0x1003
+#define PCI_DEVICE_ID_VIRTIO_RNG 0x1004
+#define PCI_DEVICE_ID_VIRTIO_BLN 0x1005
+#define PCI_DEVICE_ID_VIRTIO_SCSI 0x1008
+#define PCI_DEVICE_ID_VIRTIO_9P 0x1009
+#define PCI_DEVICE_ID_VESA 0x2000
+#define PCI_DEVICE_ID_PCI_SHMEM 0x0001
+
+#define PCI_VENDOR_ID_REDHAT_QUMRANET 0x1af4
+#define PCI_VENDOR_ID_PCI_SHMEM 0x0001
+#define PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET 0x1af4
+
+#define PCI_SUBSYSTEM_ID_VESA 0x0004
+#define PCI_SUBSYSTEM_ID_PCI_SHMEM 0x0001
+
+#define PCI_CLASS_BLK 0x018000
+#define PCI_CLASS_NET 0x020000
+#define PCI_CLASS_CONSOLE 0x078000
+/*
+ * 0xFF Device does not fit in any defined classes
+ */
+#define PCI_CLASS_RNG 0xff0000
+#define PCI_CLASS_BLN 0xff0000
+#define PCI_CLASS_9P 0xff0000
+
+#endif /* VIRTIO_PCI_DEV_H_ */
--- /dev/null
+#ifndef KVM__VIRTIO_PCI_H
+#define KVM__VIRTIO_PCI_H
+
+#include "kvm/pci.h"
+
+#include <linux/types.h>
+
+#define VIRTIO_PCI_MAX_VQ 3
+#define VIRTIO_PCI_MAX_CONFIG 1
+
+struct kvm;
+
+struct virtio_pci_ioevent_param {
+ struct virtio_device *vdev;
+ u32 vq;
+};
+
+#define VIRTIO_PCI_F_SIGNAL_MSI (1 << 0)
+
+struct virtio_pci {
+ struct pci_device_header pci_hdr;
+ void *dev;
+
+ u16 base_addr;
+ u8 status;
+ u8 isr;
+ u32 features;
+
+ /* MSI-X */
+ u16 config_vector;
+ u32 config_gsi;
+ u32 vq_vector[VIRTIO_PCI_MAX_VQ];
+ u32 gsis[VIRTIO_PCI_MAX_VQ];
+ u32 msix_io_block;
+ u64 msix_pba;
+ struct msix_table msix_table[VIRTIO_PCI_MAX_VQ + VIRTIO_PCI_MAX_CONFIG];
+
+ /* virtio queue */
+ u16 queue_selector;
+ struct virtio_pci_ioevent_param ioeventfds[VIRTIO_PCI_MAX_VQ];
+};
+
+int virtio_pci__signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq);
+int virtio_pci__signal_config(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_pci__exit(struct kvm *kvm, struct virtio_device *vdev);
+int virtio_pci__init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class);
+
+#endif
--- /dev/null
+#ifndef KVM__RNG_VIRTIO_H
+#define KVM__RNG_VIRTIO_H
+
+struct kvm;
+
+int virtio_rng__init(struct kvm *kvm);
+int virtio_rng__exit(struct kvm *kvm);
+
+#endif /* KVM__RNG_VIRTIO_H */
--- /dev/null
+#ifndef KVM__SCSI_VIRTIO_H
+#define KVM__SCSI_VIRTIO_H
+
+#include "kvm/disk-image.h"
+
+struct kvm;
+
+int virtio_scsi_init(struct kvm *kvm);
+int virtio_scsi_exit(struct kvm *kvm);
+
+/*----------------------------------------------------*/
+/* TODO: Remove this when tcm_vhost goes upstream */
+#define TRANSPORT_IQN_LEN 224
+#define VHOST_SCSI_ABI_VERSION 0
+struct vhost_scsi_target {
+ int abi_version;
+ unsigned char vhost_wwpn[TRANSPORT_IQN_LEN];
+ unsigned short vhost_tpgt;
+};
+/* VHOST_SCSI specific defines */
+#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
+#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
+#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, struct vhost_scsi_target)
+/*----------------------------------------------------*/
+
+#endif /* KVM__SCSI_VIRTIO_H */
--- /dev/null
+#ifndef KVM__VIRTIO_H
+#define KVM__VIRTIO_H
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_pci.h>
+
+#include <linux/types.h>
+#include <sys/uio.h>
+
+#include "kvm/kvm.h"
+
+#define VIRTIO_IRQ_LOW 0
+#define VIRTIO_IRQ_HIGH 1
+
+#define VIRTIO_PCI_O_CONFIG 0
+#define VIRTIO_PCI_O_MSIX 1
+
+struct virt_queue {
+ struct vring vring;
+ u32 pfn;
+ /* The last_avail_idx field is an index to ->ring of struct vring_avail.
+ It's where we assume the next request index is at. */
+ u16 last_avail_idx;
+ u16 last_used_signalled;
+};
+
+static inline u16 virt_queue__pop(struct virt_queue *queue)
+{
+ return queue->vring.avail->ring[queue->last_avail_idx++ % queue->vring.num];
+}
+
+static inline struct vring_desc *virt_queue__get_desc(struct virt_queue *queue, u16 desc_ndx)
+{
+ return &queue->vring.desc[desc_ndx];
+}
+
+static inline bool virt_queue__available(struct virt_queue *vq)
+{
+ if (!vq->vring.avail)
+ return 0;
+
+ vring_avail_event(&vq->vring) = vq->last_avail_idx;
+ return vq->vring.avail->idx != vq->last_avail_idx;
+}
+
+/*
+ * Warning: on 32-bit hosts, shifting pfn left may cause a truncation of pfn values
+ * higher than 4GB - thus, pointing to the wrong area in guest virtual memory space
+ * and breaking the virt queue which owns this pfn.
+ */
+static inline void *guest_pfn_to_host(struct kvm *kvm, u32 pfn)
+{
+ return guest_flat_to_host(kvm, (unsigned long)pfn << VIRTIO_PCI_QUEUE_ADDR_SHIFT);
+}
+
+
+struct vring_used_elem *virt_queue__set_used_elem(struct virt_queue *queue, u32 head, u32 len);
+
+bool virtio_queue__should_signal(struct virt_queue *vq);
+u16 virt_queue__get_iov(struct virt_queue *vq, struct iovec iov[],
+ u16 *out, u16 *in, struct kvm *kvm);
+u16 virt_queue__get_head_iov(struct virt_queue *vq, struct iovec iov[],
+ u16 *out, u16 *in, u16 head, struct kvm *kvm);
+u16 virt_queue__get_inout_iov(struct kvm *kvm, struct virt_queue *queue,
+ struct iovec in_iov[], struct iovec out_iov[],
+ u16 *in, u16 *out);
+int virtio__get_dev_specific_field(int offset, bool msix, u32 *config_off);
+
+enum virtio_trans {
+ VIRTIO_PCI,
+ VIRTIO_MMIO,
+};
+
+struct virtio_device {
+ bool use_vhost;
+ void *virtio;
+ struct virtio_ops *ops;
+};
+
+struct virtio_ops {
+ u8 *(*get_config)(struct kvm *kvm, void *dev);
+ u32 (*get_host_features)(struct kvm *kvm, void *dev);
+ void (*set_guest_features)(struct kvm *kvm, void *dev, u32 features);
+ int (*init_vq)(struct kvm *kvm, void *dev, u32 vq, u32 pfn);
+ int (*notify_vq)(struct kvm *kvm, void *dev, u32 vq);
+ int (*get_pfn_vq)(struct kvm *kvm, void *dev, u32 vq);
+ int (*get_size_vq)(struct kvm *kvm, void *dev, u32 vq);
+ int (*set_size_vq)(struct kvm *kvm, void *dev, u32 vq, int size);
+ void (*notify_vq_gsi)(struct kvm *kvm, void *dev, u32 vq, u32 gsi);
+ void (*notify_vq_eventfd)(struct kvm *kvm, void *dev, u32 vq, u32 efd);
+ int (*signal_vq)(struct kvm *kvm, struct virtio_device *vdev, u32 queueid);
+ int (*signal_config)(struct kvm *kvm, struct virtio_device *vdev);
+ int (*init)(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class);
+ int (*exit)(struct kvm *kvm, struct virtio_device *vdev);
+};
+
+int virtio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ struct virtio_ops *ops, enum virtio_trans trans,
+ int device_id, int subsys_id, int class);
+int virtio_compat_add_message(const char *device, const char *config);
+#endif /* KVM__VIRTIO_H */
--- /dev/null
+#ifndef KVM__VNC_H
+#define KVM__VNC_H
+
+struct framebuffer;
+
+#ifdef CONFIG_HAS_VNCSERVER
+int vnc__init(struct framebuffer *fb);
+int vnc__exit(struct framebuffer *fb);
+#else
+static inline int vnc__init(struct framebuffer *fb)
+{
+ return 0;
+}
+static inline int vnc__exit(struct framebuffer *fb)
+{
+ return 0;
+}
+#endif
+
+#endif /* KVM__VNC_H */
--- /dev/null
+#ifndef _KVM_LINUX_BITOPS_H_
+#define _KVM_LINUX_BITOPS_H_
+
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <asm/hweight.h>
+
+#define BITS_PER_LONG __WORDSIZE
+#define BITS_PER_BYTE 8
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+
+static inline void set_bit(int nr, unsigned long *addr)
+{
+ addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
+}
+
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+ addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+}
+
+static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
+{
+ return ((1UL << (nr % BITS_PER_LONG)) &
+ (((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+}
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+ return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
+
+#endif
--- /dev/null
+#ifndef __BYTE_ORDER_H__
+#define __BYTE_ORDER_H__
+
+#include <asm/byteorder.h>
+#include <linux/byteorder/generic.h>
+
+#endif
--- /dev/null
+#ifndef _PERF_LINUX_COMPILER_H_
+#define _PERF_LINUX_COMPILER_H_
+
+#ifndef __always_inline
+#define __always_inline inline
+#endif
+#define __user
+
+#ifndef __attribute_const__
+#define __attribute_const__
+#endif
+
+#define __used __attribute__((__unused__))
+#define __packed __attribute__((packed))
+#define __iomem
+#define __force
+#define __must_check
+#define unlikely
+
+#endif
--- /dev/null
+
+#ifndef KVM__LINUX_KERNEL_H_
+#define KVM__LINUX_KERNEL_H_
+
+#define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
+
+#define ALIGN(x,a) __ALIGN_MASK(x,(typeof(x))(a)-1)
+#define __ALIGN_MASK(x,mask) (((x)+(mask))&~(mask))
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+#ifndef container_of
+/**
+ * container_of - cast a member of a structure out to the containing structure
+ * @ptr: the pointer to the member.
+ * @type: the type of the container struct this is embedded in.
+ * @member: the name of the member within the struct.
+ *
+ */
+#define container_of(ptr, type, member) ({ \
+ const typeof(((type *)0)->member) * __mptr = (ptr); \
+ (type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+
+#define max(x, y) ({ \
+ typeof(x) _max1 = (x); \
+ typeof(y) _max2 = (y); \
+ (void) (&_max1 == &_max2); \
+ _max1 > _max2 ? _max1 : _max2; })
+
+#endif
--- /dev/null
+#ifndef KVM__LINUX_MODULE_H
+#define KVM__LINUX_MODULE_H
+
+#define EXPORT_SYMBOL(name)
+
+#endif
--- /dev/null
+#ifndef KVM__LINUX_PREFETCH_H
+#define KVM__LINUX_PREFETCH_H
+
+static inline void prefetch(void *a __attribute__((unused))) { }
+
+#endif
--- /dev/null
+#ifndef _LINUX_STDDEF_H
+#define _LINUX_STDDEF_H
+
+#include <linux/compiler.h>
+
+#undef NULL
+#define NULL ((void *)0)
+
+#undef offsetof
+#ifdef __compiler_offsetof
+#define offsetof(TYPE,MEMBER) __compiler_offsetof(TYPE,MEMBER)
+#else
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+#endif
--- /dev/null
+#ifndef LINUX_TYPES_H
+#define LINUX_TYPES_H
+
+#include <kvm/compiler.h>
+#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */
+#include <asm/types.h>
+
+typedef __u64 u64;
+typedef __s64 s64;
+
+typedef __u32 u32;
+typedef __s32 s32;
+
+typedef __u16 u16;
+typedef __s16 s16;
+
+typedef __u8 u8;
+typedef __s8 s8;
+
+#ifdef __CHECKER__
+#define __bitwise__ __attribute__((bitwise))
+#else
+#define __bitwise__
+#endif
+#ifdef __CHECK_ENDIAN__
+#define __bitwise __bitwise__
+#else
+#define __bitwise
+#endif
+
+
+typedef __u16 __bitwise __le16;
+typedef __u16 __bitwise __be16;
+typedef __u32 __bitwise __le32;
+typedef __u32 __bitwise __be32;
+typedef __u64 __bitwise __le64;
+typedef __u64 __bitwise __be64;
+
+struct list_head {
+ struct list_head *next, *prev;
+};
+
+struct hlist_head {
+ struct hlist_node *first;
+};
+
+struct hlist_node {
+ struct hlist_node *next, **pprev;
+};
+
+#endif /* LINUX_TYPES_H */
--- /dev/null
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <pthread.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <signal.h>
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/types.h>
+
+#include "kvm/ioeventfd.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#define IOEVENTFD_MAX_EVENTS 20
+
+static struct epoll_event events[IOEVENTFD_MAX_EVENTS];
+static int epoll_fd, epoll_stop_fd;
+static LIST_HEAD(used_ioevents);
+static bool ioeventfd_avail;
+
+static void *ioeventfd__thread(void *param)
+{
+ u64 tmp = 1;
+
+ for (;;) {
+ int nfds, i;
+
+ nfds = epoll_wait(epoll_fd, events, IOEVENTFD_MAX_EVENTS, -1);
+ for (i = 0; i < nfds; i++) {
+ struct ioevent *ioevent;
+
+ if (events[i].data.fd == epoll_stop_fd)
+ goto done;
+
+ ioevent = events[i].data.ptr;
+
+ if (read(ioevent->fd, &tmp, sizeof(tmp)) < 0)
+ die("Failed reading event");
+
+ ioevent->fn(ioevent->fn_kvm, ioevent->fn_ptr);
+ }
+ }
+
+done:
+ tmp = write(epoll_stop_fd, &tmp, sizeof(tmp));
+
+ return NULL;
+}
+
+static int ioeventfd__start(void)
+{
+ pthread_t thread;
+
+ if (!ioeventfd_avail)
+ return -ENOSYS;
+
+ return pthread_create(&thread, NULL, ioeventfd__thread, NULL);
+}
+
+int ioeventfd__init(struct kvm *kvm)
+{
+ struct epoll_event epoll_event = {.events = EPOLLIN};
+ int r;
+
+ ioeventfd_avail = kvm__supports_extension(kvm, KVM_CAP_IOEVENTFD);
+ if (!ioeventfd_avail)
+ return 1; /* Not fatal, but let caller determine no-go. */
+
+ epoll_fd = epoll_create(IOEVENTFD_MAX_EVENTS);
+ if (epoll_fd < 0)
+ return -errno;
+
+ epoll_stop_fd = eventfd(0, 0);
+ epoll_event.data.fd = epoll_stop_fd;
+
+ r = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, epoll_stop_fd, &epoll_event);
+ if (r < 0)
+ goto cleanup;
+
+ r = ioeventfd__start();
+ if (r < 0)
+ goto cleanup;
+
+ r = 0;
+
+ return r;
+
+cleanup:
+ close(epoll_stop_fd);
+ close(epoll_fd);
+
+ return r;
+}
+
+int ioeventfd__exit(struct kvm *kvm)
+{
+ u64 tmp = 1;
+ int r;
+
+ if (!ioeventfd_avail)
+ return 0;
+
+ r = write(epoll_stop_fd, &tmp, sizeof(tmp));
+ if (r < 0)
+ return r;
+
+ r = read(epoll_stop_fd, &tmp, sizeof(tmp));
+ if (r < 0)
+ return r;
+
+ close(epoll_fd);
+ close(epoll_stop_fd);
+
+ return 0;
+}
+
+int ioeventfd__add_event(struct ioevent *ioevent, bool is_pio, bool poll_in_userspace)
+{
+ struct kvm_ioeventfd kvm_ioevent;
+ struct epoll_event epoll_event;
+ struct ioevent *new_ioevent;
+ int event, r;
+
+ if (!ioeventfd_avail)
+ return -ENOSYS;
+
+ new_ioevent = malloc(sizeof(*new_ioevent));
+ if (new_ioevent == NULL)
+ return -ENOMEM;
+
+ *new_ioevent = *ioevent;
+ event = new_ioevent->fd;
+
+ kvm_ioevent = (struct kvm_ioeventfd) {
+ .addr = ioevent->io_addr,
+ .len = ioevent->io_len,
+ .datamatch = ioevent->datamatch,
+ .fd = event,
+ .flags = KVM_IOEVENTFD_FLAG_DATAMATCH,
+ };
+
+ if (is_pio)
+ kvm_ioevent.flags |= KVM_IOEVENTFD_FLAG_PIO;
+
+ r = ioctl(ioevent->fn_kvm->vm_fd, KVM_IOEVENTFD, &kvm_ioevent);
+ if (r) {
+ r = -errno;
+ goto cleanup;
+ }
+
+ if (!poll_in_userspace)
+ return 0;
+
+ epoll_event = (struct epoll_event) {
+ .events = EPOLLIN,
+ .data.ptr = new_ioevent,
+ };
+
+ r = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, event, &epoll_event);
+ if (r) {
+ r = -errno;
+ goto cleanup;
+ }
+
+ list_add_tail(&new_ioevent->list, &used_ioevents);
+
+ return 0;
+
+cleanup:
+ free(new_ioevent);
+ return r;
+}
+
+int ioeventfd__del_event(u64 addr, u64 datamatch)
+{
+ struct kvm_ioeventfd kvm_ioevent;
+ struct ioevent *ioevent;
+ u8 found = 0;
+
+ if (!ioeventfd_avail)
+ return -ENOSYS;
+
+ list_for_each_entry(ioevent, &used_ioevents, list) {
+ if (ioevent->io_addr == addr) {
+ found = 1;
+ break;
+ }
+ }
+
+ if (found == 0 || ioevent == NULL)
+ return -ENOENT;
+
+ kvm_ioevent = (struct kvm_ioeventfd) {
+ .addr = ioevent->io_addr,
+ .len = ioevent->io_len,
+ .datamatch = ioevent->datamatch,
+ .flags = KVM_IOEVENTFD_FLAG_PIO
+ | KVM_IOEVENTFD_FLAG_DEASSIGN
+ | KVM_IOEVENTFD_FLAG_DATAMATCH,
+ };
+
+ ioctl(ioevent->fn_kvm->vm_fd, KVM_IOEVENTFD, &kvm_ioevent);
+
+ epoll_ctl(epoll_fd, EPOLL_CTL_DEL, ioevent->fd, NULL);
+
+ list_del(&ioevent->list);
+
+ close(ioevent->fd);
+ free(ioevent);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/ioport.h"
+
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+#include "kvm/brlock.h"
+#include "kvm/rbtree-interval.h"
+#include "kvm/mutex.h"
+
+#include <linux/kvm.h> /* for KVM_EXIT_* */
+#include <linux/types.h>
+
+#include <stdbool.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#define ioport_node(n) rb_entry(n, struct ioport, node)
+
+DEFINE_MUTEX(ioport_mutex);
+
+static u16 free_io_port_idx; /* protected by ioport_mutex */
+
+static struct rb_root ioport_tree = RB_ROOT;
+bool ioport_debug;
+
+static u16 ioport__find_free_port(void)
+{
+ u16 free_port;
+
+ mutex_lock(&ioport_mutex);
+ free_port = IOPORT_START + free_io_port_idx * IOPORT_SIZE;
+ free_io_port_idx++;
+ mutex_unlock(&ioport_mutex);
+
+ return free_port;
+}
+
+static struct ioport *ioport_search(struct rb_root *root, u64 addr)
+{
+ struct rb_int_node *node;
+
+ node = rb_int_search_single(root, addr);
+ if (node == NULL)
+ return NULL;
+
+ return ioport_node(node);
+}
+
+static int ioport_insert(struct rb_root *root, struct ioport *data)
+{
+ return rb_int_insert(root, &data->node);
+}
+
+static void ioport_remove(struct rb_root *root, struct ioport *data)
+{
+ rb_int_erase(root, &data->node);
+}
+
+int ioport__register(u16 port, struct ioport_operations *ops, int count, void *param)
+{
+ struct ioport *entry;
+ int r;
+
+ br_write_lock();
+ if (port == IOPORT_EMPTY)
+ port = ioport__find_free_port();
+
+ entry = ioport_search(&ioport_tree, port);
+ if (entry) {
+ pr_warning("ioport re-registered: %x", port);
+ rb_int_erase(&ioport_tree, &entry->node);
+ }
+
+ entry = malloc(sizeof(*entry));
+ if (entry == NULL)
+ return -ENOMEM;
+
+ *entry = (struct ioport) {
+ .node = RB_INT_INIT(port, port + count),
+ .ops = ops,
+ .priv = param,
+ };
+
+ r = ioport_insert(&ioport_tree, entry);
+ if (r < 0) {
+ free(entry);
+ br_write_unlock();
+ return r;
+ }
+ br_write_unlock();
+
+ return port;
+}
+
+int ioport__unregister(u16 port)
+{
+ struct ioport *entry;
+ int r;
+
+ br_write_lock();
+
+ r = -ENOENT;
+ entry = ioport_search(&ioport_tree, port);
+ if (!entry)
+ goto done;
+
+ ioport_remove(&ioport_tree, entry);
+
+ free(entry);
+
+ r = 0;
+
+done:
+ br_write_unlock();
+
+ return r;
+}
+
+static void ioport__unregister_all(void)
+{
+ struct ioport *entry;
+ struct rb_node *rb;
+ struct rb_int_node *rb_node;
+
+ rb = rb_first(&ioport_tree);
+ while (rb) {
+ rb_node = rb_int(rb);
+ entry = ioport_node(rb_node);
+ ioport_remove(&ioport_tree, entry);
+ free(entry);
+ rb = rb_first(&ioport_tree);
+ }
+}
+
+static const char *to_direction(int direction)
+{
+ if (direction == KVM_EXIT_IO_IN)
+ return "IN";
+ else
+ return "OUT";
+}
+
+static void ioport_error(u16 port, void *data, int direction, int size, u32 count)
+{
+ fprintf(stderr, "IO error: %s port=%x, size=%d, count=%u\n", to_direction(direction), port, size, count);
+}
+
+bool kvm__emulate_io(struct kvm *kvm, u16 port, void *data, int direction, int size, u32 count)
+{
+ struct ioport_operations *ops;
+ bool ret = false;
+ struct ioport *entry;
+ void *ptr = data;
+
+ br_read_lock();
+ entry = ioport_search(&ioport_tree, port);
+ if (!entry)
+ goto error;
+
+ ops = entry->ops;
+
+ while (count--) {
+ if (direction == KVM_EXIT_IO_IN && ops->io_in)
+ ret = ops->io_in(entry, kvm, port, ptr, size);
+ else if (ops->io_out)
+ ret = ops->io_out(entry, kvm, port, ptr, size);
+
+ ptr += size;
+ }
+
+ br_read_unlock();
+
+ if (!ret)
+ goto error;
+
+ return true;
+error:
+ br_read_unlock();
+
+ if (ioport_debug)
+ ioport_error(port, data, direction, size, count);
+
+ return !ioport_debug;
+}
+
+int ioport__init(struct kvm *kvm)
+{
+ return 0;
+}
+
+int ioport__exit(struct kvm *kvm)
+{
+ ioport__unregister_all();
+ return 0;
+}
--- /dev/null
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+
+/* user defined header files */
+#include "kvm/builtin-debug.h"
+#include "kvm/builtin-pause.h"
+#include "kvm/builtin-resume.h"
+#include "kvm/builtin-balloon.h"
+#include "kvm/builtin-list.h"
+#include "kvm/builtin-version.h"
+#include "kvm/builtin-setup.h"
+#include "kvm/builtin-stop.h"
+#include "kvm/builtin-stat.h"
+#include "kvm/builtin-help.h"
+#include "kvm/builtin-sandbox.h"
+#include "kvm/kvm-cmd.h"
+#include "kvm/builtin-run.h"
+#include "kvm/util.h"
+
+struct cmd_struct kvm_commands[] = {
+ { "pause", kvm_cmd_pause, kvm_pause_help, 0 },
+ { "resume", kvm_cmd_resume, kvm_resume_help, 0 },
+ { "debug", kvm_cmd_debug, kvm_debug_help, 0 },
+ { "balloon", kvm_cmd_balloon, kvm_balloon_help, 0 },
+ { "list", kvm_cmd_list, kvm_list_help, 0 },
+ { "version", kvm_cmd_version, NULL, 0 },
+ { "--version", kvm_cmd_version, NULL, 0 },
+ { "stop", kvm_cmd_stop, kvm_stop_help, 0 },
+ { "stat", kvm_cmd_stat, kvm_stat_help, 0 },
+ { "help", kvm_cmd_help, NULL, 0 },
+ { "setup", kvm_cmd_setup, kvm_setup_help, 0 },
+ { "run", kvm_cmd_run, kvm_run_help, 0 },
+ { "sandbox", kvm_cmd_sandbox, kvm_run_help, 0 },
+ { NULL, NULL, NULL, 0 },
+};
+
+/*
+ * kvm_get_command: Searches the command in an array of the commands and
+ * returns a pointer to cmd_struct if a match is found.
+ *
+ * Input parameters:
+ * command: Array of possible commands. The last entry in the array must be
+ * NULL.
+ * cmd: A string command to search in the array
+ *
+ * Return Value:
+ * NULL: If the cmd is not matched with any of the command in the command array
+ * p: Pointer to cmd_struct of the matching command
+ */
+struct cmd_struct *kvm_get_command(struct cmd_struct *command,
+ const char *cmd)
+{
+ struct cmd_struct *p = command;
+
+ while (p->cmd) {
+ if (!strcmp(p->cmd, cmd))
+ return p;
+ p++;
+ }
+ return NULL;
+}
+
+int handle_command(struct cmd_struct *command, int argc, const char **argv)
+{
+ struct cmd_struct *p;
+ const char *prefix = NULL;
+ int ret = 0;
+
+ if (!argv || !*argv) {
+ p = kvm_get_command(command, "help");
+ BUG_ON(!p);
+ return p->fn(argc, argv, prefix);
+ }
+
+ p = kvm_get_command(command, argv[0]);
+ if (!p) {
+ p = kvm_get_command(command, "help");
+ BUG_ON(!p);
+ p->fn(0, NULL, prefix);
+ return EINVAL;
+ }
+
+ ret = p->fn(argc - 1, &argv[1], prefix);
+ if (ret < 0) {
+ if (errno == EPERM)
+ die("Permission error - are you root?");
+ }
+
+ return ret;
+}
--- /dev/null
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/symbol.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+
+extern struct kvm_cpu **kvm_cpus;
+extern __thread struct kvm_cpu *current_kvm_cpu;
+
+void kvm_cpu__enable_singlestep(struct kvm_cpu *vcpu)
+{
+ struct kvm_guest_debug debug = {
+ .control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP,
+ };
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_GUEST_DEBUG, &debug) < 0)
+ pr_warning("KVM_SET_GUEST_DEBUG failed");
+}
+
+void kvm_cpu__run(struct kvm_cpu *vcpu)
+{
+ int err;
+
+ if (!vcpu->is_running)
+ return;
+
+ err = ioctl(vcpu->vcpu_fd, KVM_RUN, 0);
+ if (err < 0 && (errno != EINTR && errno != EAGAIN))
+ die_perror("KVM_RUN failed");
+}
+
+static void kvm_cpu_signal_handler(int signum)
+{
+ if (signum == SIGKVMEXIT) {
+ if (current_kvm_cpu && current_kvm_cpu->is_running) {
+ current_kvm_cpu->is_running = false;
+ kvm__continue();
+ }
+ } else if (signum == SIGKVMPAUSE) {
+ current_kvm_cpu->paused = 1;
+ }
+}
+
+static void kvm_cpu__handle_coalesced_mmio(struct kvm_cpu *cpu)
+{
+ if (cpu->ring) {
+ while (cpu->ring->first != cpu->ring->last) {
+ struct kvm_coalesced_mmio *m;
+ m = &cpu->ring->coalesced_mmio[cpu->ring->first];
+ kvm_cpu__emulate_mmio(cpu->kvm,
+ m->phys_addr,
+ m->data,
+ m->len,
+ 1);
+ cpu->ring->first = (cpu->ring->first + 1) % KVM_COALESCED_MMIO_MAX;
+ }
+ }
+}
+
+void kvm_cpu__reboot(void)
+{
+ int i;
+
+ /* The kvm_cpus array contains a null pointer in the last location */
+ for (i = 0; ; i++) {
+ if (kvm_cpus[i])
+ pthread_kill(kvm_cpus[i]->thread, SIGKVMEXIT);
+ else
+ break;
+ }
+}
+
+int kvm_cpu__start(struct kvm_cpu *cpu)
+{
+ sigset_t sigset;
+
+ sigemptyset(&sigset);
+ sigaddset(&sigset, SIGALRM);
+
+ pthread_sigmask(SIG_BLOCK, &sigset, NULL);
+
+ signal(SIGKVMEXIT, kvm_cpu_signal_handler);
+ signal(SIGKVMPAUSE, kvm_cpu_signal_handler);
+
+ kvm_cpu__reset_vcpu(cpu);
+
+ if (cpu->kvm->single_step)
+ kvm_cpu__enable_singlestep(cpu);
+
+ while (cpu->is_running) {
+ if (cpu->paused) {
+ kvm__notify_paused();
+ cpu->paused = 0;
+ }
+
+ if (cpu->needs_nmi) {
+ kvm_cpu__arch_nmi(cpu);
+ cpu->needs_nmi = 0;
+ }
+
+ kvm_cpu__run(cpu);
+
+ switch (cpu->kvm_run->exit_reason) {
+ case KVM_EXIT_UNKNOWN:
+ break;
+ case KVM_EXIT_DEBUG:
+ kvm_cpu__show_registers(cpu);
+ kvm_cpu__show_code(cpu);
+ break;
+ case KVM_EXIT_IO: {
+ bool ret;
+
+ ret = kvm_cpu__emulate_io(cpu->kvm,
+ cpu->kvm_run->io.port,
+ (u8 *)cpu->kvm_run +
+ cpu->kvm_run->io.data_offset,
+ cpu->kvm_run->io.direction,
+ cpu->kvm_run->io.size,
+ cpu->kvm_run->io.count);
+
+ if (!ret)
+ goto panic_kvm;
+ break;
+ }
+ case KVM_EXIT_MMIO: {
+ bool ret;
+
+ /*
+ * If we had MMIO exit, coalesced ring should be processed
+ * *before* processing the exit itself
+ */
+ kvm_cpu__handle_coalesced_mmio(cpu);
+
+ ret = kvm_cpu__emulate_mmio(cpu->kvm,
+ cpu->kvm_run->mmio.phys_addr,
+ cpu->kvm_run->mmio.data,
+ cpu->kvm_run->mmio.len,
+ cpu->kvm_run->mmio.is_write);
+
+ if (!ret)
+ goto panic_kvm;
+ break;
+ }
+ case KVM_EXIT_INTR:
+ if (cpu->is_running)
+ break;
+ goto exit_kvm;
+ case KVM_EXIT_SHUTDOWN:
+ goto exit_kvm;
+ default: {
+ bool ret;
+
+ ret = kvm_cpu__handle_exit(cpu);
+ if (!ret)
+ goto panic_kvm;
+ break;
+ }
+ }
+ kvm_cpu__handle_coalesced_mmio(cpu);
+ }
+
+exit_kvm:
+ return 0;
+
+panic_kvm:
+ return 1;
+}
--- /dev/null
+#include "kvm/kvm-ipc.h"
+#include "kvm/rwsem.h"
+#include "kvm/read-write.h"
+#include "kvm/util.h"
+
+#include <sys/epoll.h>
+#include <sys/un.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/eventfd.h>
+
+struct kvm_ipc_head {
+ u32 type;
+ u32 len;
+};
+
+#define KVM_IPC_MAX_MSGS 16
+
+static void (*msgs[KVM_IPC_MAX_MSGS])(int fd, u32 type, u32 len, u8 *msg);
+static DECLARE_RWSEM(msgs_rwlock);
+static int epoll_fd, server_fd, stop_fd;
+static pthread_t thread;
+
+int kvm_ipc__register_handler(u32 type, void (*cb)(int fd, u32 type, u32 len, u8 *msg))
+{
+ if (type >= KVM_IPC_MAX_MSGS)
+ return -ENOSPC;
+
+ down_write(&msgs_rwlock);
+ msgs[type] = cb;
+ up_write(&msgs_rwlock);
+
+ return 0;
+}
+
+int kvm_ipc__send(int fd, u32 type)
+{
+ struct kvm_ipc_head head = {.type = type, .len = 0,};
+
+ if (write_in_full(fd, &head, sizeof(head)) < 0)
+ return -1;
+
+ return 0;
+}
+
+int kvm_ipc__send_msg(int fd, u32 type, u32 len, u8 *msg)
+{
+ struct kvm_ipc_head head = {.type = type, .len = len,};
+
+ if (write_in_full(fd, &head, sizeof(head)) < 0)
+ return -1;
+
+ if (write_in_full(fd, msg, len) < 0)
+ return -1;
+
+ return 0;
+}
+
+static int kvm_ipc__handle(int fd, u32 type, u32 len, u8 *data)
+{
+ void (*cb)(int fd, u32 type, u32 len, u8 *msg);
+
+ if (type >= KVM_IPC_MAX_MSGS)
+ return -ENOSPC;
+
+ down_read(&msgs_rwlock);
+ cb = msgs[type];
+ up_read(&msgs_rwlock);
+
+ if (cb == NULL) {
+ pr_warning("No device handles type %u\n", type);
+ return -ENODEV;
+ }
+
+ cb(fd, type, len, data);
+
+ return 0;
+}
+
+static int kvm_ipc__new_conn(int fd)
+{
+ int client;
+ struct epoll_event ev;
+
+ client = accept(fd, NULL, NULL);
+ if (client < 0)
+ return -1;
+
+ ev.events = EPOLLIN | EPOLLRDHUP;
+ ev.data.fd = client;
+ if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, client, &ev) < 0) {
+ close(client);
+ return -1;
+ }
+
+ return client;
+}
+
+static void kvm_ipc__close_conn(int fd)
+{
+ epoll_ctl(epoll_fd, EPOLL_CTL_DEL, fd, NULL);
+ close(fd);
+}
+
+static int kvm_ipc__receive(int fd)
+{
+ struct kvm_ipc_head head;
+ u8 *msg = NULL;
+ u32 n;
+
+ n = read(fd, &head, sizeof(head));
+ if (n != sizeof(head))
+ goto done;
+
+ msg = malloc(head.len);
+ if (msg == NULL)
+ goto done;
+
+ n = read_in_full(fd, msg, head.len);
+ if (n != head.len)
+ goto done;
+
+ kvm_ipc__handle(fd, head.type, head.len, msg);
+
+ return 0;
+
+done:
+ free(msg);
+ return -1;
+}
+
+static void *kvm_ipc__thread(void *param)
+{
+ struct epoll_event event;
+
+ for (;;) {
+ int nfds;
+
+ nfds = epoll_wait(epoll_fd, &event, 1, -1);
+ if (nfds > 0) {
+ int fd = event.data.fd;
+
+ if (fd == stop_fd && event.events & EPOLLIN) {
+ break;
+ } else if (fd == server_fd) {
+ int client, r;
+
+ client = kvm_ipc__new_conn(fd);
+ /*
+ * Handle multiple IPC cmd at a time
+ */
+ do {
+ r = kvm_ipc__receive(client);
+ } while (r == 0);
+
+ } else if (event.events & (EPOLLERR | EPOLLRDHUP | EPOLLHUP)) {
+ kvm_ipc__close_conn(fd);
+ } else {
+ kvm_ipc__receive(fd);
+ }
+ }
+ }
+
+ return NULL;
+}
+
+int kvm_ipc__start(int sock)
+{
+ int ret;
+ struct epoll_event ev = {0};
+
+ server_fd = sock;
+
+ epoll_fd = epoll_create(KVM_IPC_MAX_MSGS);
+ if (epoll_fd < 0) {
+ ret = epoll_fd;
+ goto err;
+ }
+
+ ev.events = EPOLLIN | EPOLLET;
+ ev.data.fd = sock;
+ if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, sock, &ev) < 0) {
+ pr_err("Failed starting IPC thread");
+ ret = -EFAULT;
+ goto err_epoll;
+ }
+
+ stop_fd = eventfd(0, 0);
+ if (stop_fd < 0) {
+ ret = stop_fd;
+ goto err_epoll;
+ }
+
+ ev.events = EPOLLIN | EPOLLET;
+ ev.data.fd = stop_fd;
+ if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, stop_fd, &ev) < 0) {
+ pr_err("Failed adding stop event to epoll");
+ ret = -EFAULT;
+ goto err_stop;
+ }
+
+ if (pthread_create(&thread, NULL, kvm_ipc__thread, NULL) != 0) {
+ pr_err("Failed starting IPC thread");
+ ret = -EFAULT;
+ goto err_stop;
+ }
+
+ return 0;
+
+err_stop:
+ close(stop_fd);
+err_epoll:
+ close(epoll_fd);
+err:
+ return ret;
+}
+
+int kvm_ipc__stop(void)
+{
+ u64 val = 1;
+ int ret;
+
+ ret = write(stop_fd, &val, sizeof(val));
+ if (ret < 0)
+ return ret;
+
+ close(server_fd);
+ close(epoll_fd);
+
+ return ret;
+}
--- /dev/null
+#include "kvm/kvm.h"
+#include "kvm/read-write.h"
+#include "kvm/util.h"
+#include "kvm/strbuf.h"
+#include "kvm/mutex.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/kvm-ipc.h"
+
+#include <linux/kvm.h>
+#include <linux/err.h>
+
+#include <sys/un.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+#include <limits.h>
+#include <signal.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <time.h>
+#include <sys/eventfd.h>
+#include <asm/unistd.h>
+#include <dirent.h>
+
+#define DEFINE_KVM_EXIT_REASON(reason) [reason] = #reason
+
+const char *kvm_exit_reasons[] = {
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_UNKNOWN),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_EXCEPTION),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_IO),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_HYPERCALL),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_DEBUG),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_HLT),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_MMIO),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_IRQ_WINDOW_OPEN),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_SHUTDOWN),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_FAIL_ENTRY),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_INTR),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_SET_TPR),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_TPR_ACCESS),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_S390_SIEIC),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_S390_RESET),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_DCR),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_NMI),
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_INTERNAL_ERROR),
+#ifdef CONFIG_PPC64
+ DEFINE_KVM_EXIT_REASON(KVM_EXIT_PAPR_HCALL),
+#endif
+};
+
+extern struct kvm *kvm;
+extern struct kvm_cpu **kvm_cpus;
+static int pause_event;
+static DEFINE_MUTEX(pause_lock);
+extern struct kvm_ext kvm_req_ext[];
+
+static char kvm_dir[PATH_MAX];
+
+static int set_dir(const char *fmt, va_list args)
+{
+ char tmp[PATH_MAX];
+
+ vsnprintf(tmp, sizeof(tmp), fmt, args);
+
+ mkdir(tmp, 0777);
+
+ if (!realpath(tmp, kvm_dir))
+ return -errno;
+
+ strcat(kvm_dir, "/");
+
+ return 0;
+}
+
+void kvm__set_dir(const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ set_dir(fmt, args);
+ va_end(args);
+}
+
+const char *kvm__get_dir(void)
+{
+ return kvm_dir;
+}
+
+bool kvm__supports_extension(struct kvm *kvm, unsigned int extension)
+{
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, extension);
+ if (ret < 0)
+ return false;
+
+ return ret;
+}
+
+static int kvm__check_extensions(struct kvm *kvm)
+{
+ int i;
+
+ for (i = 0; ; i++) {
+ if (!kvm_req_ext[i].name)
+ break;
+ if (!kvm__supports_extension(kvm, kvm_req_ext[i].code)) {
+ pr_err("Unsuppored KVM extension detected: %s",
+ kvm_req_ext[i].name);
+ return -i;
+ }
+ }
+
+ return 0;
+}
+
+static struct kvm *kvm__new(void)
+{
+ struct kvm *kvm = calloc(1, sizeof(*kvm));
+ if (!kvm)
+ return ERR_PTR(-ENOMEM);
+
+ kvm->sys_fd = -1;
+ kvm->vm_fd = -1;
+
+ return kvm;
+}
+
+#define KVM_SOCK_SUFFIX ".sock"
+#define KVM_SOCK_SUFFIX_LEN ((ssize_t)sizeof(KVM_SOCK_SUFFIX) - 1)
+
+static int kvm__create_socket(struct kvm *kvm)
+{
+ char full_name[PATH_MAX];
+ unsigned int s;
+ struct sockaddr_un local;
+ int len, r;
+
+ /* This usually 108 bytes long */
+ BUILD_BUG_ON(sizeof(local.sun_path) < 32);
+
+ if (!kvm->name)
+ return -EINVAL;
+
+ snprintf(full_name, sizeof(full_name), "%s/%s%s",
+ kvm__get_dir(), kvm->name, KVM_SOCK_SUFFIX);
+ if (access(full_name, F_OK) == 0) {
+ pr_err("Socket file %s already exist", full_name);
+ return -EEXIST;
+ }
+
+ s = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (s < 0)
+ return s;
+ local.sun_family = AF_UNIX;
+ strlcpy(local.sun_path, full_name, sizeof(local.sun_path));
+ len = strlen(local.sun_path) + sizeof(local.sun_family);
+ r = bind(s, (struct sockaddr *)&local, len);
+ if (r < 0)
+ goto fail;
+
+ r = listen(s, 5);
+ if (r < 0)
+ goto fail;
+
+ return s;
+
+fail:
+ close(s);
+ return r;
+}
+
+void kvm__remove_socket(const char *name)
+{
+ char full_name[PATH_MAX];
+
+ snprintf(full_name, sizeof(full_name), "%s/%s%s",
+ kvm__get_dir(), name, KVM_SOCK_SUFFIX);
+ unlink(full_name);
+}
+
+int kvm__get_sock_by_instance(const char *name)
+{
+ int s, len, r;
+ char sock_file[PATH_MAX];
+ struct sockaddr_un local;
+
+ snprintf(sock_file, sizeof(sock_file), "%s/%s%s",
+ kvm__get_dir(), name, KVM_SOCK_SUFFIX);
+ s = socket(AF_UNIX, SOCK_STREAM, 0);
+
+ local.sun_family = AF_UNIX;
+ strlcpy(local.sun_path, sock_file, sizeof(local.sun_path));
+ len = strlen(local.sun_path) + sizeof(local.sun_family);
+
+ r = connect(s, &local, len);
+ if (r < 0 && errno == ECONNREFUSED) {
+ /* Tell the user clean ghost socket file */
+ pr_err("\"%s\" could be a ghost socket file, please remove it",
+ sock_file);
+ return r;
+ } else if (r < 0) {
+ return r;
+ }
+
+ return s;
+}
+
+int kvm__enumerate_instances(int (*callback)(const char *name, int fd))
+{
+ int sock;
+ DIR *dir;
+ struct dirent entry, *result;
+ int ret = 0;
+
+ dir = opendir(kvm__get_dir());
+ if (!dir)
+ return -errno;
+
+ for (;;) {
+ readdir_r(dir, &entry, &result);
+ if (result == NULL)
+ break;
+ if (entry.d_type == DT_SOCK) {
+ ssize_t name_len = strlen(entry.d_name);
+ char *p;
+
+ if (name_len <= KVM_SOCK_SUFFIX_LEN)
+ continue;
+
+ p = &entry.d_name[name_len - KVM_SOCK_SUFFIX_LEN];
+ if (memcmp(KVM_SOCK_SUFFIX, p, KVM_SOCK_SUFFIX_LEN))
+ continue;
+
+ *p = 0;
+ sock = kvm__get_sock_by_instance(entry.d_name);
+ if (sock < 0)
+ continue;
+ ret = callback(entry.d_name, sock);
+ close(sock);
+ if (ret < 0)
+ break;
+ }
+ }
+
+ closedir(dir);
+
+ return ret;
+}
+
+int kvm__exit(struct kvm *kvm)
+{
+ kvm__stop_timer(kvm);
+
+ kvm__arch_delete_ram(kvm);
+ kvm_ipc__stop();
+ kvm__remove_socket(kvm->name);
+ free(kvm->name);
+ free(kvm);
+
+ return 0;
+}
+
+/*
+ * Note: KVM_SET_USER_MEMORY_REGION assumes that we don't pass overlapping
+ * memory regions to it. Therefore, be careful if you use this function for
+ * registering memory regions for emulating hardware.
+ */
+int kvm__register_mem(struct kvm *kvm, u64 guest_phys, u64 size, void *userspace_addr)
+{
+ struct kvm_userspace_memory_region mem;
+ int ret;
+
+ mem = (struct kvm_userspace_memory_region) {
+ .slot = kvm->mem_slots++,
+ .guest_phys_addr = guest_phys,
+ .memory_size = size,
+ .userspace_addr = (unsigned long)userspace_addr,
+ };
+
+ ret = ioctl(kvm->vm_fd, KVM_SET_USER_MEMORY_REGION, &mem);
+ if (ret < 0)
+ return -errno;
+
+ return 0;
+}
+
+int kvm__recommended_cpus(struct kvm *kvm)
+{
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_NR_VCPUS);
+ if (ret <= 0)
+ /*
+ * api.txt states that if KVM_CAP_NR_VCPUS does not exist,
+ * assume 4.
+ */
+ return 4;
+
+ return ret;
+}
+
+static void kvm__pid(int fd, u32 type, u32 len, u8 *msg)
+{
+ pid_t pid = getpid();
+ int r = 0;
+
+ if (type == KVM_IPC_PID)
+ r = write(fd, &pid, sizeof(pid));
+
+ if (r < 0)
+ pr_warning("Failed sending PID");
+}
+
+/*
+ * The following hack should be removed once 'x86: Raise the hard
+ * VCPU count limit' makes it's way into the mainline.
+ */
+#ifndef KVM_CAP_MAX_VCPUS
+#define KVM_CAP_MAX_VCPUS 66
+#endif
+
+int kvm__max_cpus(struct kvm *kvm)
+{
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_MAX_VCPUS);
+ if (ret <= 0)
+ ret = kvm__recommended_cpus(kvm);
+
+ return ret;
+}
+
+struct kvm *kvm__init(const char *kvm_dev, const char *hugetlbfs_path, u64 ram_size, const char *name)
+{
+ struct kvm *kvm;
+ int ret;
+
+ if (!kvm__arch_cpu_supports_vm()) {
+ pr_err("Your CPU does not support hardware virtualization");
+ ret = -ENOSYS;
+ goto err;
+ }
+
+ kvm = kvm__new();
+ if (IS_ERR(kvm))
+ return kvm;
+
+ kvm->sys_fd = open(kvm_dev, O_RDWR);
+ if (kvm->sys_fd < 0) {
+ if (errno == ENOENT)
+ pr_err("'%s' not found. Please make sure your kernel has CONFIG_KVM "
+ "enabled and that the KVM modules are loaded.", kvm_dev);
+ else if (errno == ENODEV)
+ pr_err("'%s' KVM driver not available.\n # (If the KVM "
+ "module is loaded then 'dmesg' may offer further clues "
+ "about the failure.)", kvm_dev);
+ else
+ pr_err("Could not open %s: ", kvm_dev);
+
+ ret = -errno;
+ goto err_free;
+ }
+
+ ret = ioctl(kvm->sys_fd, KVM_GET_API_VERSION, 0);
+ if (ret != KVM_API_VERSION) {
+ pr_err("KVM_API_VERSION ioctl");
+ ret = -errno;
+ goto err_sys_fd;
+ }
+
+ kvm->vm_fd = ioctl(kvm->sys_fd, KVM_CREATE_VM, 0);
+ if (kvm->vm_fd < 0) {
+ ret = kvm->vm_fd;
+ goto err_sys_fd;
+ }
+
+ kvm->name = strdup(name);
+ if (!kvm->name) {
+ ret = -ENOMEM;
+ goto err_vm_fd;
+ }
+
+ if (kvm__check_extensions(kvm)) {
+ pr_err("A required KVM extention is not supported by OS");
+ ret = -ENOSYS;
+ goto err_vm_fd;
+ }
+
+ kvm__arch_init(kvm, hugetlbfs_path, ram_size);
+
+ ret = kvm_ipc__start(kvm__create_socket(kvm));
+ if (ret < 0) {
+ pr_err("Starting ipc failed.");
+ goto err_vm_fd;
+ }
+
+ ret = kvm_ipc__register_handler(KVM_IPC_PID, kvm__pid);
+ if (ret < 0) {
+ pr_err("Register ipc handler failed.");
+ goto err_ipc;
+ }
+
+ return kvm;
+
+err_ipc:
+ kvm_ipc__stop();
+err_vm_fd:
+ close(kvm->vm_fd);
+err_sys_fd:
+ close(kvm->sys_fd);
+err_free:
+ free(kvm);
+err:
+ return ERR_PTR(ret);
+}
+
+/* RFC 1952 */
+#define GZIP_ID1 0x1f
+#define GZIP_ID2 0x8b
+#define CPIO_MAGIC "0707"
+/* initrd may be gzipped, or a plain cpio */
+static bool initrd_check(int fd)
+{
+ unsigned char id[4];
+
+ if (read_in_full(fd, id, ARRAY_SIZE(id)) < 0)
+ return false;
+
+ if (lseek(fd, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ return (id[0] == GZIP_ID1 && id[1] == GZIP_ID2) ||
+ !memcmp(id, CPIO_MAGIC, 4);
+}
+
+bool kvm__load_kernel(struct kvm *kvm, const char *kernel_filename,
+ const char *initrd_filename, const char *kernel_cmdline, u16 vidmode)
+{
+ bool ret;
+ int fd_kernel = -1, fd_initrd = -1;
+
+ fd_kernel = open(kernel_filename, O_RDONLY);
+ if (fd_kernel < 0)
+ die("Unable to open kernel %s", kernel_filename);
+
+ if (initrd_filename) {
+ fd_initrd = open(initrd_filename, O_RDONLY);
+ if (fd_initrd < 0)
+ die("Unable to open initrd %s", initrd_filename);
+
+ if (!initrd_check(fd_initrd))
+ die("%s is not an initrd", initrd_filename);
+ }
+
+ ret = load_bzimage(kvm, fd_kernel, fd_initrd, kernel_cmdline, vidmode);
+
+ if (ret)
+ goto found_kernel;
+
+ pr_warning("%s is not a bzImage. Trying to load it as a flat binary...", kernel_filename);
+
+ ret = load_flat_binary(kvm, fd_kernel, fd_initrd, kernel_cmdline);
+
+ if (ret)
+ goto found_kernel;
+
+ if (initrd_filename)
+ close(fd_initrd);
+ close(fd_kernel);
+
+ die("%s is not a valid bzImage or flat binary", kernel_filename);
+
+found_kernel:
+ if (initrd_filename)
+ close(fd_initrd);
+ close(fd_kernel);
+
+ return ret;
+}
+
+#define TIMER_INTERVAL_NS 1000000 /* 1 msec */
+
+/*
+ * This function sets up a timer that's used to inject interrupts from the
+ * userspace hypervisor into the guest at periodical intervals. Please note
+ * that clock interrupt, for example, is not handled here.
+ */
+void kvm__start_timer(struct kvm *kvm)
+{
+ struct itimerspec its;
+ struct sigevent sev;
+
+ memset(&sev, 0, sizeof(struct sigevent));
+ sev.sigev_value.sival_int = 0;
+ sev.sigev_notify = SIGEV_THREAD_ID;
+ sev.sigev_signo = SIGALRM;
+ sev._sigev_un._tid = syscall(__NR_gettid);
+
+ if (timer_create(CLOCK_REALTIME, &sev, &kvm->timerid) < 0)
+ die("timer_create()");
+
+ its.it_value.tv_sec = TIMER_INTERVAL_NS / 1000000000;
+ its.it_value.tv_nsec = TIMER_INTERVAL_NS % 1000000000;
+ its.it_interval.tv_sec = its.it_value.tv_sec;
+ its.it_interval.tv_nsec = its.it_value.tv_nsec;
+
+ if (timer_settime(kvm->timerid, 0, &its, NULL) < 0)
+ die("timer_settime()");
+}
+
+void kvm__stop_timer(struct kvm *kvm)
+{
+ if (kvm->timerid)
+ if (timer_delete(kvm->timerid) < 0)
+ die("timer_delete()");
+
+ kvm->timerid = 0;
+}
+
+void kvm__dump_mem(struct kvm *kvm, unsigned long addr, unsigned long size)
+{
+ unsigned char *p;
+ unsigned long n;
+
+ size &= ~7; /* mod 8 */
+ if (!size)
+ return;
+
+ p = guest_flat_to_host(kvm, addr);
+
+ for (n = 0; n < size; n += 8) {
+ if (!host_ptr_in_ram(kvm, p + n))
+ break;
+
+ printf(" 0x%08lx: %02x %02x %02x %02x %02x %02x %02x %02x\n",
+ addr + n, p[n + 0], p[n + 1], p[n + 2], p[n + 3],
+ p[n + 4], p[n + 5], p[n + 6], p[n + 7]);
+ }
+}
+
+void kvm__pause(void)
+{
+ int i, paused_vcpus = 0;
+
+ /* Check if the guest is running */
+ if (!kvm_cpus[0] || kvm_cpus[0]->thread == 0)
+ return;
+
+ mutex_lock(&pause_lock);
+
+ pause_event = eventfd(0, 0);
+ if (pause_event < 0)
+ die("Failed creating pause notification event");
+ for (i = 0; i < kvm->nrcpus; i++)
+ pthread_kill(kvm_cpus[i]->thread, SIGKVMPAUSE);
+
+ while (paused_vcpus < kvm->nrcpus) {
+ u64 cur_read;
+
+ if (read(pause_event, &cur_read, sizeof(cur_read)) < 0)
+ die("Failed reading pause event");
+ paused_vcpus += cur_read;
+ }
+ close(pause_event);
+}
+
+void kvm__continue(void)
+{
+ /* Check if the guest is running */
+ if (!kvm_cpus[0] || kvm_cpus[0]->thread == 0)
+ return;
+
+ mutex_unlock(&pause_lock);
+}
+
+void kvm__notify_paused(void)
+{
+ u64 p = 1;
+
+ if (write(pause_event, &p, sizeof(p)) < 0)
+ die("Failed notifying of paused VCPU.");
+
+ mutex_lock(&pause_lock);
+ mutex_unlock(&pause_lock);
+}
--- /dev/null
+#include "kvm/kvm.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+
+/* user defined header files */
+#include <kvm/kvm-cmd.h>
+
+static int handle_kvm_command(int argc, char **argv)
+{
+ return handle_command(kvm_commands, argc, (const char **) &argv[0]);
+}
+
+int main(int argc, char *argv[])
+{
+ kvm__set_dir("%s/%s", HOME_DIR, KVM_PID_FILE_PATH);
+
+ return handle_kvm_command(argc - 1, &argv[1]);
+}
--- /dev/null
+#include "kvm/kvm.h"
+#include "kvm/rbtree-interval.h"
+#include "kvm/brlock.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#include <sys/ioctl.h>
+#include <linux/kvm.h>
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/err.h>
+#include <errno.h>
+
+#define mmio_node(n) rb_entry(n, struct mmio_mapping, node)
+
+struct mmio_mapping {
+ struct rb_int_node node;
+ void (*mmio_fn)(u64 addr, u8 *data, u32 len, u8 is_write, void *ptr);
+ void *ptr;
+};
+
+static struct rb_root mmio_tree = RB_ROOT;
+bool mmio_debug = false;
+
+static struct mmio_mapping *mmio_search(struct rb_root *root, u64 addr, u64 len)
+{
+ struct rb_int_node *node;
+
+ node = rb_int_search_range(root, addr, addr + len);
+ if (node == NULL)
+ return NULL;
+
+ return mmio_node(node);
+}
+
+/* Find lowest match, Check for overlap */
+static struct mmio_mapping *mmio_search_single(struct rb_root *root, u64 addr)
+{
+ struct rb_int_node *node;
+
+ node = rb_int_search_single(root, addr);
+ if (node == NULL)
+ return NULL;
+
+ return mmio_node(node);
+}
+
+static int mmio_insert(struct rb_root *root, struct mmio_mapping *data)
+{
+ return rb_int_insert(root, &data->node);
+}
+
+static const char *to_direction(u8 is_write)
+{
+ if (is_write)
+ return "write";
+
+ return "read";
+}
+
+int kvm__register_mmio(struct kvm *kvm, u64 phys_addr, u64 phys_addr_len, bool coalesce,
+ void (*mmio_fn)(u64 addr, u8 *data, u32 len, u8 is_write, void *ptr),
+ void *ptr)
+{
+ struct mmio_mapping *mmio;
+ struct kvm_coalesced_mmio_zone zone;
+ int ret;
+
+ mmio = malloc(sizeof(*mmio));
+ if (mmio == NULL)
+ return -ENOMEM;
+
+ *mmio = (struct mmio_mapping) {
+ .node = RB_INT_INIT(phys_addr, phys_addr + phys_addr_len),
+ .mmio_fn = mmio_fn,
+ .ptr = ptr,
+ };
+
+ if (coalesce) {
+ zone = (struct kvm_coalesced_mmio_zone) {
+ .addr = phys_addr,
+ .size = phys_addr_len,
+ };
+ ret = ioctl(kvm->vm_fd, KVM_REGISTER_COALESCED_MMIO, &zone);
+ if (ret < 0) {
+ free(mmio);
+ return -errno;
+ }
+ }
+ br_write_lock();
+ ret = mmio_insert(&mmio_tree, mmio);
+ br_write_unlock();
+
+ return ret;
+}
+
+bool kvm__deregister_mmio(struct kvm *kvm, u64 phys_addr)
+{
+ struct mmio_mapping *mmio;
+ struct kvm_coalesced_mmio_zone zone;
+
+ br_write_lock();
+ mmio = mmio_search_single(&mmio_tree, phys_addr);
+ if (mmio == NULL) {
+ br_write_unlock();
+ return false;
+ }
+
+ zone = (struct kvm_coalesced_mmio_zone) {
+ .addr = phys_addr,
+ .size = 1,
+ };
+ ioctl(kvm->vm_fd, KVM_UNREGISTER_COALESCED_MMIO, &zone);
+
+ rb_int_erase(&mmio_tree, &mmio->node);
+ br_write_unlock();
+
+ free(mmio);
+ return true;
+}
+
+bool kvm__emulate_mmio(struct kvm *kvm, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ struct mmio_mapping *mmio;
+
+ br_read_lock();
+ mmio = mmio_search(&mmio_tree, phys_addr, len);
+
+ if (mmio)
+ mmio->mmio_fn(phys_addr, data, len, is_write, mmio->ptr);
+ else {
+ if (mmio_debug)
+ fprintf(stderr, "Warning: Ignoring MMIO %s at %016llx (length %u)\n",
+ to_direction(is_write), phys_addr, len);
+ }
+ br_read_unlock();
+
+ return true;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+int uip_tx_do_arp(struct uip_tx_arg *arg)
+{
+ struct uip_arp *arp, *arp2;
+ struct uip_info *info;
+ struct uip_buf *buf;
+
+ info = arg->info;
+ buf = uip_buf_clone(arg);
+
+ arp = (struct uip_arp *)(arg->eth);
+ arp2 = (struct uip_arp *)(buf->eth);
+
+ /*
+ * ARP replay code: 2
+ */
+ arp2->op = htons(0x2);
+ arp2->dmac = arp->smac;
+ arp2->dip = arp->sip;
+
+ if (arp->dip == htonl(info->host_ip)) {
+ arp2->smac = info->host_mac;
+ arp2->sip = htonl(info->host_ip);
+
+ uip_buf_set_used(info, buf);
+ }
+
+ return 0;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+struct uip_buf *uip_buf_get_used(struct uip_info *info)
+{
+ struct uip_buf *buf;
+ bool found = false;
+
+ mutex_lock(&info->buf_lock);
+
+ while (!(info->buf_used_nr > 0))
+ pthread_cond_wait(&info->buf_used_cond, &info->buf_lock);
+
+ list_for_each_entry(buf, &info->buf_head, list) {
+ if (buf->status == UIP_BUF_STATUS_USED) {
+ /*
+ * Set status to INUSE immediately to prevent
+ * someone from using this buf until we free it
+ */
+ buf->status = UIP_BUF_STATUS_INUSE;
+ info->buf_used_nr--;
+ found = true;
+ break;
+ }
+ }
+
+ mutex_unlock(&info->buf_lock);
+
+ return found ? buf : NULL;
+}
+
+struct uip_buf *uip_buf_get_free(struct uip_info *info)
+{
+ struct uip_buf *buf;
+ bool found = false;
+
+ mutex_lock(&info->buf_lock);
+
+ while (!(info->buf_free_nr > 0))
+ pthread_cond_wait(&info->buf_free_cond, &info->buf_lock);
+
+ list_for_each_entry(buf, &info->buf_head, list) {
+ if (buf->status == UIP_BUF_STATUS_FREE) {
+ /*
+ * Set status to INUSE immediately to prevent
+ * someone from using this buf until we free it
+ */
+ buf->status = UIP_BUF_STATUS_INUSE;
+ info->buf_free_nr--;
+ found = true;
+ break;
+ }
+ }
+
+ mutex_unlock(&info->buf_lock);
+
+ return found ? buf : NULL;
+}
+
+struct uip_buf *uip_buf_set_used(struct uip_info *info, struct uip_buf *buf)
+{
+ mutex_lock(&info->buf_lock);
+
+ buf->status = UIP_BUF_STATUS_USED;
+ info->buf_used_nr++;
+ pthread_cond_signal(&info->buf_used_cond);
+
+ mutex_unlock(&info->buf_lock);
+
+ return buf;
+}
+
+struct uip_buf *uip_buf_set_free(struct uip_info *info, struct uip_buf *buf)
+{
+ mutex_lock(&info->buf_lock);
+
+ buf->status = UIP_BUF_STATUS_FREE;
+ info->buf_free_nr++;
+ pthread_cond_signal(&info->buf_free_cond);
+
+ mutex_unlock(&info->buf_lock);
+
+ return buf;
+}
+
+struct uip_buf *uip_buf_clone(struct uip_tx_arg *arg)
+{
+ struct uip_buf *buf;
+ struct uip_eth *eth2;
+ struct uip_info *info;
+
+ info = arg->info;
+
+ /*
+ * Get buffer from device to guest
+ */
+ buf = uip_buf_get_free(info);
+
+ /*
+ * Clone buffer
+ */
+ memcpy(buf->vnet, arg->vnet, arg->vnet_len);
+ memcpy(buf->eth, arg->eth, arg->eth_len);
+ buf->vnet_len = arg->vnet_len;
+ buf->eth_len = arg->eth_len;
+
+ eth2 = (struct uip_eth *)buf->eth;
+ eth2->src = info->host_mac;
+ eth2->dst = arg->eth->src;
+
+ return buf;
+}
--- /dev/null
+#include "kvm/mutex.h"
+#include "kvm/uip.h"
+
+#include <linux/virtio_net.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+
+int uip_tx(struct iovec *iov, u16 out, struct uip_info *info)
+{
+ struct virtio_net_hdr *vnet;
+ struct uip_tx_arg arg;
+ int eth_len, vnet_len;
+ struct uip_eth *eth;
+ u8 *buf = NULL;
+ u16 proto;
+ int i;
+
+ /*
+ * Buffer from guest to device
+ */
+ vnet_len = iov[0].iov_len;
+ vnet = iov[0].iov_base;
+
+ eth_len = iov[1].iov_len;
+ eth = iov[1].iov_base;
+
+ /*
+ * In case, ethernet frame is in more than one iov entry.
+ * Copy iov buffer into one linear buffer.
+ */
+ if (out > 2) {
+ eth_len = 0;
+ for (i = 1; i < out; i++)
+ eth_len += iov[i].iov_len;
+
+ buf = malloc(eth_len);
+ if (!buf)
+ return -1;
+
+ eth = (struct uip_eth *)buf;
+ for (i = 1; i < out; i++) {
+ memcpy(buf, iov[i].iov_base, iov[i].iov_len);
+ buf += iov[i].iov_len;
+ }
+ }
+
+ memset(&arg, 0, sizeof(arg));
+
+ arg.vnet_len = vnet_len;
+ arg.eth_len = eth_len;
+ arg.info = info;
+ arg.vnet = vnet;
+ arg.eth = eth;
+
+ /*
+ * Check package type
+ */
+ proto = ntohs(eth->type);
+
+ switch (proto) {
+ case UIP_ETH_P_ARP:
+ uip_tx_do_arp(&arg);
+ break;
+ case UIP_ETH_P_IP:
+ uip_tx_do_ipv4(&arg);
+ break;
+ default:
+ break;
+ }
+
+ if (out > 2 && buf)
+ free(eth);
+
+ return vnet_len + eth_len;
+}
+
+int uip_rx(struct iovec *iov, u16 in, struct uip_info *info)
+{
+ struct virtio_net_hdr *vnet;
+ struct uip_eth *eth;
+ struct uip_buf *buf;
+ int vnet_len;
+ int eth_len;
+ char *p;
+ int len;
+ int cnt;
+ int i;
+
+ /*
+ * Sleep until there is a buffer for guest
+ */
+ buf = uip_buf_get_used(info);
+
+ /*
+ * Fill device to guest buffer, vnet hdr fisrt
+ */
+ vnet_len = iov[0].iov_len;
+ vnet = iov[0].iov_base;
+ if (buf->vnet_len > vnet_len) {
+ len = -1;
+ goto out;
+ }
+ memcpy(vnet, buf->vnet, buf->vnet_len);
+
+ /*
+ * Then, the real eth data
+ * Note: Be sure buf->eth_len is not bigger than the buffer len that guest provides
+ */
+ cnt = buf->eth_len;
+ p = buf->eth;
+ for (i = 1; i < in; i++) {
+ eth_len = iov[i].iov_len;
+ eth = iov[i].iov_base;
+ if (cnt > eth_len) {
+ memcpy(eth, p, eth_len);
+ cnt -= eth_len;
+ p += eth_len;
+ } else {
+ memcpy(eth, p, cnt);
+ cnt -= cnt;
+ break;
+ }
+ }
+
+ if (cnt) {
+ pr_warning("uip_rx error");
+ len = -1;
+ goto out;
+ }
+
+ len = buf->vnet_len + buf->eth_len;
+
+out:
+ uip_buf_set_free(info, buf);
+ return len;
+}
+
+int uip_init(struct uip_info *info)
+{
+ struct list_head *udp_socket_head;
+ struct list_head *tcp_socket_head;
+ struct list_head *buf_head;
+ struct uip_buf *buf;
+ int buf_nr;
+ int i;
+
+ udp_socket_head = &info->udp_socket_head;
+ tcp_socket_head = &info->tcp_socket_head;
+ buf_head = &info->buf_head;
+ buf_nr = info->buf_nr;
+
+ INIT_LIST_HEAD(udp_socket_head);
+ INIT_LIST_HEAD(tcp_socket_head);
+ INIT_LIST_HEAD(buf_head);
+
+ pthread_mutex_init(&info->udp_socket_lock, NULL);
+ pthread_mutex_init(&info->tcp_socket_lock, NULL);
+ pthread_mutex_init(&info->buf_lock, NULL);
+
+ pthread_cond_init(&info->buf_used_cond, NULL);
+ pthread_cond_init(&info->buf_free_cond, NULL);
+
+
+ for (i = 0; i < buf_nr; i++) {
+ buf = malloc(sizeof(*buf));
+ memset(buf, 0, sizeof(*buf));
+
+ buf->status = UIP_BUF_STATUS_FREE;
+ buf->info = info;
+ buf->id = i;
+ list_add_tail(&buf->list, buf_head);
+ }
+
+ list_for_each_entry(buf, buf_head, list) {
+ buf->vnet = malloc(sizeof(struct virtio_net_hdr));
+ buf->vnet_len = sizeof(struct virtio_net_hdr);
+ buf->eth = malloc(1024*64 + sizeof(struct uip_pseudo_hdr));
+ buf->eth_len = 1024*64 + sizeof(struct uip_pseudo_hdr);
+
+ memset(buf->vnet, 0, buf->vnet_len);
+ memset(buf->eth, 0, buf->eth_len);
+ }
+
+ info->buf_free_nr = buf_nr;
+ info->buf_used_nr = 0;
+
+ uip_dhcp_get_dns(info);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+static u16 uip_csum(u16 csum, u8 *addr, u16 count)
+{
+ long sum = csum;
+
+ while (count > 1) {
+ sum += *(u16 *)addr;
+ addr += 2;
+ count -= 2;
+ }
+
+ if (count > 0)
+ sum += *(unsigned char *)addr;
+
+ while (sum>>16)
+ sum = (sum & 0xffff) + (sum >> 16);
+
+ return ~sum;
+}
+
+u16 uip_csum_ip(struct uip_ip *ip)
+{
+ return uip_csum(0, &ip->vhl, uip_ip_hdrlen(ip));
+}
+
+u16 uip_csum_icmp(struct uip_icmp *icmp)
+{
+ struct uip_ip *ip;
+
+ ip = &icmp->ip;
+ return icmp->csum = uip_csum(0, &icmp->type, htons(ip->len) - uip_ip_hdrlen(ip) - 8); /* icmp header len = 8 */
+}
+
+u16 uip_csum_udp(struct uip_udp *udp)
+{
+ struct uip_pseudo_hdr hdr;
+ struct uip_ip *ip;
+ int udp_len;
+ u8 *pad;
+
+ ip = &udp->ip;
+
+ hdr.sip = ip->sip;
+ hdr.dip = ip->dip;
+ hdr.zero = 0;
+ hdr.proto = ip->proto;
+ hdr.len = udp->len;
+
+ udp_len = uip_udp_len(udp);
+
+ if (udp_len % 2) {
+ pad = (u8 *)&udp->sport + udp_len;
+ *pad = 0;
+ memcpy((u8 *)&udp->sport + udp_len + 1, &hdr, sizeof(hdr));
+ return uip_csum(0, (u8 *)&udp->sport, udp_len + 1 + sizeof(hdr));
+ } else {
+ memcpy((u8 *)&udp->sport + udp_len, &hdr, sizeof(hdr));
+ return uip_csum(0, (u8 *)&udp->sport, udp_len + sizeof(hdr));
+ }
+
+}
+
+u16 uip_csum_tcp(struct uip_tcp *tcp)
+{
+ struct uip_pseudo_hdr hdr;
+ struct uip_ip *ip;
+ u16 tcp_len;
+ u8 *pad;
+
+ ip = &tcp->ip;
+ tcp_len = ntohs(ip->len) - uip_ip_hdrlen(ip);
+
+ hdr.sip = ip->sip;
+ hdr.dip = ip->dip;
+ hdr.zero = 0;
+ hdr.proto = ip->proto;
+ hdr.len = htons(tcp_len);
+
+ if (tcp_len > UIP_MAX_TCP_PAYLOAD + 20)
+ pr_warning("tcp_len(%d) is too large", tcp_len);
+
+ if (tcp_len % 2) {
+ pad = (u8 *)&tcp->sport + tcp_len;
+ *pad = 0;
+ memcpy((u8 *)&tcp->sport + tcp_len + 1, &hdr, sizeof(hdr));
+ return uip_csum(0, (u8 *)&tcp->sport, tcp_len + 1 + sizeof(hdr));
+ } else {
+ memcpy((u8 *)&tcp->sport + tcp_len, &hdr, sizeof(hdr));
+ return uip_csum(0, (u8 *)&tcp->sport, tcp_len + sizeof(hdr));
+ }
+}
--- /dev/null
+#include "kvm/uip.h"
+
+#include <arpa/inet.h>
+
+#define EMPTY_ADDR "0.0.0.0"
+
+static inline bool uip_dhcp_is_discovery(struct uip_dhcp *dhcp)
+{
+ return (dhcp->option[2] == UIP_DHCP_DISCOVER &&
+ dhcp->option[1] == UIP_DHCP_TAG_MSG_TYPE_LEN &&
+ dhcp->option[0] == UIP_DHCP_TAG_MSG_TYPE);
+}
+
+static inline bool uip_dhcp_is_request(struct uip_dhcp *dhcp)
+{
+ return (dhcp->option[2] == UIP_DHCP_REQUEST &&
+ dhcp->option[1] == UIP_DHCP_TAG_MSG_TYPE_LEN &&
+ dhcp->option[0] == UIP_DHCP_TAG_MSG_TYPE);
+}
+
+bool uip_udp_is_dhcp(struct uip_udp *udp)
+{
+ struct uip_dhcp *dhcp;
+
+ if (ntohs(udp->sport) != UIP_DHCP_PORT_CLIENT ||
+ ntohs(udp->dport) != UIP_DHCP_PORT_SERVER)
+ return false;
+
+ dhcp = (struct uip_dhcp *)udp;
+
+ if (ntohl(dhcp->magic_cookie) != UIP_DHCP_MAGIC_COOKIE)
+ return false;
+
+ return true;
+}
+
+int uip_dhcp_get_dns(struct uip_info *info)
+{
+ char key[256], val[256];
+ struct in_addr addr;
+ int ret = -1;
+ int n = 0;
+ FILE *fp;
+ u32 ip;
+
+ fp = fopen("/etc/resolv.conf", "r");
+ if (!fp)
+ return ret;
+
+ while (!feof(fp)) {
+ if (fscanf(fp, "%s %s\n", key, val) != 2)
+ continue;
+ if (strncmp("domain", key, 6) == 0)
+ info->domain_name = strndup(val, UIP_DHCP_MAX_DOMAIN_NAME_LEN);
+ else if (strncmp("nameserver", key, 10) == 0) {
+ if (!inet_aton(val, &addr))
+ continue;
+ ip = ntohl(addr.s_addr);
+ if (n < UIP_DHCP_MAX_DNS_SERVER_NR)
+ info->dns_ip[n++] = ip;
+ ret = 0;
+ }
+ }
+
+ fclose(fp);
+ return ret;
+}
+
+static int uip_dhcp_fill_option_name_and_server(struct uip_info *info, u8 *opt, int i)
+{
+ u8 domain_name_len;
+ u32 *addr;
+ int n;
+
+ if (info->domain_name) {
+ domain_name_len = strlen(info->domain_name);
+ opt[i++] = UIP_DHCP_TAG_DOMAIN_NAME;
+ opt[i++] = domain_name_len;
+ memcpy(&opt[i], info->domain_name, domain_name_len);
+ i += domain_name_len;
+ }
+
+ for (n = 0; n < UIP_DHCP_MAX_DNS_SERVER_NR; n++) {
+ if (info->dns_ip[n] == 0)
+ continue;
+ opt[i++] = UIP_DHCP_TAG_DNS_SERVER;
+ opt[i++] = UIP_DHCP_TAG_DNS_SERVER_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->dns_ip[n]);
+ i += UIP_DHCP_TAG_DNS_SERVER_LEN;
+ }
+
+ return i;
+}
+static int uip_dhcp_fill_option(struct uip_info *info, struct uip_dhcp *dhcp, int reply_msg_type)
+{
+ int i = 0;
+ u32 *addr;
+ u8 *opt;
+
+ opt = dhcp->option;
+
+ opt[i++] = UIP_DHCP_TAG_MSG_TYPE;
+ opt[i++] = UIP_DHCP_TAG_MSG_TYPE_LEN;
+ opt[i++] = reply_msg_type;
+
+ opt[i++] = UIP_DHCP_TAG_SERVER_ID;
+ opt[i++] = UIP_DHCP_TAG_SERVER_ID_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->host_ip);
+ i += UIP_DHCP_TAG_SERVER_ID_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_LEASE_TIME;
+ opt[i++] = UIP_DHCP_TAG_LEASE_TIME_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(UIP_DHCP_LEASE_TIME);
+ i += UIP_DHCP_TAG_LEASE_TIME_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_SUBMASK;
+ opt[i++] = UIP_DHCP_TAG_SUBMASK_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->guest_netmask);
+ i += UIP_DHCP_TAG_SUBMASK_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_ROUTER;
+ opt[i++] = UIP_DHCP_TAG_ROUTER_LEN;
+ addr = (u32 *)&opt[i];
+ *addr = htonl(info->host_ip);
+ i += UIP_DHCP_TAG_ROUTER_LEN;
+
+ opt[i++] = UIP_DHCP_TAG_ROOT;
+ opt[i++] = strlen(EMPTY_ADDR);
+ addr = (u32 *)&opt[i];
+ strncpy((void *) addr, EMPTY_ADDR, strlen(EMPTY_ADDR));
+ i += strlen(EMPTY_ADDR);
+
+ i = uip_dhcp_fill_option_name_and_server(info, opt, i);
+
+ opt[i++] = UIP_DHCP_TAG_END;
+
+ return 0;
+}
+
+static int uip_dhcp_make_pkg(struct uip_info *info, struct uip_udp_socket *sk, struct uip_buf *buf, u8 reply_msg_type)
+{
+ struct uip_dhcp *dhcp;
+
+ dhcp = (struct uip_dhcp *)buf->eth;
+
+ dhcp->msg_type = 2;
+ dhcp->client_ip = 0;
+ dhcp->your_ip = htonl(info->guest_ip);
+ dhcp->server_ip = htonl(info->host_ip);
+ dhcp->agent_ip = 0;
+
+ uip_dhcp_fill_option(info, dhcp, reply_msg_type);
+
+ sk->sip = htonl(info->guest_ip);
+ sk->dip = htonl(info->host_ip);
+ sk->sport = htons(UIP_DHCP_PORT_CLIENT);
+ sk->dport = htons(UIP_DHCP_PORT_SERVER);
+
+ return 0;
+}
+
+int uip_tx_do_ipv4_udp_dhcp(struct uip_tx_arg *arg)
+{
+ struct uip_udp_socket sk;
+ struct uip_dhcp *dhcp;
+ struct uip_info *info;
+ struct uip_buf *buf;
+ u8 reply_msg_type;
+
+ dhcp = (struct uip_dhcp *)arg->eth;
+
+ if (uip_dhcp_is_discovery(dhcp))
+ reply_msg_type = UIP_DHCP_OFFER;
+ else if (uip_dhcp_is_request(dhcp))
+ reply_msg_type = UIP_DHCP_ACK;
+ else
+ return -1;
+
+ buf = uip_buf_clone(arg);
+ info = arg->info;
+
+ /*
+ * Cook DHCP pkg
+ */
+ uip_dhcp_make_pkg(info, &sk, buf, reply_msg_type);
+
+ /*
+ * Cook UDP pkg
+ */
+ uip_udp_make_pkg(info, &sk, buf, NULL, UIP_DHCP_MAX_PAYLOAD_LEN);
+
+ /*
+ * Send data received from socket to guest
+ */
+ uip_buf_set_used(info, buf);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+int uip_tx_do_ipv4_icmp(struct uip_tx_arg *arg)
+{
+ struct uip_ip *ip, *ip2;
+ struct uip_icmp *icmp2;
+ struct uip_buf *buf;
+
+ buf = uip_buf_clone(arg);
+
+ icmp2 = (struct uip_icmp *)(buf->eth);
+ ip2 = (struct uip_ip *)(buf->eth);
+ ip = (struct uip_ip *)(arg->eth);
+
+ ip2->sip = ip->dip;
+ ip2->dip = ip->sip;
+ ip2->csum = 0;
+ /*
+ * ICMP reply: 0
+ */
+ icmp2->type = 0;
+ icmp2->csum = 0;
+ ip2->csum = uip_csum_ip(ip2);
+ icmp2->csum = uip_csum_icmp(icmp2);
+
+ uip_buf_set_used(arg->info, buf);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+int uip_tx_do_ipv4(struct uip_tx_arg *arg)
+{
+ struct uip_ip *ip;
+
+ ip = (struct uip_ip *)(arg->eth);
+
+ if (uip_ip_hdrlen(ip) != 20) {
+ pr_warning("IP header length is not 20 bytes");
+ return -1;
+ }
+
+ switch (ip->proto) {
+ case UIP_IP_P_ICMP:
+ uip_tx_do_ipv4_icmp(arg);
+ break;
+ case UIP_IP_P_TCP:
+ uip_tx_do_ipv4_tcp(arg);
+ break;
+ case UIP_IP_P_UDP:
+ uip_tx_do_ipv4_udp(arg);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+#include <linux/virtio_net.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <arpa/inet.h>
+
+static int uip_tcp_socket_close(struct uip_tcp_socket *sk, int how)
+{
+ shutdown(sk->fd, how);
+
+ if (sk->write_done && sk->read_done) {
+ shutdown(sk->fd, SHUT_RDWR);
+ close(sk->fd);
+
+ mutex_lock(sk->lock);
+ list_del(&sk->list);
+ mutex_unlock(sk->lock);
+
+ free(sk);
+ }
+
+ return 0;
+}
+
+static struct uip_tcp_socket *uip_tcp_socket_find(struct uip_tx_arg *arg, u32 sip, u32 dip, u16 sport, u16 dport)
+{
+ struct list_head *sk_head;
+ pthread_mutex_t *sk_lock;
+ struct uip_tcp_socket *sk;
+
+ sk_head = &arg->info->tcp_socket_head;
+ sk_lock = &arg->info->tcp_socket_lock;
+
+ mutex_lock(sk_lock);
+ list_for_each_entry(sk, sk_head, list) {
+ if (sk->sip == sip && sk->dip == dip && sk->sport == sport && sk->dport == dport) {
+ mutex_unlock(sk_lock);
+ return sk;
+ }
+ }
+ mutex_unlock(sk_lock);
+
+ return NULL;
+}
+
+static struct uip_tcp_socket *uip_tcp_socket_alloc(struct uip_tx_arg *arg, u32 sip, u32 dip, u16 sport, u16 dport)
+{
+ struct list_head *sk_head;
+ struct uip_tcp_socket *sk;
+ pthread_mutex_t *sk_lock;
+ struct uip_tcp *tcp;
+ struct uip_ip *ip;
+ int ret;
+
+ tcp = (struct uip_tcp *)arg->eth;
+ ip = (struct uip_ip *)arg->eth;
+
+ sk_head = &arg->info->tcp_socket_head;
+ sk_lock = &arg->info->tcp_socket_lock;
+
+ sk = malloc(sizeof(*sk));
+ memset(sk, 0, sizeof(*sk));
+
+ sk->lock = sk_lock;
+ sk->info = arg->info;
+
+ sk->fd = socket(AF_INET, SOCK_STREAM, 0);
+ sk->addr.sin_family = AF_INET;
+ sk->addr.sin_port = dport;
+ sk->addr.sin_addr.s_addr = dip;
+
+ pthread_cond_init(&sk->cond, NULL);
+
+ if (ntohl(dip) == arg->info->host_ip)
+ sk->addr.sin_addr.s_addr = inet_addr("127.0.0.1");
+
+ ret = connect(sk->fd, (struct sockaddr *)&sk->addr, sizeof(sk->addr));
+ if (ret) {
+ free(sk);
+ return NULL;
+ }
+
+ sk->sip = ip->sip;
+ sk->dip = ip->dip;
+ sk->sport = tcp->sport;
+ sk->dport = tcp->dport;
+
+ mutex_lock(sk_lock);
+ list_add_tail(&sk->list, sk_head);
+ mutex_unlock(sk_lock);
+
+ return sk;
+}
+
+static int uip_tcp_payload_send(struct uip_tcp_socket *sk, u8 flag, u16 payload_len)
+{
+ struct uip_info *info;
+ struct uip_eth *eth2;
+ struct uip_tcp *tcp2;
+ struct uip_buf *buf;
+ struct uip_ip *ip2;
+
+ info = sk->info;
+
+ /*
+ * Get free buffer to send data to guest
+ */
+ buf = uip_buf_get_free(info);
+
+ /*
+ * Cook a ethernet frame
+ */
+ tcp2 = (struct uip_tcp *)buf->eth;
+ eth2 = (struct uip_eth *)buf->eth;
+ ip2 = (struct uip_ip *)buf->eth;
+
+ eth2->src = info->host_mac;
+ eth2->dst = info->guest_mac;
+ eth2->type = htons(UIP_ETH_P_IP);
+
+ ip2->vhl = UIP_IP_VER_4 | UIP_IP_HDR_LEN;
+ ip2->tos = 0;
+ ip2->id = 0;
+ ip2->flgfrag = 0;
+ ip2->ttl = UIP_IP_TTL;
+ ip2->proto = UIP_IP_P_TCP;
+ ip2->csum = 0;
+ ip2->sip = sk->dip;
+ ip2->dip = sk->sip;
+
+ tcp2->sport = sk->dport;
+ tcp2->dport = sk->sport;
+ tcp2->seq = htonl(sk->seq_server);
+ tcp2->ack = htonl(sk->ack_server);
+ /*
+ * Diable TCP options, tcp hdr len equals 20 bytes
+ */
+ tcp2->off = UIP_TCP_HDR_LEN;
+ tcp2->flg = flag;
+ tcp2->win = htons(UIP_TCP_WIN_SIZE);
+ tcp2->csum = 0;
+ tcp2->urgent = 0;
+
+ if (payload_len > 0)
+ memcpy(uip_tcp_payload(tcp2), sk->payload, payload_len);
+
+ ip2->len = htons(uip_tcp_hdrlen(tcp2) + payload_len + uip_ip_hdrlen(ip2));
+ ip2->csum = uip_csum_ip(ip2);
+ tcp2->csum = uip_csum_tcp(tcp2);
+
+ /*
+ * virtio_net_hdr
+ */
+ buf->vnet_len = sizeof(struct virtio_net_hdr);
+ memset(buf->vnet, 0, buf->vnet_len);
+
+ buf->eth_len = ntohs(ip2->len) + uip_eth_hdrlen(&ip2->eth);
+
+ /*
+ * Increase server seq
+ */
+ sk->seq_server += payload_len;
+
+ /*
+ * Send data received from socket to guest
+ */
+ uip_buf_set_used(info, buf);
+
+ return 0;
+}
+
+static void *uip_tcp_socket_thread(void *p)
+{
+ struct uip_tcp_socket *sk;
+ int len, left, ret;
+ u8 *payload, *pos;
+
+ sk = p;
+
+ payload = malloc(UIP_MAX_TCP_PAYLOAD);
+ if (!payload)
+ goto out;
+
+ while (1) {
+ pos = payload;
+
+ ret = read(sk->fd, payload, UIP_MAX_TCP_PAYLOAD);
+
+ if (ret <= 0 || ret > UIP_MAX_TCP_PAYLOAD)
+ goto out;
+
+ left = ret;
+
+ while (left > 0) {
+ mutex_lock(sk->lock);
+ while ((len = sk->guest_acked + sk->window_size - sk->seq_server) <= 0)
+ pthread_cond_wait(&sk->cond, sk->lock);
+ mutex_unlock(sk->lock);
+
+ sk->payload = pos;
+ if (len > left)
+ len = left;
+ if (len > UIP_MAX_TCP_PAYLOAD)
+ len = UIP_MAX_TCP_PAYLOAD;
+ left -= len;
+ pos += len;
+
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_ACK, len);
+ }
+ }
+
+out:
+ /*
+ * Close server to guest TCP connection
+ */
+ uip_tcp_socket_close(sk, SHUT_RD);
+
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_FIN | UIP_TCP_FLAG_ACK, 0);
+ sk->seq_server += 1;
+
+ sk->read_done = 1;
+
+ free(payload);
+ pthread_exit(NULL);
+
+ return NULL;
+}
+
+static int uip_tcp_socket_receive(struct uip_tcp_socket *sk)
+{
+ if (sk->thread == 0)
+ return pthread_create(&sk->thread, NULL, uip_tcp_socket_thread, (void *)sk);
+
+ return 0;
+}
+
+static int uip_tcp_socket_send(struct uip_tcp_socket *sk, struct uip_tcp *tcp)
+{
+ int len;
+ int ret;
+ u8 *payload;
+
+ if (sk->write_done)
+ return 0;
+
+ payload = uip_tcp_payload(tcp);
+ len = uip_tcp_payloadlen(tcp);
+
+ ret = write(sk->fd, payload, len);
+ if (ret != len)
+ pr_warning("tcp send error");
+
+ return ret;
+}
+
+int uip_tx_do_ipv4_tcp(struct uip_tx_arg *arg)
+{
+ struct uip_tcp_socket *sk;
+ struct uip_tcp *tcp;
+ struct uip_ip *ip;
+ int ret;
+
+ tcp = (struct uip_tcp *)arg->eth;
+ ip = (struct uip_ip *)arg->eth;
+
+ /*
+ * Guest is trying to start a TCP session, let's fake SYN-ACK to guest
+ */
+ if (uip_tcp_is_syn(tcp)) {
+ sk = uip_tcp_socket_alloc(arg, ip->sip, ip->dip, tcp->sport, tcp->dport);
+ if (!sk)
+ return -1;
+
+ sk->window_size = ntohs(tcp->win);
+
+ /*
+ * Setup ISN number
+ */
+ sk->isn_guest = uip_tcp_isn(tcp);
+ sk->isn_server = uip_tcp_isn_alloc();
+
+ sk->seq_server = sk->isn_server;
+ sk->ack_server = sk->isn_guest + 1;
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_SYN | UIP_TCP_FLAG_ACK, 0);
+ sk->seq_server += 1;
+
+ /*
+ * Start receive thread for data from remote to guest
+ */
+ uip_tcp_socket_receive(sk);
+
+ goto out;
+ }
+
+ /*
+ * Find socket we have allocated
+ */
+ sk = uip_tcp_socket_find(arg, ip->sip, ip->dip, tcp->sport, tcp->dport);
+ if (!sk)
+ return -1;
+
+ mutex_lock(sk->lock);
+ sk->window_size = ntohs(tcp->win);
+ sk->guest_acked = ntohl(tcp->ack);
+ pthread_cond_signal(&sk->cond);
+ mutex_unlock(sk->lock);
+
+ if (uip_tcp_is_fin(tcp)) {
+ if (sk->write_done)
+ goto out;
+
+ sk->write_done = 1;
+ sk->ack_server += 1;
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_ACK, 0);
+
+ /*
+ * Close guest to server TCP connection
+ */
+ uip_tcp_socket_close(sk, SHUT_WR);
+
+ goto out;
+ }
+
+ /*
+ * Ignore guest to server frames with zero tcp payload
+ */
+ if (uip_tcp_payloadlen(tcp) == 0)
+ goto out;
+
+ /*
+ * Sent out TCP data to remote host
+ */
+ ret = uip_tcp_socket_send(sk, tcp);
+ if (ret < 0)
+ return -1;
+ /*
+ * Send ACK to guest imediately
+ */
+ sk->ack_server += ret;
+ uip_tcp_payload_send(sk, UIP_TCP_FLAG_ACK, 0);
+
+out:
+ return 0;
+}
--- /dev/null
+#include "kvm/uip.h"
+
+#include <linux/virtio_net.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <sys/socket.h>
+#include <sys/epoll.h>
+#include <fcntl.h>
+
+#define UIP_UDP_MAX_EVENTS 1000
+
+static struct uip_udp_socket *uip_udp_socket_find(struct uip_tx_arg *arg, u32 sip, u32 dip, u16 sport, u16 dport)
+{
+ struct list_head *sk_head;
+ struct uip_udp_socket *sk;
+ pthread_mutex_t *sk_lock;
+ struct epoll_event ev;
+ int flags;
+ int ret;
+
+ sk_head = &arg->info->udp_socket_head;
+ sk_lock = &arg->info->udp_socket_lock;
+
+ /*
+ * Find existing sk
+ */
+ mutex_lock(sk_lock);
+ list_for_each_entry(sk, sk_head, list) {
+ if (sk->sip == sip && sk->dip == dip && sk->sport == sport && sk->dport == dport) {
+ mutex_unlock(sk_lock);
+ return sk;
+ }
+ }
+ mutex_unlock(sk_lock);
+
+ /*
+ * Allocate new one
+ */
+ sk = malloc(sizeof(*sk));
+ memset(sk, 0, sizeof(*sk));
+
+ sk->lock = sk_lock;
+
+ sk->fd = socket(AF_INET, SOCK_DGRAM, 0);
+ if (sk->fd < 0)
+ goto out;
+
+ /*
+ * Set non-blocking
+ */
+ flags = fcntl(sk->fd, F_GETFL, 0);
+ flags |= O_NONBLOCK;
+ fcntl(sk->fd, F_SETFL, flags);
+
+ /*
+ * Add sk->fd to epoll_wait
+ */
+ ev.events = EPOLLIN;
+ ev.data.fd = sk->fd;
+ ev.data.ptr = sk;
+ if (arg->info->udp_epollfd <= 0)
+ arg->info->udp_epollfd = epoll_create(UIP_UDP_MAX_EVENTS);
+ ret = epoll_ctl(arg->info->udp_epollfd, EPOLL_CTL_ADD, sk->fd, &ev);
+ if (ret == -1)
+ pr_warning("epoll_ctl error");
+
+ sk->addr.sin_family = AF_INET;
+ sk->addr.sin_addr.s_addr = dip;
+ sk->addr.sin_port = dport;
+
+ sk->sip = sip;
+ sk->dip = dip;
+ sk->sport = sport;
+ sk->dport = dport;
+
+ mutex_lock(sk_lock);
+ list_add_tail(&sk->list, sk_head);
+ mutex_unlock(sk_lock);
+
+ return sk;
+
+out:
+ free(sk);
+ return NULL;
+}
+
+static int uip_udp_socket_send(struct uip_udp_socket *sk, struct uip_udp *udp)
+{
+ int len;
+ int ret;
+
+ len = ntohs(udp->len) - uip_udp_hdrlen(udp);
+
+ ret = sendto(sk->fd, udp->payload, len, 0, (struct sockaddr *)&sk->addr, sizeof(sk->addr));
+ if (ret != len)
+ return -1;
+
+ return 0;
+}
+
+int uip_udp_make_pkg(struct uip_info *info, struct uip_udp_socket *sk, struct uip_buf *buf, u8* payload, int payload_len)
+{
+ struct uip_eth *eth2;
+ struct uip_udp *udp2;
+ struct uip_ip *ip2;
+
+ /*
+ * Cook a ethernet frame
+ */
+ udp2 = (struct uip_udp *)(buf->eth);
+ eth2 = (struct uip_eth *)buf->eth;
+ ip2 = (struct uip_ip *)(buf->eth);
+
+ eth2->src = info->host_mac;
+ eth2->dst = info->guest_mac;
+ eth2->type = htons(UIP_ETH_P_IP);
+
+ ip2->vhl = UIP_IP_VER_4 | UIP_IP_HDR_LEN;
+ ip2->tos = 0;
+ ip2->id = 0;
+ ip2->flgfrag = 0;
+ ip2->ttl = UIP_IP_TTL;
+ ip2->proto = UIP_IP_P_UDP;
+ ip2->csum = 0;
+
+ ip2->sip = sk->dip;
+ ip2->dip = sk->sip;
+ udp2->sport = sk->dport;
+ udp2->dport = sk->sport;
+
+ udp2->len = htons(payload_len + uip_udp_hdrlen(udp2));
+ udp2->csum = 0;
+
+ if (payload)
+ memcpy(udp2->payload, payload, payload_len);
+
+ ip2->len = udp2->len + htons(uip_ip_hdrlen(ip2));
+ ip2->csum = uip_csum_ip(ip2);
+ udp2->csum = uip_csum_udp(udp2);
+
+ /*
+ * virtio_net_hdr
+ */
+ buf->vnet_len = sizeof(struct virtio_net_hdr);
+ memset(buf->vnet, 0, buf->vnet_len);
+
+ buf->eth_len = ntohs(ip2->len) + uip_eth_hdrlen(&ip2->eth);
+
+ return 0;
+}
+
+static void *uip_udp_socket_thread(void *p)
+{
+ struct epoll_event events[UIP_UDP_MAX_EVENTS];
+ struct uip_udp_socket *sk;
+ struct uip_info *info;
+ struct uip_buf *buf;
+ int payload_len;
+ u8 *payload;
+ int nfds;
+ int i;
+
+ info = p;
+
+ do {
+ payload = malloc(UIP_MAX_UDP_PAYLOAD);
+ } while (!payload);
+
+ while (1) {
+ nfds = epoll_wait(info->udp_epollfd, events, UIP_UDP_MAX_EVENTS, -1);
+
+ if (nfds == -1)
+ continue;
+
+ for (i = 0; i < nfds; i++) {
+
+ sk = events[i].data.ptr;
+ payload_len = recvfrom(sk->fd, payload, UIP_MAX_UDP_PAYLOAD, 0, NULL, NULL);
+ if (payload_len < 0)
+ continue;
+
+ /*
+ * Get free buffer to send data to guest
+ */
+ buf = uip_buf_get_free(info);
+
+ uip_udp_make_pkg(info, sk, buf, payload, payload_len);
+
+ /*
+ * Send data received from socket to guest
+ */
+ uip_buf_set_used(info, buf);
+ }
+ }
+
+ free(payload);
+ pthread_exit(NULL);
+ return NULL;
+}
+
+int uip_tx_do_ipv4_udp(struct uip_tx_arg *arg)
+{
+ struct uip_udp_socket *sk;
+ struct uip_info *info;
+ struct uip_udp *udp;
+ struct uip_ip *ip;
+ int ret;
+
+ udp = (struct uip_udp *)(arg->eth);
+ ip = (struct uip_ip *)(arg->eth);
+ info = arg->info;
+
+ if (uip_udp_is_dhcp(udp)) {
+ uip_tx_do_ipv4_udp_dhcp(arg);
+ return 0;
+ }
+
+ /*
+ * Find socket we have allocated before, otherwise allocate one
+ */
+ sk = uip_udp_socket_find(arg, ip->sip, ip->dip, udp->sport, udp->dport);
+ if (!sk)
+ return -1;
+
+ /*
+ * Send out UDP data to remote host
+ */
+ ret = uip_udp_socket_send(sk, udp);
+ if (ret)
+ return -1;
+
+ if (!info->udp_thread)
+ pthread_create(&info->udp_thread, NULL, uip_udp_socket_thread, (void *)info);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/pci.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include <linux/err.h>
+#include <assert.h>
+
+#define PCI_BAR_OFFSET(b) (offsetof(struct pci_device_header, bar[b]))
+
+static struct pci_device_header *pci_devices[PCI_MAX_DEVICES];
+
+static union pci_config_address pci_config_address;
+
+/* This is within our PCI gap - in an unused area.
+ * Note this is a PCI *bus address*, is used to assign BARs etc.!
+ * (That's why it can still 32bit even with 64bit guests-- 64bit
+ * PCI isn't currently supported.)
+ */
+static u32 io_space_blocks = KVM_PCI_MMIO_AREA;
+
+u32 pci_get_io_space_block(u32 size)
+{
+ u32 block = io_space_blocks;
+ io_space_blocks += size;
+
+ return block;
+}
+
+static void *pci_config_address_ptr(u16 port)
+{
+ unsigned long offset;
+ void *base;
+
+ offset = port - PCI_CONFIG_ADDRESS;
+ base = &pci_config_address;
+
+ return base + offset;
+}
+
+static bool pci_config_address_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ void *p = pci_config_address_ptr(port);
+
+ memcpy(p, data, size);
+
+ return true;
+}
+
+static bool pci_config_address_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ void *p = pci_config_address_ptr(port);
+
+ memcpy(data, p, size);
+
+ return true;
+}
+
+static struct ioport_operations pci_config_address_ops = {
+ .io_in = pci_config_address_in,
+ .io_out = pci_config_address_out,
+};
+
+static bool pci_device_exists(u8 bus_number, u8 device_number, u8 function_number)
+{
+ struct pci_device_header *dev;
+
+ if (pci_config_address.bus_number != bus_number)
+ return false;
+
+ if (pci_config_address.function_number != function_number)
+ return false;
+
+ if (device_number >= PCI_MAX_DEVICES)
+ return false;
+
+ dev = pci_devices[device_number];
+
+ return dev != NULL;
+}
+
+static bool pci_config_data_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ /*
+ * If someone accesses PCI configuration space offsets that are not
+ * aligned to 4 bytes, it uses ioports to signify that.
+ */
+ pci_config_address.reg_offset = port - PCI_CONFIG_DATA;
+
+ pci__config_wr(kvm, pci_config_address, data, size);
+
+ return true;
+}
+
+static bool pci_config_data_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ /*
+ * If someone accesses PCI configuration space offsets that are not
+ * aligned to 4 bytes, it uses ioports to signify that.
+ */
+ pci_config_address.reg_offset = port - PCI_CONFIG_DATA;
+
+ pci__config_rd(kvm, pci_config_address, data, size);
+
+ return true;
+}
+
+static struct ioport_operations pci_config_data_ops = {
+ .io_in = pci_config_data_in,
+ .io_out = pci_config_data_out,
+};
+
+void pci__config_wr(struct kvm *kvm, union pci_config_address addr, void *data, int size)
+{
+ u8 dev_num;
+
+ dev_num = addr.device_number;
+
+ if (pci_device_exists(0, dev_num, 0)) {
+ unsigned long offset;
+
+ offset = addr.w & 0xff;
+ if (offset < sizeof(struct pci_device_header)) {
+ void *p = pci_devices[dev_num];
+ u8 bar = (offset - PCI_BAR_OFFSET(0)) / (sizeof(u32));
+ u32 sz = PCI_IO_SIZE;
+
+ if (bar < 6 && pci_devices[dev_num]->bar_size[bar])
+ sz = pci_devices[dev_num]->bar_size[bar];
+
+ /*
+ * If the kernel masks the BAR it would expect to find the
+ * size of the BAR there next time it reads from it.
+ * When the kernel got the size it would write the address
+ * back.
+ */
+ if (*(u32 *)(p + offset)) {
+ /* See if kernel tries to mask one of the BARs */
+ if ((offset >= PCI_BAR_OFFSET(0)) &&
+ (offset <= PCI_BAR_OFFSET(6)) &&
+ (ioport__read32(data) == 0xFFFFFFFF))
+ memcpy(p + offset, &sz, sizeof(sz));
+ else
+ memcpy(p + offset, data, size);
+ }
+ }
+ }
+}
+
+void pci__config_rd(struct kvm *kvm, union pci_config_address addr, void *data, int size)
+{
+ u8 dev_num;
+
+ dev_num = addr.device_number;
+
+ if (pci_device_exists(0, dev_num, 0)) {
+ unsigned long offset;
+
+ offset = addr.w & 0xff;
+ if (offset < sizeof(struct pci_device_header)) {
+ void *p = pci_devices[dev_num];
+
+ memcpy(data, p + offset, size);
+ } else {
+ memset(data, 0x00, size);
+ }
+ } else {
+ memset(data, 0xff, size);
+ }
+}
+
+int pci__register(struct pci_device_header *dev, u8 dev_num)
+{
+ if (dev_num >= PCI_MAX_DEVICES)
+ return -ENOSPC;
+
+ pci_devices[dev_num] = dev;
+
+ return 0;
+}
+
+struct pci_device_header *pci__find_dev(u8 dev_num)
+{
+ if (dev_num >= PCI_MAX_DEVICES)
+ return ERR_PTR(-EOVERFLOW);
+
+ return pci_devices[dev_num];
+}
+
+int pci__init(struct kvm *kvm)
+{
+ int r;
+
+ r = ioport__register(PCI_CONFIG_DATA + 0, &pci_config_data_ops, 4, NULL);
+ if (r < 0)
+ return r;
+
+ r = ioport__register(PCI_CONFIG_ADDRESS + 0, &pci_config_address_ops, 4, NULL);
+ if (r < 0) {
+ ioport__unregister(PCI_CONFIG_DATA);
+ return r;
+ }
+
+ return 0;
+}
+
+int pci__exit(struct kvm *kvm)
+{
+ ioport__unregister(PCI_CONFIG_DATA);
+ ioport__unregister(PCI_CONFIG_ADDRESS);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/kvm.h"
+
+#include <stdbool.h>
+
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename)
+{
+ return false;
+}
--- /dev/null
+/*
+ * PPC CPU identification
+ *
+ * This is a very simple "host CPU info" struct to get us going.
+ * For the little host information we need, I don't want to grub about
+ * parsing stuff in /proc/device-tree so just match host PVR to differentiate
+ * PPC970 and POWER7 (which is all that's currently supported).
+ *
+ * Qemu does something similar but this is MUCH simpler!
+ *
+ * Copyright 2012 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <kvm/kvm.h>
+#include <sys/ioctl.h>
+
+#include "cpu_info.h"
+#include "kvm/util.h"
+
+/* POWER7 */
+
+static struct cpu_info cpu_power7_info = {
+ .name = "POWER7",
+ .tb_freq = 512000000,
+ .d_bsize = 128,
+ .i_bsize = 128,
+ .flags = CPUINFO_FLAG_DFP | CPUINFO_FLAG_VSX | CPUINFO_FLAG_VMX,
+ .mmu_info = {
+ .flags = KVM_PPC_PAGE_SIZES_REAL | KVM_PPC_1T_SEGMENTS,
+ .slb_size = 32,
+ },
+};
+
+/* PPC970/G5 */
+
+static struct cpu_info cpu_970_info = {
+ .name = "G5",
+ .tb_freq = 33333333,
+ .d_bsize = 128,
+ .i_bsize = 128,
+ .flags = CPUINFO_FLAG_VMX,
+};
+
+/* This is a default catchall for 'no match' on PVR: */
+static struct cpu_info cpu_dummy_info = { .name = "unknown" };
+
+static struct pvr_info host_pvr_info[] = {
+ { 0xffffffff, 0x0f000003, &cpu_power7_info },
+ { 0xffff0000, 0x003f0000, &cpu_power7_info },
+ { 0xffff0000, 0x004a0000, &cpu_power7_info },
+ { 0xffff0000, 0x00390000, &cpu_970_info },
+ { 0xffff0000, 0x003c0000, &cpu_970_info },
+ { 0xffff0000, 0x00440000, &cpu_970_info },
+ { 0xffff0000, 0x00450000, &cpu_970_info },
+};
+
+/* If we can't query the kernel for supported page sizes assume 4K and 16M */
+static struct kvm_ppc_one_seg_page_size fallback_sps[] = {
+ [0] = {
+ .page_shift = 12,
+ .slb_enc = 0,
+ .enc = {
+ [0] = {
+ .page_shift = 12,
+ .pte_enc = 0,
+ },
+ },
+ },
+ [1] = {
+ .page_shift = 24,
+ .slb_enc = 0x100,
+ .enc = {
+ [0] = {
+ .page_shift = 24,
+ .pte_enc = 0,
+ },
+ },
+ },
+};
+
+
+static void setup_mmu_info(struct kvm *kvm, struct cpu_info *cpu_info)
+{
+ static struct kvm_ppc_smmu_info *mmu_info;
+ struct kvm_ppc_one_seg_page_size *sps;
+ int i, j, k, valid;
+
+ if (!kvm__supports_extension(kvm, KVM_CAP_PPC_GET_SMMU_INFO)) {
+ memcpy(&cpu_info->mmu_info.sps, fallback_sps, sizeof(fallback_sps));
+ } else if (ioctl(kvm->vm_fd, KVM_PPC_GET_SMMU_INFO, &cpu_info->mmu_info) < 0) {
+ die_perror("KVM_PPC_GET_SMMU_INFO failed");
+ }
+
+ mmu_info = &cpu_info->mmu_info;
+
+ if (!(mmu_info->flags & KVM_PPC_PAGE_SIZES_REAL))
+ /* Guest pages are not restricted by the backing page size */
+ return;
+
+ /* Filter based on backing page size */
+
+ for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ sps = &mmu_info->sps[i];
+
+ if (!sps->page_shift)
+ break;
+
+ if (kvm->ram_pagesize < (1ul << sps->page_shift)) {
+ /* Mark the whole segment size invalid */
+ sps->page_shift = 0;
+ continue;
+ }
+
+ /* Check each page size for the segment */
+ for (j = 0, valid = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (!sps->enc[j].page_shift)
+ break;
+
+ if (kvm->ram_pagesize < (1ul << sps->enc[j].page_shift))
+ sps->enc[j].page_shift = 0;
+ else
+ valid++;
+ }
+
+ if (!valid) {
+ /* Mark the whole segment size invalid */
+ sps->page_shift = 0;
+ continue;
+ }
+
+ /* Mark any trailing entries invalid if we broke out early */
+ for (k = j; k < KVM_PPC_PAGE_SIZES_MAX_SZ; k++)
+ sps->enc[k].page_shift = 0;
+
+ /* Collapse holes */
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (sps->enc[j].page_shift)
+ continue;
+
+ for (k = j + 1; k < KVM_PPC_PAGE_SIZES_MAX_SZ; k++) {
+ if (sps->enc[k].page_shift) {
+ sps->enc[j] = sps->enc[k];
+ sps->enc[k].page_shift = 0;
+ break;
+ }
+ }
+ }
+ }
+
+ /* Mark any trailing entries invalid if we broke out early */
+ for (j = i; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++)
+ mmu_info->sps[j].page_shift = 0;
+
+ /* Collapse holes */
+ for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ if (mmu_info->sps[i].page_shift)
+ continue;
+
+ for (j = i + 1; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (mmu_info->sps[j].page_shift) {
+ mmu_info->sps[i] = mmu_info->sps[j];
+ mmu_info->sps[j].page_shift = 0;
+ break;
+ }
+ }
+ }
+}
+
+struct cpu_info *find_cpu_info(struct kvm *kvm)
+{
+ struct cpu_info *info;
+ unsigned int i;
+ u32 pvr = kvm->pvr;
+
+ for (info = NULL, i = 0; i < ARRAY_SIZE(host_pvr_info); i++) {
+ if ((pvr & host_pvr_info[i].pvr_mask) == host_pvr_info[i].pvr) {
+ info = host_pvr_info[i].cpu_info;
+ break;
+ }
+ }
+
+ /* Didn't find anything? Rut-ro. */
+ if (!info) {
+ pr_warning("Host CPU unsupported by kvmtool\n");
+ info = &cpu_dummy_info;
+ }
+
+ setup_mmu_info(kvm, info);
+
+ return info;
+}
--- /dev/null
+/*
+ * PPC CPU identification
+ *
+ * Copyright 2012 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef CPU_INFO_H
+#define CPU_INFO_H
+
+#include <kvm/kvm.h>
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+
+struct cpu_info {
+ const char *name;
+ u32 tb_freq; /* timebase frequency */
+ u32 d_bsize; /* d-cache block size */
+ u32 i_bsize; /* i-cache block size */
+ u32 flags;
+ struct kvm_ppc_smmu_info mmu_info;
+};
+
+struct pvr_info {
+ u32 pvr_mask;
+ u32 pvr;
+ struct cpu_info *cpu_info;
+};
+
+/* Misc capabilities/CPU properties */
+#define CPUINFO_FLAG_DFP 0x00000001
+#define CPUINFO_FLAG_VMX 0x00000002
+#define CPUINFO_FLAG_VSX 0x00000004
+
+struct cpu_info *find_cpu_info(struct kvm *kvm);
+
+#endif
--- /dev/null
+#ifndef _KVM_BARRIER_H_
+#define _KVM_BARRIER_H_
+
+#include <asm/barrier.h>
+
+#endif /* _KVM_BARRIER_H_ */
--- /dev/null
+/*
+ * PPC64 architecture-specific definitions
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <time.h>
+
+/*
+ * MMIO lives after RAM, but it'd be nice if it didn't constantly move.
+ * Choose a suitably high address, e.g. 63T... This limits RAM size.
+ */
+#define PPC_MMIO_START 0x3F0000000000UL
+#define PPC_MMIO_SIZE 0x010000000000UL
+
+#define KERNEL_LOAD_ADDR 0x0000000000000000
+#define KERNEL_START_ADDR 0x0000000000000000
+#define KERNEL_SECONDARY_START_ADDR 0x0000000000000060
+#define INITRD_LOAD_ADDR 0x0000000002800000
+
+#define FDT_MAX_SIZE 0x10000
+#define RTAS_MAX_SIZE 0x10000
+
+#define TIMEBASE_FREQ 512000000ULL
+
+#define KVM_MMIO_START PPC_MMIO_START
+
+/*
+ * This is the address that pci_get_io_space_block() starts allocating
+ * from. Note that this is a PCI bus address.
+ */
+#define KVM_PCI_MMIO_AREA 0x1000000
+#define KVM_VIRTIO_MMIO_AREA 0x2000000
+
+struct spapr_phb;
+
+struct kvm {
+ int sys_fd; /* For system ioctls(), i.e. /dev/kvm */
+ int vm_fd; /* For VM ioctls() */
+ timer_t timerid; /* Posix timer for interrupts */
+
+ int nrcpus; /* Number of cpus to run */
+
+ u32 mem_slots; /* for KVM_SET_USER_MEMORY_REGION */
+
+ u64 ram_size;
+ void *ram_start;
+ u64 ram_pagesize;
+
+ u64 sdr1;
+ u32 pvr;
+
+ bool nmi_disabled;
+
+ bool single_step;
+
+ const char *vmlinux;
+ struct disk_image **disks;
+ int nr_disks;
+ unsigned long rtas_gra;
+ unsigned long rtas_size;
+ unsigned long fdt_gra;
+ unsigned long initrd_gra;
+ unsigned long initrd_size;
+ char *name;
+ int vm_state;
+ struct icp_state *icp;
+ struct spapr_phb *phb;
+};
+
+/* Helper for the various bits of code that generate FDT nodes */
+#define _FDT(exp) \
+ do { \
+ int ret = (exp); \
+ if (ret < 0) { \
+ die("Error creating device tree: %s: %s\n", \
+ #exp, fdt_strerror(ret)); \
+ } \
+ } while (0)
+
+#endif /* KVM__KVM_ARCH_H */
--- /dev/null
+/*
+ * PPC64 cpu-specific definitions
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+/* Architecture-specific kvm_cpu definitions. */
+
+#include <linux/kvm.h> /* for struct kvm_regs */
+#include <stdbool.h>
+#include <pthread.h>
+
+#define MSR_SF (1UL<<63)
+#define MSR_HV (1UL<<60)
+#define MSR_VEC (1UL<<25)
+#define MSR_VSX (1UL<<23)
+#define MSR_POW (1UL<<18)
+#define MSR_EE (1UL<<15)
+#define MSR_PR (1UL<<14)
+#define MSR_FP (1UL<<13)
+#define MSR_ME (1UL<<12)
+#define MSR_FE0 (1UL<<11)
+#define MSR_SE (1UL<<10)
+#define MSR_BE (1UL<<9)
+#define MSR_FE1 (1UL<<8)
+#define MSR_IR (1UL<<5)
+#define MSR_DR (1UL<<4)
+#define MSR_PMM (1UL<<2)
+#define MSR_RI (1UL<<1)
+#define MSR_LE (1UL<<0)
+
+#define POWER7_EXT_IRQ 0
+
+struct kvm;
+
+struct kvm_cpu {
+ pthread_t thread; /* VCPU thread */
+
+ unsigned long cpu_id;
+
+ struct kvm *kvm; /* parent KVM */
+ int vcpu_fd; /* For VCPU ioctls() */
+ struct kvm_run *kvm_run;
+
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_fpu fpu;
+
+ u8 is_running;
+ u8 paused;
+ u8 needs_nmi;
+ /*
+ * Although PPC KVM doesn't yet support coalesced MMIO, generic code
+ * needs this in our kvm_cpu:
+ */
+ struct kvm_coalesced_mmio_ring *ring;
+};
+
+void kvm_cpu__irq(struct kvm_cpu *vcpu, int pin, int level);
+
+/* This is never actually called on PPC. */
+static inline bool kvm_cpu__emulate_io(struct kvm *kvm, u16 port, void *data, int direction, int size, u32 count)
+{
+ return false;
+}
+
+bool kvm_cpu__emulate_mmio(struct kvm *kvm, u64 phys_addr, u8 *data, u32 len, u8 is_write);
+
+#endif /* KVM__KVM_CPU_ARCH_H */
--- /dev/null
+/*
+ * PPC64 ioport platform setup. There isn't any! :-)
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/ioport.h"
+
+#include <stdlib.h>
+
+void ioport__setup_arch(void)
+{
+ /* PPC has no legacy ioports to set up */
+}
--- /dev/null
+/*
+ * PPC64 IRQ routines
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/kvm.h>
+#include <sys/ioctl.h>
+
+#include <stddef.h>
+#include <stdlib.h>
+
+#include "kvm/pci.h"
+
+#include "xics.h"
+#include "spapr_pci.h"
+
+#define XICS_IRQS 1024
+
+/*
+ * FIXME: The code in this file assumes an SPAPR guest, using XICS. Make
+ * generic & cope with multiple PPC platform types.
+ */
+
+static int pci_devs = 0;
+
+int irq__register_device(u32 dev, u8 *num, u8 *pin, u8 *line)
+{
+ if (pci_devs >= PCI_MAX_DEVICES)
+ die("Hit PCI device limit!\n");
+
+ *num = pci_devs++;
+
+ *pin = 1;
+ /*
+ * Have I said how nasty I find this? Line should be dontcare... PHB
+ * should determine which CPU/XICS IRQ to fire.
+ */
+ *line = xics_alloc_irqnum();
+ return 0;
+}
+
+int irq__init(struct kvm *kvm)
+{
+ /*
+ * kvm->nr_cpus is now valid; for /now/, pass
+ * this to xics_system_init(), which assumes servers
+ * are numbered 0..nrcpus. This may not really be true,
+ * but it is OK currently.
+ */
+ kvm->icp = xics_system_init(XICS_IRQS, kvm->nrcpus);
+ return 0;
+}
+
+int irq__exit(struct kvm *kvm)
+{
+ return 0;
+}
+
+int irq__add_msix_route(struct kvm *kvm, struct msi_msg *msg)
+{
+ die(__FUNCTION__);
+ return 0;
+}
--- /dev/null
+/*
+ * PPC64 processor support
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/symbol.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include "spapr.h"
+#include "spapr_pci.h"
+#include "xics.h"
+
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+#include <assert.h>
+
+static int debug_fd;
+
+void kvm_cpu__set_debug_fd(int fd)
+{
+ debug_fd = fd;
+}
+
+int kvm_cpu__get_debug_fd(void)
+{
+ return debug_fd;
+}
+
+static struct kvm_cpu *kvm_cpu__new(struct kvm *kvm)
+{
+ struct kvm_cpu *vcpu;
+
+ vcpu = calloc(1, sizeof *vcpu);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->kvm = kvm;
+
+ return vcpu;
+}
+
+void kvm_cpu__delete(struct kvm_cpu *vcpu)
+{
+ free(vcpu);
+}
+
+struct kvm_cpu *kvm_cpu__init(struct kvm *kvm, unsigned long cpu_id)
+{
+ struct kvm_cpu *vcpu;
+ int mmap_size;
+ struct kvm_enable_cap papr_cap = { .cap = KVM_CAP_PPC_PAPR };
+
+ vcpu = kvm_cpu__new(kvm);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->cpu_id = cpu_id;
+
+ vcpu->vcpu_fd = ioctl(vcpu->kvm->vm_fd, KVM_CREATE_VCPU, cpu_id);
+ if (vcpu->vcpu_fd < 0)
+ die_perror("KVM_CREATE_VCPU ioctl");
+
+ mmap_size = ioctl(vcpu->kvm->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
+ if (mmap_size < 0)
+ die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+
+ vcpu->kvm_run = mmap(NULL, mmap_size, PROT_RW, MAP_SHARED, vcpu->vcpu_fd, 0);
+ if (vcpu->kvm_run == MAP_FAILED)
+ die("unable to mmap vcpu fd");
+
+ if (ioctl(vcpu->vcpu_fd, KVM_ENABLE_CAP, &papr_cap) < 0)
+ die("unable to enable PAPR capability");
+
+ /*
+ * We start all CPUs, directing non-primary threads into the kernel's
+ * secondary start point. When we come to support SLOF, we will start
+ * only one and SLOF will RTAS call us to ask for others to be
+ * started. (FIXME: make more generic & interface with whichever
+ * firmware a platform may be using.)
+ */
+ vcpu->is_running = true;
+
+ /* Register with IRQ controller (FIXME, assumes XICS) */
+ xics_cpu_register(vcpu);
+
+ return vcpu;
+}
+
+static void kvm_cpu__setup_fpu(struct kvm_cpu *vcpu)
+{
+ /* Don't have to do anything, there's no expected FPU state. */
+}
+
+static void kvm_cpu__setup_regs(struct kvm_cpu *vcpu)
+{
+ /*
+ * FIXME: This assumes PPC64 and Linux guest. It doesn't use the
+ * OpenFirmware entry method, but instead the "embedded" entry which
+ * passes the FDT address directly.
+ */
+ struct kvm_regs *r = &vcpu->regs;
+
+ if (vcpu->cpu_id == 0) {
+ r->pc = KERNEL_START_ADDR;
+ r->gpr[3] = vcpu->kvm->fdt_gra;
+ r->gpr[5] = 0;
+ } else {
+ r->pc = KERNEL_SECONDARY_START_ADDR;
+ r->gpr[3] = vcpu->cpu_id;
+ }
+ r->msr = 0x8000000000001000UL; /* 64bit, non-HV, ME */
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_REGS, &vcpu->regs) < 0)
+ die_perror("KVM_SET_REGS failed");
+}
+
+static void kvm_cpu__setup_sregs(struct kvm_cpu *vcpu)
+{
+ /*
+ * Some sregs setup to initialise SDR1/PVR/HIOR on PPC64 SPAPR
+ * platforms using PR KVM. (Technically, this is all ignored on
+ * SPAPR HV KVM.) Different setup is required for non-PV non-SPAPR
+ * platforms! (FIXME.)
+ */
+ struct kvm_sregs sregs;
+ struct kvm_one_reg reg = {};
+ u64 value;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ sregs.u.s.sdr1 = vcpu->kvm->sdr1;
+ sregs.pvr = vcpu->kvm->pvr;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_SREGS, &sregs) < 0)
+ die("KVM_SET_SREGS failed");
+
+ reg.id = KVM_REG_PPC_HIOR;
+ value = 0;
+ reg.addr = (u64)&value;
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_ONE_REG, ®) < 0)
+ die("KVM_SET_ONE_REG failed");
+}
+
+/**
+ * kvm_cpu__reset_vcpu - reset virtual CPU to a known state
+ */
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ kvm_cpu__setup_regs(vcpu);
+ kvm_cpu__setup_sregs(vcpu);
+ kvm_cpu__setup_fpu(vcpu);
+}
+
+/* kvm_cpu__irq - set KVM's IRQ flag on this vcpu */
+void kvm_cpu__irq(struct kvm_cpu *vcpu, int pin, int level)
+{
+ unsigned int virq = level ? KVM_INTERRUPT_SET_LEVEL : KVM_INTERRUPT_UNSET;
+
+ /* FIXME: POWER-specific */
+ if (pin != POWER7_EXT_IRQ)
+ return;
+ if (ioctl(vcpu->vcpu_fd, KVM_INTERRUPT, &virq) < 0)
+ pr_warning("Could not KVM_INTERRUPT.");
+}
+
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu)
+{
+}
+
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
+{
+ bool ret = true;
+ struct kvm_run *run = vcpu->kvm_run;
+ switch(run->exit_reason) {
+ case KVM_EXIT_PAPR_HCALL:
+ run->papr_hcall.ret = spapr_hypercall(vcpu, run->papr_hcall.nr,
+ (target_ulong*)run->papr_hcall.args);
+ break;
+ default:
+ ret = false;
+ }
+ return ret;
+}
+
+bool kvm_cpu__emulate_mmio(struct kvm *kvm, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ /*
+ * FIXME: This function will need to be split in order to support
+ * various PowerPC platforms/PHB types, etc. It currently assumes SPAPR
+ * PPC64 guest.
+ */
+ bool ret = false;
+
+ if ((phys_addr >= SPAPR_PCI_WIN_START) &&
+ (phys_addr < SPAPR_PCI_WIN_END)) {
+ ret = spapr_phb_mmio(kvm, phys_addr, data, len, is_write);
+ } else {
+ pr_warning("MMIO %s unknown address %llx (size %d)!\n",
+ is_write ? "write to" : "read from",
+ phys_addr, len);
+ }
+ return ret;
+}
+
+#define CONDSTR_BIT(m, b) (((m) & MSR_##b) ? #b" " : "")
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ int r;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, ®s) < 0)
+ die("KVM_GET_REGS failed");
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ dprintf(debug_fd, "\n Registers:\n");
+ dprintf(debug_fd, " NIP: %016llx MSR: %016llx "
+ "( %s%s%s%s%s%s%s%s%s%s%s%s)\n",
+ regs.pc, regs.msr,
+ CONDSTR_BIT(regs.msr, SF),
+ CONDSTR_BIT(regs.msr, HV), /* ! */
+ CONDSTR_BIT(regs.msr, VEC),
+ CONDSTR_BIT(regs.msr, VSX),
+ CONDSTR_BIT(regs.msr, EE),
+ CONDSTR_BIT(regs.msr, PR),
+ CONDSTR_BIT(regs.msr, FP),
+ CONDSTR_BIT(regs.msr, ME),
+ CONDSTR_BIT(regs.msr, IR),
+ CONDSTR_BIT(regs.msr, DR),
+ CONDSTR_BIT(regs.msr, RI),
+ CONDSTR_BIT(regs.msr, LE));
+ dprintf(debug_fd, " CTR: %016llx LR: %016llx CR: %08llx\n",
+ regs.ctr, regs.lr, regs.cr);
+ dprintf(debug_fd, " SRR0: %016llx SRR1: %016llx XER: %016llx\n",
+ regs.srr0, regs.srr1, regs.xer);
+ dprintf(debug_fd, " SPRG0: %016llx SPRG1: %016llx\n",
+ regs.sprg0, regs.sprg1);
+ dprintf(debug_fd, " SPRG2: %016llx SPRG3: %016llx\n",
+ regs.sprg2, regs.sprg3);
+ dprintf(debug_fd, " SPRG4: %016llx SPRG5: %016llx\n",
+ regs.sprg4, regs.sprg5);
+ dprintf(debug_fd, " SPRG6: %016llx SPRG7: %016llx\n",
+ regs.sprg6, regs.sprg7);
+ dprintf(debug_fd, " GPRs:\n ");
+ for (r = 0; r < 32; r++) {
+ dprintf(debug_fd, "%016llx ", regs.gpr[r]);
+ if ((r & 3) == 3)
+ dprintf(debug_fd, "\n ");
+ }
+ dprintf(debug_fd, "\n");
+
+ /* FIXME: Assumes SLB-based (book3s) guest */
+ for (r = 0; r < 32; r++) {
+ dprintf(debug_fd, " SLB%02d %016llx %016llx\n", r,
+ sregs.u.s.ppc64.slb[r].slbe,
+ sregs.u.s.ppc64.slb[r].slbv);
+ }
+ dprintf(debug_fd, "----------\n");
+}
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, &vcpu->regs) < 0)
+ die("KVM_GET_REGS failed");
+
+ /* FIXME: Dump/disassemble some code...! */
+
+ dprintf(debug_fd, "\n Stack:\n");
+ dprintf(debug_fd, " ------\n");
+ /* Only works in real mode: */
+ kvm__dump_mem(vcpu->kvm, vcpu->regs.gpr[1], 32);
+}
+
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu)
+{
+ /* Does nothing yet */
+}
--- /dev/null
+/*
+ * PPC64 (SPAPR) platform support
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * Portions of FDT setup borrowed from QEMU, copyright 2010 David Gibson, IBM
+ * Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+#include "libfdt.h"
+#include "cpu_info.h"
+
+#include "spapr.h"
+#include "spapr_hvcons.h"
+#include "spapr_pci.h"
+
+#include <linux/kvm.h>
+
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <asm/unistd.h>
+#include <errno.h>
+
+#include <linux/byteorder.h>
+
+#define HPT_ORDER 24
+
+#define HUGETLBFS_PATH "/var/lib/hugetlbfs/global/pagesize-16MB/"
+
+#define PHANDLE_XICP 0x00001111
+
+static char kern_cmdline[2048];
+
+struct kvm_ext kvm_req_ext[] = {
+ { DEFINE_KVM_EXT(KVM_CAP_PPC_UNSET_IRQ) },
+ { DEFINE_KVM_EXT(KVM_CAP_PPC_IRQ_LEVEL) },
+ { 0, 0 }
+};
+
+static uint32_t mfpvr(void)
+{
+ uint32_t r;
+ asm volatile ("mfpvr %0" : "=r"(r));
+ return r;
+}
+
+bool kvm__arch_cpu_supports_vm(void)
+{
+ return true;
+}
+
+void kvm__init_ram(struct kvm *kvm)
+{
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ phys_start = 0;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ /*
+ * We put MMIO at PPC_MMIO_START, high up. Make sure that this doesn't
+ * crash into the end of RAM -- on PPC64 at least, this is so high
+ * (63TB!) that this is unlikely.
+ */
+ if (phys_size >= PPC_MMIO_START)
+ die("Too much memory (%lld, what a nice problem): "
+ "overlaps MMIO!\n",
+ phys_size);
+
+ kvm__register_mem(kvm, phys_start, phys_size, host_mem);
+}
+
+void kvm__arch_set_cmdline(char *cmdline, bool video)
+{
+ /* We don't need anything unusual in here. */
+}
+
+/* Architecture-specific KVM init */
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size)
+{
+ int cap_ppc_rma;
+ unsigned long hpt;
+
+ kvm->ram_size = ram_size;
+
+ /* Map "default" hugetblfs path to the standard 16M mount point */
+ if (hugetlbfs_path && !strcmp(hugetlbfs_path, "default"))
+ hugetlbfs_path = HUGETLBFS_PATH;
+
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, kvm->ram_size);
+
+ if (kvm->ram_start == MAP_FAILED)
+ die("Couldn't map %lld bytes for RAM (%d)\n",
+ kvm->ram_size, errno);
+
+ /* FDT goes at top of memory, RTAS just below */
+ kvm->fdt_gra = kvm->ram_size - FDT_MAX_SIZE;
+ /* FIXME: Not all PPC systems have RTAS */
+ kvm->rtas_gra = kvm->fdt_gra - RTAS_MAX_SIZE;
+ madvise(kvm->ram_start, kvm->ram_size, MADV_MERGEABLE);
+
+ /* FIXME: SPAPR-PR specific; allocate a guest HPT. */
+ if (posix_memalign((void **)&hpt, (1<<HPT_ORDER), (1<<HPT_ORDER)))
+ die("Can't allocate %d bytes for HPT\n", (1<<HPT_ORDER));
+
+ kvm->sdr1 = ((hpt + 0x3ffffULL) & ~0x3ffffULL) | (HPT_ORDER-18);
+
+ kvm->pvr = mfpvr();
+
+ /* FIXME: This is book3s-specific */
+ cap_ppc_rma = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_PPC_RMA);
+ if (cap_ppc_rma == 2)
+ die("Need contiguous RMA allocation on this hardware, "
+ "which is not yet supported.");
+
+ /* Do these before FDT setup, IRQ setup, etc. */
+ /* FIXME: SPAPR-specific */
+ hypercall_init();
+ register_core_rtas();
+ /* Now that hypercalls are initialised, register a couple for the console: */
+ spapr_hvcons_init();
+ spapr_create_phb(kvm, "pci", SPAPR_PCI_BUID,
+ SPAPR_PCI_MEM_WIN_ADDR,
+ SPAPR_PCI_MEM_WIN_SIZE,
+ SPAPR_PCI_IO_WIN_ADDR,
+ SPAPR_PCI_IO_WIN_SIZE);
+}
+
+void kvm__arch_delete_ram(struct kvm *kvm)
+{
+ munmap(kvm->ram_start, kvm->ram_size);
+}
+
+void kvm__irq_trigger(struct kvm *kvm, int irq)
+{
+ kvm__irq_line(kvm, irq, 1);
+ kvm__irq_line(kvm, irq, 0);
+}
+
+void kvm__arch_periodic_poll(struct kvm *kvm)
+{
+ /* FIXME: Should register callbacks to platform-specific polls */
+ spapr_hvcons_poll(kvm);
+}
+
+int load_flat_binary(struct kvm *kvm, int fd_kernel, int fd_initrd, const char *kernel_cmdline)
+{
+ void *p;
+ void *k_start;
+ void *i_start;
+ int nr;
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ p = k_start = guest_flat_to_host(kvm, KERNEL_LOAD_ADDR);
+
+ while ((nr = read(fd_kernel, p, 65536)) > 0)
+ p += nr;
+
+ pr_info("Loaded kernel to 0x%x (%ld bytes)", KERNEL_LOAD_ADDR, p-k_start);
+
+ if (fd_initrd != -1) {
+ if (lseek(fd_initrd, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ if (p-k_start > INITRD_LOAD_ADDR)
+ die("Kernel overlaps initrd!");
+
+ /* Round up kernel size to 8byte alignment, and load initrd right after. */
+ i_start = p = guest_flat_to_host(kvm, INITRD_LOAD_ADDR);
+
+ while (((nr = read(fd_initrd, p, 65536)) > 0) &&
+ p < (kvm->ram_start + kvm->ram_size))
+ p += nr;
+
+ if (p >= (kvm->ram_start + kvm->ram_size))
+ die("initrd too big to contain in guest RAM.\n");
+
+ pr_info("Loaded initrd to 0x%x (%ld bytes)",
+ INITRD_LOAD_ADDR, p-i_start);
+ kvm->initrd_gra = INITRD_LOAD_ADDR;
+ kvm->initrd_size = p-i_start;
+ } else {
+ kvm->initrd_size = 0;
+ }
+ strncpy(kern_cmdline, kernel_cmdline, 2048);
+ kern_cmdline[2047] = '\0';
+
+ return true;
+}
+
+bool load_bzimage(struct kvm *kvm, int fd_kernel,
+ int fd_initrd, const char *kernel_cmdline, u16 vidmode)
+{
+ /* We don't support bzImages. */
+ return false;
+}
+
+struct fdt_prop {
+ void *value;
+ int size;
+};
+
+static void generate_segment_page_sizes(struct kvm_ppc_smmu_info *info, struct fdt_prop *prop)
+{
+ struct kvm_ppc_one_seg_page_size *sps;
+ int i, j, size;
+ u32 *p;
+
+ for (size = 0, i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ sps = &info->sps[i];
+
+ if (sps->page_shift == 0)
+ break;
+
+ /* page shift, slb enc & count */
+ size += 3;
+
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (info->sps[i].enc[j].page_shift == 0)
+ break;
+
+ /* page shift & pte enc */
+ size += 2;
+ }
+ }
+
+ if (!size) {
+ prop->value = NULL;
+ prop->size = 0;
+ return;
+ }
+
+ /* Convert size to bytes */
+ prop->size = size * sizeof(u32);
+
+ prop->value = malloc(prop->size);
+ if (!prop->value)
+ die_perror("malloc failed");
+
+ p = (u32 *)prop->value;
+ for (i = 0; i < KVM_PPC_PAGE_SIZES_MAX_SZ; i++) {
+ sps = &info->sps[i];
+
+ if (sps->page_shift == 0)
+ break;
+
+ *p++ = sps->page_shift;
+ *p++ = sps->slb_enc;
+
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++)
+ if (!info->sps[i].enc[j].page_shift)
+ break;
+
+ *p++ = j; /* count of enc */
+
+ for (j = 0; j < KVM_PPC_PAGE_SIZES_MAX_SZ; j++) {
+ if (!info->sps[i].enc[j].page_shift)
+ break;
+
+ *p++ = info->sps[i].enc[j].page_shift;
+ *p++ = info->sps[i].enc[j].pte_enc;
+ }
+ }
+}
+
+#define SMT_THREADS 4
+
+/*
+ * Set up the FDT for the kernel: This function is currently fairly SPAPR-heavy,
+ * and whilst most PPC targets will require CPU/memory nodes, others like RTAS
+ * should eventually be added separately.
+ */
+static void setup_fdt(struct kvm *kvm)
+{
+ uint64_t mem_reg_property[] = { 0, cpu_to_be64(kvm->ram_size) };
+ int smp_cpus = kvm->nrcpus;
+ uint32_t int_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
+ char hypertas_prop_kvm[] = "hcall-pft\0hcall-term\0"
+ "hcall-dabr\0hcall-interrupt\0hcall-tce\0hcall-vio\0"
+ "hcall-splpar\0hcall-bulk";
+ int i, j;
+ char cpu_name[30];
+ u8 staging_fdt[FDT_MAX_SIZE];
+ struct cpu_info *cpu_info = find_cpu_info(kvm);
+ struct fdt_prop segment_page_sizes;
+ u32 segment_sizes_1T[] = {0x1c, 0x28, 0xffffffff, 0xffffffff};
+
+ /* Generate an appropriate DT at kvm->fdt_gra */
+ void *fdt_dest = guest_flat_to_host(kvm, kvm->fdt_gra);
+ void *fdt = staging_fdt;
+
+ _FDT(fdt_create(fdt, FDT_MAX_SIZE));
+ _FDT(fdt_finish_reservemap(fdt));
+
+ _FDT(fdt_begin_node(fdt, ""));
+
+ _FDT(fdt_property_string(fdt, "device_type", "chrp"));
+ _FDT(fdt_property_string(fdt, "model", "IBM pSeries (kvmtool)"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x2));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x2));
+
+ /* RTAS */
+ _FDT(fdt_begin_node(fdt, "rtas"));
+ /* This is what the kernel uses to switch 'We're an LPAR'! */
+ _FDT(fdt_property(fdt, "ibm,hypertas-functions", hypertas_prop_kvm,
+ sizeof(hypertas_prop_kvm)));
+ _FDT(fdt_property_cell(fdt, "linux,rtas-base", kvm->rtas_gra));
+ _FDT(fdt_property_cell(fdt, "linux,rtas-entry", kvm->rtas_gra));
+ _FDT(fdt_property_cell(fdt, "rtas-size", kvm->rtas_size));
+ /* Now add properties for all RTAS tokens: */
+ if (spapr_rtas_fdt_setup(kvm, fdt))
+ die("Couldn't create RTAS FDT properties\n");
+
+ _FDT(fdt_end_node(fdt));
+
+ /* /chosen */
+ _FDT(fdt_begin_node(fdt, "chosen"));
+ /* cmdline */
+ _FDT(fdt_property_string(fdt, "bootargs", kern_cmdline));
+ /* Initrd */
+ if (kvm->initrd_size != 0) {
+ uint32_t ird_st_prop = cpu_to_be32(kvm->initrd_gra);
+ uint32_t ird_end_prop = cpu_to_be32(kvm->initrd_gra +
+ kvm->initrd_size);
+ _FDT(fdt_property(fdt, "linux,initrd-start",
+ &ird_st_prop, sizeof(ird_st_prop)));
+ _FDT(fdt_property(fdt, "linux,initrd-end",
+ &ird_end_prop, sizeof(ird_end_prop)));
+ }
+
+ /*
+ * stdout-path: This is assuming we're using the HV console. Also, the
+ * address is hardwired until we do a VIO bus.
+ */
+ _FDT(fdt_property_string(fdt, "linux,stdout-path",
+ "/vdevice/vty@30000000"));
+ _FDT(fdt_end_node(fdt));
+
+ /*
+ * Memory: We don't alloc. a separate RMA yet. If we ever need to
+ * (CAP_PPC_RMA == 2) then have one memory node for 0->RMAsize, and
+ * another RMAsize->endOfMem.
+ */
+ _FDT(fdt_begin_node(fdt, "memory@0"));
+ _FDT(fdt_property_string(fdt, "device_type", "memory"));
+ _FDT(fdt_property(fdt, "reg", mem_reg_property,
+ sizeof(mem_reg_property)));
+ _FDT(fdt_end_node(fdt));
+
+ generate_segment_page_sizes(&cpu_info->mmu_info, &segment_page_sizes);
+
+ /* CPUs */
+ _FDT(fdt_begin_node(fdt, "cpus"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x1));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x0));
+
+ for (i = 0; i < smp_cpus; i += SMT_THREADS) {
+ int32_t pft_size_prop[] = { 0, HPT_ORDER };
+ uint32_t servers_prop[SMT_THREADS];
+ uint32_t gservers_prop[SMT_THREADS * 2];
+ int threads = (smp_cpus - i) >= SMT_THREADS ? SMT_THREADS :
+ smp_cpus - i;
+
+ sprintf(cpu_name, "PowerPC,%s@%d", cpu_info->name, i);
+ _FDT(fdt_begin_node(fdt, cpu_name));
+ sprintf(cpu_name, "PowerPC,%s", cpu_info->name);
+ _FDT(fdt_property_string(fdt, "name", cpu_name));
+ _FDT(fdt_property_string(fdt, "device_type", "cpu"));
+
+ _FDT(fdt_property_cell(fdt, "reg", i));
+ _FDT(fdt_property_cell(fdt, "cpu-version", kvm->pvr));
+
+ _FDT(fdt_property_cell(fdt, "dcache-block-size", cpu_info->d_bsize));
+ _FDT(fdt_property_cell(fdt, "icache-block-size", cpu_info->i_bsize));
+
+ _FDT(fdt_property_cell(fdt, "timebase-frequency", cpu_info->tb_freq));
+ /* Lies, but safeish lies! */
+ _FDT(fdt_property_cell(fdt, "clock-frequency", 0xddbab200));
+
+ if (cpu_info->mmu_info.slb_size)
+ _FDT(fdt_property_cell(fdt, "ibm,slb-size", cpu_info->mmu_info.slb_size));
+
+ /*
+ * HPT size is hardwired; KVM currently fixes it at 16MB but the
+ * moment that changes we'll need to read it out of the kernel.
+ */
+ _FDT(fdt_property(fdt, "ibm,pft-size", pft_size_prop,
+ sizeof(pft_size_prop)));
+
+ _FDT(fdt_property_string(fdt, "status", "okay"));
+ _FDT(fdt_property(fdt, "64-bit", NULL, 0));
+ /* A server for each thread in this core */
+ for (j = 0; j < SMT_THREADS; j++) {
+ servers_prop[j] = cpu_to_be32(i+j);
+ /*
+ * Hack borrowed from QEMU, direct the group queues back
+ * to cpu 0:
+ */
+ gservers_prop[j*2] = cpu_to_be32(i+j);
+ gservers_prop[j*2 + 1] = 0;
+ }
+ _FDT(fdt_property(fdt, "ibm,ppc-interrupt-server#s",
+ servers_prop, threads * sizeof(uint32_t)));
+ _FDT(fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
+ gservers_prop,
+ threads * 2 * sizeof(uint32_t)));
+
+ if (segment_page_sizes.value)
+ _FDT(fdt_property(fdt, "ibm,segment-page-sizes",
+ segment_page_sizes.value,
+ segment_page_sizes.size));
+
+ if (cpu_info->mmu_info.flags & KVM_PPC_1T_SEGMENTS)
+ _FDT(fdt_property(fdt, "ibm,processor-segment-sizes",
+ segment_sizes_1T, sizeof(segment_sizes_1T)));
+
+ /* VSX / DFP options: */
+ if (cpu_info->flags & CPUINFO_FLAG_VMX)
+ _FDT(fdt_property_cell(fdt, "ibm,vmx",
+ (cpu_info->flags &
+ CPUINFO_FLAG_VSX) ? 2 : 1));
+ if (cpu_info->flags & CPUINFO_FLAG_DFP)
+ _FDT(fdt_property_cell(fdt, "ibm,dfp", 0x1));
+ _FDT(fdt_end_node(fdt));
+ }
+ _FDT(fdt_end_node(fdt));
+
+ /* IRQ controller */
+ _FDT(fdt_begin_node(fdt, "interrupt-controller@0"));
+
+ _FDT(fdt_property_string(fdt, "device_type",
+ "PowerPC-External-Interrupt-Presentation"));
+ _FDT(fdt_property_string(fdt, "compatible", "IBM,ppc-xicp"));
+ _FDT(fdt_property_cell(fdt, "reg", 0));
+ _FDT(fdt_property(fdt, "interrupt-controller", NULL, 0));
+ _FDT(fdt_property(fdt, "ibm,interrupt-server-ranges",
+ int_server_ranges_prop,
+ sizeof(int_server_ranges_prop)));
+ _FDT(fdt_property_cell(fdt, "#interrupt-cells", 2));
+ _FDT(fdt_property_cell(fdt, "linux,phandle", PHANDLE_XICP));
+ _FDT(fdt_property_cell(fdt, "phandle", PHANDLE_XICP));
+ _FDT(fdt_end_node(fdt));
+
+ /*
+ * VIO: See comment in linux,stdout-path; we don't yet represent a VIO
+ * bus/address allocation so addresses are hardwired here.
+ */
+ _FDT(fdt_begin_node(fdt, "vdevice"));
+ _FDT(fdt_property_cell(fdt, "#address-cells", 0x1));
+ _FDT(fdt_property_cell(fdt, "#size-cells", 0x0));
+ _FDT(fdt_property_string(fdt, "device_type", "vdevice"));
+ _FDT(fdt_property_string(fdt, "compatible", "IBM,vdevice"));
+ _FDT(fdt_begin_node(fdt, "vty@30000000"));
+ _FDT(fdt_property_string(fdt, "name", "vty"));
+ _FDT(fdt_property_string(fdt, "device_type", "serial"));
+ _FDT(fdt_property_string(fdt, "compatible", "hvterm1"));
+ _FDT(fdt_property_cell(fdt, "reg", 0x30000000));
+ _FDT(fdt_end_node(fdt));
+ _FDT(fdt_end_node(fdt));
+
+ /* Finalise: */
+ _FDT(fdt_end_node(fdt)); /* Root node */
+ _FDT(fdt_finish(fdt));
+
+ _FDT(fdt_open_into(fdt, fdt_dest, FDT_MAX_SIZE));
+
+ /* PCI */
+ if (spapr_populate_pci_devices(kvm, PHANDLE_XICP, fdt_dest))
+ die("Fail populating PCI device nodes");
+
+ _FDT(fdt_add_mem_rsv(fdt_dest, kvm->rtas_gra, kvm->rtas_size));
+ _FDT(fdt_pack(fdt_dest));
+
+ free(segment_page_sizes.value);
+}
+
+/**
+ * kvm__arch_setup_firmware
+ */
+int kvm__arch_setup_firmware(struct kvm *kvm)
+{
+ /*
+ * Set up RTAS stub. All it is is a single hypercall:
+ * 0: 7c 64 1b 78 mr r4,r3
+ * 4: 3c 60 00 00 lis r3,0
+ * 8: 60 63 f0 00 ori r3,r3,61440
+ * c: 44 00 00 22 sc 1
+ * 10: 4e 80 00 20 blr
+ */
+ uint32_t *rtas = guest_flat_to_host(kvm, kvm->rtas_gra);
+
+ rtas[0] = 0x7c641b78;
+ rtas[1] = 0x3c600000;
+ rtas[2] = 0x6063f000;
+ rtas[3] = 0x44000022;
+ rtas[4] = 0x4e800020;
+ kvm->rtas_size = 20;
+
+ pr_info("Set up %ld bytes of RTAS at 0x%lx\n",
+ kvm->rtas_size, kvm->rtas_gra);
+
+ /* Load SLOF */
+
+ /* Init FDT */
+ setup_fdt(kvm);
+
+ return 0;
+}
+
+int kvm__arch_free_firmware(struct kvm *kvm)
+{
+ return 0;
+}
--- /dev/null
+/*
+ * SPAPR definitions and declarations
+ *
+ * Borrowed heavily from QEMU's spapr.h,
+ * Copyright (c) 2010 David Gibson, IBM Corporation.
+ *
+ * Modifications by Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#if !defined(__HW_SPAPR_H__)
+#define __HW_SPAPR_H__
+
+#include <inttypes.h>
+
+/* We need some of the H_ hcall defs, but they're __KERNEL__ only. */
+#define __KERNEL__
+#include <asm/hvcall.h>
+#undef __KERNEL__
+
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+typedef unsigned long target_ulong;
+typedef uintptr_t target_phys_addr_t;
+
+/*
+ * The hcalls above are standardized in PAPR and implemented by pHyp
+ * as well.
+ *
+ * We also need some hcalls which are specific to qemu / KVM-on-POWER.
+ * So far we just need one for H_RTAS, but in future we'll need more
+ * for extensions like virtio. We put those into the 0xf000-0xfffc
+ * range which is reserved by PAPR for "platform-specific" hcalls.
+ */
+#define KVMPPC_HCALL_BASE 0xf000
+#define KVMPPC_H_RTAS (KVMPPC_HCALL_BASE + 0x0)
+#define KVMPPC_HCALL_MAX KVMPPC_H_RTAS
+
+#define DEBUG_SPAPR_HCALLS
+
+#ifdef DEBUG_SPAPR_HCALLS
+#define hcall_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define hcall_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+typedef target_ulong (*spapr_hcall_fn)(struct kvm_cpu *vcpu,
+ target_ulong opcode,
+ target_ulong *args);
+
+void hypercall_init(void);
+void register_core_rtas(void);
+
+void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn);
+target_ulong spapr_hypercall(struct kvm_cpu *vcpu, target_ulong opcode,
+ target_ulong *args);
+
+int spapr_rtas_fdt_setup(struct kvm *kvm, void *fdt);
+
+static inline uint32_t rtas_ld(struct kvm *kvm, target_ulong phys, int n)
+{
+ return *((uint32_t *)guest_flat_to_host(kvm, phys + 4*n));
+}
+
+static inline void rtas_st(struct kvm *kvm, target_ulong phys, int n, uint32_t val)
+{
+ *((uint32_t *)guest_flat_to_host(kvm, phys + 4*n)) = val;
+}
+
+typedef void (*spapr_rtas_fn)(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets);
+void spapr_rtas_register(const char *name, spapr_rtas_fn fn);
+target_ulong spapr_rtas_call(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets);
+
+#define SPAPR_PCI_BUID 0x800000020000001ULL
+#define SPAPR_PCI_MEM_WIN_ADDR (KVM_MMIO_START + 0xA0000000)
+#define SPAPR_PCI_MEM_WIN_SIZE 0x20000000
+#define SPAPR_PCI_IO_WIN_ADDR (SPAPR_PCI_MEM_WIN_ADDR + SPAPR_PCI_MEM_WIN_SIZE)
+#define SPAPR_PCI_IO_WIN_SIZE 0x2000000
+
+#define SPAPR_PCI_WIN_START SPAPR_PCI_MEM_WIN_ADDR
+#define SPAPR_PCI_WIN_END (SPAPR_PCI_IO_WIN_ADDR + SPAPR_PCI_IO_WIN_SIZE)
+
+#endif /* !defined (__HW_SPAPR_H__) */
--- /dev/null
+/*
+ * SPAPR hypercalls
+ *
+ * Borrowed heavily from QEMU's spapr_hcall.c,
+ * Copyright (c) 2010 David Gibson, IBM Corporation.
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+#include <stdio.h>
+#include <assert.h>
+
+static spapr_hcall_fn papr_hypercall_table[(MAX_HCALL_OPCODE / 4) + 1];
+static spapr_hcall_fn kvmppc_hypercall_table[KVMPPC_HCALL_MAX -
+ KVMPPC_HCALL_BASE + 1];
+
+static target_ulong h_set_dabr(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* FIXME: Implement this for -PR. (-HV does this in kernel.) */
+ return H_HARDWARE;
+}
+
+static target_ulong h_rtas(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ target_ulong rtas_r3 = args[0];
+ /*
+ * Pointer read from phys mem; these ptrs cannot be MMIO (!) so just
+ * reference guest RAM directly.
+ */
+ uint32_t token, nargs, nret;
+
+ token = rtas_ld(vcpu->kvm, rtas_r3, 0);
+ nargs = rtas_ld(vcpu->kvm, rtas_r3, 1);
+ nret = rtas_ld(vcpu->kvm, rtas_r3, 2);
+
+ return spapr_rtas_call(vcpu, token, nargs, rtas_r3 + 12,
+ nret, rtas_r3 + 12 + 4*nargs);
+}
+
+static target_ulong h_logical_load(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* SLOF will require these, though kernel doesn't. */
+ die(__PRETTY_FUNCTION__);
+ return H_PARAMETER;
+}
+
+static target_ulong h_logical_store(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* SLOF will require these, though kernel doesn't. */
+ die(__PRETTY_FUNCTION__);
+ return H_PARAMETER;
+}
+
+static target_ulong h_logical_icbi(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* KVM will trap this in the kernel. Die if it misses. */
+ die(__PRETTY_FUNCTION__);
+ return H_SUCCESS;
+}
+
+static target_ulong h_logical_dcbf(struct kvm_cpu *vcpu, target_ulong opcode, target_ulong *args)
+{
+ /* KVM will trap this in the kernel. Die if it misses. */
+ die(__PRETTY_FUNCTION__);
+ return H_SUCCESS;
+}
+
+void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn)
+{
+ spapr_hcall_fn *slot;
+
+ if (opcode <= MAX_HCALL_OPCODE) {
+ assert((opcode & 0x3) == 0);
+
+ slot = &papr_hypercall_table[opcode / 4];
+ } else {
+ assert((opcode >= KVMPPC_HCALL_BASE) &&
+ (opcode <= KVMPPC_HCALL_MAX));
+
+ slot = &kvmppc_hypercall_table[opcode - KVMPPC_HCALL_BASE];
+ }
+
+ assert(!(*slot) || (fn == *slot));
+ *slot = fn;
+}
+
+target_ulong spapr_hypercall(struct kvm_cpu *vcpu, target_ulong opcode,
+ target_ulong *args)
+{
+ if ((opcode <= MAX_HCALL_OPCODE)
+ && ((opcode & 0x3) == 0)) {
+ spapr_hcall_fn fn = papr_hypercall_table[opcode / 4];
+
+ if (fn) {
+ return fn(vcpu, opcode, args);
+ }
+ } else if ((opcode >= KVMPPC_HCALL_BASE) &&
+ (opcode <= KVMPPC_HCALL_MAX)) {
+ spapr_hcall_fn fn = kvmppc_hypercall_table[opcode -
+ KVMPPC_HCALL_BASE];
+
+ if (fn) {
+ return fn(vcpu, opcode, args);
+ }
+ }
+
+ hcall_dprintf("Unimplemented hcall 0x%lx\n", opcode);
+ return H_FUNCTION;
+}
+
+void hypercall_init(void)
+{
+ /* hcall-dabr */
+ spapr_register_hypercall(H_SET_DABR, h_set_dabr);
+
+ spapr_register_hypercall(H_LOGICAL_CI_LOAD, h_logical_load);
+ spapr_register_hypercall(H_LOGICAL_CI_STORE, h_logical_store);
+ spapr_register_hypercall(H_LOGICAL_CACHE_LOAD, h_logical_load);
+ spapr_register_hypercall(H_LOGICAL_CACHE_STORE, h_logical_store);
+ spapr_register_hypercall(H_LOGICAL_ICBI, h_logical_icbi);
+ spapr_register_hypercall(H_LOGICAL_DCBF, h_logical_dcbf);
+
+ /* KVM-PPC specific hcalls */
+ spapr_register_hypercall(KVMPPC_H_RTAS, h_rtas);
+}
--- /dev/null
+/*
+ * SPAPR HV console
+ *
+ * Borrowed lightly from QEMU's spapr_vty.c, Copyright (c) 2010 David Gibson,
+ * IBM Corporation.
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/term.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+#include "spapr.h"
+#include "spapr_hvcons.h"
+
+#include <stdio.h>
+#include <sys/uio.h>
+#include <errno.h>
+
+#include <linux/byteorder.h>
+
+union hv_chario {
+ struct {
+ uint64_t char0_7;
+ uint64_t char8_15;
+ } a;
+ uint8_t buf[16];
+};
+
+static unsigned long h_put_term_char(struct kvm_cpu *vcpu, unsigned long opcode, unsigned long *args)
+{
+ /* To do: Read register from args[0], and check it. */
+ unsigned long len = args[1];
+ union hv_chario data;
+ struct iovec iov;
+
+ if (len > 16) {
+ return H_PARAMETER;
+ }
+ data.a.char0_7 = cpu_to_be64(args[2]);
+ data.a.char8_15 = cpu_to_be64(args[3]);
+
+ iov.iov_base = data.buf;
+ iov.iov_len = len;
+ do {
+ int ret;
+
+ ret = term_putc_iov(CONSOLE_HV, &iov, 1, 0);
+ if (ret < 0) {
+ die("term_putc_iov error %d!\n", errno);
+ }
+ iov.iov_base += ret;
+ iov.iov_len -= ret;
+ } while (iov.iov_len > 0);
+
+ return H_SUCCESS;
+}
+
+
+static unsigned long h_get_term_char(struct kvm_cpu *vcpu, unsigned long opcode, unsigned long *args)
+{
+ /* To do: Read register from args[0], and check it. */
+ unsigned long *len = args + 0;
+ unsigned long *char0_7 = args + 1;
+ unsigned long *char8_15 = args + 2;
+ union hv_chario data;
+ struct iovec iov;
+
+ if (term_readable(CONSOLE_HV, 0)) {
+ iov.iov_base = data.buf;
+ iov.iov_len = 16;
+
+ *len = term_getc_iov(CONSOLE_HV, &iov, 1, 0);
+ *char0_7 = be64_to_cpu(data.a.char0_7);
+ *char8_15 = be64_to_cpu(data.a.char8_15);
+ } else {
+ *len = 0;
+ }
+
+ return H_SUCCESS;
+}
+
+void spapr_hvcons_poll(struct kvm *kvm)
+{
+ if (term_readable(CONSOLE_HV, 0)) {
+ /*
+ * We can inject an IRQ to guest here if we want. The guest
+ * will happily poll, though, so not required.
+ */
+ }
+}
+
+void spapr_hvcons_init(void)
+{
+ spapr_register_hypercall(H_PUT_TERM_CHAR, h_put_term_char);
+ spapr_register_hypercall(H_GET_TERM_CHAR, h_get_term_char);
+}
--- /dev/null
+/*
+ * SPAPR HV console
+ *
+ * Copyright (c) 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef spapr_hvcons_H
+#define spapr_hvcons_H
+
+#include "kvm/kvm.h"
+
+void spapr_hvcons_init(void);
+void spapr_hvcons_poll(struct kvm *kvm);
+
+#endif
--- /dev/null
+/*
+ * SPAPR PHB emulation, RTAS interface to PCI config space, device tree nodes
+ * for enumerated devices.
+ *
+ * Borrowed heavily from QEMU's spapr_pci.c,
+ * Copyright (c) 2011 Alexey Kardashevskiy, IBM Corporation.
+ * Copyright (c) 2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "spapr_pci.h"
+#include "kvm/util.h"
+#include "kvm/pci.h"
+#include "libfdt.h"
+
+#include <linux/pci_regs.h>
+#include <linux/byteorder.h>
+
+
+/* #define DEBUG_PHB yes */
+#ifdef DEBUG_PHB
+#define phb_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define phb_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+static const uint32_t bars[] = {
+ PCI_BASE_ADDRESS_0, PCI_BASE_ADDRESS_1,
+ PCI_BASE_ADDRESS_2, PCI_BASE_ADDRESS_3,
+ PCI_BASE_ADDRESS_4, PCI_BASE_ADDRESS_5
+ /*, PCI_ROM_ADDRESS*/
+};
+
+#define PCI_NUM_REGIONS 7
+
+/* Macros to operate with address in OF binding to PCI */
+#define b_x(x, p, l) (((x) & ((1<<(l))-1)) << (p))
+#define b_n(x) b_x((x), 31, 1) /* 0 if relocatable */
+#define b_p(x) b_x((x), 30, 1) /* 1 if prefetchable */
+#define b_t(x) b_x((x), 29, 1) /* 1 if the address is aliased */
+#define b_ss(x) b_x((x), 24, 2) /* the space code */
+#define b_bbbbbbbb(x) b_x((x), 16, 8) /* bus number */
+#define b_ddddd(x) b_x((x), 11, 5) /* device number */
+#define b_fff(x) b_x((x), 8, 3) /* function number */
+#define b_rrrrrrrr(x) b_x((x), 0, 8) /* register number */
+
+#define SS_M64 3
+#define SS_M32 2
+#define SS_IO 1
+#define SS_CONFIG 0
+
+
+static struct spapr_phb phb;
+
+
+static void rtas_ibm_read_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ uint32_t val = 0;
+ uint64_t buid = ((uint64_t)rtas_ld(vcpu->kvm, args, 1) << 32) | rtas_ld(vcpu->kvm, args, 2);
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 3);
+
+ if (buid != phb.buid || !dev || (size > 4)) {
+ phb_dprintf("- cfgRd buid 0x%lx cfg addr 0x%x size %d not found\n",
+ buid, addr.w, size);
+
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+ pci__config_rd(vcpu->kvm, addr, &val, size);
+ /* It appears this wants a byteswapped result... */
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val>>16);
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ phb_dprintf("- cfgRd buid 0x%lx addr 0x%x (/%d): b%d,d%d,f%d,r0x%x, val 0x%x\n",
+ buid, addr.w, size, addr.bus_number, addr.device_number, addr.function_number,
+ addr.register_number, val);
+
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, val);
+}
+
+static void rtas_read_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ uint32_t val;
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 1);
+
+ if (!dev || (size > 4)) {
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+ pci__config_rd(vcpu->kvm, addr, &val, size);
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val>>16); /* We're yuck-endian. */
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ phb_dprintf("- cfgRd addr 0x%x size %d, val 0x%x\n", addr.w, size, val);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, val);
+}
+
+static void rtas_ibm_write_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ uint64_t buid = ((uint64_t)rtas_ld(vcpu->kvm, args, 1) << 32) | rtas_ld(vcpu->kvm, args, 2);
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 3);
+ uint32_t val = rtas_ld(vcpu->kvm, args, 4);
+
+ if (buid != phb.buid || !dev || (size > 4)) {
+ phb_dprintf("- cfgWr buid 0x%lx cfg addr 0x%x/%d error (val 0x%x)\n",
+ buid, addr.w, size, val);
+
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+ phb_dprintf("- cfgWr buid 0x%lx addr 0x%x (/%d): b%d,d%d,f%d,r0x%x, val 0x%x\n",
+ buid, addr.w, size, addr.bus_number, addr.device_number, addr.function_number,
+ addr.register_number, val);
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val) << 16;
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ pci__config_wr(vcpu->kvm, addr, &val, size);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+static void rtas_write_pci_config(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ union pci_config_address addr = { .w = rtas_ld(vcpu->kvm, args, 0) };
+ struct pci_device_header *dev = pci__find_dev(addr.device_number);
+ uint32_t size = rtas_ld(vcpu->kvm, args, 1);
+ uint32_t val = rtas_ld(vcpu->kvm, args, 2);
+
+ if (!dev || (size > 4)) {
+ rtas_st(vcpu->kvm, rets, 0, -1);
+ return;
+ }
+
+ phb_dprintf("- cfgWr addr 0x%x (/%d): b%d,d%d,f%d,r0x%x, val 0x%x\n",
+ addr.w, size, addr.bus_number, addr.device_number, addr.function_number,
+ addr.register_number, val);
+ switch (size) {
+ case 4:
+ val = le32_to_cpu(val);
+ break;
+ case 2:
+ val = le16_to_cpu(val) << 16;
+ break;
+ case 1:
+ val = val >> 24;
+ break;
+ }
+ pci__config_wr(vcpu->kvm, addr, &val, size);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+void spapr_create_phb(struct kvm *kvm,
+ const char *busname, uint64_t buid,
+ uint64_t mem_win_addr, uint64_t mem_win_size,
+ uint64_t io_win_addr, uint64_t io_win_size)
+{
+ /*
+ * Since kvmtool doesn't really have any concept of buses etc.,
+ * there's nothing to register here. Just register RTAS.
+ */
+ spapr_rtas_register("read-pci-config", rtas_read_pci_config);
+ spapr_rtas_register("write-pci-config", rtas_write_pci_config);
+ spapr_rtas_register("ibm,read-pci-config", rtas_ibm_read_pci_config);
+ spapr_rtas_register("ibm,write-pci-config", rtas_ibm_write_pci_config);
+
+ phb.buid = buid;
+ phb.mem_addr = mem_win_addr;
+ phb.mem_size = mem_win_size;
+ phb.io_addr = io_win_addr;
+ phb.io_size = io_win_size;
+
+ kvm->phb = &phb;
+}
+
+static uint32_t bar_to_ss(unsigned long bar)
+{
+ if ((bar & PCI_BASE_ADDRESS_SPACE) ==
+ PCI_BASE_ADDRESS_SPACE_IO)
+ return SS_IO;
+ else if (bar & PCI_BASE_ADDRESS_MEM_TYPE_64)
+ return SS_M64;
+ else
+ return SS_M32;
+}
+
+static unsigned long bar_to_addr(unsigned long bar)
+{
+ if ((bar & PCI_BASE_ADDRESS_SPACE) ==
+ PCI_BASE_ADDRESS_SPACE_IO)
+ return bar & PCI_BASE_ADDRESS_IO_MASK;
+ else
+ return bar & PCI_BASE_ADDRESS_MEM_MASK;
+}
+
+int spapr_populate_pci_devices(struct kvm *kvm,
+ uint32_t xics_phandle,
+ void *fdt)
+{
+ int bus_off, node_off = 0, devid, fn, i, n, devices;
+ char nodename[256];
+ struct {
+ uint32_t hi;
+ uint64_t addr;
+ uint64_t size;
+ } __attribute__((packed)) reg[PCI_NUM_REGIONS + 1],
+ assigned_addresses[PCI_NUM_REGIONS];
+ uint32_t bus_range[] = { cpu_to_be32(0), cpu_to_be32(0xff) };
+ struct {
+ uint32_t hi;
+ uint64_t child;
+ uint64_t parent;
+ uint64_t size;
+ } __attribute__((packed)) ranges[] = {
+ {
+ cpu_to_be32(b_ss(1)), cpu_to_be64(0),
+ cpu_to_be64(phb.io_addr),
+ cpu_to_be64(phb.io_size),
+ },
+ {
+ cpu_to_be32(b_ss(2)), cpu_to_be64(0),
+ cpu_to_be64(phb.mem_addr),
+ cpu_to_be64(phb.mem_size),
+ },
+ };
+ uint64_t bus_reg[] = { cpu_to_be64(phb.buid), 0 };
+ uint32_t interrupt_map_mask[] = {
+ cpu_to_be32(b_ddddd(-1)|b_fff(-1)), 0x0, 0x0, 0x0};
+ uint32_t interrupt_map[SPAPR_PCI_NUM_LSI][7];
+
+ /* Start populating the FDT */
+ sprintf(nodename, "pci@%" PRIx64, phb.buid);
+ bus_off = fdt_add_subnode(fdt, 0, nodename);
+ if (bus_off < 0) {
+ die("error making bus subnode, %s\n", fdt_strerror(bus_off));
+ return bus_off;
+ }
+
+ /* Write PHB properties */
+ _FDT(fdt_setprop_string(fdt, bus_off, "device_type", "pci"));
+ _FDT(fdt_setprop_string(fdt, bus_off, "compatible", "IBM,Logical_PHB"));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "#address-cells", 0x3));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "#size-cells", 0x2));
+ _FDT(fdt_setprop_cell(fdt, bus_off, "#interrupt-cells", 0x1));
+ _FDT(fdt_setprop(fdt, bus_off, "used-by-rtas", NULL, 0));
+ _FDT(fdt_setprop(fdt, bus_off, "bus-range", &bus_range, sizeof(bus_range)));
+ _FDT(fdt_setprop(fdt, bus_off, "ranges", &ranges, sizeof(ranges)));
+ _FDT(fdt_setprop(fdt, bus_off, "reg", &bus_reg, sizeof(bus_reg)));
+ _FDT(fdt_setprop(fdt, bus_off, "interrupt-map-mask",
+ &interrupt_map_mask, sizeof(interrupt_map_mask)));
+
+ /* Populate PCI devices and allocate IRQs */
+ devices = 0;
+
+ for (devid = 0; devid < PCI_MAX_DEVICES; devid++) {
+ uint32_t *irqmap = interrupt_map[devices];
+ struct pci_device_header *hdr = pci__find_dev(devid);
+
+ if (!hdr)
+ continue;
+
+ fn = 0; /* kvmtool doesn't yet do multifunction devices */
+
+ sprintf(nodename, "pci@%u,%u", devid, fn);
+
+ /* Allocate interrupt from the map */
+ if (devid > SPAPR_PCI_NUM_LSI) {
+ die("Unexpected behaviour in spapr_populate_pci_devices,"
+ "wrong devid %u\n", devid);
+ }
+ irqmap[0] = cpu_to_be32(b_ddddd(devid)|b_fff(fn));
+ irqmap[1] = 0;
+ irqmap[2] = 0;
+ irqmap[3] = 0;
+ irqmap[4] = cpu_to_be32(xics_phandle);
+ /*
+ * This is nasty; the PCI devs are set up such that their own
+ * header's irq_line indicates the direct XICS IRQ number to
+ * use. There REALLY needs to be a hierarchical system in place
+ * to 'raise' an IRQ on the bridge which indexes/looks up which
+ * XICS IRQ to fire.
+ */
+ irqmap[5] = cpu_to_be32(hdr->irq_line);
+ irqmap[6] = cpu_to_be32(0x8);
+
+ /* Add node to FDT */
+ node_off = fdt_add_subnode(fdt, bus_off, nodename);
+ if (node_off < 0) {
+ die("error making node subnode, %s\n", fdt_strerror(bus_off));
+ return node_off;
+ }
+
+ _FDT(fdt_setprop_cell(fdt, node_off, "vendor-id",
+ le16_to_cpu(hdr->vendor_id)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "device-id",
+ le16_to_cpu(hdr->device_id)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "revision-id",
+ hdr->revision_id));
+ _FDT(fdt_setprop_cell(fdt, node_off, "class-code",
+ hdr->class[0] | (hdr->class[1] << 8) | (hdr->class[2] << 16)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "subsystem-id",
+ le16_to_cpu(hdr->subsys_id)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "subsystem-vendor-id",
+ le16_to_cpu(hdr->subsys_vendor_id)));
+
+ /* Config space region comes first */
+ reg[0].hi = cpu_to_be32(
+ b_n(0) |
+ b_p(0) |
+ b_t(0) |
+ b_ss(SS_CONFIG) |
+ b_bbbbbbbb(0) |
+ b_ddddd(devid) |
+ b_fff(fn));
+ reg[0].addr = 0;
+ reg[0].size = 0;
+
+ n = 0;
+ /* Six BARs, no ROM supported, addresses are 32bit */
+ for (i = 0; i < 6; ++i) {
+ if (0 == hdr->bar[i]) {
+ continue;
+ }
+
+ reg[n+1].hi = cpu_to_be32(
+ b_n(0) |
+ b_p(0) |
+ b_t(0) |
+ b_ss(bar_to_ss(le32_to_cpu(hdr->bar[i]))) |
+ b_bbbbbbbb(0) |
+ b_ddddd(devid) |
+ b_fff(fn) |
+ b_rrrrrrrr(bars[i]));
+ reg[n+1].addr = 0;
+ reg[n+1].size = cpu_to_be64(hdr->bar_size[i]);
+
+ assigned_addresses[n].hi = cpu_to_be32(
+ b_n(1) |
+ b_p(0) |
+ b_t(0) |
+ b_ss(bar_to_ss(le32_to_cpu(hdr->bar[i]))) |
+ b_bbbbbbbb(0) |
+ b_ddddd(devid) |
+ b_fff(fn) |
+ b_rrrrrrrr(bars[i]));
+
+ /*
+ * Writing zeroes to assigned_addresses causes the guest kernel to
+ * reassign BARs
+ */
+ assigned_addresses[n].addr = cpu_to_be64(bar_to_addr(le32_to_cpu(hdr->bar[i])));
+ assigned_addresses[n].size = reg[n+1].size;
+
+ ++n;
+ }
+ _FDT(fdt_setprop(fdt, node_off, "reg", reg, sizeof(reg[0])*(n+1)));
+ _FDT(fdt_setprop(fdt, node_off, "assigned-addresses",
+ assigned_addresses,
+ sizeof(assigned_addresses[0])*(n)));
+ _FDT(fdt_setprop_cell(fdt, node_off, "interrupts",
+ hdr->irq_pin));
+
+ /* We don't set ibm,dma-window property as we don't have an IOMMU. */
+
+ ++devices;
+ }
+
+ /* Write interrupt map */
+ _FDT(fdt_setprop(fdt, bus_off, "interrupt-map", &interrupt_map,
+ devices * sizeof(interrupt_map[0])));
+
+ return 0;
+}
--- /dev/null
+/*
+ * SPAPR PHB definitions
+ *
+ * Modifications by Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef SPAPR_PCI_H
+#define SPAPR_PCI_H
+
+#include "kvm/kvm.h"
+#include "spapr.h"
+#include <inttypes.h>
+
+/* With XICS, we can easily accomodate 1 IRQ per PCI device. */
+
+#define SPAPR_PCI_NUM_LSI 256
+
+struct spapr_phb {
+ uint64_t buid;
+ uint64_t mem_addr;
+ uint64_t mem_size;
+ uint64_t io_addr;
+ uint64_t io_size;
+};
+
+void spapr_create_phb(struct kvm *kvm,
+ const char *busname, uint64_t buid,
+ uint64_t mem_win_addr, uint64_t mem_win_size,
+ uint64_t io_win_addr, uint64_t io_win_size);
+
+int spapr_populate_pci_devices(struct kvm *kvm,
+ uint32_t xics_phandle,
+ void *fdt);
+
+static inline bool spapr_phb_mmio(struct kvm *kvm, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ if ((phys_addr >= SPAPR_PCI_IO_WIN_ADDR) &&
+ (phys_addr < SPAPR_PCI_IO_WIN_ADDR +
+ SPAPR_PCI_IO_WIN_SIZE)) {
+ return kvm__emulate_io(kvm, phys_addr - SPAPR_PCI_IO_WIN_ADDR,
+ data, is_write ? KVM_EXIT_IO_OUT :
+ KVM_EXIT_IO_IN,
+ len, 1);
+ } else if ((phys_addr >= SPAPR_PCI_MEM_WIN_ADDR) &&
+ (phys_addr < SPAPR_PCI_MEM_WIN_ADDR +
+ SPAPR_PCI_MEM_WIN_SIZE)) {
+ return kvm__emulate_mmio(kvm, phys_addr - SPAPR_PCI_MEM_WIN_ADDR,
+ data, len, is_write);
+ }
+ return false;
+}
+
+#endif
--- /dev/null
+/*
+ * SPAPR base RTAS calls
+ *
+ * Borrowed heavily from QEMU's spapr_rtas.c
+ * Copyright (c) 2010-2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "libfdt.h"
+
+#include "spapr.h"
+
+#include <stdio.h>
+#include <assert.h>
+
+#define TOKEN_BASE 0x2000
+#define TOKEN_MAX 0x100
+
+#define RTAS_CONSOLE
+
+static struct rtas_call {
+ const char *name;
+ spapr_rtas_fn fn;
+} rtas_table[TOKEN_MAX];
+
+struct rtas_call *rtas_next = rtas_table;
+
+
+static void rtas_display_character(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ char c = rtas_ld(vcpu->kvm, args, 0);
+ term_putc(CONSOLE_HV, &c, 1, 0);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+#ifdef RTAS_CONSOLE
+static void rtas_put_term_char(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ char c = rtas_ld(vcpu->kvm, args, 0);
+ term_putc(CONSOLE_HV, &c, 1, 0);
+ rtas_st(vcpu->kvm, rets, 0, 0);
+}
+
+static void rtas_get_term_char(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ int c;
+ if (term_readable(CONSOLE_HV, 0) &&
+ (c = term_getc(CONSOLE_HV, 0)) >= 0) {
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, c);
+ } else {
+ rtas_st(vcpu->kvm, rets, 0, -2);
+ }
+}
+#endif
+
+static void rtas_get_time_of_day(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct tm tm;
+ time_t tnow;
+
+ if (nret != 8) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ tnow = time(NULL);
+ /* Guest time is currently not offset in any way. */
+ gmtime_r(&tnow, &tm);
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+ rtas_st(vcpu->kvm, rets, 1, tm.tm_year + 1900);
+ rtas_st(vcpu->kvm, rets, 2, tm.tm_mon + 1);
+ rtas_st(vcpu->kvm, rets, 3, tm.tm_mday);
+ rtas_st(vcpu->kvm, rets, 4, tm.tm_hour);
+ rtas_st(vcpu->kvm, rets, 5, tm.tm_min);
+ rtas_st(vcpu->kvm, rets, 6, tm.tm_sec);
+ rtas_st(vcpu->kvm, rets, 7, 0);
+}
+
+static void rtas_set_time_of_day(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ pr_warning("%s called; TOD set ignored.\n", __FUNCTION__);
+}
+
+static void rtas_power_off(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if (nargs != 2 || nret != 1) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+ kvm_cpu__reboot();
+}
+
+static void rtas_query_cpu_stopped_state(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if (nargs != 1 || nret != 2) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /*
+ * Can read id = rtas_ld(vcpu->kvm, args, 0), but
+ * we currently start all CPUs. So just return true.
+ */
+ rtas_st(vcpu->kvm, rets, 0, 0);
+ rtas_st(vcpu->kvm, rets, 1, 2);
+}
+
+static void rtas_start_cpu(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs,
+ target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ die(__FUNCTION__);
+}
+
+target_ulong spapr_rtas_call(struct kvm_cpu *vcpu,
+ uint32_t token, uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ if ((token >= TOKEN_BASE)
+ && ((token - TOKEN_BASE) < TOKEN_MAX)) {
+ struct rtas_call *call = rtas_table + (token - TOKEN_BASE);
+
+ if (call->fn) {
+ call->fn(vcpu, token, nargs, args, nret, rets);
+ return H_SUCCESS;
+ }
+ }
+
+ /*
+ * HACK: Some Linux early debug code uses RTAS display-character,
+ * but assumes the token value is 0xa (which it is on some real
+ * machines) without looking it up in the device tree. This
+ * special case makes this work
+ */
+ if (token == 0xa) {
+ rtas_display_character(vcpu, 0xa, nargs, args, nret, rets);
+ return H_SUCCESS;
+ }
+
+ hcall_dprintf("Unknown RTAS token 0x%x\n", token);
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return H_PARAMETER;
+}
+
+void spapr_rtas_register(const char *name, spapr_rtas_fn fn)
+{
+ assert(rtas_next < (rtas_table + TOKEN_MAX));
+
+ rtas_next->name = name;
+ rtas_next->fn = fn;
+
+ rtas_next++;
+}
+
+/*
+ * This is called from the context of an open /rtas node, in order to add
+ * properties for the rtas call tokens.
+ */
+int spapr_rtas_fdt_setup(struct kvm *kvm, void *fdt)
+{
+ int ret;
+ int i;
+
+ for (i = 0; i < TOKEN_MAX; i++) {
+ struct rtas_call *call = &rtas_table[i];
+
+ if (!call->fn) {
+ continue;
+ }
+
+ ret = fdt_property_cell(fdt, call->name, i + TOKEN_BASE);
+
+ if (ret < 0) {
+ pr_warning("Couldn't add rtas token for %s: %s\n",
+ call->name, fdt_strerror(ret));
+ return ret;
+ }
+
+ }
+ return 0;
+}
+
+void register_core_rtas(void)
+{
+ spapr_rtas_register("display-character", rtas_display_character);
+ spapr_rtas_register("get-time-of-day", rtas_get_time_of_day);
+ spapr_rtas_register("set-time-of-day", rtas_set_time_of_day);
+ spapr_rtas_register("power-off", rtas_power_off);
+ spapr_rtas_register("query-cpu-stopped-state",
+ rtas_query_cpu_stopped_state);
+ spapr_rtas_register("start-cpu", rtas_start_cpu);
+#ifdef RTAS_CONSOLE
+ /* These are unused: We do console I/O via hcalls, not rtas. */
+ spapr_rtas_register("put-term-char", rtas_put_term_char);
+ spapr_rtas_register("get-term-char", rtas_get_term_char);
+#endif
+}
--- /dev/null
+/*
+ * PAPR Virtualized Interrupt System, aka ICS/ICP aka xics
+ *
+ * Borrowed heavily from QEMU's xics.c,
+ * Copyright (c) 2010,2011 David Gibson, IBM Corporation.
+ *
+ * Modifications copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include "spapr.h"
+#include "xics.h"
+#include "kvm/util.h"
+
+#include <stdio.h>
+#include <malloc.h>
+
+
+/* #define DEBUG_XICS yes */
+#ifdef DEBUG_XICS
+#define xics_dprintf(fmt, ...) \
+ do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
+#else
+#define xics_dprintf(fmt, ...) \
+ do { } while (0)
+#endif
+
+/*
+ * ICP: Presentation layer
+ */
+
+struct icp_server_state {
+ uint32_t xirr;
+ uint8_t pending_priority;
+ uint8_t mfrr;
+ struct kvm_cpu *cpu;
+};
+
+#define XICS_IRQ_OFFSET 16
+#define XISR_MASK 0x00ffffff
+#define CPPR_MASK 0xff000000
+
+#define XISR(ss) (((ss)->xirr) & XISR_MASK)
+#define CPPR(ss) (((ss)->xirr) >> 24)
+
+struct ics_state;
+
+struct icp_state {
+ unsigned long nr_servers;
+ struct icp_server_state *ss;
+ struct ics_state *ics;
+};
+
+static void ics_reject(struct ics_state *ics, int nr);
+static void ics_resend(struct ics_state *ics);
+static void ics_eoi(struct ics_state *ics, int nr);
+
+static inline void cpu_irq_raise(struct kvm_cpu *vcpu)
+{
+ xics_dprintf("INT1[%p]\n", vcpu);
+ kvm_cpu__irq(vcpu, POWER7_EXT_IRQ, 1);
+}
+
+static inline void cpu_irq_lower(struct kvm_cpu *vcpu)
+{
+ xics_dprintf("INT0[%p]\n", vcpu);
+ kvm_cpu__irq(vcpu, POWER7_EXT_IRQ, 0);
+}
+
+static void icp_check_ipi(struct icp_state *icp, int server)
+{
+ struct icp_server_state *ss = icp->ss + server;
+
+ if (XISR(ss) && (ss->pending_priority <= ss->mfrr)) {
+ return;
+ }
+
+ if (XISR(ss)) {
+ ics_reject(icp->ics, XISR(ss));
+ }
+
+ ss->xirr = (ss->xirr & ~XISR_MASK) | XICS_IPI;
+ ss->pending_priority = ss->mfrr;
+ cpu_irq_raise(ss->cpu);
+}
+
+static void icp_resend(struct icp_state *icp, int server)
+{
+ struct icp_server_state *ss = icp->ss + server;
+
+ if (ss->mfrr < CPPR(ss)) {
+ icp_check_ipi(icp, server);
+ }
+ ics_resend(icp->ics);
+}
+
+static void icp_set_cppr(struct icp_state *icp, int server, uint8_t cppr)
+{
+ struct icp_server_state *ss = icp->ss + server;
+ uint8_t old_cppr;
+ uint32_t old_xisr;
+
+ old_cppr = CPPR(ss);
+ ss->xirr = (ss->xirr & ~CPPR_MASK) | (cppr << 24);
+
+ if (cppr < old_cppr) {
+ if (XISR(ss) && (cppr <= ss->pending_priority)) {
+ old_xisr = XISR(ss);
+ ss->xirr &= ~XISR_MASK; /* Clear XISR */
+ cpu_irq_lower(ss->cpu);
+ ics_reject(icp->ics, old_xisr);
+ }
+ } else {
+ if (!XISR(ss)) {
+ icp_resend(icp, server);
+ }
+ }
+}
+
+static void icp_set_mfrr(struct icp_state *icp, int nr, uint8_t mfrr)
+{
+ struct icp_server_state *ss = icp->ss + nr;
+
+ ss->mfrr = mfrr;
+ if (mfrr < CPPR(ss)) {
+ icp_check_ipi(icp, nr);
+ }
+}
+
+static uint32_t icp_accept(struct icp_server_state *ss)
+{
+ uint32_t xirr;
+
+ cpu_irq_lower(ss->cpu);
+ xirr = ss->xirr;
+ ss->xirr = ss->pending_priority << 24;
+ return xirr;
+}
+
+static void icp_eoi(struct icp_state *icp, int server, uint32_t xirr)
+{
+ struct icp_server_state *ss = icp->ss + server;
+
+ ics_eoi(icp->ics, xirr & XISR_MASK);
+ /* Send EOI -> ICS */
+ ss->xirr = (ss->xirr & ~CPPR_MASK) | (xirr & CPPR_MASK);
+ if (!XISR(ss)) {
+ icp_resend(icp, server);
+ }
+}
+
+static void icp_irq(struct icp_state *icp, int server, int nr, uint8_t priority)
+{
+ struct icp_server_state *ss = icp->ss + server;
+ xics_dprintf("icp_irq(nr %d, server %d, prio 0x%x)\n", nr, server, priority);
+ if ((priority >= CPPR(ss))
+ || (XISR(ss) && (ss->pending_priority <= priority))) {
+ xics_dprintf("reject %d, CPPR 0x%x, XISR 0x%x, pprio 0x%x, prio 0x%x\n",
+ nr, CPPR(ss), XISR(ss), ss->pending_priority, priority);
+ ics_reject(icp->ics, nr);
+ } else {
+ if (XISR(ss)) {
+ xics_dprintf("reject %d, CPPR 0x%x, XISR 0x%x, pprio 0x%x, prio 0x%x\n",
+ nr, CPPR(ss), XISR(ss), ss->pending_priority, priority);
+ ics_reject(icp->ics, XISR(ss));
+ }
+ ss->xirr = (ss->xirr & ~XISR_MASK) | (nr & XISR_MASK);
+ ss->pending_priority = priority;
+ cpu_irq_raise(ss->cpu);
+ }
+}
+
+/*
+ * ICS: Source layer
+ */
+
+struct ics_irq_state {
+ int server;
+ uint8_t priority;
+ uint8_t saved_priority;
+ int rejected:1;
+ int masked_pending:1;
+};
+
+struct ics_state {
+ unsigned int nr_irqs;
+ unsigned int offset;
+ struct ics_irq_state *irqs;
+ struct icp_state *icp;
+};
+
+static int ics_valid_irq(struct ics_state *ics, uint32_t nr)
+{
+ return (nr >= ics->offset)
+ && (nr < (ics->offset + ics->nr_irqs));
+}
+
+static void ics_set_irq_msi(struct ics_state *ics, int srcno, int val)
+{
+ struct ics_irq_state *irq = ics->irqs + srcno;
+
+ if (val) {
+ if (irq->priority == 0xff) {
+ xics_dprintf(" irq pri ff, masked pending\n");
+ irq->masked_pending = 1;
+ } else {
+ icp_irq(ics->icp, irq->server, srcno + ics->offset, irq->priority);
+ }
+ }
+}
+
+static void ics_reject_msi(struct ics_state *ics, int nr)
+{
+ struct ics_irq_state *irq = ics->irqs + nr - ics->offset;
+
+ irq->rejected = 1;
+}
+
+static void ics_resend_msi(struct ics_state *ics)
+{
+ unsigned int i;
+
+ for (i = 0; i < ics->nr_irqs; i++) {
+ struct ics_irq_state *irq = ics->irqs + i;
+
+ /* FIXME: filter by server#? */
+ if (irq->rejected) {
+ irq->rejected = 0;
+ if (irq->priority != 0xff) {
+ icp_irq(ics->icp, irq->server, i + ics->offset, irq->priority);
+ }
+ }
+ }
+}
+
+static void ics_write_xive_msi(struct ics_state *ics, int nr, int server,
+ uint8_t priority)
+{
+ struct ics_irq_state *irq = ics->irqs + nr - ics->offset;
+
+ irq->server = server;
+ irq->priority = priority;
+ xics_dprintf("ics_write_xive_msi(nr %d, server %d, pri 0x%x)\n", nr, server, priority);
+
+ if (!irq->masked_pending || (priority == 0xff)) {
+ return;
+ }
+
+ irq->masked_pending = 0;
+ icp_irq(ics->icp, server, nr, priority);
+}
+
+static void ics_reject(struct ics_state *ics, int nr)
+{
+ ics_reject_msi(ics, nr);
+}
+
+static void ics_resend(struct ics_state *ics)
+{
+ ics_resend_msi(ics);
+}
+
+static void ics_eoi(struct ics_state *ics, int nr)
+{
+}
+
+/*
+ * Exported functions
+ */
+
+static int allocated_irqnum = XICS_IRQ_OFFSET;
+
+/*
+ * xics_alloc_irqnum(): This is hacky. The problem boils down to the PCI device
+ * code which just calls kvm__irq_line( .. pcidev->pci_hdr.irq_line ..) at will.
+ * Each PCI device's IRQ line is allocated by irq__register_device() (which
+ * allocates an IRQ AND allocates a.. PCI device num..).
+ *
+ * In future I'd like to at least mimic some kind of 'upstream IRQ controller'
+ * whereby PCI devices let their PHB know when they want to IRQ, and that
+ * percolates up.
+ *
+ * For now, allocate a REAL xics irq number and (via irq__register_device) push
+ * that into the config space. 8 bits only though!
+ */
+int xics_alloc_irqnum(void)
+{
+ int irq = allocated_irqnum++;
+
+ if (irq > 255)
+ die("Huge numbers of IRQs aren't supported with the daft kvmtool IRQ system.");
+
+ return irq;
+}
+
+static target_ulong h_cppr(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ target_ulong cppr = args[0];
+
+ xics_dprintf("h_cppr(%lx)\n", cppr);
+ icp_set_cppr(vcpu->kvm->icp, vcpu->cpu_id, cppr);
+ return H_SUCCESS;
+}
+
+static target_ulong h_ipi(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ target_ulong server = args[0];
+ target_ulong mfrr = args[1];
+
+ xics_dprintf("h_ipi(%lx, %lx)\n", server, mfrr);
+ if (server >= vcpu->kvm->icp->nr_servers) {
+ return H_PARAMETER;
+ }
+
+ icp_set_mfrr(vcpu->kvm->icp, server, mfrr);
+ return H_SUCCESS;
+}
+
+static target_ulong h_xirr(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ uint32_t xirr = icp_accept(vcpu->kvm->icp->ss + vcpu->cpu_id);
+
+ xics_dprintf("h_xirr() = %x\n", xirr);
+ args[0] = xirr;
+ return H_SUCCESS;
+}
+
+static target_ulong h_eoi(struct kvm_cpu *vcpu,
+ target_ulong opcode, target_ulong *args)
+{
+ target_ulong xirr = args[0];
+
+ xics_dprintf("h_eoi(%lx)\n", xirr);
+ icp_eoi(vcpu->kvm->icp, vcpu->cpu_id, xirr);
+ return H_SUCCESS;
+}
+
+static void rtas_set_xive(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->icp->ics;
+ uint32_t nr, server, priority;
+
+ if ((nargs != 3) || (nret != 1)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+ server = rtas_ld(vcpu->kvm, args, 1);
+ priority = rtas_ld(vcpu->kvm, args, 2);
+
+ xics_dprintf("rtas_set_xive(%x,%x,%x)\n", nr, server, priority);
+ if (!ics_valid_irq(ics, nr) || (server >= ics->icp->nr_servers)
+ || (priority > 0xff)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ ics_write_xive_msi(ics, nr, server, priority);
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+}
+
+static void rtas_get_xive(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->icp->ics;
+ uint32_t nr;
+
+ if ((nargs != 1) || (nret != 3)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+
+ if (!ics_valid_irq(ics, nr)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+ rtas_st(vcpu->kvm, rets, 1, ics->irqs[nr - ics->offset].server);
+ rtas_st(vcpu->kvm, rets, 2, ics->irqs[nr - ics->offset].priority);
+}
+
+static void rtas_int_off(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->icp->ics;
+ uint32_t nr;
+
+ if ((nargs != 1) || (nret != 1)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+
+ if (!ics_valid_irq(ics, nr)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /* ME: QEMU wrote xive_msi here, in #if 0. Deleted. */
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+}
+
+static void rtas_int_on(struct kvm_cpu *vcpu, uint32_t token,
+ uint32_t nargs, target_ulong args,
+ uint32_t nret, target_ulong rets)
+{
+ struct ics_state *ics = vcpu->kvm->icp->ics;
+ uint32_t nr;
+
+ if ((nargs != 1) || (nret != 1)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ nr = rtas_ld(vcpu->kvm, args, 0);
+
+ if (!ics_valid_irq(ics, nr)) {
+ rtas_st(vcpu->kvm, rets, 0, -3);
+ return;
+ }
+
+ /* ME: QEMU wrote xive_msi here, in #if 0. Deleted. */
+
+ rtas_st(vcpu->kvm, rets, 0, 0); /* Success */
+}
+
+void xics_cpu_register(struct kvm_cpu *vcpu)
+{
+ if (vcpu->cpu_id < vcpu->kvm->icp->nr_servers)
+ vcpu->kvm->icp->ss[vcpu->cpu_id].cpu = vcpu;
+ else
+ die("Setting invalid server for cpuid %ld\n", vcpu->cpu_id);
+}
+
+struct icp_state *xics_system_init(unsigned int nr_irqs, unsigned int nr_cpus)
+{
+ int max_server_num;
+ unsigned int i;
+ struct icp_state *icp;
+ struct ics_state *ics;
+
+ max_server_num = nr_cpus;
+
+ icp = malloc(sizeof(*icp));
+ icp->nr_servers = max_server_num + 1;
+ icp->ss = malloc(icp->nr_servers*sizeof(struct icp_server_state));
+
+ for (i = 0; i < icp->nr_servers; i++) {
+ icp->ss[i].xirr = 0;
+ icp->ss[i].pending_priority = 0;
+ icp->ss[i].cpu = 0;
+ icp->ss[i].mfrr = 0xff;
+ }
+
+ /*
+ * icp->ss[env->cpu_index].cpu is set by CPUs calling in to
+ * xics_cpu_register().
+ */
+
+ ics = malloc(sizeof(*ics));
+ ics->nr_irqs = nr_irqs;
+ ics->offset = XICS_IRQ_OFFSET;
+ ics->irqs = malloc(nr_irqs * sizeof(struct ics_irq_state));
+
+ icp->ics = ics;
+ ics->icp = icp;
+
+ for (i = 0; i < nr_irqs; i++) {
+ ics->irqs[i].server = 0;
+ ics->irqs[i].priority = 0xff;
+ ics->irqs[i].saved_priority = 0xff;
+ ics->irqs[i].rejected = 0;
+ ics->irqs[i].masked_pending = 0;
+ }
+
+ spapr_register_hypercall(H_CPPR, h_cppr);
+ spapr_register_hypercall(H_IPI, h_ipi);
+ spapr_register_hypercall(H_XIRR, h_xirr);
+ spapr_register_hypercall(H_EOI, h_eoi);
+
+ spapr_rtas_register("ibm,set-xive", rtas_set_xive);
+ spapr_rtas_register("ibm,get-xive", rtas_get_xive);
+ spapr_rtas_register("ibm,int-off", rtas_int_off);
+ spapr_rtas_register("ibm,int-on", rtas_int_on);
+
+ return icp;
+}
+
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
+{
+ /*
+ * Route event to ICS, which routes to ICP, which eventually does a
+ * kvm_cpu__irq(vcpu, POWER7_EXT_IRQ, 1)
+ */
+ xics_dprintf("Raising IRQ %d -> %d\n", irq, level);
+ ics_set_irq_msi(kvm->icp->ics, irq - kvm->icp->ics->offset, level);
+}
--- /dev/null
+/*
+ * PAPR Virtualized Interrupt System, aka ICS/ICP aka xics
+ *
+ * Copyright 2011 Matt Evans <matt@ozlabs.org>, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef XICS_H
+#define XICS_H
+
+#define XICS_IPI 0x2
+
+struct kvm_cpu;
+struct icp_state;
+
+struct icp_state *xics_system_init(unsigned int nr_irqs, unsigned int nr_cpus);
+void xics_cpu_register(struct kvm_cpu *vcpu);
+int xics_alloc_irqnum(void);
+
+#endif
--- /dev/null
+#include "kvm/symbol.h"
+
+#include "kvm/kvm.h"
+
+#include <linux/err.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <bfd.h>
+
+static bfd *abfd;
+
+int symbol_init(struct kvm *kvm)
+{
+ int ret = 0;
+
+ if (!kvm->vmlinux)
+ return -EINVAL;
+
+ bfd_init();
+
+ abfd = bfd_openr(kvm->vmlinux, NULL);
+ if (abfd == NULL) {
+ bfd_error_type err = bfd_get_error();
+
+ switch (err) {
+ case bfd_error_no_memory:
+ ret = -ENOMEM;
+ break;
+ case bfd_error_invalid_target:
+ ret = -EINVAL;
+ break;
+ default:
+ ret = -EFAULT;
+ break;
+ }
+ }
+
+ return ret;
+}
+
+static asymbol *lookup(asymbol **symbols, int nr_symbols, const char *symbol_name)
+{
+ int i, ret;
+
+ ret = -ENOENT;
+
+ for (i = 0; i < nr_symbols; i++) {
+ asymbol *symbol = symbols[i];
+
+ if (!strcmp(bfd_asymbol_name(symbol), symbol_name))
+ return symbol;
+ }
+
+ return ERR_PTR(ret);
+}
+
+char *symbol_lookup(struct kvm *kvm, unsigned long addr, char *sym, size_t size)
+{
+ const char *filename;
+ bfd_vma sym_offset;
+ bfd_vma sym_start;
+ asection *section;
+ unsigned int line;
+ const char *func;
+ long symtab_size;
+ asymbol *symbol;
+ asymbol **syms;
+ int nr_syms, ret;
+
+ ret = -ENOENT;
+ if (!abfd)
+ goto not_found;
+
+ if (!bfd_check_format(abfd, bfd_object))
+ goto not_found;
+
+ symtab_size = bfd_get_symtab_upper_bound(abfd);
+ if (!symtab_size)
+ goto not_found;
+
+ ret = -ENOMEM;
+ syms = malloc(symtab_size);
+ if (!syms)
+ goto not_found;
+
+ nr_syms = bfd_canonicalize_symtab(abfd, syms);
+
+ ret = -ENOENT;
+ section = bfd_get_section_by_name(abfd, ".debug_aranges");
+ if (!section)
+ goto not_found;
+
+ if (!bfd_find_nearest_line(abfd, section, NULL, addr, &filename, &func, &line))
+ goto not_found;
+
+ if (!func)
+ goto not_found;
+
+ symbol = lookup(syms, nr_syms, func);
+ if (IS_ERR(symbol))
+ goto not_found;
+
+ sym_start = bfd_asymbol_value(symbol);
+
+ sym_offset = addr - sym_start;
+
+ snprintf(sym, size, "%s+%llx (%s:%i)", func, (long long) sym_offset, filename, line);
+
+ sym[size - 1] = '\0';
+
+ free(syms);
+
+ return sym;
+
+not_found:
+ return ERR_PTR(ret);
+}
+
+int symbol_exit(struct kvm *kvm)
+{
+ bfd_boolean ret = TRUE;
+
+ if (abfd)
+ ret = bfd_close(abfd);
+
+ if (ret == TRUE)
+ return 0;
+
+ return -EFAULT;
+}
--- /dev/null
+#include <poll.h>
+#include <stdbool.h>
+#include <termios.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/uio.h>
+#include <signal.h>
+#include <pty.h>
+#include <utmp.h>
+
+#include "kvm/read-write.h"
+#include "kvm/term.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+#define TERM_FD_IN 0
+#define TERM_FD_OUT 1
+
+extern struct kvm *kvm;
+static struct termios orig_term;
+
+int term_escape_char = 0x01; /* ctrl-a is used for escape */
+bool term_got_escape = false;
+
+int active_console;
+
+int term_fds[4][2];
+
+int term_getc(int who, int term)
+{
+ unsigned char c;
+
+ if (who != active_console)
+ return -1;
+ if (read_in_full(term_fds[term][TERM_FD_IN], &c, 1) < 0)
+ return -1;
+
+ if (term_got_escape) {
+ term_got_escape = false;
+ if (c == 'x')
+ kvm_cpu__reboot();
+ if (c == term_escape_char)
+ return c;
+ }
+
+ if (c == term_escape_char) {
+ term_got_escape = true;
+ return -1;
+ }
+
+ return c;
+}
+
+int term_putc(int who, char *addr, int cnt, int term)
+{
+ int ret;
+
+ if (who != active_console)
+ return -1;
+
+ while (cnt--) {
+ ret = write(term_fds[term][TERM_FD_OUT], addr++, 1);
+ if (ret < 0)
+ return 0;
+ }
+
+ return cnt;
+}
+
+int term_getc_iov(int who, struct iovec *iov, int iovcnt, int term)
+{
+ int c;
+
+ if (who != active_console)
+ return 0;
+
+ c = term_getc(who, term);
+
+ if (c < 0)
+ return 0;
+
+ *((char *)iov[TERM_FD_IN].iov_base) = (char)c;
+
+ return sizeof(char);
+}
+
+int term_putc_iov(int who, struct iovec *iov, int iovcnt, int term)
+{
+ if (who != active_console)
+ return 0;
+
+ return writev(term_fds[term][TERM_FD_OUT], iov, iovcnt);
+}
+
+bool term_readable(int who, int term)
+{
+ struct pollfd pollfd = (struct pollfd) {
+ .fd = term_fds[term][TERM_FD_IN],
+ .events = POLLIN,
+ .revents = 0,
+ };
+
+ if (who != active_console)
+ return false;
+
+ return poll(&pollfd, 1, 0) > 0;
+}
+
+static void term_cleanup(void)
+{
+ int i;
+
+ for (i = 0; i < 4; i++)
+ tcsetattr(term_fds[i][TERM_FD_IN], TCSANOW, &orig_term);
+}
+
+static void term_sig_cleanup(int sig)
+{
+ term_cleanup();
+ signal(sig, SIG_DFL);
+ raise(sig);
+}
+
+void term_set_tty(int term)
+{
+ struct termios orig_term;
+ int master, slave;
+ char new_pty[PATH_MAX];
+
+ if (tcgetattr(STDIN_FILENO, &orig_term) < 0)
+ die("unable to save initial standard input settings");
+
+ orig_term.c_lflag &= ~(ICANON | ECHO | ISIG);
+
+ if (openpty(&master, &slave, new_pty, &orig_term, NULL) < 0)
+ return;
+
+ close(slave);
+
+ pr_info("Assigned terminal %d to pty %s\n", term, new_pty);
+
+ term_fds[term][TERM_FD_IN] = term_fds[term][TERM_FD_OUT] = master;
+}
+
+void term_init(void)
+{
+ struct termios term;
+ int i;
+
+ if (tcgetattr(STDIN_FILENO, &orig_term) < 0)
+ die("unable to save initial standard input settings");
+
+ term = orig_term;
+ term.c_lflag &= ~(ICANON | ECHO | ISIG);
+ tcsetattr(STDIN_FILENO, TCSANOW, &term);
+
+ for (i = 0; i < 4; i++)
+ if (term_fds[i][TERM_FD_IN] == 0) {
+ term_fds[i][TERM_FD_IN] = STDIN_FILENO;
+ term_fds[i][TERM_FD_OUT] = STDOUT_FILENO;
+ }
+
+ signal(SIGTERM, term_sig_cleanup);
+ atexit(term_cleanup);
+}
--- /dev/null
+all: kernel pit boot
+
+kernel:
+ $(MAKE) -C kernel
+.PHONY: kernel
+
+pit:
+ $(MAKE) -C pit
+.PHONY: pit
+
+boot:
+ $(MAKE) -C boot
+.PHONY: boot
+
+clean:
+ $(MAKE) -C kernel clean
+ $(MAKE) -C pit clean
+ $(MAKE) -C boot clean
+.PHONY: clean
--- /dev/null
+NAME := init
+
+OBJ := $(NAME).o
+
+all: $(.o)
+ rm -rf rootfs
+ mkdir rootfs
+ gcc -static init.c -o rootfs/init
+ mkisofs rootfs > boot_test.iso
+
+clean:
+ rm -rf rootfs boot_test.iso
+.PHONY: clean
--- /dev/null
+#include <linux/reboot.h>
+#include <unistd.h>
+
+int main(int argc, char *argv[])
+{
+ puts("hello, KVM guest!\r");
+
+ reboot(LINUX_REBOOT_CMD_RESTART);
+
+ return 0;
+}
--- /dev/null
+kernel.bin
+kernel.elf
--- /dev/null
+NAME := kernel
+
+BIN := $(NAME).bin
+ELF := $(NAME).elf
+OBJ := $(NAME).o
+
+all: $(BIN)
+
+$(BIN): $(ELF)
+ objcopy -O binary $< $@
+
+$(ELF): $(OBJ)
+ ld -Ttext=0x00 -nostdlib -static $< -o $@
+
+%.o: %.S
+ gcc -nostdinc -c $< -o $@
+
+clean:
+ rm -f $(BIN) $(ELF) $(OBJ)
+.PHONY: clean
--- /dev/null
+Compiling
+---------
+
+You can simply type:
+
+ $Â make
+
+to build a 16-bit binary that uses the i8086 instruction set.
+
+Disassembling
+-------------
+
+Use the "-m i8086" command line option with objdump to make sure it knows we're
+dealing with i8086 instruction set:
+
+ $ objdump -d -m i8086 i8086.elf
--- /dev/null
+ .code16gcc
+ .text
+ .globl _start
+ .type _start, @function
+_start:
+ # "This is probably the largest possible kernel that is bug free." -- Avi Kivity
+ 1:
+ jmp 1b
--- /dev/null
+*.bin
+*.elf
--- /dev/null
+NAME := tick
+
+BIN := $(NAME).bin
+ELF := $(NAME).elf
+OBJ := $(NAME).o
+
+all: $(BIN)
+
+$(BIN): $(ELF)
+ objcopy -O binary $< $@
+
+$(ELF): $(OBJ)
+ ld -Ttext=0x00 -nostdlib -static $< -o $@
+
+%.o: %.S
+ gcc -nostdinc -c $< -o $@
+
+clean:
+ rm -f $(BIN) $(ELF) $(OBJ)
+.PHONY: clean
--- /dev/null
+Compiling
+---------
+
+You can simply type:
+
+ $Â make
+
+to build a 16-bit binary that uses the i8086 instruction set.
+
+Disassembling
+-------------
+
+Use the "-m i8086" command line option with objdump to make sure it knows we're
+dealing with i8086 instruction set:
+
+ $ objdump -d -m i8086 i8086.elf
--- /dev/null
+#define IO_PIC 0x20
+#define IRQ_OFFSET 32
+#define IO_PIT 0x40
+#define TIMER_FREQ 1193182
+#define TIMER_DIV(x) ((TIMER_FREQ+(x)/2)/(x))
+
+/*
+ * hpa noted:
+ *
+ * 0xe0..0xef are "motherboard specific", but 0xe9 is
+ * used for Bochs debugging and 0xed is the Phoenix-reserved
+ * delay port
+ */
+#define DBG_PORT 0xe0
+
+#define TEST_COUNT 0x0200
+
+ .code16gcc
+ .text
+ .globl _start
+ .type _start, @function
+_start:
+/*
+ * fill up noop handlers
+ */
+ xorw %ax, %ax
+ xorw %di, %di
+ movw %ax, %es
+ movw $256, %cx
+fill_noop_idt:
+ movw $noop_handler, %es:(%di)
+ movw %cs, %es:2(%di)
+ add $4, %di
+ loop fill_noop_idt
+
+set_idt:
+ movw $timer_isr, %es:(IRQ_OFFSET*4)
+ movw %cs, %es:(IRQ_OFFSET*4+2)
+
+set_pic:
+ # ICW1
+ mov $0x11, %al
+ mov $(IO_PIC), %dx
+ out %al,%dx
+ # ICW2
+ mov $(IRQ_OFFSET), %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+ # ICW3
+ mov $0x00, %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+ # ICW4
+ mov $0x3, %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+
+set_pit:
+ # set 8254 mode
+ mov $(IO_PIT+3), %dx
+ mov $0x34, %al
+ outb %al, %dx
+ # set 8254 freq 1KHz
+ mov $(IO_PIT), %dx
+ movb $(TIMER_DIV(1000) % 256), %al
+ outb %al, %dx
+ movb $(TIMER_DIV(1000) / 256), %al
+ outb %al, %dx
+
+enable_irq0:
+ mov $0xfe, %al
+ mov $(IO_PIC+1), %dx
+ out %al, %dx
+ sti
+loop:
+ 1:
+ jmp 1b
+
+test_ok:
+ mov $0x3f8,%dx
+ cs lea msg2, %si
+ mov $(msg2_end-msg2), %cx
+ cs rep/outsb
+
+ /* not a valid port to force exit */
+ outb %al, $DBG_PORT
+
+timer_isr:
+ cli
+ pushaw
+ pushfw
+ mov $0x3f8,%dx
+ mov $0x2e, %al # .
+ out %al,%dx
+ decw count
+ jz test_ok
+ popfw
+ popaw
+ iretw
+
+noop_handler:
+ iretw
+
+count:
+ .word TEST_COUNT
+
+msg2:
+ .asciz "\nTest OK\n"
+msg2_end:
--- /dev/null
+#include "kvm/sdl.h"
+
+#include "kvm/framebuffer.h"
+#include "kvm/i8042.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/kvm-cpu.h"
+
+#include <SDL/SDL.h>
+#include <pthread.h>
+#include <signal.h>
+
+#define FRAME_RATE 25
+
+#define SCANCODE_UNKNOWN 0
+#define SCANCODE_NORMAL 1
+#define SCANCODE_ESCAPED 2
+#define SCANCODE_KEY_PAUSE 3
+#define SCANCODE_KEY_PRNTSCRN 4
+
+struct set2_scancode {
+ u8 code;
+ u8 type;
+};
+
+#define DEFINE_SC(_code) {\
+ .code = _code,\
+ .type = SCANCODE_NORMAL,\
+}
+
+/* escaped scancodes */
+#define DEFINE_ESC(_code) {\
+ .code = _code,\
+ .type = SCANCODE_ESCAPED,\
+}
+
+static const struct set2_scancode const keymap[256] = {
+ [9] = DEFINE_SC(0x76), /* <esc> */
+ [10] = DEFINE_SC(0x16), /* 1 */
+ [11] = DEFINE_SC(0x1e), /* 2 */
+ [12] = DEFINE_SC(0x26), /* 3 */
+ [13] = DEFINE_SC(0x25), /* 4 */
+ [14] = DEFINE_SC(0x2e), /* 5 */
+ [15] = DEFINE_SC(0x36), /* 6 */
+ [16] = DEFINE_SC(0x3d), /* 7 */
+ [17] = DEFINE_SC(0x3e), /* 8 */
+ [18] = DEFINE_SC(0x46), /* 9 */
+ [19] = DEFINE_SC(0x45), /* 9 */
+ [20] = DEFINE_SC(0x4e), /* - */
+ [21] = DEFINE_SC(0x55), /* + */
+ [22] = DEFINE_SC(0x66), /* <backspace> */
+ [23] = DEFINE_SC(0x0d), /* <tab> */
+ [24] = DEFINE_SC(0x15), /* q */
+ [25] = DEFINE_SC(0x1d), /* w */
+ [26] = DEFINE_SC(0x24), /* e */
+ [27] = DEFINE_SC(0x2d), /* r */
+ [28] = DEFINE_SC(0x2c), /* t */
+ [29] = DEFINE_SC(0x35), /* y */
+ [30] = DEFINE_SC(0x3c), /* u */
+ [31] = DEFINE_SC(0x43), /* i */
+ [32] = DEFINE_SC(0x44), /* o */
+ [33] = DEFINE_SC(0x4d), /* p */
+ [34] = DEFINE_SC(0x54), /* [ */
+ [35] = DEFINE_SC(0x5b), /* ] */
+ [36] = DEFINE_SC(0x5a), /* <enter> */
+ [37] = DEFINE_SC(0x14), /* <left ctrl> */
+ [38] = DEFINE_SC(0x1c), /* a */
+ [39] = DEFINE_SC(0x1b), /* s */
+ [40] = DEFINE_SC(0x23), /* d */
+ [41] = DEFINE_SC(0x2b), /* f */
+ [42] = DEFINE_SC(0x34), /* g */
+ [43] = DEFINE_SC(0x33), /* h */
+ [44] = DEFINE_SC(0x3b), /* j */
+ [45] = DEFINE_SC(0x42), /* k */
+ [46] = DEFINE_SC(0x4b), /* l */
+ [47] = DEFINE_SC(0x4c), /* ; */
+ [48] = DEFINE_SC(0x52), /* ' */
+ [49] = DEFINE_SC(0x0e), /* ` */
+ [50] = DEFINE_SC(0x12), /* <left shift> */
+ [51] = DEFINE_SC(0x5d), /* \ */
+ [52] = DEFINE_SC(0x1a), /* z */
+ [53] = DEFINE_SC(0x22), /* x */
+ [54] = DEFINE_SC(0x21), /* c */
+ [55] = DEFINE_SC(0x2a), /* v */
+ [56] = DEFINE_SC(0x32), /* b */
+ [57] = DEFINE_SC(0x31), /* n */
+ [58] = DEFINE_SC(0x3a), /* m */
+ [59] = DEFINE_SC(0x41), /* < */
+ [60] = DEFINE_SC(0x49), /* > */
+ [61] = DEFINE_SC(0x4a), /* / */
+ [62] = DEFINE_SC(0x59), /* <right shift> */
+ [63] = DEFINE_SC(0x7c), /* keypad * */
+ [64] = DEFINE_SC(0x11), /* <left alt> */
+ [65] = DEFINE_SC(0x29), /* <space> */
+
+ [67] = DEFINE_SC(0x05), /* <F1> */
+ [68] = DEFINE_SC(0x06), /* <F2> */
+ [69] = DEFINE_SC(0x04), /* <F3> */
+ [70] = DEFINE_SC(0x0c), /* <F4> */
+ [71] = DEFINE_SC(0x03), /* <F5> */
+ [72] = DEFINE_SC(0x0b), /* <F6> */
+ [73] = DEFINE_SC(0x83), /* <F7> */
+ [74] = DEFINE_SC(0x0a), /* <F8> */
+ [75] = DEFINE_SC(0x01), /* <F9> */
+ [76] = DEFINE_SC(0x09), /* <F10> */
+
+ [79] = DEFINE_SC(0x6c), /* keypad 7 */
+ [80] = DEFINE_SC(0x75), /* keypad 8 */
+ [81] = DEFINE_SC(0x7d), /* keypad 9 */
+ [82] = DEFINE_SC(0x7b), /* keypad - */
+ [83] = DEFINE_SC(0x6b), /* keypad 4 */
+ [84] = DEFINE_SC(0x73), /* keypad 5 */
+ [85] = DEFINE_SC(0x74), /* keypad 6 */
+ [86] = DEFINE_SC(0x79), /* keypad + */
+ [87] = DEFINE_SC(0x69), /* keypad 1 */
+ [88] = DEFINE_SC(0x72), /* keypad 2 */
+ [89] = DEFINE_SC(0x7a), /* keypad 3 */
+ [90] = DEFINE_SC(0x70), /* keypad 0 */
+ [91] = DEFINE_SC(0x71), /* keypad . */
+
+ [94] = DEFINE_SC(0x61), /* <INT 1> */
+ [95] = DEFINE_SC(0x78), /* <F11> */
+ [96] = DEFINE_SC(0x07), /* <F12> */
+
+ [104] = DEFINE_ESC(0x5a), /* keypad <enter> */
+ [105] = DEFINE_ESC(0x14), /* <right ctrl> */
+ [106] = DEFINE_ESC(0x4a), /* keypad / */
+ [108] = DEFINE_ESC(0x11), /* <right alt> */
+ [110] = DEFINE_ESC(0x6c), /* <home> */
+ [111] = DEFINE_ESC(0x75), /* <up> */
+ [112] = DEFINE_ESC(0x7d), /* <pag up> */
+ [113] = DEFINE_ESC(0x6b), /* <left> */
+ [114] = DEFINE_ESC(0x74), /* <right> */
+ [115] = DEFINE_ESC(0x69), /* <end> */
+ [116] = DEFINE_ESC(0x72), /* <down> */
+ [117] = DEFINE_ESC(0x7a), /* <pag down> */
+ [118] = DEFINE_ESC(0x70), /* <ins> */
+ [119] = DEFINE_ESC(0x71), /* <delete> */
+};
+static bool running, done;
+
+static const struct set2_scancode *to_code(u8 scancode)
+{
+ return &keymap[scancode];
+}
+
+static void key_press(const struct set2_scancode *sc)
+{
+ switch (sc->type) {
+ case SCANCODE_ESCAPED:
+ kbd_queue(0xe0);
+ /* fallthrough */
+ case SCANCODE_NORMAL:
+ kbd_queue(sc->code);
+ break;
+ case SCANCODE_KEY_PAUSE:
+ kbd_queue(0xe1);
+ kbd_queue(0x14);
+ kbd_queue(0x77);
+ kbd_queue(0xe1);
+ kbd_queue(0xf0);
+ kbd_queue(0x14);
+ kbd_queue(0x77);
+ break;
+ case SCANCODE_KEY_PRNTSCRN:
+ kbd_queue(0xe0);
+ kbd_queue(0x12);
+ kbd_queue(0xe0);
+ kbd_queue(0x7c);
+ break;
+ }
+}
+
+static void key_release(const struct set2_scancode *sc)
+{
+ switch (sc->type) {
+ case SCANCODE_ESCAPED:
+ kbd_queue(0xe0);
+ /* fallthrough */
+ case SCANCODE_NORMAL:
+ kbd_queue(0xf0);
+ kbd_queue(sc->code);
+ break;
+ case SCANCODE_KEY_PAUSE:
+ /* nothing to do */
+ break;
+ case SCANCODE_KEY_PRNTSCRN:
+ kbd_queue(0xe0);
+ kbd_queue(0xf0);
+ kbd_queue(0x7c);
+ kbd_queue(0xe0);
+ kbd_queue(0xf0);
+ kbd_queue(0x12);
+ break;
+ }
+}
+
+static void *sdl__thread(void *p)
+{
+ Uint32 rmask, gmask, bmask, amask;
+ struct framebuffer *fb = p;
+ SDL_Surface *guest_screen;
+ SDL_Surface *screen;
+ SDL_Event ev;
+ Uint32 flags;
+
+ if (SDL_Init(SDL_INIT_VIDEO) != 0)
+ die("Unable to initialize SDL");
+
+ rmask = 0x000000ff;
+ gmask = 0x0000ff00;
+ bmask = 0x00ff0000;
+ amask = 0x00000000;
+
+ guest_screen = SDL_CreateRGBSurfaceFrom(fb->mem, fb->width, fb->height, fb->depth, fb->width * fb->depth / 8, rmask, gmask, bmask, amask);
+ if (!guest_screen)
+ die("Unable to create SDL RBG surface");
+
+ flags = SDL_HWSURFACE | SDL_ASYNCBLIT | SDL_HWACCEL | SDL_DOUBLEBUF;
+
+ SDL_WM_SetCaption("KVM tool", "KVM tool");
+
+ screen = SDL_SetVideoMode(fb->width, fb->height, fb->depth, flags);
+ if (!screen)
+ die("Unable to set SDL video mode");
+
+ SDL_EnableKeyRepeat(200, 50);
+
+ while (running) {
+ SDL_BlitSurface(guest_screen, NULL, screen, NULL);
+ SDL_Flip(screen);
+
+ while (SDL_PollEvent(&ev)) {
+ switch (ev.type) {
+ case SDL_KEYDOWN: {
+ const struct set2_scancode *sc = to_code(ev.key.keysym.scancode);
+ if (sc->type == SCANCODE_UNKNOWN) {
+ pr_warning("key '%d' not found in keymap", ev.key.keysym.scancode);
+ break;
+ }
+ key_press(sc);
+ break;
+ }
+ case SDL_KEYUP: {
+ const struct set2_scancode *sc = to_code(ev.key.keysym.scancode);
+ if (sc->type == SCANCODE_UNKNOWN)
+ break;
+ key_release(sc);
+ break;
+ }
+ case SDL_QUIT:
+ goto exit;
+ }
+ }
+
+ SDL_Delay(1000 / FRAME_RATE);
+ }
+
+ if (running == false && done == false) {
+ done = true;
+ return NULL;
+ }
+exit:
+ kvm_cpu__reboot();
+
+ return NULL;
+}
+
+static int sdl__start(struct framebuffer *fb)
+{
+ pthread_t thread;
+
+ running = true;
+
+ if (pthread_create(&thread, NULL, sdl__thread, fb) != 0)
+ return -1;
+
+ return 0;
+}
+
+static int sdl__stop(struct framebuffer *fb)
+{
+ running = false;
+ while (done == false)
+ sleep(0);
+
+ return 0;
+}
+
+static struct fb_target_operations sdl_ops = {
+ .start = sdl__start,
+ .stop = sdl__stop,
+};
+
+int sdl__init(struct framebuffer *fb)
+{
+ return fb__attach(fb, &sdl_ops);
+}
+
+int sdl__exit(struct framebuffer *fb)
+{
+ return sdl__stop(fb);
+}
--- /dev/null
+#include "kvm/vnc.h"
+
+#include "kvm/framebuffer.h"
+#include "kvm/i8042.h"
+
+#include <linux/types.h>
+#include <rfb/keysym.h>
+#include <rfb/rfb.h>
+#include <pthread.h>
+
+#define VESA_QUEUE_SIZE 128
+#define VESA_IRQ 14
+
+/*
+ * This "6000" value is pretty much the result of experimentation
+ * It seems that around this value, things update pretty smoothly
+ */
+#define VESA_UPDATE_TIME 6000
+
+/*
+ * We can map the letters and numbers without a fuss,
+ * but the other characters not so much.
+ */
+static char letters[26] = {
+ 0x1c, 0x32, 0x21, 0x23, 0x24, /* a-e */
+ 0x2b, 0x34, 0x33, 0x43, 0x3b, /* f-j */
+ 0x42, 0x4b, 0x3a, 0x31, 0x44, /* k-o */
+ 0x4d, 0x15, 0x2d, 0x1b, 0x2c, /* p-t */
+ 0x3c, 0x2a, 0x1d, 0x22, 0x35, /* u-y */
+ 0x1a,
+};
+
+static rfbScreenInfoPtr server;
+static char num[10] = {
+ 0x45, 0x16, 0x1e, 0x26, 0x2e, 0x23, 0x36, 0x3d, 0x3e, 0x46,
+};
+
+/*
+ * This is called when the VNC server receives a key event
+ * The reason this function is such a beast is that we have
+ * to convert from ASCII characters (which is what VNC gets)
+ * to PC keyboard scancodes, which is what Linux expects to
+ * get from its keyboard. ASCII and the scancode set don't
+ * really seem to mesh in any good way beyond some basics with
+ * the letters and numbers.
+ */
+static void kbd_handle_key(rfbBool down, rfbKeySym key, rfbClientPtr cl)
+{
+ char tosend = 0;
+
+ if (key >= 0x41 && key <= 0x5a)
+ key += 0x20; /* convert to lowercase */
+
+ if (key >= 0x61 && key <= 0x7a) /* a-z */
+ tosend = letters[key - 0x61];
+
+ if (key >= 0x30 && key <= 0x39)
+ tosend = num[key - 0x30];
+
+ switch (key) {
+ case XK_Insert: kbd_queue(0xe0); tosend = 0x70; break;
+ case XK_Delete: kbd_queue(0xe0); tosend = 0x71; break;
+ case XK_Up: kbd_queue(0xe0); tosend = 0x75; break;
+ case XK_Down: kbd_queue(0xe0); tosend = 0x72; break;
+ case XK_Left: kbd_queue(0xe0); tosend = 0x6b; break;
+ case XK_Right: kbd_queue(0xe0); tosend = 0x74; break;
+ case XK_Page_Up: kbd_queue(0xe0); tosend = 0x7d; break;
+ case XK_Page_Down: kbd_queue(0xe0); tosend = 0x7a; break;
+ case XK_Home: kbd_queue(0xe0); tosend = 0x6c; break;
+ case XK_BackSpace: tosend = 0x66; break;
+ case XK_Tab: tosend = 0x0d; break;
+ case XK_Return: tosend = 0x5a; break;
+ case XK_Escape: tosend = 0x76; break;
+ case XK_End: tosend = 0x69; break;
+ case XK_Shift_L: tosend = 0x12; break;
+ case XK_Shift_R: tosend = 0x59; break;
+ case XK_Control_R: kbd_queue(0xe0);
+ case XK_Control_L: tosend = 0x14; break;
+ case XK_Alt_R: kbd_queue(0xe0);
+ case XK_Alt_L: tosend = 0x11; break;
+ case XK_quoteleft: tosend = 0x0e; break;
+ case XK_minus: tosend = 0x4e; break;
+ case XK_equal: tosend = 0x55; break;
+ case XK_bracketleft: tosend = 0x54; break;
+ case XK_bracketright: tosend = 0x5b; break;
+ case XK_backslash: tosend = 0x5d; break;
+ case XK_Caps_Lock: tosend = 0x58; break;
+ case XK_semicolon: tosend = 0x4c; break;
+ case XK_quoteright: tosend = 0x52; break;
+ case XK_comma: tosend = 0x41; break;
+ case XK_period: tosend = 0x49; break;
+ case XK_slash: tosend = 0x4a; break;
+ case XK_space: tosend = 0x29; break;
+
+ /*
+ * This is where I handle the shifted characters.
+ * They don't really map nicely the way A-Z maps to a-z,
+ * so I'm doing it manually
+ */
+ case XK_exclam: tosend = 0x16; break;
+ case XK_quotedbl: tosend = 0x52; break;
+ case XK_numbersign: tosend = 0x26; break;
+ case XK_dollar: tosend = 0x25; break;
+ case XK_percent: tosend = 0x2e; break;
+ case XK_ampersand: tosend = 0x3d; break;
+ case XK_parenleft: tosend = 0x46; break;
+ case XK_parenright: tosend = 0x45; break;
+ case XK_asterisk: tosend = 0x3e; break;
+ case XK_plus: tosend = 0x55; break;
+ case XK_colon: tosend = 0x4c; break;
+ case XK_less: tosend = 0x41; break;
+ case XK_greater: tosend = 0x49; break;
+ case XK_question: tosend = 0x4a; break;
+ case XK_at: tosend = 0x1e; break;
+ case XK_asciicircum: tosend = 0x36; break;
+ case XK_underscore: tosend = 0x4e; break;
+ case XK_braceleft: tosend = 0x54; break;
+ case XK_braceright: tosend = 0x5b; break;
+ case XK_bar: tosend = 0x5d; break;
+ case XK_asciitilde: tosend = 0x0e; break;
+ default: break;
+ }
+
+ /*
+ * If this is a "key up" event (the user has released the key, we
+ * need to send 0xf0 first.
+ */
+ if (!down && tosend != 0x0)
+ kbd_queue(0xf0);
+
+ if (tosend)
+ kbd_queue(tosend);
+}
+
+/* The previous X and Y coordinates of the mouse */
+static int xlast, ylast = -1;
+
+/*
+ * This function is called by the VNC server whenever a mouse event occurs.
+ */
+static void kbd_handle_ptr(int buttonMask, int x, int y, rfbClientPtr cl)
+{
+ int dx, dy;
+ char b1 = 0x8;
+
+ /* The VNC mask and the PS/2 button encoding are the same */
+ b1 |= buttonMask;
+
+ if (xlast >= 0 && ylast >= 0) {
+ /* The PS/2 mouse sends deltas, not absolutes */
+ dx = x - xlast;
+ dy = ylast - y;
+
+ /* Set overflow bits if needed */
+ if (dy > 255)
+ b1 |= 0x80;
+ if (dx > 255)
+ b1 |= 0x40;
+
+ /* Set negative bits if needed */
+ if (dy < 0)
+ b1 |= 0x20;
+ if (dx < 0)
+ b1 |= 0x10;
+
+ mouse_queue(b1);
+ mouse_queue(dx);
+ mouse_queue(dy);
+ }
+
+ xlast = x;
+ ylast = y;
+ rfbDefaultPtrAddEvent(buttonMask, x, y, cl);
+}
+
+static void *vnc__thread(void *p)
+{
+ struct framebuffer *fb = p;
+ /*
+ * Make a fake argc and argv because the getscreen function
+ * seems to want it.
+ */
+ char argv[1][1] = {{0}};
+ int argc = 1;
+
+ server = rfbGetScreen(&argc, (char **) argv, fb->width, fb->height, 8, 3, 4);
+ server->frameBuffer = fb->mem;
+ server->alwaysShared = TRUE;
+ server->kbdAddEvent = kbd_handle_key;
+ server->ptrAddEvent = kbd_handle_ptr;
+ rfbInitServer(server);
+
+ while (rfbIsActive(server)) {
+ rfbMarkRectAsModified(server, 0, 0, fb->width, fb->height);
+ rfbProcessEvents(server, server->deferUpdateTime * VESA_UPDATE_TIME);
+ }
+ return NULL;
+}
+
+static int vnc__start(struct framebuffer *fb)
+{
+ pthread_t thread;
+
+ if (pthread_create(&thread, NULL, vnc__thread, fb) != 0)
+ return -1;
+
+ return 0;
+}
+
+static int vnc__stop(struct framebuffer *fb)
+{
+ rfbShutdownServer(server, TRUE);
+
+ return 0;
+}
+
+static struct fb_target_operations vnc_ops = {
+ .start = vnc__start,
+ .stop = vnc__stop,
+};
+
+int vnc__init(struct framebuffer *fb)
+{
+ return fb__attach(fb, &vnc_ops);
+}
+
+int vnc__exit(struct framebuffer *fb)
+{
+ return vnc__stop(fb);
+}
\ No newline at end of file
--- /dev/null
+#!/bin/sh
+
+if [ $# -eq 1 ] ; then
+ OUTPUT=$1
+fi
+
+GVF=${OUTPUT}KVMTOOLS-VERSION-FILE
+
+LF='
+'
+
+# First check if there is a .git to get the version from git describe
+# otherwise try to get the version from the kernel makefile
+if test -d ../../.git -o -f ../../.git &&
+ VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
+ case "$VN" in
+ *$LF*) (exit 1) ;;
+ v[0-9]*)
+ git update-index -q --refresh
+ test -z "$(git diff-index --name-only HEAD --)" ||
+ VN="$VN-dirty" ;;
+ esac
+then
+ VN=$(echo "$VN" | sed -e 's/-/./g');
+else
+ VN=$(MAKEFLAGS= make -sC ../.. kernelversion)
+fi
+
+VN=$(expr "$VN" : v*'\(.*\)')
+
+if test -r $GVF
+then
+ VC=$(sed -e 's/^KVMTOOLS_VERSION = //' <$GVF)
+else
+ VC=unset
+fi
+test "$VN" = "$VC" || {
+ echo >&2 "KVMTOOLS_VERSION = $VN"
+ echo "KVMTOOLS_VERSION = $VN" >$GVF
+}
--- /dev/null
+#!/bin/sh
+
+echo "/* Automatically generated by $0 */
+struct cmdname_help
+{
+ char name[16];
+ char help[80];
+};
+
+static struct cmdname_help common_cmds[] = {"
+
+sed -n 's/^lkvm-\([^ \t]*\).*common/\1/p' command-list.txt |
+while read cmd
+do
+ # TODO following sed command should be fixed
+ sed -n '/^NAME/,/^lkvm-'"$cmd"'/ {
+ /NAME/d
+ /--/d
+ s/.*kvm-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/
+ p
+ }' "Documentation/kvm-$cmd.txt"
+done
+echo "};"
--- /dev/null
+#!/bin/sh
+switch=vbr0
+/sbin/ifconfig $1 0.0.0.0 up
+/usr/sbin/brctl addif ${switch} $1
+/usr/sbin/brctl setfd ${switch} 0
+/usr/sbin/brctl stp ${switch} off
--- /dev/null
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <stdbool.h>
+
+/* user defined includes */
+#include <linux/types.h>
+#include <kvm/util.h>
+#include <kvm/parse-options.h>
+#include <kvm/strbuf.h>
+
+#define OPT_SHORT 1
+#define OPT_UNSET 2
+
+static int opterror(const struct option *opt, const char *reason, int flags)
+{
+ if (flags & OPT_SHORT)
+ return pr_err("switch `%c' %s", opt->short_name, reason);
+ if (flags & OPT_UNSET)
+ return pr_err("option `no-%s' %s", opt->long_name, reason);
+ return pr_err("option `%s' %s", opt->long_name, reason);
+}
+
+static int get_arg(struct parse_opt_ctx_t *p, const struct option *opt,
+ int flags, const char **arg)
+{
+ if (p->opt) {
+ *arg = p->opt;
+ p->opt = NULL;
+ } else if ((opt->flags & PARSE_OPT_LASTARG_DEFAULT) && (p->argc == 1 ||
+ **(p->argv + 1) == '-')) {
+ *arg = (const char *)opt->defval;
+ } else if (p->argc > 1) {
+ p->argc--;
+ *arg = *++p->argv;
+ } else
+ return opterror(opt, "requires a value", flags);
+ return 0;
+}
+
+static int readnum(const struct option *opt, int flags,
+ const char *str, char **end)
+{
+ switch (opt->type) {
+ case OPTION_INTEGER:
+ *(int *)opt->value = strtol(str, end, 0);
+ break;
+ case OPTION_UINTEGER:
+ *(unsigned int *)opt->value = strtol(str, end, 0);
+ break;
+ case OPTION_LONG:
+ *(long *)opt->value = strtol(str, end, 0);
+ break;
+ case OPTION_U64:
+ *(u64 *)opt->value = strtoull(str, end, 0);
+ break;
+ default:
+ return opterror(opt, "invalid numeric conversion", flags);
+ }
+
+ return 0;
+}
+
+static int get_value(struct parse_opt_ctx_t *p,
+ const struct option *opt, int flags)
+{
+ const char *s, *arg = NULL;
+ const int unset = flags & OPT_UNSET;
+
+ if (unset && p->opt)
+ return opterror(opt, "takes no value", flags);
+ if (unset && (opt->flags & PARSE_OPT_NONEG))
+ return opterror(opt, "isn't available", flags);
+
+ if (!(flags & OPT_SHORT) && p->opt) {
+ switch (opt->type) {
+ case OPTION_CALLBACK:
+ if (!(opt->flags & PARSE_OPT_NOARG))
+ break;
+ /* FALLTHROUGH */
+ case OPTION_BOOLEAN:
+ case OPTION_INCR:
+ case OPTION_BIT:
+ case OPTION_SET_UINT:
+ case OPTION_SET_PTR:
+ return opterror(opt, "takes no value", flags);
+ case OPTION_END:
+ case OPTION_ARGUMENT:
+ case OPTION_GROUP:
+ case OPTION_STRING:
+ case OPTION_INTEGER:
+ case OPTION_UINTEGER:
+ case OPTION_LONG:
+ case OPTION_U64:
+ default:
+ break;
+ }
+ }
+
+ switch (opt->type) {
+ case OPTION_BIT:
+ if (unset)
+ *(int *)opt->value &= ~opt->defval;
+ else
+ *(int *)opt->value |= opt->defval;
+ return 0;
+
+ case OPTION_BOOLEAN:
+ *(bool *)opt->value = unset ? false : true;
+ return 0;
+
+ case OPTION_INCR:
+ *(int *)opt->value = unset ? 0 : *(int *)opt->value + 1;
+ return 0;
+
+ case OPTION_SET_UINT:
+ *(unsigned int *)opt->value = unset ? 0 : opt->defval;
+ return 0;
+
+ case OPTION_SET_PTR:
+ *(void **)opt->value = unset ? NULL : (void *)opt->defval;
+ return 0;
+
+ case OPTION_STRING:
+ if (unset)
+ *(const char **)opt->value = NULL;
+ else if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+ *(const char **)opt->value = (const char *)opt->defval;
+ else
+ return get_arg(p, opt, flags,
+ (const char **)opt->value);
+ return 0;
+
+ case OPTION_CALLBACK:
+ if (unset)
+ return (*opt->callback)(opt, NULL, 1) ? (-1) : 0;
+ if (opt->flags & PARSE_OPT_NOARG)
+ return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt)
+ return (*opt->callback)(opt, NULL, 0) ? (-1) : 0;
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return (*opt->callback)(opt, arg, 0) ? (-1) : 0;
+
+ case OPTION_INTEGER:
+ if (unset) {
+ *(int *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(int *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_UINTEGER:
+ if (unset) {
+ *(unsigned int *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(unsigned int *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_LONG:
+ if (unset) {
+ *(long *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(long *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_U64:
+ if (unset) {
+ *(u64 *)opt->value = 0;
+ return 0;
+ }
+ if (opt->flags & PARSE_OPT_OPTARG && !p->opt) {
+ *(u64 *)opt->value = opt->defval;
+ return 0;
+ }
+ if (get_arg(p, opt, flags, &arg))
+ return -1;
+ return readnum(opt, flags, arg, (char **)&s);
+
+ case OPTION_END:
+ case OPTION_ARGUMENT:
+ case OPTION_GROUP:
+ default:
+ die("should not happen, someone must be hit on the forehead");
+ }
+}
+
+#define USAGE_OPTS_WIDTH 24
+#define USAGE_GAP 2
+
+static int usage_with_options_internal(const char * const *usagestr,
+ const struct option *opts, int full)
+{
+ if (!usagestr)
+ return PARSE_OPT_HELP;
+
+ fprintf(stderr, "\n usage: %s\n", *usagestr++);
+ while (*usagestr && **usagestr)
+ fprintf(stderr, " or: %s\n", *usagestr++);
+ while (*usagestr) {
+ fprintf(stderr, "%s%s\n",
+ **usagestr ? " " : "",
+ *usagestr);
+ usagestr++;
+ }
+
+ if (opts->type != OPTION_GROUP)
+ fputc('\n', stderr);
+
+ for (; opts->type != OPTION_END; opts++) {
+ size_t pos;
+ int pad;
+
+ if (opts->type == OPTION_GROUP) {
+ fputc('\n', stderr);
+ if (*opts->help)
+ fprintf(stderr, "%s\n", opts->help);
+ continue;
+ }
+ if (!full && (opts->flags & PARSE_OPT_HIDDEN))
+ continue;
+
+ pos = fprintf(stderr, " ");
+ if (opts->short_name)
+ pos += fprintf(stderr, "-%c", opts->short_name);
+ else
+ pos += fprintf(stderr, " ");
+
+ if (opts->long_name && opts->short_name)
+ pos += fprintf(stderr, ", ");
+ if (opts->long_name)
+ pos += fprintf(stderr, "--%s", opts->long_name);
+
+ switch (opts->type) {
+ case OPTION_ARGUMENT:
+ break;
+ case OPTION_LONG:
+ case OPTION_U64:
+ case OPTION_INTEGER:
+ case OPTION_UINTEGER:
+ if (opts->flags & PARSE_OPT_OPTARG)
+ if (opts->long_name)
+ pos += fprintf(stderr, "[=<n>]");
+ else
+ pos += fprintf(stderr, "[<n>]");
+ else
+ pos += fprintf(stderr, " <n>");
+ break;
+ case OPTION_CALLBACK:
+ if (opts->flags & PARSE_OPT_NOARG)
+ break;
+ /* FALLTHROUGH */
+ case OPTION_STRING:
+ if (opts->argh) {
+ if (opts->flags & PARSE_OPT_OPTARG)
+ if (opts->long_name)
+ pos += fprintf(stderr, "[=<%s>]", opts->argh);
+ else
+ pos += fprintf(stderr, "[<%s>]", opts->argh);
+ else
+ pos += fprintf(stderr, " <%s>", opts->argh);
+ } else {
+ if (opts->flags & PARSE_OPT_OPTARG)
+ if (opts->long_name)
+ pos += fprintf(stderr, "[=...]");
+ else
+ pos += fprintf(stderr, "[...]");
+ else
+ pos += fprintf(stderr, " ...");
+ }
+ break;
+ default: /* OPTION_{BIT,BOOLEAN,SET_UINT,SET_PTR} */
+ case OPTION_END:
+ case OPTION_GROUP:
+ case OPTION_BIT:
+ case OPTION_BOOLEAN:
+ case OPTION_INCR:
+ case OPTION_SET_UINT:
+ case OPTION_SET_PTR:
+ break;
+ }
+ if (pos <= USAGE_OPTS_WIDTH)
+ pad = USAGE_OPTS_WIDTH - pos;
+ else {
+ fputc('\n', stderr);
+ pad = USAGE_OPTS_WIDTH;
+ }
+ fprintf(stderr, "%*s%s\n", pad + USAGE_GAP, "", opts->help);
+ }
+ fputc('\n', stderr);
+
+ return PARSE_OPT_HELP;
+}
+
+void usage_with_options(const char * const *usagestr,
+ const struct option *opts)
+{
+ usage_with_options_internal(usagestr, opts, 0);
+ exit(129);
+}
+
+static void check_typos(const char *arg, const struct option *options)
+{
+ if (strlen(arg) < 3)
+ return;
+
+ if (!prefixcmp(arg, "no-")) {
+ pr_err("did you mean `--%s` (with two dashes ?)", arg);
+ exit(129);
+ }
+
+ for (; options->type != OPTION_END; options++) {
+ if (!options->long_name)
+ continue;
+ if (!prefixcmp(options->long_name, arg)) {
+ pr_err("did you mean `--%s` (with two dashes ?)", arg);
+ exit(129);
+ }
+ }
+}
+
+static int parse_options_usage(const char * const *usagestr,
+ const struct option *opts)
+{
+ return usage_with_options_internal(usagestr, opts, 0);
+}
+
+static int parse_short_opt(struct parse_opt_ctx_t *p,
+ const struct option *options)
+{
+ for (; options->type != OPTION_END; options++) {
+ if (options->short_name == *p->opt) {
+ p->opt = p->opt[1] ? p->opt + 1 : NULL;
+ return get_value(p, options, OPT_SHORT);
+ }
+ }
+ return -2;
+}
+
+static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg,
+ const struct option *options)
+{
+ const char *arg_end = strchr(arg, '=');
+ const struct option *abbrev_option = NULL, *ambiguous_option = NULL;
+ int abbrev_flags = 0, ambiguous_flags = 0;
+
+ if (!arg_end)
+ arg_end = arg + strlen(arg);
+
+ for (; options->type != OPTION_END; options++) {
+ const char *rest;
+ int flags = 0;
+
+ if (!options->long_name)
+ continue;
+
+ rest = skip_prefix(arg, options->long_name);
+ if (options->type == OPTION_ARGUMENT) {
+ if (!rest)
+ continue;
+ if (*rest == '=')
+ return opterror(options, "takes no value",
+ flags);
+ if (*rest)
+ continue;
+ p->out[p->cpidx++] = arg - 2;
+ return 0;
+ }
+ if (!rest) {
+ /* abbreviated? */
+ if (!strncmp(options->long_name, arg, arg_end - arg)) {
+is_abbreviated:
+ if (abbrev_option) {
+ /*
+ * If this is abbreviated, it is
+ * ambiguous. So when there is no
+ * exact match later, we need to
+ * error out.
+ */
+ ambiguous_option = abbrev_option;
+ ambiguous_flags = abbrev_flags;
+ }
+ if (!(flags & OPT_UNSET) && *arg_end)
+ p->opt = arg_end + 1;
+ abbrev_option = options;
+ abbrev_flags = flags;
+ continue;
+ }
+ /* negated and abbreviated very much? */
+ if (!prefixcmp("no-", arg)) {
+ flags |= OPT_UNSET;
+ goto is_abbreviated;
+ }
+ /* negated? */
+ if (strncmp(arg, "no-", 3))
+ continue;
+ flags |= OPT_UNSET;
+ rest = skip_prefix(arg + 3, options->long_name);
+ /* abbreviated and negated? */
+ if (!rest && !prefixcmp(options->long_name, arg + 3))
+ goto is_abbreviated;
+ if (!rest)
+ continue;
+ }
+ if (*rest) {
+ if (*rest != '=')
+ continue;
+ p->opt = rest + 1;
+ }
+ return get_value(p, options, flags);
+ }
+
+ if (ambiguous_option)
+ return pr_err("Ambiguous option: %s "
+ "(could be --%s%s or --%s%s)",
+ arg,
+ (ambiguous_flags & OPT_UNSET) ? "no-" : "",
+ ambiguous_option->long_name,
+ (abbrev_flags & OPT_UNSET) ? "no-" : "",
+ abbrev_option->long_name);
+ if (abbrev_option)
+ return get_value(p, abbrev_option, abbrev_flags);
+ return -2;
+}
+
+
+static void parse_options_start(struct parse_opt_ctx_t *ctx, int argc,
+ const char **argv, int flags)
+{
+ memset(ctx, 0, sizeof(*ctx));
+ ctx->argc = argc;
+ ctx->argv = argv;
+ ctx->out = argv;
+ ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0);
+ ctx->flags = flags;
+ if ((flags & PARSE_OPT_KEEP_UNKNOWN) &&
+ (flags & PARSE_OPT_STOP_AT_NON_OPTION))
+ die("STOP_AT_NON_OPTION and KEEP_UNKNOWN don't go together");
+}
+
+static int parse_options_end(struct parse_opt_ctx_t *ctx)
+{
+ memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out));
+ ctx->out[ctx->cpidx + ctx->argc] = NULL;
+ return ctx->cpidx + ctx->argc;
+}
+
+
+static int parse_options_step(struct parse_opt_ctx_t *ctx,
+ const struct option *options, const char * const usagestr[])
+{
+ int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+
+ /* we must reset ->opt, unknown short option leave it dangling */
+ ctx->opt = NULL;
+
+ for (; ctx->argc; ctx->argc--, ctx->argv++) {
+ const char *arg = ctx->argv[0];
+
+ if (*arg != '-' || !arg[1]) {
+ if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
+ break;
+ ctx->out[ctx->cpidx++] = ctx->argv[0];
+ continue;
+ }
+
+ if (arg[1] != '-') {
+ ctx->opt = arg + 1;
+ if (internal_help && *ctx->opt == 'h')
+ return parse_options_usage(usagestr, options);
+ switch (parse_short_opt(ctx, options)) {
+ case -1:
+ return parse_options_usage(usagestr, options);
+ case -2:
+ goto unknown;
+ default:
+ break;
+ }
+ if (ctx->opt)
+ check_typos(arg + 1, options);
+ while (ctx->opt) {
+ if (internal_help && *ctx->opt == 'h')
+ return parse_options_usage(usagestr,
+ options);
+ switch (parse_short_opt(ctx, options)) {
+ case -1:
+ return parse_options_usage(usagestr,
+ options);
+ case -2:
+ /* fake a short option thing to hide
+ * the fact that we may have
+ * started to parse aggregated stuff
+ *
+ * This is leaky, too bad.
+ */
+ ctx->argv[0] = strdup(ctx->opt - 1);
+ *(char *)ctx->argv[0] = '-';
+ goto unknown;
+ default:
+ break;
+ }
+ }
+ continue;
+ }
+
+ if (!arg[2]) { /* "--" */
+ if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) {
+ ctx->argc--;
+ ctx->argv++;
+ }
+ break;
+ }
+
+ if (internal_help && !strcmp(arg + 2, "help-all"))
+ return usage_with_options_internal(usagestr, options,
+ 1);
+ if (internal_help && !strcmp(arg + 2, "help"))
+ return parse_options_usage(usagestr, options);
+ switch (parse_long_opt(ctx, arg + 2, options)) {
+ case -1:
+ return parse_options_usage(usagestr, options);
+ case -2:
+ goto unknown;
+ default:
+ break;
+ }
+ continue;
+unknown:
+ if (!(ctx->flags & PARSE_OPT_KEEP_UNKNOWN))
+ return PARSE_OPT_UNKNOWN;
+ ctx->out[ctx->cpidx++] = ctx->argv[0];
+ ctx->opt = NULL;
+ }
+ return PARSE_OPT_DONE;
+}
+
+int parse_options(int argc, const char **argv, const struct option *options,
+ const char * const usagestr[], int flags)
+{
+ struct parse_opt_ctx_t ctx;
+
+ parse_options_start(&ctx, argc, argv, flags);
+ switch (parse_options_step(&ctx, options, usagestr)) {
+ case PARSE_OPT_HELP:
+ exit(129);
+ case PARSE_OPT_DONE:
+ break;
+ default: /* PARSE_OPT_UNKNOWN */
+ if (ctx.argv[0][1] == '-') {
+ pr_err("unknown option `%s'", ctx.argv[0] + 2);
+ } else {
+ pr_err("unknown switch `%c'", *ctx.opt);
+ }
+ usage_with_options(usagestr, options);
+ }
+
+ return parse_options_end(&ctx);
+}
--- /dev/null
+#include <kvm/rbtree-interval.h>
+#include <stddef.h>
+#include <errno.h>
+
+struct rb_int_node *rb_int_search_single(struct rb_root *root, u64 point)
+{
+ struct rb_node *node = root->rb_node;
+ struct rb_node *lowest = NULL;
+
+ while (node) {
+ struct rb_int_node *cur = rb_int(node);
+
+ if (node->rb_left && (rb_int(node->rb_left)->max_high > point)) {
+ node = node->rb_left;
+ } else if (cur->low <= point && cur->high > point) {
+ lowest = node;
+ break;
+ } else if (point > cur->low) {
+ node = node->rb_right;
+ } else {
+ break;
+ }
+ }
+
+ if (lowest == NULL)
+ return NULL;
+
+ return rb_int(lowest);
+}
+
+struct rb_int_node *rb_int_search_range(struct rb_root *root, u64 low, u64 high)
+{
+ struct rb_int_node *range;
+
+ range = rb_int_search_single(root, low);
+ if (range == NULL)
+ return NULL;
+
+ /* We simply verify that 'high' is smaller than the end of the range where 'low' is located */
+ if (range->high < high)
+ return NULL;
+
+ return range;
+}
+
+static void update_node_max_high(struct rb_node *node, void *arg)
+{
+ struct rb_int_node *i_node = rb_int(node);
+
+ i_node->max_high = i_node->high;
+
+ if (node->rb_left)
+ i_node->max_high = max(i_node->max_high, rb_int(node->rb_left)->max_high);
+ if (node->rb_right)
+ i_node->max_high = max(i_node->max_high, rb_int(node->rb_right)->max_high);
+}
+
+int rb_int_insert(struct rb_root *root, struct rb_int_node *i_node)
+{
+ struct rb_node **node = &(root->rb_node), *parent = NULL;
+
+ while (*node) {
+ int result = i_node->low - rb_int(*node)->low;
+
+ parent = *node;
+ if (result < 0)
+ node = &((*node)->rb_left);
+ else if (result > 0)
+ node = &((*node)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&i_node->node, parent, node);
+ rb_insert_color(&i_node->node, root);
+
+ rb_augment_insert(&i_node->node, update_node_max_high, NULL);
+ return 0;
+}
+
+void rb_int_erase(struct rb_root *root, struct rb_int_node *node)
+{
+ struct rb_node *deepest;
+
+ deepest = rb_augment_erase_begin(&node->node);
+ rb_erase(&node->node, root);
+ rb_augment_erase_end(deepest, update_node_max_high, NULL);
+
+}
--- /dev/null
+#include "kvm/read-write.h"
+
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+
+/* Same as read(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xread(int fd, void *buf, size_t count)
+{
+ ssize_t nr;
+
+restart:
+ nr = read(fd, buf, count);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as write(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xwrite(int fd, const void *buf, size_t count)
+{
+ ssize_t nr;
+
+restart:
+ nr = write(fd, buf, count);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+ssize_t read_in_full(int fd, void *buf, size_t count)
+{
+ ssize_t total = 0;
+ char *p = buf;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xread(fd, p, count);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ count -= nr;
+ total += nr;
+ p += nr;
+ }
+
+ return total;
+}
+
+ssize_t write_in_full(int fd, const void *buf, size_t count)
+{
+ const char *p = buf;
+ ssize_t total = 0;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xwrite(fd, p, count);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+ count -= nr;
+ total += nr;
+ p += nr;
+ }
+
+ return total;
+}
+
+/* Same as pread(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpread(int fd, void *buf, size_t count, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = pread(fd, buf, count, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as pwrite(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpwrite(int fd, const void *buf, size_t count, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = pwrite(fd, buf, count, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+ssize_t pread_in_full(int fd, void *buf, size_t count, off_t offset)
+{
+ ssize_t total = 0;
+ char *p = buf;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpread(fd, p, count, offset);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ count -= nr;
+ total += nr;
+ p += nr;
+ offset += nr;
+ }
+
+ return total;
+}
+
+ssize_t pwrite_in_full(int fd, const void *buf, size_t count, off_t offset)
+{
+ const char *p = buf;
+ ssize_t total = 0;
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpwrite(fd, p, count, offset);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+ count -= nr;
+ total += nr;
+ p += nr;
+ offset += nr;
+ }
+
+ return total;
+}
+
+/* Same as readv(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xreadv(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t nr;
+
+restart:
+ nr = readv(fd, iov, iovcnt);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as writev(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xwritev(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t nr;
+
+restart:
+ nr = writev(fd, iov, iovcnt);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+static inline ssize_t get_iov_size(const struct iovec *iov, int iovcnt)
+{
+ size_t size = 0;
+ while (iovcnt--)
+ size += (iov++)->iov_len;
+
+ return size;
+}
+
+static inline void shift_iovec(const struct iovec **iov, int *iovcnt,
+ size_t nr, ssize_t *total, size_t *count, off_t *offset)
+{
+ while (nr >= (*iov)->iov_len) {
+ nr -= (*iov)->iov_len;
+ *total += (*iov)->iov_len;
+ *count -= (*iov)->iov_len;
+ if (offset)
+ *offset += (*iov)->iov_len;
+ (*iovcnt)--;
+ (*iov)++;
+ }
+}
+
+ssize_t readv_in_full(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xreadv(fd, iov, iovcnt);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, NULL);
+ }
+
+ return total;
+}
+
+ssize_t writev_in_full(int fd, const struct iovec *iov, int iovcnt)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xwritev(fd, iov, iovcnt);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, NULL);
+ }
+
+ return total;
+}
+
+/* Same as preadv(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpreadv(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = preadv(fd, iov, iovcnt, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+/* Same as pwritev(2) except that this function never returns EAGAIN or EINTR. */
+ssize_t xpwritev(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t nr;
+
+restart:
+ nr = pwritev(fd, iov, iovcnt, offset);
+ if ((nr < 0) && ((errno == EAGAIN) || (errno == EINTR)))
+ goto restart;
+
+ return nr;
+}
+
+ssize_t preadv_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpreadv(fd, iov, iovcnt, offset);
+ if (nr <= 0) {
+ if (total > 0)
+ return total;
+
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, &offset);
+ }
+
+ return total;
+}
+
+ssize_t pwritev_in_full(int fd, const struct iovec *iov, int iovcnt, off_t offset)
+{
+ ssize_t total = 0;
+ size_t count = get_iov_size(iov, iovcnt);
+
+ while (count > 0) {
+ ssize_t nr;
+
+ nr = xpwritev(fd, iov, iovcnt, offset);
+ if (nr < 0)
+ return -1;
+ if (nr == 0) {
+ errno = ENOSPC;
+ return -1;
+ }
+
+ shift_iovec(&iov, &iovcnt, nr, &total, &count, &offset);
+ }
+
+ return total;
+}
+
+#ifdef CONFIG_HAS_AIO
+int aio_pwritev(io_context_t ctx, struct iocb *iocb, int fd, const struct iovec *iov, int iovcnt,
+ off_t offset, int ev, void *param)
+{
+ struct iocb *ios[1] = { iocb };
+ int ret;
+
+ io_prep_pwritev(iocb, fd, iov, iovcnt, offset);
+ io_set_eventfd(iocb, ev);
+ iocb->data = param;
+
+restart:
+ ret = io_submit(ctx, 1, ios);
+ if (ret == -EAGAIN)
+ goto restart;
+ return ret;
+}
+
+int aio_preadv(io_context_t ctx, struct iocb *iocb, int fd, const struct iovec *iov, int iovcnt,
+ off_t offset, int ev, void *param)
+{
+ struct iocb *ios[1] = { iocb };
+ int ret;
+
+ io_prep_preadv(iocb, fd, iov, iovcnt, offset);
+ io_set_eventfd(iocb, ev);
+ iocb->data = param;
+
+restart:
+ ret = io_submit(ctx, 1, ios);
+ if (ret == -EAGAIN)
+ goto restart;
+ return ret;
+}
+#endif
--- /dev/null
+#!/bin/bash
+#
+# Author: Amos Kong <kongjianjun@gmail.com>
+# Date: Apr 14, 2011
+# Description: this script is used to create/delete a private bridge,
+# launch a dhcp server on the bridge by dnsmasq.
+#
+# @ ./set_private_br.sh $bridge_name $subnet_prefix
+# @ ./set_private_br.sh vbr0 192.168.33
+
+brname='vbr0'
+subnet='192.168.33'
+
+add_br()
+{
+ echo "add new private bridge: $brname"
+ /usr/sbin/brctl addbr $brname
+ echo 1 > /proc/sys/net/ipv6/conf/$brname/disable_ipv6
+ echo 1 > /proc/sys/net/ipv4/ip_forward
+ /usr/sbin/brctl stp $brname on
+ /usr/sbin/brctl setfd $brname 0
+ ifconfig $brname $subnet.1
+ ifconfig $brname up
+ # Add forward rule, then guest can access public network
+ iptables -t nat -A POSTROUTING -s $subnet.254/24 ! -d $subnet.254/24 -j MASQUERADE
+ /etc/init.d/dnsmasq stop
+ /etc/init.d/tftpd-hpa stop 2>/dev/null
+ dnsmasq --strict-order --bind-interfaces --listen-address $subnet.1 --dhcp-range $subnet.1,$subnet.254 $tftp_cmd
+}
+
+del_br()
+{
+ echo "cleanup bridge setup"
+ kill -9 `pgrep dnsmasq|tail -1`
+ ifconfig $brname down
+ /usr/sbin/brctl delbr $brname
+ iptables -t nat -D POSTROUTING -s $subnet.254/24 ! -d $subnet.254/24 -j MASQUERADE
+}
+
+
+if [ $# = 0 ]; then
+ del_br 2>/dev/null
+ exit
+fi
+if [ $# > 1 ]; then
+ brname="$1"
+fi
+if [ $# = 2 ]; then
+ subnet="$2"
+fi
+add_br
--- /dev/null
+
+/* user defined headers */
+#include <kvm/util.h>
+#include <kvm/strbuf.h>
+
+int prefixcmp(const char *str, const char *prefix)
+{
+ for (; ; str++, prefix++) {
+ if (!*prefix)
+ return 0;
+ else if (*str != *prefix)
+ return (unsigned char)*prefix - (unsigned char)*str;
+ }
+}
+
+/**
+ * strlcat - Append a length-limited, %NUL-terminated string to another
+ * @dest: The string to be appended to
+ * @src: The string to append to it
+ * @count: The size of the destination buffer.
+ */
+size_t strlcat(char *dest, const char *src, size_t count)
+{
+ size_t dsize = strlen(dest);
+ size_t len = strlen(src);
+ size_t res = dsize + len;
+
+ DIE_IF(dsize >= count);
+
+ dest += dsize;
+ count -= dsize;
+ if (len >= count)
+ len = count - 1;
+
+ memcpy(dest, src, len);
+ dest[len] = 0;
+
+ return res;
+}
+
+/**
+ * strlcpy - Copy a %NUL terminated string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @size: size of destination buffer
+ *
+ * Compatible with *BSD: the result is always a valid
+ * NUL-terminated string that fits in the buffer (unless,
+ * of course, the buffer size is zero). It does not pad
+ * out the result like strncpy() does.
+ */
+size_t strlcpy(char *dest, const char *src, size_t size)
+{
+ size_t ret = strlen(src);
+
+ if (size) {
+ size_t len = (ret >= size) ? size - 1 : ret;
+ memcpy(dest, src, len);
+ dest[len] = '\0';
+ }
+ return ret;
+}
--- /dev/null
+#include "kvm/threadpool.h"
+#include "kvm/mutex.h"
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <pthread.h>
+#include <stdbool.h>
+
+static pthread_mutex_t job_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_mutex_t thread_mutex = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t job_cond = PTHREAD_COND_INITIALIZER;
+
+static LIST_HEAD(head);
+
+static pthread_t *threads;
+static long threadcount;
+
+static struct thread_pool__job *thread_pool__job_pop_locked(void)
+{
+ struct thread_pool__job *job;
+
+ if (list_empty(&head))
+ return NULL;
+
+ job = list_first_entry(&head, struct thread_pool__job, queue);
+ list_del(&job->queue);
+
+ return job;
+}
+
+static void thread_pool__job_push_locked(struct thread_pool__job *job)
+{
+ list_add_tail(&job->queue, &head);
+}
+
+static struct thread_pool__job *thread_pool__job_pop(void)
+{
+ struct thread_pool__job *job;
+
+ mutex_lock(&job_mutex);
+ job = thread_pool__job_pop_locked();
+ mutex_unlock(&job_mutex);
+ return job;
+}
+
+static void thread_pool__job_push(struct thread_pool__job *job)
+{
+ mutex_lock(&job_mutex);
+ thread_pool__job_push_locked(job);
+ mutex_unlock(&job_mutex);
+}
+
+static void thread_pool__handle_job(struct thread_pool__job *job)
+{
+ while (job) {
+ job->callback(job->kvm, job->data);
+
+ mutex_lock(&job->mutex);
+
+ if (--job->signalcount > 0)
+ /* If the job was signaled again while we were working */
+ thread_pool__job_push(job);
+
+ mutex_unlock(&job->mutex);
+
+ job = thread_pool__job_pop();
+ }
+}
+
+static void thread_pool__threadfunc_cleanup(void *param)
+{
+ mutex_unlock(&job_mutex);
+}
+
+static void *thread_pool__threadfunc(void *param)
+{
+ pthread_cleanup_push(thread_pool__threadfunc_cleanup, NULL);
+
+ for (;;) {
+ struct thread_pool__job *curjob;
+
+ mutex_lock(&job_mutex);
+ while ((curjob = thread_pool__job_pop_locked()) == NULL)
+ pthread_cond_wait(&job_cond, &job_mutex);
+ mutex_unlock(&job_mutex);
+
+ thread_pool__handle_job(curjob);
+ }
+
+ pthread_cleanup_pop(0);
+
+ return NULL;
+}
+
+static int thread_pool__addthread(void)
+{
+ int res;
+ void *newthreads;
+
+ mutex_lock(&thread_mutex);
+ newthreads = realloc(threads, (threadcount + 1) * sizeof(pthread_t));
+ if (newthreads == NULL) {
+ mutex_unlock(&thread_mutex);
+ return -1;
+ }
+
+ threads = newthreads;
+
+ res = pthread_create(threads + threadcount, NULL,
+ thread_pool__threadfunc, NULL);
+
+ if (res == 0)
+ threadcount++;
+ mutex_unlock(&thread_mutex);
+
+ return res;
+}
+
+int thread_pool__init(unsigned long thread_count)
+{
+ unsigned long i;
+
+ for (i = 0; i < thread_count; i++)
+ if (thread_pool__addthread() < 0)
+ return i;
+
+ return i;
+}
+
+void thread_pool__do_job(struct thread_pool__job *job)
+{
+ struct thread_pool__job *jobinfo = job;
+
+ if (jobinfo == NULL || jobinfo->callback == NULL)
+ return;
+
+ mutex_lock(&jobinfo->mutex);
+ if (jobinfo->signalcount++ == 0)
+ thread_pool__job_push(job);
+ mutex_unlock(&jobinfo->mutex);
+
+ mutex_lock(&job_mutex);
+ pthread_cond_signal(&job_cond);
+ mutex_unlock(&job_mutex);
+}
--- /dev/null
+/*
+ * Taken from perf which in turn take it from GIT
+ */
+
+#include "kvm/util.h"
+
+#include <kvm/kvm.h>
+#include <linux/magic.h> /* For HUGETLBFS_MAGIC */
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/statfs.h>
+
+static void report(const char *prefix, const char *err, va_list params)
+{
+ char msg[1024];
+ vsnprintf(msg, sizeof(msg), err, params);
+ fprintf(stderr, " %s%s\n", prefix, msg);
+}
+
+static NORETURN void die_builtin(const char *err, va_list params)
+{
+ report(" Fatal: ", err, params);
+ exit(128);
+}
+
+static void error_builtin(const char *err, va_list params)
+{
+ report(" Error: ", err, params);
+}
+
+static void warn_builtin(const char *warn, va_list params)
+{
+ report(" Warning: ", warn, params);
+}
+
+static void info_builtin(const char *info, va_list params)
+{
+ report(" Info: ", info, params);
+}
+
+void die(const char *err, ...)
+{
+ va_list params;
+
+ va_start(params, err);
+ die_builtin(err, params);
+ va_end(params);
+}
+
+int pr_err(const char *err, ...)
+{
+ va_list params;
+
+ va_start(params, err);
+ error_builtin(err, params);
+ va_end(params);
+ return -1;
+}
+
+void pr_warning(const char *warn, ...)
+{
+ va_list params;
+
+ va_start(params, warn);
+ warn_builtin(warn, params);
+ va_end(params);
+}
+
+void pr_info(const char *info, ...)
+{
+ va_list params;
+
+ va_start(params, info);
+ info_builtin(info, params);
+ va_end(params);
+}
+
+void die_perror(const char *s)
+{
+ perror(s);
+ exit(1);
+}
+
+void *mmap_hugetlbfs(struct kvm *kvm, const char *htlbfs_path, u64 size)
+{
+ char mpath[PATH_MAX];
+ int fd;
+ struct statfs sfs;
+ void *addr;
+ unsigned long blk_size;
+
+ if (statfs(htlbfs_path, &sfs) < 0)
+ die("Can't stat %s\n", htlbfs_path);
+
+ if ((unsigned int)sfs.f_type != HUGETLBFS_MAGIC)
+ die("%s is not hugetlbfs!\n", htlbfs_path);
+
+ blk_size = (unsigned long)sfs.f_bsize;
+ if (sfs.f_bsize == 0 || blk_size > size) {
+ die("Can't use hugetlbfs pagesize %ld for mem size %lld\n",
+ blk_size, size);
+ }
+
+ kvm->ram_pagesize = blk_size;
+
+ snprintf(mpath, PATH_MAX, "%s/kvmtoolXXXXXX", htlbfs_path);
+ fd = mkstemp(mpath);
+ if (fd < 0)
+ die("Can't open %s for hugetlbfs map\n", mpath);
+ unlink(mpath);
+ if (ftruncate(fd, size) < 0)
+ die("Can't ftruncate for mem mapping size %lld\n",
+ size);
+ addr = mmap(NULL, size, PROT_RW, MAP_PRIVATE, fd, 0);
+ close(fd);
+
+ return addr;
+}
+
+/* This function wraps the decision between hugetlbfs map (if requested) or normal mmap */
+void *mmap_anon_or_hugetlbfs(struct kvm *kvm, const char *hugetlbfs_path, u64 size)
+{
+ if (hugetlbfs_path)
+ /*
+ * We don't /need/ to map guest RAM from hugetlbfs, but we do so
+ * if the user specifies a hugetlbfs path.
+ */
+ return mmap_hugetlbfs(kvm, hugetlbfs_path, size);
+ else {
+ kvm->ram_pagesize = getpagesize();
+ return mmap(NULL, size, PROT_RW, MAP_ANON_NORESERVE, -1, 0);
+ }
+}
--- /dev/null
+#include "kvm/util.h"
+#include "kvm/virtio-9p.h"
+
+#include <endian.h>
+#include <stdint.h>
+
+#include <linux/compiler.h>
+#include <net/9p/9p.h>
+
+static void virtio_p9_pdu_read(struct p9_pdu *pdu, void *data, size_t size)
+{
+ size_t len;
+ int i, copied = 0;
+ u16 iov_cnt = pdu->out_iov_cnt;
+ size_t offset = pdu->read_offset;
+ struct iovec *iov = pdu->out_iov;
+
+ for (i = 0; i < iov_cnt && size; i++) {
+ if (offset >= iov[i].iov_len) {
+ offset -= iov[i].iov_len;
+ continue;
+ } else {
+ len = MIN(iov[i].iov_len - offset, size);
+ memcpy(data, iov[i].iov_base + offset, len);
+ size -= len;
+ data += len;
+ offset = 0;
+ copied += len;
+ }
+ }
+ pdu->read_offset += copied;
+}
+
+static void virtio_p9_pdu_write(struct p9_pdu *pdu,
+ const void *data, size_t size)
+{
+ size_t len;
+ int i, copied = 0;
+ u16 iov_cnt = pdu->in_iov_cnt;
+ size_t offset = pdu->write_offset;
+ struct iovec *iov = pdu->in_iov;
+
+ for (i = 0; i < iov_cnt && size; i++) {
+ if (offset >= iov[i].iov_len) {
+ offset -= iov[i].iov_len;
+ continue;
+ } else {
+ len = MIN(iov[i].iov_len - offset, size);
+ memcpy(iov[i].iov_base + offset, data, len);
+ size -= len;
+ data += len;
+ offset = 0;
+ copied += len;
+ }
+ }
+ pdu->write_offset += copied;
+}
+
+static void virtio_p9_wstat_free(struct p9_wstat *stbuf)
+{
+ free(stbuf->name);
+ free(stbuf->uid);
+ free(stbuf->gid);
+ free(stbuf->muid);
+}
+
+static int virtio_p9_decode(struct p9_pdu *pdu, const char *fmt, va_list ap)
+{
+ int retval = 0;
+ const char *ptr;
+
+ for (ptr = fmt; *ptr; ptr++) {
+ switch (*ptr) {
+ case 'b':
+ {
+ int8_t *val = va_arg(ap, int8_t *);
+ virtio_p9_pdu_read(pdu, val, sizeof(*val));
+ }
+ break;
+ case 'w':
+ {
+ int16_t le_val;
+ int16_t *val = va_arg(ap, int16_t *);
+ virtio_p9_pdu_read(pdu, &le_val, sizeof(le_val));
+ *val = le16toh(le_val);
+ }
+ break;
+ case 'd':
+ {
+ int32_t le_val;
+ int32_t *val = va_arg(ap, int32_t *);
+ virtio_p9_pdu_read(pdu, &le_val, sizeof(le_val));
+ *val = le32toh(le_val);
+ }
+ break;
+ case 'q':
+ {
+ int64_t le_val;
+ int64_t *val = va_arg(ap, int64_t *);
+ virtio_p9_pdu_read(pdu, &le_val, sizeof(le_val));
+ *val = le64toh(le_val);
+ }
+ break;
+ case 's':
+ {
+ int16_t len;
+ char **str = va_arg(ap, char **);
+
+ virtio_p9_pdu_readf(pdu, "w", &len);
+ *str = malloc(len + 1);
+ if (*str == NULL) {
+ retval = ENOMEM;
+ break;
+ }
+ virtio_p9_pdu_read(pdu, *str, len);
+ (*str)[len] = 0;
+ }
+ break;
+ case 'Q':
+ {
+ struct p9_qid *qid = va_arg(ap, struct p9_qid *);
+ retval = virtio_p9_pdu_readf(pdu, "bdq",
+ &qid->type, &qid->version,
+ &qid->path);
+ }
+ break;
+ case 'S':
+ {
+ struct p9_wstat *stbuf = va_arg(ap, struct p9_wstat *);
+ memset(stbuf, 0, sizeof(struct p9_wstat));
+ stbuf->n_uid = stbuf->n_gid = stbuf->n_muid = -1;
+ retval = virtio_p9_pdu_readf(pdu, "wwdQdddqssss",
+ &stbuf->size, &stbuf->type,
+ &stbuf->dev, &stbuf->qid,
+ &stbuf->mode, &stbuf->atime,
+ &stbuf->mtime, &stbuf->length,
+ &stbuf->name, &stbuf->uid,
+ &stbuf->gid, &stbuf->muid);
+ if (retval)
+ virtio_p9_wstat_free(stbuf);
+ }
+ break;
+ case 'I':
+ {
+ struct p9_iattr_dotl *p9attr = va_arg(ap,
+ struct p9_iattr_dotl *);
+
+ retval = virtio_p9_pdu_readf(pdu, "ddddqqqqq",
+ &p9attr->valid,
+ &p9attr->mode,
+ &p9attr->uid,
+ &p9attr->gid,
+ &p9attr->size,
+ &p9attr->atime_sec,
+ &p9attr->atime_nsec,
+ &p9attr->mtime_sec,
+ &p9attr->mtime_nsec);
+ }
+ break;
+ default:
+ retval = EINVAL;
+ break;
+ }
+ }
+ return retval;
+}
+
+static int virtio_p9_pdu_encode(struct p9_pdu *pdu, const char *fmt, va_list ap)
+{
+ int retval = 0;
+ const char *ptr;
+
+ for (ptr = fmt; *ptr; ptr++) {
+ switch (*ptr) {
+ case 'b':
+ {
+ int8_t val = va_arg(ap, int);
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 'w':
+ {
+ int16_t val = htole16(va_arg(ap, int));
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 'd':
+ {
+ int32_t val = htole32(va_arg(ap, int32_t));
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 'q':
+ {
+ int64_t val = htole64(va_arg(ap, int64_t));
+ virtio_p9_pdu_write(pdu, &val, sizeof(val));
+ }
+ break;
+ case 's':
+ {
+ uint16_t len = 0;
+ const char *s = va_arg(ap, char *);
+ if (s)
+ len = MIN(strlen(s), USHRT_MAX);
+ virtio_p9_pdu_writef(pdu, "w", len);
+ virtio_p9_pdu_write(pdu, s, len);
+ }
+ break;
+ case 'Q':
+ {
+ struct p9_qid *qid = va_arg(ap, struct p9_qid *);
+ retval = virtio_p9_pdu_writef(pdu, "bdq",
+ qid->type, qid->version,
+ qid->path);
+ }
+ break;
+ case 'S':
+ {
+ struct p9_wstat *stbuf = va_arg(ap, struct p9_wstat *);
+ retval = virtio_p9_pdu_writef(pdu, "wwdQdddqssss",
+ stbuf->size, stbuf->type,
+ stbuf->dev, &stbuf->qid,
+ stbuf->mode, stbuf->atime,
+ stbuf->mtime, stbuf->length,
+ stbuf->name, stbuf->uid,
+ stbuf->gid, stbuf->muid);
+ }
+ break;
+ case 'A':
+ {
+ struct p9_stat_dotl *stbuf = va_arg(ap,
+ struct p9_stat_dotl *);
+ retval = virtio_p9_pdu_writef(pdu,
+ "qQdddqqqqqqqqqqqqqqq",
+ stbuf->st_result_mask,
+ &stbuf->qid,
+ stbuf->st_mode,
+ stbuf->st_uid,
+ stbuf->st_gid,
+ stbuf->st_nlink,
+ stbuf->st_rdev,
+ stbuf->st_size,
+ stbuf->st_blksize,
+ stbuf->st_blocks,
+ stbuf->st_atime_sec,
+ stbuf->st_atime_nsec,
+ stbuf->st_mtime_sec,
+ stbuf->st_mtime_nsec,
+ stbuf->st_ctime_sec,
+ stbuf->st_ctime_nsec,
+ stbuf->st_btime_sec,
+ stbuf->st_btime_nsec,
+ stbuf->st_gen,
+ stbuf->st_data_version);
+ }
+ break;
+ default:
+ retval = EINVAL;
+ break;
+ }
+ }
+ return retval;
+}
+
+int virtio_p9_pdu_readf(struct p9_pdu *pdu, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ va_start(ap, fmt);
+ ret = virtio_p9_decode(pdu, fmt, ap);
+ va_end(ap);
+
+ return ret;
+}
+
+int virtio_p9_pdu_writef(struct p9_pdu *pdu, const char *fmt, ...)
+{
+ int ret;
+ va_list ap;
+
+ va_start(ap, fmt);
+ ret = virtio_p9_pdu_encode(pdu, fmt, ap);
+ va_end(ap);
+
+ return ret;
+}
--- /dev/null
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/threadpool.h"
+#include "kvm/irq.h"
+#include "kvm/virtio-9p.h"
+#include "kvm/guest_compat.h"
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/vfs.h>
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_9p.h>
+#include <net/9p/9p.h>
+
+static LIST_HEAD(devs);
+static int compat_id = -1;
+
+static int insert_new_fid(struct p9_dev *dev, struct p9_fid *fid);
+static struct p9_fid *find_or_create_fid(struct p9_dev *dev, u32 fid)
+{
+ struct rb_node *node = dev->fids.rb_node;
+ struct p9_fid *pfid = NULL;
+
+ while (node) {
+ struct p9_fid *cur = rb_entry(node, struct p9_fid, node);
+
+ if (fid < cur->fid) {
+ node = node->rb_left;
+ } else if (fid > cur->fid) {
+ node = node->rb_right;
+ } else {
+ return cur;
+ }
+ }
+
+ pfid = calloc(sizeof(*pfid), 1);
+ if (!pfid)
+ return NULL;
+
+ pfid->fid = fid;
+ strcpy(pfid->abs_path, dev->root_dir);
+ pfid->path = pfid->abs_path + strlen(dev->root_dir);
+
+ insert_new_fid(dev, pfid);
+
+ return pfid;
+}
+
+static int insert_new_fid(struct p9_dev *dev, struct p9_fid *fid)
+{
+ struct rb_node **node = &(dev->fids.rb_node), *parent = NULL;
+
+ while (*node) {
+ int result = fid->fid - rb_entry(*node, struct p9_fid, node)->fid;
+
+ parent = *node;
+ if (result < 0)
+ node = &((*node)->rb_left);
+ else if (result > 0)
+ node = &((*node)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ rb_link_node(&fid->node, parent, node);
+ rb_insert_color(&fid->node, &dev->fids);
+ return 0;
+}
+
+static struct p9_fid *get_fid(struct p9_dev *p9dev, int fid)
+{
+ struct p9_fid *new;
+
+ new = find_or_create_fid(p9dev, fid);
+
+ return new;
+}
+
+/* Warning: Immediately use value returned from this function */
+static const char *rel_to_abs(struct p9_dev *p9dev,
+ const char *path, char *abs_path)
+{
+ sprintf(abs_path, "%s/%s", p9dev->root_dir, path);
+
+ return abs_path;
+}
+
+static void stat2qid(struct stat *st, struct p9_qid *qid)
+{
+ *qid = (struct p9_qid) {
+ .path = st->st_ino,
+ .version = st->st_mtime,
+ };
+
+ if (S_ISDIR(st->st_mode))
+ qid->type |= P9_QTDIR;
+}
+
+static void close_fid(struct p9_dev *p9dev, u32 fid)
+{
+ struct p9_fid *pfid = get_fid(p9dev, fid);
+
+ if (pfid->fd > 0)
+ close(pfid->fd);
+
+ if (pfid->dir)
+ closedir(pfid->dir);
+
+ rb_erase(&pfid->node, &p9dev->fids);
+ free(pfid);
+}
+
+static void virtio_p9_set_reply_header(struct p9_pdu *pdu, u32 size)
+{
+ u8 cmd;
+ u16 tag;
+
+ pdu->read_offset = sizeof(u32);
+ virtio_p9_pdu_readf(pdu, "bw", &cmd, &tag);
+ pdu->write_offset = 0;
+ /* cmd + 1 is the reply message */
+ virtio_p9_pdu_writef(pdu, "dbw", size, cmd + 1, tag);
+}
+
+static u16 virtio_p9_update_iov_cnt(struct iovec iov[], u32 count, int iov_cnt)
+{
+ int i;
+ u32 total = 0;
+ for (i = 0; (i < iov_cnt) && (total < count); i++) {
+ if (total + iov[i].iov_len > count) {
+ /* we don't need this iov fully */
+ iov[i].iov_len -= ((total + iov[i].iov_len) - count);
+ i++;
+ break;
+ }
+ total += iov[i].iov_len;
+ }
+ return i;
+}
+
+static void virtio_p9_error_reply(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, int err, u32 *outlen)
+{
+ u16 tag;
+
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", err);
+ *outlen = pdu->write_offset;
+
+ /* read the tag from input */
+ pdu->read_offset = sizeof(u32) + sizeof(u8);
+ virtio_p9_pdu_readf(pdu, "w", &tag);
+
+ /* Update the header */
+ pdu->write_offset = 0;
+ virtio_p9_pdu_writef(pdu, "dbw", *outlen, P9_RLERROR, tag);
+}
+
+static void virtio_p9_version(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 msize;
+ char *version;
+ virtio_p9_pdu_readf(pdu, "ds", &msize, &version);
+ /*
+ * reply with the same msize the client sent us
+ * Error out if the request is not for 9P2000.L
+ */
+ if (!strcmp(version, VIRTIO_9P_VERSION_DOTL))
+ virtio_p9_pdu_writef(pdu, "ds", msize, version);
+ else
+ virtio_p9_pdu_writef(pdu, "ds", msize, "unknown");
+
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(version);
+ return;
+}
+
+static void virtio_p9_clunk(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid;
+
+ virtio_p9_pdu_readf(pdu, "d", &fid);
+ close_fid(p9dev, fid);
+
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+}
+
+/*
+ * FIXME!! Need to map to protocol independent value. Upstream
+ * 9p also have the same BUG
+ */
+static int virtio_p9_openflags(int flags)
+{
+ flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT | O_DIRECT);
+ flags |= O_NOFOLLOW;
+ return flags;
+}
+
+static bool is_dir(struct p9_fid *fid)
+{
+ struct stat st;
+
+ stat(fid->abs_path, &st);
+
+ return S_ISDIR(st.st_mode);
+}
+
+static void virtio_p9_open(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid, flags;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *new_fid;
+
+
+ virtio_p9_pdu_readf(pdu, "dd", &fid, &flags);
+ new_fid = get_fid(p9dev, fid);
+
+ if (lstat(new_fid->abs_path, &st) < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+
+ if (is_dir(new_fid)) {
+ new_fid->dir = opendir(new_fid->abs_path);
+ if (!new_fid->dir)
+ goto err_out;
+ } else {
+ new_fid->fd = open(new_fid->abs_path,
+ virtio_p9_openflags(flags));
+ if (new_fid->fd < 0)
+ goto err_out;
+ }
+ /* FIXME!! need ot send proper iounit */
+ virtio_p9_pdu_writef(pdu, "Qd", &qid, 0);
+
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_create(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int fd, ret;
+ char *name;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *dfid;
+ char full_path[PATH_MAX];
+ u32 dfid_val, flags, mode, gid;
+
+ virtio_p9_pdu_readf(pdu, "dsddd", &dfid_val,
+ &name, &flags, &mode, &gid);
+ dfid = get_fid(p9dev, dfid_val);
+
+ flags = virtio_p9_openflags(flags);
+
+ sprintf(full_path, "%s/%s", dfid->abs_path, name);
+ fd = open(full_path, flags | O_CREAT, mode);
+ if (fd < 0)
+ goto err_out;
+ dfid->fd = fd;
+
+ if (lstat(full_path, &st) < 0)
+ goto err_out;
+
+ ret = chmod(full_path, mode & 0777);
+ if (ret < 0)
+ goto err_out;
+
+ ret = lchown(full_path, dfid->uid, gid);
+ if (ret < 0)
+ goto err_out;
+
+ sprintf(dfid->path, "%s/%s", dfid->path, name);
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Qd", &qid, 0);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(name);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_mkdir(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *dfid;
+ char full_path[PATH_MAX];
+ u32 dfid_val, mode, gid;
+
+ virtio_p9_pdu_readf(pdu, "dsdd", &dfid_val,
+ &name, &mode, &gid);
+ dfid = get_fid(p9dev, dfid_val);
+
+ sprintf(full_path, "%s/%s", dfid->abs_path, name);
+ ret = mkdir(full_path, mode);
+ if (ret < 0)
+ goto err_out;
+
+ if (lstat(full_path, &st) < 0)
+ goto err_out;
+
+ ret = chmod(full_path, mode & 0777);
+ if (ret < 0)
+ goto err_out;
+
+ ret = lchown(full_path, dfid->uid, gid);
+ if (ret < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Qd", &qid, 0);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(name);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_walk(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u8 i;
+ u16 nwqid;
+ u16 nwname;
+ struct p9_qid wqid;
+ struct p9_fid *new_fid, *old_fid;
+ u32 fid_val, newfid_val;
+
+
+ virtio_p9_pdu_readf(pdu, "ddw", &fid_val, &newfid_val, &nwname);
+ new_fid = get_fid(p9dev, newfid_val);
+
+ nwqid = 0;
+ if (nwname) {
+ struct p9_fid *fid = get_fid(p9dev, fid_val);
+
+ strcpy(new_fid->path, fid->path);
+ /* skip the space for count */
+ pdu->write_offset += sizeof(u16);
+ for (i = 0; i < nwname; i++) {
+ struct stat st;
+ char tmp[PATH_MAX] = {0};
+ char full_path[PATH_MAX];
+ char *str;
+
+ virtio_p9_pdu_readf(pdu, "s", &str);
+
+ /* Format the new path we're 'walk'ing into */
+ sprintf(tmp, "%s/%s", new_fid->path, str);
+
+ free(str);
+
+ if (lstat(rel_to_abs(p9dev, tmp, full_path), &st) < 0)
+ goto err_out;
+
+ stat2qid(&st, &wqid);
+ strcpy(new_fid->path, tmp);
+ new_fid->uid = fid->uid;
+ nwqid++;
+ virtio_p9_pdu_writef(pdu, "Q", &wqid);
+ }
+ } else {
+ /*
+ * update write_offset so our outlen get correct value
+ */
+ pdu->write_offset += sizeof(u16);
+ old_fid = get_fid(p9dev, fid_val);
+ strcpy(new_fid->path, old_fid->path);
+ new_fid->uid = old_fid->uid;
+ }
+ *outlen = pdu->write_offset;
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", nwqid);
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_attach(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ char *uname;
+ char *aname;
+ struct stat st;
+ struct p9_qid qid;
+ struct p9_fid *fid;
+ u32 fid_val, afid, uid;
+
+ virtio_p9_pdu_readf(pdu, "ddssd", &fid_val, &afid,
+ &uname, &aname, &uid);
+
+ free(uname);
+ free(aname);
+
+ if (lstat(p9dev->root_dir, &st) < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+
+ fid = get_fid(p9dev, fid_val);
+ fid->uid = uid;
+ strcpy(fid->path, "/");
+
+ virtio_p9_pdu_writef(pdu, "Q", &qid);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_fill_stat(struct p9_dev *p9dev,
+ struct stat *st, struct p9_stat_dotl *statl)
+{
+ memset(statl, 0, sizeof(*statl));
+ statl->st_mode = st->st_mode;
+ statl->st_nlink = st->st_nlink;
+ statl->st_uid = st->st_uid;
+ statl->st_gid = st->st_gid;
+ statl->st_rdev = st->st_rdev;
+ statl->st_size = st->st_size;
+ statl->st_blksize = st->st_blksize;
+ statl->st_blocks = st->st_blocks;
+ statl->st_atime_sec = st->st_atime;
+ statl->st_atime_nsec = st->st_atim.tv_nsec;
+ statl->st_mtime_sec = st->st_mtime;
+ statl->st_mtime_nsec = st->st_mtim.tv_nsec;
+ statl->st_ctime_sec = st->st_ctime;
+ statl->st_ctime_nsec = st->st_ctim.tv_nsec;
+ /* Currently we only support BASIC fields in stat */
+ statl->st_result_mask = P9_STATS_BASIC;
+ stat2qid(st, &statl->qid);
+}
+
+static void virtio_p9_read(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u64 offset;
+ u32 fid_val;
+ u16 iov_cnt;
+ void *iov_base;
+ size_t iov_len;
+ u32 count, rcount;
+ struct p9_fid *fid;
+
+
+ rcount = 0;
+ virtio_p9_pdu_readf(pdu, "dqd", &fid_val, &offset, &count);
+ fid = get_fid(p9dev, fid_val);
+
+ iov_base = pdu->in_iov[0].iov_base;
+ iov_len = pdu->in_iov[0].iov_len;
+ iov_cnt = pdu->in_iov_cnt;
+ pdu->in_iov[0].iov_base += VIRTIO_9P_HDR_LEN + sizeof(u32);
+ pdu->in_iov[0].iov_len -= VIRTIO_9P_HDR_LEN + sizeof(u32);
+ pdu->in_iov_cnt = virtio_p9_update_iov_cnt(pdu->in_iov,
+ count,
+ pdu->in_iov_cnt);
+ rcount = preadv(fid->fd, pdu->in_iov,
+ pdu->in_iov_cnt, offset);
+ if (rcount > count)
+ rcount = count;
+ /*
+ * Update the iov_base back, so that rest of
+ * pdu_writef works correctly.
+ */
+ pdu->in_iov[0].iov_base = iov_base;
+ pdu->in_iov[0].iov_len = iov_len;
+ pdu->in_iov_cnt = iov_cnt;
+
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", rcount);
+ *outlen = pdu->write_offset + rcount;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+}
+
+static int virtio_p9_dentry_size(struct dirent *dent)
+{
+ /*
+ * Size of each dirent:
+ * qid(13) + offset(8) + type(1) + name_len(2) + name
+ */
+ return 24 + strlen(dent->d_name);
+}
+
+static void virtio_p9_readdir(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid_val;
+ u32 count, rcount;
+ struct stat st;
+ struct p9_fid *fid;
+ struct dirent *dent;
+ char full_path[PATH_MAX];
+ u64 offset, old_offset;
+
+ rcount = 0;
+ virtio_p9_pdu_readf(pdu, "dqd", &fid_val, &offset, &count);
+ fid = get_fid(p9dev, fid_val);
+
+ if (!is_dir(fid)) {
+ errno = EINVAL;
+ goto err_out;
+ }
+
+ /* Move the offset specified */
+ seekdir(fid->dir, offset);
+
+ old_offset = offset;
+ /* If reading a dir, fill the buffer with p9_stat entries */
+ dent = readdir(fid->dir);
+
+ /* Skip the space for writing count */
+ pdu->write_offset += sizeof(u32);
+ while (dent) {
+ u32 read;
+ struct p9_qid qid;
+
+ if ((rcount + virtio_p9_dentry_size(dent)) > count) {
+ /* seek to the previous offset and return */
+ seekdir(fid->dir, old_offset);
+ break;
+ }
+ old_offset = dent->d_off;
+ lstat(rel_to_abs(p9dev, dent->d_name, full_path), &st);
+ stat2qid(&st, &qid);
+ read = pdu->write_offset;
+ virtio_p9_pdu_writef(pdu, "Qqbs", &qid, dent->d_off,
+ dent->d_type, dent->d_name);
+ rcount += pdu->write_offset - read;
+ dent = readdir(fid->dir);
+ }
+
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ virtio_p9_pdu_writef(pdu, "d", rcount);
+ *outlen = pdu->write_offset + rcount;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+
+static void virtio_p9_getattr(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid_val;
+ struct stat st;
+ u64 request_mask;
+ struct p9_fid *fid;
+ struct p9_stat_dotl statl;
+
+ virtio_p9_pdu_readf(pdu, "dq", &fid_val, &request_mask);
+ fid = get_fid(p9dev, fid_val);
+ if (lstat(fid->abs_path, &st) < 0)
+ goto err_out;
+
+ virtio_p9_fill_stat(p9dev, &st, &statl);
+ virtio_p9_pdu_writef(pdu, "A", &statl);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+/* FIXME!! from linux/fs.h */
+/*
+ * Attribute flags. These should be or-ed together to figure out what
+ * has been changed!
+ */
+#define ATTR_MODE (1 << 0)
+#define ATTR_UID (1 << 1)
+#define ATTR_GID (1 << 2)
+#define ATTR_SIZE (1 << 3)
+#define ATTR_ATIME (1 << 4)
+#define ATTR_MTIME (1 << 5)
+#define ATTR_CTIME (1 << 6)
+#define ATTR_ATIME_SET (1 << 7)
+#define ATTR_MTIME_SET (1 << 8)
+#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */
+#define ATTR_ATTR_FLAG (1 << 10)
+#define ATTR_KILL_SUID (1 << 11)
+#define ATTR_KILL_SGID (1 << 12)
+#define ATTR_FILE (1 << 13)
+#define ATTR_KILL_PRIV (1 << 14)
+#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
+#define ATTR_TIMES_SET (1 << 16)
+
+#define ATTR_MASK 127
+
+static void virtio_p9_setattr(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret = 0;
+ u32 fid_val;
+ struct p9_fid *fid;
+ struct p9_iattr_dotl p9attr;
+
+ virtio_p9_pdu_readf(pdu, "dI", &fid_val, &p9attr);
+ fid = get_fid(p9dev, fid_val);
+
+ if (p9attr.valid & ATTR_MODE) {
+ ret = chmod(fid->abs_path, p9attr.mode);
+ if (ret < 0)
+ goto err_out;
+ }
+ if (p9attr.valid & (ATTR_ATIME | ATTR_MTIME)) {
+ struct timespec times[2];
+ if (p9attr.valid & ATTR_ATIME) {
+ if (p9attr.valid & ATTR_ATIME_SET) {
+ times[0].tv_sec = p9attr.atime_sec;
+ times[0].tv_nsec = p9attr.atime_nsec;
+ } else {
+ times[0].tv_nsec = UTIME_NOW;
+ }
+ } else {
+ times[0].tv_nsec = UTIME_OMIT;
+ }
+ if (p9attr.valid & ATTR_MTIME) {
+ if (p9attr.valid & ATTR_MTIME_SET) {
+ times[1].tv_sec = p9attr.mtime_sec;
+ times[1].tv_nsec = p9attr.mtime_nsec;
+ } else {
+ times[1].tv_nsec = UTIME_NOW;
+ }
+ } else
+ times[1].tv_nsec = UTIME_OMIT;
+
+ ret = utimensat(-1, fid->abs_path, times, AT_SYMLINK_NOFOLLOW);
+ if (ret < 0)
+ goto err_out;
+ }
+ /*
+ * If the only valid entry in iattr is ctime we can call
+ * chown(-1,-1) to update the ctime of the file
+ */
+ if ((p9attr.valid & (ATTR_UID | ATTR_GID)) ||
+ ((p9attr.valid & ATTR_CTIME)
+ && !((p9attr.valid & ATTR_MASK) & ~ATTR_CTIME))) {
+ if (!(p9attr.valid & ATTR_UID))
+ p9attr.uid = -1;
+
+ if (!(p9attr.valid & ATTR_GID))
+ p9attr.gid = -1;
+
+ ret = lchown(fid->abs_path, p9attr.uid, p9attr.gid);
+ if (ret < 0)
+ goto err_out;
+ }
+ if (p9attr.valid & (ATTR_SIZE)) {
+ ret = truncate(fid->abs_path, p9attr.size);
+ if (ret < 0)
+ goto err_out;
+ }
+ *outlen = VIRTIO_9P_HDR_LEN;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_write(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+
+ u64 offset;
+ u32 fid_val;
+ u32 count;
+ ssize_t res;
+ u16 iov_cnt;
+ void *iov_base;
+ size_t iov_len;
+ struct p9_fid *fid;
+ /* u32 fid + u64 offset + u32 count */
+ int twrite_size = sizeof(u32) + sizeof(u64) + sizeof(u32);
+
+ virtio_p9_pdu_readf(pdu, "dqd", &fid_val, &offset, &count);
+ fid = get_fid(p9dev, fid_val);
+
+ iov_base = pdu->out_iov[0].iov_base;
+ iov_len = pdu->out_iov[0].iov_len;
+ iov_cnt = pdu->out_iov_cnt;
+
+ /* Adjust the iovec to skip the header and meta data */
+ pdu->out_iov[0].iov_base += (sizeof(struct p9_msg) + twrite_size);
+ pdu->out_iov[0].iov_len -= (sizeof(struct p9_msg) + twrite_size);
+ pdu->out_iov_cnt = virtio_p9_update_iov_cnt(pdu->out_iov, count,
+ pdu->out_iov_cnt);
+ res = pwritev(fid->fd, pdu->out_iov, pdu->out_iov_cnt, offset);
+ /*
+ * Update the iov_base back, so that rest of
+ * pdu_readf works correctly.
+ */
+ pdu->out_iov[0].iov_base = iov_base;
+ pdu->out_iov[0].iov_len = iov_len;
+ pdu->out_iov_cnt = iov_cnt;
+
+ if (res < 0)
+ goto err_out;
+ virtio_p9_pdu_writef(pdu, "d", res);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_remove(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u32 fid_val;
+ struct p9_fid *fid;
+
+ virtio_p9_pdu_readf(pdu, "d", &fid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ ret = remove(fid->abs_path);
+ if (ret < 0)
+ goto err_out;
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_rename(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u32 fid_val, new_fid_val;
+ struct p9_fid *fid, *new_fid;
+ char full_path[PATH_MAX], *new_name;
+
+ virtio_p9_pdu_readf(pdu, "dds", &fid_val, &new_fid_val, &new_name);
+ fid = get_fid(p9dev, fid_val);
+ new_fid = get_fid(p9dev, new_fid_val);
+
+ sprintf(full_path, "%s/%s", new_fid->abs_path, new_name);
+ ret = rename(fid->abs_path, full_path);
+ if (ret < 0)
+ goto err_out;
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_readlink(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u32 fid_val;
+ struct p9_fid *fid;
+ char target_path[PATH_MAX];
+
+ virtio_p9_pdu_readf(pdu, "d", &fid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ memset(target_path, 0, PATH_MAX);
+ ret = readlink(fid->abs_path, target_path, PATH_MAX - 1);
+ if (ret < 0)
+ goto err_out;
+
+ virtio_p9_pdu_writef(pdu, "s", target_path);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_statfs(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ u64 fsid;
+ u32 fid_val;
+ struct p9_fid *fid;
+ struct statfs stat_buf;
+
+ virtio_p9_pdu_readf(pdu, "d", &fid_val);
+ fid = get_fid(p9dev, fid_val);
+
+ ret = statfs(fid->abs_path, &stat_buf);
+ if (ret < 0)
+ goto err_out;
+ /* FIXME!! f_blocks needs update based on client msize */
+ fsid = (unsigned int) stat_buf.f_fsid.__val[0] |
+ (unsigned long long)stat_buf.f_fsid.__val[1] << 32;
+ virtio_p9_pdu_writef(pdu, "ddqqqqqqd", stat_buf.f_type,
+ stat_buf.f_bsize, stat_buf.f_blocks,
+ stat_buf.f_bfree, stat_buf.f_bavail,
+ stat_buf.f_files, stat_buf.f_ffree,
+ fsid, stat_buf.f_namelen);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_mknod(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ struct stat st;
+ struct p9_fid *dfid;
+ struct p9_qid qid;
+ char full_path[PATH_MAX];
+ u32 fid_val, mode, major, minor, gid;
+
+ virtio_p9_pdu_readf(pdu, "dsdddd", &fid_val, &name, &mode,
+ &major, &minor, &gid);
+
+ dfid = get_fid(p9dev, fid_val);
+ sprintf(full_path, "%s/%s", dfid->abs_path, name);
+ ret = mknod(full_path, mode, makedev(major, minor));
+ if (ret < 0)
+ goto err_out;
+
+ if (lstat(full_path, &st) < 0)
+ goto err_out;
+
+ ret = chmod(full_path, mode & 0777);
+ if (ret < 0)
+ goto err_out;
+
+ ret = lchown(full_path, dfid->uid, gid);
+ if (ret < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Q", &qid);
+ free(name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_fsync(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ struct p9_fid *fid;
+ u32 fid_val, datasync;
+
+ virtio_p9_pdu_readf(pdu, "dd", &fid_val, &datasync);
+ fid = get_fid(p9dev, fid_val);
+
+ if (datasync)
+ ret = fdatasync(fid->fd);
+ else
+ ret = fsync(fid->fd);
+ if (ret < 0)
+ goto err_out;
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_symlink(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ struct stat st;
+ u32 fid_val, gid;
+ struct p9_qid qid;
+ struct p9_fid *dfid;
+ char new_name[PATH_MAX];
+ char *old_path, *name;
+
+ virtio_p9_pdu_readf(pdu, "dssd", &fid_val, &name, &old_path, &gid);
+
+ dfid = get_fid(p9dev, fid_val);
+ sprintf(new_name, "%s/%s", dfid->abs_path, name);
+ ret = symlink(old_path, new_name);
+ if (ret < 0)
+ goto err_out;
+
+ if (lstat(new_name, &st) < 0)
+ goto err_out;
+
+ ret = lchown(new_name, dfid->uid, gid);
+ if (ret < 0)
+ goto err_out;
+
+ stat2qid(&st, &qid);
+ virtio_p9_pdu_writef(pdu, "Q", &qid);
+ free(name);
+ free(old_path);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ free(old_path);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_link(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ u32 fid_val, dfid_val;
+ struct p9_fid *dfid, *fid;
+ char full_path[PATH_MAX];
+
+ virtio_p9_pdu_readf(pdu, "dds", &dfid_val, &fid_val, &name);
+
+ dfid = get_fid(p9dev, dfid_val);
+ fid = get_fid(p9dev, fid_val);
+ sprintf(full_path, "%s/%s", dfid->abs_path, name);
+ ret = link(fid->abs_path, full_path);
+ if (ret < 0)
+ goto err_out;
+ free(name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+
+}
+
+static void virtio_p9_lock(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u8 ret;
+ u32 fid_val;
+ struct p9_flock flock;
+
+ virtio_p9_pdu_readf(pdu, "dbdqqds", &fid_val, &flock.type,
+ &flock.flags, &flock.start, &flock.length,
+ &flock.proc_id, &flock.client_id);
+
+ /* Just return success */
+ ret = P9_LOCK_SUCCESS;
+ virtio_p9_pdu_writef(pdu, "d", ret);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(flock.client_id);
+ return;
+}
+
+static void virtio_p9_getlock(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u32 fid_val;
+ struct p9_getlock glock;
+ virtio_p9_pdu_readf(pdu, "dbqqds", &fid_val, &glock.type,
+ &glock.start, &glock.length, &glock.proc_id,
+ &glock.client_id);
+
+ /* Just return success */
+ glock.type = F_UNLCK;
+ virtio_p9_pdu_writef(pdu, "bqqds", glock.type,
+ glock.start, glock.length, glock.proc_id,
+ glock.client_id);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ free(glock.client_id);
+ return;
+}
+
+static int virtio_p9_ancestor(char *path, char *ancestor)
+{
+ int size = strlen(ancestor);
+ if (!strncmp(path, ancestor, size)) {
+ /*
+ * Now check whether ancestor is a full name or
+ * or directory component and not just part
+ * of a name.
+ */
+ if (path[size] == '\0' || path[size] == '/')
+ return 1;
+ }
+ return 0;
+}
+
+static void virtio_p9_fix_path(char *fid_path, char *old_name, char *new_name)
+{
+ char tmp_name[PATH_MAX];
+ size_t rp_sz = strlen(old_name);
+
+ if (rp_sz == strlen(fid_path)) {
+ /* replace the full name */
+ strcpy(fid_path, new_name);
+ return;
+ }
+ /* save the trailing path details */
+ strcpy(tmp_name, fid_path + rp_sz);
+ sprintf(fid_path, "%s%s", new_name, tmp_name);
+ return;
+}
+
+static void rename_fids(struct p9_dev *p9dev, char *old_name, char *new_name)
+{
+ struct rb_node *node = rb_first(&p9dev->fids);
+
+ while (node) {
+ struct p9_fid *fid = rb_entry(node, struct p9_fid, node);
+
+ if (fid->fid != P9_NOFID && virtio_p9_ancestor(fid->path, old_name)) {
+ virtio_p9_fix_path(fid->path, old_name, new_name);
+ }
+ node = rb_next(node);
+ }
+}
+
+static void virtio_p9_renameat(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *old_name, *new_name;
+ u32 old_dfid_val, new_dfid_val;
+ struct p9_fid *old_dfid, *new_dfid;
+ char old_full_path[PATH_MAX], new_full_path[PATH_MAX];
+
+
+ virtio_p9_pdu_readf(pdu, "dsds", &old_dfid_val, &old_name,
+ &new_dfid_val, &new_name);
+
+ old_dfid = get_fid(p9dev, old_dfid_val);
+ new_dfid = get_fid(p9dev, new_dfid_val);
+
+ sprintf(old_full_path, "%s/%s", old_dfid->abs_path, old_name);
+ sprintf(new_full_path, "%s/%s", new_dfid->abs_path, new_name);
+ ret = rename(old_full_path, new_full_path);
+ if (ret < 0)
+ goto err_out;
+ /*
+ * Now fix path in other fids, if the renamed path is part of
+ * that.
+ */
+ rename_fids(p9dev, old_name, new_name);
+ free(old_name);
+ free(new_name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(old_name);
+ free(new_name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_unlinkat(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ int ret;
+ char *name;
+ u32 fid_val, flags;
+ struct p9_fid *fid;
+ char full_path[PATH_MAX];
+
+ virtio_p9_pdu_readf(pdu, "dsd", &fid_val, &name, &flags);
+ fid = get_fid(p9dev, fid_val);
+
+ sprintf(full_path, "%s/%s", fid->abs_path, name);
+ ret = remove(full_path);
+ if (ret < 0)
+ goto err_out;
+ free(name);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+ return;
+err_out:
+ free(name);
+ virtio_p9_error_reply(p9dev, pdu, errno, outlen);
+ return;
+}
+
+static void virtio_p9_flush(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ u16 tag, oldtag;
+
+ virtio_p9_pdu_readf(pdu, "ww", &tag, &oldtag);
+ virtio_p9_pdu_writef(pdu, "w", tag);
+ *outlen = pdu->write_offset;
+ virtio_p9_set_reply_header(pdu, *outlen);
+
+ return;
+}
+
+static void virtio_p9_eopnotsupp(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen)
+{
+ return virtio_p9_error_reply(p9dev, pdu, EOPNOTSUPP, outlen);
+}
+
+typedef void p9_handler(struct p9_dev *p9dev,
+ struct p9_pdu *pdu, u32 *outlen);
+
+/* FIXME should be removed when merging with latest linus tree */
+#define P9_TRENAMEAT 74
+#define P9_TUNLINKAT 76
+
+static p9_handler *virtio_9p_dotl_handler [] = {
+ [P9_TREADDIR] = virtio_p9_readdir,
+ [P9_TSTATFS] = virtio_p9_statfs,
+ [P9_TGETATTR] = virtio_p9_getattr,
+ [P9_TSETATTR] = virtio_p9_setattr,
+ [P9_TXATTRWALK] = virtio_p9_eopnotsupp,
+ [P9_TXATTRCREATE] = virtio_p9_eopnotsupp,
+ [P9_TMKNOD] = virtio_p9_mknod,
+ [P9_TLOCK] = virtio_p9_lock,
+ [P9_TGETLOCK] = virtio_p9_getlock,
+ [P9_TRENAMEAT] = virtio_p9_renameat,
+ [P9_TREADLINK] = virtio_p9_readlink,
+ [P9_TUNLINKAT] = virtio_p9_unlinkat,
+ [P9_TMKDIR] = virtio_p9_mkdir,
+ [P9_TVERSION] = virtio_p9_version,
+ [P9_TLOPEN] = virtio_p9_open,
+ [P9_TATTACH] = virtio_p9_attach,
+ [P9_TWALK] = virtio_p9_walk,
+ [P9_TCLUNK] = virtio_p9_clunk,
+ [P9_TFSYNC] = virtio_p9_fsync,
+ [P9_TREAD] = virtio_p9_read,
+ [P9_TFLUSH] = virtio_p9_flush,
+ [P9_TLINK] = virtio_p9_link,
+ [P9_TSYMLINK] = virtio_p9_symlink,
+ [P9_TLCREATE] = virtio_p9_create,
+ [P9_TWRITE] = virtio_p9_write,
+ [P9_TREMOVE] = virtio_p9_remove,
+ [P9_TRENAME] = virtio_p9_rename,
+};
+
+static struct p9_pdu *virtio_p9_pdu_init(struct kvm *kvm, struct virt_queue *vq)
+{
+ struct p9_pdu *pdu = calloc(1, sizeof(*pdu));
+ if (!pdu)
+ return NULL;
+
+ /* skip the pdu header p9_msg */
+ pdu->read_offset = VIRTIO_9P_HDR_LEN;
+ pdu->write_offset = VIRTIO_9P_HDR_LEN;
+ pdu->queue_head = virt_queue__get_inout_iov(kvm, vq, pdu->in_iov,
+ pdu->out_iov, &pdu->in_iov_cnt, &pdu->out_iov_cnt);
+ return pdu;
+}
+
+static u8 virtio_p9_get_cmd(struct p9_pdu *pdu)
+{
+ struct p9_msg *msg;
+ /*
+ * we can peek directly into pdu for a u8
+ * value. The host endianess won't be an issue
+ */
+ msg = pdu->out_iov[0].iov_base;
+ return msg->cmd;
+}
+
+static bool virtio_p9_do_io_request(struct kvm *kvm, struct p9_dev_job *job)
+{
+ u8 cmd;
+ u32 len = 0;
+ p9_handler *handler;
+ struct p9_dev *p9dev;
+ struct virt_queue *vq;
+ struct p9_pdu *p9pdu;
+
+ vq = job->vq;
+ p9dev = job->p9dev;
+
+ p9pdu = virtio_p9_pdu_init(kvm, vq);
+ cmd = virtio_p9_get_cmd(p9pdu);
+
+ if ((cmd >= ARRAY_SIZE(virtio_9p_dotl_handler)) ||
+ !virtio_9p_dotl_handler[cmd])
+ handler = virtio_p9_eopnotsupp;
+ else
+ handler = virtio_9p_dotl_handler[cmd];
+
+ handler(p9dev, p9pdu, &len);
+ virt_queue__set_used_elem(vq, p9pdu->queue_head, len);
+ free(p9pdu);
+ return true;
+}
+
+static void virtio_p9_do_io(struct kvm *kvm, void *param)
+{
+ struct p9_dev_job *job = (struct p9_dev_job *)param;
+ struct p9_dev *p9dev = job->p9dev;
+ struct virt_queue *vq = job->vq;
+
+ while (virt_queue__available(vq)) {
+ virtio_p9_do_io_request(kvm, job);
+ p9dev->vdev.ops->signal_vq(kvm, &p9dev->vdev, vq - p9dev->vqs);
+ }
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct p9_dev *p9dev = dev;
+
+ return ((u8 *)(p9dev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1 << VIRTIO_9P_MOUNT_TAG;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct p9_dev *p9dev = dev;
+
+ p9dev->features = features;
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct p9_dev *p9dev = dev;
+ struct p9_dev_job *job;
+ struct virt_queue *queue;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &p9dev->vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+ job = &p9dev->jobs[vq];
+
+ vring_init(&queue->vring, VIRTQUEUE_NUM, p, VIRTIO_PCI_VRING_ALIGN);
+
+ *job = (struct p9_dev_job) {
+ .vq = queue,
+ .p9dev = p9dev,
+ };
+ thread_pool__init_job(&job->job_id, kvm, virtio_p9_do_io, job);
+
+ return 0;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct p9_dev *p9dev = dev;
+
+ thread_pool__do_job(&p9dev->jobs[vq].job_id);
+
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct p9_dev *p9dev = dev;
+
+ return p9dev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTQUEUE_NUM;
+}
+
+struct virtio_ops p9_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_vq = notify_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+};
+
+int virtio_9p__init(struct kvm *kvm)
+{
+ struct p9_dev *p9dev;
+
+ list_for_each_entry(p9dev, &devs, list) {
+ virtio_init(kvm, p9dev, &p9dev->vdev, &p9_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_9P, VIRTIO_ID_9P, PCI_CLASS_9P);
+ }
+
+ return 0;
+}
+
+int virtio_9p__register(struct kvm *kvm, const char *root, const char *tag_name)
+{
+ struct p9_dev *p9dev;
+ int err = 0;
+
+ p9dev = calloc(1, sizeof(*p9dev));
+ if (!p9dev)
+ return -ENOMEM;
+
+ if (!tag_name)
+ tag_name = VIRTIO_9P_DEFAULT_TAG;
+
+ p9dev->config = calloc(1, sizeof(*p9dev->config) + strlen(tag_name) + 1);
+ if (p9dev->config == NULL) {
+ err = -ENOMEM;
+ goto free_p9dev;
+ }
+
+ strcpy(p9dev->root_dir, root);
+ p9dev->config->tag_len = strlen(tag_name);
+ if (p9dev->config->tag_len > MAX_TAG_LEN) {
+ err = -EINVAL;
+ goto free_p9dev_config;
+ }
+
+ memcpy(&p9dev->config->tag, tag_name, strlen(tag_name));
+
+ list_add(&p9dev->list, &devs);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-9p", "CONFIG_NET_9P_VIRTIO");
+
+ return err;
+
+free_p9dev_config:
+ free(p9dev->config);
+free_p9dev:
+ free(p9dev);
+ return err;
+}
--- /dev/null
+#include "kvm/virtio-balloon.h"
+
+#include "kvm/virtio-pci-dev.h"
+
+#include "kvm/virtio.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/guest_compat.h"
+#include "kvm/kvm-ipc.h"
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_balloon.h>
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <pthread.h>
+#include <sys/eventfd.h>
+
+#define NUM_VIRT_QUEUES 3
+#define VIRTIO_BLN_QUEUE_SIZE 128
+#define VIRTIO_BLN_INFLATE 0
+#define VIRTIO_BLN_DEFLATE 1
+#define VIRTIO_BLN_STATS 2
+
+struct bln_dev {
+ struct list_head list;
+ struct virtio_device vdev;
+
+ u32 features;
+
+ /* virtio queue */
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct thread_pool__job jobs[NUM_VIRT_QUEUES];
+
+ struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
+ struct virtio_balloon_stat *cur_stat;
+ u32 cur_stat_head;
+ u16 stat_count;
+ int stat_waitfd;
+
+ struct virtio_balloon_config config;
+};
+
+static struct bln_dev bdev;
+extern struct kvm *kvm;
+static int compat_id = -1;
+
+static bool virtio_bln_do_io_request(struct kvm *kvm, struct bln_dev *bdev, struct virt_queue *queue)
+{
+ struct iovec iov[VIRTIO_BLN_QUEUE_SIZE];
+ unsigned int len = 0;
+ u16 out, in, head;
+ u32 *ptrs, i;
+
+ head = virt_queue__get_iov(queue, iov, &out, &in, kvm);
+ ptrs = iov[0].iov_base;
+ len = iov[0].iov_len / sizeof(u32);
+
+ for (i = 0 ; i < len ; i++) {
+ void *guest_ptr;
+
+ guest_ptr = guest_flat_to_host(kvm, ptrs[i] << VIRTIO_BALLOON_PFN_SHIFT);
+ if (queue == &bdev->vqs[VIRTIO_BLN_INFLATE]) {
+ madvise(guest_ptr, 1 << VIRTIO_BALLOON_PFN_SHIFT, MADV_DONTNEED);
+ bdev->config.actual++;
+ } else if (queue == &bdev->vqs[VIRTIO_BLN_DEFLATE]) {
+ bdev->config.actual--;
+ }
+ }
+
+ virt_queue__set_used_elem(queue, head, len);
+
+ return true;
+}
+
+static bool virtio_bln_do_stat_request(struct kvm *kvm, struct bln_dev *bdev, struct virt_queue *queue)
+{
+ struct iovec iov[VIRTIO_BLN_QUEUE_SIZE];
+ u16 out, in, head;
+ struct virtio_balloon_stat *stat;
+ u64 wait_val = 1;
+
+ head = virt_queue__get_iov(queue, iov, &out, &in, kvm);
+ stat = iov[0].iov_base;
+
+ /* Initial empty stat buffer */
+ if (bdev->cur_stat == NULL) {
+ bdev->cur_stat = stat;
+ bdev->cur_stat_head = head;
+
+ return true;
+ }
+
+ memcpy(bdev->stats, stat, iov[0].iov_len);
+
+ bdev->stat_count = iov[0].iov_len / sizeof(struct virtio_balloon_stat);
+ bdev->cur_stat = stat;
+ bdev->cur_stat_head = head;
+
+ if (write(bdev->stat_waitfd, &wait_val, sizeof(wait_val)) <= 0)
+ return -EFAULT;
+
+ return 1;
+}
+
+static void virtio_bln_do_io(struct kvm *kvm, void *param)
+{
+ struct virt_queue *vq = param;
+
+ if (vq == &bdev.vqs[VIRTIO_BLN_STATS]) {
+ virtio_bln_do_stat_request(kvm, &bdev, vq);
+ bdev.vdev.ops->signal_vq(kvm, &bdev.vdev, VIRTIO_BLN_STATS);
+ return;
+ }
+
+ while (virt_queue__available(vq)) {
+ virtio_bln_do_io_request(kvm, &bdev, vq);
+ bdev.vdev.ops->signal_vq(kvm, &bdev.vdev, vq - bdev.vqs);
+ }
+}
+
+static int virtio_bln__collect_stats(void)
+{
+ u64 tmp;
+
+ virt_queue__set_used_elem(&bdev.vqs[VIRTIO_BLN_STATS], bdev.cur_stat_head,
+ sizeof(struct virtio_balloon_stat));
+ bdev.vdev.ops->signal_vq(kvm, &bdev.vdev, VIRTIO_BLN_STATS);
+
+ if (read(bdev.stat_waitfd, &tmp, sizeof(tmp)) <= 0)
+ return -EFAULT;
+
+ return 0;
+}
+
+static void virtio_bln__print_stats(int fd, u32 type, u32 len, u8 *msg)
+{
+ int r;
+
+ if (WARN_ON(type != KVM_IPC_STAT || len))
+ return;
+
+ if (virtio_bln__collect_stats() < 0)
+ return;
+
+ r = write(fd, bdev.stats, sizeof(bdev.stats));
+ if (r < 0)
+ pr_warning("Failed sending memory stats");
+}
+
+static void handle_mem(int fd, u32 type, u32 len, u8 *msg)
+{
+ int mem;
+
+ if (WARN_ON(type != KVM_IPC_BALLOON || len != sizeof(int)))
+ return;
+
+ mem = *(int *)msg;
+ if (mem > 0) {
+ bdev.config.num_pages += 256 * mem;
+ } else if (mem < 0) {
+ if (bdev.config.num_pages < (u32)(256 * (-mem)))
+ return;
+
+ bdev.config.num_pages += 256 * mem;
+ }
+
+ /* Notify that the configuration space has changed */
+ bdev.vdev.ops->signal_config(kvm, &bdev.vdev);
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct bln_dev *bdev = dev;
+
+ return ((u8 *)(&bdev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1 << VIRTIO_BALLOON_F_STATS_VQ;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct bln_dev *bdev = dev;
+
+ bdev->features = features;
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct bln_dev *bdev = dev;
+ struct virt_queue *queue;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &bdev->vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+
+ thread_pool__init_job(&bdev->jobs[vq], kvm, virtio_bln_do_io, queue);
+ vring_init(&queue->vring, VIRTIO_BLN_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
+
+ return 0;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct bln_dev *bdev = dev;
+
+ thread_pool__do_job(&bdev->jobs[vq]);
+
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct bln_dev *bdev = dev;
+
+ return bdev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_BLN_QUEUE_SIZE;
+}
+
+struct virtio_ops bln_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_vq = notify_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+};
+
+void virtio_bln__init(struct kvm *kvm)
+{
+ kvm_ipc__register_handler(KVM_IPC_BALLOON, handle_mem);
+ kvm_ipc__register_handler(KVM_IPC_STAT, virtio_bln__print_stats);
+
+ bdev.stat_waitfd = eventfd(0, 0);
+ memset(&bdev.config, 0, sizeof(struct virtio_balloon_config));
+
+ virtio_init(kvm, &bdev, &bdev.vdev, &bln_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_BLN, VIRTIO_ID_BALLOON, PCI_CLASS_BLN);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-balloon", "CONFIG_VIRTIO_BALLOON");
+}
--- /dev/null
+#include "kvm/virtio-blk.h"
+
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/disk-image.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/guest_compat.h"
+#include "kvm/virtio-pci.h"
+#include "kvm/virtio.h"
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_blk.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <pthread.h>
+
+#define VIRTIO_BLK_MAX_DEV 4
+
+/*
+ * the header and status consume too entries
+ */
+#define DISK_SEG_MAX (VIRTIO_BLK_QUEUE_SIZE - 2)
+#define VIRTIO_BLK_QUEUE_SIZE 256
+#define NUM_VIRT_QUEUES 1
+
+struct blk_dev_req {
+ struct virt_queue *vq;
+ struct blk_dev *bdev;
+ struct iovec iov[VIRTIO_BLK_QUEUE_SIZE];
+ u16 out, in, head;
+ struct kvm *kvm;
+};
+
+struct blk_dev {
+ pthread_mutex_t mutex;
+
+ struct list_head list;
+
+ struct virtio_device vdev;
+ struct virtio_blk_config blk_config;
+ struct disk_image *disk;
+ u32 features;
+
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct blk_dev_req reqs[VIRTIO_BLK_QUEUE_SIZE];
+
+ pthread_t io_thread;
+ int io_efd;
+
+ struct kvm *kvm;
+};
+
+static LIST_HEAD(bdevs);
+static int compat_id = -1;
+
+void virtio_blk_complete(void *param, long len)
+{
+ struct blk_dev_req *req = param;
+ struct blk_dev *bdev = req->bdev;
+ int queueid = req->vq - bdev->vqs;
+ u8 *status;
+
+ /* status */
+ status = req->iov[req->out + req->in - 1].iov_base;
+ *status = (len < 0) ? VIRTIO_BLK_S_IOERR : VIRTIO_BLK_S_OK;
+
+ mutex_lock(&bdev->mutex);
+ virt_queue__set_used_elem(req->vq, req->head, len);
+ mutex_unlock(&bdev->mutex);
+
+ if (virtio_queue__should_signal(&bdev->vqs[queueid]))
+ bdev->vdev.ops->signal_vq(req->kvm, &bdev->vdev, queueid);
+}
+
+static void virtio_blk_do_io_request(struct kvm *kvm, struct blk_dev_req *req)
+{
+ struct virtio_blk_outhdr *req_hdr;
+ ssize_t block_cnt;
+ struct blk_dev *bdev;
+ struct iovec *iov;
+ u16 out, in;
+
+ block_cnt = -1;
+ bdev = req->bdev;
+ iov = req->iov;
+ out = req->out;
+ in = req->in;
+ req_hdr = iov[0].iov_base;
+
+ switch (req_hdr->type) {
+ case VIRTIO_BLK_T_IN:
+ block_cnt = disk_image__read(bdev->disk, req_hdr->sector,
+ iov + 1, in + out - 2, req);
+ break;
+ case VIRTIO_BLK_T_OUT:
+ block_cnt = disk_image__write(bdev->disk, req_hdr->sector,
+ iov + 1, in + out - 2, req);
+ break;
+ case VIRTIO_BLK_T_FLUSH:
+ block_cnt = disk_image__flush(bdev->disk);
+ virtio_blk_complete(req, block_cnt);
+ break;
+ case VIRTIO_BLK_T_GET_ID:
+ block_cnt = VIRTIO_BLK_ID_BYTES;
+ disk_image__get_serial(bdev->disk,
+ (iov + 1)->iov_base, &block_cnt);
+ virtio_blk_complete(req, block_cnt);
+ break;
+ default:
+ pr_warning("request type %d", req_hdr->type);
+ block_cnt = -1;
+ break;
+ }
+}
+
+static void virtio_blk_do_io(struct kvm *kvm, struct virt_queue *vq, struct blk_dev *bdev)
+{
+ struct blk_dev_req *req;
+ u16 head;
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__pop(vq);
+ req = &bdev->reqs[head];
+ req->head = virt_queue__get_head_iov(vq, req->iov, &req->out,
+ &req->in, head, kvm);
+ req->vq = vq;
+
+ virtio_blk_do_io_request(kvm, req);
+ }
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct blk_dev *bdev = dev;
+
+ return ((u8 *)(&bdev->blk_config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1UL << VIRTIO_BLK_F_SEG_MAX
+ | 1UL << VIRTIO_BLK_F_FLUSH
+ | 1UL << VIRTIO_RING_F_EVENT_IDX
+ | 1UL << VIRTIO_RING_F_INDIRECT_DESC;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct blk_dev *bdev = dev;
+
+ bdev->features = features;
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct blk_dev *bdev = dev;
+ struct virt_queue *queue;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &bdev->vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+
+ vring_init(&queue->vring, VIRTIO_BLK_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
+
+ return 0;
+}
+
+static void *virtio_blk_thread(void *dev)
+{
+ struct blk_dev *bdev = dev;
+ u64 data;
+ int r;
+
+ while (1) {
+ r = read(bdev->io_efd, &data, sizeof(u64));
+ if (r < 0)
+ continue;
+ virtio_blk_do_io(bdev->kvm, &bdev->vqs[0], bdev);
+ }
+
+ pthread_exit(NULL);
+ return NULL;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct blk_dev *bdev = dev;
+ u64 data = 1;
+ int r;
+
+ r = write(bdev->io_efd, &data, sizeof(data));
+ if (r < 0)
+ return r;
+
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct blk_dev *bdev = dev;
+
+ return bdev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ /* FIXME: dynamic */
+ return VIRTIO_BLK_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static struct virtio_ops blk_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_vq = notify_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+};
+
+static int virtio_blk__init_one(struct kvm *kvm, struct disk_image *disk)
+{
+ struct blk_dev *bdev;
+ unsigned int i;
+
+ if (!disk)
+ return -EINVAL;
+
+ bdev = calloc(1, sizeof(struct blk_dev));
+ if (bdev == NULL)
+ return -ENOMEM;
+
+ *bdev = (struct blk_dev) {
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+ .disk = disk,
+ .blk_config = (struct virtio_blk_config) {
+ .capacity = disk->size / SECTOR_SIZE,
+ .seg_max = DISK_SEG_MAX,
+ },
+ .io_efd = eventfd(0, 0),
+ .kvm = kvm,
+ };
+
+ virtio_init(kvm, bdev, &bdev->vdev, &blk_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_BLK, VIRTIO_ID_BLOCK, PCI_CLASS_BLK);
+
+ list_add_tail(&bdev->list, &bdevs);
+
+ for (i = 0; i < ARRAY_SIZE(bdev->reqs); i++) {
+ bdev->reqs[i].bdev = bdev;
+ bdev->reqs[i].kvm = kvm;
+ }
+
+ disk_image__set_callback(bdev->disk, virtio_blk_complete);
+
+ pthread_create(&bdev->io_thread, NULL, virtio_blk_thread, bdev);
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-blk", "CONFIG_VIRTIO_BLK");
+
+ return 0;
+}
+
+static int virtio_blk__exit_one(struct kvm *kvm, struct blk_dev *bdev)
+{
+ list_del(&bdev->list);
+ free(bdev);
+
+ return 0;
+}
+
+int virtio_blk__init(struct kvm *kvm)
+{
+ int i, r = 0;
+
+ for (i = 0; i < kvm->nr_disks; i++) {
+ if (kvm->disks[i]->wwpn)
+ continue;
+ r = virtio_blk__init_one(kvm, kvm->disks[i]);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return 0;
+cleanup:
+ return virtio_blk__exit(kvm);
+}
+
+int virtio_blk__exit(struct kvm *kvm)
+{
+ while (!list_empty(&bdevs)) {
+ struct blk_dev *bdev;
+
+ bdev = list_first_entry(&bdevs, struct blk_dev, list);
+ virtio_blk__exit_one(kvm, bdev);
+ }
+
+ return 0;
+}
--- /dev/null
+#include "kvm/virtio-console.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/disk-image.h"
+#include "kvm/virtio.h"
+#include "kvm/ioport.h"
+#include "kvm/util.h"
+#include "kvm/term.h"
+#include "kvm/mutex.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/threadpool.h"
+#include "kvm/irq.h"
+#include "kvm/guest_compat.h"
+
+#include <linux/virtio_console.h>
+#include <linux/virtio_ring.h>
+#include <linux/virtio_blk.h>
+
+#include <sys/uio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <termios.h>
+#include <unistd.h>
+#include <fcntl.h>
+
+#define VIRTIO_CONSOLE_QUEUE_SIZE 128
+#define VIRTIO_CONSOLE_NUM_QUEUES 2
+#define VIRTIO_CONSOLE_RX_QUEUE 0
+#define VIRTIO_CONSOLE_TX_QUEUE 1
+
+struct con_dev {
+ pthread_mutex_t mutex;
+
+ struct virtio_device vdev;
+ struct virt_queue vqs[VIRTIO_CONSOLE_NUM_QUEUES];
+ struct virtio_console_config config;
+ u32 features;
+
+ struct thread_pool__job jobs[VIRTIO_CONSOLE_NUM_QUEUES];
+};
+
+static struct con_dev cdev = {
+ .mutex = PTHREAD_MUTEX_INITIALIZER,
+
+ .config = {
+ .cols = 80,
+ .rows = 24,
+ .max_nr_ports = 1,
+ },
+};
+
+static int compat_id = -1;
+
+/*
+ * Interrupts are injected for hvc0 only.
+ */
+static void virtio_console__inject_interrupt_callback(struct kvm *kvm, void *param)
+{
+ struct iovec iov[VIRTIO_CONSOLE_QUEUE_SIZE];
+ struct virt_queue *vq;
+ u16 out, in;
+ u16 head;
+ int len;
+
+ mutex_lock(&cdev.mutex);
+
+ vq = param;
+
+ if (term_readable(CONSOLE_VIRTIO, 0) && virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ len = term_getc_iov(CONSOLE_VIRTIO, iov, in, 0);
+ virt_queue__set_used_elem(vq, head, len);
+ cdev.vdev.ops->signal_vq(kvm, &cdev.vdev, vq - cdev.vqs);
+ }
+
+ mutex_unlock(&cdev.mutex);
+}
+
+void virtio_console__inject_interrupt(struct kvm *kvm)
+{
+ thread_pool__do_job(&cdev.jobs[VIRTIO_CONSOLE_RX_QUEUE]);
+}
+
+static void virtio_console_handle_callback(struct kvm *kvm, void *param)
+{
+ struct iovec iov[VIRTIO_CONSOLE_QUEUE_SIZE];
+ struct virt_queue *vq;
+ u16 out, in;
+ u16 head;
+ u32 len;
+
+ vq = param;
+
+ /*
+ * The current Linux implementation polls for the buffer
+ * to be used, rather than waiting for an interrupt.
+ * So there is no need to inject an interrupt for the tx path.
+ */
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ len = term_putc_iov(CONSOLE_VIRTIO, iov, out, 0);
+ virt_queue__set_used_elem(vq, head, len);
+ }
+
+}
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct con_dev *cdev = dev;
+
+ return ((u8 *)(&cdev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 0;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ /* Unused */
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct virt_queue *queue;
+ void *p;
+
+ BUG_ON(vq >= VIRTIO_CONSOLE_NUM_QUEUES);
+
+ compat__remove_message(compat_id);
+
+ queue = &cdev.vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+
+ vring_init(&queue->vring, VIRTIO_CONSOLE_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
+
+ if (vq == VIRTIO_CONSOLE_TX_QUEUE)
+ thread_pool__init_job(&cdev.jobs[vq], kvm, virtio_console_handle_callback, queue);
+ else if (vq == VIRTIO_CONSOLE_RX_QUEUE)
+ thread_pool__init_job(&cdev.jobs[vq], kvm, virtio_console__inject_interrupt_callback, queue);
+
+ return 0;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct con_dev *cdev = dev;
+
+ thread_pool__do_job(&cdev->jobs[vq]);
+
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct con_dev *cdev = dev;
+
+ return cdev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_CONSOLE_QUEUE_SIZE;
+}
+
+static struct virtio_ops con_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_vq = notify_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+};
+
+void virtio_console__init(struct kvm *kvm)
+{
+ virtio_init(kvm, &cdev, &cdev.vdev, &con_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_CONSOLE, VIRTIO_ID_CONSOLE, PCI_CLASS_CONSOLE);
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-console", "CONFIG_VIRTIO_CONSOLE");
+}
--- /dev/null
+#include <linux/virtio_ring.h>
+#include <linux/types.h>
+#include <sys/uio.h>
+#include <stdlib.h>
+
+#include "kvm/guest_compat.h"
+#include "kvm/barrier.h"
+#include "kvm/virtio.h"
+#include "kvm/virtio-pci.h"
+#include "kvm/virtio-mmio.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+
+struct vring_used_elem *virt_queue__set_used_elem(struct virt_queue *queue, u32 head, u32 len)
+{
+ struct vring_used_elem *used_elem;
+
+ used_elem = &queue->vring.used->ring[queue->vring.used->idx % queue->vring.num];
+ used_elem->id = head;
+ used_elem->len = len;
+
+ /*
+ * Use wmb to assure that used elem was updated with head and len.
+ * We need a wmb here since we can't advance idx unless we're ready
+ * to pass the used element to the guest.
+ */
+ wmb();
+ queue->vring.used->idx++;
+
+ /*
+ * Use wmb to assure used idx has been increased before we signal the guest.
+ * Without a wmb here the guest may ignore the queue since it won't see
+ * an updated idx.
+ */
+ wmb();
+
+ return used_elem;
+}
+
+/*
+ * Each buffer in the virtqueues is actually a chain of descriptors. This
+ * function returns the next descriptor in the chain, or vq->vring.num if we're
+ * at the end.
+ */
+static unsigned next_desc(struct vring_desc *desc,
+ unsigned int i, unsigned int max)
+{
+ unsigned int next;
+
+ /* If this descriptor says it doesn't chain, we're done. */
+ if (!(desc[i].flags & VRING_DESC_F_NEXT))
+ return max;
+
+ /* Check they're not leading us off end of descriptors. */
+ next = desc[i].next;
+ /* Make sure compiler knows to grab that: we don't want it changing! */
+ wmb();
+
+ return next;
+}
+
+u16 virt_queue__get_head_iov(struct virt_queue *vq, struct iovec iov[], u16 *out, u16 *in, u16 head, struct kvm *kvm)
+{
+ struct vring_desc *desc;
+ u16 idx;
+ u16 max;
+
+ idx = head;
+ *out = *in = 0;
+ max = vq->vring.num;
+ desc = vq->vring.desc;
+
+ if (desc[idx].flags & VRING_DESC_F_INDIRECT) {
+ max = desc[idx].len / sizeof(struct vring_desc);
+ desc = guest_flat_to_host(kvm, desc[idx].addr);
+ idx = 0;
+ }
+
+ do {
+ /* Grab the first descriptor, and check it's OK. */
+ iov[*out + *in].iov_len = desc[idx].len;
+ iov[*out + *in].iov_base = guest_flat_to_host(kvm, desc[idx].addr);
+ /* If this is an input descriptor, increment that count. */
+ if (desc[idx].flags & VRING_DESC_F_WRITE)
+ (*in)++;
+ else
+ (*out)++;
+ } while ((idx = next_desc(desc, idx, max)) != max);
+
+ return head;
+}
+
+u16 virt_queue__get_iov(struct virt_queue *vq, struct iovec iov[], u16 *out, u16 *in, struct kvm *kvm)
+{
+ u16 head;
+
+ head = virt_queue__pop(vq);
+
+ return virt_queue__get_head_iov(vq, iov, out, in, head, kvm);
+}
+
+/* in and out are relative to guest */
+u16 virt_queue__get_inout_iov(struct kvm *kvm, struct virt_queue *queue,
+ struct iovec in_iov[], struct iovec out_iov[],
+ u16 *in, u16 *out)
+{
+ struct vring_desc *desc;
+ u16 head, idx;
+
+ idx = head = virt_queue__pop(queue);
+ *out = *in = 0;
+ do {
+ desc = virt_queue__get_desc(queue, idx);
+ if (desc->flags & VRING_DESC_F_WRITE) {
+ in_iov[*in].iov_base = guest_flat_to_host(kvm,
+ desc->addr);
+ in_iov[*in].iov_len = desc->len;
+ (*in)++;
+ } else {
+ out_iov[*out].iov_base = guest_flat_to_host(kvm,
+ desc->addr);
+ out_iov[*out].iov_len = desc->len;
+ (*out)++;
+ }
+ if (desc->flags & VRING_DESC_F_NEXT)
+ idx = desc->next;
+ else
+ break;
+ } while (1);
+
+ return head;
+}
+
+int virtio__get_dev_specific_field(int offset, bool msix, u32 *config_off)
+{
+ if (msix) {
+ if (offset < 4)
+ return VIRTIO_PCI_O_MSIX;
+ else
+ offset -= 4;
+ }
+
+ *config_off = offset;
+
+ return VIRTIO_PCI_O_CONFIG;
+}
+
+bool virtio_queue__should_signal(struct virt_queue *vq)
+{
+ u16 old_idx, new_idx, event_idx;
+
+ old_idx = vq->last_used_signalled;
+ new_idx = vq->vring.used->idx;
+ event_idx = vring_used_event(&vq->vring);
+
+ if (vring_need_event(event_idx, new_idx, old_idx)) {
+ vq->last_used_signalled = new_idx;
+ return true;
+ }
+
+ return false;
+}
+
+int virtio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ struct virtio_ops *ops, enum virtio_trans trans,
+ int device_id, int subsys_id, int class)
+{
+ void *virtio;
+
+ switch (trans) {
+ case VIRTIO_PCI:
+ virtio = calloc(sizeof(struct virtio_pci), 1);
+ if (!virtio)
+ return -ENOMEM;
+ vdev->virtio = virtio;
+ vdev->ops = ops;
+ vdev->ops->signal_vq = virtio_pci__signal_vq;
+ vdev->ops->signal_config = virtio_pci__signal_config;
+ vdev->ops->init = virtio_pci__init;
+ vdev->ops->exit = virtio_pci__exit;
+ vdev->ops->init(kvm, dev, vdev, device_id, subsys_id, class);
+ break;
+ case VIRTIO_MMIO:
+ virtio = calloc(sizeof(struct virtio_mmio), 1);
+ if (!virtio)
+ return -ENOMEM;
+ vdev->virtio = virtio;
+ vdev->ops = ops;
+ vdev->ops->signal_vq = virtio_mmio_signal_vq;
+ vdev->ops->signal_config = virtio_mmio_signal_config;
+ vdev->ops->init = virtio_mmio_init;
+ vdev->ops->exit = virtio_mmio_exit;
+ vdev->ops->init(kvm, dev, vdev, device_id, subsys_id, class);
+ break;
+ default:
+ return -1;
+ };
+
+ return 0;
+}
+
+int virtio_compat_add_message(const char *device, const char *config)
+{
+ int len = 1024;
+ int compat_id;
+ char *title;
+ char *desc;
+
+ title = malloc(len);
+ if (!title)
+ return -ENOMEM;
+
+ desc = malloc(len);
+ if (!desc) {
+ free(title);
+ return -ENOMEM;
+ }
+
+ snprintf(title, len, "%s device was not detected.", device);
+ snprintf(desc, len, "While you have requested a %s device, "
+ "the guest kernel did not initialize it.\n"
+ "\tPlease make sure that the guest kernel was "
+ "compiled with %s=y enabled in .config.",
+ device, config);
+
+ compat_id = compat__add_message(title, desc);
+
+ free(desc);
+ free(title);
+
+ return compat_id;
+}
--- /dev/null
+#include "kvm/virtio-mmio.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/ioport.h"
+#include "kvm/virtio.h"
+#include "kvm/kvm.h"
+#include "kvm/irq.h"
+
+#include <linux/virtio_mmio.h>
+#include <string.h>
+
+static u32 virtio_mmio_io_space_blocks = KVM_VIRTIO_MMIO_AREA;
+
+static u32 virtio_mmio_get_io_space_block(u32 size)
+{
+ u32 block = virtio_mmio_io_space_blocks;
+ virtio_mmio_io_space_blocks += size;
+
+ return block;
+}
+
+static void virtio_mmio_ioevent_callback(struct kvm *kvm, void *param)
+{
+ struct virtio_mmio_ioevent_param *ioeventfd = param;
+ struct virtio_mmio *vmmio = ioeventfd->vdev->virtio;
+
+ ioeventfd->vdev->ops->notify_vq(kvm, vmmio->dev, ioeventfd->vq);
+}
+
+static int virtio_mmio_init_ioeventfd(struct kvm *kvm,
+ struct virtio_device *vdev, u32 vq)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ struct ioevent ioevent;
+ int err;
+
+ vmmio->ioeventfds[vq] = (struct virtio_mmio_ioevent_param) {
+ .vdev = vdev,
+ .vq = vq,
+ };
+
+ ioevent = (struct ioevent) {
+ .io_addr = vmmio->addr + VIRTIO_MMIO_QUEUE_NOTIFY,
+ .io_len = sizeof(u32),
+ .fn = virtio_mmio_ioevent_callback,
+ .fn_ptr = &vmmio->ioeventfds[vq],
+ .datamatch = vq,
+ .fn_kvm = kvm,
+ .fd = eventfd(0, 0),
+ };
+
+ if (vdev->use_vhost)
+ /*
+ * Vhost will poll the eventfd in host kernel side,
+ * no need to poll in userspace.
+ */
+ err = ioeventfd__add_event(&ioevent, true, false);
+ else
+ /* Need to poll in userspace. */
+ err = ioeventfd__add_event(&ioevent, true, true);
+ if (err)
+ return err;
+
+ if (vdev->ops->notify_vq_eventfd)
+ vdev->ops->notify_vq_eventfd(kvm, vmmio->dev, vq, ioevent.fd);
+
+ return 0;
+}
+
+int virtio_mmio_signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ vmmio->hdr.interrupt_state |= VIRTIO_MMIO_INT_VRING;
+ kvm__irq_trigger(vmmio->kvm, vmmio->irq);
+
+ return 0;
+}
+
+int virtio_mmio_signal_config(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+
+ vmmio->hdr.interrupt_state |= VIRTIO_MMIO_INT_CONFIG;
+ kvm__irq_trigger(vmmio->kvm, vmmio->irq);
+
+ return 0;
+}
+
+static void virtio_mmio_device_specific(u64 addr, u8 *data, u32 len,
+ u8 is_write, struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u32 i;
+
+ for (i = 0; i < len; i++) {
+ if (is_write)
+ vdev->ops->get_config(vmmio->kvm, vmmio->dev)[addr + i] =
+ *(u8 *)data + i;
+ else
+ data[i] = vdev->ops->get_config(vmmio->kvm,
+ vmmio->dev)[addr + i];
+ }
+}
+
+static void virtio_mmio_config_in(u64 addr, void *data, u32 len,
+ struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u32 val = 0;
+
+ switch (addr) {
+ case VIRTIO_MMIO_MAGIC_VALUE:
+ case VIRTIO_MMIO_VERSION:
+ case VIRTIO_MMIO_DEVICE_ID:
+ case VIRTIO_MMIO_VENDOR_ID:
+ case VIRTIO_MMIO_STATUS:
+ case VIRTIO_MMIO_INTERRUPT_STATUS:
+ ioport__write32(data, *(u32 *)(((void *)&vmmio->hdr) + addr));
+ break;
+ case VIRTIO_MMIO_HOST_FEATURES:
+ if (vmmio->hdr.host_features_sel == 0)
+ val = vdev->ops->get_host_features(vmmio->kvm,
+ vmmio->dev);
+ ioport__write32(data, val);
+ break;
+ case VIRTIO_MMIO_QUEUE_PFN:
+ val = vdev->ops->get_pfn_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel);
+ ioport__write32(data, val);
+ break;
+ case VIRTIO_MMIO_QUEUE_NUM_MAX:
+ val = vdev->ops->get_size_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel);
+ ioport__write32(data, val);
+ break;
+ default:
+ break;
+ }
+}
+
+static void virtio_mmio_config_out(u64 addr, void *data, u32 len,
+ struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u32 val = 0;
+
+ switch (addr) {
+ case VIRTIO_MMIO_HOST_FEATURES_SEL:
+ case VIRTIO_MMIO_GUEST_FEATURES_SEL:
+ case VIRTIO_MMIO_QUEUE_SEL:
+ case VIRTIO_MMIO_STATUS:
+ val = ioport__read32(data);
+ *(u32 *)(((void *)&vmmio->hdr) + addr) = val;
+ break;
+ case VIRTIO_MMIO_GUEST_FEATURES:
+ if (vmmio->hdr.guest_features_sel == 0) {
+ val = ioport__read32(data);
+ vdev->ops->set_guest_features(vmmio->kvm,
+ vmmio->dev, val);
+ }
+ break;
+ case VIRTIO_MMIO_GUEST_PAGE_SIZE:
+ val = ioport__read32(data);
+ vmmio->hdr.guest_page_size = val;
+ /* FIXME: set guest page size */
+ break;
+ case VIRTIO_MMIO_QUEUE_NUM:
+ val = ioport__read32(data);
+ vmmio->hdr.queue_num = val;
+ /* FIXME: set vq size */
+ vdev->ops->set_size_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel, val);
+ break;
+ case VIRTIO_MMIO_QUEUE_ALIGN:
+ val = ioport__read32(data);
+ vmmio->hdr.queue_align = val;
+ /* FIXME: set used ring alignment */
+ break;
+ case VIRTIO_MMIO_QUEUE_PFN:
+ val = ioport__read32(data);
+ virtio_mmio_init_ioeventfd(vmmio->kvm, vdev, vmmio->hdr.queue_sel);
+ vdev->ops->init_vq(vmmio->kvm, vmmio->dev,
+ vmmio->hdr.queue_sel, val);
+ break;
+ case VIRTIO_MMIO_QUEUE_NOTIFY:
+ val = ioport__read32(data);
+ vdev->ops->notify_vq(vmmio->kvm, vmmio->dev, val);
+ break;
+ case VIRTIO_MMIO_INTERRUPT_ACK:
+ val = ioport__read32(data);
+ vmmio->hdr.interrupt_state &= ~val;
+ break;
+ default:
+ break;
+ };
+}
+
+static void virtio_mmio_mmio_callback(u64 addr, u8 *data, u32 len,
+ u8 is_write, void *ptr)
+{
+ struct virtio_device *vdev = ptr;
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u32 offset = addr - vmmio->addr;
+
+ if (offset >= VIRTIO_MMIO_CONFIG) {
+ offset -= VIRTIO_MMIO_CONFIG;
+ virtio_mmio_device_specific(offset, data, len, is_write, ptr);
+ return;
+ }
+
+ if (is_write)
+ virtio_mmio_config_out(offset, data, len, ptr);
+ else
+ virtio_mmio_config_in(offset, data, len, ptr);
+}
+
+int virtio_mmio_init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ u8 device, pin, line;
+
+ vmmio->addr = virtio_mmio_get_io_space_block(VIRTIO_MMIO_IO_SIZE);
+ vmmio->kvm = kvm;
+ vmmio->dev = dev;
+
+ kvm__register_mmio(kvm, vmmio->addr, VIRTIO_MMIO_IO_SIZE,
+ false, virtio_mmio_mmio_callback, vdev);
+
+ vmmio->hdr = (struct virtio_mmio_hdr) {
+ .magic = {'v', 'i', 'r', 't'},
+ .version = 1,
+ .device_id = device_id - 0x1000 + 1,
+ .vendor_id = 0x4d564b4c , /* 'LKVM' */
+ .queue_num_max = 256,
+ };
+
+ if (irq__register_device(subsys_id, &device, &pin, &line) < 0)
+ return -1;
+ vmmio->irq = line;
+
+ /*
+ * Instantiate guest virtio-mmio devices using kernel command line
+ * (or module) parameter, e.g
+ *
+ * virtio_mmio.devices=0x200@0xd2000000:5,0x200@0xd2000200:6
+ */
+ pr_info("virtio-mmio.devices=0x%x@0x%x:%d\n", VIRTIO_MMIO_IO_SIZE, vmmio->addr, line);
+
+ return 0;
+}
+
+int virtio_mmio_exit(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_mmio *vmmio = vdev->virtio;
+ int i;
+
+ kvm__deregister_mmio(kvm, vmmio->addr);
+
+ for (i = 0; i < VIRTIO_MMIO_MAX_VQ; i++)
+ ioeventfd__del_event(vmmio->addr + VIRTIO_MMIO_QUEUE_NOTIFY, i);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/virtio-net.h"
+#include "kvm/virtio.h"
+#include "kvm/types.h"
+#include "kvm/mutex.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/irq.h"
+#include "kvm/uip.h"
+#include "kvm/guest_compat.h"
+
+#include <linux/vhost.h>
+#include <linux/virtio_net.h>
+#include <linux/if_tun.h>
+#include <linux/types.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+
+#include <unistd.h>
+#include <fcntl.h>
+
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/eventfd.h>
+
+#define VIRTIO_NET_QUEUE_SIZE 256
+#define VIRTIO_NET_NUM_QUEUES 2
+#define VIRTIO_NET_RX_QUEUE 0
+#define VIRTIO_NET_TX_QUEUE 1
+
+struct net_dev;
+
+extern struct kvm *kvm;
+
+struct net_dev_operations {
+ int (*rx)(struct iovec *iov, u16 in, struct net_dev *ndev);
+ int (*tx)(struct iovec *iov, u16 in, struct net_dev *ndev);
+};
+
+struct net_dev {
+ pthread_mutex_t mutex;
+ struct virtio_device vdev;
+ struct list_head list;
+
+ struct virt_queue vqs[VIRTIO_NET_NUM_QUEUES];
+ struct virtio_net_config config;
+ u32 features;
+
+ pthread_t io_rx_thread;
+ pthread_mutex_t io_rx_lock;
+ pthread_cond_t io_rx_cond;
+
+ pthread_t io_tx_thread;
+ pthread_mutex_t io_tx_lock;
+ pthread_cond_t io_tx_cond;
+
+ int vhost_fd;
+ int tap_fd;
+ char tap_name[IFNAMSIZ];
+
+ int mode;
+
+ struct uip_info info;
+ struct net_dev_operations *ops;
+ struct kvm *kvm;
+};
+
+static LIST_HEAD(ndevs);
+static int compat_id = -1;
+
+static void *virtio_net_rx_thread(void *p)
+{
+ struct iovec iov[VIRTIO_NET_QUEUE_SIZE];
+ struct virt_queue *vq;
+ struct kvm *kvm;
+ struct net_dev *ndev = p;
+ u16 out, in;
+ u16 head;
+ int len;
+
+ kvm = ndev->kvm;
+ vq = &ndev->vqs[VIRTIO_NET_RX_QUEUE];
+
+ while (1) {
+ mutex_lock(&ndev->io_rx_lock);
+ if (!virt_queue__available(vq))
+ pthread_cond_wait(&ndev->io_rx_cond, &ndev->io_rx_lock);
+ mutex_unlock(&ndev->io_rx_lock);
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ len = ndev->ops->rx(iov, in, ndev);
+ virt_queue__set_used_elem(vq, head, len);
+
+ /* We should interrupt guest right now, otherwise latency is huge. */
+ if (virtio_queue__should_signal(&ndev->vqs[VIRTIO_NET_RX_QUEUE]))
+ ndev->vdev.ops->signal_vq(kvm, &ndev->vdev,
+ VIRTIO_NET_RX_QUEUE);
+ }
+ }
+
+ pthread_exit(NULL);
+ return NULL;
+
+}
+
+static void *virtio_net_tx_thread(void *p)
+{
+ struct iovec iov[VIRTIO_NET_QUEUE_SIZE];
+ struct virt_queue *vq;
+ struct kvm *kvm;
+ struct net_dev *ndev = p;
+ u16 out, in;
+ u16 head;
+ int len;
+
+ kvm = ndev->kvm;
+ vq = &ndev->vqs[VIRTIO_NET_TX_QUEUE];
+
+ while (1) {
+ mutex_lock(&ndev->io_tx_lock);
+ if (!virt_queue__available(vq))
+ pthread_cond_wait(&ndev->io_tx_cond, &ndev->io_tx_lock);
+ mutex_unlock(&ndev->io_tx_lock);
+
+ while (virt_queue__available(vq)) {
+ head = virt_queue__get_iov(vq, iov, &out, &in, kvm);
+ len = ndev->ops->tx(iov, out, ndev);
+ virt_queue__set_used_elem(vq, head, len);
+ }
+
+ if (virtio_queue__should_signal(&ndev->vqs[VIRTIO_NET_TX_QUEUE]))
+ ndev->vdev.ops->signal_vq(kvm, &ndev->vdev, VIRTIO_NET_TX_QUEUE);
+ }
+
+ pthread_exit(NULL);
+
+ return NULL;
+
+}
+
+static void virtio_net_handle_callback(struct kvm *kvm, struct net_dev *ndev, int queue)
+{
+ switch (queue) {
+ case VIRTIO_NET_TX_QUEUE:
+ mutex_lock(&ndev->io_tx_lock);
+ pthread_cond_signal(&ndev->io_tx_cond);
+ mutex_unlock(&ndev->io_tx_lock);
+ break;
+ case VIRTIO_NET_RX_QUEUE:
+ mutex_lock(&ndev->io_rx_lock);
+ pthread_cond_signal(&ndev->io_rx_cond);
+ mutex_unlock(&ndev->io_rx_lock);
+ break;
+ default:
+ pr_warning("Unknown queue index %u", queue);
+ }
+}
+
+static bool virtio_net__tap_init(const struct virtio_net_params *params,
+ struct net_dev *ndev)
+{
+ int sock = socket(AF_INET, SOCK_STREAM, 0);
+ int pid, status, offload, hdr_len;
+ struct sockaddr_in sin = {0};
+ struct ifreq ifr;
+
+ /* Did the user already gave us the FD? */
+ if (params->fd) {
+ ndev->tap_fd = params->fd;
+ return 1;
+ }
+
+ ndev->tap_fd = open("/dev/net/tun", O_RDWR);
+ if (ndev->tap_fd < 0) {
+ pr_warning("Unable to open /dev/net/tun");
+ goto fail;
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
+ if (ioctl(ndev->tap_fd, TUNSETIFF, &ifr) < 0) {
+ pr_warning("Config tap device error. Are you root?");
+ goto fail;
+ }
+
+ strncpy(ndev->tap_name, ifr.ifr_name, sizeof(ndev->tap_name));
+
+ if (ioctl(ndev->tap_fd, TUNSETNOCSUM, 1) < 0) {
+ pr_warning("Config tap device TUNSETNOCSUM error");
+ goto fail;
+ }
+
+ hdr_len = sizeof(struct virtio_net_hdr);
+ if (ioctl(ndev->tap_fd, TUNSETVNETHDRSZ, &hdr_len) < 0)
+ pr_warning("Config tap device TUNSETVNETHDRSZ error");
+
+ offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_UFO;
+ if (ioctl(ndev->tap_fd, TUNSETOFFLOAD, offload) < 0) {
+ pr_warning("Config tap device TUNSETOFFLOAD error");
+ goto fail;
+ }
+
+ if (strcmp(params->script, "none")) {
+ pid = fork();
+ if (pid == 0) {
+ execl(params->script, params->script, ndev->tap_name, NULL);
+ _exit(1);
+ } else {
+ waitpid(pid, &status, 0);
+ if (WIFEXITED(status) && WEXITSTATUS(status) != 0) {
+ pr_warning("Fail to setup tap by %s", params->script);
+ goto fail;
+ }
+ }
+ } else {
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, ndev->tap_name, sizeof(ndev->tap_name));
+ sin.sin_addr.s_addr = inet_addr(params->host_ip);
+ memcpy(&(ifr.ifr_addr), &sin, sizeof(ifr.ifr_addr));
+ ifr.ifr_addr.sa_family = AF_INET;
+ if (ioctl(sock, SIOCSIFADDR, &ifr) < 0) {
+ pr_warning("Could not set ip address on tap device");
+ goto fail;
+ }
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy(ifr.ifr_name, ndev->tap_name, sizeof(ndev->tap_name));
+ ioctl(sock, SIOCGIFFLAGS, &ifr);
+ ifr.ifr_flags |= IFF_UP | IFF_RUNNING;
+ if (ioctl(sock, SIOCSIFFLAGS, &ifr) < 0)
+ pr_warning("Could not bring tap device up");
+
+ close(sock);
+
+ return 1;
+
+fail:
+ if (sock >= 0)
+ close(sock);
+ if (ndev->tap_fd >= 0)
+ close(ndev->tap_fd);
+
+ return 0;
+}
+
+static void virtio_net__io_thread_init(struct kvm *kvm, struct net_dev *ndev)
+{
+ pthread_mutex_init(&ndev->io_tx_lock, NULL);
+ pthread_mutex_init(&ndev->io_rx_lock, NULL);
+
+ pthread_cond_init(&ndev->io_tx_cond, NULL);
+ pthread_cond_init(&ndev->io_rx_cond, NULL);
+
+ pthread_create(&ndev->io_tx_thread, NULL, virtio_net_tx_thread, ndev);
+ pthread_create(&ndev->io_rx_thread, NULL, virtio_net_rx_thread, ndev);
+}
+
+static inline int tap_ops_tx(struct iovec *iov, u16 out, struct net_dev *ndev)
+{
+ return writev(ndev->tap_fd, iov, out);
+}
+
+static inline int tap_ops_rx(struct iovec *iov, u16 in, struct net_dev *ndev)
+{
+ return readv(ndev->tap_fd, iov, in);
+}
+
+static inline int uip_ops_tx(struct iovec *iov, u16 out, struct net_dev *ndev)
+{
+ return uip_tx(iov, out, &ndev->info);
+}
+
+static inline int uip_ops_rx(struct iovec *iov, u16 in, struct net_dev *ndev)
+{
+ return uip_rx(iov, in, &ndev->info);
+}
+
+static struct net_dev_operations tap_ops = {
+ .rx = tap_ops_rx,
+ .tx = tap_ops_tx,
+};
+
+static struct net_dev_operations uip_ops = {
+ .rx = uip_ops_rx,
+ .tx = uip_ops_tx,
+};
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct net_dev *ndev = dev;
+
+ return ((u8 *)(&ndev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1UL << VIRTIO_NET_F_MAC
+ | 1UL << VIRTIO_NET_F_CSUM
+ | 1UL << VIRTIO_NET_F_HOST_UFO
+ | 1UL << VIRTIO_NET_F_HOST_TSO4
+ | 1UL << VIRTIO_NET_F_HOST_TSO6
+ | 1UL << VIRTIO_NET_F_GUEST_UFO
+ | 1UL << VIRTIO_NET_F_GUEST_TSO4
+ | 1UL << VIRTIO_NET_F_GUEST_TSO6
+ | 1UL << VIRTIO_RING_F_EVENT_IDX
+ | 1UL << VIRTIO_RING_F_INDIRECT_DESC;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct net_dev *ndev = dev;
+
+ ndev->features = features;
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct vhost_vring_state state = { .index = vq };
+ struct vhost_vring_addr addr;
+ struct net_dev *ndev = dev;
+ struct virt_queue *queue;
+ void *p;
+ int r;
+
+ compat__remove_message(compat_id);
+
+ queue = &ndev->vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+
+ /* FIXME: respect pci and mmio vring alignment */
+ vring_init(&queue->vring, VIRTIO_NET_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
+
+ if (ndev->vhost_fd == 0)
+ return 0;
+
+ state.num = queue->vring.num;
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_NUM, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_NUM failed");
+ state.num = 0;
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_BASE, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_BASE failed");
+
+ addr = (struct vhost_vring_addr) {
+ .index = vq,
+ .desc_user_addr = (u64)(unsigned long)queue->vring.desc,
+ .avail_user_addr = (u64)(unsigned long)queue->vring.avail,
+ .used_user_addr = (u64)(unsigned long)queue->vring.used,
+ };
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_ADDR, &addr);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_ADDR failed");
+
+ return 0;
+}
+
+static void notify_vq_gsi(struct kvm *kvm, void *dev, u32 vq, u32 gsi)
+{
+ struct net_dev *ndev = dev;
+ struct kvm_irqfd irq;
+ struct vhost_vring_file file;
+ int r;
+
+ if (ndev->vhost_fd == 0)
+ return;
+
+ irq = (struct kvm_irqfd) {
+ .gsi = gsi,
+ .fd = eventfd(0, 0),
+ };
+ file = (struct vhost_vring_file) {
+ .index = vq,
+ .fd = irq.fd,
+ };
+
+ r = ioctl(kvm->vm_fd, KVM_IRQFD, &irq);
+ if (r < 0)
+ die_perror("KVM_IRQFD failed");
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_CALL, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_CALL failed");
+ file.fd = ndev->tap_fd;
+ r = ioctl(ndev->vhost_fd, VHOST_NET_SET_BACKEND, &file);
+ if (r != 0)
+ die("VHOST_NET_SET_BACKEND failed %d", errno);
+
+}
+
+static void notify_vq_eventfd(struct kvm *kvm, void *dev, u32 vq, u32 efd)
+{
+ struct net_dev *ndev = dev;
+ struct vhost_vring_file file = {
+ .index = vq,
+ .fd = efd,
+ };
+ int r;
+
+ if (ndev->vhost_fd == 0)
+ return;
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_VRING_KICK, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_KICK failed");
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct net_dev *ndev = dev;
+
+ virtio_net_handle_callback(kvm, ndev, vq);
+
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct net_dev *ndev = dev;
+
+ return ndev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ /* FIXME: dynamic */
+ return VIRTIO_NET_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ /* FIXME: dynamic */
+ return size;
+}
+
+static struct virtio_ops net_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .notify_vq = notify_vq,
+ .notify_vq_gsi = notify_vq_gsi,
+ .notify_vq_eventfd = notify_vq_eventfd,
+};
+
+static void virtio_net__vhost_init(struct kvm *kvm, struct net_dev *ndev)
+{
+ u64 features = 1UL << VIRTIO_RING_F_EVENT_IDX;
+ struct vhost_memory *mem;
+ int r;
+
+ ndev->vhost_fd = open("/dev/vhost-net", O_RDWR);
+ if (ndev->vhost_fd < 0)
+ die_perror("Failed openning vhost-net device");
+
+ mem = calloc(1, sizeof(*mem) + sizeof(struct vhost_memory_region));
+ if (mem == NULL)
+ die("Failed allocating memory for vhost memory map");
+
+ mem->nregions = 1;
+ mem->regions[0] = (struct vhost_memory_region) {
+ .guest_phys_addr = 0,
+ .memory_size = kvm->ram_size,
+ .userspace_addr = (unsigned long)kvm->ram_start,
+ };
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_OWNER);
+ if (r != 0)
+ die_perror("VHOST_SET_OWNER failed");
+
+ r = ioctl(ndev->vhost_fd, VHOST_SET_FEATURES, &features);
+ if (r != 0)
+ die_perror("VHOST_SET_FEATURES failed");
+ r = ioctl(ndev->vhost_fd, VHOST_SET_MEM_TABLE, mem);
+ if (r != 0)
+ die_perror("VHOST_SET_MEM_TABLE failed");
+
+ ndev->vdev.use_vhost = true;
+
+ free(mem);
+}
+
+void virtio_net__init(const struct virtio_net_params *params)
+{
+ int i;
+ struct net_dev *ndev;
+
+ if (!params)
+ return;
+
+ ndev = calloc(1, sizeof(struct net_dev));
+ if (ndev == NULL)
+ die("Failed allocating ndev");
+
+ list_add_tail(&ndev->list, &ndevs);
+
+ ndev->kvm = params->kvm;
+
+ mutex_init(&ndev->mutex);
+ ndev->config.status = VIRTIO_NET_S_LINK_UP;
+
+ for (i = 0 ; i < 6 ; i++) {
+ ndev->config.mac[i] = params->guest_mac[i];
+ ndev->info.guest_mac.addr[i] = params->guest_mac[i];
+ ndev->info.host_mac.addr[i] = params->host_mac[i];
+ }
+
+ ndev->mode = params->mode;
+ if (ndev->mode == NET_MODE_TAP) {
+ if (!virtio_net__tap_init(params, ndev))
+ die_perror("You have requested a TAP device, but creation of one has failed because");
+ ndev->ops = &tap_ops;
+ } else {
+ ndev->info.host_ip = ntohl(inet_addr(params->host_ip));
+ ndev->info.guest_ip = ntohl(inet_addr(params->guest_ip));
+ ndev->info.guest_netmask = ntohl(inet_addr("255.255.255.0"));
+ ndev->info.buf_nr = 20,
+ uip_init(&ndev->info);
+ ndev->ops = &uip_ops;
+ }
+
+ if (params->trans && strcmp(params->trans, "mmio") == 0)
+ virtio_init(kvm, ndev, &ndev->vdev, &net_dev_virtio_ops,
+ VIRTIO_MMIO, PCI_DEVICE_ID_VIRTIO_NET, VIRTIO_ID_NET, PCI_CLASS_NET);
+ else
+ virtio_init(kvm, ndev, &ndev->vdev, &net_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_NET, VIRTIO_ID_NET, PCI_CLASS_NET);
+
+ if (params->vhost)
+ virtio_net__vhost_init(params->kvm, ndev);
+ else
+ virtio_net__io_thread_init(params->kvm, ndev);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-net", "CONFIG_VIRTIO_NET");
+}
--- /dev/null
+#include "kvm/virtio-pci.h"
+
+#include "kvm/ioport.h"
+#include "kvm/kvm.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/irq.h"
+#include "kvm/virtio.h"
+#include "kvm/ioeventfd.h"
+
+#include <sys/ioctl.h>
+#include <linux/virtio_pci.h>
+#include <linux/byteorder.h>
+#include <string.h>
+
+static void virtio_pci__ioevent_callback(struct kvm *kvm, void *param)
+{
+ struct virtio_pci_ioevent_param *ioeventfd = param;
+ struct virtio_pci *vpci = ioeventfd->vdev->virtio;
+
+ ioeventfd->vdev->ops->notify_vq(kvm, vpci->dev, ioeventfd->vq);
+}
+
+static int virtio_pci__init_ioeventfd(struct kvm *kvm, struct virtio_device *vdev, u32 vq)
+{
+ struct ioevent ioevent;
+ struct virtio_pci *vpci = vdev->virtio;
+ int r;
+
+ vpci->ioeventfds[vq] = (struct virtio_pci_ioevent_param) {
+ .vdev = vdev,
+ .vq = vq,
+ };
+
+ ioevent = (struct ioevent) {
+ .io_addr = vpci->base_addr + VIRTIO_PCI_QUEUE_NOTIFY,
+ .io_len = sizeof(u16),
+ .fn = virtio_pci__ioevent_callback,
+ .fn_ptr = &vpci->ioeventfds[vq],
+ .datamatch = vq,
+ .fn_kvm = kvm,
+ .fd = eventfd(0, 0),
+ };
+
+ if (vdev->use_vhost)
+ /*
+ * Vhost will poll the eventfd in host kernel side,
+ * no need to poll in userspace.
+ */
+ r = ioeventfd__add_event(&ioevent, true, false);
+ else
+ /* Need to poll in userspace. */
+ r = ioeventfd__add_event(&ioevent, true, true);
+ if (r)
+ return r;
+
+ if (vdev->ops->notify_vq_eventfd)
+ vdev->ops->notify_vq_eventfd(kvm, vpci->dev, vq, ioevent.fd);
+
+ return 0;
+}
+
+static inline bool virtio_pci__msix_enabled(struct virtio_pci *vpci)
+{
+ return vpci->pci_hdr.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_ENABLE);
+}
+
+static bool virtio_pci__specific_io_in(struct kvm *kvm, struct virtio_device *vdev, u16 port,
+ void *data, int size, int offset)
+{
+ u32 config_offset;
+ struct virtio_pci *vpci = vdev->virtio;
+ int type = virtio__get_dev_specific_field(offset - 20,
+ virtio_pci__msix_enabled(vpci),
+ &config_offset);
+ if (type == VIRTIO_PCI_O_MSIX) {
+ switch (offset) {
+ case VIRTIO_MSI_CONFIG_VECTOR:
+ ioport__write16(data, vpci->config_vector);
+ break;
+ case VIRTIO_MSI_QUEUE_VECTOR:
+ ioport__write16(data, vpci->vq_vector[vpci->queue_selector]);
+ break;
+ };
+
+ return true;
+ } else if (type == VIRTIO_PCI_O_CONFIG) {
+ u8 cfg;
+
+ cfg = vdev->ops->get_config(kvm, vpci->dev)[config_offset];
+ ioport__write8(data, cfg);
+ return true;
+ }
+
+ return false;
+}
+
+static bool virtio_pci__io_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ unsigned long offset;
+ bool ret = true;
+ struct virtio_device *vdev;
+ struct virtio_pci *vpci;
+ u32 val;
+
+ vdev = ioport->priv;
+ vpci = vdev->virtio;
+ offset = port - vpci->base_addr;
+
+ switch (offset) {
+ case VIRTIO_PCI_HOST_FEATURES:
+ val = vdev->ops->get_host_features(kvm, vpci->dev);
+ ioport__write32(data, val);
+ break;
+ case VIRTIO_PCI_QUEUE_PFN:
+ val = vdev->ops->get_pfn_vq(kvm, vpci->dev, vpci->queue_selector);
+ ioport__write32(data, val);
+ break;
+ case VIRTIO_PCI_QUEUE_NUM:
+ val = vdev->ops->get_size_vq(kvm, vpci->dev, vpci->queue_selector);
+ ioport__write16(data, val);
+ break;
+ case VIRTIO_PCI_STATUS:
+ ioport__write8(data, vpci->status);
+ break;
+ case VIRTIO_PCI_ISR:
+ ioport__write8(data, vpci->isr);
+ kvm__irq_line(kvm, vpci->pci_hdr.irq_line, VIRTIO_IRQ_LOW);
+ vpci->isr = VIRTIO_IRQ_LOW;
+ break;
+ default:
+ ret = virtio_pci__specific_io_in(kvm, vdev, port, data, size, offset);
+ break;
+ };
+
+ return ret;
+}
+
+static bool virtio_pci__specific_io_out(struct kvm *kvm, struct virtio_device *vdev, u16 port,
+ void *data, int size, int offset)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ u32 config_offset, gsi, vec;
+ int type = virtio__get_dev_specific_field(offset - 20, virtio_pci__msix_enabled(vpci),
+ &config_offset);
+ if (type == VIRTIO_PCI_O_MSIX) {
+ switch (offset) {
+ case VIRTIO_MSI_CONFIG_VECTOR:
+ vec = vpci->config_vector = ioport__read16(data);
+
+ gsi = irq__add_msix_route(kvm, &vpci->msix_table[vec].msg);
+
+ vpci->config_gsi = gsi;
+ break;
+ case VIRTIO_MSI_QUEUE_VECTOR:
+ vec = vpci->vq_vector[vpci->queue_selector] = ioport__read16(data);
+
+ gsi = irq__add_msix_route(kvm, &vpci->msix_table[vec].msg);
+ vpci->gsis[vpci->queue_selector] = gsi;
+ if (vdev->ops->notify_vq_gsi)
+ vdev->ops->notify_vq_gsi(kvm, vpci->dev,
+ vpci->queue_selector, gsi);
+ break;
+ };
+
+ return true;
+ } else if (type == VIRTIO_PCI_O_CONFIG) {
+ vdev->ops->get_config(kvm, vpci->dev)[config_offset] = *(u8 *)data;
+
+ return true;
+ }
+
+ return false;
+}
+
+static bool virtio_pci__io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ unsigned long offset;
+ bool ret = true;
+ struct virtio_device *vdev;
+ struct virtio_pci *vpci;
+ u32 val;
+
+ vdev = ioport->priv;
+ vpci = vdev->virtio;
+ offset = port - vpci->base_addr;
+
+ switch (offset) {
+ case VIRTIO_PCI_GUEST_FEATURES:
+ val = ioport__read32(data);
+ vdev->ops->set_guest_features(kvm, vpci->dev, val);
+ break;
+ case VIRTIO_PCI_QUEUE_PFN:
+ val = ioport__read32(data);
+ virtio_pci__init_ioeventfd(kvm, vdev, vpci->queue_selector);
+ vdev->ops->init_vq(kvm, vpci->dev, vpci->queue_selector, val);
+ break;
+ case VIRTIO_PCI_QUEUE_SEL:
+ vpci->queue_selector = ioport__read16(data);
+ break;
+ case VIRTIO_PCI_QUEUE_NOTIFY:
+ val = ioport__read16(data);
+ vdev->ops->notify_vq(kvm, vpci->dev, val);
+ break;
+ case VIRTIO_PCI_STATUS:
+ vpci->status = ioport__read8(data);
+ break;
+ default:
+ ret = virtio_pci__specific_io_out(kvm, vdev, port, data, size, offset);
+ break;
+ };
+
+ return ret;
+}
+
+static struct ioport_operations virtio_pci__io_ops = {
+ .io_in = virtio_pci__io_in,
+ .io_out = virtio_pci__io_out,
+};
+
+static void virtio_pci__mmio_callback(u64 addr, u8 *data, u32 len, u8 is_write, void *ptr)
+{
+ struct virtio_pci *vpci = ptr;
+ void *table;
+ u32 offset;
+
+ if (addr > vpci->msix_io_block + PCI_IO_SIZE) {
+ table = &vpci->msix_pba;
+ offset = vpci->msix_io_block + PCI_IO_SIZE;
+ } else {
+ table = &vpci->msix_table;
+ offset = vpci->msix_io_block;
+ }
+
+ if (is_write)
+ memcpy(table + addr - offset, data, len);
+ else
+ memcpy(data, table + addr - offset, len);
+}
+
+static void virtio_pci__signal_msi(struct kvm *kvm, struct virtio_pci *vpci, int vec)
+{
+ struct kvm_msi msi = {
+ .address_lo = vpci->msix_table[vec].msg.address_lo,
+ .address_hi = vpci->msix_table[vec].msg.address_hi,
+ .data = vpci->msix_table[vec].msg.data,
+ };
+
+ ioctl(kvm->vm_fd, KVM_SIGNAL_MSI, &msi);
+}
+
+int virtio_pci__signal_vq(struct kvm *kvm, struct virtio_device *vdev, u32 vq)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ int tbl = vpci->vq_vector[vq];
+
+ if (virtio_pci__msix_enabled(vpci)) {
+ if (vpci->pci_hdr.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_MASKALL) ||
+ vpci->msix_table[tbl].ctrl & cpu_to_le16(PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
+
+ vpci->msix_pba |= 1 << tbl;
+ return 0;
+ }
+
+ if (vpci->features & VIRTIO_PCI_F_SIGNAL_MSI)
+ virtio_pci__signal_msi(kvm, vpci, vpci->vq_vector[vq]);
+ else
+ kvm__irq_trigger(kvm, vpci->gsis[vq]);
+ } else {
+ vpci->isr = VIRTIO_IRQ_HIGH;
+ kvm__irq_trigger(kvm, vpci->pci_hdr.irq_line);
+ }
+ return 0;
+}
+
+int virtio_pci__signal_config(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ int tbl = vpci->config_vector;
+
+ if (virtio_pci__msix_enabled(vpci)) {
+ if (vpci->pci_hdr.msix.ctrl & cpu_to_le16(PCI_MSIX_FLAGS_MASKALL) ||
+ vpci->msix_table[tbl].ctrl & cpu_to_le16(PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
+
+ vpci->msix_pba |= 1 << tbl;
+ return 0;
+ }
+
+ if (vpci->features & VIRTIO_PCI_F_SIGNAL_MSI)
+ virtio_pci__signal_msi(kvm, vpci, vpci->vq_vector[vpci->config_vector]);
+ else
+ kvm__irq_trigger(kvm, vpci->config_gsi);
+ } else {
+ vpci->isr = VIRTIO_PCI_ISR_CONFIG;
+ kvm__irq_trigger(kvm, vpci->pci_hdr.irq_line);
+ }
+
+ return 0;
+}
+
+int virtio_pci__init(struct kvm *kvm, void *dev, struct virtio_device *vdev,
+ int device_id, int subsys_id, int class)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ u8 pin, line, ndev;
+ int r;
+
+ vpci->dev = dev;
+ vpci->msix_io_block = pci_get_io_space_block(PCI_IO_SIZE * 2);
+
+ r = ioport__register(IOPORT_EMPTY, &virtio_pci__io_ops, IOPORT_SIZE, vdev);
+ if (r < 0)
+ return r;
+
+ vpci->base_addr = (u16)r;
+ r = kvm__register_mmio(kvm, vpci->msix_io_block, PCI_IO_SIZE, false,
+ virtio_pci__mmio_callback, vpci);
+ if (r < 0)
+ goto free_ioport;
+
+ vpci->pci_hdr = (struct pci_device_header) {
+ .vendor_id = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET),
+ .device_id = cpu_to_le16(device_id),
+ .header_type = PCI_HEADER_TYPE_NORMAL,
+ .revision_id = 0,
+ .class[0] = class & 0xff,
+ .class[1] = (class >> 8) & 0xff,
+ .class[2] = (class >> 16) & 0xff,
+ .subsys_vendor_id = cpu_to_le16(PCI_SUBSYSTEM_VENDOR_ID_REDHAT_QUMRANET),
+ .subsys_id = cpu_to_le16(subsys_id),
+ .bar[0] = cpu_to_le32(vpci->base_addr
+ | PCI_BASE_ADDRESS_SPACE_IO),
+ .bar[1] = cpu_to_le32(vpci->msix_io_block
+ | PCI_BASE_ADDRESS_SPACE_MEMORY),
+ .status = cpu_to_le16(PCI_STATUS_CAP_LIST),
+ .capabilities = (void *)&vpci->pci_hdr.msix - (void *)&vpci->pci_hdr,
+ .bar_size[0] = IOPORT_SIZE,
+ .bar_size[1] = PCI_IO_SIZE,
+ .bar_size[3] = PCI_IO_SIZE,
+ };
+
+ vpci->pci_hdr.msix.cap = PCI_CAP_ID_MSIX;
+ vpci->pci_hdr.msix.next = 0;
+ /*
+ * We at most have VIRTIO_PCI_MAX_VQ entries for virt queue,
+ * VIRTIO_PCI_MAX_CONFIG entries for config.
+ *
+ * To quote the PCI spec:
+ *
+ * System software reads this field to determine the
+ * MSI-X Table Size N, which is encoded as N-1.
+ * For example, a returned value of "00000000011"
+ * indicates a table size of 4.
+ */
+ vpci->pci_hdr.msix.ctrl = cpu_to_le16(VIRTIO_PCI_MAX_VQ + VIRTIO_PCI_MAX_CONFIG - 1);
+
+ /*
+ * Both table and PBA could be mapped on the same BAR, but for now
+ * we're not in short of BARs
+ */
+ vpci->pci_hdr.msix.table_offset = cpu_to_le32(1); /* Use BAR 1 */
+ vpci->pci_hdr.msix.pba_offset = cpu_to_le32(1 | PCI_IO_SIZE); /* Use BAR 3 */
+ vpci->config_vector = 0;
+
+ r = irq__register_device(subsys_id, &ndev, &pin, &line);
+ if (r < 0)
+ goto free_mmio;
+
+ if (kvm__supports_extension(kvm, KVM_CAP_SIGNAL_MSI))
+ vpci->features |= VIRTIO_PCI_F_SIGNAL_MSI;
+
+ vpci->pci_hdr.irq_pin = pin;
+ vpci->pci_hdr.irq_line = line;
+ r = pci__register(&vpci->pci_hdr, ndev);
+ if (r < 0)
+ goto free_ioport;
+
+ return 0;
+
+free_mmio:
+ kvm__deregister_mmio(kvm, vpci->msix_io_block);
+free_ioport:
+ ioport__unregister(vpci->base_addr);
+ return r;
+}
+
+int virtio_pci__exit(struct kvm *kvm, struct virtio_device *vdev)
+{
+ struct virtio_pci *vpci = vdev->virtio;
+ int i;
+
+ kvm__deregister_mmio(kvm, vpci->msix_io_block);
+ ioport__unregister(vpci->base_addr);
+
+ for (i = 0; i < VIRTIO_PCI_MAX_VQ; i++)
+ ioeventfd__del_event(vpci->base_addr + VIRTIO_PCI_QUEUE_NOTIFY, i);
+
+ return 0;
+}
--- /dev/null
+#include "kvm/virtio-rng.h"
+
+#include "kvm/virtio-pci-dev.h"
+
+#include "kvm/virtio.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+#include "kvm/threadpool.h"
+#include "kvm/guest_compat.h"
+
+#include <linux/virtio_ring.h>
+#include <linux/virtio_rng.h>
+
+#include <linux/list.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <pthread.h>
+#include <linux/kernel.h>
+
+#define NUM_VIRT_QUEUES 1
+#define VIRTIO_RNG_QUEUE_SIZE 128
+
+struct rng_dev_job {
+ struct virt_queue *vq;
+ struct rng_dev *rdev;
+ struct thread_pool__job job_id;
+};
+
+struct rng_dev {
+ struct list_head list;
+ struct virtio_device vdev;
+
+ int fd;
+
+ /* virtio queue */
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct rng_dev_job jobs[NUM_VIRT_QUEUES];
+};
+
+static LIST_HEAD(rdevs);
+static int compat_id = -1;
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ /* Unused */
+ return 0;
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ /* Unused */
+ return 0;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ /* Unused */
+}
+
+static bool virtio_rng_do_io_request(struct kvm *kvm, struct rng_dev *rdev, struct virt_queue *queue)
+{
+ struct iovec iov[VIRTIO_RNG_QUEUE_SIZE];
+ unsigned int len = 0;
+ u16 out, in, head;
+
+ head = virt_queue__get_iov(queue, iov, &out, &in, kvm);
+ len = readv(rdev->fd, iov, in);
+
+ virt_queue__set_used_elem(queue, head, len);
+
+ return true;
+}
+
+static void virtio_rng_do_io(struct kvm *kvm, void *param)
+{
+ struct rng_dev_job *job = param;
+ struct virt_queue *vq = job->vq;
+ struct rng_dev *rdev = job->rdev;
+
+ while (virt_queue__available(vq))
+ virtio_rng_do_io_request(kvm, rdev, vq);
+
+ rdev->vdev.ops->signal_vq(kvm, &rdev->vdev, vq - rdev->vqs);
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct rng_dev *rdev = dev;
+ struct virt_queue *queue;
+ struct rng_dev_job *job;
+ void *p;
+
+ compat__remove_message(compat_id);
+
+ queue = &rdev->vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+
+ job = &rdev->jobs[vq];
+
+ vring_init(&queue->vring, VIRTIO_RNG_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
+
+ *job = (struct rng_dev_job) {
+ .vq = queue,
+ .rdev = rdev,
+ };
+
+ thread_pool__init_job(&job->job_id, kvm, virtio_rng_do_io, job);
+
+ return 0;
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct rng_dev *rdev = dev;
+
+ thread_pool__do_job(&rdev->jobs[vq].job_id);
+
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct rng_dev *rdev = dev;
+
+ return rdev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_RNG_QUEUE_SIZE;
+}
+
+static struct virtio_ops rng_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .notify_vq = notify_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+};
+
+int virtio_rng__init(struct kvm *kvm)
+{
+ struct rng_dev *rdev;
+ int r;
+
+ rdev = malloc(sizeof(*rdev));
+ if (rdev == NULL)
+ return -ENOMEM;
+
+ rdev->fd = open("/dev/urandom", O_RDONLY);
+ if (rdev->fd < 0) {
+ r = rdev->fd;
+ goto cleanup;
+ }
+
+ r = virtio_init(kvm, rdev, &rdev->vdev, &rng_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_RNG, VIRTIO_ID_RNG, PCI_CLASS_RNG);
+ if (r < 0)
+ goto cleanup;
+
+ list_add_tail(&rdev->list, &rdevs);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-rng", "CONFIG_HW_RANDOM_VIRTIO");
+ return 0;
+cleanup:
+ close(rdev->fd);
+ free(rdev);
+
+ return r;
+}
+
+int virtio_rng__exit(struct kvm *kvm)
+{
+ struct rng_dev *rdev, *tmp;
+
+ list_for_each_entry_safe(rdev, tmp, &rdevs, list) {
+ list_del(&rdev->list);
+ rdev->vdev.ops->exit(kvm, &rdev->vdev);
+ free(rdev);
+ }
+
+ return 0;
+}
--- /dev/null
+#include "kvm/virtio-scsi.h"
+#include "kvm/virtio-pci-dev.h"
+#include "kvm/disk-image.h"
+#include "kvm/kvm.h"
+#include "kvm/pci.h"
+#include "kvm/ioeventfd.h"
+#include "kvm/guest_compat.h"
+#include "kvm/virtio-pci.h"
+#include "kvm/virtio.h"
+
+#include <linux/kernel.h>
+#include <linux/virtio_scsi.h>
+#include <linux/vhost.h>
+
+#define VIRTIO_SCSI_QUEUE_SIZE 128
+#define NUM_VIRT_QUEUES 3
+
+static LIST_HEAD(sdevs);
+static int compat_id = -1;
+
+struct scsi_dev {
+ struct virt_queue vqs[NUM_VIRT_QUEUES];
+ struct virtio_scsi_config config;
+ struct vhost_scsi_target target;
+ u32 features;
+ int vhost_fd;
+ struct virtio_device vdev;
+ struct list_head list;
+ struct kvm *kvm;
+};
+
+static u8 *get_config(struct kvm *kvm, void *dev)
+{
+ struct scsi_dev *sdev = dev;
+
+ return ((u8 *)(&sdev->config));
+}
+
+static u32 get_host_features(struct kvm *kvm, void *dev)
+{
+ return 1UL << VIRTIO_RING_F_EVENT_IDX |
+ 1UL << VIRTIO_RING_F_INDIRECT_DESC;
+}
+
+static void set_guest_features(struct kvm *kvm, void *dev, u32 features)
+{
+ struct scsi_dev *sdev = dev;
+
+ sdev->features = features;
+}
+
+static int init_vq(struct kvm *kvm, void *dev, u32 vq, u32 pfn)
+{
+ struct vhost_vring_state state = { .index = vq };
+ struct vhost_vring_addr addr;
+ struct scsi_dev *sdev = dev;
+ struct virt_queue *queue;
+ void *p;
+ int r;
+
+ compat__remove_message(compat_id);
+
+ queue = &sdev->vqs[vq];
+ queue->pfn = pfn;
+ p = guest_pfn_to_host(kvm, queue->pfn);
+
+ vring_init(&queue->vring, VIRTIO_SCSI_QUEUE_SIZE, p, VIRTIO_PCI_VRING_ALIGN);
+
+ if (sdev->vhost_fd == 0)
+ return 0;
+
+ state.num = queue->vring.num;
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_NUM, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_NUM failed");
+ state.num = 0;
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_BASE, &state);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_BASE failed");
+
+ addr = (struct vhost_vring_addr) {
+ .index = vq,
+ .desc_user_addr = (u64)(unsigned long)queue->vring.desc,
+ .avail_user_addr = (u64)(unsigned long)queue->vring.avail,
+ .used_user_addr = (u64)(unsigned long)queue->vring.used,
+ };
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_ADDR, &addr);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_ADDR failed");
+
+ return 0;
+}
+
+static void notify_vq_gsi(struct kvm *kvm, void *dev, u32 vq, u32 gsi)
+{
+ struct vhost_vring_file file;
+ struct scsi_dev *sdev = dev;
+ struct kvm_irqfd irq;
+ int r;
+
+ if (sdev->vhost_fd == 0)
+ return;
+
+ irq = (struct kvm_irqfd) {
+ .gsi = gsi,
+ .fd = eventfd(0, 0),
+ };
+ file = (struct vhost_vring_file) {
+ .index = vq,
+ .fd = irq.fd,
+ };
+
+ r = ioctl(kvm->vm_fd, KVM_IRQFD, &irq);
+ if (r < 0)
+ die_perror("KVM_IRQFD failed");
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_CALL, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_CALL failed");
+
+ if (vq > 0)
+ return;
+
+ r = ioctl(sdev->vhost_fd, VHOST_SCSI_SET_ENDPOINT, &sdev->target);
+ if (r != 0)
+ die("VHOST_SCSI_SET_ENDPOINT failed %d", errno);
+}
+
+static void notify_vq_eventfd(struct kvm *kvm, void *dev, u32 vq, u32 efd)
+{
+ struct scsi_dev *sdev = dev;
+ struct vhost_vring_file file = {
+ .index = vq,
+ .fd = efd,
+ };
+ int r;
+
+ if (sdev->vhost_fd == 0)
+ return;
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_VRING_KICK, &file);
+ if (r < 0)
+ die_perror("VHOST_SET_VRING_KICK failed");
+}
+
+static int notify_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return 0;
+}
+
+static int get_pfn_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ struct scsi_dev *sdev = dev;
+
+ return sdev->vqs[vq].pfn;
+}
+
+static int get_size_vq(struct kvm *kvm, void *dev, u32 vq)
+{
+ return VIRTIO_SCSI_QUEUE_SIZE;
+}
+
+static int set_size_vq(struct kvm *kvm, void *dev, u32 vq, int size)
+{
+ return size;
+}
+
+static struct virtio_ops scsi_dev_virtio_ops = (struct virtio_ops) {
+ .get_config = get_config,
+ .get_host_features = get_host_features,
+ .set_guest_features = set_guest_features,
+ .init_vq = init_vq,
+ .get_pfn_vq = get_pfn_vq,
+ .get_size_vq = get_size_vq,
+ .set_size_vq = set_size_vq,
+ .notify_vq = notify_vq,
+ .notify_vq_gsi = notify_vq_gsi,
+ .notify_vq_eventfd = notify_vq_eventfd,
+};
+
+static void virtio_scsi_vhost_init(struct kvm *kvm, struct scsi_dev *sdev)
+{
+ struct vhost_memory *mem;
+ u64 features;
+ int r;
+
+ sdev->vhost_fd = open("/dev/vhost-scsi", O_RDWR);
+ if (sdev->vhost_fd < 0)
+ die_perror("Failed openning vhost-scsi device");
+
+ mem = calloc(1, sizeof(*mem) + sizeof(struct vhost_memory_region));
+ if (mem == NULL)
+ die("Failed allocating memory for vhost memory map");
+
+ mem->nregions = 1;
+ mem->regions[0] = (struct vhost_memory_region) {
+ .guest_phys_addr = 0,
+ .memory_size = kvm->ram_size,
+ .userspace_addr = (unsigned long)kvm->ram_start,
+ };
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_OWNER);
+ if (r != 0)
+ die_perror("VHOST_SET_OWNER failed");
+
+ r = ioctl(sdev->vhost_fd, VHOST_GET_FEATURES, &features);
+ if (r != 0)
+ die_perror("VHOST_GET_FEATURES failed");
+
+ r = ioctl(sdev->vhost_fd, VHOST_SET_FEATURES, &features);
+ if (r != 0)
+ die_perror("VHOST_SET_FEATURES failed");
+ r = ioctl(sdev->vhost_fd, VHOST_SET_MEM_TABLE, mem);
+ if (r != 0)
+ die_perror("VHOST_SET_MEM_TABLE failed");
+
+ sdev->vdev.use_vhost = true;
+
+ free(mem);
+}
+
+
+static int virtio_scsi_init_one(struct kvm *kvm, struct disk_image *disk)
+{
+ struct scsi_dev *sdev;
+
+ if (!disk)
+ return -EINVAL;
+
+ sdev = calloc(1, sizeof(struct scsi_dev));
+ if (sdev == NULL)
+ return -ENOMEM;
+
+ *sdev = (struct scsi_dev) {
+ .config = (struct virtio_scsi_config) {
+ .num_queues = NUM_VIRT_QUEUES - 2,
+ .seg_max = VIRTIO_SCSI_CDB_SIZE - 2,
+ .max_sectors = 65535,
+ .cmd_per_lun = 128,
+ .sense_size = VIRTIO_SCSI_SENSE_SIZE,
+ .cdb_size = VIRTIO_SCSI_CDB_SIZE,
+ .max_channel = 0,
+ .max_target = 0,
+ .max_lun = 16383,
+ .event_info_size = sizeof(struct virtio_scsi_event),
+ },
+ .kvm = kvm,
+ };
+ strncpy((char *)&sdev->target.vhost_wwpn, disk->wwpn, sizeof(sdev->target.vhost_wwpn));
+ sdev->target.vhost_tpgt = strtol(disk->tpgt, NULL, 0);
+
+ virtio_init(kvm, sdev, &sdev->vdev, &scsi_dev_virtio_ops,
+ VIRTIO_PCI, PCI_DEVICE_ID_VIRTIO_SCSI, VIRTIO_ID_SCSI, PCI_CLASS_BLK);
+
+ list_add_tail(&sdev->list, &sdevs);
+
+ virtio_scsi_vhost_init(kvm, sdev);
+
+ if (compat_id == -1)
+ compat_id = virtio_compat_add_message("virtio-scsi", "CONFIG_VIRTIO_SCSI");
+
+ return 0;
+}
+
+static int virtio_scsi_exit_one(struct kvm *kvm, struct scsi_dev *sdev)
+{
+ int r;
+
+ r = ioctl(sdev->vhost_fd, VHOST_SCSI_CLEAR_ENDPOINT, &sdev->target);
+ if (r != 0)
+ die("VHOST_SCSI_CLEAR_ENDPOINT failed %d", errno);
+
+ list_del(&sdev->list);
+ free(sdev);
+
+ return 0;
+}
+
+int virtio_scsi_init(struct kvm *kvm)
+{
+ int i, r = 0;
+
+ for (i = 0; i < kvm->nr_disks; i++) {
+ if (!kvm->disks[i]->wwpn)
+ continue;
+ r = virtio_scsi_init_one(kvm, kvm->disks[i]);
+ if (r < 0)
+ goto cleanup;
+ }
+
+ return 0;
+cleanup:
+ return virtio_scsi_exit(kvm);
+}
+
+int virtio_scsi_exit(struct kvm *kvm)
+{
+ while (!list_empty(&sdevs)) {
+ struct scsi_dev *sdev;
+
+ sdev = list_first_entry(&sdevs, struct scsi_dev, list);
+ virtio_scsi_exit_one(kvm, sdev);
+ }
+
+ return 0;
+}
--- /dev/null
+#include "kvm/kvm.h"
+#include "kvm/boot-protocol.h"
+#include "kvm/e820.h"
+#include "kvm/interrupt.h"
+#include "kvm/util.h"
+
+#include <string.h>
+#include <asm/e820.h>
+
+#include "bios/bios-rom.h"
+
+struct irq_handler {
+ unsigned long address;
+ unsigned int irq;
+ void *handler;
+ size_t size;
+};
+
+#define BIOS_IRQ_PA_ADDR(name) (MB_BIOS_BEGIN + BIOS_OFFSET__##name)
+#define BIOS_IRQ_FUNC(name) ((char *)&bios_rom[BIOS_OFFSET__##name])
+#define BIOS_IRQ_SIZE(name) (BIOS_ENTRY_SIZE(BIOS_OFFSET__##name))
+
+#define DEFINE_BIOS_IRQ_HANDLER(_irq, _handler) \
+ { \
+ .irq = _irq, \
+ .address = BIOS_IRQ_PA_ADDR(_handler), \
+ .handler = BIOS_IRQ_FUNC(_handler), \
+ .size = BIOS_IRQ_SIZE(_handler), \
+ }
+
+static struct irq_handler bios_irq_handlers[] = {
+ DEFINE_BIOS_IRQ_HANDLER(0x10, bios_int10),
+ DEFINE_BIOS_IRQ_HANDLER(0x15, bios_int15),
+};
+
+static void setup_irq_handler(struct kvm *kvm, struct irq_handler *handler)
+{
+ struct real_intr_desc intr_desc;
+ void *p;
+
+ p = guest_flat_to_host(kvm, handler->address);
+ memcpy(p, handler->handler, handler->size);
+
+ intr_desc = (struct real_intr_desc) {
+ .segment = REAL_SEGMENT(MB_BIOS_BEGIN),
+ .offset = handler->address - MB_BIOS_BEGIN,
+ };
+
+ DIE_IF((handler->address - MB_BIOS_BEGIN) > 0xffffUL);
+
+ interrupt_table__set(&kvm->interrupt_table, &intr_desc, handler->irq);
+}
+
+/**
+ * e820_setup - setup some simple E820 memory map
+ * @kvm - guest system descriptor
+ */
+static void e820_setup(struct kvm *kvm)
+{
+ struct e820map *e820;
+ struct e820entry *mem_map;
+ unsigned int i = 0;
+
+ e820 = guest_flat_to_host(kvm, E820_MAP_START);
+ mem_map = e820->map;
+
+ mem_map[i++] = (struct e820entry) {
+ .addr = REAL_MODE_IVT_BEGIN,
+ .size = EBDA_START - REAL_MODE_IVT_BEGIN,
+ .type = E820_RAM,
+ };
+ mem_map[i++] = (struct e820entry) {
+ .addr = EBDA_START,
+ .size = VGA_RAM_BEGIN - EBDA_START,
+ .type = E820_RESERVED,
+ };
+ mem_map[i++] = (struct e820entry) {
+ .addr = MB_BIOS_BEGIN,
+ .size = MB_BIOS_END - MB_BIOS_BEGIN,
+ .type = E820_RESERVED,
+ };
+ if (kvm->ram_size < KVM_32BIT_GAP_START) {
+ mem_map[i++] = (struct e820entry) {
+ .addr = BZ_KERNEL_START,
+ .size = kvm->ram_size - BZ_KERNEL_START,
+ .type = E820_RAM,
+ };
+ } else {
+ mem_map[i++] = (struct e820entry) {
+ .addr = BZ_KERNEL_START,
+ .size = KVM_32BIT_GAP_START - BZ_KERNEL_START,
+ .type = E820_RAM,
+ };
+ mem_map[i++] = (struct e820entry) {
+ .addr = KVM_32BIT_MAX_MEM_SIZE,
+ .size = kvm->ram_size - KVM_32BIT_MAX_MEM_SIZE,
+ .type = E820_RAM,
+ };
+ }
+
+ BUG_ON(i > E820_X_MAX);
+
+ e820->nr_map = i;
+}
+
+static void setup_vga_rom(struct kvm *kvm)
+{
+ u16 *mode;
+ void *p;
+
+ p = guest_flat_to_host(kvm, VGA_ROM_OEM_STRING);
+ memset(p, 0, VGA_ROM_OEM_STRING_SIZE);
+ strncpy(p, "KVM VESA", VGA_ROM_OEM_STRING_SIZE);
+
+ mode = guest_flat_to_host(kvm, VGA_ROM_MODES);
+ mode[0] = 0x0112;
+ mode[1] = 0xffff;
+}
+
+/**
+ * setup_bios - inject BIOS into guest memory
+ * @kvm - guest system descriptor
+ */
+void setup_bios(struct kvm *kvm)
+{
+ unsigned long address = MB_BIOS_BEGIN;
+ struct real_intr_desc intr_desc;
+ unsigned int i;
+ void *p;
+
+ /*
+ * before anything else -- clean some known areas
+ * we definitely don't want any trash here
+ */
+ p = guest_flat_to_host(kvm, BDA_START);
+ memset(p, 0, BDA_END - BDA_START);
+
+ p = guest_flat_to_host(kvm, EBDA_START);
+ memset(p, 0, EBDA_END - EBDA_START);
+
+ p = guest_flat_to_host(kvm, MB_BIOS_BEGIN);
+ memset(p, 0, MB_BIOS_END - MB_BIOS_BEGIN);
+
+ p = guest_flat_to_host(kvm, VGA_ROM_BEGIN);
+ memset(p, 0, VGA_ROM_END - VGA_ROM_BEGIN);
+
+ /* just copy the bios rom into the place */
+ p = guest_flat_to_host(kvm, MB_BIOS_BEGIN);
+ memcpy(p, bios_rom, bios_rom_size);
+
+ /* E820 memory map must be present */
+ e820_setup(kvm);
+
+ /* VESA needs own tricks */
+ setup_vga_rom(kvm);
+
+ /*
+ * Setup a *fake* real mode vector table, it has only
+ * one real handler which does just iret
+ */
+ address = BIOS_IRQ_PA_ADDR(bios_intfake);
+ intr_desc = (struct real_intr_desc) {
+ .segment = REAL_SEGMENT(MB_BIOS_BEGIN),
+ .offset = address - MB_BIOS_BEGIN,
+ };
+ interrupt_table__setup(&kvm->interrupt_table, &intr_desc);
+
+ for (i = 0; i < ARRAY_SIZE(bios_irq_handlers); i++)
+ setup_irq_handler(kvm, &bios_irq_handlers[i]);
+
+ /* we almost done */
+ p = guest_flat_to_host(kvm, 0);
+ interrupt_table__copy(&kvm->interrupt_table, p, REAL_INTR_SIZE);
+}
--- /dev/null
+bios-rom.bin
+bios-rom.bin.elf
+bios-rom.h
--- /dev/null
+#include <kvm/assembly.h>
+
+ .org 0
+#ifdef CONFIG_X86_64
+ .code64
+#else
+ .code32
+#endif
+
+GLOBAL(bios_rom)
+ .incbin "x86/bios/bios.bin"
+END(bios_rom)
--- /dev/null
+#include "kvm/e820.h"
+
+#include "kvm/segment.h"
+#include "kvm/bios.h"
+
+#include <asm/processor-flags.h>
+#include <asm/e820.h>
+
+static inline void set_fs(u16 seg)
+{
+ asm volatile("movw %0,%%fs" : : "rm" (seg));
+}
+
+static inline u8 rdfs8(unsigned long addr)
+{
+ u8 v;
+
+ asm volatile("addr32 movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+
+ return v;
+}
+
+static inline u32 rdfs32(unsigned long addr)
+{
+ u32 v;
+
+ asm volatile("addr32 movl %%fs:%1,%0" : "=q" (v) : "m" (*(u32 *)addr));
+
+ return v;
+}
+
+bioscall void e820_query_map(struct biosregs *regs)
+{
+ struct e820map *e820;
+ u32 map_size;
+ u16 fs_seg;
+ u32 ndx;
+
+ e820 = (struct e820map *)E820_MAP_START;
+ fs_seg = flat_to_seg16(E820_MAP_START);
+ set_fs(fs_seg);
+
+ ndx = regs->ebx;
+
+ map_size = rdfs32(flat_to_off16((u32)&e820->nr_map, fs_seg));
+
+ if (ndx < map_size) {
+ u32 start;
+ unsigned int i;
+ u8 *p;
+
+ fs_seg = flat_to_seg16(E820_MAP_START);
+ set_fs(fs_seg);
+
+ start = (u32)&e820->map[ndx];
+
+ p = (void *) regs->edi;
+
+ for (i = 0; i < sizeof(struct e820entry); i++)
+ *p++ = rdfs8(flat_to_off16(start + i, fs_seg));
+ }
+
+ regs->eax = SMAP;
+ regs->ecx = sizeof(struct e820entry);
+ regs->ebx = ++ndx;
+
+ /* Clear CF to indicate success. */
+ regs->eflags &= ~X86_EFLAGS_CF;
+
+ if (ndx >= map_size)
+ regs->ebx = 0; /* end of map */
+}
--- /dev/null
+/*
+ * Our pretty trivial BIOS emulation
+ */
+
+#include <kvm/bios.h>
+#include <kvm/assembly.h>
+
+ .org 0
+ .code16gcc
+
+#define EFLAGS_CF (1 << 0)
+
+#include "macro.S"
+
+/* If you change these macros, remember to update 'struct biosregs' */
+.macro SAVE_BIOSREGS
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %edi
+ pushl %esi
+ pushl %ebp
+ pushl %esp
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ pushl %eax
+.endm
+
+.macro RESTORE_BIOSREGS
+ popl %eax
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esp
+ popl %ebp
+ popl %esi
+ popl %edi
+ popl %ds
+ popl %es
+ popl %fs
+.endm
+
+/*
+ * fake interrupt handler, nothing can be faster ever
+ */
+ENTRY(bios_intfake)
+ /*
+ * Set CF to indicate failure. We don't want callers to think that the
+ * interrupt handler succeeded and then treat the return values in
+ * registers as valid data.
+ */
+ orl $EFLAGS_CF, 0x4(%esp)
+
+ IRET
+ENTRY_END(bios_intfake)
+
+/*
+ * int 10 - video - service
+ */
+ENTRY(bios_int10)
+ SAVE_BIOSREGS
+
+ movl %esp, %eax
+ /* this is way easier than doing it in assembly */
+ /* just push all the regs and jump to a C handler */
+ call int10_handler
+
+ RESTORE_BIOSREGS
+
+ /* Clear CF to indicate success. */
+ andl $~EFLAGS_CF, 0x4(%esp)
+
+ IRET
+ENTRY_END(bios_int10)
+
+ENTRY(bios_int15)
+ SAVE_BIOSREGS
+
+ movl %esp, %eax
+ call int15_handler
+
+ RESTORE_BIOSREGS
+
+ IRET
+ENTRY_END(bios_int15)
+
+GLOBAL(__locals)
+
+#include "local.S"
+
+END(__locals)
--- /dev/null
+#!/bin/sh
+
+echo "/* Autogenerated file, don't edit */"
+echo "#ifndef BIOS_OFFSETS_H"
+echo "#define BIOS_OFFSETS_H"
+
+echo ""
+echo "#define BIOS_ENTRY_SIZE(name) (name##_end - name)"
+echo ""
+
+nm bios.bin.elf | grep ' [Tt] ' | awk '{ print "#define BIOS_OFFSET__" $3 " 0x" $1; }'
+
+echo ""
+echo "#endif"
--- /dev/null
+#include "kvm/segment.h"
+#include "kvm/bios.h"
+#include "kvm/vesa.h"
+
+#include "bios/memcpy.h"
+
+#include <boot/vesa.h>
+
+static far_ptr gen_far_ptr(unsigned int pa)
+{
+ far_ptr ptr;
+
+ ptr.seg = (pa >> 4);
+ ptr.off = pa - (ptr.seg << 4);
+
+ return ptr;
+}
+
+static inline void outb(unsigned short port, unsigned char val)
+{
+ asm volatile("outb %0, %1" : : "a"(val), "Nd"(port));
+}
+
+/*
+ * It's probably much more useful to make this print to the serial
+ * line rather than print to a non-displayed VGA memory
+ */
+static inline void int10_putchar(struct biosregs *args)
+{
+ u8 al = args->eax & 0xFF;
+
+ outb(0x3f8, al);
+}
+
+static void vbe_get_mode(struct biosregs *args)
+{
+ struct vesa_mode_info *info = (struct vesa_mode_info *) args->edi;
+
+ *info = (struct vesa_mode_info) {
+ .mode_attr = 0xd9, /* 11011011 */
+ .logical_scan = VESA_WIDTH*4,
+ .h_res = VESA_WIDTH,
+ .v_res = VESA_HEIGHT,
+ .bpp = VESA_BPP,
+ .memory_layout = 6,
+ .memory_planes = 1,
+ .lfb_ptr = VESA_MEM_ADDR,
+ .rmask = 8,
+ .gmask = 8,
+ .bmask = 8,
+ .resv_mask = 8,
+ .resv_pos = 24,
+ .bpos = 16,
+ .gpos = 8,
+ };
+}
+
+static void vbe_get_info(struct biosregs *args)
+{
+ struct vesa_general_info *infop = (struct vesa_general_info *) args->edi;
+ struct vesa_general_info info;
+
+ info = (struct vesa_general_info) {
+ .signature = VESA_MAGIC,
+ .version = 0x102,
+ .vendor_string = gen_far_ptr(VGA_ROM_BEGIN),
+ .capabilities = 0x10,
+ .video_mode_ptr = gen_far_ptr(VGA_ROM_MODES),
+ .total_memory = (4 * VESA_WIDTH * VESA_HEIGHT) / 0x10000,
+ };
+
+ memcpy16(args->es, infop, args->ds, &info, sizeof(info));
+}
+
+#define VBE_STATUS_OK 0x004F
+
+static void int10_vesa(struct biosregs *args)
+{
+ u8 al;
+
+ al = args->eax & 0xff;
+
+ switch (al) {
+ case 0x00:
+ vbe_get_info(args);
+ break;
+ case 0x01:
+ vbe_get_mode(args);
+ break;
+ }
+
+ args->eax = VBE_STATUS_OK;
+}
+
+bioscall void int10_handler(struct biosregs *args)
+{
+ u8 ah;
+
+ ah = (args->eax & 0xff00) >> 8;
+
+ switch (ah) {
+ case 0x0e:
+ int10_putchar(args);
+ break;
+ case 0x4f:
+ int10_vesa(args);
+ break;
+ }
+
+}
--- /dev/null
+#include "kvm/bios.h"
+
+#include "kvm/e820.h"
+
+#include <asm/processor-flags.h>
+
+bioscall void int15_handler(struct biosregs *regs)
+{
+ switch (regs->eax) {
+ case 0xe820:
+ e820_query_map(regs);
+ break;
+ default:
+ /* Set CF to indicate failure. */
+ regs->eflags |= X86_EFLAGS_CF;
+ break;
+ }
+}
--- /dev/null
+/*
+ * Local variables for almost every BIOS irq handler
+ * Must be put somewhere inside irq handler body
+ */
+__CALLER_SS: .int 0
+__CALLER_SP: .long 0
+__CALLER_CLOBBER: .long 0
--- /dev/null
+/*
+ * handy BIOS macros
+ */
+
+/*
+ * switch to BIOS stack
+ */
+.macro stack_swap
+ movw %ss, %cs:(__CALLER_SS)
+ movl %esp, %cs:(__CALLER_SP)
+ movl %edx, %cs:(__CALLER_CLOBBER)
+ movw $MB_BIOS_SS, %dx
+ movw %dx, %ss
+ movw $MB_BIOS_SP, %sp
+ movl %cs:(__CALLER_CLOBBER), %edx
+.endm
+
+/*
+ * restore the original stack
+ */
+.macro stack_restore
+ movl %cs:(__CALLER_SP), %esp
+ movw %cs:(__CALLER_SS), %ss
+.endm
+
--- /dev/null
+#include "bios/memcpy.h"
+
+/*
+ * Copy memory area in 16-bit real mode.
+ */
+void memcpy16(u16 dst_seg, void *dst, u16 src_seg, const void *src, size_t len)
+{
+ __asm__ __volatile__ (
+ "pushw %%ds \n"
+ "pushw %%es \n"
+ "movw %[src_seg], %%ds \n"
+ "movw %[dst_seg], %%es \n"
+ "rep movsb %%ds:(%%si), %%es:(%%di) \n"
+ "popw %%es \n"
+ "popw %%ds \n"
+ :
+ : "S"(src),
+ "D"(dst),
+ "c"(len),
+ [src_seg] "r"(src_seg),
+ [dst_seg] "r"(dst_seg)
+ : "cc", "memory");
+}
--- /dev/null
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+
+SECTIONS {
+ .text 0 : {
+ *(.text)
+ }
+
+ /DISCARD/ : {
+ *(.debug*)
+ *(.data)
+ *(.bss)
+ *(.eh_frame*)
+ }
+}
+
--- /dev/null
+#include "kvm/kvm.h"
+
+#include "kvm/util.h"
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <fcntl.h>
+
+#define BIOS_SELECTOR 0xf000
+#define BIOS_IP 0xfff0
+#define BIOS_SP 0x8000
+
+bool kvm__load_firmware(struct kvm *kvm, const char *firmware_filename)
+{
+ struct stat st;
+ void *p;
+ int fd;
+ int nr;
+
+ fd = open(firmware_filename, O_RDONLY);
+ if (fd < 0)
+ return false;
+
+ if (fstat(fd, &st))
+ return false;
+
+ if (st.st_size > MB_FIRMWARE_BIOS_SIZE)
+ die("firmware image %s is too big to fit in memory (%Lu KB).\n", firmware_filename, (u64)(st.st_size / 1024));
+
+ p = guest_flat_to_host(kvm, MB_FIRMWARE_BIOS_BEGIN);
+
+ while ((nr = read(fd, p, st.st_size)) > 0)
+ p += nr;
+
+ kvm->boot_selector = BIOS_SELECTOR;
+ kvm->boot_ip = BIOS_IP;
+ kvm->boot_sp = BIOS_SP;
+
+ return true;
+}
--- /dev/null
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#include <sys/ioctl.h>
+#include <stdlib.h>
+
+#define CPUID_FUNC_PERFMON 0x0A
+
+#define MAX_KVM_CPUID_ENTRIES 100
+
+static void filter_cpuid(struct kvm_cpuid2 *kvm_cpuid)
+{
+ unsigned int i;
+
+ /*
+ * Filter CPUID functions that are not supported by the hypervisor.
+ */
+ for (i = 0; i < kvm_cpuid->nent; i++) {
+ struct kvm_cpuid_entry2 *entry = &kvm_cpuid->entries[i];
+
+ switch (entry->function) {
+ case 1:
+ /* Set X86_FEATURE_HYPERVISOR */
+ if (entry->index == 0)
+ entry->ecx |= (1 << 31);
+ break;
+ case 6:
+ /* Clear X86_FEATURE_EPB */
+ entry->ecx = entry->ecx & ~(1 << 3);
+ break;
+ case CPUID_FUNC_PERFMON:
+ entry->eax = 0x00; /* disable it */
+ break;
+ default:
+ /* Keep the CPUID function as -is */
+ break;
+ };
+ }
+}
+
+void kvm_cpu__setup_cpuid(struct kvm_cpu *vcpu)
+{
+ struct kvm_cpuid2 *kvm_cpuid;
+
+ kvm_cpuid = calloc(1, sizeof(*kvm_cpuid) +
+ MAX_KVM_CPUID_ENTRIES * sizeof(*kvm_cpuid->entries));
+
+ kvm_cpuid->nent = MAX_KVM_CPUID_ENTRIES;
+ if (ioctl(vcpu->kvm->sys_fd, KVM_GET_SUPPORTED_CPUID, kvm_cpuid) < 0)
+ die_perror("KVM_GET_SUPPORTED_CPUID failed");
+
+ filter_cpuid(kvm_cpuid);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_CPUID2, kvm_cpuid) < 0)
+ die_perror("KVM_SET_CPUID2 failed");
+
+ free(kvm_cpuid);
+}
--- /dev/null
+#ifndef ASSEMBLY_H_
+#define ASSEMBLY_H_
+
+#define __ALIGN .p2align 4, 0x90
+#define ENTRY(name) \
+ __ALIGN; \
+ .globl name; \
+ name:
+
+#define GLOBAL(name) \
+ .globl name; \
+ name:
+
+#define ENTRY_END(name) GLOBAL(name##_end)
+#define END(name) GLOBAL(name##_end)
+
+/*
+ * gas produces size override prefix with which
+ * we are unhappy, lets make it hardcoded for
+ * 16 bit mode
+ */
+#define IRET .byte 0xcf
+
+#endif /* ASSEMBLY_H_ */
--- /dev/null
+#ifndef _KVM_BARRIER_H_
+#define _KVM_BARRIER_H_
+
+#define barrier() asm volatile("": : :"memory")
+
+#define mb() asm volatile ("mfence": : :"memory")
+#define rmb() asm volatile ("lfence": : :"memory")
+#define wmb() asm volatile ("sfence": : :"memory")
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() rmb()
+#define smp_wmb() wmb()
+#else
+#define smp_mb() barrier()
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#endif
+
+#endif /* _KVM_BARRIER_H_ */
--- /dev/null
+#ifndef BIOS_EXPORT_H_
+#define BIOS_EXPORT_H_
+
+struct kvm;
+
+extern char bios_rom[0];
+extern char bios_rom_end[0];
+
+#define bios_rom_size (bios_rom_end - bios_rom)
+
+extern void setup_bios(struct kvm *kvm);
+
+#endif /* BIOS_EXPORT_H_ */
--- /dev/null
+#ifndef BIOS_H_
+#define BIOS_H_
+
+/*
+ * X86-32 Memory Map (typical)
+ * start end
+ * Real Mode Interrupt Vector Table 0x00000000 0x000003FF
+ * BDA area 0x00000400 0x000004FF
+ * Conventional Low Memory 0x00000500 0x0009FBFF
+ * EBDA area 0x0009FC00 0x0009FFFF
+ * VIDEO RAM 0x000A0000 0x000BFFFF
+ * VIDEO ROM (BIOS) 0x000C0000 0x000C7FFF
+ * ROMs & unus. space (mapped hw & misc)0x000C8000 0x000EFFFF 160 KiB (typically)
+ * Motherboard BIOS 0x000F0000 0x000FFFFF
+ * Extended Memory 0x00100000 0xFEBFFFFF
+ * Reserved (configs, ACPI, PnP, etc) 0xFEC00000 0xFFFFFFFF
+ */
+
+#define REAL_MODE_IVT_BEGIN 0x00000000
+#define REAL_MODE_IVT_END 0x000003ff
+
+#define BDA_START 0x00000400
+#define BDA_END 0x000004ff
+
+#define EBDA_START 0x0009fc00
+#define EBDA_END 0x0009ffff
+
+#define E820_MAP_START EBDA_START
+
+#define MB_BIOS_BEGIN 0x000f0000
+#define MB_FIRMWARE_BIOS_BEGIN 0x000e0000
+#define MB_BIOS_END 0x000fffff
+
+#define MB_BIOS_SIZE (MB_BIOS_END - MB_BIOS_BEGIN + 1)
+#define MB_FIRMWARE_BIOS_SIZE (MB_BIOS_END - MB_FIRMWARE_BIOS_BEGIN + 1)
+
+#define VGA_RAM_BEGIN 0x000a0000
+#define VGA_RAM_END 0x000bffff
+
+#define VGA_ROM_BEGIN 0x000c0000
+#define VGA_ROM_OEM_STRING VGA_ROM_BEGIN
+#define VGA_ROM_OEM_STRING_SIZE 16
+#define VGA_ROM_MODES (VGA_ROM_OEM_STRING + VGA_ROM_OEM_STRING_SIZE)
+#define VGA_ROM_MODES_SIZE 32
+#define VGA_ROM_END 0x000c7fff
+
+/* we handle one page only */
+#define VGA_RAM_SEG (VGA_RAM_BEGIN >> 4)
+#define VGA_PAGE_SIZE 0x007d0 /* 80x25 */
+
+/* real mode interrupt vector table */
+#define REAL_INTR_BASE REAL_MODE_IVT_BEGIN
+#define REAL_INTR_VECTORS 256
+
+/*
+ * BIOS stack must be at absolute predefined memory address
+ * We reserve 64 bytes for BIOS stack
+ */
+#define MB_BIOS_SS 0xfff7
+#define MB_BIOS_SP 0x40
+
+/*
+ * When interfere with assembler code we need to be sure how
+ * arguments are passed in real mode.
+ */
+#define bioscall __attribute__((regparm(3)))
+
+#ifndef __ASSEMBLER__
+
+#include <linux/types.h>
+
+struct biosregs {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+ u32 esp;
+ u32 ebp;
+ u32 esi;
+ u32 edi;
+ u32 ds;
+ u32 es;
+ u32 fs;
+ u32 eip;
+ u32 eflags;
+};
+
+extern bioscall void int10_handler(struct biosregs *regs);
+extern bioscall void int15_handler(struct biosregs *regs);
+
+#endif
+
+#endif /* BIOS_H_ */
--- /dev/null
+/*
+ * Linux boot protocol specifics
+ */
+
+#ifndef BOOT_PROTOCOL_H_
+#define BOOT_PROTOCOL_H_
+
+/*
+ * The protected mode kernel part of a modern bzImage is loaded
+ * at 1 MB by default.
+ */
+#define BZ_DEFAULT_SETUP_SECTS 4
+#define BZ_KERNEL_START 0x100000UL
+#define INITRD_START 0x1000000UL
+
+#endif /* BOOT_PROTOCOL_H_ */
--- /dev/null
+#ifndef KVM__CPUFEATURE_H
+#define KVM__CPUFEATURE_H
+
+#define CPUID_VENDOR_INTEL_1 0x756e6547 /* "Genu" */
+#define CPUID_VENDOR_INTEL_2 0x49656e69 /* "ineI" */
+#define CPUID_VENDOR_INTEL_3 0x6c65746e /* "ntel" */
+
+#define CPUID_VENDOR_AMD_1 0x68747541 /* "Auth" */
+#define CPUID_VENDOR_AMD_2 0x69746e65 /* "enti" */
+#define CPUID_VENDOR_AMD_3 0x444d4163 /* "cAMD" */
+
+/*
+ * CPUID flags we need to deal with
+ */
+#define KVM__X86_FEATURE_VMX 5 /* Hardware virtualization */
+#define KVM__X86_FEATURE_SVM 2 /* Secure virtual machine */
+#define KVM__X86_FEATURE_XSAVE 26 /* XSAVE/XRSTOR/XSETBV/XGETBV */
+
+#define cpu_feature_disable(reg, feature) \
+ ((reg) & ~(1 << (feature)))
+#define cpu_feature_enable(reg, feature) \
+ ((reg) | (1 << (feature)))
+
+struct cpuid_regs {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+};
+
+static inline void host_cpuid(struct cpuid_regs *regs)
+{
+ asm volatile("cpuid"
+ : "=a" (regs->eax),
+ "=b" (regs->ebx),
+ "=c" (regs->ecx),
+ "=d" (regs->edx)
+ : "0" (regs->eax), "2" (regs->ecx));
+}
+
+#endif /* KVM__CPUFEATURE_H */
--- /dev/null
+#ifndef KVM__INTERRUPT_H
+#define KVM__INTERRUPT_H
+
+#include <linux/types.h>
+#include "kvm/bios.h"
+#include "kvm/bios-export.h"
+
+struct real_intr_desc {
+ u16 offset;
+ u16 segment;
+} __attribute__((packed));
+
+#define REAL_SEGMENT_SHIFT 4
+#define REAL_SEGMENT(addr) ((addr) >> REAL_SEGMENT_SHIFT)
+#define REAL_OFFSET(addr) ((addr) & ((1 << REAL_SEGMENT_SHIFT) - 1))
+#define REAL_INTR_SIZE (REAL_INTR_VECTORS * sizeof(struct real_intr_desc))
+
+struct interrupt_table {
+ struct real_intr_desc entries[REAL_INTR_VECTORS];
+};
+
+void interrupt_table__copy(struct interrupt_table *itable, void *dst, unsigned int size);
+void interrupt_table__setup(struct interrupt_table *itable, struct real_intr_desc *entry);
+void interrupt_table__set(struct interrupt_table *itable, struct real_intr_desc *entry, unsigned int num);
+
+#endif /* KVM__INTERRUPT_H */
--- /dev/null
+#ifndef KVM__KVM_ARCH_H
+#define KVM__KVM_ARCH_H
+
+#include "kvm/interrupt.h"
+#include "kvm/segment.h"
+
+#include <stdbool.h>
+#include <linux/types.h>
+#include <time.h>
+
+/*
+ * The hole includes VESA framebuffer and PCI memory.
+ */
+#define KVM_32BIT_MAX_MEM_SIZE (1ULL << 32)
+#define KVM_32BIT_GAP_SIZE (768 << 20)
+#define KVM_32BIT_GAP_START (KVM_32BIT_MAX_MEM_SIZE - KVM_32BIT_GAP_SIZE)
+
+#define KVM_MMIO_START KVM_32BIT_GAP_START
+
+/* This is the address that pci_get_io_space_block() starts allocating
+ * from. Note that this is a PCI bus address (though same on x86).
+ */
+#define KVM_PCI_MMIO_AREA (KVM_MMIO_START + 0x1000000)
+#define KVM_VIRTIO_MMIO_AREA (KVM_MMIO_START + 0x2000000)
+
+struct kvm {
+ int sys_fd; /* For system ioctls(), i.e. /dev/kvm */
+ int vm_fd; /* For VM ioctls() */
+ timer_t timerid; /* Posix timer for interrupts */
+
+ int nrcpus; /* Number of cpus to run */
+
+ u32 mem_slots; /* for KVM_SET_USER_MEMORY_REGION */
+
+ u64 ram_size;
+ void *ram_start;
+ u64 ram_pagesize;
+
+ bool nmi_disabled;
+
+ bool single_step;
+
+ u16 boot_selector;
+ u16 boot_ip;
+ u16 boot_sp;
+
+ struct interrupt_table interrupt_table;
+
+ const char *vmlinux;
+ struct disk_image **disks;
+ int nr_disks;
+
+ char *name;
+
+ int vm_state;
+};
+
+static inline void *guest_flat_to_host(struct kvm *kvm, unsigned long offset); /* In kvm.h */
+
+static inline void *guest_real_to_host(struct kvm *kvm, u16 selector, u16 offset)
+{
+ unsigned long flat = segment_to_flat(selector, offset);
+
+ return guest_flat_to_host(kvm, flat);
+}
+
+#endif /* KVM__KVM_ARCH_H */
--- /dev/null
+#ifndef KVM__KVM_CPU_ARCH_H
+#define KVM__KVM_CPU_ARCH_H
+
+/* Architecture-specific kvm_cpu definitions. */
+
+#include <linux/kvm.h> /* for struct kvm_regs */
+#include "kvm/kvm.h" /* for kvm__emulate_{mm}io() */
+#include <stdbool.h>
+#include <pthread.h>
+
+struct kvm;
+
+struct kvm_cpu {
+ pthread_t thread; /* VCPU thread */
+
+ unsigned long cpu_id;
+
+ struct kvm *kvm; /* parent KVM */
+ int vcpu_fd; /* For VCPU ioctls() */
+ struct kvm_run *kvm_run;
+
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_fpu fpu;
+
+ struct kvm_msrs *msrs; /* dynamically allocated */
+
+ u8 is_running;
+ u8 paused;
+ u8 needs_nmi;
+
+ struct kvm_coalesced_mmio_ring *ring;
+};
+
+/*
+ * As these are such simple wrappers, let's have them in the header so they'll
+ * be cheaper to call:
+ */
+static inline bool kvm_cpu__emulate_io(struct kvm *kvm, u16 port, void *data, int direction, int size, u32 count)
+{
+ return kvm__emulate_io(kvm, port, data, direction, size, count);
+}
+
+static inline bool kvm_cpu__emulate_mmio(struct kvm *kvm, u64 phys_addr, u8 *data, u32 len, u8 is_write)
+{
+ return kvm__emulate_mmio(kvm, phys_addr, data, len, is_write);
+}
+
+#endif /* KVM__KVM_CPU_ARCH_H */
--- /dev/null
+#ifndef KVM_MPTABLE_H_
+#define KVM_MPTABLE_H_
+
+struct kvm;
+
+int mptable__init(struct kvm *kvm);
+int mptable__exit(struct kvm *kvm);
+
+#endif /* KVM_MPTABLE_H_ */
--- /dev/null
+#include "kvm/interrupt.h"
+
+#include "kvm/util.h"
+
+#include <string.h>
+
+void interrupt_table__copy(struct interrupt_table *itable, void *dst, unsigned int size)
+{
+ if (size < sizeof(itable->entries))
+ die("An attempt to overwrite host memory");
+
+ memcpy(dst, itable->entries, sizeof(itable->entries));
+}
+
+void interrupt_table__setup(struct interrupt_table *itable, struct real_intr_desc *entry)
+{
+ unsigned int i;
+
+ for (i = 0; i < REAL_INTR_VECTORS; i++)
+ itable->entries[i] = *entry;
+}
+
+void interrupt_table__set(struct interrupt_table *itable,
+ struct real_intr_desc *entry, unsigned int num)
+{
+ if (num < REAL_INTR_VECTORS)
+ itable->entries[num] = *entry;
+}
--- /dev/null
+#include "kvm/ioport.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+
+static bool debug_io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ exit(EXIT_SUCCESS);
+}
+
+static struct ioport_operations debug_ops = {
+ .io_out = debug_io_out,
+};
+
+static bool seabios_debug_io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ char ch;
+
+ ch = ioport__read8(data);
+
+ putchar(ch);
+
+ return true;
+}
+
+static struct ioport_operations seabios_debug_ops = {
+ .io_out = seabios_debug_io_out,
+};
+
+static bool dummy_io_in(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static bool dummy_io_out(struct ioport *ioport, struct kvm *kvm, u16 port, void *data, int size)
+{
+ return true;
+}
+
+static struct ioport_operations dummy_read_write_ioport_ops = {
+ .io_in = dummy_io_in,
+ .io_out = dummy_io_out,
+};
+
+static struct ioport_operations dummy_write_only_ioport_ops = {
+ .io_out = dummy_io_out,
+};
+
+void ioport__setup_arch(void)
+{
+ /* Legacy ioport setup */
+
+ /* 0x0020 - 0x003F - 8259A PIC 1 */
+ ioport__register(0x0020, &dummy_read_write_ioport_ops, 2, NULL);
+
+ /* PORT 0040-005F - PIT - PROGRAMMABLE INTERVAL TIMER (8253, 8254) */
+ ioport__register(0x0040, &dummy_read_write_ioport_ops, 4, NULL);
+
+ /* 0x00A0 - 0x00AF - 8259A PIC 2 */
+ ioport__register(0x00A0, &dummy_read_write_ioport_ops, 2, NULL);
+
+ /* PORT 00E0-00EF are 'motherboard specific' so we use them for our
+ internal debugging purposes. */
+ ioport__register(IOPORT_DBG, &debug_ops, 1, NULL);
+
+ /* PORT 00ED - DUMMY PORT FOR DELAY??? */
+ ioport__register(0x00ED, &dummy_write_only_ioport_ops, 1, NULL);
+
+ /* 0x00F0 - 0x00FF - Math co-processor */
+ ioport__register(0x00F0, &dummy_write_only_ioport_ops, 2, NULL);
+
+ /* PORT 03D4-03D5 - COLOR VIDEO - CRT CONTROL REGISTERS */
+ ioport__register(0x03D4, &dummy_read_write_ioport_ops, 1, NULL);
+ ioport__register(0x03D5, &dummy_write_only_ioport_ops, 1, NULL);
+
+ ioport__register(0x402, &seabios_debug_ops, 1, NULL);
+}
--- /dev/null
+#include "kvm/irq.h"
+#include "kvm/kvm.h"
+#include "kvm/util.h"
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include <linux/kvm.h>
+#include <sys/ioctl.h>
+
+#include <stddef.h>
+#include <stdlib.h>
+
+#define IRQ_MAX_GSI 64
+#define IRQCHIP_MASTER 0
+#define IRQCHIP_SLAVE 1
+#define IRQCHIP_IOAPIC 2
+
+static u8 next_line = 5;
+static u8 next_dev = 1;
+static struct rb_root pci_tree = RB_ROOT;
+
+/* First 24 GSIs are routed between IRQCHIPs and IOAPICs */
+static u32 gsi = 24;
+
+struct kvm_irq_routing *irq_routing;
+
+static int irq__add_routing(u32 gsi, u32 type, u32 irqchip, u32 pin)
+{
+ if (gsi >= IRQ_MAX_GSI)
+ return -ENOSPC;
+
+ irq_routing->entries[irq_routing->nr++] =
+ (struct kvm_irq_routing_entry) {
+ .gsi = gsi,
+ .type = type,
+ .u.irqchip.irqchip = irqchip,
+ .u.irqchip.pin = pin,
+ };
+
+ return 0;
+}
+
+static struct pci_dev *search(struct rb_root *root, u32 id)
+{
+ struct rb_node *node = root->rb_node;
+
+ while (node) {
+ struct pci_dev *data = rb_entry(node, struct pci_dev, node);
+ int result;
+
+ result = id - data->id;
+
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return data;
+ }
+ return NULL;
+}
+
+static int insert(struct rb_root *root, struct pci_dev *data)
+{
+ struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct pci_dev *this = container_of(*new, struct pci_dev, node);
+ int result = data->id - this->id;
+
+ parent = *new;
+ if (result < 0)
+ new = &((*new)->rb_left);
+ else if (result > 0)
+ new = &((*new)->rb_right);
+ else
+ return -EEXIST;
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&data->node, parent, new);
+ rb_insert_color(&data->node, root);
+
+ return 0;
+}
+
+int irq__register_device(u32 dev, u8 *num, u8 *pin, u8 *line)
+{
+ struct pci_dev *node;
+ int r;
+
+ node = search(&pci_tree, dev);
+
+ if (!node) {
+ /* We haven't found a node - First device of it's kind */
+ node = malloc(sizeof(*node));
+ if (node == NULL)
+ return -ENOMEM;
+
+ *node = (struct pci_dev) {
+ .id = dev,
+ /*
+ * PCI supports only INTA#,B#,C#,D# per device.
+ * A#,B#,C#,D# are allowed for multifunctional
+ * devices so stick with A# for our single
+ * function devices.
+ */
+ .pin = 1,
+ };
+
+ INIT_LIST_HEAD(&node->lines);
+
+ r = insert(&pci_tree, node);
+ if (r) {
+ free(node);
+ return r;
+ }
+ }
+
+ if (node) {
+ /* This device already has a pin assigned, give out a new line and device id */
+ struct irq_line *new = malloc(sizeof(*new));
+ if (new == NULL)
+ return -ENOMEM;
+
+ new->line = next_line++;
+ *line = new->line;
+ *pin = node->pin;
+ *num = next_dev++;
+
+ list_add(&new->node, &node->lines);
+
+ return 0;
+ }
+
+ return -EFAULT;
+}
+
+int irq__init(struct kvm *kvm)
+{
+ int i, r;
+
+ irq_routing = calloc(sizeof(struct kvm_irq_routing) +
+ IRQ_MAX_GSI * sizeof(struct kvm_irq_routing_entry), 1);
+ if (irq_routing == NULL)
+ return -ENOMEM;
+
+ /* Hook first 8 GSIs to master IRQCHIP */
+ for (i = 0; i < 8; i++)
+ if (i != 2)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_MASTER, i);
+
+ /* Hook next 8 GSIs to slave IRQCHIP */
+ for (i = 8; i < 16; i++)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_SLAVE, i - 8);
+
+ /* Last but not least, IOAPIC */
+ for (i = 0; i < 24; i++) {
+ if (i == 0)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_IOAPIC, 2);
+ else if (i != 2)
+ irq__add_routing(i, KVM_IRQ_ROUTING_IRQCHIP, IRQCHIP_IOAPIC, i);
+ }
+
+ r = ioctl(kvm->vm_fd, KVM_SET_GSI_ROUTING, irq_routing);
+ if (r) {
+ free(irq_routing);
+ return errno;
+ }
+
+ return 0;
+}
+
+int irq__exit(struct kvm *kvm)
+{
+ struct rb_node *ent;
+
+ free(irq_routing);
+
+ while ((ent = rb_first(&pci_tree))) {
+ struct pci_dev *dev;
+ struct irq_line *line;
+
+ dev = rb_entry(ent, struct pci_dev, node);
+ while (!list_empty(&dev->lines)) {
+ line = list_first_entry(&dev->lines, struct irq_line, node);
+ list_del(&line->node);
+ free(line);
+ }
+ rb_erase(&dev->node, &pci_tree);
+ free(dev);
+ }
+
+ return 0;
+}
+
+int irq__add_msix_route(struct kvm *kvm, struct msi_msg *msg)
+{
+ int r;
+
+ irq_routing->entries[irq_routing->nr++] =
+ (struct kvm_irq_routing_entry) {
+ .gsi = gsi,
+ .type = KVM_IRQ_ROUTING_MSI,
+ .u.msi.address_hi = msg->address_hi,
+ .u.msi.address_lo = msg->address_lo,
+ .u.msi.data = msg->data,
+ };
+
+ r = ioctl(kvm->vm_fd, KVM_SET_GSI_ROUTING, irq_routing);
+ if (r)
+ return r;
+
+ return gsi++;
+}
+
+struct rb_node *irq__get_pci_tree(void)
+{
+ return rb_first(&pci_tree);
+}
--- /dev/null
+#include "kvm/kvm-cpu.h"
+
+#include "kvm/symbol.h"
+#include "kvm/util.h"
+#include "kvm/kvm.h"
+
+#include <asm/msr-index.h>
+#include <asm/apicdef.h>
+#include <linux/err.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+
+static int debug_fd;
+
+void kvm_cpu__set_debug_fd(int fd)
+{
+ debug_fd = fd;
+}
+
+int kvm_cpu__get_debug_fd(void)
+{
+ return debug_fd;
+}
+
+static inline bool is_in_protected_mode(struct kvm_cpu *vcpu)
+{
+ return vcpu->sregs.cr0 & 0x01;
+}
+
+static inline u64 ip_to_flat(struct kvm_cpu *vcpu, u64 ip)
+{
+ u64 cs;
+
+ /*
+ * NOTE! We should take code segment base address into account here.
+ * Luckily it's usually zero because Linux uses flat memory model.
+ */
+ if (is_in_protected_mode(vcpu))
+ return ip;
+
+ cs = vcpu->sregs.cs.selector;
+
+ return ip + (cs << 4);
+}
+
+static inline u32 selector_to_base(u16 selector)
+{
+ /*
+ * KVM on Intel requires 'base' to be 'selector * 16' in real mode.
+ */
+ return (u32)selector << 4;
+}
+
+static struct kvm_cpu *kvm_cpu__new(struct kvm *kvm)
+{
+ struct kvm_cpu *vcpu;
+
+ vcpu = calloc(1, sizeof(*vcpu));
+ if (!vcpu)
+ return NULL;
+
+ vcpu->kvm = kvm;
+
+ return vcpu;
+}
+
+void kvm_cpu__delete(struct kvm_cpu *vcpu)
+{
+ if (vcpu->msrs)
+ free(vcpu->msrs);
+
+ free(vcpu);
+}
+
+static int kvm_cpu__set_lint(struct kvm_cpu *vcpu)
+{
+ struct local_apic lapic;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_LAPIC, &lapic))
+ return -1;
+
+ lapic.lvt_lint0.delivery_mode = APIC_MODE_EXTINT;
+ lapic.lvt_lint1.delivery_mode = APIC_MODE_NMI;
+
+ return ioctl(vcpu->vcpu_fd, KVM_SET_LAPIC, &lapic);
+}
+
+struct kvm_cpu *kvm_cpu__init(struct kvm *kvm, unsigned long cpu_id)
+{
+ struct kvm_cpu *vcpu;
+ int mmap_size;
+ int coalesced_offset;
+
+ vcpu = kvm_cpu__new(kvm);
+ if (!vcpu)
+ return NULL;
+
+ vcpu->cpu_id = cpu_id;
+
+ vcpu->vcpu_fd = ioctl(vcpu->kvm->vm_fd, KVM_CREATE_VCPU, cpu_id);
+ if (vcpu->vcpu_fd < 0)
+ die_perror("KVM_CREATE_VCPU ioctl");
+
+ mmap_size = ioctl(vcpu->kvm->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
+ if (mmap_size < 0)
+ die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+
+ vcpu->kvm_run = mmap(NULL, mmap_size, PROT_RW, MAP_SHARED, vcpu->vcpu_fd, 0);
+ if (vcpu->kvm_run == MAP_FAILED)
+ die("unable to mmap vcpu fd");
+
+ coalesced_offset = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_COALESCED_MMIO);
+ if (coalesced_offset)
+ vcpu->ring = (void *)vcpu->kvm_run + (coalesced_offset * PAGE_SIZE);
+
+ if (kvm_cpu__set_lint(vcpu))
+ die_perror("KVM_SET_LAPIC failed");
+
+ vcpu->is_running = true;
+
+ return vcpu;
+}
+
+static struct kvm_msrs *kvm_msrs__new(size_t nmsrs)
+{
+ struct kvm_msrs *vcpu = calloc(1, sizeof(*vcpu) + (sizeof(struct kvm_msr_entry) * nmsrs));
+
+ if (!vcpu)
+ die("out of memory");
+
+ return vcpu;
+}
+
+#define KVM_MSR_ENTRY(_index, _data) \
+ (struct kvm_msr_entry) { .index = _index, .data = _data }
+
+static void kvm_cpu__setup_msrs(struct kvm_cpu *vcpu)
+{
+ unsigned long ndx = 0;
+
+ vcpu->msrs = kvm_msrs__new(100);
+
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_SYSENTER_CS, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_SYSENTER_ESP, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_SYSENTER_EIP, 0x0);
+#ifdef CONFIG_X86_64
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_STAR, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_CSTAR, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_KERNEL_GS_BASE, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_SYSCALL_MASK, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_LSTAR, 0x0);
+#endif
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_TSC, 0x0);
+ vcpu->msrs->entries[ndx++] = KVM_MSR_ENTRY(MSR_IA32_MISC_ENABLE,
+ MSR_IA32_MISC_ENABLE_FAST_STRING);
+
+ vcpu->msrs->nmsrs = ndx;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_MSRS, vcpu->msrs) < 0)
+ die_perror("KVM_SET_MSRS failed");
+}
+
+static void kvm_cpu__setup_fpu(struct kvm_cpu *vcpu)
+{
+ vcpu->fpu = (struct kvm_fpu) {
+ .fcw = 0x37f,
+ .mxcsr = 0x1f80,
+ };
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_FPU, &vcpu->fpu) < 0)
+ die_perror("KVM_SET_FPU failed");
+}
+
+static void kvm_cpu__setup_regs(struct kvm_cpu *vcpu)
+{
+ vcpu->regs = (struct kvm_regs) {
+ /* We start the guest in 16-bit real mode */
+ .rflags = 0x0000000000000002ULL,
+
+ .rip = vcpu->kvm->boot_ip,
+ .rsp = vcpu->kvm->boot_sp,
+ .rbp = vcpu->kvm->boot_sp,
+ };
+
+ if (vcpu->regs.rip > USHRT_MAX)
+ die("ip 0x%llx is too high for real mode", (u64)vcpu->regs.rip);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_REGS, &vcpu->regs) < 0)
+ die_perror("KVM_SET_REGS failed");
+}
+
+static void kvm_cpu__setup_sregs(struct kvm_cpu *vcpu)
+{
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &vcpu->sregs) < 0)
+ die_perror("KVM_GET_SREGS failed");
+
+ vcpu->sregs.cs.selector = vcpu->kvm->boot_selector;
+ vcpu->sregs.cs.base = selector_to_base(vcpu->kvm->boot_selector);
+ vcpu->sregs.ss.selector = vcpu->kvm->boot_selector;
+ vcpu->sregs.ss.base = selector_to_base(vcpu->kvm->boot_selector);
+ vcpu->sregs.ds.selector = vcpu->kvm->boot_selector;
+ vcpu->sregs.ds.base = selector_to_base(vcpu->kvm->boot_selector);
+ vcpu->sregs.es.selector = vcpu->kvm->boot_selector;
+ vcpu->sregs.es.base = selector_to_base(vcpu->kvm->boot_selector);
+ vcpu->sregs.fs.selector = vcpu->kvm->boot_selector;
+ vcpu->sregs.fs.base = selector_to_base(vcpu->kvm->boot_selector);
+ vcpu->sregs.gs.selector = vcpu->kvm->boot_selector;
+ vcpu->sregs.gs.base = selector_to_base(vcpu->kvm->boot_selector);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_SET_SREGS, &vcpu->sregs) < 0)
+ die_perror("KVM_SET_SREGS failed");
+}
+
+/**
+ * kvm_cpu__reset_vcpu - reset virtual CPU to a known state
+ */
+void kvm_cpu__reset_vcpu(struct kvm_cpu *vcpu)
+{
+ kvm_cpu__setup_cpuid(vcpu);
+ kvm_cpu__setup_sregs(vcpu);
+ kvm_cpu__setup_regs(vcpu);
+ kvm_cpu__setup_fpu(vcpu);
+ kvm_cpu__setup_msrs(vcpu);
+}
+
+bool kvm_cpu__handle_exit(struct kvm_cpu *vcpu)
+{
+ return false;
+}
+
+static void print_dtable(const char *name, struct kvm_dtable *dtable)
+{
+ dprintf(debug_fd, " %s %016llx %08hx\n",
+ name, (u64) dtable->base, (u16) dtable->limit);
+}
+
+static void print_segment(const char *name, struct kvm_segment *seg)
+{
+ dprintf(debug_fd, " %s %04hx %016llx %08x %02hhx %x %x %x %x %x %x %x\n",
+ name, (u16) seg->selector, (u64) seg->base, (u32) seg->limit,
+ (u8) seg->type, seg->present, seg->dpl, seg->db, seg->s, seg->l, seg->g, seg->avl);
+}
+
+void kvm_cpu__show_registers(struct kvm_cpu *vcpu)
+{
+ unsigned long cr0, cr2, cr3;
+ unsigned long cr4, cr8;
+ unsigned long rax, rbx, rcx;
+ unsigned long rdx, rsi, rdi;
+ unsigned long rbp, r8, r9;
+ unsigned long r10, r11, r12;
+ unsigned long r13, r14, r15;
+ unsigned long rip, rsp;
+ struct kvm_sregs sregs;
+ unsigned long rflags;
+ struct kvm_regs regs;
+ int i;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, ®s) < 0)
+ die("KVM_GET_REGS failed");
+
+ rflags = regs.rflags;
+
+ rip = regs.rip; rsp = regs.rsp;
+ rax = regs.rax; rbx = regs.rbx; rcx = regs.rcx;
+ rdx = regs.rdx; rsi = regs.rsi; rdi = regs.rdi;
+ rbp = regs.rbp; r8 = regs.r8; r9 = regs.r9;
+ r10 = regs.r10; r11 = regs.r11; r12 = regs.r12;
+ r13 = regs.r13; r14 = regs.r14; r15 = regs.r15;
+
+ dprintf(debug_fd, "\n Registers:\n");
+ dprintf(debug_fd, " ----------\n");
+ dprintf(debug_fd, " rip: %016lx rsp: %016lx flags: %016lx\n", rip, rsp, rflags);
+ dprintf(debug_fd, " rax: %016lx rbx: %016lx rcx: %016lx\n", rax, rbx, rcx);
+ dprintf(debug_fd, " rdx: %016lx rsi: %016lx rdi: %016lx\n", rdx, rsi, rdi);
+ dprintf(debug_fd, " rbp: %016lx r8: %016lx r9: %016lx\n", rbp, r8, r9);
+ dprintf(debug_fd, " r10: %016lx r11: %016lx r12: %016lx\n", r10, r11, r12);
+ dprintf(debug_fd, " r13: %016lx r14: %016lx r15: %016lx\n", r13, r14, r15);
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
+ die("KVM_GET_REGS failed");
+
+ cr0 = sregs.cr0; cr2 = sregs.cr2; cr3 = sregs.cr3;
+ cr4 = sregs.cr4; cr8 = sregs.cr8;
+
+ dprintf(debug_fd, " cr0: %016lx cr2: %016lx cr3: %016lx\n", cr0, cr2, cr3);
+ dprintf(debug_fd, " cr4: %016lx cr8: %016lx\n", cr4, cr8);
+ dprintf(debug_fd, "\n Segment registers:\n");
+ dprintf(debug_fd, " ------------------\n");
+ dprintf(debug_fd, " register selector base limit type p dpl db s l g avl\n");
+ print_segment("cs ", &sregs.cs);
+ print_segment("ss ", &sregs.ss);
+ print_segment("ds ", &sregs.ds);
+ print_segment("es ", &sregs.es);
+ print_segment("fs ", &sregs.fs);
+ print_segment("gs ", &sregs.gs);
+ print_segment("tr ", &sregs.tr);
+ print_segment("ldt", &sregs.ldt);
+ print_dtable("gdt", &sregs.gdt);
+ print_dtable("idt", &sregs.idt);
+
+ dprintf(debug_fd, "\n APIC:\n");
+ dprintf(debug_fd, " -----\n");
+ dprintf(debug_fd, " efer: %016llx apic base: %016llx nmi: %s\n",
+ (u64) sregs.efer, (u64) sregs.apic_base,
+ (vcpu->kvm->nmi_disabled ? "disabled" : "enabled"));
+
+ dprintf(debug_fd, "\n Interrupt bitmap:\n");
+ dprintf(debug_fd, " -----------------\n");
+ for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++)
+ dprintf(debug_fd, " %016llx", (u64) sregs.interrupt_bitmap[i]);
+ dprintf(debug_fd, "\n");
+}
+
+#define MAX_SYM_LEN 128
+
+void kvm_cpu__show_code(struct kvm_cpu *vcpu)
+{
+ unsigned int code_bytes = 64;
+ unsigned int code_prologue = 43;
+ unsigned int code_len = code_bytes;
+ char sym[MAX_SYM_LEN] = SYMBOL_DEFAULT_UNKNOWN, *psym;
+ unsigned char c;
+ unsigned int i;
+ u8 *ip;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_REGS, &vcpu->regs) < 0)
+ die("KVM_GET_REGS failed");
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &vcpu->sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ ip = guest_flat_to_host(vcpu->kvm, ip_to_flat(vcpu, vcpu->regs.rip) - code_prologue);
+
+ dprintf(debug_fd, "\n Code:\n");
+ dprintf(debug_fd, " -----\n");
+
+ psym = symbol_lookup(vcpu->kvm, vcpu->regs.rip, sym, MAX_SYM_LEN);
+ if (IS_ERR(psym))
+ dprintf(debug_fd,
+ "Warning: symbol_lookup() failed to find symbol "
+ "with error: %ld\n", PTR_ERR(psym));
+
+ dprintf(debug_fd, " rip: [<%016lx>] %s\n\n", (unsigned long) vcpu->regs.rip, sym);
+
+ for (i = 0; i < code_len; i++, ip++) {
+ if (!host_ptr_in_ram(vcpu->kvm, ip))
+ break;
+
+ c = *ip;
+
+ if (ip == guest_flat_to_host(vcpu->kvm, ip_to_flat(vcpu, vcpu->regs.rip)))
+ dprintf(debug_fd, " <%02x>", c);
+ else
+ dprintf(debug_fd, " %02x", c);
+ }
+
+ dprintf(debug_fd, "\n");
+
+ dprintf(debug_fd, "\n Stack:\n");
+ dprintf(debug_fd, " ------\n");
+ kvm__dump_mem(vcpu->kvm, vcpu->regs.rsp, 32);
+}
+
+void kvm_cpu__show_page_tables(struct kvm_cpu *vcpu)
+{
+ u64 *pte1;
+ u64 *pte2;
+ u64 *pte3;
+ u64 *pte4;
+
+ if (!is_in_protected_mode(vcpu))
+ return;
+
+ if (ioctl(vcpu->vcpu_fd, KVM_GET_SREGS, &vcpu->sregs) < 0)
+ die("KVM_GET_SREGS failed");
+
+ pte4 = guest_flat_to_host(vcpu->kvm, vcpu->sregs.cr3);
+ if (!host_ptr_in_ram(vcpu->kvm, pte4))
+ return;
+
+ pte3 = guest_flat_to_host(vcpu->kvm, (*pte4 & ~0xfff));
+ if (!host_ptr_in_ram(vcpu->kvm, pte3))
+ return;
+
+ pte2 = guest_flat_to_host(vcpu->kvm, (*pte3 & ~0xfff));
+ if (!host_ptr_in_ram(vcpu->kvm, pte2))
+ return;
+
+ pte1 = guest_flat_to_host(vcpu->kvm, (*pte2 & ~0xfff));
+ if (!host_ptr_in_ram(vcpu->kvm, pte1))
+ return;
+
+ dprintf(debug_fd, "Page Tables:\n");
+ if (*pte2 & (1 << 7))
+ dprintf(debug_fd, " pte4: %016llx pte3: %016llx"
+ " pte2: %016llx\n",
+ *pte4, *pte3, *pte2);
+ else
+ dprintf(debug_fd, " pte4: %016llx pte3: %016llx pte2: %016"
+ "llx pte1: %016llx\n",
+ *pte4, *pte3, *pte2, *pte1);
+}
+
+void kvm_cpu__arch_nmi(struct kvm_cpu *cpu)
+{
+ struct kvm_lapic_state klapic;
+ struct local_apic *lapic = (void *)&klapic;
+
+ if (ioctl(cpu->vcpu_fd, KVM_GET_LAPIC, &klapic) != 0)
+ return;
+
+ if (lapic->lvt_lint1.mask)
+ return;
+
+ if (lapic->lvt_lint1.delivery_mode != APIC_MODE_NMI)
+ return;
+
+ ioctl(cpu->vcpu_fd, KVM_NMI);
+}
--- /dev/null
+#include "kvm/kvm.h"
+#include "kvm/boot-protocol.h"
+#include "kvm/cpufeature.h"
+#include "kvm/interrupt.h"
+#include "kvm/mptable.h"
+#include "kvm/util.h"
+#include "kvm/8250-serial.h"
+#include "kvm/virtio-console.h"
+
+#include <asm/bootparam.h>
+#include <linux/kvm.h>
+
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <fcntl.h>
+
+struct kvm_ext kvm_req_ext[] = {
+ { DEFINE_KVM_EXT(KVM_CAP_COALESCED_MMIO) },
+ { DEFINE_KVM_EXT(KVM_CAP_SET_TSS_ADDR) },
+ { DEFINE_KVM_EXT(KVM_CAP_PIT2) },
+ { DEFINE_KVM_EXT(KVM_CAP_USER_MEMORY) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQ_ROUTING) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQCHIP) },
+ { DEFINE_KVM_EXT(KVM_CAP_HLT) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQ_INJECT_STATUS) },
+ { DEFINE_KVM_EXT(KVM_CAP_EXT_CPUID) },
+ { 0, 0 }
+};
+
+bool kvm__arch_cpu_supports_vm(void)
+{
+ struct cpuid_regs regs;
+ u32 eax_base;
+ int feature;
+
+ regs = (struct cpuid_regs) {
+ .eax = 0x00,
+ };
+ host_cpuid(®s);
+
+ switch (regs.ebx) {
+ case CPUID_VENDOR_INTEL_1:
+ eax_base = 0x00;
+ feature = KVM__X86_FEATURE_VMX;
+ break;
+
+ case CPUID_VENDOR_AMD_1:
+ eax_base = 0x80000000;
+ feature = KVM__X86_FEATURE_SVM;
+ break;
+
+ default:
+ return false;
+ }
+
+ regs = (struct cpuid_regs) {
+ .eax = eax_base,
+ };
+ host_cpuid(®s);
+
+ if (regs.eax < eax_base + 0x01)
+ return false;
+
+ regs = (struct cpuid_regs) {
+ .eax = eax_base + 0x01
+ };
+ host_cpuid(®s);
+
+ return regs.ecx & (1 << feature);
+}
+
+/*
+ * Allocating RAM size bigger than 4GB requires us to leave a gap
+ * in the RAM which is used for PCI MMIO, hotplug, and unconfigured
+ * devices (see documentation of e820_setup_gap() for details).
+ *
+ * If we're required to initialize RAM bigger than 4GB, we will create
+ * a gap between 0xe0000000 and 0x100000000 in the guest virtual mem space.
+ */
+
+void kvm__init_ram(struct kvm *kvm)
+{
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ if (kvm->ram_size < KVM_32BIT_GAP_START) {
+ /* Use a single block of RAM for 32bit RAM */
+
+ phys_start = 0;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ kvm__register_mem(kvm, phys_start, phys_size, host_mem);
+ } else {
+ /* First RAM range from zero to the PCI gap: */
+
+ phys_start = 0;
+ phys_size = KVM_32BIT_GAP_START;
+ host_mem = kvm->ram_start;
+
+ kvm__register_mem(kvm, phys_start, phys_size, host_mem);
+
+ /* Second RAM range from 4GB to the end of RAM: */
+
+ phys_start = KVM_32BIT_MAX_MEM_SIZE;
+ phys_size = kvm->ram_size - phys_start;
+ host_mem = kvm->ram_start + phys_start;
+
+ kvm__register_mem(kvm, phys_start, phys_size, host_mem);
+ }
+}
+
+/* Arch-specific commandline setup */
+void kvm__arch_set_cmdline(char *cmdline, bool video)
+{
+ strcpy(cmdline, "noapic noacpi pci=conf1 reboot=k panic=1 i8042.direct=1 "
+ "i8042.dumbkbd=1 i8042.nopnp=1");
+ if (video)
+ strcat(cmdline, " video=vesafb console=tty0");
+ else
+ strcat(cmdline, " console=ttyS0 earlyprintk=serial i8042.noaux=1");
+}
+
+/* Architecture-specific KVM init */
+void kvm__arch_init(struct kvm *kvm, const char *hugetlbfs_path, u64 ram_size)
+{
+ struct kvm_pit_config pit_config = { .flags = 0, };
+ int ret;
+
+ ret = ioctl(kvm->vm_fd, KVM_SET_TSS_ADDR, 0xfffbd000);
+ if (ret < 0)
+ die_perror("KVM_SET_TSS_ADDR ioctl");
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_PIT2, &pit_config);
+ if (ret < 0)
+ die_perror("KVM_CREATE_PIT2 ioctl");
+
+ if (ram_size < KVM_32BIT_GAP_START) {
+ kvm->ram_size = ram_size;
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, ram_size);
+ } else {
+ kvm->ram_start = mmap_anon_or_hugetlbfs(kvm, hugetlbfs_path, ram_size + KVM_32BIT_GAP_SIZE);
+ kvm->ram_size = ram_size + KVM_32BIT_GAP_SIZE;
+ if (kvm->ram_start != MAP_FAILED)
+ /*
+ * We mprotect the gap (see kvm__init_ram() for details) PROT_NONE so that
+ * if we accidently write to it, we will know.
+ */
+ mprotect(kvm->ram_start + KVM_32BIT_GAP_START, KVM_32BIT_GAP_SIZE, PROT_NONE);
+ }
+ if (kvm->ram_start == MAP_FAILED)
+ die("out of memory");
+
+ madvise(kvm->ram_start, kvm->ram_size, MADV_MERGEABLE);
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_IRQCHIP);
+ if (ret < 0)
+ die_perror("KVM_CREATE_IRQCHIP ioctl");
+}
+
+void kvm__arch_delete_ram(struct kvm *kvm)
+{
+ munmap(kvm->ram_start, kvm->ram_size);
+}
+
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
+{
+ struct kvm_irq_level irq_level;
+
+ irq_level = (struct kvm_irq_level) {
+ {
+ .irq = irq,
+ },
+ .level = level,
+ };
+
+ if (ioctl(kvm->vm_fd, KVM_IRQ_LINE, &irq_level) < 0)
+ die_perror("KVM_IRQ_LINE failed");
+}
+
+void kvm__irq_trigger(struct kvm *kvm, int irq)
+{
+ kvm__irq_line(kvm, irq, 1);
+ kvm__irq_line(kvm, irq, 0);
+}
+
+#define BOOT_LOADER_SELECTOR 0x1000
+#define BOOT_LOADER_IP 0x0000
+#define BOOT_LOADER_SP 0x8000
+#define BOOT_CMDLINE_OFFSET 0x20000
+
+#define BOOT_PROTOCOL_REQUIRED 0x206
+#define LOAD_HIGH 0x01
+
+int load_flat_binary(struct kvm *kvm, int fd_kernel, int fd_initrd, const char *kernel_cmdline)
+{
+ void *p;
+ int nr;
+
+ /*
+ * Some architectures may support loading an initrd alongside the flat kernel,
+ * but we do not.
+ */
+ if (fd_initrd != -1)
+ pr_warning("Loading initrd with flat binary not supported.");
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ p = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
+
+ while ((nr = read(fd_kernel, p, 65536)) > 0)
+ p += nr;
+
+ kvm->boot_selector = BOOT_LOADER_SELECTOR;
+ kvm->boot_ip = BOOT_LOADER_IP;
+ kvm->boot_sp = BOOT_LOADER_SP;
+
+ return true;
+}
+
+static const char *BZIMAGE_MAGIC = "HdrS";
+
+bool load_bzimage(struct kvm *kvm, int fd_kernel,
+ int fd_initrd, const char *kernel_cmdline, u16 vidmode)
+{
+ struct boot_params *kern_boot;
+ unsigned long setup_sects;
+ struct boot_params boot;
+ size_t cmdline_size;
+ ssize_t setup_size;
+ void *p;
+ int nr;
+
+ /*
+ * See Documentation/x86/boot.txt for details no bzImage on-disk and
+ * memory layout.
+ */
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ if (read(fd_kernel, &boot, sizeof(boot)) != sizeof(boot))
+ return false;
+
+ if (memcmp(&boot.hdr.header, BZIMAGE_MAGIC, strlen(BZIMAGE_MAGIC)))
+ return false;
+
+ if (boot.hdr.version < BOOT_PROTOCOL_REQUIRED)
+ die("Too old kernel");
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
+ die_perror("lseek");
+
+ if (!boot.hdr.setup_sects)
+ boot.hdr.setup_sects = BZ_DEFAULT_SETUP_SECTS;
+ setup_sects = boot.hdr.setup_sects + 1;
+
+ setup_size = setup_sects << 9;
+ p = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
+
+ /* copy setup.bin to mem*/
+ if (read(fd_kernel, p, setup_size) != setup_size)
+ die_perror("read");
+
+ /* copy vmlinux.bin to BZ_KERNEL_START*/
+ p = guest_flat_to_host(kvm, BZ_KERNEL_START);
+
+ while ((nr = read(fd_kernel, p, 65536)) > 0)
+ p += nr;
+
+ p = guest_flat_to_host(kvm, BOOT_CMDLINE_OFFSET);
+ if (kernel_cmdline) {
+ cmdline_size = strlen(kernel_cmdline) + 1;
+ if (cmdline_size > boot.hdr.cmdline_size)
+ cmdline_size = boot.hdr.cmdline_size;
+
+ memset(p, 0, boot.hdr.cmdline_size);
+ memcpy(p, kernel_cmdline, cmdline_size - 1);
+ }
+
+ kern_boot = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, 0x00);
+
+ kern_boot->hdr.cmd_line_ptr = BOOT_CMDLINE_OFFSET;
+ kern_boot->hdr.type_of_loader = 0xff;
+ kern_boot->hdr.heap_end_ptr = 0xfe00;
+ kern_boot->hdr.loadflags |= CAN_USE_HEAP;
+ kern_boot->hdr.vid_mode = vidmode;
+
+ /*
+ * Read initrd image into guest memory
+ */
+ if (fd_initrd >= 0) {
+ struct stat initrd_stat;
+ unsigned long addr;
+
+ if (fstat(fd_initrd, &initrd_stat))
+ die_perror("fstat");
+
+ addr = boot.hdr.initrd_addr_max & ~0xfffff;
+ for (;;) {
+ if (addr < BZ_KERNEL_START)
+ die("Not enough memory for initrd");
+ else if (addr < (kvm->ram_size - initrd_stat.st_size))
+ break;
+ addr -= 0x100000;
+ }
+
+ p = guest_flat_to_host(kvm, addr);
+ nr = read(fd_initrd, p, initrd_stat.st_size);
+ if (nr != initrd_stat.st_size)
+ die("Failed to read initrd");
+
+ kern_boot->hdr.ramdisk_image = addr;
+ kern_boot->hdr.ramdisk_size = initrd_stat.st_size;
+ }
+
+ kvm->boot_selector = BOOT_LOADER_SELECTOR;
+ /*
+ * The real-mode setup code starts at offset 0x200 of a bzImage. See
+ * Documentation/x86/boot.txt for details.
+ */
+ kvm->boot_ip = BOOT_LOADER_IP + 0x200;
+ kvm->boot_sp = BOOT_LOADER_SP;
+
+ return true;
+}
+
+/**
+ * kvm__arch_setup_firmware - inject BIOS into guest system memory
+ * @kvm - guest system descriptor
+ *
+ * This function is a main routine where we poke guest memory
+ * and install BIOS there.
+ */
+int kvm__arch_setup_firmware(struct kvm *kvm)
+{
+ int r;
+
+ /* standart minimal configuration */
+ setup_bios(kvm);
+
+ /* FIXME: SMP, ACPI and friends here */
+
+ /* MP table */
+ r = mptable__init(kvm);
+
+ return r;
+}
+
+int kvm__arch_free_firmware(struct kvm *kvm)
+{
+ int r;
+
+ /* MP table */
+ r = mptable__exit(kvm);
+
+ return r;
+}
+
+void kvm__arch_periodic_poll(struct kvm *kvm)
+{
+ serial8250__update_consoles(kvm);
+ virtio_console__inject_interrupt(kvm);
+}
--- /dev/null
+#include "kvm/kvm.h"
+#include "kvm/bios.h"
+#include "kvm/apic.h"
+#include "kvm/mptable.h"
+#include "kvm/util.h"
+#include "kvm/irq.h"
+
+#include <linux/kernel.h>
+#include <string.h>
+
+#include <asm/mpspec_def.h>
+#include <linux/types.h>
+
+/*
+ * FIXME: please make sure the addresses borrowed
+ * for apic/ioapic never overlaped! We need a global
+ * tracker of system resources (including io, mmio,
+ * and friends).
+ */
+
+static unsigned int mpf_checksum(unsigned char *mp, int len)
+{
+ unsigned int sum = 0;
+
+ while (len--)
+ sum += *mp++;
+
+ return sum & 0xFF;
+}
+
+static unsigned int gen_cpu_flag(unsigned int cpu, unsigned int ncpu)
+{
+ /* sets enabled/disabled | BSP/AP processor */
+ return ( (cpu < ncpu) ? CPU_ENABLED : 0) |
+ ((cpu == 0) ? CPU_BOOTPROCESSOR : 0x00);
+}
+
+#define MPTABLE_SIG_FLOATING "_MP_"
+#define MPTABLE_OEM "KVMCPU00"
+#define MPTABLE_PRODUCTID "0.1 "
+#define MPTABLE_PCIBUSTYPE "PCI "
+#define MPTABLE_ISABUSTYPE "ISA "
+
+#define MPTABLE_STRNCPY(d, s) memcpy(d, s, sizeof(d))
+
+/* It should be more than enough */
+#define MPTABLE_MAX_SIZE (32 << 20)
+
+/*
+ * Too many cpus will require x2apic mode
+ * and rather ACPI support so we limit it
+ * here for a while.
+ */
+#define MPTABLE_MAX_CPUS 255
+
+static void mptable_add_irq_src(struct mpc_intsrc *mpc_intsrc,
+ u16 srcbusid, u16 srcbusirq,
+ u16 dstapic, u16 dstirq)
+{
+ *mpc_intsrc = (struct mpc_intsrc) {
+ .type = MP_INTSRC,
+ .irqtype = mp_INT,
+ .irqflag = MP_IRQDIR_DEFAULT,
+ .srcbus = srcbusid,
+ .srcbusirq = srcbusirq,
+ .dstapic = dstapic,
+ .dstirq = dstirq
+ };
+}
+
+/**
+ * mptable_setup - create mptable and fill guest memory with it
+ */
+int mptable__init(struct kvm *kvm)
+{
+ unsigned long real_mpc_table, real_mpf_intel, size;
+ struct mpf_intel *mpf_intel;
+ struct mpc_table *mpc_table;
+ struct mpc_cpu *mpc_cpu;
+ struct mpc_bus *mpc_bus;
+ struct mpc_ioapic *mpc_ioapic;
+ struct mpc_intsrc *mpc_intsrc;
+ struct rb_node *pci_tree;
+
+ const int pcibusid = 0;
+ const int isabusid = 1;
+
+ unsigned int i, nentries = 0, ncpus = kvm->nrcpus;
+ unsigned int ioapicid;
+ void *last_addr;
+
+ /* That is where MP table will be in guest memory */
+ real_mpc_table = ALIGN(MB_BIOS_BEGIN + bios_rom_size, 16);
+
+ if (ncpus > MPTABLE_MAX_CPUS) {
+ pr_warning("Too many cpus: %d limited to %d",
+ ncpus, MPTABLE_MAX_CPUS);
+ ncpus = MPTABLE_MAX_CPUS;
+ }
+
+ mpc_table = calloc(1, MPTABLE_MAX_SIZE);
+ if (!mpc_table)
+ return -ENOMEM;
+
+ MPTABLE_STRNCPY(mpc_table->signature, MPC_SIGNATURE);
+ MPTABLE_STRNCPY(mpc_table->oem, MPTABLE_OEM);
+ MPTABLE_STRNCPY(mpc_table->productid, MPTABLE_PRODUCTID);
+
+ mpc_table->spec = 4;
+ mpc_table->lapic = APIC_ADDR(0);
+ mpc_table->oemcount = ncpus; /* will be updated again at end */
+
+ /*
+ * CPUs enumeration. Technically speaking we should
+ * ask either host or HV for apic version supported
+ * but for a while we simply put some random value
+ * here.
+ */
+ mpc_cpu = (void *)&mpc_table[1];
+ for (i = 0; i < ncpus; i++) {
+ mpc_cpu->type = MP_PROCESSOR;
+ mpc_cpu->apicid = i;
+ mpc_cpu->apicver = KVM_APIC_VERSION;
+ mpc_cpu->cpuflag = gen_cpu_flag(i, ncpus);
+ mpc_cpu->cpufeature = 0x600; /* some default value */
+ mpc_cpu->featureflag = 0x201; /* some default value */
+ mpc_cpu++;
+ }
+
+ last_addr = (void *)mpc_cpu;
+ nentries += ncpus;
+
+ /*
+ * PCI buses.
+ * FIXME: Some callback here to obtain real number
+ * of PCI buses present in system.
+ */
+ mpc_bus = last_addr;
+ mpc_bus->type = MP_BUS;
+ mpc_bus->busid = pcibusid;
+ MPTABLE_STRNCPY(mpc_bus->bustype, MPTABLE_PCIBUSTYPE);
+
+ last_addr = (void *)&mpc_bus[1];
+ nentries++;
+
+ /*
+ * ISA bus.
+ * FIXME: Same issue as for PCI bus.
+ */
+ mpc_bus = last_addr;
+ mpc_bus->type = MP_BUS;
+ mpc_bus->busid = isabusid;
+ MPTABLE_STRNCPY(mpc_bus->bustype, MPTABLE_ISABUSTYPE);
+
+ last_addr = (void *)&mpc_bus[1];
+ nentries++;
+
+ /*
+ * IO-APIC chip.
+ */
+ ioapicid = ncpus + 1;
+ mpc_ioapic = last_addr;
+ mpc_ioapic->type = MP_IOAPIC;
+ mpc_ioapic->apicid = ioapicid;
+ mpc_ioapic->apicver = KVM_APIC_VERSION;
+ mpc_ioapic->flags = MPC_APIC_USABLE;
+ mpc_ioapic->apicaddr = IOAPIC_ADDR(0);
+
+ last_addr = (void *)&mpc_ioapic[1];
+ nentries++;
+
+ /*
+ * IRQ sources.
+ *
+ * FIXME: Same issue as with buses. We definitely
+ * need kind of collector routine which enumerate
+ * resources used first and pass them here.
+ * At moment we know we have only virtio block device
+ * and virtio console but this is g00berfish.
+ *
+ * Also note we use PCI irqs here, no for ISA bus yet.
+ */
+
+ for (pci_tree = irq__get_pci_tree(); pci_tree; pci_tree = rb_next(pci_tree)) {
+ struct pci_dev *dev = rb_entry(pci_tree, struct pci_dev, node);
+ struct irq_line *irq_line;
+
+ list_for_each_entry(irq_line, &dev->lines, node) {
+ unsigned char srcbusirq;
+
+ srcbusirq = (dev->id << 2) | (dev->pin - 1);
+
+ mpc_intsrc = last_addr;
+
+ mptable_add_irq_src(mpc_intsrc, pcibusid, srcbusirq, ioapicid, irq_line->line);
+ last_addr = (void *)&mpc_intsrc[1];
+ nentries++;
+ }
+ }
+
+ /*
+ * Local IRQs assignment (LINT0, LINT1)
+ */
+ mpc_intsrc = last_addr;
+ mpc_intsrc->type = MP_LINTSRC;
+ mpc_intsrc->irqtype = mp_ExtINT;
+ mpc_intsrc->irqtype = mp_INT;
+ mpc_intsrc->irqflag = MP_IRQDIR_DEFAULT;
+ mpc_intsrc->srcbus = isabusid;
+ mpc_intsrc->srcbusirq = 0;
+ mpc_intsrc->dstapic = 0; /* FIXME: BSP apic */
+ mpc_intsrc->dstirq = 0; /* LINT0 */
+
+ last_addr = (void *)&mpc_intsrc[1];
+ nentries++;
+
+ mpc_intsrc = last_addr;
+ mpc_intsrc->type = MP_LINTSRC;
+ mpc_intsrc->irqtype = mp_NMI;
+ mpc_intsrc->irqflag = MP_IRQDIR_DEFAULT;
+ mpc_intsrc->srcbus = isabusid;
+ mpc_intsrc->srcbusirq = 0;
+ mpc_intsrc->dstapic = 0; /* FIXME: BSP apic */
+ mpc_intsrc->dstirq = 1; /* LINT1 */
+
+ last_addr = (void *)&mpc_intsrc[1];
+ nentries++;
+
+ /*
+ * Floating MP table finally.
+ */
+ real_mpf_intel = ALIGN((unsigned long)last_addr - (unsigned long)mpc_table, 16);
+ mpf_intel = (void *)((unsigned long)mpc_table + real_mpf_intel);
+
+ MPTABLE_STRNCPY(mpf_intel->signature, MPTABLE_SIG_FLOATING);
+ mpf_intel->length = 1;
+ mpf_intel->specification= 4;
+ mpf_intel->physptr = (unsigned int)real_mpc_table;
+ mpf_intel->checksum = -mpf_checksum((unsigned char *)mpf_intel, sizeof(*mpf_intel));
+
+ /*
+ * No last_addr inclrement here please, we need last
+ * active position here to compute table size.
+ */
+
+ /*
+ * Don't forget to update header in fixed table.
+ */
+ mpc_table->oemcount = nentries;
+ mpc_table->length = last_addr - (void *)mpc_table;
+ mpc_table->checksum = -mpf_checksum((unsigned char *)mpc_table, mpc_table->length);
+
+
+ /*
+ * We will copy the whole table, no need to separate
+ * floating structure and table itkvm.
+ */
+ size = (unsigned long)mpf_intel + sizeof(*mpf_intel) - (unsigned long)mpc_table;
+
+ /*
+ * The finial check -- never get out of system bios
+ * area. Lets also check for allocated memory overrun,
+ * in real it's late but still usefull.
+ */
+
+ if (size > (unsigned long)(MB_BIOS_END - bios_rom_size) ||
+ size > MPTABLE_MAX_SIZE) {
+ free(mpc_table);
+ pr_err("MP table is too big");
+
+ return -E2BIG;
+ }
+
+ /*
+ * OK, it is time to move it to guest memory.
+ */
+ memcpy(guest_flat_to_host(kvm, real_mpc_table), mpc_table, size);
+
+ free(mpc_table);
+
+ return 0;
+}
+
+int mptable__exit(struct kvm *kvm)
+{
+ return 0;
+}
#include <stdarg.h>
#include <ctype.h>
#include <errno.h>
+#include <stdint.h>
#include "event-parse.h"
#include "event-utils.h"
if (!string->str)
die("malloc str");
- args[i] = (unsigned long long)string->str;
+ args[i] = (uintptr_t)string->str;
strings = string;
trace_seq_destroy(&str);
break;
*
* /sys/kernel/debug/tracing/events/.../.../format
*/
-int pevent_parse_event(struct pevent *pevent,
- const char *buf, unsigned long size,
- const char *sys)
+enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
+ unsigned long size, const char *sys)
{
struct event_format *event;
int ret;
event = alloc_event();
if (!event)
- return -ENOMEM;
+ return PEVENT_ERRNO__MEM_ALLOC_FAILED;
event->name = event_read_name();
if (!event->name) {
/* Bad event? */
- free(event);
- return -1;
+ ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+ goto event_alloc_failed;
}
if (strcmp(sys, "ftrace") == 0) {
-
event->flags |= EVENT_FL_ISFTRACE;
if (strcmp(event->name, "bprint") == 0)
}
event->id = event_read_id();
- if (event->id < 0)
- die("failed to read event id");
+ if (event->id < 0) {
+ ret = PEVENT_ERRNO__READ_ID_FAILED;
+ /*
+ * This isn't an allocation error actually.
+ * But as the ID is critical, just bail out.
+ */
+ goto event_alloc_failed;
+ }
event->system = strdup(sys);
- if (!event->system)
- die("failed to allocate system");
+ if (!event->system) {
+ ret = PEVENT_ERRNO__MEM_ALLOC_FAILED;
+ goto event_alloc_failed;
+ }
/* Add pevent to event so that it can be referenced */
event->pevent = pevent;
ret = event_read_format(event);
if (ret < 0) {
- do_warning("failed to read event format for %s", event->name);
- goto event_failed;
+ ret = PEVENT_ERRNO__READ_FORMAT_FAILED;
+ goto event_parse_failed;
}
/*
ret = event_read_print(event);
if (ret < 0) {
- do_warning("failed to read event print fmt for %s",
- event->name);
show_warning = 1;
- goto event_failed;
+ ret = PEVENT_ERRNO__READ_PRINT_FAILED;
+ goto event_parse_failed;
}
show_warning = 1;
struct print_arg *arg, **list;
/* old ftrace had no args */
-
list = &event->print_fmt.args;
for (field = event->format.fields; field; field = field->next) {
arg = alloc_arg();
- *list = arg;
- list = &arg->next;
arg->type = PRINT_FIELD;
arg->field.name = strdup(field->name);
if (!arg->field.name) {
- do_warning("failed to allocate field name");
event->flags |= EVENT_FL_FAILED;
- return -1;
+ free_arg(arg);
+ return PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED;
}
arg->field.field = field;
+ *list = arg;
+ list = &arg->next;
}
return 0;
}
return 0;
- event_failed:
+ event_parse_failed:
event->flags |= EVENT_FL_FAILED;
/* still add it even if it failed */
add_event(pevent, event);
- return -1;
+ return ret;
+
+ event_alloc_failed:
+ free(event->system);
+ free(event->name);
+ free(event);
+ return ret;
+}
+
+#undef _PE
+#define _PE(code, str) str
+static const char * const pevent_error_str[] = {
+ PEVENT_ERRORS
+};
+#undef _PE
+
+int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
+ char *buf, size_t buflen)
+{
+ int idx;
+ const char *msg;
+
+ if (errnum >= 0) {
+ msg = strerror_r(errnum, buf, buflen);
+ if (msg != buf) {
+ size_t len = strlen(msg);
+ char *c = mempcpy(buf, msg, min(buflen-1, len));
+ *c = '\0';
+ }
+ return 0;
+ }
+
+ if (errnum <= __PEVENT_ERRNO__START ||
+ errnum >= __PEVENT_ERRNO__END)
+ return -1;
+
+ idx = errnum - __PEVENT_ERRNO__START - 1;
+ msg = pevent_error_str[idx];
+
+ switch (errnum) {
+ case PEVENT_ERRNO__MEM_ALLOC_FAILED:
+ case PEVENT_ERRNO__PARSE_EVENT_FAILED:
+ case PEVENT_ERRNO__READ_ID_FAILED:
+ case PEVENT_ERRNO__READ_FORMAT_FAILED:
+ case PEVENT_ERRNO__READ_PRINT_FAILED:
+ case PEVENT_ERRNO__OLD_FTRACE_ARG_FAILED:
+ snprintf(buf, buflen, "%s", msg);
+ break;
+
+ default:
+ /* cannot reach here */
+ break;
+ }
+
+ return 0;
}
int get_field_val(struct trace_seq *s, struct format_field *field,
PEVENT_NSEC_OUTPUT = 1, /* output in NSECS */
};
+#define PEVENT_ERRORS \
+ _PE(MEM_ALLOC_FAILED, "failed to allocate memory"), \
+ _PE(PARSE_EVENT_FAILED, "failed to parse event"), \
+ _PE(READ_ID_FAILED, "failed to read event id"), \
+ _PE(READ_FORMAT_FAILED, "failed to read event format"), \
+ _PE(READ_PRINT_FAILED, "failed to read event print fmt"), \
+ _PE(OLD_FTRACE_ARG_FAILED,"failed to allocate field name for ftrace")
+
+#undef _PE
+#define _PE(__code, __str) PEVENT_ERRNO__ ## __code
+enum pevent_errno {
+ PEVENT_ERRNO__SUCCESS = 0,
+
+ /*
+ * Choose an arbitrary negative big number not to clash with standard
+ * errno since SUS requires the errno has distinct positive values.
+ * See 'Issue 6' in the link below.
+ *
+ * http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/errno.h.html
+ */
+ __PEVENT_ERRNO__START = -100000,
+
+ PEVENT_ERRORS,
+
+ __PEVENT_ERRNO__END,
+};
+#undef _PE
+
struct cmdline;
struct cmdline_list;
struct func_map;
int pevent_parse_header_page(struct pevent *pevent, char *buf, unsigned long size,
int long_size);
-int pevent_parse_event(struct pevent *pevent, const char *buf,
- unsigned long size, const char *sys);
+enum pevent_errno pevent_parse_event(struct pevent *pevent, const char *buf,
+ unsigned long size, const char *sys);
void *pevent_get_field_raw(struct trace_seq *s, struct event_format *event,
const char *name, struct pevent_record *record,
const char *pevent_data_comm_from_pid(struct pevent *pevent, int pid);
void pevent_event_info(struct trace_seq *s, struct event_format *event,
struct pevent_record *record);
+int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum,
+ char *buf, size_t buflen);
struct event_format **pevent_list_events(struct pevent *pevent, enum event_sort_type);
struct format_field **pevent_event_common_fields(struct event_format *event);
void __vwarning(const char *fmt, ...);
void __vpr_stat(const char *fmt, ...);
+#define min(x, y) ({ \
+ typeof(x) _min1 = (x); \
+ typeof(y) _min2 = (y); \
+ (void) (&_min1 == &_min2); \
+ _min1 < _min2 ? _min1 : _min2; })
+
static inline char *strim(char *string)
{
char *ret;
#install-html: html
# '$(SHELL_PATH_SQ)' ./install-webdoc.sh $(DESTDIR)$(htmldir)
-../PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
- $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) PERF-VERSION-FILE
+$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
+ $(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) $(OUTPUT)PERF-VERSION-FILE
--include ../PERF-VERSION-FILE
+-include $(OUTPUT)PERF-VERSION-FILE
#
# Determine "include::" file references in asciidoc files.
--- /dev/null
+perf supports a simple JIT interface to resolve symbols for dynamic code generated
+by a JIT.
+
+The JIT has to write a /tmp/perf-%d.map (%d = pid of process) file
+
+This is a text file.
+
+Each line has the following format, fields separated with spaces:
+
+START SIZE symbolname
+
+START and SIZE are hex numbers without 0x.
+symbolname is the rest of the line, so it could contain special characters.
+
+The ownership of the file has to match the process.
This command displays the symbolic event types which can be selected in the
various perf commands with the -e option.
+[[EVENT_MODIFIERS]]
EVENT MODIFIERS
---------------
Events can optionally have a modifer by appending a colon and one or
-more modifiers. Modifiers allow the user to restrict when events are
-counted with 'u' for user-space, 'k' for kernel, 'h' for hypervisor.
-Additional modifiers are 'G' for guest counting (in KVM guests) and 'H'
-for host counting (not in KVM guests).
+more modifiers. Modifiers allow the user to restrict the events to be
+counted. The following modifiers exist:
+
+ u - user-space counting
+ k - kernel counting
+ h - hypervisor counting
+ G - guest counting (in KVM guests)
+ H - host counting (not in KVM guests)
+ p - precise level
The 'p' modifier can be used for specifying how precise the instruction
-address should be. The 'p' modifier is currently only implemented for
-Intel PEBS and can be specified multiple times:
- 0 - SAMPLE_IP can have arbitrary skid
- 1 - SAMPLE_IP must have constant skid
- 2 - SAMPLE_IP requested to have 0 skid
- 3 - SAMPLE_IP must have 0 skid
+address should be. The 'p' modifier can be specified multiple times:
+
+ 0 - SAMPLE_IP can have arbitrary skid
+ 1 - SAMPLE_IP must have constant skid
+ 2 - SAMPLE_IP requested to have 0 skid
+ 3 - SAMPLE_IP must have 0 skid
+
+For Intel systems precise event sampling is implemented with PEBS
+which supports up to precise-level 2.
-The PEBS implementation now supports up to 2.
+On AMD systems it is implemented using IBS (up to precise-level 2).
+The precise modifier works with event types 0x76 (cpu-cycles, CPU
+clocks not halted) and 0xC1 (micro-ops retired). Both events map to
+IBS execution sampling (IBS op) with the IBS Op Counter Control bit
+(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+Manual Volume 2: System Programming, 13.3 Instruction-Based
+Sampling). Examples to use IBS:
+
+ perf record -a -e cpu-cycles:p ... # use ibs op counting cycles
+ perf record -a -e r076:p ... # same as -e cpu-cycles:p
+ perf record -a -e r0C1:p ... # use ibs op counting micro-ops
RAW HARDWARE EVENT DESCRIPTOR
-----------------------------
of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+Note: Only the following bit fields can be set in x86 counter
+registers: event, umask, edge, inv, cmask. Esp. guest/host only and
+OS/user mode flags must be setup using <<EVENT_MODIFIERS, EVENT
+MODIFIERS>>.
+
Example:
If the Intel docs for a QM720 Core i7 describe an event as:
linkperf:perf-stat[1], linkperf:perf-top[1],
linkperf:perf-record[1],
http://www.intel.com/Assets/PDF/manual/253669.pdf[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
-http://support.amd.com/us/Processor_TechDocs/24593.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
+http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
descriptions below):
----
- use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/perf-script-Util/lib";
- use lib "./perf-script-Util/lib";
+ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+ use lib "./Perf-Trace-Util/lib";
use Perf::Trace::Core;
use Perf::Trace::Context;
use Perf::Trace::Util;
import sys
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
- '/scripts/python/perf-script-Util/lib/Perf/Trace')
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
from perf_trace_context import *
from Core import *
import sys
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
- '/scripts/python/perf-script-Util/lib/Perf/Trace')
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
from perf_trace_context import *
from Core import *
import sys
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
- '/scripts/python/perf-script-Util/lib/Perf/Trace')
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
from perf_trace_context import *
from Core import *
drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
drwxr-xr-x 2 trz trz 4096 2010-01-26 22:29 bin
-rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-script.py
-drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 perf-script-Util
+drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 Perf-Trace-Util
-rw-r--r-- 1 trz trz 1462 2010-01-26 22:30 syscall-counts.py
----
import sys
sys.path.append(os.environ['PERF_EXEC_PATH'] + \
- '/scripts/python/perf-script-Util/lib/Perf/Trace')
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
from perf_trace_context import *
from Core import *
#
# Define NO_NEWT if you do not want TUI support.
#
+# Define NO_GTK2 if you do not want GTK+ GUI support.
+#
# Define NO_DEMANGLE if you do not want C++ symbol demangling.
+#
+# Define NO_LIBELF if you do not want libelf dependency (e.g. cross-builds)
+#
+# Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
+# backtrace post unwind.
$(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
-e s/s390x/s390/ -e s/parisc64/parisc/ \
-e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-e s/sh[234].*/sh/ )
+NO_PERF_REGS := 1
CC = $(CROSS_COMPILE)gcc
AR = $(CROSS_COMPILE)ar
# Additional ARCH settings for x86
ifeq ($(ARCH),i386)
- ARCH := x86
+ ARCH := x86
+ NO_PERF_REGS := 0
+ LIBUNWIND_LIBS = -lunwind -lunwind-x86
endif
ifeq ($(ARCH),x86_64)
ARCH := x86
ARCH_CFLAGS := -DARCH_X86_64
ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
endif
+ NO_PERF_REGS := 0
+ LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
endif
# Treat warnings as errors unless directed not to
PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
endif
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
EXTLIBS = -lpthread -lrt -lelf -lm
ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
ALL_LDFLAGS = $(LDFLAGS)
TRACE_EVENT_DIR = ../lib/traceevent/
-ifeq ("$(origin O)", "command line")
- TE_PATH=$(OUTPUT)/
+ifneq ($(OUTPUT),)
+ TE_PATH=$(OUTPUT)
else
- TE_PATH=$(TRACE_EVENT_DIR)/
+ TE_PATH=$(TRACE_EVENT_DIR)
endif
LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
LIB_H += util/target.h
LIB_H += util/rblist.h
LIB_H += util/intlist.h
+LIB_H += util/perf_regs.h
+LIB_H += util/unwind.h
+LIB_H += ui/helpline.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
LIB_OBJS += $(OUTPUT)util/wrapper.o
LIB_OBJS += $(OUTPUT)util/sigchain.o
LIB_OBJS += $(OUTPUT)util/symbol.o
+LIB_OBJS += $(OUTPUT)util/symbol-elf.o
LIB_OBJS += $(OUTPUT)util/dso-test-data.o
LIB_OBJS += $(OUTPUT)util/color.o
LIB_OBJS += $(OUTPUT)util/pager.o
LIB_OBJS += $(OUTPUT)util/target.o
LIB_OBJS += $(OUTPUT)util/rblist.o
LIB_OBJS += $(OUTPUT)util/intlist.o
+LIB_OBJS += $(OUTPUT)ui/helpline.o
+LIB_OBJS += $(OUTPUT)ui/stdio/hist.o
BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
-
BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
-
# Benchmark modules
BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-include config.mak.autogen
-include config.mak
-ifndef NO_DWARF
-FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
-ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y)
- msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+ifdef NO_LIBELF
NO_DWARF := 1
-endif # Dwarf support
-endif # NO_DWARF
-
--include arch/$(ARCH)/Makefile
-
-ifneq ($(OUTPUT),)
- BASIC_CFLAGS += -I$(OUTPUT)
-endif
-
+ NO_DEMANGLE := 1
+ NO_LIBUNWIND := 1
+else
FLAGS_LIBELF=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS)
ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y)
FLAGS_GLIBC=$(ALL_CFLAGS) $(ALL_LDFLAGS)
ifneq ($(call try-cc,$(SOURCE_GLIBC),$(FLAGS_GLIBC)),y)
msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
else
- msg := $(error No libelf.h/libelf found, please install libelf-dev/elfutils-libelf-devel);
+ NO_LIBELF := 1
+ NO_DWARF := 1
+ NO_DEMANGLE := 1
endif
endif
+endif # NO_LIBELF
+
+ifndef NO_LIBUNWIND
+# for linking with debug library, run like:
+# make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+ifdef LIBUNWIND_DIR
+ LIBUNWIND_CFLAGS := -I$(LIBUNWIND_DIR)/include
+ LIBUNWIND_LDFLAGS := -L$(LIBUNWIND_DIR)/lib
+endif
+
+FLAGS_UNWIND=$(LIBUNWIND_CFLAGS) $(ALL_CFLAGS) $(LIBUNWIND_LDFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(LIBUNWIND_LIBS)
+ifneq ($(call try-cc,$(SOURCE_LIBUNWIND),$(FLAGS_UNWIND)),y)
+ msg := $(warning No libunwind found, disabling post unwind support. Please install libunwind-dev[el] >= 0.99);
+ NO_LIBUNWIND := 1
+endif # Libunwind support
+endif # NO_LIBUNWIND
+
+-include arch/$(ARCH)/Makefile
+
+ifneq ($(OUTPUT),)
+ BASIC_CFLAGS += -I$(OUTPUT)
+endif
+
+ifdef NO_LIBELF
+BASIC_CFLAGS += -DNO_LIBELF_SUPPORT
+
+EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
+
+# Remove ELF/DWARF dependent codes
+LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/probe-event.o,$(LIB_OBJS))
+LIB_OBJS := $(filter-out $(OUTPUT)util/probe-finder.o,$(LIB_OBJS))
+
+BUILTIN_OBJS := $(filter-out $(OUTPUT)builtin-probe.o,$(BUILTIN_OBJS))
+
+# Use minimal symbol handling
+LIB_OBJS += $(OUTPUT)util/symbol-minimal.o
+
+else # NO_LIBELF
ifneq ($(call try-cc,$(SOURCE_ELF_MMAP),$(FLAGS_COMMON)),y)
BASIC_CFLAGS += -DLIBELF_NO_MMAP
endif
+FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
+ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y)
+ msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+ NO_DWARF := 1
+endif # Dwarf support
+
ifndef NO_DWARF
ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
LIB_OBJS += $(OUTPUT)util/dwarf-aux.o
endif # PERF_HAVE_DWARF_REGS
endif # NO_DWARF
+endif # NO_LIBELF
+
+ifdef NO_LIBUNWIND
+ BASIC_CFLAGS += -DNO_LIBUNWIND_SUPPORT
+else
+ EXTLIBS += $(LIBUNWIND_LIBS)
+ BASIC_CFLAGS := $(LIBUNWIND_CFLAGS) $(BASIC_CFLAGS)
+ BASIC_LDFLAGS := $(LIBUNWIND_LDFLAGS) $(BASIC_LDFLAGS)
+ LIB_OBJS += $(OUTPUT)util/unwind.o
+endif
ifdef NO_NEWT
BASIC_CFLAGS += -DNO_NEWT_SUPPORT
LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
LIB_OBJS += $(OUTPUT)ui/browsers/map.o
- LIB_OBJS += $(OUTPUT)ui/helpline.o
LIB_OBJS += $(OUTPUT)ui/progress.o
LIB_OBJS += $(OUTPUT)ui/util.o
LIB_OBJS += $(OUTPUT)ui/tui/setup.o
LIB_OBJS += $(OUTPUT)ui/tui/util.o
+ LIB_OBJS += $(OUTPUT)ui/tui/helpline.o
LIB_H += ui/browser.h
LIB_H += ui/browsers/map.h
- LIB_H += ui/helpline.h
LIB_H += ui/keysyms.h
LIB_H += ui/libslang.h
LIB_H += ui/progress.h
ifdef NO_GTK2
BASIC_CFLAGS += -DNO_GTK2_SUPPORT
else
- FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0)
+ FLAGS_GTK2=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) $(shell pkg-config --libs --cflags gtk+-2.0 2>/dev/null)
ifneq ($(call try-cc,$(SOURCE_GTK2),$(FLAGS_GTK2)),y)
msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
BASIC_CFLAGS += -DNO_GTK2_SUPPORT
ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y)
BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR
endif
- BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
- EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
+ BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0 2>/dev/null)
+ EXTLIBS += $(shell pkg-config --libs gtk+-2.0 2>/dev/null)
LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
LIB_OBJS += $(OUTPUT)ui/gtk/util.o
+ LIB_OBJS += $(OUTPUT)ui/gtk/helpline.o
# Make sure that it'd be included only once.
ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),)
LIB_OBJS += $(OUTPUT)ui/setup.o
endif
endif
+ifeq ($(NO_PERF_REGS),0)
+ ifeq ($(ARCH),x86)
+ LIB_H += arch/x86/include/perf_regs.h
+ endif
+else
+ BASIC_CFLAGS += -DNO_PERF_REGS
+endif
ifdef NO_STRLCPY
BASIC_CFLAGS += -DNO_STRLCPY
template_dir_SQ = $(subst ','\'',$(template_dir))
htmldir_SQ = $(subst ','\'',$(htmldir))
prefix_SQ = $(subst ','\'',$(prefix))
+sysconfdir_SQ = $(subst ','\'',$(sysconfdir))
SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
# over the general rule for .o
$(OUTPUT)util/%-flex.o: $(OUTPUT)util/%-flex.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -Iutil/ -w $<
+ $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -w $<
$(OUTPUT)util/%-bison.o: $(OUTPUT)util/%-bison.c $(OUTPUT)PERF-CFLAGS
- $(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -Iutil/ -w $<
+ $(QUIET_CC)$(CC) -o $@ -c -Iutil/ $(ALL_CFLAGS) -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $<
$(OUTPUT)%.o: %.c $(OUTPUT)PERF-CFLAGS
$(QUIET_CC)$(CC) -o $@ -c $(ALL_CFLAGS) $<
# libtraceevent.a
$(LIBTRACEEVENT):
- $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) $(COMMAND_O) libtraceevent.a
+ $(QUIET_SUBDIR0)$(TRACE_EVENT_DIR) $(QUIET_SUBDIR1) O=$(OUTPUT) libtraceevent.a
help:
@echo 'Perf make targets:'
$(INSTALL) scripts/python/Perf-Trace-Util/lib/Perf/Trace/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/Perf-Trace-Util/lib/Perf/Trace'
$(INSTALL) scripts/python/*.py -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python'
$(INSTALL) scripts/python/bin/* -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/python/bin'
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'
+ $(INSTALL) bash_completion '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
install-python_ext:
$(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
PERF_HAVE_DWARF_REGS := 1
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+endif
LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
--- /dev/null
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include "../../util/types.h"
+#include "../../../../../arch/x86/include/asm/perf_regs.h"
+
+#ifndef ARCH_X86_64
+#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#else
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#endif
+#define PERF_REG_IP PERF_REG_X86_IP
+#define PERF_REG_SP PERF_REG_X86_SP
+
+static inline const char *perf_reg_name(int id)
+{
+ switch (id) {
+ case PERF_REG_X86_AX:
+ return "AX";
+ case PERF_REG_X86_BX:
+ return "BX";
+ case PERF_REG_X86_CX:
+ return "CX";
+ case PERF_REG_X86_DX:
+ return "DX";
+ case PERF_REG_X86_SI:
+ return "SI";
+ case PERF_REG_X86_DI:
+ return "DI";
+ case PERF_REG_X86_BP:
+ return "BP";
+ case PERF_REG_X86_SP:
+ return "SP";
+ case PERF_REG_X86_IP:
+ return "IP";
+ case PERF_REG_X86_FLAGS:
+ return "FLAGS";
+ case PERF_REG_X86_CS:
+ return "CS";
+ case PERF_REG_X86_SS:
+ return "SS";
+ case PERF_REG_X86_DS:
+ return "DS";
+ case PERF_REG_X86_ES:
+ return "ES";
+ case PERF_REG_X86_FS:
+ return "FS";
+ case PERF_REG_X86_GS:
+ return "GS";
+#ifdef ARCH_X86_64
+ case PERF_REG_X86_R8:
+ return "R8";
+ case PERF_REG_X86_R9:
+ return "R9";
+ case PERF_REG_X86_R10:
+ return "R10";
+ case PERF_REG_X86_R11:
+ return "R11";
+ case PERF_REG_X86_R12:
+ return "R12";
+ case PERF_REG_X86_R13:
+ return "R13";
+ case PERF_REG_X86_R14:
+ return "R14";
+ case PERF_REG_X86_R15:
+ return "R15";
+#endif /* ARCH_X86_64 */
+ default:
+ return NULL;
+ }
+
+ return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
--- /dev/null
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+#ifdef ARCH_X86_64
+int unwind__arch_reg_id(int regnum)
+{
+ int id;
+
+ switch (regnum) {
+ case UNW_X86_64_RAX:
+ id = PERF_REG_X86_AX;
+ break;
+ case UNW_X86_64_RDX:
+ id = PERF_REG_X86_DX;
+ break;
+ case UNW_X86_64_RCX:
+ id = PERF_REG_X86_CX;
+ break;
+ case UNW_X86_64_RBX:
+ id = PERF_REG_X86_BX;
+ break;
+ case UNW_X86_64_RSI:
+ id = PERF_REG_X86_SI;
+ break;
+ case UNW_X86_64_RDI:
+ id = PERF_REG_X86_DI;
+ break;
+ case UNW_X86_64_RBP:
+ id = PERF_REG_X86_BP;
+ break;
+ case UNW_X86_64_RSP:
+ id = PERF_REG_X86_SP;
+ break;
+ case UNW_X86_64_R8:
+ id = PERF_REG_X86_R8;
+ break;
+ case UNW_X86_64_R9:
+ id = PERF_REG_X86_R9;
+ break;
+ case UNW_X86_64_R10:
+ id = PERF_REG_X86_R10;
+ break;
+ case UNW_X86_64_R11:
+ id = PERF_REG_X86_R11;
+ break;
+ case UNW_X86_64_R12:
+ id = PERF_REG_X86_R12;
+ break;
+ case UNW_X86_64_R13:
+ id = PERF_REG_X86_R13;
+ break;
+ case UNW_X86_64_R14:
+ id = PERF_REG_X86_R14;
+ break;
+ case UNW_X86_64_R15:
+ id = PERF_REG_X86_R15;
+ break;
+ case UNW_X86_64_RIP:
+ id = PERF_REG_X86_IP;
+ break;
+ default:
+ pr_err("unwind: invalid reg id %d\n", regnum);
+ return -EINVAL;
+ }
+
+ return id;
+}
+#else
+int unwind__arch_reg_id(int regnum)
+{
+ int id;
+
+ switch (regnum) {
+ case UNW_X86_EAX:
+ id = PERF_REG_X86_AX;
+ break;
+ case UNW_X86_EDX:
+ id = PERF_REG_X86_DX;
+ break;
+ case UNW_X86_ECX:
+ id = PERF_REG_X86_CX;
+ break;
+ case UNW_X86_EBX:
+ id = PERF_REG_X86_BX;
+ break;
+ case UNW_X86_ESI:
+ id = PERF_REG_X86_SI;
+ break;
+ case UNW_X86_EDI:
+ id = PERF_REG_X86_DI;
+ break;
+ case UNW_X86_EBP:
+ id = PERF_REG_X86_BP;
+ break;
+ case UNW_X86_ESP:
+ id = PERF_REG_X86_SP;
+ break;
+ case UNW_X86_EIP:
+ id = PERF_REG_X86_IP;
+ break;
+ default:
+ pr_err("unwind: invalid reg id %d\n", regnum);
+ return -EINVAL;
+ }
+
+ return id;
+}
+#endif /* ARCH_X86_64 */
--- /dev/null
+# perf completion
+
+have perf &&
+_perf()
+{
+ local cur cmd
+
+ COMPREPLY=()
+ _get_comp_words_by_ref cur prev
+
+ cmd=${COMP_WORDS[0]}
+
+ # List perf subcommands
+ if [ $COMP_CWORD -eq 1 ]; then
+ cmds=$($cmd --list-cmds)
+ COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+ # List possible events for -e option
+ elif [[ $prev == "-e" && "${COMP_WORDS[1]}" == @(record|stat|top) ]]; then
+ cmds=$($cmd list --raw-dump)
+ COMPREPLY=( $( compgen -W '$cmds' -- "$cur" ) )
+ # Fall down to list regular files
+ else
+ _filedir
+ fi
+} &&
+complete -F _perf perf
#include "util/session.h"
#include "util/symbol.h"
-#include <libelf.h>
-
static const char *input_name;
static bool force;
static bool show_kernel;
{
struct perf_session *session;
- elf_version(EV_CURRENT);
+ symbol__elf_init();
session = perf_session__new(input_name, O_RDONLY, force, false,
&build_id__mark_dso_hit_ops);
* If this fails, too bad, let the other side
* account this as unresolved.
*/
- } else
+ } else {
+#ifndef NO_LIBELF_SUPPORT
pr_warning("no symbols found in %s, maybe "
"install a debug package?\n",
al.map->dso->long_name);
+#endif
+ }
}
}
#include "builtin.h"
#include "perf.h"
+#include "util/evsel.h"
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
#define PATH_SYS_NODE "/sys/devices/system/node"
-struct perf_kmem {
- struct perf_tool tool;
- struct perf_session *session;
-};
-
static void init_cpunode_map(void)
{
FILE *fp;
}
}
-static void process_alloc_event(void *data,
- struct event_format *event,
- int cpu,
- u64 timestamp __used,
- struct thread *thread __used,
- int node)
+static void perf_evsel__process_alloc_event(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ int node)
{
+ struct event_format *event = evsel->tp_format;
+ void *data = sample->raw_data;
unsigned long call_site;
unsigned long ptr;
- int bytes_req;
+ int bytes_req, cpu = sample->cpu;
int bytes_alloc;
int node1, node2;
return NULL;
}
-static void process_free_event(void *data,
- struct event_format *event,
- int cpu,
- u64 timestamp __used,
- struct thread *thread __used)
+static void perf_evsel__process_free_event(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
- unsigned long ptr;
+ unsigned long ptr = raw_field_value(evsel->tp_format, "ptr",
+ sample->raw_data);
struct alloc_stat *s_alloc, *s_caller;
- ptr = raw_field_value(event, "ptr", data);
-
s_alloc = search_alloc_stat(ptr, 0, &root_alloc_stat, ptr_cmp);
if (!s_alloc)
return;
- if (cpu != s_alloc->alloc_cpu) {
+ if ((short)sample->cpu != s_alloc->alloc_cpu) {
s_alloc->pingpong++;
s_caller = search_alloc_stat(0, s_alloc->call_site,
s_alloc->alloc_cpu = -1;
}
-static void process_raw_event(struct perf_tool *tool,
- union perf_event *raw_event __used, void *data,
- int cpu, u64 timestamp, struct thread *thread)
+static void perf_evsel__process_kmem_event(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
- struct perf_kmem *kmem = container_of(tool, struct perf_kmem, tool);
- struct event_format *event;
- int type;
-
- type = trace_parse_common_type(kmem->session->pevent, data);
- event = pevent_find_event(kmem->session->pevent, type);
+ struct event_format *event = evsel->tp_format;
if (!strcmp(event->name, "kmalloc") ||
!strcmp(event->name, "kmem_cache_alloc")) {
- process_alloc_event(data, event, cpu, timestamp, thread, 0);
+ perf_evsel__process_alloc_event(evsel, sample, 0);
return;
}
if (!strcmp(event->name, "kmalloc_node") ||
!strcmp(event->name, "kmem_cache_alloc_node")) {
- process_alloc_event(data, event, cpu, timestamp, thread, 1);
+ perf_evsel__process_alloc_event(evsel, sample, 1);
return;
}
if (!strcmp(event->name, "kfree") ||
!strcmp(event->name, "kmem_cache_free")) {
- process_free_event(data, event, cpu, timestamp, thread);
+ perf_evsel__process_free_event(evsel, sample);
return;
}
}
-static int process_sample_event(struct perf_tool *tool,
+static int process_sample_event(struct perf_tool *tool __used,
union perf_event *event,
struct perf_sample *sample,
- struct perf_evsel *evsel __used,
+ struct perf_evsel *evsel,
struct machine *machine)
{
struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
- process_raw_event(tool, event, sample->raw_data, sample->cpu,
- sample->time, thread);
-
+ perf_evsel__process_kmem_event(evsel, sample);
return 0;
}
-static struct perf_kmem perf_kmem = {
- .tool = {
- .sample = process_sample_event,
- .comm = perf_event__process_comm,
- .ordered_samples = true,
- },
+static struct perf_tool perf_kmem = {
+ .sample = process_sample_event,
+ .comm = perf_event__process_comm,
+ .ordered_samples = true,
};
static double fragmentation(unsigned long n_req, unsigned long n_alloc)
int err = -EINVAL;
struct perf_session *session;
- session = perf_session__new(input_name, O_RDONLY, 0, false,
- &perf_kmem.tool);
+ session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_kmem);
if (session == NULL)
return -ENOMEM;
- perf_kmem.session = session;
-
if (perf_session__create_kernel_maps(session) < 0)
goto out_delete;
goto out_delete;
setup_pager();
- err = perf_session__process_events(session, &perf_kmem.tool);
+ err = perf_session__process_events(session, &perf_kmem);
if (err != 0)
goto out_delete;
sort_result();
setup_pager();
if (argc == 1)
- print_events(NULL);
+ print_events(NULL, false);
else {
int i;
for (i = 1; i < argc; ++i) {
- if (i > 1)
+ if (i > 2)
putchar('\n');
if (strncmp(argv[i], "tracepoint", 10) == 0)
- print_tracepoint_events(NULL, NULL);
+ print_tracepoint_events(NULL, NULL, false);
else if (strcmp(argv[i], "hw") == 0 ||
strcmp(argv[i], "hardware") == 0)
print_events_type(PERF_TYPE_HARDWARE);
print_events_type(PERF_TYPE_SOFTWARE);
else if (strcmp(argv[i], "cache") == 0 ||
strcmp(argv[i], "hwcache") == 0)
- print_hwcache_events(NULL);
+ print_hwcache_events(NULL, false);
+ else if (strcmp(argv[i], "--raw-dump") == 0)
+ print_events(NULL, true);
else {
char *sep = strchr(argv[i], ':'), *s;
int sep_idx;
if (sep == NULL) {
- print_events(argv[i]);
+ print_events(argv[i], false);
continue;
}
sep_idx = sep - argv[i];
return -1;
s[sep_idx] = '\0';
- print_tracepoint_events(s, s + sep_idx + 1);
+ print_tracepoint_events(s, s + sep_idx + 1, false);
free(s);
}
}
#include "builtin.h"
#include "perf.h"
+#include "util/evsel.h"
#include "util/util.h"
#include "util/cache.h"
#include "util/symbol.h"
struct trace_lock_handler {
void (*acquire_event)(struct trace_acquire_event *,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ const struct perf_sample *sample);
void (*acquired_event)(struct trace_acquired_event *,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ const struct perf_sample *sample);
void (*contended_event)(struct trace_contended_event *,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ const struct perf_sample *sample);
void (*release_event)(struct trace_release_event *,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ const struct perf_sample *sample);
};
static struct lock_seq_stat *get_seq(struct thread_stat *ts, void *addr)
static void
report_lock_acquire_event(struct trace_acquire_event *acquire_event,
- struct event_format *__event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ const struct perf_sample *sample)
{
struct lock_stat *ls;
struct thread_stat *ts;
if (ls->discard)
return;
- ts = thread_stat_findnew(thread->pid);
+ ts = thread_stat_findnew(sample->tid);
seq = get_seq(ts, acquire_event->addr);
switch (seq->state) {
}
ls->nr_acquire++;
- seq->prev_event_time = timestamp;
+ seq->prev_event_time = sample->time;
end:
return;
}
static void
report_lock_acquired_event(struct trace_acquired_event *acquired_event,
- struct event_format *__event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ const struct perf_sample *sample)
{
+ u64 timestamp = sample->time;
struct lock_stat *ls;
struct thread_stat *ts;
struct lock_seq_stat *seq;
if (ls->discard)
return;
- ts = thread_stat_findnew(thread->pid);
+ ts = thread_stat_findnew(sample->tid);
seq = get_seq(ts, acquired_event->addr);
switch (seq->state) {
static void
report_lock_contended_event(struct trace_contended_event *contended_event,
- struct event_format *__event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ const struct perf_sample *sample)
{
struct lock_stat *ls;
struct thread_stat *ts;
if (ls->discard)
return;
- ts = thread_stat_findnew(thread->pid);
+ ts = thread_stat_findnew(sample->tid);
seq = get_seq(ts, contended_event->addr);
switch (seq->state) {
seq->state = SEQ_STATE_CONTENDED;
ls->nr_contended++;
- seq->prev_event_time = timestamp;
+ seq->prev_event_time = sample->time;
end:
return;
}
static void
report_lock_release_event(struct trace_release_event *release_event,
- struct event_format *__event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ const struct perf_sample *sample)
{
struct lock_stat *ls;
struct thread_stat *ts;
if (ls->discard)
return;
- ts = thread_stat_findnew(thread->pid);
+ ts = thread_stat_findnew(sample->tid);
seq = get_seq(ts, release_event->addr);
switch (seq->state) {
static struct trace_lock_handler *trace_handler;
-static void
-process_lock_acquire_event(void *data,
- struct event_format *event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+static void perf_evsel__process_lock_acquire(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
struct trace_acquire_event acquire_event;
+ struct event_format *event = evsel->tp_format;
+ void *data = sample->raw_data;
u64 tmp; /* this is required for casting... */
tmp = raw_field_value(event, "lockdep_addr", data);
acquire_event.flag = (int)raw_field_value(event, "flag", data);
if (trace_handler->acquire_event)
- trace_handler->acquire_event(&acquire_event, event, cpu, timestamp, thread);
+ trace_handler->acquire_event(&acquire_event, sample);
}
-static void
-process_lock_acquired_event(void *data,
- struct event_format *event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+static void perf_evsel__process_lock_acquired(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
struct trace_acquired_event acquired_event;
+ struct event_format *event = evsel->tp_format;
+ void *data = sample->raw_data;
u64 tmp; /* this is required for casting... */
tmp = raw_field_value(event, "lockdep_addr", data);
acquired_event.name = (char *)raw_field_ptr(event, "name", data);
if (trace_handler->acquire_event)
- trace_handler->acquired_event(&acquired_event, event, cpu, timestamp, thread);
+ trace_handler->acquired_event(&acquired_event, sample);
}
-static void
-process_lock_contended_event(void *data,
- struct event_format *event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+static void perf_evsel__process_lock_contended(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
struct trace_contended_event contended_event;
+ struct event_format *event = evsel->tp_format;
+ void *data = sample->raw_data;
u64 tmp; /* this is required for casting... */
tmp = raw_field_value(event, "lockdep_addr", data);
contended_event.name = (char *)raw_field_ptr(event, "name", data);
if (trace_handler->acquire_event)
- trace_handler->contended_event(&contended_event, event, cpu, timestamp, thread);
+ trace_handler->contended_event(&contended_event, sample);
}
-static void
-process_lock_release_event(void *data,
- struct event_format *event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+static void perf_evsel__process_lock_release(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
struct trace_release_event release_event;
+ struct event_format *event = evsel->tp_format;
+ void *data = sample->raw_data;
u64 tmp; /* this is required for casting... */
tmp = raw_field_value(event, "lockdep_addr", data);
release_event.name = (char *)raw_field_ptr(event, "name", data);
if (trace_handler->acquire_event)
- trace_handler->release_event(&release_event, event, cpu, timestamp, thread);
+ trace_handler->release_event(&release_event, sample);
}
-static void
-process_raw_event(void *data, int cpu, u64 timestamp, struct thread *thread)
+static void perf_evsel__process_lock_event(struct perf_evsel *evsel,
+ struct perf_sample *sample)
{
- struct event_format *event;
- int type;
-
- type = trace_parse_common_type(session->pevent, data);
- event = pevent_find_event(session->pevent, type);
+ struct event_format *event = evsel->tp_format;
if (!strcmp(event->name, "lock_acquire"))
- process_lock_acquire_event(data, event, cpu, timestamp, thread);
+ perf_evsel__process_lock_acquire(evsel, sample);
if (!strcmp(event->name, "lock_acquired"))
- process_lock_acquired_event(data, event, cpu, timestamp, thread);
+ perf_evsel__process_lock_acquired(evsel, sample);
if (!strcmp(event->name, "lock_contended"))
- process_lock_contended_event(data, event, cpu, timestamp, thread);
+ perf_evsel__process_lock_contended(evsel, sample);
if (!strcmp(event->name, "lock_release"))
- process_lock_release_event(data, event, cpu, timestamp, thread);
+ perf_evsel__process_lock_release(evsel, sample);
}
static void print_bad_events(int bad, int total)
static int process_sample_event(struct perf_tool *tool __used,
union perf_event *event,
struct perf_sample *sample,
- struct perf_evsel *evsel __used,
+ struct perf_evsel *evsel,
struct machine *machine)
{
struct thread *thread = machine__findnew_thread(machine, sample->tid);
return -1;
}
- process_raw_event(sample->raw_data, sample->cpu, sample->time, thread);
-
+ perf_evsel__process_lock_event(evsel, sample);
return 0;
}
OPT_END()
};
+static const char * const lock_tracepoints[] = {
+ "lock:lock_acquire", /* CONFIG_LOCKDEP */
+ "lock:lock_acquired", /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+ "lock:lock_contended", /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
+ "lock:lock_release", /* CONFIG_LOCKDEP */
+};
+
static const char *record_args[] = {
"record",
"-R",
"-f",
"-m", "1024",
"-c", "1",
- "-e", "lock:lock_acquire",
- "-e", "lock:lock_acquired",
- "-e", "lock:lock_contended",
- "-e", "lock:lock_release",
};
static int __cmd_record(int argc, const char **argv)
unsigned int rec_argc, i, j;
const char **rec_argv;
+ for (i = 0; i < ARRAY_SIZE(lock_tracepoints); i++) {
+ if (!is_valid_tracepoint(lock_tracepoints[i])) {
+ pr_err("tracepoint %s is not enabled. "
+ "Are CONFIG_LOCKDEP and CONFIG_LOCK_STAT enabled?\n",
+ lock_tracepoints[i]);
+ return 1;
+ }
+ }
+
rec_argc = ARRAY_SIZE(record_args) + argc - 1;
- rec_argv = calloc(rec_argc + 1, sizeof(char *));
+ /* factor of 2 is for -e in front of each tracepoint */
+ rec_argc += 2 * ARRAY_SIZE(lock_tracepoints);
+ rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
return -ENOMEM;
for (i = 0; i < ARRAY_SIZE(record_args); i++)
rec_argv[i] = strdup(record_args[i]);
+ for (j = 0; j < ARRAY_SIZE(lock_tracepoints); j++) {
+ rec_argv[i++] = "-e";
+ rec_argv[i++] = strdup(lock_tracepoints[j]);
+ }
+
for (j = 1; j < (unsigned int)argc; j++, i++)
rec_argv[i] = argv[j];
#include <sched.h>
#include <sys/mman.h>
+#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
+
+#ifdef NO_LIBUNWIND_SUPPORT
+static char callchain_help[] = CALLCHAIN_HELP "[fp]";
+#else
+static unsigned long default_stack_dump_size = 8192;
+static char callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+#endif
+
enum write_mode_t {
WRITE_FORCE,
WRITE_APPEND
if (evlist->nr_entries != other->nr_entries)
return false;
- pair = list_entry(other->entries.next, struct perf_evsel, node);
+ pair = perf_evlist__first(other);
list_for_each_entry(pos, &evlist->entries, node) {
if (memcmp(&pos->attr, &pair->attr, sizeof(pos->attr) != 0))
return false;
- pair = list_entry(pair->node.next, struct perf_evsel, node);
+ pair = perf_evsel__next(pair);
}
return true;
static void perf_record__open(struct perf_record *rec)
{
- struct perf_evsel *pos, *first;
+ struct perf_evsel *pos;
struct perf_evlist *evlist = rec->evlist;
struct perf_session *session = rec->session;
struct perf_record_opts *opts = &rec->opts;
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
-
perf_evlist__config_attrs(evlist, opts);
+ if (opts->group)
+ perf_evlist__set_leader(evlist);
+
list_for_each_entry(pos, &evlist->entries, node) {
struct perf_event_attr *attr = &pos->attr;
- struct xyarray *group_fd = NULL;
/*
* Check if parse_single_tracepoint_event has already asked for
* PERF_SAMPLE_TIME.
*/
bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
- if (opts->group && pos != first)
- group_fd = first->fd;
fallback_missing_features:
if (opts->exclude_guest_missing)
attr->exclude_guest = attr->exclude_host = 0;
retry_sample_id:
attr->sample_id_all = opts->sample_id_all_missing ? 0 : 1;
try_again:
- if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
- opts->group, group_fd) < 0) {
+ if (perf_evsel__open(pos, evlist->cpus, evlist->threads) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
return ret;
}
+#ifndef NO_LIBUNWIND_SUPPORT
+static int get_stack_size(char *str, unsigned long *_size)
+{
+ char *endptr;
+ unsigned long size;
+ unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
+
+ size = strtoul(str, &endptr, 0);
+
+ do {
+ if (*endptr)
+ break;
+
+ size = round_up(size, sizeof(u64));
+ if (!size || size > max_size)
+ break;
+
+ *_size = size;
+ return 0;
+
+ } while (0);
+
+ pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
+ max_size, str);
+ return -1;
+}
+#endif /* !NO_LIBUNWIND_SUPPORT */
+
+static int
+parse_callchain_opt(const struct option *opt __used, const char *arg,
+ int unset)
+{
+ struct perf_record *rec = (struct perf_record *)opt->value;
+ char *tok, *name, *saveptr = NULL;
+ char *buf;
+ int ret = -1;
+
+ /* --no-call-graph */
+ if (unset)
+ return 0;
+
+ /* We specified default option if none is provided. */
+ BUG_ON(!arg);
+
+ /* We need buffer that we know we can write to. */
+ buf = malloc(strlen(arg) + 1);
+ if (!buf)
+ return -ENOMEM;
+
+ strcpy(buf, arg);
+
+ tok = strtok_r((char *)buf, ",", &saveptr);
+ name = tok ? : (char *)buf;
+
+ do {
+ /* Framepointer style */
+ if (!strncmp(name, "fp", sizeof("fp"))) {
+ if (!strtok_r(NULL, ",", &saveptr)) {
+ rec->opts.call_graph = CALLCHAIN_FP;
+ ret = 0;
+ } else
+ pr_err("callchain: No more arguments "
+ "needed for -g fp\n");
+ break;
+
+#ifndef NO_LIBUNWIND_SUPPORT
+ /* Dwarf style */
+ } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
+ ret = 0;
+ rec->opts.call_graph = CALLCHAIN_DWARF;
+ rec->opts.stack_dump_size = default_stack_dump_size;
+
+ tok = strtok_r(NULL, ",", &saveptr);
+ if (tok) {
+ unsigned long size = 0;
+
+ ret = get_stack_size(tok, &size);
+ rec->opts.stack_dump_size = size;
+ }
+
+ if (!ret)
+ pr_debug("callchain: stack dump size %d\n",
+ rec->opts.stack_dump_size);
+#endif /* !NO_LIBUNWIND_SUPPORT */
+ } else {
+ pr_err("callchain: Unknown -g option "
+ "value: %s\n", arg);
+ break;
+ }
+
+ } while (0);
+
+ free(buf);
+
+ if (!ret)
+ pr_debug("callchain: type %d\n", rec->opts.call_graph);
+
+ return ret;
+}
+
static const char * const record_usage[] = {
"perf record [<options>] [<command>]",
"perf record [<options>] -- <command> [<options>]",
"number of mmap data pages"),
OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
- OPT_BOOLEAN('g', "call-graph", &record.opts.call_graph,
- "do call-graph (stack chain/backtrace) recording"),
+ OPT_CALLBACK_DEFAULT('g', "call-graph", &record, "mode[,dump_size]",
+ callchain_help, &parse_callchain_opt,
+ "fp"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
if ((sort__has_parent || symbol_conf.use_callchain)
&& sample->callchain) {
- err = machine__resolve_callchain(machine, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
if (err)
return err;
}
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
- err = machine__resolve_callchain(machine, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample, &parent);
if (err)
return err;
}
desc);
}
- if (dump_trace) {
- perf_session__fprintf_nr_events(session, stdout);
- goto out_delete;
- }
-
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
+ if (dump_trace) {
+ perf_session__fprintf_nr_events(session, stdout);
+ goto out_delete;
+ }
+
nr_samples = 0;
list_for_each_entry(pos, &session->evlist->entries, node) {
struct hists *hists = &pos->hists;
static unsigned long nr_tasks;
-struct perf_sched {
- struct perf_tool tool;
- struct perf_session *session;
-};
-
struct sched_atom;
struct task_desc {
void (*switch_event)(struct trace_switch_event *,
struct machine *,
struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ struct perf_sample *sample);
void (*runtime_event)(struct trace_runtime_event *,
struct machine *,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ struct perf_sample *sample);
void (*wakeup_event)(struct trace_wakeup_event *,
struct machine *,
struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ struct perf_sample *sample);
void (*fork_event)(struct trace_fork_event *,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ struct event_format *event);
void (*migrate_task_event)(struct trace_migrate_task_event *,
- struct machine *machine,
- struct event_format *,
- int cpu,
- u64 timestamp,
- struct thread *thread);
+ struct machine *machine,
+ struct perf_sample *sample);
};
static void
replay_wakeup_event(struct trace_wakeup_event *wakeup_event,
struct machine *machine __used,
- struct event_format *event,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ struct event_format *event, struct perf_sample *sample)
{
struct task_desc *waker, *wakee;
waker = register_pid(wakeup_event->common_pid, "<unknown>");
wakee = register_pid(wakeup_event->pid, wakeup_event->comm);
- add_sched_event_wakeup(waker, timestamp, wakee);
+ add_sched_event_wakeup(waker, sample->time, wakee);
}
static u64 cpu_last_switched[MAX_CPUS];
replay_switch_event(struct trace_switch_event *switch_event,
struct machine *machine __used,
struct event_format *event,
- int cpu,
- u64 timestamp,
- struct thread *thread __used)
+ struct perf_sample *sample)
{
struct task_desc *prev, __used *next;
- u64 timestamp0;
+ u64 timestamp0, timestamp = sample->time;
+ int cpu = sample->cpu;
s64 delta;
if (verbose)
static void
replay_fork_event(struct trace_fork_event *fork_event,
- struct event_format *event,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ struct event_format *event)
{
if (verbose) {
printf("sched_fork event %p\n", event);
static void
latency_fork_event(struct trace_fork_event *fork_event __used,
- struct event_format *event __used,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ struct event_format *event __used)
{
/* should insert the newcomer */
}
latency_switch_event(struct trace_switch_event *switch_event,
struct machine *machine,
struct event_format *event __used,
- int cpu,
- u64 timestamp,
- struct thread *thread __used)
+ struct perf_sample *sample)
{
struct work_atoms *out_events, *in_events;
struct thread *sched_out, *sched_in;
- u64 timestamp0;
+ u64 timestamp0, timestamp = sample->time;
+ int cpu = sample->cpu;
s64 delta;
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
static void
latency_runtime_event(struct trace_runtime_event *runtime_event,
- struct machine *machine,
- struct event_format *event __used,
- int cpu,
- u64 timestamp,
- struct thread *this_thread __used)
+ struct machine *machine, struct perf_sample *sample)
{
struct thread *thread = machine__findnew_thread(machine, runtime_event->pid);
struct work_atoms *atoms = thread_atoms_search(&atom_root, thread, &cmp_pid);
+ u64 timestamp = sample->time;
+ int cpu = sample->cpu;
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
if (!atoms) {
static void
latency_wakeup_event(struct trace_wakeup_event *wakeup_event,
- struct machine *machine,
- struct event_format *__event __used,
- int cpu __used,
- u64 timestamp,
- struct thread *thread __used)
+ struct machine *machine, struct event_format *event __used,
+ struct perf_sample *sample)
{
struct work_atoms *atoms;
struct work_atom *atom;
struct thread *wakee;
+ u64 timestamp = sample->time;
/* Note for later, it may be interesting to observe the failing cases */
if (!wakeup_event->success)
static void
latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
- struct machine *machine,
- struct event_format *__event __used,
- int cpu __used,
- u64 timestamp,
- struct thread *thread __used)
+ struct machine *machine, struct perf_sample *sample)
{
+ u64 timestamp = sample->time;
struct work_atoms *atoms;
struct work_atom *atom;
struct thread *migrant;
struct event_format *event,
struct perf_sample *sample,
struct machine *machine,
- struct thread *thread)
+ struct thread *thread __used)
{
void *data = sample->raw_data;
struct trace_wakeup_event wakeup_event;
FILL_FIELD(wakeup_event, cpu, event, data);
if (trace_handler->wakeup_event)
- trace_handler->wakeup_event(&wakeup_event, machine, event,
- sample->cpu, sample->time, thread);
+ trace_handler->wakeup_event(&wakeup_event, machine, event, sample);
}
/*
map_switch_event(struct trace_switch_event *switch_event,
struct machine *machine,
struct event_format *event __used,
- int this_cpu,
- u64 timestamp,
- struct thread *thread __used)
+ struct perf_sample *sample)
{
struct thread *sched_out __used, *sched_in;
int new_shortname;
- u64 timestamp0;
+ u64 timestamp0, timestamp = sample->time;
s64 delta;
- int cpu;
+ int cpu, this_cpu = sample->cpu;
BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
struct event_format *event,
struct perf_sample *sample,
struct machine *machine,
- struct thread *thread)
+ struct thread *thread __used)
{
int this_cpu = sample->cpu;
void *data = sample->raw_data;
nr_context_switch_bugs++;
}
if (trace_handler->switch_event)
- trace_handler->switch_event(&switch_event, machine, event,
- this_cpu, sample->time, thread);
+ trace_handler->switch_event(&switch_event, machine, event, sample);
curr_pid[this_cpu] = switch_event.next_pid;
}
struct event_format *event,
struct perf_sample *sample,
struct machine *machine,
- struct thread *thread)
+ struct thread *thread __used)
{
void *data = sample->raw_data;
struct trace_runtime_event runtime_event;
FILL_FIELD(runtime_event, vruntime, event, data);
if (trace_handler->runtime_event)
- trace_handler->runtime_event(&runtime_event, machine, event,
- sample->cpu, sample->time, thread);
+ trace_handler->runtime_event(&runtime_event, machine, sample);
}
static void
struct event_format *event,
struct perf_sample *sample,
struct machine *machine __used,
- struct thread *thread)
+ struct thread *thread __used)
{
void *data = sample->raw_data;
struct trace_fork_event fork_event;
FILL_FIELD(fork_event, child_pid, event, data);
if (trace_handler->fork_event)
- trace_handler->fork_event(&fork_event, event,
- sample->cpu, sample->time, thread);
+ trace_handler->fork_event(&fork_event, event);
}
static void
struct event_format *event,
struct perf_sample *sample,
struct machine *machine,
- struct thread *thread)
+ struct thread *thread __used)
{
void *data = sample->raw_data;
struct trace_migrate_task_event migrate_task_event;
FILL_FIELD(migrate_task_event, cpu, event, data);
if (trace_handler->migrate_task_event)
- trace_handler->migrate_task_event(&migrate_task_event, machine,
- event, sample->cpu,
- sample->time, thread);
+ trace_handler->migrate_task_event(&migrate_task_event, machine, sample);
}
typedef void (*tracepoint_handler)(struct perf_tool *tool, struct event_format *event,
struct machine *machine,
struct thread *thread);
-static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
+static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __used,
union perf_event *event __used,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
- struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
- struct pevent *pevent = sched->session->pevent;
struct thread *thread = machine__findnew_thread(machine, sample->pid);
if (thread == NULL) {
if (evsel->handler.func != NULL) {
tracepoint_handler f = evsel->handler.func;
-
- if (evsel->handler.data == NULL)
- evsel->handler.data = pevent_find_event(pevent,
- evsel->attr.config);
-
- f(tool, evsel->handler.data, sample, machine, thread);
+ f(tool, evsel->tp_format, sample, machine, thread);
}
return 0;
}
-static struct perf_sched perf_sched = {
- .tool = {
- .sample = perf_sched__process_tracepoint_sample,
- .comm = perf_event__process_comm,
- .lost = perf_event__process_lost,
- .fork = perf_event__process_task,
- .ordered_samples = true,
- },
+static struct perf_tool perf_sched = {
+ .sample = perf_sched__process_tracepoint_sample,
+ .comm = perf_event__process_comm,
+ .lost = perf_event__process_lost,
+ .fork = perf_event__process_task,
+ .ordered_samples = true,
};
static void read_events(bool destroy, struct perf_session **psession)
};
struct perf_session *session;
- session = perf_session__new(input_name, O_RDONLY, 0, false,
- &perf_sched.tool);
+ session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_sched);
if (session == NULL)
die("No Memory");
- perf_sched.session = session;
-
err = perf_session__set_tracepoints_handlers(session, handlers);
assert(err == 0);
if (perf_session__has_traces(session, "record -R")) {
- err = perf_session__process_events(session, &perf_sched.tool);
+ err = perf_session__process_events(session, &perf_sched);
if (err)
die("Failed to process events, error %d", err);
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
-struct perf_script {
- struct perf_tool tool;
- struct perf_session *session;
-};
-
enum perf_output_field {
PERF_OUTPUT_COMM = 1U << 0,
PERF_OUTPUT_TID = 1U << 1,
return 0;
}
-static void print_sample_start(struct pevent *pevent,
- struct perf_sample *sample,
+static void print_sample_start(struct perf_sample *sample,
struct thread *thread,
struct perf_evsel *evsel)
{
- int type;
struct perf_event_attr *attr = &evsel->attr;
- struct event_format *event;
const char *evname = NULL;
unsigned long secs;
unsigned long usecs;
}
if (PRINT_FIELD(EVNAME)) {
- if (attr->type == PERF_TYPE_TRACEPOINT) {
- /*
- * XXX Do we really need this here?
- * perf_evlist__set_tracepoint_names should have done
- * this already
- */
- type = trace_parse_common_type(pevent,
- sample->raw_data);
- event = pevent_find_event(pevent, type);
- if (event)
- evname = event->name;
- } else
- evname = perf_evsel__name(evsel);
-
+ evname = perf_evsel__name(evsel);
printf("%s: ", evname ? evname : "[unknown]");
}
}
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine,
+ perf_evsel__print_ip(evsel, event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
printf("\n");
}
-static void process_event(union perf_event *event __unused,
- struct pevent *pevent,
- struct perf_sample *sample,
- struct perf_evsel *evsel,
- struct machine *machine,
- struct thread *thread)
+static void process_event(union perf_event *event, struct perf_sample *sample,
+ struct perf_evsel *evsel, struct machine *machine,
+ struct addr_location *al)
{
struct perf_event_attr *attr = &evsel->attr;
+ struct thread *thread = al->thread;
if (output[attr->type].fields == 0)
return;
- print_sample_start(pevent, sample, thread, evsel);
+ print_sample_start(sample, thread, evsel);
if (is_bts_event(attr)) {
print_sample_bts(event, sample, evsel, machine, thread);
}
if (PRINT_FIELD(TRACE))
- print_trace_event(pevent, sample->cpu, sample->raw_data,
- sample->raw_size);
-
+ event_format__print(evsel->tp_format, sample->cpu,
+ sample->raw_data, sample->raw_size);
if (PRINT_FIELD(ADDR))
print_sample_addr(event, sample, machine, thread, attr);
printf(" ");
else
printf("\n");
- perf_event__print_ip(event, sample, machine,
+ perf_evsel__print_ip(evsel, event, sample, machine,
PRINT_FIELD(SYM), PRINT_FIELD(DSO),
PRINT_FIELD(SYMOFFSET));
}
struct machine *machine)
{
struct addr_location al;
- struct perf_script *scr = container_of(tool, struct perf_script, tool);
struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
if (thread == NULL) {
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
return 0;
- scripting_ops->process_event(event, scr->session->pevent,
- sample, evsel, machine, thread);
+ scripting_ops->process_event(event, sample, evsel, machine, &al);
evsel->hists.stats.total_period += sample->period;
return 0;
}
-static struct perf_script perf_script = {
- .tool = {
- .sample = process_sample_event,
- .mmap = perf_event__process_mmap,
- .comm = perf_event__process_comm,
- .exit = perf_event__process_task,
- .fork = perf_event__process_task,
- .attr = perf_event__process_attr,
- .event_type = perf_event__process_event_type,
- .tracing_data = perf_event__process_tracing_data,
- .build_id = perf_event__process_build_id,
- .ordered_samples = true,
- .ordering_requires_timestamps = true,
- },
+static struct perf_tool perf_script = {
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .exit = perf_event__process_task,
+ .fork = perf_event__process_task,
+ .attr = perf_event__process_attr,
+ .event_type = perf_event__process_event_type,
+ .tracing_data = perf_event__process_tracing_data,
+ .build_id = perf_event__process_build_id,
+ .ordered_samples = true,
+ .ordering_requires_timestamps = true,
};
extern volatile int session_done;
signal(SIGINT, sig_handler);
- ret = perf_session__process_events(session, &perf_script.tool);
+ ret = perf_session__process_events(session, &perf_script);
if (debug_mode)
pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
setup_pager();
session = perf_session__new(input_name, O_RDONLY, 0, false,
- &perf_script.tool);
+ &perf_script);
if (session == NULL)
return -ENOMEM;
- perf_script.session = session;
-
if (cpu_list) {
if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
return -1;
struct perf_evsel *first)
{
struct perf_event_attr *attr = &evsel->attr;
- struct xyarray *group_fd = NULL;
bool exclude_guest_missing = false;
int ret;
- if (group && evsel != first)
- group_fd = first->fd;
-
if (scale)
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
if (perf_target__has_cpu(&target)) {
- ret = perf_evsel__open_per_cpu(evsel, evsel_list->cpus,
- group, group_fd);
+ ret = perf_evsel__open_per_cpu(evsel, evsel_list->cpus);
if (ret)
goto check_ret;
return 0;
attr->enable_on_exec = 1;
}
- ret = perf_evsel__open_per_thread(evsel, evsel_list->threads,
- group, group_fd);
+ ret = perf_evsel__open_per_thread(evsel, evsel_list->threads);
if (!ret)
return 0;
/* fall through */
close(child_ready_pipe[0]);
}
- first = list_entry(evsel_list->entries.next, struct perf_evsel, node);
+ if (group)
+ perf_evlist__set_leader(evsel_list);
+
+ first = perf_evlist__first(evsel_list);
list_for_each_entry(counter, &evsel_list->entries, node) {
if (create_perf_stat_counter(counter, first) < 0) {
goto out_thread_map_delete;
}
- if (perf_evsel__open_per_thread(evsel, threads, false, NULL) < 0) {
+ if (perf_evsel__open_per_thread(evsel, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
goto out_thread_map_delete;
}
- if (perf_evsel__open(evsel, cpus, threads, false, NULL) < 0) {
+ if (perf_evsel__open(evsel, cpus, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
perf_evlist__add(evlist, evsels[i]);
- if (perf_evsel__open(evsels[i], cpus, threads, false, NULL) < 0) {
+ if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
pr_debug("failed to open counter: %s, "
"tweak /proc/sys/kernel/perf_event_paranoid?\n",
strerror(errno));
/*
* Config the evsels, setting attr->comm on the first one, etc.
*/
- evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+ evsel = perf_evlist__first(evlist);
evsel->attr.sample_type |= PERF_SAMPLE_CPU;
evsel->attr.sample_type |= PERF_SAMPLE_TID;
evsel->attr.sample_type |= PERF_SAMPLE_TIME;
* Call sys_perf_event_open on all the fds on all the evsels,
* grouping them if asked to.
*/
- err = perf_evlist__open(evlist, opts.group);
+ err = perf_evlist__open(evlist);
if (err < 0) {
pr_debug("perf_evlist__open: %s\n", strerror(errno));
goto out_delete_evlist;
prompt_integer(&counter, "Enter details event counter");
if (counter >= top->evlist->nr_entries) {
- top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+ top->sym_evsel = perf_evlist__first(top->evlist);
fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
sleep(1);
break;
if (top->sym_evsel->idx == counter)
break;
} else
- top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+ top->sym_evsel = perf_evlist__first(top->evlist);
break;
case 'f':
prompt_integer(&top->count_filter, "Enter display event count filter");
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
- err = machine__resolve_callchain(machine, al.thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel,
+ al.thread, sample,
+ &parent);
+
if (err)
return;
}
static void perf_top__start_counters(struct perf_top *top)
{
- struct perf_evsel *counter, *first;
+ struct perf_evsel *counter;
struct perf_evlist *evlist = top->evlist;
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ if (top->group)
+ perf_evlist__set_leader(evlist);
list_for_each_entry(counter, &evlist->entries, node) {
struct perf_event_attr *attr = &counter->attr;
- struct xyarray *group_fd = NULL;
-
- if (top->group && counter != first)
- group_fd = first->fd;
attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
attr->sample_id_all = top->sample_id_all_missing ? 0 : 1;
try_again:
if (perf_evsel__open(counter, top->evlist->cpus,
- top->evlist->threads, top->group,
- group_fd) < 0) {
+ top->evlist->threads) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
pos->attr.sample_period = top.default_interval;
}
- top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
+ top.sym_evsel = perf_evlist__first(top.evlist);
symbol_conf.priv_size = sizeof(struct annotation);
perf-timechart mainporcelain common
perf-top mainporcelain common
perf-script mainporcelain common
-perf-probe mainporcelain common
+perf-probe mainporcelain full
perf-kmem mainporcelain common
perf-lock mainporcelain common
perf-kvm mainporcelain common
return 0;
}
endef
+
+ifndef NO_LIBUNWIND
+define SOURCE_LIBUNWIND
+#include <libunwind.h>
+#include <stdlib.h>
+
+extern int UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+int main(void)
+{
+ unw_addr_space_t addr_space;
+ addr_space = unw_create_addr_space(NULL, 0);
+ unw_init_remote(NULL, addr_space, NULL);
+ dwarf_search_unwind_table(addr_space, 0, NULL, NULL, 0, NULL);
+ return 0;
+}
+endef
+endif
int use_browser = -1;
static int use_pager = -1;
+struct cmd_struct {
+ const char *cmd;
+ int (*fn)(int, const char **, const char *);
+ int option;
+};
+
+static struct cmd_struct commands[] = {
+ { "buildid-cache", cmd_buildid_cache, 0 },
+ { "buildid-list", cmd_buildid_list, 0 },
+ { "diff", cmd_diff, 0 },
+ { "evlist", cmd_evlist, 0 },
+ { "help", cmd_help, 0 },
+ { "list", cmd_list, 0 },
+ { "record", cmd_record, 0 },
+ { "report", cmd_report, 0 },
+ { "bench", cmd_bench, 0 },
+ { "stat", cmd_stat, 0 },
+ { "timechart", cmd_timechart, 0 },
+ { "top", cmd_top, 0 },
+ { "annotate", cmd_annotate, 0 },
+ { "version", cmd_version, 0 },
+ { "script", cmd_script, 0 },
+ { "sched", cmd_sched, 0 },
+#ifndef NO_LIBELF_SUPPORT
+ { "probe", cmd_probe, 0 },
+#endif
+ { "kmem", cmd_kmem, 0 },
+ { "lock", cmd_lock, 0 },
+ { "kvm", cmd_kvm, 0 },
+ { "test", cmd_test, 0 },
+ { "inject", cmd_inject, 0 },
+};
+
struct pager_config {
const char *cmd;
int val;
fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
if (envchanged)
*envchanged = 1;
+ } else if (!strcmp(cmd, "--list-cmds")) {
+ unsigned int i;
+
+ for (i = 0; i < ARRAY_SIZE(commands); i++) {
+ struct cmd_struct *p = commands+i;
+ printf("%s ", p->cmd);
+ }
+ exit(0);
} else {
fprintf(stderr, "Unknown option: %s\n", cmd);
usage(perf_usage_string);
*/
#define NEED_WORK_TREE (1<<2)
-struct cmd_struct {
- const char *cmd;
- int (*fn)(int, const char **, const char *);
- int option;
-};
-
static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
{
int status;
static void handle_internal_command(int argc, const char **argv)
{
const char *cmd = argv[0];
- static struct cmd_struct commands[] = {
- { "buildid-cache", cmd_buildid_cache, 0 },
- { "buildid-list", cmd_buildid_list, 0 },
- { "diff", cmd_diff, 0 },
- { "evlist", cmd_evlist, 0 },
- { "help", cmd_help, 0 },
- { "list", cmd_list, 0 },
- { "record", cmd_record, 0 },
- { "report", cmd_report, 0 },
- { "bench", cmd_bench, 0 },
- { "stat", cmd_stat, 0 },
- { "timechart", cmd_timechart, 0 },
- { "top", cmd_top, 0 },
- { "annotate", cmd_annotate, 0 },
- { "version", cmd_version, 0 },
- { "script", cmd_script, 0 },
- { "sched", cmd_sched, 0 },
- { "probe", cmd_probe, 0 },
- { "kmem", cmd_kmem, 0 },
- { "lock", cmd_lock, 0 },
- { "kvm", cmd_kvm, 0 },
- { "test", cmd_test, 0 },
- { "inject", cmd_inject, 0 },
- };
unsigned int i;
static const char ext[] = STRIP_EXTENSION;
#include "util/target.h"
+enum perf_call_graph_mode {
+ CALLCHAIN_NONE,
+ CALLCHAIN_FP,
+ CALLCHAIN_DWARF
+};
+
struct perf_record_opts {
struct perf_target target;
- bool call_graph;
+ int call_graph;
bool group;
bool inherit_stat;
bool no_delay;
u64 branch_stack;
u64 default_interval;
u64 user_interval;
+ u16 stack_dump_size;
};
#endif
--- /dev/null
+# EventClass.py
+#
+# This is a library defining some events types classes, which could
+# be used by other scripts to analyzing the perf samples.
+#
+# Currently there are just a few classes defined for examples,
+# PerfEvent is the base class for all perf event sample, PebsEvent
+# is a HW base Intel x86 PEBS event, and user could add more SW/HW
+# event classes based on requirements.
+
+import struct
+
+# Event types, user could add more here
+EVTYPE_GENERIC = 0
+EVTYPE_PEBS = 1 # Basic PEBS event
+EVTYPE_PEBS_LL = 2 # PEBS event with load latency info
+EVTYPE_IBS = 3
+
+#
+# Currently we don't have good way to tell the event type, but by
+# the size of raw buffer, raw PEBS event with load latency data's
+# size is 176 bytes, while the pure PEBS event's size is 144 bytes.
+#
+def create_event(name, comm, dso, symbol, raw_buf):
+ if (len(raw_buf) == 144):
+ event = PebsEvent(name, comm, dso, symbol, raw_buf)
+ elif (len(raw_buf) == 176):
+ event = PebsNHM(name, comm, dso, symbol, raw_buf)
+ else:
+ event = PerfEvent(name, comm, dso, symbol, raw_buf)
+
+ return event
+
+class PerfEvent(object):
+ event_num = 0
+ def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_GENERIC):
+ self.name = name
+ self.comm = comm
+ self.dso = dso
+ self.symbol = symbol
+ self.raw_buf = raw_buf
+ self.ev_type = ev_type
+ PerfEvent.event_num += 1
+
+ def show(self):
+ print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+
+#
+# Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
+# contains the context info when that event happened: the EFLAGS and
+# linear IP info, as well as all the registers.
+#
+class PebsEvent(PerfEvent):
+ pebs_num = 0
+ def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS):
+ tmp_buf=raw_buf[0:80]
+ flags, ip, ax, bx, cx, dx, si, di, bp, sp = struct.unpack('QQQQQQQQQQ', tmp_buf)
+ self.flags = flags
+ self.ip = ip
+ self.ax = ax
+ self.bx = bx
+ self.cx = cx
+ self.dx = dx
+ self.si = si
+ self.di = di
+ self.bp = bp
+ self.sp = sp
+
+ PerfEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type)
+ PebsEvent.pebs_num += 1
+ del tmp_buf
+
+#
+# Intel Nehalem and Westmere support PEBS plus Load Latency info which lie
+# in the four 64 bit words write after the PEBS data:
+# Status: records the IA32_PERF_GLOBAL_STATUS register value
+# DLA: Data Linear Address (EIP)
+# DSE: Data Source Encoding, where the latency happens, hit or miss
+# in L1/L2/L3 or IO operations
+# LAT: the actual latency in cycles
+#
+class PebsNHM(PebsEvent):
+ pebs_nhm_num = 0
+ def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS_LL):
+ tmp_buf=raw_buf[144:176]
+ status, dla, dse, lat = struct.unpack('QQQQ', tmp_buf)
+ self.status = status
+ self.dla = dla
+ self.dse = dse
+ self.lat = lat
+
+ PebsEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type)
+ PebsNHM.pebs_nhm_num += 1
+ del tmp_buf
--- /dev/null
+# event_analyzing_sample.py: general event handler in python
+#
+# Current perf report is already very powerful with the annotation integrated,
+# and this script is not trying to be as powerful as perf report, but
+# providing end user/developer a flexible way to analyze the events other
+# than trace points.
+#
+# The 2 database related functions in this script just show how to gather
+# the basic information, and users can modify and write their own functions
+# according to their specific requirement.
+#
+# The first function "show_general_events" just does a basic grouping for all
+# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is
+# for a x86 HW PMU event: PEBS with load latency data.
+#
+
+import os
+import sys
+import math
+import struct
+import sqlite3
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+ '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from EventClass import *
+
+#
+# If the perf.data has a big number of samples, then the insert operation
+# will be very time consuming (about 10+ minutes for 10000 samples) if the
+# .db database is on disk. Move the .db file to RAM based FS to speedup
+# the handling, which will cut the time down to several seconds.
+#
+con = sqlite3.connect("/dev/shm/perf.db")
+con.isolation_level = None
+
+def trace_begin():
+ print "In trace_begin:\n"
+
+ #
+ # Will create several tables at the start, pebs_ll is for PEBS data with
+ # load latency info, while gen_events is for general event.
+ #
+ con.execute("""
+ create table if not exists gen_events (
+ name text,
+ symbol text,
+ comm text,
+ dso text
+ );""")
+ con.execute("""
+ create table if not exists pebs_ll (
+ name text,
+ symbol text,
+ comm text,
+ dso text,
+ flags integer,
+ ip integer,
+ status integer,
+ dse integer,
+ dla integer,
+ lat integer
+ );""")
+
+#
+# Create and insert event object to a database so that user could
+# do more analysis with simple database commands.
+#
+def process_event(param_dict):
+ event_attr = param_dict["attr"]
+ sample = param_dict["sample"]
+ raw_buf = param_dict["raw_buf"]
+ comm = param_dict["comm"]
+ name = param_dict["ev_name"]
+
+ # Symbol and dso info are not always resolved
+ if (param_dict.has_key("dso")):
+ dso = param_dict["dso"]
+ else:
+ dso = "Unknown_dso"
+
+ if (param_dict.has_key("symbol")):
+ symbol = param_dict["symbol"]
+ else:
+ symbol = "Unknown_symbol"
+
+ # Create the event object and insert it to the right table in database
+ event = create_event(name, comm, dso, symbol, raw_buf)
+ insert_db(event)
+
+def insert_db(event):
+ if event.ev_type == EVTYPE_GENERIC:
+ con.execute("insert into gen_events values(?, ?, ?, ?)",
+ (event.name, event.symbol, event.comm, event.dso))
+ elif event.ev_type == EVTYPE_PEBS_LL:
+ event.ip &= 0x7fffffffffffffff
+ event.dla &= 0x7fffffffffffffff
+ con.execute("insert into pebs_ll values (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+ (event.name, event.symbol, event.comm, event.dso, event.flags,
+ event.ip, event.status, event.dse, event.dla, event.lat))
+
+def trace_end():
+ print "In trace_end:\n"
+ # We show the basic info for the 2 type of event classes
+ show_general_events()
+ show_pebs_ll()
+ con.close()
+
+#
+# As the event number may be very big, so we can't use linear way
+# to show the histogram in real number, but use a log2 algorithm.
+#
+
+def num2sym(num):
+ # Each number will have at least one '#'
+ snum = '#' * (int)(math.log(num, 2) + 1)
+ return snum
+
+def show_general_events():
+
+ # Check the total record number in the table
+ count = con.execute("select count(*) from gen_events")
+ for t in count:
+ print "There is %d records in gen_events table" % t[0]
+ if t[0] == 0:
+ return
+
+ print "Statistics about the general events grouped by thread/symbol/dso: \n"
+
+ # Group by thread
+ commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)")
+ print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)
+ for row in commq:
+ print "%16s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by symbol
+ print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)
+ symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)")
+ for row in symbolq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by dso
+ print "\n%40s %8s %16s\n%s" % ("dso", "number", "histogram", "="*74)
+ dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)")
+ for row in dsoq:
+ print "%40s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+#
+# This function just shows the basic info, and we could do more with the
+# data in the tables, like checking the function parameters when some
+# big latency events happen.
+#
+def show_pebs_ll():
+
+ count = con.execute("select count(*) from pebs_ll")
+ for t in count:
+ print "There is %d records in pebs_ll table" % t[0]
+ if t[0] == 0:
+ return
+
+ print "Statistics about the PEBS Load Latency events grouped by thread/symbol/dse/latency: \n"
+
+ # Group by thread
+ commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)")
+ print "\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)
+ for row in commq:
+ print "%16s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by symbol
+ print "\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)
+ symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)")
+ for row in symbolq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by dse
+ dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)")
+ print "\n%32s %8s %16s\n%s" % ("dse", "number", "histogram", "="*58)
+ for row in dseq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+ # Group by latency
+ latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat")
+ print "\n%32s %8s %16s\n%s" % ("latency", "number", "histogram", "="*58)
+ for row in latq:
+ print "%32s %8d %s" % (row[0], row[1], num2sym(row[1]))
+
+def trace_unhandled(event_name, context, event_fields_dict):
+ print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
struct hist_entry *he_selection;
struct map_symbol *selection;
int print_seq;
+ bool show_dso;
bool has_symbols;
};
}
static char *callchain_list__sym_name(struct callchain_list *cl,
- char *bf, size_t bfsize)
+ char *bf, size_t bfsize, bool show_dso)
{
+ int printed;
+
if (cl->ms.sym)
- return cl->ms.sym->name;
+ printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+ else
+ printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+
+ if (show_dso)
+ scnprintf(bf + printed, bfsize - printed, " %s",
+ cl->ms.map ? cl->ms.map->dso->short_name : "unknown");
- snprintf(bf, bfsize, "%#" PRIx64, cl->ip);
return bf;
}
remaining -= cumul;
list_for_each_entry(chain, &child->val, list) {
- char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str;
+ char bf[1024], *alloc_str;
const char *str;
int color;
bool was_first = first;
}
alloc_str = NULL;
- str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+ str = callchain_list__sym_name(chain, bf, sizeof(bf),
+ browser->show_dso);
if (was_first) {
double percent = cumul * 100.0 / new_total;
char folded_sign = ' ';
list_for_each_entry(chain, &node->val, list) {
- char ipstr[BITS_PER_LONG / 4 + 1], *s;
+ char bf[1024], *s;
int color;
folded_sign = callchain_list__folded(chain);
*is_current_entry = true;
}
- s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+ s = callchain_list__sym_name(chain, bf, sizeof(bf),
+ browser->show_dso);
ui_browser__gotorc(&browser->b, row, 0);
ui_browser__set_color(&browser->b, color);
slsmg_write_nstring(" ", offset);
}
if (row_offset == 0) {
- hist_entry__snprintf(entry, s, sizeof(s), browser->hists);
+ hist_entry__sort_snprintf(entry, s, sizeof(s), browser->hists);
percent = (entry->period * 100.0) / browser->hists->stats.total_period;
ui_browser__set_percent_color(&browser->b, percent, current_entry);
remaining -= cumul;
list_for_each_entry(chain, &child->val, list) {
- char ipstr[BITS_PER_LONG / 4 + 1], *alloc_str;
+ char bf[1024], *alloc_str;
const char *str;
bool was_first = first;
folded_sign = callchain_list__folded(chain);
alloc_str = NULL;
- str = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+ str = callchain_list__sym_name(chain, bf, sizeof(bf),
+ browser->show_dso);
if (was_first) {
double percent = cumul * 100.0 / new_total;
int printed = 0;
list_for_each_entry(chain, &node->val, list) {
- char ipstr[BITS_PER_LONG / 4 + 1], *s;
+ char bf[1024], *s;
folded_sign = callchain_list__folded(chain);
- s = callchain_list__sym_name(chain, ipstr, sizeof(ipstr));
+ s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso);
printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
}
if (symbol_conf.use_callchain)
folded_sign = hist_entry__folded(he);
- hist_entry__snprintf(he, s, sizeof(s), browser->hists);
+ hist_entry__sort_snprintf(he, s, sizeof(s), browser->hists);
percent = (he->period * 100.0) / browser->hists->stats.total_period;
if (symbol_conf.use_callchain)
continue;
case 'd':
goto zoom_dso;
+ case 'V':
+ browser->show_dso = !browser->show_dso;
+ continue;
case 't':
goto zoom_thread;
case '/':
"d Zoom into current DSO\n"
"t Zoom into current Thread\n"
"P Print histograms to perf.hist.N\n"
+ "V Verbose (DSO names in callchains, etc)\n"
"/ Filter symbol by name");
continue;
case K_ENTER:
#include "../evsel.h"
#include "../sort.h"
#include "../hist.h"
+#include "../helpline.h"
#include "gtk.h"
#include <signal.h>
}
int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
- const char *help __used,
+ const char *help,
void (*timer) (void *arg)__used,
void *arg __used, int delay_secs __used)
{
gtk_window_set_position(GTK_WINDOW(window), GTK_WIN_POS_CENTER);
+ ui_helpline__push(help);
+
gtk_main();
perf_gtk__deactivate_context(&pgctx);
struct perf_gtk_context *perf_gtk__activate_context(GtkWidget *window);
int perf_gtk__deactivate_context(struct perf_gtk_context **ctx);
+void perf_gtk__init_helpline(void);
+
#ifndef HAVE_GTK_INFO_BAR
static inline GtkWidget *perf_gtk__setup_info_bar(void)
{
--- /dev/null
+#include <stdio.h>
+#include <string.h>
+
+#include "gtk.h"
+#include "../ui.h"
+#include "../helpline.h"
+#include "../../util/debug.h"
+
+static void gtk_helpline_pop(void)
+{
+ if (!perf_gtk__is_active_context(pgctx))
+ return;
+
+ gtk_statusbar_pop(GTK_STATUSBAR(pgctx->statbar),
+ pgctx->statbar_ctx_id);
+}
+
+static void gtk_helpline_push(const char *msg)
+{
+ if (!perf_gtk__is_active_context(pgctx))
+ return;
+
+ gtk_statusbar_push(GTK_STATUSBAR(pgctx->statbar),
+ pgctx->statbar_ctx_id, msg);
+}
+
+static struct ui_helpline gtk_helpline_fns = {
+ .pop = gtk_helpline_pop,
+ .push = gtk_helpline_push,
+};
+
+void perf_gtk__init_helpline(void)
+{
+ helpline_fns = >k_helpline_fns;
+}
+
+int perf_gtk__show_helpline(const char *fmt, va_list ap)
+{
+ int ret;
+ char *ptr;
+ static int backlog;
+
+ ret = vscnprintf(ui_helpline__current + backlog,
+ sizeof(ui_helpline__current) - backlog, fmt, ap);
+ backlog += ret;
+
+ /* only first line can be displayed */
+ ptr = strchr(ui_helpline__current, '\n');
+ if (ptr && (ptr - ui_helpline__current) <= backlog) {
+ *ptr = '\0';
+ ui_helpline__puts(ui_helpline__current);
+ backlog = 0;
+ }
+
+ return ret;
+}
int perf_gtk__init(void)
{
perf_error__register(&perf_gtk_eops);
+ perf_gtk__init_helpline();
return gtk_init_check(NULL, NULL) ? 0 : -1;
}
void perf_gtk__exit(bool wait_for_ok __used)
{
+ if (!perf_gtk__is_active_context(pgctx))
+ return;
perf_error__unregister(&perf_gtk_eops);
gtk_main_quit();
}
* For now, just add stubs for NO_NEWT=1 build.
*/
#ifdef NO_NEWT_SUPPORT
-int ui_helpline__show_help(const char *format __used, va_list ap __used)
-{
- return 0;
-}
-
void ui_progress__update(u64 curr __used, u64 total __used,
const char *title __used)
{
#include "../debug.h"
#include "helpline.h"
#include "ui.h"
-#include "libslang.h"
-void ui_helpline__pop(void)
+char ui_helpline__current[512];
+
+static void nop_helpline__pop(void)
{
}
-char ui_helpline__current[512];
+static void nop_helpline__push(const char *msg __used)
+{
+}
-void ui_helpline__push(const char *msg)
+static struct ui_helpline default_helpline_fns = {
+ .pop = nop_helpline__pop,
+ .push = nop_helpline__push,
+};
+
+struct ui_helpline *helpline_fns = &default_helpline_fns;
+
+void ui_helpline__pop(void)
{
- const size_t sz = sizeof(ui_helpline__current);
+ helpline_fns->pop();
+}
- SLsmg_gotorc(SLtt_Screen_Rows - 1, 0);
- SLsmg_set_color(0);
- SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
- SLsmg_refresh();
- strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
+void ui_helpline__push(const char *msg)
+{
+ helpline_fns->push(msg);
}
void ui_helpline__vpush(const char *fmt, va_list ap)
ui_helpline__pop();
ui_helpline__push(msg);
}
-
-void ui_helpline__init(void)
-{
- ui_helpline__puts(" ");
-}
-
-char ui_helpline__last_msg[1024];
-
-int ui_helpline__show_help(const char *format, va_list ap)
-{
- int ret;
- static int backlog;
-
- pthread_mutex_lock(&ui__lock);
- ret = vscnprintf(ui_helpline__last_msg + backlog,
- sizeof(ui_helpline__last_msg) - backlog, format, ap);
- backlog += ret;
-
- if (ui_helpline__last_msg[backlog - 1] == '\n') {
- ui_helpline__puts(ui_helpline__last_msg);
- SLsmg_refresh();
- backlog = 0;
- }
- pthread_mutex_unlock(&ui__lock);
-
- return ret;
-}
#include <stdio.h>
#include <stdarg.h>
+#include "../util/cache.h"
+
+struct ui_helpline {
+ void (*pop)(void);
+ void (*push)(const char *msg);
+};
+
+extern struct ui_helpline *helpline_fns;
+
void ui_helpline__init(void);
+
void ui_helpline__pop(void);
void ui_helpline__push(const char *msg);
void ui_helpline__vpush(const char *fmt, va_list ap);
void ui_helpline__fpush(const char *fmt, ...);
void ui_helpline__puts(const char *msg);
-extern char ui_helpline__current[];
+extern char ui_helpline__current[512];
+
+#ifdef NO_NEWT_SUPPORT
+static inline int ui_helpline__show_help(const char *format __used,
+ va_list ap __used)
+{
+ return 0;
+}
+#else
+extern char ui_helpline__last_msg[];
+int ui_helpline__show_help(const char *format, va_list ap);
+#endif /* NO_NEWT_SUPPORT */
+
+#ifdef NO_GTK2_SUPPORT
+static inline int perf_gtk__show_helpline(const char *format __used,
+ va_list ap __used)
+{
+ return 0;
+}
+#else
+int perf_gtk__show_helpline(const char *format, va_list ap);
+#endif /* NO_GTK2_SUPPORT */
#endif /* _PERF_UI_HELPLINE_H_ */
+#include <pthread.h>
+
#include "../cache.h"
#include "../debug.h"
+pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
+
void setup_browser(bool fallback_to_pager)
{
if (!isatty(1) || dump_trace)
--- /dev/null
+#include <stdio.h>
+#include <math.h>
+
+#include "../../util/util.h"
+#include "../../util/hist.h"
+#include "../../util/sort.h"
+
+
+static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
+{
+ int i;
+ int ret = fprintf(fp, " ");
+
+ for (i = 0; i < left_margin; i++)
+ ret += fprintf(fp, " ");
+
+ return ret;
+}
+
+static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
+ int left_margin)
+{
+ int i;
+ size_t ret = callchain__fprintf_left_margin(fp, left_margin);
+
+ for (i = 0; i < depth; i++)
+ if (depth_mask & (1 << i))
+ ret += fprintf(fp, "| ");
+ else
+ ret += fprintf(fp, " ");
+
+ ret += fprintf(fp, "\n");
+
+ return ret;
+}
+
+static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
+ int depth, int depth_mask, int period,
+ u64 total_samples, u64 hits,
+ int left_margin)
+{
+ int i;
+ size_t ret = 0;
+
+ ret += callchain__fprintf_left_margin(fp, left_margin);
+ for (i = 0; i < depth; i++) {
+ if (depth_mask & (1 << i))
+ ret += fprintf(fp, "|");
+ else
+ ret += fprintf(fp, " ");
+ if (!period && i == depth - 1) {
+ double percent;
+
+ percent = hits * 100.0 / total_samples;
+ ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+ } else
+ ret += fprintf(fp, "%s", " ");
+ }
+ if (chain->ms.sym)
+ ret += fprintf(fp, "%s\n", chain->ms.sym->name);
+ else
+ ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip);
+
+ return ret;
+}
+
+static struct symbol *rem_sq_bracket;
+static struct callchain_list rem_hits;
+
+static void init_rem_hits(void)
+{
+ rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
+ if (!rem_sq_bracket) {
+ fprintf(stderr, "Not enough memory to display remaining hits\n");
+ return;
+ }
+
+ strcpy(rem_sq_bracket->name, "[...]");
+ rem_hits.ms.sym = rem_sq_bracket;
+}
+
+static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
+ u64 total_samples, int depth,
+ int depth_mask, int left_margin)
+{
+ struct rb_node *node, *next;
+ struct callchain_node *child;
+ struct callchain_list *chain;
+ int new_depth_mask = depth_mask;
+ u64 remaining;
+ size_t ret = 0;
+ int i;
+ uint entries_printed = 0;
+
+ remaining = total_samples;
+
+ node = rb_first(root);
+ while (node) {
+ u64 new_total;
+ u64 cumul;
+
+ child = rb_entry(node, struct callchain_node, rb_node);
+ cumul = callchain_cumul_hits(child);
+ remaining -= cumul;
+
+ /*
+ * The depth mask manages the output of pipes that show
+ * the depth. We don't want to keep the pipes of the current
+ * level for the last child of this depth.
+ * Except if we have remaining filtered hits. They will
+ * supersede the last child
+ */
+ next = rb_next(node);
+ if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
+ new_depth_mask &= ~(1 << (depth - 1));
+
+ /*
+ * But we keep the older depth mask for the line separator
+ * to keep the level link until we reach the last child
+ */
+ ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
+ left_margin);
+ i = 0;
+ list_for_each_entry(chain, &child->val, list) {
+ ret += ipchain__fprintf_graph(fp, chain, depth,
+ new_depth_mask, i++,
+ total_samples,
+ cumul,
+ left_margin);
+ }
+
+ if (callchain_param.mode == CHAIN_GRAPH_REL)
+ new_total = child->children_hit;
+ else
+ new_total = total_samples;
+
+ ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
+ depth + 1,
+ new_depth_mask | (1 << depth),
+ left_margin);
+ node = next;
+ if (++entries_printed == callchain_param.print_limit)
+ break;
+ }
+
+ if (callchain_param.mode == CHAIN_GRAPH_REL &&
+ remaining && remaining != total_samples) {
+
+ if (!rem_sq_bracket)
+ return ret;
+
+ new_depth_mask &= ~(1 << (depth - 1));
+ ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+ new_depth_mask, 0, total_samples,
+ remaining, left_margin);
+ }
+
+ return ret;
+}
+
+static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
+ u64 total_samples, int left_margin)
+{
+ struct callchain_node *cnode;
+ struct callchain_list *chain;
+ u32 entries_printed = 0;
+ bool printed = false;
+ struct rb_node *node;
+ int i = 0;
+ int ret = 0;
+
+ /*
+ * If have one single callchain root, don't bother printing
+ * its percentage (100 % in fractal mode and the same percentage
+ * than the hist in graph mode). This also avoid one level of column.
+ */
+ node = rb_first(root);
+ if (node && !rb_next(node)) {
+ cnode = rb_entry(node, struct callchain_node, rb_node);
+ list_for_each_entry(chain, &cnode->val, list) {
+ /*
+ * If we sort by symbol, the first entry is the same than
+ * the symbol. No need to print it otherwise it appears as
+ * displayed twice.
+ */
+ if (!i++ && sort__first_dimension == SORT_SYM)
+ continue;
+ if (!printed) {
+ ret += callchain__fprintf_left_margin(fp, left_margin);
+ ret += fprintf(fp, "|\n");
+ ret += callchain__fprintf_left_margin(fp, left_margin);
+ ret += fprintf(fp, "---");
+ left_margin += 3;
+ printed = true;
+ } else
+ ret += callchain__fprintf_left_margin(fp, left_margin);
+
+ if (chain->ms.sym)
+ ret += fprintf(fp, " %s\n", chain->ms.sym->name);
+ else
+ ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+
+ if (++entries_printed == callchain_param.print_limit)
+ break;
+ }
+ root = &cnode->rb_root;
+ }
+
+ ret += __callchain__fprintf_graph(fp, root, total_samples,
+ 1, 1, left_margin);
+ ret += fprintf(fp, "\n");
+
+ return ret;
+}
+
+static size_t __callchain__fprintf_flat(FILE *fp,
+ struct callchain_node *self,
+ u64 total_samples)
+{
+ struct callchain_list *chain;
+ size_t ret = 0;
+
+ if (!self)
+ return 0;
+
+ ret += __callchain__fprintf_flat(fp, self->parent, total_samples);
+
+
+ list_for_each_entry(chain, &self->val, list) {
+ if (chain->ip >= PERF_CONTEXT_MAX)
+ continue;
+ if (chain->ms.sym)
+ ret += fprintf(fp, " %s\n", chain->ms.sym->name);
+ else
+ ret += fprintf(fp, " %p\n",
+ (void *)(long)chain->ip);
+ }
+
+ return ret;
+}
+
+static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self,
+ u64 total_samples)
+{
+ size_t ret = 0;
+ u32 entries_printed = 0;
+ struct rb_node *rb_node;
+ struct callchain_node *chain;
+
+ rb_node = rb_first(self);
+ while (rb_node) {
+ double percent;
+
+ chain = rb_entry(rb_node, struct callchain_node, rb_node);
+ percent = chain->hit * 100.0 / total_samples;
+
+ ret = percent_color_fprintf(fp, " %6.2f%%\n", percent);
+ ret += __callchain__fprintf_flat(fp, chain, total_samples);
+ ret += fprintf(fp, "\n");
+ if (++entries_printed == callchain_param.print_limit)
+ break;
+
+ rb_node = rb_next(rb_node);
+ }
+
+ return ret;
+}
+
+static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
+ u64 total_samples, int left_margin,
+ FILE *fp)
+{
+ switch (callchain_param.mode) {
+ case CHAIN_GRAPH_REL:
+ return callchain__fprintf_graph(fp, &he->sorted_chain, he->period,
+ left_margin);
+ break;
+ case CHAIN_GRAPH_ABS:
+ return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+ left_margin);
+ break;
+ case CHAIN_FLAT:
+ return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
+ break;
+ case CHAIN_NONE:
+ break;
+ default:
+ pr_err("Bad callchain mode\n");
+ }
+
+ return 0;
+}
+
+static int hist_entry__period_snprintf(struct hist_entry *he, char *s,
+ size_t size, struct hists *pair_hists,
+ bool show_displacement, long displacement,
+ bool color, u64 total_period)
+{
+ u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
+ u64 nr_events;
+ const char *sep = symbol_conf.field_sep;
+ int ret;
+
+ if (symbol_conf.exclude_other && !he->parent)
+ return 0;
+
+ if (pair_hists) {
+ period = he->pair ? he->pair->period : 0;
+ nr_events = he->pair ? he->pair->nr_events : 0;
+ total = pair_hists->stats.total_period;
+ period_sys = he->pair ? he->pair->period_sys : 0;
+ period_us = he->pair ? he->pair->period_us : 0;
+ period_guest_sys = he->pair ? he->pair->period_guest_sys : 0;
+ period_guest_us = he->pair ? he->pair->period_guest_us : 0;
+ } else {
+ period = he->period;
+ nr_events = he->nr_events;
+ total = total_period;
+ period_sys = he->period_sys;
+ period_us = he->period_us;
+ period_guest_sys = he->period_guest_sys;
+ period_guest_us = he->period_guest_us;
+ }
+
+ if (total) {
+ if (color)
+ ret = percent_color_snprintf(s, size,
+ sep ? "%.2f" : " %6.2f%%",
+ (period * 100.0) / total);
+ else
+ ret = scnprintf(s, size, sep ? "%.2f" : " %6.2f%%",
+ (period * 100.0) / total);
+ if (symbol_conf.show_cpu_utilization) {
+ ret += percent_color_snprintf(s + ret, size - ret,
+ sep ? "%.2f" : " %6.2f%%",
+ (period_sys * 100.0) / total);
+ ret += percent_color_snprintf(s + ret, size - ret,
+ sep ? "%.2f" : " %6.2f%%",
+ (period_us * 100.0) / total);
+ if (perf_guest) {
+ ret += percent_color_snprintf(s + ret,
+ size - ret,
+ sep ? "%.2f" : " %6.2f%%",
+ (period_guest_sys * 100.0) /
+ total);
+ ret += percent_color_snprintf(s + ret,
+ size - ret,
+ sep ? "%.2f" : " %6.2f%%",
+ (period_guest_us * 100.0) /
+ total);
+ }
+ }
+ } else
+ ret = scnprintf(s, size, sep ? "%" PRIu64 : "%12" PRIu64 " ", period);
+
+ if (symbol_conf.show_nr_samples) {
+ if (sep)
+ ret += scnprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events);
+ else
+ ret += scnprintf(s + ret, size - ret, "%11" PRIu64, nr_events);
+ }
+
+ if (symbol_conf.show_total_period) {
+ if (sep)
+ ret += scnprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period);
+ else
+ ret += scnprintf(s + ret, size - ret, " %12" PRIu64, period);
+ }
+
+ if (pair_hists) {
+ char bf[32];
+ double old_percent = 0, new_percent = 0, diff;
+
+ if (total > 0)
+ old_percent = (period * 100.0) / total;
+ if (total_period > 0)
+ new_percent = (he->period * 100.0) / total_period;
+
+ diff = new_percent - old_percent;
+
+ if (fabs(diff) >= 0.01)
+ scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
+ else
+ scnprintf(bf, sizeof(bf), " ");
+
+ if (sep)
+ ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
+ else
+ ret += scnprintf(s + ret, size - ret, "%11.11s", bf);
+
+ if (show_displacement) {
+ if (displacement)
+ scnprintf(bf, sizeof(bf), "%+4ld", displacement);
+ else
+ scnprintf(bf, sizeof(bf), " ");
+
+ if (sep)
+ ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
+ else
+ ret += scnprintf(s + ret, size - ret, "%6.6s", bf);
+ }
+ }
+
+ return ret;
+}
+
+int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size,
+ struct hists *hists)
+{
+ const char *sep = symbol_conf.field_sep;
+ struct sort_entry *se;
+ int ret = 0;
+
+ list_for_each_entry(se, &hist_entry__sort_list, list) {
+ if (se->elide)
+ continue;
+
+ ret += scnprintf(s + ret, size - ret, "%s", sep ?: " ");
+ ret += se->se_snprintf(he, s + ret, size - ret,
+ hists__col_len(hists, se->se_width_idx));
+ }
+
+ return ret;
+}
+
+static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
+ struct hists *hists,
+ u64 total_period, FILE *fp)
+{
+ int left_margin = 0;
+
+ if (sort__first_dimension == SORT_COMM) {
+ struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
+ typeof(*se), list);
+ left_margin = hists__col_len(hists, se->se_width_idx);
+ left_margin -= thread__comm_len(he->thread);
+ }
+
+ return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
+}
+
+static int hist_entry__fprintf(struct hist_entry *he, size_t size,
+ struct hists *hists, struct hists *pair_hists,
+ bool show_displacement, long displacement,
+ u64 total_period, FILE *fp)
+{
+ char bf[512];
+ int ret;
+
+ if (size == 0 || size > sizeof(bf))
+ size = sizeof(bf);
+
+ ret = hist_entry__period_snprintf(he, bf, size, pair_hists,
+ show_displacement, displacement,
+ true, total_period);
+ hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
+
+ ret = fprintf(fp, "%s\n", bf);
+
+ if (symbol_conf.use_callchain)
+ ret += hist_entry__callchain_fprintf(he, hists,
+ total_period, fp);
+
+ return ret;
+}
+
+size_t hists__fprintf(struct hists *hists, struct hists *pair,
+ bool show_displacement, bool show_header, int max_rows,
+ int max_cols, FILE *fp)
+{
+ struct sort_entry *se;
+ struct rb_node *nd;
+ size_t ret = 0;
+ u64 total_period;
+ unsigned long position = 1;
+ long displacement = 0;
+ unsigned int width;
+ const char *sep = symbol_conf.field_sep;
+ const char *col_width = symbol_conf.col_width_list_str;
+ int nr_rows = 0;
+
+ init_rem_hits();
+
+ if (!show_header)
+ goto print_entries;
+
+ fprintf(fp, "# %s", pair ? "Baseline" : "Overhead");
+
+ if (symbol_conf.show_cpu_utilization) {
+ if (sep) {
+ ret += fprintf(fp, "%csys", *sep);
+ ret += fprintf(fp, "%cus", *sep);
+ if (perf_guest) {
+ ret += fprintf(fp, "%cguest sys", *sep);
+ ret += fprintf(fp, "%cguest us", *sep);
+ }
+ } else {
+ ret += fprintf(fp, " sys ");
+ ret += fprintf(fp, " us ");
+ if (perf_guest) {
+ ret += fprintf(fp, " guest sys ");
+ ret += fprintf(fp, " guest us ");
+ }
+ }
+ }
+
+ if (symbol_conf.show_nr_samples) {
+ if (sep)
+ fprintf(fp, "%cSamples", *sep);
+ else
+ fputs(" Samples ", fp);
+ }
+
+ if (symbol_conf.show_total_period) {
+ if (sep)
+ ret += fprintf(fp, "%cPeriod", *sep);
+ else
+ ret += fprintf(fp, " Period ");
+ }
+
+ if (pair) {
+ if (sep)
+ ret += fprintf(fp, "%cDelta", *sep);
+ else
+ ret += fprintf(fp, " Delta ");
+
+ if (show_displacement) {
+ if (sep)
+ ret += fprintf(fp, "%cDisplacement", *sep);
+ else
+ ret += fprintf(fp, " Displ");
+ }
+ }
+
+ list_for_each_entry(se, &hist_entry__sort_list, list) {
+ if (se->elide)
+ continue;
+ if (sep) {
+ fprintf(fp, "%c%s", *sep, se->se_header);
+ continue;
+ }
+ width = strlen(se->se_header);
+ if (symbol_conf.col_width_list_str) {
+ if (col_width) {
+ hists__set_col_len(hists, se->se_width_idx,
+ atoi(col_width));
+ col_width = strchr(col_width, ',');
+ if (col_width)
+ ++col_width;
+ }
+ }
+ if (!hists__new_col_len(hists, se->se_width_idx, width))
+ width = hists__col_len(hists, se->se_width_idx);
+ fprintf(fp, " %*s", width, se->se_header);
+ }
+
+ fprintf(fp, "\n");
+ if (max_rows && ++nr_rows >= max_rows)
+ goto out;
+
+ if (sep)
+ goto print_entries;
+
+ fprintf(fp, "# ........");
+ if (symbol_conf.show_cpu_utilization)
+ fprintf(fp, " ....... .......");
+ if (symbol_conf.show_nr_samples)
+ fprintf(fp, " ..........");
+ if (symbol_conf.show_total_period)
+ fprintf(fp, " ............");
+ if (pair) {
+ fprintf(fp, " ..........");
+ if (show_displacement)
+ fprintf(fp, " .....");
+ }
+ list_for_each_entry(se, &hist_entry__sort_list, list) {
+ unsigned int i;
+
+ if (se->elide)
+ continue;
+
+ fprintf(fp, " ");
+ width = hists__col_len(hists, se->se_width_idx);
+ if (width == 0)
+ width = strlen(se->se_header);
+ for (i = 0; i < width; i++)
+ fprintf(fp, ".");
+ }
+
+ fprintf(fp, "\n");
+ if (max_rows && ++nr_rows >= max_rows)
+ goto out;
+
+ fprintf(fp, "#\n");
+ if (max_rows && ++nr_rows >= max_rows)
+ goto out;
+
+print_entries:
+ total_period = hists->stats.total_period;
+
+ for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+ struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+ if (h->filtered)
+ continue;
+
+ if (show_displacement) {
+ if (h->pair != NULL)
+ displacement = ((long)h->pair->position -
+ (long)position);
+ else
+ displacement = 0;
+ ++position;
+ }
+ ret += hist_entry__fprintf(h, max_cols, hists, pair, show_displacement,
+ displacement, total_period, fp);
+
+ if (max_rows && ++nr_rows >= max_rows)
+ goto out;
+
+ if (h->ms.map == NULL && verbose > 1) {
+ __map_groups__fprintf_maps(&h->thread->mg,
+ MAP__FUNCTION, verbose, fp);
+ fprintf(fp, "%.10s end\n", graph_dotted_line);
+ }
+ }
+out:
+ free(rem_sq_bracket);
+
+ return ret;
+}
+
+size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp)
+{
+ int i;
+ size_t ret = 0;
+
+ for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
+ const char *name;
+
+ if (hists->stats.nr_events[i] == 0)
+ continue;
+
+ name = perf_event__name(i);
+ if (!strcmp(name, "UNKNOWN"))
+ continue;
+
+ ret += fprintf(fp, "%16s events: %10d\n", name,
+ hists->stats.nr_events[i]);
+ }
+
+ return ret;
+}
--- /dev/null
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <pthread.h>
+
+#include "../../util/debug.h"
+#include "../helpline.h"
+#include "../ui.h"
+#include "../libslang.h"
+
+static void tui_helpline__pop(void)
+{
+}
+
+static void tui_helpline__push(const char *msg)
+{
+ const size_t sz = sizeof(ui_helpline__current);
+
+ SLsmg_gotorc(SLtt_Screen_Rows - 1, 0);
+ SLsmg_set_color(0);
+ SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols);
+ SLsmg_refresh();
+ strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0';
+}
+
+struct ui_helpline tui_helpline_fns = {
+ .pop = tui_helpline__pop,
+ .push = tui_helpline__push,
+};
+
+void ui_helpline__init(void)
+{
+ helpline_fns = &tui_helpline_fns;
+ ui_helpline__puts(" ");
+}
+
+char ui_helpline__last_msg[1024];
+
+int ui_helpline__show_help(const char *format, va_list ap)
+{
+ int ret;
+ static int backlog;
+
+ pthread_mutex_lock(&ui__lock);
+ ret = vscnprintf(ui_helpline__last_msg + backlog,
+ sizeof(ui_helpline__last_msg) - backlog, format, ap);
+ backlog += ret;
+
+ if (ui_helpline__last_msg[backlog - 1] == '\n') {
+ ui_helpline__puts(ui_helpline__last_msg);
+ SLsmg_refresh();
+ backlog = 0;
+ }
+ pthread_mutex_unlock(&ui__lock);
+
+ return ret;
+}
#include "../libslang.h"
#include "../keysyms.h"
-pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
-
static volatile int ui__need_resize;
extern struct perf_error_ops perf_tui_eops;
if (verbose >= level) {
va_start(args, fmt);
- if (use_browser > 0)
+ if (use_browser == 1)
ret = ui_helpline__show_help(fmt, args);
+ else if (use_browser == 2)
+ ret = perf_gtk__show_helpline(fmt, args);
else
ret = vfprintf(stderr, fmt, args);
va_end(args);
#include <stdbool.h>
#include "event.h"
+#include "../ui/helpline.h"
extern int verbose;
extern bool quiet, dump_trace;
struct perf_error_ops;
#if defined(NO_NEWT_SUPPORT) && defined(NO_GTK2_SUPPORT)
-static inline int ui_helpline__show_help(const char *format __used, va_list ap __used)
-{
- return 0;
-}
-
static inline void ui_progress__update(u64 curr __used, u64 total __used,
const char *title __used) {}
#else /* NO_NEWT_SUPPORT && NO_GTK2_SUPPORT */
-extern char ui_helpline__last_msg[];
-int ui_helpline__show_help(const char *format, va_list ap);
#include "../ui/progress.h"
int ui__error(const char *format, ...) __attribute__((format(printf, 1, 2)));
#include "../ui/util.h"
};
static int find_symbol_cb(void *arg, const char *name, char type,
- u64 start, u64 end __used)
+ u64 start)
{
struct process_symbol_args *args = arg;
u64 array[];
};
+struct regs_dump {
+ u64 *regs;
+};
+
+struct stack_dump {
+ u16 offset;
+ u64 size;
+ char *data;
+};
+
struct perf_sample {
u64 ip;
u32 pid, tid;
void *raw_data;
struct ip_callchain *callchain;
struct branch_stack *branch_stack;
+ struct regs_dump user_regs;
+ struct stack_dump user_stack;
};
#define BUILD_ID_SIZE 20
if (evlist->cpus->map[0] < 0)
opts->no_inherit = true;
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ first = perf_evlist__first(evlist);
list_for_each_entry(evsel, &evlist->entries, node) {
perf_evsel__config(evsel, opts, first);
evlist->nr_entries += nr_entries;
}
+void __perf_evlist__set_leader(struct list_head *list)
+{
+ struct perf_evsel *evsel, *leader;
+
+ leader = list_entry(list->next, struct perf_evsel, node);
+ leader->leader = NULL;
+
+ list_for_each_entry(evsel, list, node) {
+ if (evsel != leader)
+ evsel->leader = leader;
+ }
+}
+
+void perf_evlist__set_leader(struct perf_evlist *evlist)
+{
+ if (evlist->nr_entries)
+ __perf_evlist__set_leader(&evlist->entries);
+}
+
int perf_evlist__add_default(struct perf_evlist *evlist)
{
struct perf_event_attr attr = {
int hash;
if (evlist->nr_entries == 1)
- return list_entry(evlist->entries.next, struct perf_evsel, node);
+ return perf_evlist__first(evlist);
hash = hash_64(id, PERF_EVLIST__HLIST_BITS);
head = &evlist->heads[hash];
return sid->evsel;
if (!perf_evlist__sample_id_all(evlist))
- return list_entry(evlist->entries.next, struct perf_evsel, node);
+ return perf_evlist__first(evlist);
return NULL;
}
return 0;
}
-bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_type(struct perf_evlist *evlist)
{
- struct perf_evsel *pos, *first;
-
- pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
list_for_each_entry_continue(pos, &evlist->entries, node) {
if (first->attr.sample_type != pos->attr.sample_type)
return true;
}
-u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+u64 perf_evlist__sample_type(struct perf_evlist *evlist)
{
- struct perf_evsel *first;
-
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ struct perf_evsel *first = perf_evlist__first(evlist);
return first->attr.sample_type;
}
-u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist)
+u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist)
{
- struct perf_evsel *first;
+ struct perf_evsel *first = perf_evlist__first(evlist);
struct perf_sample *data;
u64 sample_type;
u16 size = 0;
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
-
if (!first->attr.sample_id_all)
goto out;
return size;
}
-bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist)
{
- struct perf_evsel *pos, *first;
-
- pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;
list_for_each_entry_continue(pos, &evlist->entries, node) {
if (first->attr.sample_id_all != pos->attr.sample_id_all)
return true;
}
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
+bool perf_evlist__sample_id_all(struct perf_evlist *evlist)
{
- struct perf_evsel *first;
-
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
+ struct perf_evsel *first = perf_evlist__first(evlist);
return first->attr.sample_id_all;
}
evlist->selected = evsel;
}
-int perf_evlist__open(struct perf_evlist *evlist, bool group)
+int perf_evlist__open(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel, *first;
+ struct perf_evsel *evsel;
int err, ncpus, nthreads;
- first = list_entry(evlist->entries.next, struct perf_evsel, node);
-
list_for_each_entry(evsel, &evlist->entries, node) {
- struct xyarray *group_fd = NULL;
-
- if (group && evsel != first)
- group_fd = first->fd;
-
- err = perf_evsel__open(evsel, evlist->cpus, evlist->threads,
- group, group_fd);
+ err = perf_evsel__open(evsel, evlist->cpus, evlist->threads);
if (err < 0)
goto out_err;
}
int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
struct perf_sample *sample, bool swapped)
{
- struct perf_evsel *e = list_entry(evlist->entries.next, struct perf_evsel, node);
- return perf_evsel__parse_sample(e, event, sample, swapped);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+ return perf_evsel__parse_sample(evsel, event, sample, swapped);
}
#include <stdio.h>
#include "../perf.h"
#include "event.h"
+#include "evsel.h"
#include "util.h"
#include <unistd.h>
void *handler;
};
-struct perf_evsel;
-
struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
struct thread_map *threads);
void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus,
union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
-int perf_evlist__open(struct perf_evlist *evlist, bool group);
+int perf_evlist__open(struct perf_evlist *evlist);
void perf_evlist__config_attrs(struct perf_evlist *evlist,
struct perf_record_opts *opts);
void perf_evlist__delete_maps(struct perf_evlist *evlist);
int perf_evlist__set_filters(struct perf_evlist *evlist);
-u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
-u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist);
+void __perf_evlist__set_leader(struct list_head *list);
+void perf_evlist__set_leader(struct perf_evlist *evlist);
+
+u64 perf_evlist__sample_type(struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
+u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
int perf_evlist__parse_sample(struct perf_evlist *evlist, union perf_event *event,
struct perf_sample *sample, bool swapped);
-bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
-bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_type(struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(struct perf_evlist *evlist);
void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
struct list_head *list,
int nr_entries);
+static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
+{
+ return list_entry(evlist->entries.next, struct perf_evsel, node);
+}
+
+static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
+{
+ return list_entry(evlist->entries.prev, struct perf_evsel, node);
+}
#endif /* __PERF_EVLIST_H */
*/
#include <byteswap.h>
+#include <linux/bitops.h>
#include "asm/bug.h"
#include "evsel.h"
#include "evlist.h"
#include "thread_map.h"
#include "target.h"
#include "../../../include/linux/hw_breakpoint.h"
+#include "../../include/linux/perf_event.h"
+#include "perf_regs.h"
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-#define GROUP_FD(group_fd, cpu) (*(int *)xyarray__entry(group_fd, cpu, 0))
static int __perf_evsel__sample_size(u64 sample_type)
{
break;
default:
- scnprintf(bf, sizeof(bf), "%s", "unknown attr type");
+ scnprintf(bf, sizeof(bf), "unknown attr type: %d",
+ evsel->attr.type);
break;
}
attr->mmap_data = track;
}
- if (opts->call_graph)
+ if (opts->call_graph) {
attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
+ if (opts->call_graph == CALLCHAIN_DWARF) {
+ attr->sample_type |= PERF_SAMPLE_REGS_USER |
+ PERF_SAMPLE_STACK_USER;
+ attr->sample_regs_user = PERF_REGS_MASK;
+ attr->sample_stack_user = opts->stack_dump_size;
+ attr->exclude_callchain_user = 1;
+ }
+ }
+
if (perf_target__has_cpu(&opts->target))
attr->sample_type |= PERF_SAMPLE_CPU;
{
perf_evsel__exit(evsel);
close_cgroup(evsel->cgrp);
+ free(evsel->group_name);
free(evsel->name);
free(evsel);
}
return 0;
}
+static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
+{
+ struct perf_evsel *leader = evsel->leader;
+ int fd;
+
+ if (!leader)
+ return -1;
+
+ /*
+ * Leader must be already processed/open,
+ * if not it's a bug.
+ */
+ BUG_ON(!leader->fd);
+
+ fd = FD(leader, cpu, thread);
+ BUG_ON(fd == -1);
+
+ return fd;
+}
+
static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads, bool group,
- struct xyarray *group_fds)
+ struct thread_map *threads)
{
int cpu, thread;
unsigned long flags = 0;
}
for (cpu = 0; cpu < cpus->nr; cpu++) {
- int group_fd = group_fds ? GROUP_FD(group_fds, cpu) : -1;
for (thread = 0; thread < threads->nr; thread++) {
+ int group_fd;
if (!evsel->cgrp)
pid = threads->map[thread];
+ group_fd = get_group_fd(evsel, cpu, thread);
+
FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
pid,
cpus->map[cpu],
err = -errno;
goto out_close;
}
-
- if (group && group_fd == -1)
- group_fd = FD(evsel, cpu, thread);
}
}
};
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads, bool group,
- struct xyarray *group_fd)
+ struct thread_map *threads)
{
if (cpus == NULL) {
/* Work around old compiler warnings about strict aliasing */
if (threads == NULL)
threads = &empty_thread_map.map;
- return __perf_evsel__open(evsel, cpus, threads, group, group_fd);
+ return __perf_evsel__open(evsel, cpus, threads);
}
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
- struct cpu_map *cpus, bool group,
- struct xyarray *group_fd)
+ struct cpu_map *cpus)
{
- return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group,
- group_fd);
+ return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
}
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
- struct thread_map *threads, bool group,
- struct xyarray *group_fd)
+ struct thread_map *threads)
{
- return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group,
- group_fd);
+ return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
}
static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
struct perf_sample *data, bool swapped)
{
u64 type = evsel->attr.sample_type;
+ u64 regs_user = evsel->attr.sample_regs_user;
const u64 *array;
/*
sz /= sizeof(u64);
array += sz;
}
+
+ if (type & PERF_SAMPLE_REGS_USER) {
+ /* First u64 tells us if we have any regs in sample. */
+ u64 avail = *array++;
+
+ if (avail) {
+ data->user_regs.regs = (u64 *)array;
+ array += hweight_long(regs_user);
+ }
+ }
+
+ if (type & PERF_SAMPLE_STACK_USER) {
+ u64 size = *array++;
+
+ data->user_stack.offset = ((char *)(array - 1)
+ - (char *) event);
+
+ if (!size) {
+ data->user_stack.size = 0;
+ } else {
+ data->user_stack.data = (char *)array;
+ array += size / sizeof(*array);
+ data->user_stack.size = *array;
+ }
+ }
+
return 0;
}
u64 *id;
struct perf_counts *counts;
int idx;
- int ids;
+ u32 ids;
struct hists hists;
char *name;
+ struct event_format *tp_format;
union {
void *priv;
off_t id_offset;
} handler;
unsigned int sample_size;
bool supported;
+ /* parse modifier helper */
+ int exclude_GH;
+ struct perf_evsel *leader;
+ char *group_name;
};
struct cpu_map;
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
- struct cpu_map *cpus, bool group,
- struct xyarray *group_fds);
+ struct cpu_map *cpus);
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
- struct thread_map *threads, bool group,
- struct xyarray *group_fds);
+ struct thread_map *threads);
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
- struct thread_map *threads, bool group,
- struct xyarray *group_fds);
+ struct thread_map *threads);
void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
#define perf_evsel__match(evsel, t, c) \
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *sample, bool swapped);
+
+static inline struct perf_evsel *perf_evsel__next(struct perf_evsel *evsel)
+{
+ return list_entry(evsel->node.next, struct perf_evsel, node);
+}
#endif /* __PERF_EVSEL_H */
p
}' "Documentation/perf-$cmd.txt"
done
+
+echo "#ifndef NO_LIBELF_SUPPORT"
+sed -n -e 's/^perf-\([^ ]*\)[ ].* full.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+ sed -n '
+ /^NAME/,/perf-'"$cmd"'/H
+ ${
+ x
+ s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/
+ p
+ }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* NO_LIBELF_SUPPORT */"
echo "};"
#include "symbol.h"
#include "debug.h"
#include "cpumap.h"
+#include "pmu.h"
static bool no_buildid_cache = false;
-static int event_count;
-static struct perf_trace_event_type *events;
+static int trace_event_count;
+static struct perf_trace_event_type *trace_events;
static u32 header_argc;
static const char **header_argv;
if (strlen(name) > MAX_EVENT_NAME)
pr_warning("Event %s will be truncated\n", name);
- nevents = realloc(events, (event_count + 1) * sizeof(*events));
+ nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events));
if (nevents == NULL)
return -ENOMEM;
- events = nevents;
+ trace_events = nevents;
- memset(&events[event_count], 0, sizeof(struct perf_trace_event_type));
- events[event_count].event_id = id;
- strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1);
- event_count++;
+ memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type));
+ trace_events[trace_event_count].event_id = id;
+ strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1);
+ trace_event_count++;
return 0;
}
char *perf_header__find_event(u64 id)
{
int i;
- for (i = 0 ; i < event_count; i++) {
- if (events[i].event_id == id)
- return events[i].name;
+ for (i = 0 ; i < trace_event_count; i++) {
+ if (trace_events[i].event_id == id)
+ return trace_events[i].name;
}
return NULL;
}
static int write_event_desc(int fd, struct perf_header *h __used,
struct perf_evlist *evlist)
{
- struct perf_evsel *attr;
+ struct perf_evsel *evsel;
u32 nre = 0, nri, sz;
int ret;
- list_for_each_entry(attr, &evlist->entries, node)
+ list_for_each_entry(evsel, &evlist->entries, node)
nre++;
/*
/*
* size of perf_event_attr struct
*/
- sz = (u32)sizeof(attr->attr);
+ sz = (u32)sizeof(evsel->attr);
ret = do_write(fd, &sz, sizeof(sz));
if (ret < 0)
return ret;
- list_for_each_entry(attr, &evlist->entries, node) {
+ list_for_each_entry(evsel, &evlist->entries, node) {
- ret = do_write(fd, &attr->attr, sz);
+ ret = do_write(fd, &evsel->attr, sz);
if (ret < 0)
return ret;
/*
* copy into an nri to be independent of the
* type of ids,
*/
- nri = attr->ids;
+ nri = evsel->ids;
ret = do_write(fd, &nri, sizeof(nri));
if (ret < 0)
return ret;
/*
* write event string as passed on cmdline
*/
- ret = do_write_string(fd, perf_evsel__name(attr));
+ ret = do_write_string(fd, perf_evsel__name(evsel));
if (ret < 0)
return ret;
/*
* write unique ids for this event
*/
- ret = do_write(fd, attr->id, attr->ids * sizeof(u64));
+ ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
if (ret < 0)
return ret;
}
return ret;
}
+/*
+ * File format:
+ *
+ * struct pmu_mappings {
+ * u32 pmu_num;
+ * struct pmu_map {
+ * u32 type;
+ * char name[];
+ * }[pmu_num];
+ * };
+ */
+
+static int write_pmu_mappings(int fd, struct perf_header *h __used,
+ struct perf_evlist *evlist __used)
+{
+ struct perf_pmu *pmu = NULL;
+ off_t offset = lseek(fd, 0, SEEK_CUR);
+ __u32 pmu_num = 0;
+
+ /* write real pmu_num later */
+ do_write(fd, &pmu_num, sizeof(pmu_num));
+
+ while ((pmu = perf_pmu__scan(pmu))) {
+ if (!pmu->name)
+ continue;
+ pmu_num++;
+ do_write(fd, &pmu->type, sizeof(pmu->type));
+ do_write_string(fd, pmu->name);
+ }
+
+ if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
+ /* discard all */
+ lseek(fd, offset, SEEK_SET);
+ return -1;
+ }
+
+ return 0;
+}
+
/*
* default get_cpuid(): nothing gets recorded
* actual implementation must be in arch/$(ARCH)/util/header.c
}
}
-static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+static void free_event_desc(struct perf_evsel *events)
{
- struct perf_event_attr attr;
- uint64_t id;
+ struct perf_evsel *evsel;
+
+ if (!events)
+ return;
+
+ for (evsel = events; evsel->attr.size; evsel++) {
+ if (evsel->name)
+ free(evsel->name);
+ if (evsel->id)
+ free(evsel->id);
+ }
+
+ free(events);
+}
+
+static struct perf_evsel *
+read_event_desc(struct perf_header *ph, int fd)
+{
+ struct perf_evsel *evsel, *events = NULL;
+ u64 *id;
void *buf = NULL;
- char *str;
u32 nre, sz, nr, i, j;
ssize_t ret;
size_t msz;
if (ph->needs_swap)
sz = bswap_32(sz);
- memset(&attr, 0, sizeof(attr));
-
/* buffer to hold on file attr struct */
buf = malloc(sz);
if (!buf)
goto error;
- msz = sizeof(attr);
+ /* the last event terminates with evsel->attr.size == 0: */
+ events = calloc(nre + 1, sizeof(*events));
+ if (!events)
+ goto error;
+
+ msz = sizeof(evsel->attr);
if (sz < msz)
msz = sz;
- for (i = 0 ; i < nre; i++) {
+ for (i = 0, evsel = events; i < nre; evsel++, i++) {
+ evsel->idx = i;
/*
* must read entire on-file attr struct to
if (ph->needs_swap)
perf_event__attr_swap(buf);
- memcpy(&attr, buf, msz);
+ memcpy(&evsel->attr, buf, msz);
ret = read(fd, &nr, sizeof(nr));
if (ret != (ssize_t)sizeof(nr))
if (ph->needs_swap)
nr = bswap_32(nr);
- str = do_read_string(fd, ph);
- fprintf(fp, "# event : name = %s, ", str);
- free(str);
+ evsel->name = do_read_string(fd, ph);
+
+ if (!nr)
+ continue;
+
+ id = calloc(nr, sizeof(*id));
+ if (!id)
+ goto error;
+ evsel->ids = nr;
+ evsel->id = id;
+
+ for (j = 0 ; j < nr; j++) {
+ ret = read(fd, id, sizeof(*id));
+ if (ret != (ssize_t)sizeof(*id))
+ goto error;
+ if (ph->needs_swap)
+ *id = bswap_64(*id);
+ id++;
+ }
+ }
+out:
+ if (buf)
+ free(buf);
+ return events;
+error:
+ if (events)
+ free_event_desc(events);
+ events = NULL;
+ goto out;
+}
+
+static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+{
+ struct perf_evsel *evsel, *events = read_event_desc(ph, fd);
+ u32 j;
+ u64 *id;
+
+ if (!events) {
+ fprintf(fp, "# event desc: not available or unable to read\n");
+ return;
+ }
+
+ for (evsel = events; evsel->attr.size; evsel++) {
+ fprintf(fp, "# event : name = %s, ", evsel->name);
fprintf(fp, "type = %d, config = 0x%"PRIx64
", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64,
- attr.type,
- (u64)attr.config,
- (u64)attr.config1,
- (u64)attr.config2);
+ evsel->attr.type,
+ (u64)evsel->attr.config,
+ (u64)evsel->attr.config1,
+ (u64)evsel->attr.config2);
fprintf(fp, ", excl_usr = %d, excl_kern = %d",
- attr.exclude_user,
- attr.exclude_kernel);
+ evsel->attr.exclude_user,
+ evsel->attr.exclude_kernel);
fprintf(fp, ", excl_host = %d, excl_guest = %d",
- attr.exclude_host,
- attr.exclude_guest);
+ evsel->attr.exclude_host,
+ evsel->attr.exclude_guest);
- fprintf(fp, ", precise_ip = %d", attr.precise_ip);
+ fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip);
- if (nr)
+ if (evsel->ids) {
fprintf(fp, ", id = {");
-
- for (j = 0 ; j < nr; j++) {
- ret = read(fd, &id, sizeof(id));
- if (ret != (ssize_t)sizeof(id))
- goto error;
-
- if (ph->needs_swap)
- id = bswap_64(id);
-
- if (j)
- fputc(',', fp);
-
- fprintf(fp, " %"PRIu64, id);
- }
- if (nr && j == nr)
+ for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
+ if (j)
+ fputc(',', fp);
+ fprintf(fp, " %"PRIu64, *id);
+ }
fprintf(fp, " }");
+ }
+
fputc('\n', fp);
}
- free(buf);
- return;
-error:
- fprintf(fp, "# event desc: not available or unable to read\n");
+
+ free_event_desc(events);
}
static void print_total_mem(struct perf_header *h __used, int fd, FILE *fp)
fprintf(fp, "# contains samples with branch stack\n");
}
+static void print_pmu_mappings(struct perf_header *ph, int fd, FILE *fp)
+{
+ const char *delimiter = "# pmu mappings: ";
+ char *name;
+ int ret;
+ u32 pmu_num;
+ u32 type;
+
+ ret = read(fd, &pmu_num, sizeof(pmu_num));
+ if (ret != sizeof(pmu_num))
+ goto error;
+
+ if (!pmu_num) {
+ fprintf(fp, "# pmu mappings: not available\n");
+ return;
+ }
+
+ while (pmu_num) {
+ if (read(fd, &type, sizeof(type)) != sizeof(type))
+ break;
+ name = do_read_string(fd, ph);
+ if (!name)
+ break;
+ pmu_num--;
+ fprintf(fp, "%s%s = %" PRIu32, delimiter, name, type);
+ free(name);
+ delimiter = ", ";
+ }
+
+ fprintf(fp, "\n");
+
+ if (!pmu_num)
+ return;
+error:
+ fprintf(fp, "# pmu mappings: unable to read\n");
+}
+
static int __event_process_build_id(struct build_id_event *bev,
char *filename,
struct perf_session *session)
return 0;
}
+static struct perf_evsel *
+perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
+{
+ struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if (evsel->idx == idx)
+ return evsel;
+ }
+
+ return NULL;
+}
+
+static void
+perf_evlist__set_event_name(struct perf_evlist *evlist, struct perf_evsel *event)
+{
+ struct perf_evsel *evsel;
+
+ if (!event->name)
+ return;
+
+ evsel = perf_evlist__find_by_index(evlist, event->idx);
+ if (!evsel)
+ return;
+
+ if (evsel->name)
+ return;
+
+ evsel->name = strdup(event->name);
+}
+
+static int
+process_event_desc(struct perf_file_section *section __unused,
+ struct perf_header *header, int feat __unused, int fd,
+ void *data __used)
+{
+ struct perf_session *session = container_of(header, struct perf_session, header);
+ struct perf_evsel *evsel, *events = read_event_desc(header, fd);
+
+ if (!events)
+ return 0;
+
+ for (evsel = events; evsel->attr.size; evsel++)
+ perf_evlist__set_event_name(session->evlist, evsel);
+
+ free_event_desc(events);
+
+ return 0;
+}
+
struct feature_ops {
int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
void (*print)(struct perf_header *h, int fd, FILE *fp);
FEAT_OPA(HEADER_CPUDESC, cpudesc),
FEAT_OPA(HEADER_CPUID, cpuid),
FEAT_OPA(HEADER_TOTAL_MEM, total_mem),
- FEAT_OPA(HEADER_EVENT_DESC, event_desc),
+ FEAT_OPP(HEADER_EVENT_DESC, event_desc),
FEAT_OPA(HEADER_CMDLINE, cmdline),
FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology),
FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology),
FEAT_OPA(HEADER_BRANCH_STACK, branch_stack),
+ FEAT_OPA(HEADER_PMU_MAPPINGS, pmu_mappings),
};
struct header_print_data {
struct perf_file_header f_header;
struct perf_file_attr f_attr;
struct perf_header *header = &session->header;
- struct perf_evsel *attr, *pair = NULL;
+ struct perf_evsel *evsel, *pair = NULL;
int err;
lseek(fd, sizeof(f_header), SEEK_SET);
if (session->evlist != evlist)
- pair = list_entry(session->evlist->entries.next, struct perf_evsel, node);
+ pair = perf_evlist__first(session->evlist);
- list_for_each_entry(attr, &evlist->entries, node) {
- attr->id_offset = lseek(fd, 0, SEEK_CUR);
- err = do_write(fd, attr->id, attr->ids * sizeof(u64));
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ evsel->id_offset = lseek(fd, 0, SEEK_CUR);
+ err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
if (err < 0) {
out_err_write:
pr_debug("failed to write perf header\n");
err = do_write(fd, pair->id, pair->ids * sizeof(u64));
if (err < 0)
goto out_err_write;
- attr->ids += pair->ids;
- pair = list_entry(pair->node.next, struct perf_evsel, node);
+ evsel->ids += pair->ids;
+ pair = perf_evsel__next(pair);
}
}
header->attr_offset = lseek(fd, 0, SEEK_CUR);
- list_for_each_entry(attr, &evlist->entries, node) {
+ list_for_each_entry(evsel, &evlist->entries, node) {
f_attr = (struct perf_file_attr){
- .attr = attr->attr,
+ .attr = evsel->attr,
.ids = {
- .offset = attr->id_offset,
- .size = attr->ids * sizeof(u64),
+ .offset = evsel->id_offset,
+ .size = evsel->ids * sizeof(u64),
}
};
err = do_write(fd, &f_attr, sizeof(f_attr));
}
header->event_offset = lseek(fd, 0, SEEK_CUR);
- header->event_size = event_count * sizeof(struct perf_trace_event_type);
- if (events) {
- err = do_write(fd, events, header->event_size);
+ header->event_size = trace_event_count * sizeof(struct perf_trace_event_type);
+ if (trace_events) {
+ err = do_write(fd, trace_events, header->event_size);
if (err < 0) {
pr_debug("failed to write perf header events\n");
return err;
static const int attr_file_abi_sizes[] = {
[0] = PERF_ATTR_SIZE_VER0,
[1] = PERF_ATTR_SIZE_VER1,
+ [2] = PERF_ATTR_SIZE_VER2,
+ [3] = PERF_ATTR_SIZE_VER3,
0,
};
if (event->name == NULL)
return -1;
+ evsel->tp_format = event;
return 0;
}
if (f_header.event_types.size) {
lseek(fd, f_header.event_types.offset, SEEK_SET);
- events = malloc(f_header.event_types.size);
- if (events == NULL)
+ trace_events = malloc(f_header.event_types.size);
+ if (trace_events == NULL)
return -ENOMEM;
- if (perf_header__getbuffer64(header, fd, events,
+ if (perf_header__getbuffer64(header, fd, trace_events,
f_header.event_types.size))
goto out_errno;
- event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type);
+ trace_event_count = f_header.event_types.size / sizeof(struct perf_trace_event_type);
}
perf_header__process_sections(header, fd, &session->pevent,
}
int perf_event__synthesize_attr(struct perf_tool *tool,
- struct perf_event_attr *attr, u16 ids, u64 *id,
+ struct perf_event_attr *attr, u32 ids, u64 *id,
perf_event__handler_t process)
{
union perf_event *ev;
memcpy(ev->attr.id, id, ids * sizeof(u64));
ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
- ev->attr.header.size = size;
+ ev->attr.header.size = (u16)size;
- err = process(tool, ev, NULL, NULL);
+ if (ev->attr.header.size == size)
+ err = process(tool, ev, NULL, NULL);
+ else
+ err = -E2BIG;
free(ev);
struct perf_session *session,
perf_event__handler_t process)
{
- struct perf_evsel *attr;
+ struct perf_evsel *evsel;
int err = 0;
- list_for_each_entry(attr, &session->evlist->entries, node) {
- err = perf_event__synthesize_attr(tool, &attr->attr, attr->ids,
- attr->id, process);
+ list_for_each_entry(evsel, &session->evlist->entries, node) {
+ err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
+ evsel->id, process);
if (err) {
pr_debug("failed to create perf header attribute\n");
return err;
int perf_event__process_attr(union perf_event *event,
struct perf_evlist **pevlist)
{
- unsigned int i, ids, n_ids;
+ u32 i, ids, n_ids;
struct perf_evsel *evsel;
struct perf_evlist *evlist = *pevlist;
struct perf_trace_event_type *type;
int i, err = 0;
- for (i = 0; i < event_count; i++) {
- type = &events[i];
+ for (i = 0; i < trace_event_count; i++) {
+ type = &trace_events[i];
err = perf_event__synthesize_event_type(tool, type->event_id,
type->name, process,
if (size_read + padding != size)
die("tracing data size mismatch");
+ perf_evlist__set_tracepoint_names(session->evlist, session->pevent);
+
return size_read + padding;
}
HEADER_CPU_TOPOLOGY,
HEADER_NUMA_TOPOLOGY,
HEADER_BRANCH_STACK,
+ HEADER_PMU_MAPPINGS,
HEADER_LAST_FEATURE,
HEADER_FEAT_BITS = 256,
};
int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
int perf_event__synthesize_attr(struct perf_tool *tool,
- struct perf_event_attr *attr, u16 ids, u64 *id,
+ struct perf_event_attr *attr, u32 ids, u64 *id,
perf_event__handler_t process);
int perf_event__synthesize_attrs(struct perf_tool *tool,
struct perf_session *session,
return false;
}
-static void hists__reset_col_len(struct hists *hists)
+void hists__reset_col_len(struct hists *hists)
{
enum hist_column col;
hists__set_col_len(hists, dso, unresolved_col_width);
}
-static void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
+void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
{
const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
u16 len;
}
}
+void hists__output_recalc_col_len(struct hists *hists, int max_rows)
+{
+ struct rb_node *next = rb_first(&hists->entries);
+ struct hist_entry *n;
+ int row = 0;
+
+ hists__reset_col_len(hists);
+
+ while (next && row++ < max_rows) {
+ n = rb_entry(next, struct hist_entry, rb_node);
+ if (!n->filtered)
+ hists__calc_col_len(hists, n);
+ next = rb_next(&n->rb_node);
+ }
+}
+
static void hist_entry__add_cpumode_period(struct hist_entry *he,
unsigned int cpumode, u64 period)
{
return __hists__output_resort(hists, true);
}
-static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
-{
- int i;
- int ret = fprintf(fp, " ");
-
- for (i = 0; i < left_margin; i++)
- ret += fprintf(fp, " ");
-
- return ret;
-}
-
-static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
- int left_margin)
-{
- int i;
- size_t ret = callchain__fprintf_left_margin(fp, left_margin);
-
- for (i = 0; i < depth; i++)
- if (depth_mask & (1 << i))
- ret += fprintf(fp, "| ");
- else
- ret += fprintf(fp, " ");
-
- ret += fprintf(fp, "\n");
-
- return ret;
-}
-
-static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
- int depth, int depth_mask, int period,
- u64 total_samples, u64 hits,
- int left_margin)
-{
- int i;
- size_t ret = 0;
-
- ret += callchain__fprintf_left_margin(fp, left_margin);
- for (i = 0; i < depth; i++) {
- if (depth_mask & (1 << i))
- ret += fprintf(fp, "|");
- else
- ret += fprintf(fp, " ");
- if (!period && i == depth - 1) {
- double percent;
-
- percent = hits * 100.0 / total_samples;
- ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
- } else
- ret += fprintf(fp, "%s", " ");
- }
- if (chain->ms.sym)
- ret += fprintf(fp, "%s\n", chain->ms.sym->name);
- else
- ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip);
-
- return ret;
-}
-
-static struct symbol *rem_sq_bracket;
-static struct callchain_list rem_hits;
-
-static void init_rem_hits(void)
-{
- rem_sq_bracket = malloc(sizeof(*rem_sq_bracket) + 6);
- if (!rem_sq_bracket) {
- fprintf(stderr, "Not enough memory to display remaining hits\n");
- return;
- }
-
- strcpy(rem_sq_bracket->name, "[...]");
- rem_hits.ms.sym = rem_sq_bracket;
-}
-
-static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
- u64 total_samples, int depth,
- int depth_mask, int left_margin)
-{
- struct rb_node *node, *next;
- struct callchain_node *child;
- struct callchain_list *chain;
- int new_depth_mask = depth_mask;
- u64 remaining;
- size_t ret = 0;
- int i;
- uint entries_printed = 0;
-
- remaining = total_samples;
-
- node = rb_first(root);
- while (node) {
- u64 new_total;
- u64 cumul;
-
- child = rb_entry(node, struct callchain_node, rb_node);
- cumul = callchain_cumul_hits(child);
- remaining -= cumul;
-
- /*
- * The depth mask manages the output of pipes that show
- * the depth. We don't want to keep the pipes of the current
- * level for the last child of this depth.
- * Except if we have remaining filtered hits. They will
- * supersede the last child
- */
- next = rb_next(node);
- if (!next && (callchain_param.mode != CHAIN_GRAPH_REL || !remaining))
- new_depth_mask &= ~(1 << (depth - 1));
-
- /*
- * But we keep the older depth mask for the line separator
- * to keep the level link until we reach the last child
- */
- ret += ipchain__fprintf_graph_line(fp, depth, depth_mask,
- left_margin);
- i = 0;
- list_for_each_entry(chain, &child->val, list) {
- ret += ipchain__fprintf_graph(fp, chain, depth,
- new_depth_mask, i++,
- total_samples,
- cumul,
- left_margin);
- }
-
- if (callchain_param.mode == CHAIN_GRAPH_REL)
- new_total = child->children_hit;
- else
- new_total = total_samples;
-
- ret += __callchain__fprintf_graph(fp, &child->rb_root, new_total,
- depth + 1,
- new_depth_mask | (1 << depth),
- left_margin);
- node = next;
- if (++entries_printed == callchain_param.print_limit)
- break;
- }
-
- if (callchain_param.mode == CHAIN_GRAPH_REL &&
- remaining && remaining != total_samples) {
-
- if (!rem_sq_bracket)
- return ret;
-
- new_depth_mask &= ~(1 << (depth - 1));
- ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
- new_depth_mask, 0, total_samples,
- remaining, left_margin);
- }
-
- return ret;
-}
-
-static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
- u64 total_samples, int left_margin)
-{
- struct callchain_node *cnode;
- struct callchain_list *chain;
- u32 entries_printed = 0;
- bool printed = false;
- struct rb_node *node;
- int i = 0;
- int ret = 0;
-
- /*
- * If have one single callchain root, don't bother printing
- * its percentage (100 % in fractal mode and the same percentage
- * than the hist in graph mode). This also avoid one level of column.
- */
- node = rb_first(root);
- if (node && !rb_next(node)) {
- cnode = rb_entry(node, struct callchain_node, rb_node);
- list_for_each_entry(chain, &cnode->val, list) {
- /*
- * If we sort by symbol, the first entry is the same than
- * the symbol. No need to print it otherwise it appears as
- * displayed twice.
- */
- if (!i++ && sort__first_dimension == SORT_SYM)
- continue;
- if (!printed) {
- ret += callchain__fprintf_left_margin(fp, left_margin);
- ret += fprintf(fp, "|\n");
- ret += callchain__fprintf_left_margin(fp, left_margin);
- ret += fprintf(fp, "---");
- left_margin += 3;
- printed = true;
- } else
- ret += callchain__fprintf_left_margin(fp, left_margin);
-
- if (chain->ms.sym)
- ret += fprintf(fp, " %s\n", chain->ms.sym->name);
- else
- ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
-
- if (++entries_printed == callchain_param.print_limit)
- break;
- }
- root = &cnode->rb_root;
- }
-
- ret += __callchain__fprintf_graph(fp, root, total_samples,
- 1, 1, left_margin);
- ret += fprintf(fp, "\n");
-
- return ret;
-}
-
-static size_t __callchain__fprintf_flat(FILE *fp,
- struct callchain_node *self,
- u64 total_samples)
-{
- struct callchain_list *chain;
- size_t ret = 0;
-
- if (!self)
- return 0;
-
- ret += __callchain__fprintf_flat(fp, self->parent, total_samples);
-
-
- list_for_each_entry(chain, &self->val, list) {
- if (chain->ip >= PERF_CONTEXT_MAX)
- continue;
- if (chain->ms.sym)
- ret += fprintf(fp, " %s\n", chain->ms.sym->name);
- else
- ret += fprintf(fp, " %p\n",
- (void *)(long)chain->ip);
- }
-
- return ret;
-}
-
-static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *self,
- u64 total_samples)
-{
- size_t ret = 0;
- u32 entries_printed = 0;
- struct rb_node *rb_node;
- struct callchain_node *chain;
-
- rb_node = rb_first(self);
- while (rb_node) {
- double percent;
-
- chain = rb_entry(rb_node, struct callchain_node, rb_node);
- percent = chain->hit * 100.0 / total_samples;
-
- ret = percent_color_fprintf(fp, " %6.2f%%\n", percent);
- ret += __callchain__fprintf_flat(fp, chain, total_samples);
- ret += fprintf(fp, "\n");
- if (++entries_printed == callchain_param.print_limit)
- break;
-
- rb_node = rb_next(rb_node);
- }
-
- return ret;
-}
-
-static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
- u64 total_samples, int left_margin,
- FILE *fp)
-{
- switch (callchain_param.mode) {
- case CHAIN_GRAPH_REL:
- return callchain__fprintf_graph(fp, &he->sorted_chain, he->period,
- left_margin);
- break;
- case CHAIN_GRAPH_ABS:
- return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
- left_margin);
- break;
- case CHAIN_FLAT:
- return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
- break;
- case CHAIN_NONE:
- break;
- default:
- pr_err("Bad callchain mode\n");
- }
-
- return 0;
-}
-
-void hists__output_recalc_col_len(struct hists *hists, int max_rows)
-{
- struct rb_node *next = rb_first(&hists->entries);
- struct hist_entry *n;
- int row = 0;
-
- hists__reset_col_len(hists);
-
- while (next && row++ < max_rows) {
- n = rb_entry(next, struct hist_entry, rb_node);
- if (!n->filtered)
- hists__calc_col_len(hists, n);
- next = rb_next(&n->rb_node);
- }
-}
-
-static int hist_entry__pcnt_snprintf(struct hist_entry *he, char *s,
- size_t size, struct hists *pair_hists,
- bool show_displacement, long displacement,
- bool color, u64 total_period)
-{
- u64 period, total, period_sys, period_us, period_guest_sys, period_guest_us;
- u64 nr_events;
- const char *sep = symbol_conf.field_sep;
- int ret;
-
- if (symbol_conf.exclude_other && !he->parent)
- return 0;
-
- if (pair_hists) {
- period = he->pair ? he->pair->period : 0;
- nr_events = he->pair ? he->pair->nr_events : 0;
- total = pair_hists->stats.total_period;
- period_sys = he->pair ? he->pair->period_sys : 0;
- period_us = he->pair ? he->pair->period_us : 0;
- period_guest_sys = he->pair ? he->pair->period_guest_sys : 0;
- period_guest_us = he->pair ? he->pair->period_guest_us : 0;
- } else {
- period = he->period;
- nr_events = he->nr_events;
- total = total_period;
- period_sys = he->period_sys;
- period_us = he->period_us;
- period_guest_sys = he->period_guest_sys;
- period_guest_us = he->period_guest_us;
- }
-
- if (total) {
- if (color)
- ret = percent_color_snprintf(s, size,
- sep ? "%.2f" : " %6.2f%%",
- (period * 100.0) / total);
- else
- ret = scnprintf(s, size, sep ? "%.2f" : " %6.2f%%",
- (period * 100.0) / total);
- if (symbol_conf.show_cpu_utilization) {
- ret += percent_color_snprintf(s + ret, size - ret,
- sep ? "%.2f" : " %6.2f%%",
- (period_sys * 100.0) / total);
- ret += percent_color_snprintf(s + ret, size - ret,
- sep ? "%.2f" : " %6.2f%%",
- (period_us * 100.0) / total);
- if (perf_guest) {
- ret += percent_color_snprintf(s + ret,
- size - ret,
- sep ? "%.2f" : " %6.2f%%",
- (period_guest_sys * 100.0) /
- total);
- ret += percent_color_snprintf(s + ret,
- size - ret,
- sep ? "%.2f" : " %6.2f%%",
- (period_guest_us * 100.0) /
- total);
- }
- }
- } else
- ret = scnprintf(s, size, sep ? "%" PRIu64 : "%12" PRIu64 " ", period);
-
- if (symbol_conf.show_nr_samples) {
- if (sep)
- ret += scnprintf(s + ret, size - ret, "%c%" PRIu64, *sep, nr_events);
- else
- ret += scnprintf(s + ret, size - ret, "%11" PRIu64, nr_events);
- }
-
- if (symbol_conf.show_total_period) {
- if (sep)
- ret += scnprintf(s + ret, size - ret, "%c%" PRIu64, *sep, period);
- else
- ret += scnprintf(s + ret, size - ret, " %12" PRIu64, period);
- }
-
- if (pair_hists) {
- char bf[32];
- double old_percent = 0, new_percent = 0, diff;
-
- if (total > 0)
- old_percent = (period * 100.0) / total;
- if (total_period > 0)
- new_percent = (he->period * 100.0) / total_period;
-
- diff = new_percent - old_percent;
-
- if (fabs(diff) >= 0.01)
- scnprintf(bf, sizeof(bf), "%+4.2F%%", diff);
- else
- scnprintf(bf, sizeof(bf), " ");
-
- if (sep)
- ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
- else
- ret += scnprintf(s + ret, size - ret, "%11.11s", bf);
-
- if (show_displacement) {
- if (displacement)
- scnprintf(bf, sizeof(bf), "%+4ld", displacement);
- else
- scnprintf(bf, sizeof(bf), " ");
-
- if (sep)
- ret += scnprintf(s + ret, size - ret, "%c%s", *sep, bf);
- else
- ret += scnprintf(s + ret, size - ret, "%6.6s", bf);
- }
- }
-
- return ret;
-}
-
-int hist_entry__snprintf(struct hist_entry *he, char *s, size_t size,
- struct hists *hists)
-{
- const char *sep = symbol_conf.field_sep;
- struct sort_entry *se;
- int ret = 0;
-
- list_for_each_entry(se, &hist_entry__sort_list, list) {
- if (se->elide)
- continue;
-
- ret += scnprintf(s + ret, size - ret, "%s", sep ?: " ");
- ret += se->se_snprintf(he, s + ret, size - ret,
- hists__col_len(hists, se->se_width_idx));
- }
-
- return ret;
-}
-
-static int hist_entry__fprintf(struct hist_entry *he, size_t size,
- struct hists *hists, struct hists *pair_hists,
- bool show_displacement, long displacement,
- u64 total_period, FILE *fp)
-{
- char bf[512];
- int ret;
-
- if (size == 0 || size > sizeof(bf))
- size = sizeof(bf);
-
- ret = hist_entry__pcnt_snprintf(he, bf, size, pair_hists,
- show_displacement, displacement,
- true, total_period);
- hist_entry__snprintf(he, bf + ret, size - ret, hists);
- return fprintf(fp, "%s\n", bf);
-}
-
-static size_t hist_entry__fprintf_callchain(struct hist_entry *he,
- struct hists *hists,
- u64 total_period, FILE *fp)
-{
- int left_margin = 0;
-
- if (sort__first_dimension == SORT_COMM) {
- struct sort_entry *se = list_first_entry(&hist_entry__sort_list,
- typeof(*se), list);
- left_margin = hists__col_len(hists, se->se_width_idx);
- left_margin -= thread__comm_len(he->thread);
- }
-
- return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
-}
-
-size_t hists__fprintf(struct hists *hists, struct hists *pair,
- bool show_displacement, bool show_header, int max_rows,
- int max_cols, FILE *fp)
-{
- struct sort_entry *se;
- struct rb_node *nd;
- size_t ret = 0;
- u64 total_period;
- unsigned long position = 1;
- long displacement = 0;
- unsigned int width;
- const char *sep = symbol_conf.field_sep;
- const char *col_width = symbol_conf.col_width_list_str;
- int nr_rows = 0;
-
- init_rem_hits();
-
- if (!show_header)
- goto print_entries;
-
- fprintf(fp, "# %s", pair ? "Baseline" : "Overhead");
-
- if (symbol_conf.show_cpu_utilization) {
- if (sep) {
- ret += fprintf(fp, "%csys", *sep);
- ret += fprintf(fp, "%cus", *sep);
- if (perf_guest) {
- ret += fprintf(fp, "%cguest sys", *sep);
- ret += fprintf(fp, "%cguest us", *sep);
- }
- } else {
- ret += fprintf(fp, " sys ");
- ret += fprintf(fp, " us ");
- if (perf_guest) {
- ret += fprintf(fp, " guest sys ");
- ret += fprintf(fp, " guest us ");
- }
- }
- }
-
- if (symbol_conf.show_nr_samples) {
- if (sep)
- fprintf(fp, "%cSamples", *sep);
- else
- fputs(" Samples ", fp);
- }
-
- if (symbol_conf.show_total_period) {
- if (sep)
- ret += fprintf(fp, "%cPeriod", *sep);
- else
- ret += fprintf(fp, " Period ");
- }
-
- if (pair) {
- if (sep)
- ret += fprintf(fp, "%cDelta", *sep);
- else
- ret += fprintf(fp, " Delta ");
-
- if (show_displacement) {
- if (sep)
- ret += fprintf(fp, "%cDisplacement", *sep);
- else
- ret += fprintf(fp, " Displ");
- }
- }
-
- list_for_each_entry(se, &hist_entry__sort_list, list) {
- if (se->elide)
- continue;
- if (sep) {
- fprintf(fp, "%c%s", *sep, se->se_header);
- continue;
- }
- width = strlen(se->se_header);
- if (symbol_conf.col_width_list_str) {
- if (col_width) {
- hists__set_col_len(hists, se->se_width_idx,
- atoi(col_width));
- col_width = strchr(col_width, ',');
- if (col_width)
- ++col_width;
- }
- }
- if (!hists__new_col_len(hists, se->se_width_idx, width))
- width = hists__col_len(hists, se->se_width_idx);
- fprintf(fp, " %*s", width, se->se_header);
- }
-
- fprintf(fp, "\n");
- if (max_rows && ++nr_rows >= max_rows)
- goto out;
-
- if (sep)
- goto print_entries;
-
- fprintf(fp, "# ........");
- if (symbol_conf.show_cpu_utilization)
- fprintf(fp, " ....... .......");
- if (symbol_conf.show_nr_samples)
- fprintf(fp, " ..........");
- if (symbol_conf.show_total_period)
- fprintf(fp, " ............");
- if (pair) {
- fprintf(fp, " ..........");
- if (show_displacement)
- fprintf(fp, " .....");
- }
- list_for_each_entry(se, &hist_entry__sort_list, list) {
- unsigned int i;
-
- if (se->elide)
- continue;
-
- fprintf(fp, " ");
- width = hists__col_len(hists, se->se_width_idx);
- if (width == 0)
- width = strlen(se->se_header);
- for (i = 0; i < width; i++)
- fprintf(fp, ".");
- }
-
- fprintf(fp, "\n");
- if (max_rows && ++nr_rows >= max_rows)
- goto out;
-
- fprintf(fp, "#\n");
- if (max_rows && ++nr_rows >= max_rows)
- goto out;
-
-print_entries:
- total_period = hists->stats.total_period;
-
- for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
- struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
- if (h->filtered)
- continue;
-
- if (show_displacement) {
- if (h->pair != NULL)
- displacement = ((long)h->pair->position -
- (long)position);
- else
- displacement = 0;
- ++position;
- }
- ret += hist_entry__fprintf(h, max_cols, hists, pair, show_displacement,
- displacement, total_period, fp);
-
- if (symbol_conf.use_callchain)
- ret += hist_entry__fprintf_callchain(h, hists, total_period, fp);
- if (max_rows && ++nr_rows >= max_rows)
- goto out;
-
- if (h->ms.map == NULL && verbose > 1) {
- __map_groups__fprintf_maps(&h->thread->mg,
- MAP__FUNCTION, verbose, fp);
- fprintf(fp, "%.10s end\n", graph_dotted_line);
- }
- }
-out:
- free(rem_sq_bracket);
-
- return ret;
-}
-
/*
* See hists__fprintf to match the column widths
*/
++hists->stats.nr_events[0];
++hists->stats.nr_events[type];
}
-
-size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp)
-{
- int i;
- size_t ret = 0;
-
- for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
- const char *name;
-
- if (hists->stats.nr_events[i] == 0)
- continue;
-
- name = perf_event__name(i);
- if (!strcmp(name, "UNKNOWN"))
- continue;
-
- ret += fprintf(fp, "%16s events: %10d\n", name,
- hists->stats.nr_events[i]);
- }
-
- return ret;
-}
struct symbol *parent, u64 period);
int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
-int hist_entry__snprintf(struct hist_entry *self, char *bf, size_t size,
- struct hists *hists);
+int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size,
+ struct hists *hists);
void hist_entry__free(struct hist_entry *);
struct hist_entry *__hists__add_branch_entry(struct hists *self,
u16 hists__col_len(struct hists *self, enum hist_column col);
void hists__set_col_len(struct hists *self, enum hist_column col, u16 len);
bool hists__new_col_len(struct hists *self, enum hist_column col, u16 len);
+void hists__reset_col_len(struct hists *hists);
+void hists__calc_col_len(struct hists *hists, struct hist_entry *he);
struct perf_evlist;
#endif
#define __used __attribute__((__unused__))
+#define __packed __attribute__((__packed__))
#endif
return NULL;
}
+/*
+ * Constructor variant for modules (where we know from /proc/modules where
+ * they are loaded) and for vmlinux, where only after we load all the
+ * symbols we'll know where it starts and ends.
+ */
+struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
+{
+ struct map *map = calloc(1, (sizeof(*map) +
+ (dso->kernel ? sizeof(struct kmap) : 0)));
+ if (map != NULL) {
+ /*
+ * ->end will be filled after we load all the symbols
+ */
+ map__init(map, type, start, 0, 0, dso);
+ }
+
+ return map;
+}
+
void map__delete(struct map *self)
{
free(self);
pr_warning(", continuing without symbols\n");
return -1;
} else if (nr == 0) {
+#ifndef NO_LIBELF_SUPPORT
const size_t len = strlen(name);
const size_t real_len = len - sizeof(DSO__DELETED);
pr_warning("no symbols found in %s, maybe install "
"a debug package?\n", name);
}
-
+#endif
return -1;
}
/*
return addr;
}
-u64 map__objdump_2ip(struct map *map, u64 addr)
-{
- u64 ip = map->dso->adjust_symbols ?
- addr :
- map->unmap_ip(map, addr); /* RIP -> IP */
- return ip;
-}
-
void map_groups__init(struct map_groups *mg)
{
int i;
/* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
u64 map__rip_2objdump(struct map *map, u64 rip);
-u64 map__objdump_2ip(struct map *map, u64 addr);
struct symbol;
struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
u64 pgoff, u32 pid, char *filename,
enum map_type type);
+struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
void map__delete(struct map *self);
struct map *map__clone(struct map *self);
int map__overlap(struct map *l, struct map *r);
void machine__exit(struct machine *self);
void machine__delete(struct machine *self);
+struct perf_evsel;
+struct perf_sample;
int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel,
struct thread *thread,
- struct ip_callchain *chain,
+ struct perf_sample *sample,
struct symbol **parent);
int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
u64 addr);
static int test__checkevent_tracepoint(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
static int test__checkevent_raw(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
static int test__checkevent_numeric(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
static int test__checkevent_symbolic_name(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
static int test__checkevent_symbolic_name_config(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
static int test__checkevent_symbolic_alias(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type);
static int test__checkevent_genhw(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->attr.type);
static int test__checkevent_breakpoint(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
static int test__checkevent_breakpoint_x(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->attr.type);
static int test__checkevent_breakpoint_r(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type",
static int test__checkevent_breakpoint_w(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type",
static int test__checkevent_breakpoint_rw(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type",
static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
static int test__checkevent_raw_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
static int test__checkevent_numeric_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
static int test__checkevent_exclude_host_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
static int test__checkevent_exclude_guest_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
static int test__checkevent_genhw_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
static int test__checkevent_breakpoint_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
+
TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
TEST_ASSERT_VAL("wrong name",
- !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:u"));
+ !strcmp(perf_evsel__name(evsel), "mem:0:u"));
return test__checkevent_breakpoint(evlist);
}
static int test__checkevent_breakpoint_x_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
TEST_ASSERT_VAL("wrong name",
- !strcmp(perf_evsel__name(evsel), "mem:0x0:x:k"));
+ !strcmp(perf_evsel__name(evsel), "mem:0:x:k"));
return test__checkevent_breakpoint_x(evlist);
}
static int test__checkevent_breakpoint_r_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
TEST_ASSERT_VAL("wrong name",
- !strcmp(perf_evsel__name(evsel), "mem:0x0:r:hp"));
+ !strcmp(perf_evsel__name(evsel), "mem:0:r:hp"));
return test__checkevent_breakpoint_r(evlist);
}
static int test__checkevent_breakpoint_w_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
TEST_ASSERT_VAL("wrong name",
- !strcmp(perf_evsel__name(evsel), "mem:0x0:w:up"));
+ !strcmp(perf_evsel__name(evsel), "mem:0:w:up"));
return test__checkevent_breakpoint_w(evlist);
}
static int test__checkevent_breakpoint_rw_modifier(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip);
TEST_ASSERT_VAL("wrong name",
- !strcmp(perf_evsel__name(evsel), "mem:0x0:rw:kp"));
+ !strcmp(perf_evsel__name(evsel), "mem:0:rw:kp"));
return test__checkevent_breakpoint_rw(evlist);
}
static int test__checkevent_pmu(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel = list_entry(evlist->entries.next,
- struct perf_evsel, node);
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
static int test__checkevent_list(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
/* r1 */
- evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
TEST_ASSERT_VAL("wrong config1", 0 == evsel->attr.config1);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
/* syscalls:sys_enter_open:k */
- evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+ evsel = perf_evsel__next(evsel);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
TEST_ASSERT_VAL("wrong sample_type",
PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
/* 1:1:hp */
- evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+ evsel = perf_evsel__next(evsel);
TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
static int test__checkevent_pmu_name(struct perf_evlist *evlist)
{
- struct perf_evsel *evsel;
+ struct perf_evsel *evsel = perf_evlist__first(evlist);
/* cpu/config=1,name=krava/u */
- evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
TEST_ASSERT_VAL("wrong config", 1 == evsel->attr.config);
TEST_ASSERT_VAL("wrong name", !strcmp(perf_evsel__name(evsel), "krava"));
/* cpu/config=2/u" */
- evsel = list_entry(evsel->node.next, struct perf_evsel, node);
+ evsel = perf_evsel__next(evsel);
TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->attr.type);
TEST_ASSERT_VAL("wrong config", 2 == evsel->attr.config);
TEST_ASSERT_VAL("wrong name",
- !strcmp(perf_evsel__name(evsel), "raw 0x2:u"));
+ !strcmp(perf_evsel__name(evsel), "cpu/config=2/u"));
return 0;
}
return 0;
}
+static int test__group1(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel, *leader;
+
+ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+
+ /* instructions:k */
+ evsel = leader = perf_evlist__first(evlist);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ /* cycles:upp */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+
+ return 0;
+}
+
+static int test__group2(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel, *leader;
+
+ TEST_ASSERT_VAL("wrong number of entries", 3 == evlist->nr_entries);
+
+ /* faults + :ku modifier */
+ evsel = leader = perf_evlist__first(evlist);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_SOFTWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_SW_PAGE_FAULTS == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ /* cache-references + :u modifier */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CACHE_REFERENCES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+
+ /* cycles:k */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ return 0;
+}
+
+static int test__group3(struct perf_evlist *evlist __used)
+{
+ struct perf_evsel *evsel, *leader;
+
+ TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+
+ /* group1 syscalls:sys_enter_open:H */
+ evsel = leader = perf_evlist__first(evlist);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong sample_type",
+ PERF_TP_SAMPLE_TYPE == evsel->attr.sample_type);
+ TEST_ASSERT_VAL("wrong sample_period", 1 == evsel->attr.sample_period);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+ TEST_ASSERT_VAL("wrong group name",
+ !strcmp(leader->group_name, "group1"));
+
+ /* group1 cycles:kppp */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 3);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+ TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+
+ /* group2 cycles + G modifier */
+ evsel = leader = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+ TEST_ASSERT_VAL("wrong group name",
+ !strcmp(leader->group_name, "group2"));
+
+ /* group2 1:3 + G modifier */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", 1 == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config", 3 == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+
+ /* instructions:u */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ return 0;
+}
+
+static int test__group4(struct perf_evlist *evlist __used)
+{
+ struct perf_evsel *evsel, *leader;
+
+ TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->nr_entries);
+
+ /* cycles:u + p */
+ evsel = leader = perf_evlist__first(evlist);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 1);
+ TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ /* instructions:kp + p */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", evsel->attr.precise_ip == 2);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+
+ return 0;
+}
+
+static int test__group5(struct perf_evlist *evlist __used)
+{
+ struct perf_evsel *evsel, *leader;
+
+ TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
+
+ /* cycles + G */
+ evsel = leader = perf_evlist__first(evlist);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ /* instructions + G */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+
+ /* cycles:G */
+ evsel = leader = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong group name", !evsel->group_name);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ /* instructions:G */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_INSTRUCTIONS == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", !evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == leader);
+
+ /* cycles */
+ evsel = perf_evsel__next(evsel);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_HARDWARE == evsel->attr.type);
+ TEST_ASSERT_VAL("wrong config",
+ PERF_COUNT_HW_CPU_CYCLES == evsel->attr.config);
+ TEST_ASSERT_VAL("wrong exclude_user", !evsel->attr.exclude_user);
+ TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->attr.exclude_kernel);
+ TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
+ TEST_ASSERT_VAL("wrong exclude guest", evsel->attr.exclude_guest);
+ TEST_ASSERT_VAL("wrong exclude host", !evsel->attr.exclude_host);
+ TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
+ TEST_ASSERT_VAL("wrong leader", evsel->leader == NULL);
+
+ return 0;
+}
+
struct test__event_st {
const char *name;
__u32 type;
.name = "mem:0:rw:kp",
.check = test__checkevent_breakpoint_rw_modifier,
},
+ [28] = {
+ .name = "{instructions:k,cycles:upp}",
+ .check = test__group1,
+ },
+ [29] = {
+ .name = "{faults:k,cache-references}:u,cycles:k",
+ .check = test__group2,
+ },
+ [30] = {
+ .name = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
+ .check = test__group3,
+ },
+ [31] = {
+ .name = "{cycles:u,instructions:kp}:p",
+ .check = test__group4,
+ },
+ [32] = {
+ .name = "{cycles,instructions}:G,{cycles:G,instructions:G},cycles",
+ .check = test__group5,
+ },
};
static struct test__event_st test__events_pmu[] = {
},
};
-#define TEST__TERMS_CNT (sizeof(test__terms) / \
- sizeof(struct test__term))
-
static int test_event(struct test__event_st *e)
{
struct perf_evlist *evlist;
static int test_events(struct test__event_st *events, unsigned cnt)
{
- int ret = 0;
+ int ret1, ret2 = 0;
unsigned i;
for (i = 0; i < cnt; i++) {
struct test__event_st *e = &events[i];
pr_debug("running test %d '%s'\n", i, e->name);
- ret = test_event(e);
- if (ret)
- break;
+ ret1 = test_event(e);
+ if (ret1)
+ ret2 = ret1;
}
- return ret;
+ return ret2;
}
static int test_term(struct test__term *t)
int parse_events__test(void)
{
- int ret;
+ int ret1, ret2 = 0;
#define TEST_EVENTS(tests) \
do { \
- ret = test_events(tests, ARRAY_SIZE(tests)); \
- if (ret) \
- return ret; \
+ ret1 = test_events(tests, ARRAY_SIZE(tests)); \
+ if (!ret2) \
+ ret2 = ret1; \
} while (0)
TEST_EVENTS(test__events);
if (test_pmu())
TEST_EVENTS(test__events_pmu);
- return test_terms(test__terms, ARRAY_SIZE(test__terms));
+ ret1 = test_terms(test__terms, ARRAY_SIZE(test__terms));
+ if (!ret2)
+ ret2 = ret1;
+
+ return ret2;
}
}
int parse_events_add_numeric(struct list_head **list, int *idx,
- unsigned long type, unsigned long config,
+ u32 type, u64 config,
struct list_head *head_config)
{
struct perf_event_attr attr;
pmu_event_name(head_config));
}
+int parse_events__modifier_group(struct list_head *list,
+ char *event_mod)
+{
+ return parse_events__modifier_event(list, event_mod, true);
+}
+
+void parse_events__set_leader(char *name, struct list_head *list)
+{
+ struct perf_evsel *leader;
+
+ __perf_evlist__set_leader(list);
+ leader = list_entry(list->next, struct perf_evsel, node);
+ leader->group_name = name ? strdup(name) : NULL;
+}
+
void parse_events_update_lists(struct list_head *list_event,
struct list_head *list_all)
{
/*
* Called for single event definition. Update the
- * 'all event' list, and reinit the 'signle event'
+ * 'all event' list, and reinit the 'single event'
* list, for next event definition.
*/
list_splice_tail(list_event, list_all);
free(list_event);
}
-int parse_events_modifier(struct list_head *list, char *str)
+struct event_modifier {
+ int eu;
+ int ek;
+ int eh;
+ int eH;
+ int eG;
+ int precise;
+ int exclude_GH;
+};
+
+static int get_event_modifier(struct event_modifier *mod, char *str,
+ struct perf_evsel *evsel)
{
- struct perf_evsel *evsel;
- int exclude = 0, exclude_GH = 0;
- int eu = 0, ek = 0, eh = 0, eH = 0, eG = 0, precise = 0;
+ int eu = evsel ? evsel->attr.exclude_user : 0;
+ int ek = evsel ? evsel->attr.exclude_kernel : 0;
+ int eh = evsel ? evsel->attr.exclude_hv : 0;
+ int eH = evsel ? evsel->attr.exclude_host : 0;
+ int eG = evsel ? evsel->attr.exclude_guest : 0;
+ int precise = evsel ? evsel->attr.precise_ip : 0;
- if (str == NULL)
- return 0;
+ int exclude = eu | ek | eh;
+ int exclude_GH = evsel ? evsel->exclude_GH : 0;
+
+ /*
+ * We are here for group and 'GH' was not set as event
+ * modifier and whatever event/group modifier override
+ * default 'GH' setup.
+ */
+ if (evsel && !exclude_GH)
+ eH = eG = 0;
+
+ memset(mod, 0, sizeof(*mod));
while (*str) {
if (*str == 'u') {
if (precise > 3)
return -EINVAL;
+ mod->eu = eu;
+ mod->ek = ek;
+ mod->eh = eh;
+ mod->eH = eH;
+ mod->eG = eG;
+ mod->precise = precise;
+ mod->exclude_GH = exclude_GH;
+ return 0;
+}
+
+int parse_events__modifier_event(struct list_head *list, char *str, bool add)
+{
+ struct perf_evsel *evsel;
+ struct event_modifier mod;
+
+ if (str == NULL)
+ return 0;
+
+ if (!add && get_event_modifier(&mod, str, NULL))
+ return -EINVAL;
+
list_for_each_entry(evsel, list, node) {
- evsel->attr.exclude_user = eu;
- evsel->attr.exclude_kernel = ek;
- evsel->attr.exclude_hv = eh;
- evsel->attr.precise_ip = precise;
- evsel->attr.exclude_host = eH;
- evsel->attr.exclude_guest = eG;
+
+ if (add && get_event_modifier(&mod, str, evsel))
+ return -EINVAL;
+
+ evsel->attr.exclude_user = mod.eu;
+ evsel->attr.exclude_kernel = mod.ek;
+ evsel->attr.exclude_hv = mod.eh;
+ evsel->attr.precise_ip = mod.precise;
+ evsel->attr.exclude_host = mod.eH;
+ evsel->attr.exclude_guest = mod.eG;
+ evsel->exclude_GH = mod.exclude_GH;
+ }
+
+ return 0;
+}
+
+int parse_events_name(struct list_head *list, char *name)
+{
+ struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, list, node) {
+ if (!evsel->name)
+ evsel->name = strdup(name);
}
return 0;
struct perf_evsel *last = NULL;
if (evlist->nr_entries > 0)
- last = list_entry(evlist->entries.prev, struct perf_evsel, node);
+ last = perf_evlist__last(evlist);
if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
fprintf(stderr,
* Print the events from <debugfs_mount_point>/tracing/events
*/
-void print_tracepoint_events(const char *subsys_glob, const char *event_glob)
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
+ bool name_only)
{
DIR *sys_dir, *evt_dir;
struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
!strglobmatch(evt_dirent.d_name, event_glob))
continue;
+ if (name_only) {
+ printf("%s:%s ", sys_dirent.d_name, evt_dirent.d_name);
+ continue;
+ }
+
snprintf(evt_path, MAXPATHLEN, "%s:%s",
sys_dirent.d_name, evt_dirent.d_name);
printf(" %-50s [%s]\n", evt_path,
__print_events_type(type, event_symbols_hw, PERF_COUNT_HW_MAX);
}
-int print_hwcache_events(const char *event_glob)
+int print_hwcache_events(const char *event_glob, bool name_only)
{
unsigned int type, op, i, printed = 0;
char name[64];
if (event_glob != NULL && !strglobmatch(name, event_glob))
continue;
- printf(" %-50s [%s]\n", name,
- event_type_descriptors[PERF_TYPE_HW_CACHE]);
+ if (name_only)
+ printf("%s ", name);
+ else
+ printf(" %-50s [%s]\n", name,
+ event_type_descriptors[PERF_TYPE_HW_CACHE]);
++printed;
}
}
}
static void print_symbol_events(const char *event_glob, unsigned type,
- struct event_symbol *syms, unsigned max)
+ struct event_symbol *syms, unsigned max,
+ bool name_only)
{
unsigned i, printed = 0;
char name[MAX_NAME_LEN];
(syms->alias && strglobmatch(syms->alias, event_glob))))
continue;
+ if (name_only) {
+ printf("%s ", syms->symbol);
+ continue;
+ }
+
if (strlen(syms->alias))
snprintf(name, MAX_NAME_LEN, "%s OR %s", syms->symbol, syms->alias);
else
/*
* Print the help text for the event symbols:
*/
-void print_events(const char *event_glob)
+void print_events(const char *event_glob, bool name_only)
{
-
- printf("\n");
- printf("List of pre-defined events (to be used in -e):\n");
+ if (!name_only) {
+ printf("\n");
+ printf("List of pre-defined events (to be used in -e):\n");
+ }
print_symbol_events(event_glob, PERF_TYPE_HARDWARE,
- event_symbols_hw, PERF_COUNT_HW_MAX);
+ event_symbols_hw, PERF_COUNT_HW_MAX, name_only);
print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
- event_symbols_sw, PERF_COUNT_SW_MAX);
+ event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
- print_hwcache_events(event_glob);
+ print_hwcache_events(event_glob, name_only);
if (event_glob != NULL)
return;
- printf("\n");
- printf(" %-50s [%s]\n",
- "rNNN",
- event_type_descriptors[PERF_TYPE_RAW]);
- printf(" %-50s [%s]\n",
- "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
- event_type_descriptors[PERF_TYPE_RAW]);
- printf(" (see 'perf list --help' on how to encode it)\n");
- printf("\n");
-
- printf(" %-50s [%s]\n",
- "mem:<addr>[:access]",
+ if (!name_only) {
+ printf("\n");
+ printf(" %-50s [%s]\n",
+ "rNNN",
+ event_type_descriptors[PERF_TYPE_RAW]);
+ printf(" %-50s [%s]\n",
+ "cpu/t1=v1[,t2=v2,t3 ...]/modifier",
+ event_type_descriptors[PERF_TYPE_RAW]);
+ printf(" (see 'perf list --help' on how to encode it)\n");
+ printf("\n");
+
+ printf(" %-50s [%s]\n",
+ "mem:<addr>[:access]",
event_type_descriptors[PERF_TYPE_BREAKPOINT]);
- printf("\n");
+ printf("\n");
+ }
- print_tracepoint_events(NULL, NULL);
+ print_tracepoint_events(NULL, NULL, name_only);
}
int parse_events__is_hardcoded_term(struct parse_events__term *term)
static int new_term(struct parse_events__term **_term, int type_val,
int type_term, char *config,
- char *str, long num)
+ char *str, u64 num)
{
struct parse_events__term *term;
}
int parse_events__term_num(struct parse_events__term **term,
- int type_term, char *config, long num)
+ int type_term, char *config, u64 num)
{
return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
config, NULL, num);
char *config;
union {
char *str;
- long num;
+ u64 num;
} val;
int type_val;
int type_term;
int parse_events__is_hardcoded_term(struct parse_events__term *term);
int parse_events__term_num(struct parse_events__term **_term,
- int type_term, char *config, long num);
+ int type_term, char *config, u64 num);
int parse_events__term_str(struct parse_events__term **_term,
int type_term, char *config, char *str);
int parse_events__term_clone(struct parse_events__term **new,
struct parse_events__term *term);
void parse_events__free_terms(struct list_head *terms);
-int parse_events_modifier(struct list_head *list, char *str);
+int parse_events__modifier_event(struct list_head *list, char *str, bool add);
+int parse_events__modifier_group(struct list_head *list, char *event_mod);
+int parse_events_name(struct list_head *list, char *name);
int parse_events_add_tracepoint(struct list_head **list, int *idx,
char *sys, char *event);
int parse_events_add_numeric(struct list_head **list, int *idx,
- unsigned long type, unsigned long config,
+ u32 type, u64 config,
struct list_head *head_config);
int parse_events_add_cache(struct list_head **list, int *idx,
char *type, char *op_result1, char *op_result2);
void *ptr, char *type);
int parse_events_add_pmu(struct list_head **list, int *idx,
char *pmu , struct list_head *head_config);
+void parse_events__set_leader(char *name, struct list_head *list);
void parse_events_update_lists(struct list_head *list_event,
struct list_head *list_all);
void parse_events_error(void *data, void *scanner, char const *msg);
int parse_events__test(void);
-void print_events(const char *event_glob);
+void print_events(const char *event_glob, bool name_only);
void print_events_type(u8 type);
-void print_tracepoint_events(const char *subsys_glob, const char *event_glob);
-int print_hwcache_events(const char *event_glob);
+void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
+ bool name_only);
+int print_hwcache_events(const char *event_glob, bool name_only);
extern int is_valid_tracepoint(const char *event_string);
extern int valid_debugfs_mount(const char *debugfs);
static int __value(YYSTYPE *yylval, char *str, int base, int token)
{
- long num;
+ u64 num;
errno = 0;
- num = strtoul(str, NULL, base);
+ num = strtoull(str, NULL, base);
if (errno)
return PE_ERROR;
%}
%x mem
+%s config
+%x event
+
+group [^,{}/]*[{][^}]*[}][^,{}/]*
+event_pmu [^,{}/]+[/][^/]*[/][^,{}/]*
+event [^,{}/]+
num_dec [0-9]+
num_hex 0x[a-fA-F0-9]+
{
int start_token;
- start_token = (int) parse_events_get_extra(yyscanner);
+ start_token = parse_events_get_extra(yyscanner);
+
+ if (start_token == PE_START_TERMS)
+ BEGIN(config);
+ else if (start_token == PE_START_EVENTS)
+ BEGIN(event);
+
if (start_token) {
parse_events_set_extra(NULL, yyscanner);
return start_token;
}
%}
+<event>{
+
+{group} {
+ BEGIN(INITIAL); yyless(0);
+ }
+
+{event_pmu} |
+{event} {
+ str(yyscanner, PE_EVENT_NAME);
+ BEGIN(INITIAL); yyless(0);
+ return PE_EVENT_NAME;
+ }
+
+. |
+<<EOF>> {
+ BEGIN(INITIAL); yyless(0);
+ }
+
+}
+
cpu-cycles|cycles { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
stalled-cycles-frontend|idle-cycles-frontend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
stalled-cycles-backend|idle-cycles-backend { return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
refs|Reference|ops|access |
misses|miss { return str(yyscanner, PE_NAME_CACHE_OP_RESULT); }
- /*
- * These are event config hardcoded term names to be specified
- * within xxx/.../ syntax. So far we dont clash with other names,
- * so we can put them here directly. In case the we have a conflict
- * in future, this needs to go into '//' condition block.
- */
+<config>{
config { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); }
period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
+, { return ','; }
+"/" { BEGIN(INITIAL); return '/'; }
+}
mem: { BEGIN(mem); return PE_PREFIX_MEM; }
r{num_raw_hex} { return raw(yyscanner); }
{modifier_event} { return str(yyscanner, PE_MODIFIER_EVENT); }
{name} { return str(yyscanner, PE_NAME); }
-"/" { return '/'; }
+"/" { BEGIN(config); return '/'; }
- { return '-'; }
-, { return ','; }
+, { BEGIN(event); return ','; }
: { return ':'; }
+"{" { BEGIN(event); return '{'; }
+"}" { return '}'; }
= { return '='; }
\n { }
%token PE_START_EVENTS PE_START_TERMS
%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
+%token PE_EVENT_NAME
%token PE_NAME
%token PE_MODIFIER_EVENT PE_MODIFIER_BP
%token PE_NAME_CACHE_TYPE PE_NAME_CACHE_OP_RESULT
-%token PE_PREFIX_MEM PE_PREFIX_RAW
+%token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
%token PE_ERROR
%type <num> PE_VALUE
%type <num> PE_VALUE_SYM_HW
%type <str> PE_NAME_CACHE_OP_RESULT
%type <str> PE_MODIFIER_EVENT
%type <str> PE_MODIFIER_BP
+%type <str> PE_EVENT_NAME
%type <num> value_sym
%type <head> event_config
%type <term> event_term
%type <head> event_legacy_numeric
%type <head> event_legacy_raw
%type <head> event_def
+%type <head> event_mod
+%type <head> event_name
+%type <head> event
+%type <head> events
+%type <head> group_def
+%type <head> group
+%type <head> groups
%union
{
char *str;
- unsigned long num;
+ u64 num;
struct list_head *head;
struct parse_events__term *term;
}
%%
start:
-PE_START_EVENTS events
+PE_START_EVENTS start_events
|
-PE_START_TERMS terms
+PE_START_TERMS start_terms
+
+start_events: groups
+{
+ struct parse_events_data__events *data = _data;
+
+ parse_events_update_lists($1, &data->list);
+}
+
+groups:
+groups ',' group
+{
+ struct list_head *list = $1;
+ struct list_head *group = $3;
+
+ parse_events_update_lists(group, list);
+ $$ = list;
+}
+|
+groups ',' event
+{
+ struct list_head *list = $1;
+ struct list_head *event = $3;
+
+ parse_events_update_lists(event, list);
+ $$ = list;
+}
+|
+group
+|
+event
+
+group:
+group_def ':' PE_MODIFIER_EVENT
+{
+ struct list_head *list = $1;
+
+ ABORT_ON(parse_events__modifier_group(list, $3));
+ $$ = list;
+}
+|
+group_def
+
+group_def:
+PE_NAME '{' events '}'
+{
+ struct list_head *list = $3;
+
+ parse_events__set_leader($1, list);
+ $$ = list;
+}
+|
+'{' events '}'
+{
+ struct list_head *list = $2;
+
+ parse_events__set_leader(NULL, list);
+ $$ = list;
+}
events:
-events ',' event | event
+events ',' event
+{
+ struct list_head *event = $3;
+ struct list_head *list = $1;
-event:
-event_def PE_MODIFIER_EVENT
+ parse_events_update_lists(event, list);
+ $$ = list;
+}
+|
+event
+
+event: event_mod
+
+event_mod:
+event_name PE_MODIFIER_EVENT
{
- struct parse_events_data__events *data = _data;
+ struct list_head *list = $1;
/*
* Apply modifier on all events added by single event definition
* (there could be more events added for multiple tracepoint
* definitions via '*?'.
*/
- ABORT_ON(parse_events_modifier($1, $2));
- parse_events_update_lists($1, &data->list);
+ ABORT_ON(parse_events__modifier_event(list, $2, false));
+ $$ = list;
}
|
-event_def
-{
- struct parse_events_data__events *data = _data;
+event_name
- parse_events_update_lists($1, &data->list);
+event_name:
+PE_EVENT_NAME event_def
+{
+ ABORT_ON(parse_events_name($2, $1));
+ free($1);
+ $$ = $2;
}
+|
+event_def
event_def: event_pmu |
event_legacy_symbol |
struct parse_events_data__events *data = _data;
struct list_head *list = NULL;
- ABORT_ON(parse_events_add_numeric(&list, &data->idx, $1, $3, NULL));
+ ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL));
$$ = list;
}
$$ = list;
}
-terms: event_config
+start_terms: event_config
{
struct parse_events_data__terms *data = _data;
data->terms = $1;
{
struct parse_events__term *term;
- ABORT_ON(parse_events__term_str(&term, $1, NULL, $3));
+ ABORT_ON(parse_events__term_str(&term, (int)$1, NULL, $3));
$$ = term;
}
|
{
struct parse_events__term *term;
- ABORT_ON(parse_events__term_num(&term, $1, NULL, $3));
+ ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, $3));
$$ = term;
}
|
{
struct parse_events__term *term;
- ABORT_ON(parse_events__term_num(&term, $1, NULL, 1));
+ ABORT_ON(parse_events__term_num(&term, (int)$1, NULL, 1));
$$ = term;
}
--- /dev/null
+#ifndef __PERF_REGS_H
+#define __PERF_REGS_H
+
+#ifndef NO_PERF_REGS
+#include <perf_regs.h>
+#else
+#define PERF_REGS_MASK 0
+
+static inline const char *perf_reg_name(int id __used)
+{
+ return NULL;
+}
+#endif /* NO_PERF_REGS */
+#endif /* __PERF_REGS_H */
#include "pmu.h"
#include "parse-events.h"
+#define EVENT_SOURCE_DEVICE_PATH "/bus/event_source/devices/"
+
int perf_pmu_parse(struct list_head *list, char *name);
extern FILE *perf_pmu_in;
return -1;
snprintf(path, PATH_MAX,
- "%s/bus/event_source/devices/%s/format", sysfs, name);
+ "%s" EVENT_SOURCE_DEVICE_PATH "%s/format", sysfs, name);
if (stat(path, &st) < 0)
return 0; /* no error if format does not exist */
return -1;
snprintf(path, PATH_MAX,
- "%s/bus/event_source/devices/%s/type", sysfs, name);
+ "%s" EVENT_SOURCE_DEVICE_PATH "%s/type", sysfs, name);
if (stat(path, &st) < 0)
return -1;
return ret;
}
+/* Add all pmus in sysfs to pmu list: */
+static void pmu_read_sysfs(void)
+{
+ char path[PATH_MAX];
+ const char *sysfs;
+ DIR *dir;
+ struct dirent *dent;
+
+ sysfs = sysfs_find_mountpoint();
+ if (!sysfs)
+ return;
+
+ snprintf(path, PATH_MAX,
+ "%s" EVENT_SOURCE_DEVICE_PATH, sysfs);
+
+ dir = opendir(path);
+ if (!dir)
+ return;
+
+ while ((dent = readdir(dir))) {
+ if (!strcmp(dent->d_name, ".") || !strcmp(dent->d_name, ".."))
+ continue;
+ /* add to static LIST_HEAD(pmus): */
+ perf_pmu__find(dent->d_name);
+ }
+
+ closedir(dir);
+}
+
static struct perf_pmu *pmu_lookup(char *name)
{
struct perf_pmu *pmu;
return NULL;
}
+struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu)
+{
+ /*
+ * pmu iterator: If pmu is NULL, we start at the begin,
+ * otherwise return the next pmu. Returns NULL on end.
+ */
+ if (!pmu) {
+ pmu_read_sysfs();
+ pmu = list_prepare_entry(pmu, &pmus, list);
+ }
+ list_for_each_entry_continue(pmu, &pmus, list)
+ return pmu;
+ return NULL;
+}
+
struct perf_pmu *perf_pmu__find(char *name)
{
struct perf_pmu *pmu;
int config, unsigned long *bits);
void perf_pmu__set_format(unsigned long *bits, long from, long to);
+struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
+
int perf_pmu__test(void);
#endif /* __PMU_H */
* This will group just the fds for this single evsel, to group
* multiple events, use evlist.open().
*/
- if (perf_evsel__open(evsel, cpus, threads, group, NULL) < 0) {
+ if (perf_evsel__open(evsel, cpus, threads) < 0) {
PyErr_SetFromErrno(PyExc_OSError);
return NULL;
}
if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist, &group))
return NULL;
- if (perf_evlist__open(evlist, group) < 0) {
+ if (group)
+ perf_evlist__set_leader(evlist);
+
+ if (perf_evlist__open(evlist) < 0) {
PyErr_SetFromErrno(PyExc_OSError);
return NULL;
}
define_event_symbols(event, ev_name, args->next);
}
-static inline
-struct event_format *find_cache_event(struct pevent *pevent, int type)
+static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
{
static char ev_name[256];
struct event_format *event;
+ int type = evsel->attr.config;
if (events[type])
return events[type];
- events[type] = event = pevent_find_event(pevent, type);
+ events[type] = event = evsel->tp_format;
if (!event)
return NULL;
}
static void perl_process_tracepoint(union perf_event *perf_event __unused,
- struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine __unused,
- struct thread *thread)
+ struct addr_location *al)
{
struct format_field *field;
static char handler[256];
unsigned long long val;
unsigned long s, ns;
struct event_format *event;
- int type;
int pid;
int cpu = sample->cpu;
void *data = sample->raw_data;
unsigned long long nsecs = sample->time;
+ struct thread *thread = al->thread;
char *comm = thread->comm;
dSP;
if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
return;
- type = trace_parse_common_type(pevent, data);
-
- event = find_cache_event(pevent, type);
+ event = find_cache_event(evsel);
if (!event)
- die("ug! no event found for type %d", type);
+ die("ug! no event found for type %d", evsel->attr.config);
- pid = trace_parse_common_pid(pevent, data);
+ pid = raw_field_value(event, "common_pid", data);
sprintf(handler, "%s::%s", event->system, event->name);
offset = field->offset;
XPUSHs(sv_2mortal(newSVpv((char *)data + offset, 0)));
} else { /* FIELD_IS_NUMERIC */
- val = read_size(pevent, data + field->offset,
+ val = read_size(event, data + field->offset,
field->size);
if (field->flags & FIELD_IS_SIGNED) {
XPUSHs(sv_2mortal(newSViv(val)));
LEAVE;
}
-static void perl_process_event_generic(union perf_event *pevent __unused,
+static void perl_process_event_generic(union perf_event *event,
struct perf_sample *sample,
- struct perf_evsel *evsel __unused,
+ struct perf_evsel *evsel,
struct machine *machine __unused,
- struct thread *thread __unused)
+ struct addr_location *al __unused)
{
dSP;
ENTER;
SAVETMPS;
PUSHMARK(SP);
- XPUSHs(sv_2mortal(newSVpvn((const char *)pevent, pevent->header.size)));
+ XPUSHs(sv_2mortal(newSVpvn((const char *)event, event->header.size)));
XPUSHs(sv_2mortal(newSVpvn((const char *)&evsel->attr, sizeof(evsel->attr))));
XPUSHs(sv_2mortal(newSVpvn((const char *)sample, sizeof(*sample))));
XPUSHs(sv_2mortal(newSVpvn((const char *)sample->raw_data, sample->raw_size)));
}
static void perl_process_event(union perf_event *event,
- struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine,
- struct thread *thread)
+ struct addr_location *al)
{
- perl_process_tracepoint(event, pevent, sample, evsel, machine, thread);
- perl_process_event_generic(event, sample, evsel, machine, thread);
+ perl_process_tracepoint(event, sample, evsel, machine, al);
+ perl_process_event_generic(event, sample, evsel, machine, al);
}
static void run_start_sub(void)
#include <errno.h>
#include "../../perf.h"
+#include "../evsel.h"
#include "../util.h"
#include "../event.h"
#include "../thread.h"
#include "../trace-event.h"
+#include "../evsel.h"
PyMODINIT_FUNC initperf_trace_context(void);
define_event_symbols(event, ev_name, args->next);
}
-static inline
-struct event_format *find_cache_event(struct pevent *pevent, int type)
+static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
{
static char ev_name[256];
struct event_format *event;
+ int type = evsel->attr.config;
+ /*
+ * XXX: Do we really need to cache this since now we have evsel->tp_format
+ * cached already? Need to re-read this "cache" routine that as well calls
+ * define_event_symbols() :-\
+ */
if (events[type])
return events[type];
- events[type] = event = pevent_find_event(pevent, type);
+ events[type] = event = evsel->tp_format;
if (!event)
return NULL;
return event;
}
-static void python_process_event(union perf_event *perf_event __unused,
- struct pevent *pevent,
+static void python_process_tracepoint(union perf_event *perf_event __unused,
struct perf_sample *sample,
- struct perf_evsel *evsel __unused,
+ struct perf_evsel *evsel,
struct machine *machine __unused,
- struct thread *thread)
+ struct addr_location *al)
{
PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
static char handler_name[256];
unsigned long s, ns;
struct event_format *event;
unsigned n = 0;
- int type;
int pid;
int cpu = sample->cpu;
void *data = sample->raw_data;
unsigned long long nsecs = sample->time;
+ struct thread *thread = al->thread;
char *comm = thread->comm;
t = PyTuple_New(MAX_FIELDS);
if (!t)
Py_FatalError("couldn't create Python tuple");
- type = trace_parse_common_type(pevent, data);
-
- event = find_cache_event(pevent, type);
+ event = find_cache_event(evsel);
if (!event)
- die("ug! no event found for type %d", type);
+ die("ug! no event found for type %d", (int)evsel->attr.config);
- pid = trace_parse_common_pid(pevent, data);
+ pid = raw_field_value(event, "common_pid", data);
sprintf(handler_name, "%s__%s", event->system, event->name);
offset = field->offset;
obj = PyString_FromString((char *)data + offset);
} else { /* FIELD_IS_NUMERIC */
- val = read_size(pevent, data + field->offset,
+ val = read_size(event, data + field->offset,
field->size);
if (field->flags & FIELD_IS_SIGNED) {
if ((long long)val >= LONG_MIN &&
Py_DECREF(t);
}
+static void python_process_general_event(union perf_event *perf_event __unused,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine __unused,
+ struct addr_location *al)
+{
+ PyObject *handler, *retval, *t, *dict;
+ static char handler_name[64];
+ unsigned n = 0;
+ struct thread *thread = al->thread;
+
+ /*
+ * Use the MAX_FIELDS to make the function expandable, though
+ * currently there is only one item for the tuple.
+ */
+ t = PyTuple_New(MAX_FIELDS);
+ if (!t)
+ Py_FatalError("couldn't create Python tuple");
+
+ dict = PyDict_New();
+ if (!dict)
+ Py_FatalError("couldn't create Python dictionary");
+
+ snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
+
+ handler = PyDict_GetItemString(main_dict, handler_name);
+ if (!handler || !PyCallable_Check(handler))
+ goto exit;
+
+ PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+ PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize(
+ (const char *)&evsel->attr, sizeof(evsel->attr)));
+ PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize(
+ (const char *)sample, sizeof(*sample)));
+ PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize(
+ (const char *)sample->raw_data, sample->raw_size));
+ PyDict_SetItemString(dict, "comm",
+ PyString_FromString(thread->comm));
+ if (al->map) {
+ PyDict_SetItemString(dict, "dso",
+ PyString_FromString(al->map->dso->name));
+ }
+ if (al->sym) {
+ PyDict_SetItemString(dict, "symbol",
+ PyString_FromString(al->sym->name));
+ }
+
+ PyTuple_SetItem(t, n++, dict);
+ if (_PyTuple_Resize(&t, n) == -1)
+ Py_FatalError("error resizing Python tuple");
+
+ retval = PyObject_CallObject(handler, t);
+ if (retval == NULL)
+ handler_call_die(handler_name);
+exit:
+ Py_DECREF(dict);
+ Py_DECREF(t);
+}
+
+static void python_process_event(union perf_event *perf_event,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine,
+ struct addr_location *al)
+{
+ switch (evsel->attr.type) {
+ case PERF_TYPE_TRACEPOINT:
+ python_process_tracepoint(perf_event, sample, evsel,
+ machine, al);
+ break;
+ /* Reserve for future process_hw/sw/raw APIs */
+ default:
+ python_process_general_event(perf_event, sample, evsel,
+ machine, al);
+ }
+}
+
static int run_start_sub(void)
{
PyObject *handler, *retval;
#include "util.h"
#include "cpumap.h"
#include "event-parse.h"
+#include "perf_regs.h"
+#include "unwind.h"
static int perf_session__open(struct perf_session *self, bool force)
{
return bi;
}
-int machine__resolve_callchain(struct machine *self,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent)
+static int machine__resolve_callchain_sample(struct machine *machine,
+ struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent)
+
{
u8 cpumode = PERF_RECORD_MISC_USER;
unsigned int i;
if (ip >= PERF_CONTEXT_MAX) {
switch (ip) {
case PERF_CONTEXT_HV:
- cpumode = PERF_RECORD_MISC_HYPERVISOR; break;
+ cpumode = PERF_RECORD_MISC_HYPERVISOR;
+ break;
case PERF_CONTEXT_KERNEL:
- cpumode = PERF_RECORD_MISC_KERNEL; break;
+ cpumode = PERF_RECORD_MISC_KERNEL;
+ break;
case PERF_CONTEXT_USER:
- cpumode = PERF_RECORD_MISC_USER; break;
+ cpumode = PERF_RECORD_MISC_USER;
+ break;
default:
pr_debug("invalid callchain context: "
"%"PRId64"\n", (s64) ip);
}
al.filtered = false;
- thread__find_addr_location(thread, self, cpumode,
+ thread__find_addr_location(thread, machine, cpumode,
MAP__FUNCTION, ip, &al, NULL);
if (al.sym != NULL) {
if (sort__has_parent && !*parent &&
return 0;
}
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+ struct callchain_cursor *cursor = arg;
+ return callchain_cursor_append(cursor, entry->ip,
+ entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct perf_sample *sample,
+ struct symbol **parent)
+
+{
+ int ret;
+
+ callchain_cursor_reset(&callchain_cursor);
+
+ ret = machine__resolve_callchain_sample(machine, thread,
+ sample->callchain, parent);
+ if (ret)
+ return ret;
+
+ /* Can we do dwarf post unwind? */
+ if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+ (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+ return 0;
+
+ return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+ thread, evsel->attr.sample_regs_user,
+ sample);
+
+}
+
static int process_event_synth_tracing_data_stub(union perf_event *event __used,
struct perf_session *session __used)
{
sample->branch_stack->entries[i].to);
}
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+ unsigned rid, i = 0;
+
+ for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+ u64 val = regs[i++];
+
+ printf(".... %-5s 0x%" PRIx64 "\n",
+ perf_reg_name(rid), val);
+ }
+}
+
+static void regs_user__printf(struct perf_sample *sample, u64 mask)
+{
+ struct regs_dump *user_regs = &sample->user_regs;
+
+ if (user_regs->regs) {
+ printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+ regs_dump__printf(mask, user_regs->regs);
+ }
+}
+
+static void stack_user__printf(struct stack_dump *dump)
+{
+ printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
+ dump->size, dump->offset);
+}
+
static void perf_session__print_tstamp(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample)
event->header.size, perf_event__name(event->header.type));
}
-static void dump_sample(struct perf_session *session, union perf_event *event,
+static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
struct perf_sample *sample)
{
u64 sample_type;
event->header.misc, sample->pid, sample->tid, sample->ip,
sample->period, sample->addr);
- sample_type = perf_evlist__sample_type(session->evlist);
+ sample_type = evsel->attr.sample_type;
if (sample_type & PERF_SAMPLE_CALLCHAIN)
callchain__printf(sample);
if (sample_type & PERF_SAMPLE_BRANCH_STACK)
branch_stack__printf(sample);
+
+ if (sample_type & PERF_SAMPLE_REGS_USER)
+ regs_user__printf(sample, evsel->attr.sample_regs_user);
+
+ if (sample_type & PERF_SAMPLE_STACK_USER)
+ stack_user__printf(&sample->user_stack);
}
static struct machine *
switch (event->header.type) {
case PERF_RECORD_SAMPLE:
- dump_sample(session, event, sample);
+ dump_sample(evsel, event, sample);
if (evsel == NULL) {
++session->hists.stats.nr_unknown_id;
return 0;
return NULL;
}
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, int print_sym,
- int print_dso, int print_symoffset)
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine,
+ int print_sym, int print_dso, int print_symoffset)
{
struct addr_location al;
struct callchain_cursor_node *node;
if (symbol_conf.use_callchain && sample->callchain) {
- if (machine__resolve_callchain(machine, al.thread,
- sample->callchain, NULL) != 0) {
+
+ if (machine__resolve_callchain(machine, evsel, al.thread,
+ sample, NULL) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
return;
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
- struct machine *machine, int print_sym,
- int print_dso, int print_symoffset);
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine,
+ int print_sym, int print_dso, int print_symoffset);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
--- /dev/null
+#include <libelf.h>
+#include <gelf.h>
+#include <elf.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <unistd.h>
+#include <inttypes.h>
+
+#include "symbol.h"
+#include "debug.h"
+
+#ifndef NT_GNU_BUILD_ID
+#define NT_GNU_BUILD_ID 3
+#endif
+
+/**
+ * elf_symtab__for_each_symbol - iterate thru all the symbols
+ *
+ * @syms: struct elf_symtab instance to iterate
+ * @idx: uint32_t idx
+ * @sym: GElf_Sym iterator
+ */
+#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \
+ for (idx = 0, gelf_getsym(syms, idx, &sym);\
+ idx < nr_syms; \
+ idx++, gelf_getsym(syms, idx, &sym))
+
+static inline uint8_t elf_sym__type(const GElf_Sym *sym)
+{
+ return GELF_ST_TYPE(sym->st_info);
+}
+
+static inline int elf_sym__is_function(const GElf_Sym *sym)
+{
+ return elf_sym__type(sym) == STT_FUNC &&
+ sym->st_name != 0 &&
+ sym->st_shndx != SHN_UNDEF;
+}
+
+static inline bool elf_sym__is_object(const GElf_Sym *sym)
+{
+ return elf_sym__type(sym) == STT_OBJECT &&
+ sym->st_name != 0 &&
+ sym->st_shndx != SHN_UNDEF;
+}
+
+static inline int elf_sym__is_label(const GElf_Sym *sym)
+{
+ return elf_sym__type(sym) == STT_NOTYPE &&
+ sym->st_name != 0 &&
+ sym->st_shndx != SHN_UNDEF &&
+ sym->st_shndx != SHN_ABS;
+}
+
+static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
+{
+ switch (type) {
+ case MAP__FUNCTION:
+ return elf_sym__is_function(sym);
+ case MAP__VARIABLE:
+ return elf_sym__is_object(sym);
+ default:
+ return false;
+ }
+}
+
+static inline const char *elf_sym__name(const GElf_Sym *sym,
+ const Elf_Data *symstrs)
+{
+ return symstrs->d_buf + sym->st_name;
+}
+
+static inline const char *elf_sec__name(const GElf_Shdr *shdr,
+ const Elf_Data *secstrs)
+{
+ return secstrs->d_buf + shdr->sh_name;
+}
+
+static inline int elf_sec__is_text(const GElf_Shdr *shdr,
+ const Elf_Data *secstrs)
+{
+ return strstr(elf_sec__name(shdr, secstrs), "text") != NULL;
+}
+
+static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
+ const Elf_Data *secstrs)
+{
+ return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
+}
+
+static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
+ enum map_type type)
+{
+ switch (type) {
+ case MAP__FUNCTION:
+ return elf_sec__is_text(shdr, secstrs);
+ case MAP__VARIABLE:
+ return elf_sec__is_data(shdr, secstrs);
+ default:
+ return false;
+ }
+}
+
+static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
+{
+ Elf_Scn *sec = NULL;
+ GElf_Shdr shdr;
+ size_t cnt = 1;
+
+ while ((sec = elf_nextscn(elf, sec)) != NULL) {
+ gelf_getshdr(sec, &shdr);
+
+ if ((addr >= shdr.sh_addr) &&
+ (addr < (shdr.sh_addr + shdr.sh_size)))
+ return cnt;
+
+ ++cnt;
+ }
+
+ return -1;
+}
+
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+ GElf_Shdr *shp, const char *name,
+ size_t *idx)
+{
+ Elf_Scn *sec = NULL;
+ size_t cnt = 1;
+
+ /* Elf is corrupted/truncated, avoid calling elf_strptr. */
+ if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL))
+ return NULL;
+
+ while ((sec = elf_nextscn(elf, sec)) != NULL) {
+ char *str;
+
+ gelf_getshdr(sec, shp);
+ str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+ if (!strcmp(name, str)) {
+ if (idx)
+ *idx = cnt;
+ break;
+ }
+ ++cnt;
+ }
+
+ return sec;
+}
+
+#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
+ for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
+ idx < nr_entries; \
+ ++idx, pos = gelf_getrel(reldata, idx, &pos_mem))
+
+#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \
+ for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \
+ idx < nr_entries; \
+ ++idx, pos = gelf_getrela(reldata, idx, &pos_mem))
+
+/*
+ * We need to check if we have a .dynsym, so that we can handle the
+ * .plt, synthesizing its symbols, that aren't on the symtabs (be it
+ * .dynsym or .symtab).
+ * And always look at the original dso, not at debuginfo packages, that
+ * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
+ */
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map,
+ symbol_filter_t filter)
+{
+ uint32_t nr_rel_entries, idx;
+ GElf_Sym sym;
+ u64 plt_offset;
+ GElf_Shdr shdr_plt;
+ struct symbol *f;
+ GElf_Shdr shdr_rel_plt, shdr_dynsym;
+ Elf_Data *reldata, *syms, *symstrs;
+ Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym;
+ size_t dynsym_idx;
+ GElf_Ehdr ehdr;
+ char sympltname[1024];
+ Elf *elf;
+ int nr = 0, symidx, err = 0;
+
+ if (!ss->dynsym)
+ return 0;
+
+ elf = ss->elf;
+ ehdr = ss->ehdr;
+
+ scn_dynsym = ss->dynsym;
+ shdr_dynsym = ss->dynshdr;
+ dynsym_idx = ss->dynsym_idx;
+
+ if (scn_dynsym == NULL)
+ goto out_elf_end;
+
+ scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
+ ".rela.plt", NULL);
+ if (scn_plt_rel == NULL) {
+ scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
+ ".rel.plt", NULL);
+ if (scn_plt_rel == NULL)
+ goto out_elf_end;
+ }
+
+ err = -1;
+
+ if (shdr_rel_plt.sh_link != dynsym_idx)
+ goto out_elf_end;
+
+ if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL)
+ goto out_elf_end;
+
+ /*
+ * Fetch the relocation section to find the idxes to the GOT
+ * and the symbols in the .dynsym they refer to.
+ */
+ reldata = elf_getdata(scn_plt_rel, NULL);
+ if (reldata == NULL)
+ goto out_elf_end;
+
+ syms = elf_getdata(scn_dynsym, NULL);
+ if (syms == NULL)
+ goto out_elf_end;
+
+ scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link);
+ if (scn_symstrs == NULL)
+ goto out_elf_end;
+
+ symstrs = elf_getdata(scn_symstrs, NULL);
+ if (symstrs == NULL)
+ goto out_elf_end;
+
+ if (symstrs->d_size == 0)
+ goto out_elf_end;
+
+ nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
+ plt_offset = shdr_plt.sh_offset;
+
+ if (shdr_rel_plt.sh_type == SHT_RELA) {
+ GElf_Rela pos_mem, *pos;
+
+ elf_section__for_each_rela(reldata, pos, pos_mem, idx,
+ nr_rel_entries) {
+ symidx = GELF_R_SYM(pos->r_info);
+ plt_offset += shdr_plt.sh_entsize;
+ gelf_getsym(syms, symidx, &sym);
+ snprintf(sympltname, sizeof(sympltname),
+ "%s@plt", elf_sym__name(&sym, symstrs));
+
+ f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+ STB_GLOBAL, sympltname);
+ if (!f)
+ goto out_elf_end;
+
+ if (filter && filter(map, f))
+ symbol__delete(f);
+ else {
+ symbols__insert(&dso->symbols[map->type], f);
+ ++nr;
+ }
+ }
+ } else if (shdr_rel_plt.sh_type == SHT_REL) {
+ GElf_Rel pos_mem, *pos;
+ elf_section__for_each_rel(reldata, pos, pos_mem, idx,
+ nr_rel_entries) {
+ symidx = GELF_R_SYM(pos->r_info);
+ plt_offset += shdr_plt.sh_entsize;
+ gelf_getsym(syms, symidx, &sym);
+ snprintf(sympltname, sizeof(sympltname),
+ "%s@plt", elf_sym__name(&sym, symstrs));
+
+ f = symbol__new(plt_offset, shdr_plt.sh_entsize,
+ STB_GLOBAL, sympltname);
+ if (!f)
+ goto out_elf_end;
+
+ if (filter && filter(map, f))
+ symbol__delete(f);
+ else {
+ symbols__insert(&dso->symbols[map->type], f);
+ ++nr;
+ }
+ }
+ }
+
+ err = 0;
+out_elf_end:
+ if (err == 0)
+ return nr;
+ pr_debug("%s: problems reading %s PLT info.\n",
+ __func__, dso->long_name);
+ return 0;
+}
+
+/*
+ * Align offset to 4 bytes as needed for note name and descriptor data.
+ */
+#define NOTE_ALIGN(n) (((n) + 3) & -4U)
+
+static int elf_read_build_id(Elf *elf, void *bf, size_t size)
+{
+ int err = -1;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ Elf_Data *data;
+ Elf_Scn *sec;
+ Elf_Kind ek;
+ void *ptr;
+
+ if (size < BUILD_ID_SIZE)
+ goto out;
+
+ ek = elf_kind(elf);
+ if (ek != ELF_K_ELF)
+ goto out;
+
+ if (gelf_getehdr(elf, &ehdr) == NULL) {
+ pr_err("%s: cannot get elf header.\n", __func__);
+ goto out;
+ }
+
+ /*
+ * Check following sections for notes:
+ * '.note.gnu.build-id'
+ * '.notes'
+ * '.note' (VDSO specific)
+ */
+ do {
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".note.gnu.build-id", NULL);
+ if (sec)
+ break;
+
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".notes", NULL);
+ if (sec)
+ break;
+
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".note", NULL);
+ if (sec)
+ break;
+
+ return err;
+
+ } while (0);
+
+ data = elf_getdata(sec, NULL);
+ if (data == NULL)
+ goto out;
+
+ ptr = data->d_buf;
+ while (ptr < (data->d_buf + data->d_size)) {
+ GElf_Nhdr *nhdr = ptr;
+ size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
+ descsz = NOTE_ALIGN(nhdr->n_descsz);
+ const char *name;
+
+ ptr += sizeof(*nhdr);
+ name = ptr;
+ ptr += namesz;
+ if (nhdr->n_type == NT_GNU_BUILD_ID &&
+ nhdr->n_namesz == sizeof("GNU")) {
+ if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
+ size_t sz = min(size, descsz);
+ memcpy(bf, ptr, sz);
+ memset(bf + sz, 0, size - sz);
+ err = descsz;
+ break;
+ }
+ }
+ ptr += descsz;
+ }
+
+out:
+ return err;
+}
+
+int filename__read_build_id(const char *filename, void *bf, size_t size)
+{
+ int fd, err = -1;
+ Elf *elf;
+
+ if (size < BUILD_ID_SIZE)
+ goto out;
+
+ fd = open(filename, O_RDONLY);
+ if (fd < 0)
+ goto out;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL) {
+ pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
+ goto out_close;
+ }
+
+ err = elf_read_build_id(elf, bf, size);
+
+ elf_end(elf);
+out_close:
+ close(fd);
+out:
+ return err;
+}
+
+int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+{
+ int fd, err = -1;
+
+ if (size < BUILD_ID_SIZE)
+ goto out;
+
+ fd = open(filename, O_RDONLY);
+ if (fd < 0)
+ goto out;
+
+ while (1) {
+ char bf[BUFSIZ];
+ GElf_Nhdr nhdr;
+ size_t namesz, descsz;
+
+ if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
+ break;
+
+ namesz = NOTE_ALIGN(nhdr.n_namesz);
+ descsz = NOTE_ALIGN(nhdr.n_descsz);
+ if (nhdr.n_type == NT_GNU_BUILD_ID &&
+ nhdr.n_namesz == sizeof("GNU")) {
+ if (read(fd, bf, namesz) != (ssize_t)namesz)
+ break;
+ if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
+ size_t sz = min(descsz, size);
+ if (read(fd, build_id, sz) == (ssize_t)sz) {
+ memset(build_id + sz, 0, size - sz);
+ err = 0;
+ break;
+ }
+ } else if (read(fd, bf, descsz) != (ssize_t)descsz)
+ break;
+ } else {
+ int n = namesz + descsz;
+ if (read(fd, bf, n) != n)
+ break;
+ }
+ }
+ close(fd);
+out:
+ return err;
+}
+
+int filename__read_debuglink(const char *filename, char *debuglink,
+ size_t size)
+{
+ int fd, err = -1;
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ Elf_Data *data;
+ Elf_Scn *sec;
+ Elf_Kind ek;
+
+ fd = open(filename, O_RDONLY);
+ if (fd < 0)
+ goto out;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL) {
+ pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
+ goto out_close;
+ }
+
+ ek = elf_kind(elf);
+ if (ek != ELF_K_ELF)
+ goto out_close;
+
+ if (gelf_getehdr(elf, &ehdr) == NULL) {
+ pr_err("%s: cannot get elf header.\n", __func__);
+ goto out_close;
+ }
+
+ sec = elf_section_by_name(elf, &ehdr, &shdr,
+ ".gnu_debuglink", NULL);
+ if (sec == NULL)
+ goto out_close;
+
+ data = elf_getdata(sec, NULL);
+ if (data == NULL)
+ goto out_close;
+
+ /* the start of this section is a zero-terminated string */
+ strncpy(debuglink, data->d_buf, size);
+
+ elf_end(elf);
+
+out_close:
+ close(fd);
+out:
+ return err;
+}
+
+static int dso__swap_init(struct dso *dso, unsigned char eidata)
+{
+ static unsigned int const endian = 1;
+
+ dso->needs_swap = DSO_SWAP__NO;
+
+ switch (eidata) {
+ case ELFDATA2LSB:
+ /* We are big endian, DSO is little endian. */
+ if (*(unsigned char const *)&endian != 1)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ case ELFDATA2MSB:
+ /* We are little endian, DSO is big endian. */
+ if (*(unsigned char const *)&endian != 0)
+ dso->needs_swap = DSO_SWAP__YES;
+ break;
+
+ default:
+ pr_err("unrecognized DSO data encoding %d\n", eidata);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+bool symsrc__possibly_runtime(struct symsrc *ss)
+{
+ return ss->dynsym || ss->opdsec;
+}
+
+bool symsrc__has_symtab(struct symsrc *ss)
+{
+ return ss->symtab != NULL;
+}
+
+void symsrc__destroy(struct symsrc *ss)
+{
+ free(ss->name);
+ elf_end(ss->elf);
+ close(ss->fd);
+}
+
+int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
+ enum dso_binary_type type)
+{
+ int err = -1;
+ GElf_Ehdr ehdr;
+ Elf *elf;
+ int fd;
+
+ fd = open(name, O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL) {
+ pr_debug("%s: cannot read %s ELF file.\n", __func__, name);
+ goto out_close;
+ }
+
+ if (gelf_getehdr(elf, &ehdr) == NULL) {
+ pr_debug("%s: cannot get elf header.\n", __func__);
+ goto out_elf_end;
+ }
+
+ if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
+ goto out_elf_end;
+
+ /* Always reject images with a mismatched build-id: */
+ if (dso->has_build_id) {
+ u8 build_id[BUILD_ID_SIZE];
+
+ if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0)
+ goto out_elf_end;
+
+ if (!dso__build_id_equal(dso, build_id))
+ goto out_elf_end;
+ }
+
+ ss->symtab = elf_section_by_name(elf, &ehdr, &ss->symshdr, ".symtab",
+ NULL);
+ if (ss->symshdr.sh_type != SHT_SYMTAB)
+ ss->symtab = NULL;
+
+ ss->dynsym_idx = 0;
+ ss->dynsym = elf_section_by_name(elf, &ehdr, &ss->dynshdr, ".dynsym",
+ &ss->dynsym_idx);
+ if (ss->dynshdr.sh_type != SHT_DYNSYM)
+ ss->dynsym = NULL;
+
+ ss->opdidx = 0;
+ ss->opdsec = elf_section_by_name(elf, &ehdr, &ss->opdshdr, ".opd",
+ &ss->opdidx);
+ if (ss->opdshdr.sh_type != SHT_PROGBITS)
+ ss->opdsec = NULL;
+
+ if (dso->kernel == DSO_TYPE_USER) {
+ GElf_Shdr shdr;
+ ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
+ elf_section_by_name(elf, &ehdr, &shdr,
+ ".gnu.prelink_undo",
+ NULL) != NULL);
+ } else {
+ ss->adjust_symbols = 0;
+ }
+
+ ss->name = strdup(name);
+ if (!ss->name)
+ goto out_elf_end;
+
+ ss->elf = elf;
+ ss->fd = fd;
+ ss->ehdr = ehdr;
+ ss->type = type;
+
+ return 0;
+
+out_elf_end:
+ elf_end(elf);
+out_close:
+ close(fd);
+ return err;
+}
+
+int dso__load_sym(struct dso *dso, struct map *map,
+ struct symsrc *syms_ss, struct symsrc *runtime_ss,
+ symbol_filter_t filter, int kmodule)
+{
+ struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
+ struct map *curr_map = map;
+ struct dso *curr_dso = dso;
+ Elf_Data *symstrs, *secstrs;
+ uint32_t nr_syms;
+ int err = -1;
+ uint32_t idx;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ Elf_Data *syms, *opddata = NULL;
+ GElf_Sym sym;
+ Elf_Scn *sec, *sec_strndx;
+ Elf *elf;
+ int nr = 0;
+
+ dso->symtab_type = syms_ss->type;
+
+ if (!syms_ss->symtab) {
+ syms_ss->symtab = syms_ss->dynsym;
+ syms_ss->symshdr = syms_ss->dynshdr;
+ }
+
+ elf = syms_ss->elf;
+ ehdr = syms_ss->ehdr;
+ sec = syms_ss->symtab;
+ shdr = syms_ss->symshdr;
+
+ if (runtime_ss->opdsec)
+ opddata = elf_rawdata(runtime_ss->opdsec, NULL);
+
+ syms = elf_getdata(sec, NULL);
+ if (syms == NULL)
+ goto out_elf_end;
+
+ sec = elf_getscn(elf, shdr.sh_link);
+ if (sec == NULL)
+ goto out_elf_end;
+
+ symstrs = elf_getdata(sec, NULL);
+ if (symstrs == NULL)
+ goto out_elf_end;
+
+ sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+ if (sec_strndx == NULL)
+ goto out_elf_end;
+
+ secstrs = elf_getdata(sec_strndx, NULL);
+ if (secstrs == NULL)
+ goto out_elf_end;
+
+ nr_syms = shdr.sh_size / shdr.sh_entsize;
+
+ memset(&sym, 0, sizeof(sym));
+ dso->adjust_symbols = runtime_ss->adjust_symbols;
+ elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
+ struct symbol *f;
+ const char *elf_name = elf_sym__name(&sym, symstrs);
+ char *demangled = NULL;
+ int is_label = elf_sym__is_label(&sym);
+ const char *section_name;
+ bool used_opd = false;
+
+ if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
+ strcmp(elf_name, kmap->ref_reloc_sym->name) == 0)
+ kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+
+ if (!is_label && !elf_sym__is_a(&sym, map->type))
+ continue;
+
+ /* Reject ARM ELF "mapping symbols": these aren't unique and
+ * don't identify functions, so will confuse the profile
+ * output: */
+ if (ehdr.e_machine == EM_ARM) {
+ if (!strcmp(elf_name, "$a") ||
+ !strcmp(elf_name, "$d") ||
+ !strcmp(elf_name, "$t"))
+ continue;
+ }
+
+ if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) {
+ u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr;
+ u64 *opd = opddata->d_buf + offset;
+ sym.st_value = DSO__SWAP(dso, u64, *opd);
+ sym.st_shndx = elf_addr_to_index(runtime_ss->elf,
+ sym.st_value);
+ used_opd = true;
+ }
+
+ sec = elf_getscn(runtime_ss->elf, sym.st_shndx);
+ if (!sec)
+ goto out_elf_end;
+
+ gelf_getshdr(sec, &shdr);
+
+ if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
+ continue;
+
+ section_name = elf_sec__name(&shdr, secstrs);
+
+ /* On ARM, symbols for thumb functions have 1 added to
+ * the symbol address as a flag - remove it */
+ if ((ehdr.e_machine == EM_ARM) &&
+ (map->type == MAP__FUNCTION) &&
+ (sym.st_value & 1))
+ --sym.st_value;
+
+ if (dso->kernel != DSO_TYPE_USER || kmodule) {
+ char dso_name[PATH_MAX];
+
+ if (strcmp(section_name,
+ (curr_dso->short_name +
+ dso->short_name_len)) == 0)
+ goto new_symbol;
+
+ if (strcmp(section_name, ".text") == 0) {
+ curr_map = map;
+ curr_dso = dso;
+ goto new_symbol;
+ }
+
+ snprintf(dso_name, sizeof(dso_name),
+ "%s%s", dso->short_name, section_name);
+
+ curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
+ if (curr_map == NULL) {
+ u64 start = sym.st_value;
+
+ if (kmodule)
+ start += map->start + shdr.sh_offset;
+
+ curr_dso = dso__new(dso_name);
+ if (curr_dso == NULL)
+ goto out_elf_end;
+ curr_dso->kernel = dso->kernel;
+ curr_dso->long_name = dso->long_name;
+ curr_dso->long_name_len = dso->long_name_len;
+ curr_map = map__new2(start, curr_dso,
+ map->type);
+ if (curr_map == NULL) {
+ dso__delete(curr_dso);
+ goto out_elf_end;
+ }
+ curr_map->map_ip = identity__map_ip;
+ curr_map->unmap_ip = identity__map_ip;
+ curr_dso->symtab_type = dso->symtab_type;
+ map_groups__insert(kmap->kmaps, curr_map);
+ dsos__add(&dso->node, curr_dso);
+ dso__set_loaded(curr_dso, map->type);
+ } else
+ curr_dso = curr_map->dso;
+
+ goto new_symbol;
+ }
+
+ if ((used_opd && runtime_ss->adjust_symbols)
+ || (!used_opd && syms_ss->adjust_symbols)) {
+ pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
+ "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
+ (u64)sym.st_value, (u64)shdr.sh_addr,
+ (u64)shdr.sh_offset);
+ sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+ }
+ /*
+ * We need to figure out if the object was created from C++ sources
+ * DWARF DW_compile_unit has this, but we don't always have access
+ * to it...
+ */
+ demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI);
+ if (demangled != NULL)
+ elf_name = demangled;
+new_symbol:
+ f = symbol__new(sym.st_value, sym.st_size,
+ GELF_ST_BIND(sym.st_info), elf_name);
+ free(demangled);
+ if (!f)
+ goto out_elf_end;
+
+ if (filter && filter(curr_map, f))
+ symbol__delete(f);
+ else {
+ symbols__insert(&curr_dso->symbols[curr_map->type], f);
+ nr++;
+ }
+ }
+
+ /*
+ * For misannotated, zeroed, ASM function sizes.
+ */
+ if (nr > 0) {
+ symbols__fixup_duplicate(&dso->symbols[map->type]);
+ symbols__fixup_end(&dso->symbols[map->type]);
+ if (kmap) {
+ /*
+ * We need to fixup this here too because we create new
+ * maps here, for things like vsyscall sections.
+ */
+ __map_groups__fixup_end(kmap->kmaps, map->type);
+ }
+ }
+ err = nr;
+out_elf_end:
+ return err;
+}
+
+void symbol__elf_init(void)
+{
+ elf_version(EV_CURRENT);
+}
--- /dev/null
+#include "symbol.h"
+
+#include <elf.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <string.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+
+
+static bool check_need_swap(int file_endian)
+{
+ const int data = 1;
+ u8 *check = (u8 *)&data;
+ int host_endian;
+
+ if (check[0] == 1)
+ host_endian = ELFDATA2LSB;
+ else
+ host_endian = ELFDATA2MSB;
+
+ return host_endian != file_endian;
+}
+
+#define NOTE_ALIGN(sz) (((sz) + 3) & ~3)
+
+#define NT_GNU_BUILD_ID 3
+
+static int read_build_id(void *note_data, size_t note_len, void *bf,
+ size_t size, bool need_swap)
+{
+ struct {
+ u32 n_namesz;
+ u32 n_descsz;
+ u32 n_type;
+ } *nhdr;
+ void *ptr;
+
+ ptr = note_data;
+ while (ptr < (note_data + note_len)) {
+ const char *name;
+ size_t namesz, descsz;
+
+ nhdr = ptr;
+ if (need_swap) {
+ nhdr->n_namesz = bswap_32(nhdr->n_namesz);
+ nhdr->n_descsz = bswap_32(nhdr->n_descsz);
+ nhdr->n_type = bswap_32(nhdr->n_type);
+ }
+
+ namesz = NOTE_ALIGN(nhdr->n_namesz);
+ descsz = NOTE_ALIGN(nhdr->n_descsz);
+
+ ptr += sizeof(*nhdr);
+ name = ptr;
+ ptr += namesz;
+ if (nhdr->n_type == NT_GNU_BUILD_ID &&
+ nhdr->n_namesz == sizeof("GNU")) {
+ if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
+ size_t sz = min(size, descsz);
+ memcpy(bf, ptr, sz);
+ memset(bf + sz, 0, size - sz);
+ return 0;
+ }
+ }
+ ptr += descsz;
+ }
+
+ return -1;
+}
+
+int filename__read_debuglink(const char *filename __used,
+ char *debuglink __used, size_t size __used)
+{
+ return -1;
+}
+
+/*
+ * Just try PT_NOTE header otherwise fails
+ */
+int filename__read_build_id(const char *filename, void *bf, size_t size)
+{
+ FILE *fp;
+ int ret = -1;
+ bool need_swap = false;
+ u8 e_ident[EI_NIDENT];
+ size_t buf_size;
+ void *buf;
+ int i;
+
+ fp = fopen(filename, "r");
+ if (fp == NULL)
+ return -1;
+
+ if (fread(e_ident, sizeof(e_ident), 1, fp) != 1)
+ goto out;
+
+ if (memcmp(e_ident, ELFMAG, SELFMAG) ||
+ e_ident[EI_VERSION] != EV_CURRENT)
+ goto out;
+
+ need_swap = check_need_swap(e_ident[EI_DATA]);
+
+ /* for simplicity */
+ fseek(fp, 0, SEEK_SET);
+
+ if (e_ident[EI_CLASS] == ELFCLASS32) {
+ Elf32_Ehdr ehdr;
+ Elf32_Phdr *phdr;
+
+ if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+ goto out;
+
+ if (need_swap) {
+ ehdr.e_phoff = bswap_32(ehdr.e_phoff);
+ ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
+ ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+ }
+
+ buf_size = ehdr.e_phentsize * ehdr.e_phnum;
+ buf = malloc(buf_size);
+ if (buf == NULL)
+ goto out;
+
+ fseek(fp, ehdr.e_phoff, SEEK_SET);
+ if (fread(buf, buf_size, 1, fp) != 1)
+ goto out_free;
+
+ for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+ void *tmp;
+
+ if (need_swap) {
+ phdr->p_type = bswap_32(phdr->p_type);
+ phdr->p_offset = bswap_32(phdr->p_offset);
+ phdr->p_filesz = bswap_32(phdr->p_filesz);
+ }
+
+ if (phdr->p_type != PT_NOTE)
+ continue;
+
+ buf_size = phdr->p_filesz;
+ tmp = realloc(buf, buf_size);
+ if (tmp == NULL)
+ goto out_free;
+
+ buf = tmp;
+ fseek(fp, phdr->p_offset, SEEK_SET);
+ if (fread(buf, buf_size, 1, fp) != 1)
+ goto out_free;
+
+ ret = read_build_id(buf, buf_size, bf, size, need_swap);
+ if (ret == 0)
+ ret = size;
+ break;
+ }
+ } else {
+ Elf64_Ehdr ehdr;
+ Elf64_Phdr *phdr;
+
+ if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1)
+ goto out;
+
+ if (need_swap) {
+ ehdr.e_phoff = bswap_64(ehdr.e_phoff);
+ ehdr.e_phentsize = bswap_16(ehdr.e_phentsize);
+ ehdr.e_phnum = bswap_16(ehdr.e_phnum);
+ }
+
+ buf_size = ehdr.e_phentsize * ehdr.e_phnum;
+ buf = malloc(buf_size);
+ if (buf == NULL)
+ goto out;
+
+ fseek(fp, ehdr.e_phoff, SEEK_SET);
+ if (fread(buf, buf_size, 1, fp) != 1)
+ goto out_free;
+
+ for (i = 0, phdr = buf; i < ehdr.e_phnum; i++, phdr++) {
+ void *tmp;
+
+ if (need_swap) {
+ phdr->p_type = bswap_32(phdr->p_type);
+ phdr->p_offset = bswap_64(phdr->p_offset);
+ phdr->p_filesz = bswap_64(phdr->p_filesz);
+ }
+
+ if (phdr->p_type != PT_NOTE)
+ continue;
+
+ buf_size = phdr->p_filesz;
+ tmp = realloc(buf, buf_size);
+ if (tmp == NULL)
+ goto out_free;
+
+ buf = tmp;
+ fseek(fp, phdr->p_offset, SEEK_SET);
+ if (fread(buf, buf_size, 1, fp) != 1)
+ goto out_free;
+
+ ret = read_build_id(buf, buf_size, bf, size, need_swap);
+ if (ret == 0)
+ ret = size;
+ break;
+ }
+ }
+out_free:
+ free(buf);
+out:
+ fclose(fp);
+ return ret;
+}
+
+int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
+{
+ int fd;
+ int ret = -1;
+ struct stat stbuf;
+ size_t buf_size;
+ void *buf;
+
+ fd = open(filename, O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ if (fstat(fd, &stbuf) < 0)
+ goto out;
+
+ buf_size = stbuf.st_size;
+ buf = malloc(buf_size);
+ if (buf == NULL)
+ goto out;
+
+ if (read(fd, buf, buf_size) != (ssize_t) buf_size)
+ goto out_free;
+
+ ret = read_build_id(buf, buf_size, build_id, size, false);
+out_free:
+ free(buf);
+out:
+ close(fd);
+ return ret;
+}
+
+int symsrc__init(struct symsrc *ss, struct dso *dso __used, const char *name,
+ enum dso_binary_type type)
+{
+ int fd = open(name, O_RDONLY);
+ if (fd < 0)
+ return -1;
+
+ ss->name = strdup(name);
+ if (!ss->name)
+ goto out_close;
+
+ ss->type = type;
+
+ return 0;
+out_close:
+ close(fd);
+ return -1;
+}
+
+bool symsrc__possibly_runtime(struct symsrc *ss __used)
+{
+ /* Assume all sym sources could be a runtime image. */
+ return true;
+}
+
+bool symsrc__has_symtab(struct symsrc *ss __used)
+{
+ return false;
+}
+
+void symsrc__destroy(struct symsrc *ss)
+{
+ free(ss->name);
+ close(ss->fd);
+}
+
+int dso__synthesize_plt_symbols(struct dso *dso __used,
+ struct symsrc *ss __used,
+ struct map *map __used,
+ symbol_filter_t filter __used)
+{
+ return 0;
+}
+
+int dso__load_sym(struct dso *dso, struct map *map __used, struct symsrc *ss,
+ struct symsrc *runtime_ss __used,
+ symbol_filter_t filter __used, int kmodule __used)
+{
+ unsigned char *build_id[BUILD_ID_SIZE];
+
+ if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
+ dso__set_build_id(dso, build_id);
+ return 1;
+ }
+ return 0;
+}
+
+void symbol__elf_init(void)
+{
+}
#include "symbol.h"
#include "strlist.h"
-#include <libelf.h>
-#include <gelf.h>
#include <elf.h>
#include <limits.h>
#include <sys/utsname.h>
#define KSYM_NAME_LEN 256
#endif
-#ifndef NT_GNU_BUILD_ID
-#define NT_GNU_BUILD_ID 3
-#endif
-
static void dso_cache__free(struct rb_root *root);
-static bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
-static int elf_read_build_id(Elf *elf, void *bf, size_t size);
-static void dsos__add(struct list_head *head, struct dso *dso);
-static struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
static int dso__load_kernel_sym(struct dso *dso, struct map *map,
symbol_filter_t filter);
static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map,
return SYMBOL_B;
}
-static void symbols__fixup_duplicate(struct rb_root *symbols)
+void symbols__fixup_duplicate(struct rb_root *symbols)
{
struct rb_node *nd;
struct symbol *curr, *next;
}
}
-static void symbols__fixup_end(struct rb_root *symbols)
+void symbols__fixup_end(struct rb_root *symbols)
{
struct rb_node *nd, *prevnd = rb_first(symbols);
struct symbol *curr, *prev;
curr->end = roundup(curr->start, 4096);
}
-static void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
+void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
{
struct map *prev, *curr;
struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
__map_groups__fixup_end(mg, i);
}
-static struct symbol *symbol__new(u64 start, u64 len, u8 binding,
- const char *name)
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
{
size_t namelen = strlen(name) + 1;
struct symbol *sym = calloc(1, (symbol_conf.priv_size +
dso->has_build_id = 1;
}
-static void symbols__insert(struct rb_root *symbols, struct symbol *sym)
+void symbols__insert(struct rb_root *symbols, struct symbol *sym)
{
struct rb_node **p = &symbols->rb_node;
struct rb_node *parent = NULL;
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
- char type, u64 start, u64 end))
+ char type, u64 start))
{
char *line = NULL;
size_t n;
break;
}
- /*
- * module symbols are not sorted so we add all
- * symbols with zero length and rely on
- * symbols__fixup_end() to fix it up.
- */
err = process_symbol(arg, symbol_name,
- symbol_type, start, start);
+ symbol_type, start);
if (err)
break;
}
}
static int map__process_kallsym_symbol(void *arg, const char *name,
- char type, u64 start, u64 end)
+ char type, u64 start)
{
struct symbol *sym;
struct process_kallsyms_args *a = arg;
if (!symbol_type__is_a(type, a->map->type))
return 0;
- sym = symbol__new(start, end - start + 1,
- kallsyms2elf_type(type), name);
+ /*
+ * module symbols are not sorted so we add all
+ * symbols, setting length to 0, and rely on
+ * symbols__fixup_end() to fix it up.
+ */
+ sym = symbol__new(start, 0, kallsyms2elf_type(type), name);
if (sym == NULL)
return -ENOMEM;
/*
return -1;
}
-/**
- * elf_symtab__for_each_symbol - iterate thru all the symbols
- *
- * @syms: struct elf_symtab instance to iterate
- * @idx: uint32_t idx
- * @sym: GElf_Sym iterator
- */
-#define elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) \
- for (idx = 0, gelf_getsym(syms, idx, &sym);\
- idx < nr_syms; \
- idx++, gelf_getsym(syms, idx, &sym))
-
-static inline uint8_t elf_sym__type(const GElf_Sym *sym)
-{
- return GELF_ST_TYPE(sym->st_info);
-}
-
-static inline int elf_sym__is_function(const GElf_Sym *sym)
-{
- return elf_sym__type(sym) == STT_FUNC &&
- sym->st_name != 0 &&
- sym->st_shndx != SHN_UNDEF;
-}
-
-static inline bool elf_sym__is_object(const GElf_Sym *sym)
-{
- return elf_sym__type(sym) == STT_OBJECT &&
- sym->st_name != 0 &&
- sym->st_shndx != SHN_UNDEF;
-}
-
-static inline int elf_sym__is_label(const GElf_Sym *sym)
-{
- return elf_sym__type(sym) == STT_NOTYPE &&
- sym->st_name != 0 &&
- sym->st_shndx != SHN_UNDEF &&
- sym->st_shndx != SHN_ABS;
-}
-
-static inline const char *elf_sec__name(const GElf_Shdr *shdr,
- const Elf_Data *secstrs)
-{
- return secstrs->d_buf + shdr->sh_name;
-}
-
-static inline int elf_sec__is_text(const GElf_Shdr *shdr,
- const Elf_Data *secstrs)
-{
- return strstr(elf_sec__name(shdr, secstrs), "text") != NULL;
-}
-
-static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
- const Elf_Data *secstrs)
-{
- return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
-}
-
-static inline const char *elf_sym__name(const GElf_Sym *sym,
- const Elf_Data *symstrs)
-{
- return symstrs->d_buf + sym->st_name;
-}
-
-static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
- GElf_Shdr *shp, const char *name,
- size_t *idx)
-{
- Elf_Scn *sec = NULL;
- size_t cnt = 1;
-
- while ((sec = elf_nextscn(elf, sec)) != NULL) {
- char *str;
-
- gelf_getshdr(sec, shp);
- str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
- if (!strcmp(name, str)) {
- if (idx)
- *idx = cnt;
- break;
- }
- ++cnt;
- }
-
- return sec;
-}
-
-#define elf_section__for_each_rel(reldata, pos, pos_mem, idx, nr_entries) \
- for (idx = 0, pos = gelf_getrel(reldata, 0, &pos_mem); \
- idx < nr_entries; \
- ++idx, pos = gelf_getrel(reldata, idx, &pos_mem))
-
-#define elf_section__for_each_rela(reldata, pos, pos_mem, idx, nr_entries) \
- for (idx = 0, pos = gelf_getrela(reldata, 0, &pos_mem); \
- idx < nr_entries; \
- ++idx, pos = gelf_getrela(reldata, idx, &pos_mem))
-
-/*
- * We need to check if we have a .dynsym, so that we can handle the
- * .plt, synthesizing its symbols, that aren't on the symtabs (be it
- * .dynsym or .symtab).
- * And always look at the original dso, not at debuginfo packages, that
- * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
- */
-static int
-dso__synthesize_plt_symbols(struct dso *dso, char *name, struct map *map,
- symbol_filter_t filter)
-{
- uint32_t nr_rel_entries, idx;
- GElf_Sym sym;
- u64 plt_offset;
- GElf_Shdr shdr_plt;
- struct symbol *f;
- GElf_Shdr shdr_rel_plt, shdr_dynsym;
- Elf_Data *reldata, *syms, *symstrs;
- Elf_Scn *scn_plt_rel, *scn_symstrs, *scn_dynsym;
- size_t dynsym_idx;
- GElf_Ehdr ehdr;
- char sympltname[1024];
- Elf *elf;
- int nr = 0, symidx, fd, err = 0;
-
- fd = open(name, O_RDONLY);
- if (fd < 0)
- goto out;
-
- elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
- if (elf == NULL)
- goto out_close;
-
- if (gelf_getehdr(elf, &ehdr) == NULL)
- goto out_elf_end;
-
- scn_dynsym = elf_section_by_name(elf, &ehdr, &shdr_dynsym,
- ".dynsym", &dynsym_idx);
- if (scn_dynsym == NULL)
- goto out_elf_end;
-
- scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
- ".rela.plt", NULL);
- if (scn_plt_rel == NULL) {
- scn_plt_rel = elf_section_by_name(elf, &ehdr, &shdr_rel_plt,
- ".rel.plt", NULL);
- if (scn_plt_rel == NULL)
- goto out_elf_end;
- }
-
- err = -1;
-
- if (shdr_rel_plt.sh_link != dynsym_idx)
- goto out_elf_end;
-
- if (elf_section_by_name(elf, &ehdr, &shdr_plt, ".plt", NULL) == NULL)
- goto out_elf_end;
-
- /*
- * Fetch the relocation section to find the idxes to the GOT
- * and the symbols in the .dynsym they refer to.
- */
- reldata = elf_getdata(scn_plt_rel, NULL);
- if (reldata == NULL)
- goto out_elf_end;
-
- syms = elf_getdata(scn_dynsym, NULL);
- if (syms == NULL)
- goto out_elf_end;
-
- scn_symstrs = elf_getscn(elf, shdr_dynsym.sh_link);
- if (scn_symstrs == NULL)
- goto out_elf_end;
-
- symstrs = elf_getdata(scn_symstrs, NULL);
- if (symstrs == NULL)
- goto out_elf_end;
-
- nr_rel_entries = shdr_rel_plt.sh_size / shdr_rel_plt.sh_entsize;
- plt_offset = shdr_plt.sh_offset;
-
- if (shdr_rel_plt.sh_type == SHT_RELA) {
- GElf_Rela pos_mem, *pos;
-
- elf_section__for_each_rela(reldata, pos, pos_mem, idx,
- nr_rel_entries) {
- symidx = GELF_R_SYM(pos->r_info);
- plt_offset += shdr_plt.sh_entsize;
- gelf_getsym(syms, symidx, &sym);
- snprintf(sympltname, sizeof(sympltname),
- "%s@plt", elf_sym__name(&sym, symstrs));
-
- f = symbol__new(plt_offset, shdr_plt.sh_entsize,
- STB_GLOBAL, sympltname);
- if (!f)
- goto out_elf_end;
-
- if (filter && filter(map, f))
- symbol__delete(f);
- else {
- symbols__insert(&dso->symbols[map->type], f);
- ++nr;
- }
- }
- } else if (shdr_rel_plt.sh_type == SHT_REL) {
- GElf_Rel pos_mem, *pos;
- elf_section__for_each_rel(reldata, pos, pos_mem, idx,
- nr_rel_entries) {
- symidx = GELF_R_SYM(pos->r_info);
- plt_offset += shdr_plt.sh_entsize;
- gelf_getsym(syms, symidx, &sym);
- snprintf(sympltname, sizeof(sympltname),
- "%s@plt", elf_sym__name(&sym, symstrs));
-
- f = symbol__new(plt_offset, shdr_plt.sh_entsize,
- STB_GLOBAL, sympltname);
- if (!f)
- goto out_elf_end;
-
- if (filter && filter(map, f))
- symbol__delete(f);
- else {
- symbols__insert(&dso->symbols[map->type], f);
- ++nr;
- }
- }
- }
-
- err = 0;
-out_elf_end:
- elf_end(elf);
-out_close:
- close(fd);
-
- if (err == 0)
- return nr;
-out:
- pr_debug("%s: problems reading %s PLT info.\n",
- __func__, dso->long_name);
- return 0;
-}
-
-static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
-{
- switch (type) {
- case MAP__FUNCTION:
- return elf_sym__is_function(sym);
- case MAP__VARIABLE:
- return elf_sym__is_object(sym);
- default:
- return false;
- }
-}
-
-static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
- enum map_type type)
-{
- switch (type) {
- case MAP__FUNCTION:
- return elf_sec__is_text(shdr, secstrs);
- case MAP__VARIABLE:
- return elf_sec__is_data(shdr, secstrs);
- default:
- return false;
- }
-}
-
-static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
-{
- Elf_Scn *sec = NULL;
- GElf_Shdr shdr;
- size_t cnt = 1;
-
- while ((sec = elf_nextscn(elf, sec)) != NULL) {
- gelf_getshdr(sec, &shdr);
-
- if ((addr >= shdr.sh_addr) &&
- (addr < (shdr.sh_addr + shdr.sh_size)))
- return cnt;
-
- ++cnt;
- }
-
- return -1;
-}
-
-static int dso__swap_init(struct dso *dso, unsigned char eidata)
-{
- static unsigned int const endian = 1;
-
- dso->needs_swap = DSO_SWAP__NO;
-
- switch (eidata) {
- case ELFDATA2LSB:
- /* We are big endian, DSO is little endian. */
- if (*(unsigned char const *)&endian != 1)
- dso->needs_swap = DSO_SWAP__YES;
- break;
-
- case ELFDATA2MSB:
- /* We are little endian, DSO is big endian. */
- if (*(unsigned char const *)&endian != 0)
- dso->needs_swap = DSO_SWAP__YES;
- break;
-
- default:
- pr_err("unrecognized DSO data encoding %d\n", eidata);
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
- int fd, symbol_filter_t filter, int kmodule,
- int want_symtab)
-{
- struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
- struct map *curr_map = map;
- struct dso *curr_dso = dso;
- Elf_Data *symstrs, *secstrs;
- uint32_t nr_syms;
- int err = -1;
- uint32_t idx;
- GElf_Ehdr ehdr;
- GElf_Shdr shdr, opdshdr;
- Elf_Data *syms, *opddata = NULL;
- GElf_Sym sym;
- Elf_Scn *sec, *sec_strndx, *opdsec;
- Elf *elf;
- int nr = 0;
- size_t opdidx = 0;
-
- elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
- if (elf == NULL) {
- pr_debug("%s: cannot read %s ELF file.\n", __func__, name);
- goto out_close;
- }
-
- if (gelf_getehdr(elf, &ehdr) == NULL) {
- pr_debug("%s: cannot get elf header.\n", __func__);
- goto out_elf_end;
- }
-
- if (dso__swap_init(dso, ehdr.e_ident[EI_DATA]))
- goto out_elf_end;
-
- /* Always reject images with a mismatched build-id: */
- if (dso->has_build_id) {
- u8 build_id[BUILD_ID_SIZE];
-
- if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0)
- goto out_elf_end;
-
- if (!dso__build_id_equal(dso, build_id))
- goto out_elf_end;
- }
-
- sec = elf_section_by_name(elf, &ehdr, &shdr, ".symtab", NULL);
- if (sec == NULL) {
- if (want_symtab)
- goto out_elf_end;
-
- sec = elf_section_by_name(elf, &ehdr, &shdr, ".dynsym", NULL);
- if (sec == NULL)
- goto out_elf_end;
- }
-
- opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx);
- if (opdshdr.sh_type != SHT_PROGBITS)
- opdsec = NULL;
- if (opdsec)
- opddata = elf_rawdata(opdsec, NULL);
-
- syms = elf_getdata(sec, NULL);
- if (syms == NULL)
- goto out_elf_end;
-
- sec = elf_getscn(elf, shdr.sh_link);
- if (sec == NULL)
- goto out_elf_end;
-
- symstrs = elf_getdata(sec, NULL);
- if (symstrs == NULL)
- goto out_elf_end;
-
- sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
- if (sec_strndx == NULL)
- goto out_elf_end;
-
- secstrs = elf_getdata(sec_strndx, NULL);
- if (secstrs == NULL)
- goto out_elf_end;
-
- nr_syms = shdr.sh_size / shdr.sh_entsize;
-
- memset(&sym, 0, sizeof(sym));
- if (dso->kernel == DSO_TYPE_USER) {
- dso->adjust_symbols = (ehdr.e_type == ET_EXEC ||
- elf_section_by_name(elf, &ehdr, &shdr,
- ".gnu.prelink_undo",
- NULL) != NULL);
- } else {
- dso->adjust_symbols = 0;
- }
- elf_symtab__for_each_symbol(syms, nr_syms, idx, sym) {
- struct symbol *f;
- const char *elf_name = elf_sym__name(&sym, symstrs);
- char *demangled = NULL;
- int is_label = elf_sym__is_label(&sym);
- const char *section_name;
-
- if (kmap && kmap->ref_reloc_sym && kmap->ref_reloc_sym->name &&
- strcmp(elf_name, kmap->ref_reloc_sym->name) == 0)
- kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
-
- if (!is_label && !elf_sym__is_a(&sym, map->type))
- continue;
-
- /* Reject ARM ELF "mapping symbols": these aren't unique and
- * don't identify functions, so will confuse the profile
- * output: */
- if (ehdr.e_machine == EM_ARM) {
- if (!strcmp(elf_name, "$a") ||
- !strcmp(elf_name, "$d") ||
- !strcmp(elf_name, "$t"))
- continue;
- }
-
- if (opdsec && sym.st_shndx == opdidx) {
- u32 offset = sym.st_value - opdshdr.sh_addr;
- u64 *opd = opddata->d_buf + offset;
- sym.st_value = DSO__SWAP(dso, u64, *opd);
- sym.st_shndx = elf_addr_to_index(elf, sym.st_value);
- }
-
- sec = elf_getscn(elf, sym.st_shndx);
- if (!sec)
- goto out_elf_end;
-
- gelf_getshdr(sec, &shdr);
-
- if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
- continue;
-
- section_name = elf_sec__name(&shdr, secstrs);
-
- /* On ARM, symbols for thumb functions have 1 added to
- * the symbol address as a flag - remove it */
- if ((ehdr.e_machine == EM_ARM) &&
- (map->type == MAP__FUNCTION) &&
- (sym.st_value & 1))
- --sym.st_value;
-
- if (dso->kernel != DSO_TYPE_USER || kmodule) {
- char dso_name[PATH_MAX];
-
- if (strcmp(section_name,
- (curr_dso->short_name +
- dso->short_name_len)) == 0)
- goto new_symbol;
-
- if (strcmp(section_name, ".text") == 0) {
- curr_map = map;
- curr_dso = dso;
- goto new_symbol;
- }
-
- snprintf(dso_name, sizeof(dso_name),
- "%s%s", dso->short_name, section_name);
-
- curr_map = map_groups__find_by_name(kmap->kmaps, map->type, dso_name);
- if (curr_map == NULL) {
- u64 start = sym.st_value;
-
- if (kmodule)
- start += map->start + shdr.sh_offset;
-
- curr_dso = dso__new(dso_name);
- if (curr_dso == NULL)
- goto out_elf_end;
- curr_dso->kernel = dso->kernel;
- curr_dso->long_name = dso->long_name;
- curr_dso->long_name_len = dso->long_name_len;
- curr_map = map__new2(start, curr_dso,
- map->type);
- if (curr_map == NULL) {
- dso__delete(curr_dso);
- goto out_elf_end;
- }
- curr_map->map_ip = identity__map_ip;
- curr_map->unmap_ip = identity__map_ip;
- curr_dso->symtab_type = dso->symtab_type;
- map_groups__insert(kmap->kmaps, curr_map);
- dsos__add(&dso->node, curr_dso);
- dso__set_loaded(curr_dso, map->type);
- } else
- curr_dso = curr_map->dso;
-
- goto new_symbol;
- }
-
- if (curr_dso->adjust_symbols) {
- pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
- "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
- (u64)sym.st_value, (u64)shdr.sh_addr,
- (u64)shdr.sh_offset);
- sym.st_value -= shdr.sh_addr - shdr.sh_offset;
- }
- /*
- * We need to figure out if the object was created from C++ sources
- * DWARF DW_compile_unit has this, but we don't always have access
- * to it...
- */
- demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI);
- if (demangled != NULL)
- elf_name = demangled;
-new_symbol:
- f = symbol__new(sym.st_value, sym.st_size,
- GELF_ST_BIND(sym.st_info), elf_name);
- free(demangled);
- if (!f)
- goto out_elf_end;
-
- if (filter && filter(curr_map, f))
- symbol__delete(f);
- else {
- symbols__insert(&curr_dso->symbols[curr_map->type], f);
- nr++;
- }
- }
-
- /*
- * For misannotated, zeroed, ASM function sizes.
- */
- if (nr > 0) {
- symbols__fixup_duplicate(&dso->symbols[map->type]);
- symbols__fixup_end(&dso->symbols[map->type]);
- if (kmap) {
- /*
- * We need to fixup this here too because we create new
- * maps here, for things like vsyscall sections.
- */
- __map_groups__fixup_end(kmap->kmaps, map->type);
- }
- }
- err = nr;
-out_elf_end:
- elf_end(elf);
-out_close:
- return err;
-}
-
-static bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
+bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
{
return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
}
return have_build_id;
}
-/*
- * Align offset to 4 bytes as needed for note name and descriptor data.
- */
-#define NOTE_ALIGN(n) (((n) + 3) & -4U)
-
-static int elf_read_build_id(Elf *elf, void *bf, size_t size)
-{
- int err = -1;
- GElf_Ehdr ehdr;
- GElf_Shdr shdr;
- Elf_Data *data;
- Elf_Scn *sec;
- Elf_Kind ek;
- void *ptr;
-
- if (size < BUILD_ID_SIZE)
- goto out;
-
- ek = elf_kind(elf);
- if (ek != ELF_K_ELF)
- goto out;
-
- if (gelf_getehdr(elf, &ehdr) == NULL) {
- pr_err("%s: cannot get elf header.\n", __func__);
- goto out;
- }
-
- /*
- * Check following sections for notes:
- * '.note.gnu.build-id'
- * '.notes'
- * '.note' (VDSO specific)
- */
- do {
- sec = elf_section_by_name(elf, &ehdr, &shdr,
- ".note.gnu.build-id", NULL);
- if (sec)
- break;
-
- sec = elf_section_by_name(elf, &ehdr, &shdr,
- ".notes", NULL);
- if (sec)
- break;
-
- sec = elf_section_by_name(elf, &ehdr, &shdr,
- ".note", NULL);
- if (sec)
- break;
-
- return err;
-
- } while (0);
-
- data = elf_getdata(sec, NULL);
- if (data == NULL)
- goto out;
-
- ptr = data->d_buf;
- while (ptr < (data->d_buf + data->d_size)) {
- GElf_Nhdr *nhdr = ptr;
- size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
- descsz = NOTE_ALIGN(nhdr->n_descsz);
- const char *name;
-
- ptr += sizeof(*nhdr);
- name = ptr;
- ptr += namesz;
- if (nhdr->n_type == NT_GNU_BUILD_ID &&
- nhdr->n_namesz == sizeof("GNU")) {
- if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
- size_t sz = min(size, descsz);
- memcpy(bf, ptr, sz);
- memset(bf + sz, 0, size - sz);
- err = descsz;
- break;
- }
- }
- ptr += descsz;
- }
-
-out:
- return err;
-}
-
-int filename__read_build_id(const char *filename, void *bf, size_t size)
-{
- int fd, err = -1;
- Elf *elf;
-
- if (size < BUILD_ID_SIZE)
- goto out;
-
- fd = open(filename, O_RDONLY);
- if (fd < 0)
- goto out;
-
- elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
- if (elf == NULL) {
- pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
- goto out_close;
- }
-
- err = elf_read_build_id(elf, bf, size);
-
- elf_end(elf);
-out_close:
- close(fd);
-out:
- return err;
-}
-
-int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
-{
- int fd, err = -1;
-
- if (size < BUILD_ID_SIZE)
- goto out;
-
- fd = open(filename, O_RDONLY);
- if (fd < 0)
- goto out;
-
- while (1) {
- char bf[BUFSIZ];
- GElf_Nhdr nhdr;
- size_t namesz, descsz;
-
- if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
- break;
-
- namesz = NOTE_ALIGN(nhdr.n_namesz);
- descsz = NOTE_ALIGN(nhdr.n_descsz);
- if (nhdr.n_type == NT_GNU_BUILD_ID &&
- nhdr.n_namesz == sizeof("GNU")) {
- if (read(fd, bf, namesz) != (ssize_t)namesz)
- break;
- if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
- size_t sz = min(descsz, size);
- if (read(fd, build_id, sz) == (ssize_t)sz) {
- memset(build_id + sz, 0, size - sz);
- err = 0;
- break;
- }
- } else if (read(fd, bf, descsz) != (ssize_t)descsz)
- break;
- } else {
- int n = namesz + descsz;
- if (read(fd, bf, n) != n)
- break;
- }
- }
- close(fd);
-out:
- return err;
-}
-
-static int filename__read_debuglink(const char *filename,
- char *debuglink, size_t size)
-{
- int fd, err = -1;
- Elf *elf;
- GElf_Ehdr ehdr;
- GElf_Shdr shdr;
- Elf_Data *data;
- Elf_Scn *sec;
- Elf_Kind ek;
-
- fd = open(filename, O_RDONLY);
- if (fd < 0)
- goto out;
-
- elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
- if (elf == NULL) {
- pr_debug2("%s: cannot read %s ELF file.\n", __func__, filename);
- goto out_close;
- }
-
- ek = elf_kind(elf);
- if (ek != ELF_K_ELF)
- goto out_close;
-
- if (gelf_getehdr(elf, &ehdr) == NULL) {
- pr_err("%s: cannot get elf header.\n", __func__);
- goto out_close;
- }
-
- sec = elf_section_by_name(elf, &ehdr, &shdr,
- ".gnu_debuglink", NULL);
- if (sec == NULL)
- goto out_close;
-
- data = elf_getdata(sec, NULL);
- if (data == NULL)
- goto out_close;
-
- /* the start of this section is a zero-terminated string */
- strncpy(debuglink, data->d_buf, size);
-
- elf_end(elf);
-
-out_close:
- close(fd);
-out:
- return err;
-}
-
char dso__symtab_origin(const struct dso *dso)
{
static const char origin[] = {
[DSO_BINARY_TYPE__KALLSYMS] = 'k',
+ [DSO_BINARY_TYPE__VMLINUX] = 'v',
[DSO_BINARY_TYPE__JAVA_JIT] = 'j',
[DSO_BINARY_TYPE__DEBUGLINK] = 'l',
[DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B',
[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K',
[DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g',
[DSO_BINARY_TYPE__GUEST_KMODULE] = 'G',
+ [DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V',
};
if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
default:
case DSO_BINARY_TYPE__KALLSYMS:
+ case DSO_BINARY_TYPE__VMLINUX:
case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+ case DSO_BINARY_TYPE__GUEST_VMLINUX:
case DSO_BINARY_TYPE__JAVA_JIT:
case DSO_BINARY_TYPE__NOT_FOUND:
ret = -1;
{
char *name;
int ret = -1;
- int fd;
u_int i;
struct machine *machine;
char *root_dir = (char *) "";
- int want_symtab;
+ int ss_pos = 0;
+ struct symsrc ss_[2];
+ struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
dso__set_loaded(dso, map->type);
root_dir = machine->root_dir;
/* Iterate over candidate debug images.
- * On the first pass, only load images if they have a full symtab.
- * Failing that, do a second pass where we accept .dynsym also
+ * Keep track of "interesting" ones (those which have a symtab, dynsym,
+ * and/or opd section) for processing.
*/
- want_symtab = 1;
-restart:
for (i = 0; i < DSO_BINARY_TYPE__SYMTAB_CNT; i++) {
+ struct symsrc *ss = &ss_[ss_pos];
+ bool next_slot = false;
- dso->symtab_type = binary_type_symtab[i];
+ enum dso_binary_type symtab_type = binary_type_symtab[i];
- if (dso__binary_type_file(dso, dso->symtab_type,
+ if (dso__binary_type_file(dso, symtab_type,
root_dir, name, PATH_MAX))
continue;
/* Name is now the name of the next image to try */
- fd = open(name, O_RDONLY);
- if (fd < 0)
+ if (symsrc__init(ss, dso, name, symtab_type) < 0)
continue;
- ret = dso__load_sym(dso, map, name, fd, filter, 0,
- want_symtab);
- close(fd);
+ if (!syms_ss && symsrc__has_symtab(ss)) {
+ syms_ss = ss;
+ next_slot = true;
+ }
- /*
- * Some people seem to have debuginfo files _WITHOUT_ debug
- * info!?!?
- */
- if (!ret)
- continue;
+ if (!runtime_ss && symsrc__possibly_runtime(ss)) {
+ runtime_ss = ss;
+ next_slot = true;
+ }
- if (ret > 0) {
- int nr_plt;
+ if (next_slot) {
+ ss_pos++;
- nr_plt = dso__synthesize_plt_symbols(dso, name, map, filter);
- if (nr_plt > 0)
- ret += nr_plt;
- break;
+ if (syms_ss && runtime_ss)
+ break;
}
+
}
- /*
- * If we wanted a full symtab but no image had one,
- * relax our requirements and repeat the search.
- */
- if (ret <= 0 && want_symtab) {
- want_symtab = 0;
- goto restart;
+ if (!runtime_ss && !syms_ss)
+ goto out_free;
+
+ if (runtime_ss && !syms_ss) {
+ syms_ss = runtime_ss;
+ }
+
+ /* We'll have to hope for the best */
+ if (!runtime_ss && syms_ss)
+ runtime_ss = syms_ss;
+
+ if (syms_ss)
+ ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, 0);
+ else
+ ret = -1;
+
+ if (ret > 0) {
+ int nr_plt;
+
+ nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map, filter);
+ if (nr_plt > 0)
+ ret += nr_plt;
}
+ for (; ss_pos > 0; ss_pos--)
+ symsrc__destroy(&ss_[ss_pos - 1]);
+out_free:
free(name);
if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
return 0;
return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
}
-/*
- * Constructor variant for modules (where we know from /proc/modules where
- * they are loaded) and for vmlinux, where only after we load all the
- * symbols we'll know where it starts and ends.
- */
-static struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
-{
- struct map *map = calloc(1, (sizeof(*map) +
- (dso->kernel ? sizeof(struct kmap) : 0)));
- if (map != NULL) {
- /*
- * ->end will be filled after we load all the symbols
- */
- map__init(map, type, start, 0, 0, dso);
- }
-
- return map;
-}
-
struct map *machine__new_module(struct machine *machine, u64 start,
const char *filename)
{
int dso__load_vmlinux(struct dso *dso, struct map *map,
const char *vmlinux, symbol_filter_t filter)
{
- int err = -1, fd;
+ int err = -1;
+ struct symsrc ss;
char symfs_vmlinux[PATH_MAX];
+ enum dso_binary_type symtab_type;
snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
symbol_conf.symfs, vmlinux);
- fd = open(symfs_vmlinux, O_RDONLY);
- if (fd < 0)
+
+ if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+ symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
+ else
+ symtab_type = DSO_BINARY_TYPE__VMLINUX;
+
+ if (symsrc__init(&ss, dso, symfs_vmlinux, symtab_type))
return -1;
- dso__set_long_name(dso, (char *)vmlinux);
- dso__set_loaded(dso, map->type);
- err = dso__load_sym(dso, map, symfs_vmlinux, fd, filter, 0, 0);
- close(fd);
+ err = dso__load_sym(dso, map, &ss, &ss, filter, 0);
+ symsrc__destroy(&ss);
- if (err > 0)
+ if (err > 0) {
+ dso__set_long_name(dso, (char *)vmlinux);
+ dso__set_loaded(dso, map->type);
pr_debug("Using %s for symbols\n", symfs_vmlinux);
+ }
return err;
}
filename = dso__build_id_filename(dso, NULL, 0);
if (filename != NULL) {
err = dso__load_vmlinux(dso, map, filename, filter);
- if (err > 0) {
- dso__set_long_name(dso, filename);
+ if (err > 0)
goto out;
- }
free(filename);
}
free(kallsyms_allocated_filename);
if (err > 0) {
+ dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
out_fixup:
- if (kallsyms_filename != NULL)
- dso__set_long_name(dso, strdup("[kernel.kallsyms]"));
map__fixup_start(map);
map__fixup_end(map);
}
return err;
}
-static void dsos__add(struct list_head *head, struct dso *dso)
+void dsos__add(struct list_head *head, struct dso *dso)
{
list_add_tail(&dso->node, head);
}
};
static int symbol__in_kernel(void *arg, const char *name,
- char type __used, u64 start, u64 end __used)
+ char type __used, u64 start)
{
struct process_args *args = arg;
symbol_conf.priv_size = ALIGN(symbol_conf.priv_size, sizeof(u64));
- elf_version(EV_CURRENT);
+ symbol__elf_init();
+
if (symbol_conf.sort_by_name)
symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
sizeof(struct symbol));
#include <stdio.h>
#include <byteswap.h>
+#ifndef NO_LIBELF_SUPPORT
+#include <libelf.h>
+#include <gelf.h>
+#include <elf.h>
+#endif
+
#ifdef HAVE_CPLUS_DEMANGLE
extern char *cplus_demangle(const char *, int);
enum dso_binary_type {
DSO_BINARY_TYPE__KALLSYMS = 0,
DSO_BINARY_TYPE__GUEST_KALLSYMS,
+ DSO_BINARY_TYPE__VMLINUX,
+ DSO_BINARY_TYPE__GUEST_VMLINUX,
DSO_BINARY_TYPE__JAVA_JIT,
DSO_BINARY_TYPE__DEBUGLINK,
DSO_BINARY_TYPE__BUILD_ID_CACHE,
char name[0];
};
+struct symsrc {
+ char *name;
+ int fd;
+ enum dso_binary_type type;
+
+#ifndef NO_LIBELF_SUPPORT
+ Elf *elf;
+ GElf_Ehdr ehdr;
+
+ Elf_Scn *opdsec;
+ size_t opdidx;
+ GElf_Shdr opdshdr;
+
+ Elf_Scn *symtab;
+ GElf_Shdr symshdr;
+
+ Elf_Scn *dynsym;
+ size_t dynsym_idx;
+ GElf_Shdr dynshdr;
+
+ bool adjust_symbols;
+#endif
+};
+
+void symsrc__destroy(struct symsrc *ss);
+int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
+ enum dso_binary_type type);
+bool symsrc__has_symtab(struct symsrc *ss);
+bool symsrc__possibly_runtime(struct symsrc *ss);
+
#define DSO__SWAP(dso, type, val) \
({ \
type ____r = val; \
void dso__sort_by_name(struct dso *dso, enum map_type type);
+void dsos__add(struct list_head *head, struct dso *dso);
struct dso *__dsos__findnew(struct list_head *head, const char *name);
int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
char dso__symtab_origin(const struct dso *dso);
void dso__set_long_name(struct dso *dso, char *name);
void dso__set_build_id(struct dso *dso, void *build_id);
+bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
void dso__read_running_kernel_build_id(struct dso *dso,
struct machine *machine);
struct map *dso__new_map(const char *name);
int build_id__sprintf(const u8 *build_id, int len, char *bf);
int kallsyms__parse(const char *filename, void *arg,
int (*process_symbol)(void *arg, const char *name,
- char type, u64 start, u64 end));
+ char type, u64 start));
+int filename__read_debuglink(const char *filename, char *debuglink,
+ size_t size);
void machine__destroy_kernel_maps(struct machine *machine);
int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
int symbol__init(void);
void symbol__exit(void);
+void symbol__elf_init(void);
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
size_t symbol__fprintf_symname_offs(const struct symbol *sym,
const struct addr_location *al, FILE *fp);
size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
struct machine *machine, u64 addr,
u8 *data, ssize_t size);
int dso__test_data(void);
+int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
+ struct symsrc *runtime_ss, symbol_filter_t filter,
+ int kmodule);
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
+ struct map *map, symbol_filter_t filter);
+
+void symbols__insert(struct rb_root *symbols, struct symbol *sym);
+void symbols__fixup_duplicate(struct rb_root *symbols);
+void symbols__fixup_end(struct rb_root *symbols);
+void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
+
#endif /* __PERF_SYMBOL */
}
if (top->evlist->nr_entries == 1) {
- struct perf_evsel *first;
- first = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+ struct perf_evsel *first = perf_evlist__first(top->evlist);
ret += SNPRINTF(bf + ret, size - ret, "%" PRIu64 "%s ",
(uint64_t)first->attr.sample_period,
top->freq ? "Hz" : "");
return pevent_data_pid(pevent, &record);
}
-unsigned long long read_size(struct pevent *pevent, void *ptr, int size)
+unsigned long long read_size(struct event_format *event, void *ptr, int size)
{
- return pevent_read_number(pevent, ptr, size);
+ return pevent_read_number(event->pevent, ptr, size);
}
-void print_trace_event(struct pevent *pevent, int cpu, void *data, int size)
+void event_format__print(struct event_format *event,
+ int cpu, void *data, int size)
{
- struct event_format *event;
struct pevent_record record;
struct trace_seq s;
- int type;
-
- type = trace_parse_common_type(pevent, data);
-
- event = pevent_find_event(pevent, type);
- if (!event) {
- warning("ug! no event found for type %d", type);
- return;
- }
memset(&record, 0, sizeof(record));
record.cpu = cpu;
trace_seq_do_printf(&s);
}
+void print_trace_event(struct pevent *pevent, int cpu, void *data, int size)
+{
+ int type = trace_parse_common_type(pevent, data);
+ struct event_format *event = pevent_find_event(pevent, type);
+
+ if (!event) {
+ warning("ug! no event found for type %d", type);
+ return;
+ }
+
+ event_format__print(event, cpu, data, size);
+}
+
void print_event(struct pevent *pevent, int cpu, void *data, int size,
unsigned long long nsecs, char *comm)
{
{
static int idx;
- if (!pevent->events)
+ if (!pevent || !pevent->events)
return NULL;
if (!event) {
}
static void process_event_unsupported(union perf_event *event __unused,
- struct pevent *pevent __unused,
struct perf_sample *sample __unused,
struct perf_evsel *evsel __unused,
struct machine *machine __unused,
- struct thread *thread __unused)
+ struct addr_location *al __unused)
{
}
struct perf_sample;
union perf_event;
struct perf_tool;
-struct thread;
extern int header_page_size_size;
extern int header_page_ts_size;
struct pevent *read_trace_init(int file_bigendian, int host_bigendian);
void print_trace_event(struct pevent *pevent, int cpu, void *data, int size);
+void event_format__print(struct event_format *event,
+ int cpu, void *data, int size);
void print_event(struct pevent *pevent, int cpu, void *data, int size,
unsigned long long nsecs, char *comm);
struct event_format *trace_find_next_event(struct pevent *pevent,
struct event_format *event);
-unsigned long long read_size(struct pevent *pevent, void *ptr, int size);
+unsigned long long read_size(struct event_format *event, void *ptr, int size);
unsigned long long eval_flag(const char *flag);
struct pevent_record *trace_read_data(struct pevent *pevent, int cpu);
void tracing_data_put(struct tracing_data *tdata);
+struct addr_location;
+
+struct perf_session;
+
struct scripting_ops {
const char *name;
int (*start_script) (const char *script, int argc, const char **argv);
int (*stop_script) (void);
void (*process_event) (union perf_event *event,
- struct pevent *pevent,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine,
- struct thread *thread);
+ struct addr_location *al);
int (*generate_script) (struct pevent *pevent, const char *outfile);
};
--- /dev/null
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ * Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "util.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+ unw_word_t ip,
+ unw_dyn_info_t *di,
+ unw_proc_info_t *pi,
+ int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+#define DW_EH_PE_FORMAT_MASK 0x0f /* format of the encoded value */
+#define DW_EH_PE_APPL_MASK 0x70 /* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit 0xff
+#define DW_EH_PE_ptr 0x00 /* pointer-sized unsigned value */
+#define DW_EH_PE_udata4 0x03 /* unsigned 32-bit value */
+#define DW_EH_PE_udata8 0x04 /* unsigned 64-bit value */
+#define DW_EH_PE_sdata4 0x0b /* signed 32-bit value */
+#define DW_EH_PE_sdata8 0x0c /* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr 0x00 /* absolute value */
+#define DW_EH_PE_pcrel 0x10 /* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel 0x40 /* start-of-procedure-relative */
+#define DW_EH_PE_aligned 0x50 /* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect 0x80
+ * #define DW_EH_PE_uleb128 0x01
+ * #define DW_EH_PE_udata2 0x02
+ * #define DW_EH_PE_sleb128 0x09
+ * #define DW_EH_PE_sdata2 0x0a
+ * #define DW_EH_PE_textrel 0x20
+ * #define DW_EH_PE_datarel 0x30
+ */
+
+struct unwind_info {
+ struct perf_sample *sample;
+ struct machine *machine;
+ struct thread *thread;
+ u64 sample_uregs;
+};
+
+#define dw_read(ptr, type, end) ({ \
+ type *__p = (type *) ptr; \
+ type __v; \
+ if ((__p + 1) > (type *) end) \
+ return -EINVAL; \
+ __v = *__p++; \
+ ptr = (typeof(ptr)) __p; \
+ __v; \
+ })
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+ u8 encoding)
+{
+ u8 *cur = *p;
+ *val = 0;
+
+ switch (encoding) {
+ case DW_EH_PE_omit:
+ *val = 0;
+ goto out;
+ case DW_EH_PE_ptr:
+ *val = dw_read(cur, unsigned long, end);
+ goto out;
+ default:
+ break;
+ }
+
+ switch (encoding & DW_EH_PE_APPL_MASK) {
+ case DW_EH_PE_absptr:
+ break;
+ case DW_EH_PE_pcrel:
+ *val = (unsigned long) cur;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if ((encoding & 0x07) == 0x00)
+ encoding |= DW_EH_PE_udata4;
+
+ switch (encoding & DW_EH_PE_FORMAT_MASK) {
+ case DW_EH_PE_sdata4:
+ *val += dw_read(cur, s32, end);
+ break;
+ case DW_EH_PE_udata4:
+ *val += dw_read(cur, u32, end);
+ break;
+ case DW_EH_PE_sdata8:
+ *val += dw_read(cur, s64, end);
+ break;
+ case DW_EH_PE_udata8:
+ *val += dw_read(cur, u64, end);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ out:
+ *p = cur;
+ return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({ \
+ u64 __v; \
+ if (__dw_read_encoded_value(&ptr, end, &__v, enc)) { \
+ return -EINVAL; \
+ } \
+ __v; \
+ })
+
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+ GElf_Shdr *shp, const char *name)
+{
+ Elf_Scn *sec = NULL;
+
+ while ((sec = elf_nextscn(elf, sec)) != NULL) {
+ char *str;
+
+ gelf_getshdr(sec, shp);
+ str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+ if (!strcmp(name, str))
+ break;
+ }
+
+ return sec;
+}
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+ Elf *elf;
+ GElf_Ehdr ehdr;
+ GElf_Shdr shdr;
+ u64 offset = 0;
+
+ elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+ if (elf == NULL)
+ return 0;
+
+ do {
+ if (gelf_getehdr(elf, &ehdr) == NULL)
+ break;
+
+ if (!elf_section_by_name(elf, &ehdr, &shdr, name))
+ break;
+
+ offset = shdr.sh_offset;
+ } while (0);
+
+ elf_end(elf);
+ return offset;
+}
+
+struct table_entry {
+ u32 start_ip_offset;
+ u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+ unsigned char version;
+ unsigned char eh_frame_ptr_enc;
+ unsigned char fde_count_enc;
+ unsigned char table_enc;
+
+ /*
+ * The rest of the header is variable-length and consists of the
+ * following members:
+ *
+ * encoded_t eh_frame_ptr;
+ * encoded_t fde_count;
+ */
+
+ /* A single encoded pointer should not be more than 8 bytes. */
+ u64 enc[2];
+
+ /*
+ * struct {
+ * encoded_t start_ip;
+ * encoded_t fde_addr;
+ * } binary_search_table[fde_count];
+ */
+ char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+ u64 offset, u64 *table_data, u64 *segbase,
+ u64 *fde_count)
+{
+ struct eh_frame_hdr hdr;
+ u8 *enc = (u8 *) &hdr.enc;
+ u8 *end = (u8 *) &hdr.data;
+ ssize_t r;
+
+ r = dso__data_read_offset(dso, machine, offset,
+ (u8 *) &hdr, sizeof(hdr));
+ if (r != sizeof(hdr))
+ return -EINVAL;
+
+ /* We dont need eh_frame_ptr, just skip it. */
+ dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+ *fde_count = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+ *segbase = offset;
+ *table_data = (enc - (u8 *) &hdr) + offset;
+ return 0;
+}
+
+static int read_unwind_spec(struct dso *dso, struct machine *machine,
+ u64 *table_data, u64 *segbase, u64 *fde_count)
+{
+ int ret = -EINVAL, fd;
+ u64 offset;
+
+ fd = dso__data_fd(dso, machine);
+ if (fd < 0)
+ return -EINVAL;
+
+ offset = elf_section_offset(fd, ".eh_frame_hdr");
+ close(fd);
+
+ if (offset)
+ ret = unwind_spec_ehframe(dso, machine, offset,
+ table_data, segbase,
+ fde_count);
+
+ /* TODO .debug_frame check if eh_frame_hdr fails */
+ return ret;
+}
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+ struct addr_location al;
+
+ thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al);
+ return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+ int need_unwind_info, void *arg)
+{
+ struct unwind_info *ui = arg;
+ struct map *map;
+ unw_dyn_info_t di;
+ u64 table_data, segbase, fde_count;
+
+ map = find_map(ip, ui);
+ if (!map || !map->dso)
+ return -EINVAL;
+
+ pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+ if (read_unwind_spec(map->dso, ui->machine,
+ &table_data, &segbase, &fde_count))
+ return -EINVAL;
+
+ memset(&di, 0, sizeof(di));
+ di.format = UNW_INFO_FORMAT_REMOTE_TABLE;
+ di.start_ip = map->start;
+ di.end_ip = map->end;
+ di.u.rti.segbase = map->start + segbase;
+ di.u.rti.table_data = map->start + table_data;
+ di.u.rti.table_len = fde_count * sizeof(struct table_entry)
+ / sizeof(unw_word_t);
+ return dwarf_search_unwind_table(as, ip, &di, pi,
+ need_unwind_info, arg);
+}
+
+static int access_fpreg(unw_addr_space_t __used as, unw_regnum_t __used num,
+ unw_fpreg_t __used *val, int __used __write,
+ void __used *arg)
+{
+ pr_err("unwind: access_fpreg unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __used as,
+ unw_word_t __used *dil_addr,
+ void __used *arg)
+{
+ return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __used as, unw_cursor_t __used *cu,
+ void __used *arg)
+{
+ pr_err("unwind: resume unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __used as, unw_word_t __used addr,
+ char __used *bufp, size_t __used buf_len,
+ unw_word_t __used *offp, void __used *arg)
+{
+ pr_err("unwind: get_proc_name unsupported\n");
+ return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+ unw_word_t *data)
+{
+ struct addr_location al;
+ ssize_t size;
+
+ thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, addr, &al);
+ if (!al.map) {
+ pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+ return -1;
+ }
+
+ if (!al.map->dso)
+ return -1;
+
+ size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+ addr, (u8 *) data, sizeof(*data));
+
+ return !(size == sizeof(*data));
+}
+
+static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
+ u64 sample_regs)
+{
+ int i, idx = 0;
+
+ if (!(sample_regs & (1 << id)))
+ return -EINVAL;
+
+ for (i = 0; i < id; i++) {
+ if (sample_regs & (1 << i))
+ idx++;
+ }
+
+ *valp = regs->regs[idx];
+ return 0;
+}
+
+static int access_mem(unw_addr_space_t __used as,
+ unw_word_t addr, unw_word_t *valp,
+ int __write, void *arg)
+{
+ struct unwind_info *ui = arg;
+ struct stack_dump *stack = &ui->sample->user_stack;
+ unw_word_t start, end;
+ int offset;
+ int ret;
+
+ /* Don't support write, probably not needed. */
+ if (__write || !stack || !ui->sample->user_regs.regs) {
+ *valp = 0;
+ return 0;
+ }
+
+ ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
+ ui->sample_uregs);
+ if (ret)
+ return ret;
+
+ end = start + stack->size;
+
+ /* Check overflow. */
+ if (addr + sizeof(unw_word_t) < addr)
+ return -EINVAL;
+
+ if (addr < start || addr + sizeof(unw_word_t) >= end) {
+ ret = access_dso_mem(ui, addr, valp);
+ if (ret) {
+ pr_debug("unwind: access_mem %p not inside range %p-%p\n",
+ (void *)addr, (void *)start, (void *)end);
+ *valp = 0;
+ return ret;
+ }
+ return 0;
+ }
+
+ offset = addr - start;
+ *valp = *(unw_word_t *)&stack->data[offset];
+ pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
+ (void *)addr, (unsigned long)*valp, offset);
+ return 0;
+}
+
+static int access_reg(unw_addr_space_t __used as,
+ unw_regnum_t regnum, unw_word_t *valp,
+ int __write, void *arg)
+{
+ struct unwind_info *ui = arg;
+ int id, ret;
+
+ /* Don't support write, I suspect we don't need it. */
+ if (__write) {
+ pr_err("unwind: access_reg w %d\n", regnum);
+ return 0;
+ }
+
+ if (!ui->sample->user_regs.regs) {
+ *valp = 0;
+ return 0;
+ }
+
+ id = unwind__arch_reg_id(regnum);
+ if (id < 0)
+ return -EINVAL;
+
+ ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+ if (ret) {
+ pr_err("unwind: can't read reg %d\n", regnum);
+ return ret;
+ }
+
+ pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+ return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __used as,
+ unw_proc_info_t *pi __used,
+ void *arg __used)
+{
+ pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread, struct machine *machine,
+ unwind_entry_cb_t cb, void *arg)
+{
+ struct unwind_entry e;
+ struct addr_location al;
+
+ thread__find_addr_location(thread, machine,
+ PERF_RECORD_MISC_USER,
+ MAP__FUNCTION, ip, &al, NULL);
+
+ e.ip = ip;
+ e.map = al.map;
+ e.sym = al.sym;
+
+ pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+ al.sym ? al.sym->name : "''",
+ ip,
+ al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+ return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+ switch (err) {
+ case UNW_EINVAL:
+ pr_err("unwind: Only supports local.\n");
+ break;
+ case UNW_EUNSPEC:
+ pr_err("unwind: Unspecified error.\n");
+ break;
+ case UNW_EBADREG:
+ pr_err("unwind: Register unavailable.\n");
+ break;
+ default:
+ break;
+ }
+}
+
+static unw_accessors_t accessors = {
+ .find_proc_info = find_proc_info,
+ .put_unwind_info = put_unwind_info,
+ .get_dyn_info_list_addr = get_dyn_info_list_addr,
+ .access_mem = access_mem,
+ .access_reg = access_reg,
+ .access_fpreg = access_fpreg,
+ .resume = resume,
+ .get_proc_name = get_proc_name,
+};
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+ void *arg)
+{
+ unw_addr_space_t addr_space;
+ unw_cursor_t c;
+ int ret;
+
+ addr_space = unw_create_addr_space(&accessors, 0);
+ if (!addr_space) {
+ pr_err("unwind: Can't create unwind address space.\n");
+ return -ENOMEM;
+ }
+
+ ret = unw_init_remote(&c, addr_space, ui);
+ if (ret)
+ display_error(ret);
+
+ while (!ret && (unw_step(&c) > 0)) {
+ unw_word_t ip;
+
+ unw_get_reg(&c, UNW_REG_IP, &ip);
+ ret = entry(ip, ui->thread, ui->machine, cb, arg);
+ }
+
+ unw_destroy_addr_space(addr_space);
+ return ret;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+ struct machine *machine, struct thread *thread,
+ u64 sample_uregs, struct perf_sample *data)
+{
+ unw_word_t ip;
+ struct unwind_info ui = {
+ .sample = data,
+ .sample_uregs = sample_uregs,
+ .thread = thread,
+ .machine = machine,
+ };
+ int ret;
+
+ if (!data->user_regs.regs)
+ return -EINVAL;
+
+ ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+ if (ret)
+ return ret;
+
+ ret = entry(ip, thread, machine, cb, arg);
+ if (ret)
+ return -ENOMEM;
+
+ return get_entries(&ui, cb, arg);
+}
--- /dev/null
+#ifndef __UNWIND_H
+#define __UNWIND_H
+
+#include "types.h"
+#include "event.h"
+#include "symbol.h"
+
+struct unwind_entry {
+ struct map *map;
+ struct symbol *sym;
+ u64 ip;
+};
+
+typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
+
+#ifndef NO_LIBUNWIND_SUPPORT
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+ struct machine *machine,
+ struct thread *thread,
+ u64 sample_uregs,
+ struct perf_sample *data);
+int unwind__arch_reg_id(int regnum);
+#else
+static inline int
+unwind__get_entries(unwind_entry_cb_t cb __used, void *arg __used,
+ struct machine *machine __used,
+ struct thread *thread __used,
+ u64 sample_uregs __used,
+ struct perf_sample *data __used)
+{
+ return 0;
+}
+#endif /* NO_LIBUNWIND_SUPPORT */
+#endif /* __UNWIND_H */
#include "../perf.h"
#include "util.h"
#include <sys/mman.h>
+#include <execinfo.h>
+#include <stdio.h>
+#include <stdlib.h>
/*
* XXX We need to find a better place for these things...
return n;
}
+
+/* Obtain a backtrace and print it to stdout. */
+void dump_stack(void)
+{
+ void *array[16];
+ size_t size = backtrace(array, ARRAY_SIZE(array));
+ char **strings = backtrace_symbols(array, size);
+ size_t i;
+
+ printf("Obtained %zd stack frames.\n", size);
+
+ for (i = 0; i < size; i++)
+ printf("%s\n", strings[i]);
+
+ free(strings);
+}
char *rtrim(char *s);
+void dump_stack(void);
+
#endif
ifeq ("$(origin O)", "command line")
- OUTPUT := $(O)/
- COMMAND_O := O=$(O)
+ dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+ ABSOLUTE_O := $(shell cd $(O) ; pwd)
+ OUTPUT := $(ABSOLUTE_O)/
+ COMMAND_O := O=$(ABSOLUTE_O)
endif
ifneq ($(OUTPUT),)