Merge branch 'tip/x86/core-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core
diff --git a/Documentation/ABI/testing/sysfs-bus-rbd b/Documentation/ABI/testing/sysfs-bus-rbd
index fa72ccb..dbedafb 100644
--- a/Documentation/ABI/testing/sysfs-bus-rbd
+++ b/Documentation/ABI/testing/sysfs-bus-rbd
@@ -57,13 +57,6 @@
$ echo <snap-name> > /sys/bus/rbd/devices/<dev-id>/snap_create
-rollback_snap
-
- Rolls back data to the specified snapshot. This goes over the entire
- list of rados blocks and sends a rollback command to each.
-
- $ echo <snap-name> > /sys/bus/rbd/devices/<dev-id>/snap_rollback
-
snap_*
A directory per each snapshot
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 81c287f..0293fc8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1885,6 +1885,11 @@
arch_perfmon: [X86] Force use of architectural
perfmon on Intel CPUs instead of the
CPU specific event set.
+ timer: [X86] Force use of architectural NMI
+ timer mode (see also oprofile.timer
+ for generic hr timer mode)
+ [s390] Force legacy basic mode sampling
+ (report cpu_type "timer")
oops=panic Always panic on oopses. Default is to just kill the
process, but there is a small probability of
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index b510564..bb24c2a 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -191,8 +191,6 @@
Currently, only exact string matches are supported.
-Currently, the maximum number of predicates in a filter is 16.
-
5.2 Setting filters
-------------------
diff --git a/Makefile b/Makefile
index d1ea73f..a43733d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 3
PATCHLEVEL = 2
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Saber-toothed Squirrel
# *DOCUMENTATION*
diff --git a/arch/Kconfig b/arch/Kconfig
index 4b0669c..2505740 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -30,6 +30,10 @@
config HAVE_OPROFILE
bool
+config OPROFILE_NMI_TIMER
+ def_bool y
+ depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
+
config KPROBES
bool "Kprobes"
depends on MODULES
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e084b7e..776d76b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -220,8 +220,9 @@
be avoided when possible.
config PHYS_OFFSET
- hex "Physical address of main memory"
+ hex "Physical address of main memory" if MMU
depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
+ default DRAM_BASE if !MMU
help
Please provide the physical address corresponding to the
location of main memory in your system.
diff --git a/arch/arm/include/asm/unwind.h b/arch/arm/include/asm/unwind.h
index a5edf42..d1c3f3a 100644
--- a/arch/arm/include/asm/unwind.h
+++ b/arch/arm/include/asm/unwind.h
@@ -30,14 +30,15 @@
};
struct unwind_idx {
- unsigned long addr;
+ unsigned long addr_offset;
unsigned long insn;
};
struct unwind_table {
struct list_head list;
- struct unwind_idx *start;
- struct unwind_idx *stop;
+ const struct unwind_idx *start;
+ const struct unwind_idx *origin;
+ const struct unwind_idx *stop;
unsigned long begin_addr;
unsigned long end_addr;
};
@@ -49,15 +50,6 @@
extern void unwind_table_del(struct unwind_table *tab);
extern void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk);
-#ifdef CONFIG_ARM_UNWIND
-extern int __init unwind_init(void);
-#else
-static inline int __init unwind_init(void)
-{
- return 0;
-}
-#endif
-
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_ARM_UNWIND
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 8e9c98e..88b0941 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -640,6 +640,9 @@
static int __devinit armpmu_device_probe(struct platform_device *pdev)
{
+ if (!cpu_pmu)
+ return -ENODEV;
+
cpu_pmu->plat_device = pdev;
return 0;
}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 3448a3f..8fc2c8f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -895,8 +895,6 @@
{
struct machine_desc *mdesc;
- unwind_init();
-
setup_processor();
mdesc = setup_machine_fdt(__atags_pointer);
if (!mdesc)
@@ -904,6 +902,12 @@
machine_desc = mdesc;
machine_name = mdesc->name;
+#ifdef CONFIG_ZONE_DMA
+ if (mdesc->dma_zone_size) {
+ extern unsigned long arm_dma_zone_size;
+ arm_dma_zone_size = mdesc->dma_zone_size;
+ }
+#endif
if (mdesc->soft_reboot)
reboot_setup("s");
@@ -934,12 +938,6 @@
tcm_init();
-#ifdef CONFIG_ZONE_DMA
- if (mdesc->dma_zone_size) {
- extern unsigned long arm_dma_zone_size;
- arm_dma_zone_size = mdesc->dma_zone_size;
- }
-#endif
#ifdef CONFIG_MULTI_IRQ_HANDLER
handle_arch_irq = mdesc->handle_irq;
#endif
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index e7e8365..00df012 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -67,7 +67,7 @@
struct unwind_ctrl_block {
unsigned long vrs[16]; /* virtual register set */
- unsigned long *insn; /* pointer to the current instructions word */
+ const unsigned long *insn; /* pointer to the current instructions word */
int entries; /* number of entries left to interpret */
int byte; /* current byte number in the instructions word */
};
@@ -83,8 +83,9 @@
PC = 15
};
-extern struct unwind_idx __start_unwind_idx[];
-extern struct unwind_idx __stop_unwind_idx[];
+extern const struct unwind_idx __start_unwind_idx[];
+static const struct unwind_idx *__origin_unwind_idx;
+extern const struct unwind_idx __stop_unwind_idx[];
static DEFINE_SPINLOCK(unwind_lock);
static LIST_HEAD(unwind_tables);
@@ -98,45 +99,99 @@
})
/*
- * Binary search in the unwind index. The entries entries are
+ * Binary search in the unwind index. The entries are
* guaranteed to be sorted in ascending order by the linker.
+ *
+ * start = first entry
+ * origin = first entry with positive offset (or stop if there is no such entry)
+ * stop - 1 = last entry
*/
-static struct unwind_idx *search_index(unsigned long addr,
- struct unwind_idx *first,
- struct unwind_idx *last)
+static const struct unwind_idx *search_index(unsigned long addr,
+ const struct unwind_idx *start,
+ const struct unwind_idx *origin,
+ const struct unwind_idx *stop)
{
- pr_debug("%s(%08lx, %p, %p)\n", __func__, addr, first, last);
+ unsigned long addr_prel31;
- if (addr < first->addr) {
- pr_warning("unwind: Unknown symbol address %08lx\n", addr);
- return NULL;
- } else if (addr >= last->addr)
- return last;
+ pr_debug("%s(%08lx, %p, %p, %p)\n",
+ __func__, addr, start, origin, stop);
- while (first < last - 1) {
- struct unwind_idx *mid = first + ((last - first + 1) >> 1);
+ /*
+ * only search in the section with the matching sign. This way the
+ * prel31 numbers can be compared as unsigned longs.
+ */
+ if (addr < (unsigned long)start)
+ /* negative offsets: [start; origin) */
+ stop = origin;
+ else
+ /* positive offsets: [origin; stop) */
+ start = origin;
- if (addr < mid->addr)
- last = mid;
- else
- first = mid;
+ /* prel31 for address relavive to start */
+ addr_prel31 = (addr - (unsigned long)start) & 0x7fffffff;
+
+ while (start < stop - 1) {
+ const struct unwind_idx *mid = start + ((stop - start) >> 1);
+
+ /*
+ * As addr_prel31 is relative to start an offset is needed to
+ * make it relative to mid.
+ */
+ if (addr_prel31 - ((unsigned long)mid - (unsigned long)start) <
+ mid->addr_offset)
+ stop = mid;
+ else {
+ /* keep addr_prel31 relative to start */
+ addr_prel31 -= ((unsigned long)mid -
+ (unsigned long)start);
+ start = mid;
+ }
}
- return first;
+ if (likely(start->addr_offset <= addr_prel31))
+ return start;
+ else {
+ pr_warning("unwind: Unknown symbol address %08lx\n", addr);
+ return NULL;
+ }
}
-static struct unwind_idx *unwind_find_idx(unsigned long addr)
+static const struct unwind_idx *unwind_find_origin(
+ const struct unwind_idx *start, const struct unwind_idx *stop)
{
- struct unwind_idx *idx = NULL;
+ pr_debug("%s(%p, %p)\n", __func__, start, stop);
+ while (start < stop) {
+ const struct unwind_idx *mid = start + ((stop - start) >> 1);
+
+ if (mid->addr_offset >= 0x40000000)
+ /* negative offset */
+ start = mid + 1;
+ else
+ /* positive offset */
+ stop = mid;
+ }
+ pr_debug("%s -> %p\n", __func__, stop);
+ return stop;
+}
+
+static const struct unwind_idx *unwind_find_idx(unsigned long addr)
+{
+ const struct unwind_idx *idx = NULL;
unsigned long flags;
pr_debug("%s(%08lx)\n", __func__, addr);
- if (core_kernel_text(addr))
+ if (core_kernel_text(addr)) {
+ if (unlikely(!__origin_unwind_idx))
+ __origin_unwind_idx =
+ unwind_find_origin(__start_unwind_idx,
+ __stop_unwind_idx);
+
/* main unwind table */
idx = search_index(addr, __start_unwind_idx,
- __stop_unwind_idx - 1);
- else {
+ __origin_unwind_idx,
+ __stop_unwind_idx);
+ } else {
/* module unwind tables */
struct unwind_table *table;
@@ -145,7 +200,8 @@
if (addr >= table->begin_addr &&
addr < table->end_addr) {
idx = search_index(addr, table->start,
- table->stop - 1);
+ table->origin,
+ table->stop);
/* Move-to-front to exploit common traces */
list_move(&table->list, &unwind_tables);
break;
@@ -274,7 +330,7 @@
int unwind_frame(struct stackframe *frame)
{
unsigned long high, low;
- struct unwind_idx *idx;
+ const struct unwind_idx *idx;
struct unwind_ctrl_block ctrl;
/* only go to a higher address on the stack */
@@ -399,7 +455,6 @@
unsigned long text_size)
{
unsigned long flags;
- struct unwind_idx *idx;
struct unwind_table *tab = kmalloc(sizeof(*tab), GFP_KERNEL);
pr_debug("%s(%08lx, %08lx, %08lx, %08lx)\n", __func__, start, size,
@@ -408,15 +463,12 @@
if (!tab)
return tab;
- tab->start = (struct unwind_idx *)start;
- tab->stop = (struct unwind_idx *)(start + size);
+ tab->start = (const struct unwind_idx *)start;
+ tab->stop = (const struct unwind_idx *)(start + size);
+ tab->origin = unwind_find_origin(tab->start, tab->stop);
tab->begin_addr = text_addr;
tab->end_addr = text_addr + text_size;
- /* Convert the symbol addresses to absolute values */
- for (idx = tab->start; idx < tab->stop; idx++)
- idx->addr = prel31_to_addr(&idx->addr);
-
spin_lock_irqsave(&unwind_lock, flags);
list_add_tail(&tab->list, &unwind_tables);
spin_unlock_irqrestore(&unwind_lock, flags);
@@ -437,16 +489,3 @@
kfree(tab);
}
-
-int __init unwind_init(void)
-{
- struct unwind_idx *idx;
-
- /* Convert the symbol addresses to absolute values */
- for (idx = __start_unwind_idx; idx < __stop_unwind_idx; idx++)
- idx->addr = prel31_to_addr(&idx->addr);
-
- pr_debug("unwind: ARM stack unwinding initialised\n");
-
- return 0;
-}
diff --git a/arch/arm/mach-exynos/mct.c b/arch/arm/mach-exynos/mct.c
index 97343df..85b5527 100644
--- a/arch/arm/mach-exynos/mct.c
+++ b/arch/arm/mach-exynos/mct.c
@@ -44,8 +44,6 @@
char name[10];
};
-static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
-
static void exynos4_mct_write(unsigned int value, void *addr)
{
void __iomem *stat_addr;
@@ -264,6 +262,9 @@
}
#ifdef CONFIG_LOCAL_TIMERS
+
+static DEFINE_PER_CPU(struct mct_clock_event_device, percpu_mct_tick);
+
/* Clock event handling */
static void exynos4_mct_tick_stop(struct mct_clock_event_device *mevt)
{
@@ -428,9 +429,13 @@
void local_timer_stop(struct clock_event_device *evt)
{
+ unsigned int cpu = smp_processor_id();
evt->set_mode(CLOCK_EVT_MODE_UNUSED, evt);
if (mct_int_type == MCT_INT_SPI)
- disable_irq(evt->irq);
+ if (cpu == 0)
+ remove_irq(evt->irq, &mct_tick0_event_irq);
+ else
+ remove_irq(evt->irq, &mct_tick1_event_irq);
else
disable_percpu_irq(IRQ_MCT_LOCALTIMER);
}
@@ -443,6 +448,7 @@
clk_rate = clk_get_rate(mct_clk);
+#ifdef CONFIG_LOCAL_TIMERS
if (mct_int_type == MCT_INT_PPI) {
int err;
@@ -452,6 +458,7 @@
WARN(err, "MCT: can't request IRQ %d (%d)\n",
IRQ_MCT_LOCALTIMER, err);
}
+#endif /* CONFIG_LOCAL_TIMERS */
}
static void __init exynos4_timer_init(void)
diff --git a/arch/arm/mach-mx5/board-mx51_babbage.c b/arch/arm/mach-mx5/board-mx51_babbage.c
index 5c837603..24994bb 100644
--- a/arch/arm/mach-mx5/board-mx51_babbage.c
+++ b/arch/arm/mach-mx5/board-mx51_babbage.c
@@ -362,7 +362,7 @@
{
iomux_v3_cfg_t usbh1stp = MX51_PAD_USBH1_STP__USBH1_STP;
iomux_v3_cfg_t power_key = NEW_PAD_CTRL(MX51_PAD_EIM_A27__GPIO2_21,
- PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH | PAD_CTL_PUS_100K_UP);
+ PAD_CTL_SRE_FAST | PAD_CTL_DSE_HIGH);
imx51_soc_init();
diff --git a/arch/arm/mach-mx5/board-mx53_evk.c b/arch/arm/mach-mx5/board-mx53_evk.c
index 6bea31a..64bbfce 100644
--- a/arch/arm/mach-mx5/board-mx53_evk.c
+++ b/arch/arm/mach-mx5/board-mx53_evk.c
@@ -106,7 +106,7 @@
gpio_set_value(MX53_EVK_FEC_PHY_RST, 1);
}
-static struct fec_platform_data mx53_evk_fec_pdata = {
+static const struct fec_platform_data mx53_evk_fec_pdata __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
diff --git a/arch/arm/mach-mx5/board-mx53_loco.c b/arch/arm/mach-mx5/board-mx53_loco.c
index 7678f77..237bdec 100644
--- a/arch/arm/mach-mx5/board-mx53_loco.c
+++ b/arch/arm/mach-mx5/board-mx53_loco.c
@@ -242,7 +242,7 @@
gpio_set_value(LOCO_FEC_PHY_RST, 1);
}
-static struct fec_platform_data mx53_loco_fec_data = {
+static const struct fec_platform_data mx53_loco_fec_data __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
diff --git a/arch/arm/mach-mx5/board-mx53_smd.c b/arch/arm/mach-mx5/board-mx53_smd.c
index 59c0845..d42132a 100644
--- a/arch/arm/mach-mx5/board-mx53_smd.c
+++ b/arch/arm/mach-mx5/board-mx53_smd.c
@@ -104,7 +104,7 @@
gpio_set_value(SMD_FEC_PHY_RST, 1);
}
-static struct fec_platform_data mx53_smd_fec_data = {
+static const struct fec_platform_data mx53_smd_fec_data __initconst = {
.phy = PHY_INTERFACE_MODE_RMII,
};
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index ba1aa07..c15c5c9 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -193,7 +193,7 @@
static void __init rx51_charger_init(void)
{
WARN_ON(gpio_request_one(RX51_USB_TRANSCEIVER_RST_GPIO,
- GPIOF_OUT_INIT_LOW, "isp1704_reset"));
+ GPIOF_OUT_INIT_HIGH, "isp1704_reset"));
platform_device_register(&rx51_charger_device);
}
diff --git a/arch/arm/mach-omap2/mcbsp.c b/arch/arm/mach-omap2/mcbsp.c
index 292eee3..28fcb27 100644
--- a/arch/arm/mach-omap2/mcbsp.c
+++ b/arch/arm/mach-omap2/mcbsp.c
@@ -145,6 +145,9 @@
pdata->reg_size = 4;
pdata->has_ccr = true;
}
+ pdata->set_clk_src = omap2_mcbsp_set_clk_src;
+ if (id == 1)
+ pdata->mux_signal = omap2_mcbsp1_mux_rx_clk;
if (oh->class->rev == MCBSP_CONFIG_TYPE3) {
if (id == 2)
@@ -174,9 +177,6 @@
name, oh->name);
return PTR_ERR(pdev);
}
- pdata->set_clk_src = omap2_mcbsp_set_clk_src;
- if (id == 1)
- pdata->mux_signal = omap2_mcbsp1_mux_rx_clk;
omap_mcbsp_count++;
return 0;
}
diff --git a/arch/arm/mach-s5pv210/mach-smdkv210.c b/arch/arm/mach-s5pv210/mach-smdkv210.c
index a9106c3..8662ef6 100644
--- a/arch/arm/mach-s5pv210/mach-smdkv210.c
+++ b/arch/arm/mach-s5pv210/mach-smdkv210.c
@@ -273,6 +273,7 @@
static struct platform_pwm_backlight_data smdkv210_bl_data = {
.pwm_id = 3,
+ .pwm_period_ns = 1000,
};
static void __init smdkv210_map_io(void)
diff --git a/arch/arm/plat-mxc/cpufreq.c b/arch/arm/plat-mxc/cpufreq.c
index 74aac96..adbff70 100644
--- a/arch/arm/plat-mxc/cpufreq.c
+++ b/arch/arm/plat-mxc/cpufreq.c
@@ -17,6 +17,7 @@
* the CPU clock speed on the fly.
*/
+#include <linux/module.h>
#include <linux/cpufreq.h>
#include <linux/clk.h>
#include <linux/err.h>
diff --git a/arch/arm/plat-mxc/pwm.c b/arch/arm/plat-mxc/pwm.c
index 42d74ea..845de59 100644
--- a/arch/arm/plat-mxc/pwm.c
+++ b/arch/arm/plat-mxc/pwm.c
@@ -32,6 +32,9 @@
#define MX3_PWMSAR 0x0C /* PWM Sample Register */
#define MX3_PWMPR 0x10 /* PWM Period Register */
#define MX3_PWMCR_PRESCALER(x) (((x - 1) & 0xFFF) << 4)
+#define MX3_PWMCR_DOZEEN (1 << 24)
+#define MX3_PWMCR_WAITEN (1 << 23)
+#define MX3_PWMCR_DBGEN (1 << 22)
#define MX3_PWMCR_CLKSRC_IPG_HIGH (2 << 16)
#define MX3_PWMCR_CLKSRC_IPG (1 << 16)
#define MX3_PWMCR_EN (1 << 0)
@@ -77,7 +80,9 @@
writel(duty_cycles, pwm->mmio_base + MX3_PWMSAR);
writel(period_cycles, pwm->mmio_base + MX3_PWMPR);
- cr = MX3_PWMCR_PRESCALER(prescale) | MX3_PWMCR_EN;
+ cr = MX3_PWMCR_PRESCALER(prescale) |
+ MX3_PWMCR_DOZEEN | MX3_PWMCR_WAITEN |
+ MX3_PWMCR_DBGEN | MX3_PWMCR_EN;
if (cpu_is_mx25())
cr |= MX3_PWMCR_CLKSRC_IPG;
diff --git a/arch/arm/plat-samsung/dev-backlight.c b/arch/arm/plat-samsung/dev-backlight.c
index e657305..a976c02 100644
--- a/arch/arm/plat-samsung/dev-backlight.c
+++ b/arch/arm/plat-samsung/dev-backlight.c
@@ -15,7 +15,6 @@
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/pwm_backlight.h>
-#include <linux/slab.h>
#include <plat/devs.h>
#include <plat/gpio-cfg.h>
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
index f43c0e4..9daee91 100644
--- a/arch/s390/oprofile/hwsampler.c
+++ b/arch/s390/oprofile/hwsampler.c
@@ -22,6 +22,7 @@
#include <asm/irq.h>
#include "hwsampler.h"
+#include "op_counter.h"
#define MAX_NUM_SDB 511
#define MIN_NUM_SDB 1
@@ -896,6 +897,8 @@
if (sample_data_ptr->P == 1) {
/* userspace sample */
unsigned int pid = sample_data_ptr->prim_asn;
+ if (!counter_config.user)
+ goto skip_sample;
rcu_read_lock();
tsk = pid_task(find_vpid(pid), PIDTYPE_PID);
if (tsk)
@@ -903,6 +906,8 @@
rcu_read_unlock();
} else {
/* kernelspace sample */
+ if (!counter_config.kernel)
+ goto skip_sample;
regs = task_pt_regs(current);
}
@@ -910,7 +915,7 @@
oprofile_add_ext_hw_sample(sample_data_ptr->ia, regs, 0,
!sample_data_ptr->P, tsk);
mutex_unlock(&hws_sem);
-
+ skip_sample:
sample_data_ptr++;
}
}
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 6efc18b..6cf2286 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -2,10 +2,11 @@
* arch/s390/oprofile/init.c
*
* S390 Version
- * Copyright (C) 2003 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ * Copyright (C) 2002-2011 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Author(s): Thomas Spatzier (tspat@de.ibm.com)
* Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com)
* Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com)
+ * Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
*
* @remark Copyright 2002-2011 OProfile authors
*/
@@ -14,6 +15,8 @@
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/fs.h>
+#include <linux/module.h>
+#include <asm/processor.h>
#include "../../../drivers/oprofile/oprof.h"
@@ -22,6 +25,7 @@
#ifdef CONFIG_64BIT
#include "hwsampler.h"
+#include "op_counter.h"
#define DEFAULT_INTERVAL 4127518
@@ -35,16 +39,41 @@
static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
-static int hwsampler_file;
+static int hwsampler_enabled;
static int hwsampler_running; /* start_mutex must be held to change */
+static int hwsampler_available;
static struct oprofile_operations timer_ops;
+struct op_counter_config counter_config;
+
+enum __force_cpu_type {
+ reserved = 0, /* do not force */
+ timer,
+};
+static int force_cpu_type;
+
+static int set_cpu_type(const char *str, struct kernel_param *kp)
+{
+ if (!strcmp(str, "timer")) {
+ force_cpu_type = timer;
+ printk(KERN_INFO "oprofile: forcing timer to be returned "
+ "as cpu type\n");
+ } else {
+ force_cpu_type = 0;
+ }
+
+ return 0;
+}
+module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
+MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
+ "(report cpu_type \"timer\"");
+
static int oprofile_hwsampler_start(void)
{
int retval;
- hwsampler_running = hwsampler_file;
+ hwsampler_running = hwsampler_enabled;
if (!hwsampler_running)
return timer_ops.start();
@@ -72,10 +101,16 @@
return;
}
+/*
+ * File ops used for:
+ * /dev/oprofile/0/enabled
+ * /dev/oprofile/hwsampling/hwsampler (cpu_type = timer)
+ */
+
static ssize_t hwsampler_read(struct file *file, char __user *buf,
size_t count, loff_t *offset)
{
- return oprofilefs_ulong_to_user(hwsampler_file, buf, count, offset);
+ return oprofilefs_ulong_to_user(hwsampler_enabled, buf, count, offset);
}
static ssize_t hwsampler_write(struct file *file, char const __user *buf,
@@ -91,6 +126,9 @@
if (retval)
return retval;
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
if (oprofile_started)
/*
* save to do without locking as we set
@@ -99,7 +137,7 @@
*/
return -EBUSY;
- hwsampler_file = val;
+ hwsampler_enabled = val;
return count;
}
@@ -109,38 +147,311 @@
.write = hwsampler_write,
};
-static int oprofile_create_hwsampling_files(struct super_block *sb,
- struct dentry *root)
+/*
+ * File ops used for:
+ * /dev/oprofile/0/count
+ * /dev/oprofile/hwsampling/hw_interval (cpu_type = timer)
+ *
+ * Make sure that the value is within the hardware range.
+ */
+
+static ssize_t hw_interval_read(struct file *file, char __user *buf,
+ size_t count, loff_t *offset)
{
- struct dentry *hw_dir;
+ return oprofilefs_ulong_to_user(oprofile_hw_interval, buf,
+ count, offset);
+}
- /* reinitialize default values */
- hwsampler_file = 1;
+static ssize_t hw_interval_write(struct file *file, char const __user *buf,
+ size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
- hw_dir = oprofilefs_mkdir(sb, root, "hwsampling");
- if (!hw_dir)
+ if (*offset)
+ return -EINVAL;
+ retval = oprofilefs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+ if (val < oprofile_min_interval)
+ oprofile_hw_interval = oprofile_min_interval;
+ else if (val > oprofile_max_interval)
+ oprofile_hw_interval = oprofile_max_interval;
+ else
+ oprofile_hw_interval = val;
+
+ return count;
+}
+
+static const struct file_operations hw_interval_fops = {
+ .read = hw_interval_read,
+ .write = hw_interval_write,
+};
+
+/*
+ * File ops used for:
+ * /dev/oprofile/0/event
+ * Only a single event with number 0 is supported with this counter.
+ *
+ * /dev/oprofile/0/unit_mask
+ * This is a dummy file needed by the user space tools.
+ * No value other than 0 is accepted or returned.
+ */
+
+static ssize_t hwsampler_zero_read(struct file *file, char __user *buf,
+ size_t count, loff_t *offset)
+{
+ return oprofilefs_ulong_to_user(0, buf, count, offset);
+}
+
+static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
+ size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
return -EINVAL;
- oprofilefs_create_file(sb, hw_dir, "hwsampler", &hwsampler_fops);
- oprofilefs_create_ulong(sb, hw_dir, "hw_interval",
- &oprofile_hw_interval);
- oprofilefs_create_ro_ulong(sb, hw_dir, "hw_min_interval",
- &oprofile_min_interval);
- oprofilefs_create_ro_ulong(sb, hw_dir, "hw_max_interval",
- &oprofile_max_interval);
- oprofilefs_create_ulong(sb, hw_dir, "hw_sdbt_blocks",
- &oprofile_sdbt_blocks);
+ retval = oprofilefs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+ if (val != 0)
+ return -EINVAL;
+ return count;
+}
+static const struct file_operations zero_fops = {
+ .read = hwsampler_zero_read,
+ .write = hwsampler_zero_write,
+};
+
+/* /dev/oprofile/0/kernel file ops. */
+
+static ssize_t hwsampler_kernel_read(struct file *file, char __user *buf,
+ size_t count, loff_t *offset)
+{
+ return oprofilefs_ulong_to_user(counter_config.kernel,
+ buf, count, offset);
+}
+
+static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
+ size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = oprofilefs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
+ counter_config.kernel = val;
+
+ return count;
+}
+
+static const struct file_operations kernel_fops = {
+ .read = hwsampler_kernel_read,
+ .write = hwsampler_kernel_write,
+};
+
+/* /dev/oprofile/0/user file ops. */
+
+static ssize_t hwsampler_user_read(struct file *file, char __user *buf,
+ size_t count, loff_t *offset)
+{
+ return oprofilefs_ulong_to_user(counter_config.user,
+ buf, count, offset);
+}
+
+static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
+ size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = oprofilefs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
+ counter_config.user = val;
+
+ return count;
+}
+
+static const struct file_operations user_fops = {
+ .read = hwsampler_user_read,
+ .write = hwsampler_user_write,
+};
+
+
+/*
+ * File ops used for: /dev/oprofile/timer/enabled
+ * The value always has to be the inverted value of hwsampler_enabled. So
+ * no separate variable is created. That way we do not need locking.
+ */
+
+static ssize_t timer_enabled_read(struct file *file, char __user *buf,
+ size_t count, loff_t *offset)
+{
+ return oprofilefs_ulong_to_user(!hwsampler_enabled, buf, count, offset);
+}
+
+static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
+ size_t count, loff_t *offset)
+{
+ unsigned long val;
+ int retval;
+
+ if (*offset)
+ return -EINVAL;
+
+ retval = oprofilefs_ulong_from_user(&val, buf, count);
+ if (retval)
+ return retval;
+
+ if (val != 0 && val != 1)
+ return -EINVAL;
+
+ /* Timer cannot be disabled without having hardware sampling. */
+ if (val == 0 && !hwsampler_available)
+ return -EINVAL;
+
+ if (oprofile_started)
+ /*
+ * save to do without locking as we set
+ * hwsampler_running in start() when start_mutex is
+ * held
+ */
+ return -EBUSY;
+
+ hwsampler_enabled = !val;
+
+ return count;
+}
+
+static const struct file_operations timer_enabled_fops = {
+ .read = timer_enabled_read,
+ .write = timer_enabled_write,
+};
+
+
+static int oprofile_create_hwsampling_files(struct super_block *sb,
+ struct dentry *root)
+{
+ struct dentry *dir;
+
+ dir = oprofilefs_mkdir(sb, root, "timer");
+ if (!dir)
+ return -EINVAL;
+
+ oprofilefs_create_file(sb, dir, "enabled", &timer_enabled_fops);
+
+ if (!hwsampler_available)
+ return 0;
+
+ /* reinitialize default values */
+ hwsampler_enabled = 1;
+ counter_config.kernel = 1;
+ counter_config.user = 1;
+
+ if (!force_cpu_type) {
+ /*
+ * Create the counter file system. A single virtual
+ * counter is created which can be used to
+ * enable/disable hardware sampling dynamically from
+ * user space. The user space will configure a single
+ * counter with a single event. The value of 'event'
+ * and 'unit_mask' are not evaluated by the kernel code
+ * and can only be set to 0.
+ */
+
+ dir = oprofilefs_mkdir(sb, root, "0");
+ if (!dir)
+ return -EINVAL;
+
+ oprofilefs_create_file(sb, dir, "enabled", &hwsampler_fops);
+ oprofilefs_create_file(sb, dir, "event", &zero_fops);
+ oprofilefs_create_file(sb, dir, "count", &hw_interval_fops);
+ oprofilefs_create_file(sb, dir, "unit_mask", &zero_fops);
+ oprofilefs_create_file(sb, dir, "kernel", &kernel_fops);
+ oprofilefs_create_file(sb, dir, "user", &user_fops);
+ oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+ &oprofile_sdbt_blocks);
+
+ } else {
+ /*
+ * Hardware sampling can be used but the cpu_type is
+ * forced to timer in order to deal with legacy user
+ * space tools. The /dev/oprofile/hwsampling fs is
+ * provided in that case.
+ */
+ dir = oprofilefs_mkdir(sb, root, "hwsampling");
+ if (!dir)
+ return -EINVAL;
+
+ oprofilefs_create_file(sb, dir, "hwsampler",
+ &hwsampler_fops);
+ oprofilefs_create_file(sb, dir, "hw_interval",
+ &hw_interval_fops);
+ oprofilefs_create_ro_ulong(sb, dir, "hw_min_interval",
+ &oprofile_min_interval);
+ oprofilefs_create_ro_ulong(sb, dir, "hw_max_interval",
+ &oprofile_max_interval);
+ oprofilefs_create_ulong(sb, dir, "hw_sdbt_blocks",
+ &oprofile_sdbt_blocks);
+ }
return 0;
}
static int oprofile_hwsampler_init(struct oprofile_operations *ops)
{
+ /*
+ * Initialize the timer mode infrastructure as well in order
+ * to be able to switch back dynamically. oprofile_timer_init
+ * is not supposed to fail.
+ */
+ if (oprofile_timer_init(ops))
+ BUG();
+
+ memcpy(&timer_ops, ops, sizeof(timer_ops));
+ ops->create_files = oprofile_create_hwsampling_files;
+
+ /*
+ * If the user space tools do not support newer cpu types,
+ * the force_cpu_type module parameter
+ * can be used to always return \"timer\" as cpu type.
+ */
+ if (force_cpu_type != timer) {
+ struct cpuid id;
+
+ get_cpu_id (&id);
+
+ switch (id.machine) {
+ case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
+ case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
+ default: return -ENODEV;
+ }
+ }
+
if (hwsampler_setup())
return -ENODEV;
/*
- * create hwsampler files only if hwsampler_setup() succeeds.
+ * Query the range for the sampling interval from the
+ * hardware.
*/
oprofile_min_interval = hwsampler_query_min_interval();
if (oprofile_min_interval == 0)
@@ -155,23 +466,17 @@
if (oprofile_hw_interval > oprofile_max_interval)
oprofile_hw_interval = oprofile_max_interval;
- if (oprofile_timer_init(ops))
- return -ENODEV;
-
- printk(KERN_INFO "oprofile: using hardware sampling\n");
-
- memcpy(&timer_ops, ops, sizeof(timer_ops));
+ printk(KERN_INFO "oprofile: System z hardware sampling "
+ "facility found.\n");
ops->start = oprofile_hwsampler_start;
ops->stop = oprofile_hwsampler_stop;
- ops->create_files = oprofile_create_hwsampling_files;
return 0;
}
static void oprofile_hwsampler_exit(void)
{
- oprofile_timer_exit();
hwsampler_shutdown();
}
@@ -182,7 +487,15 @@
ops->backtrace = s390_backtrace;
#ifdef CONFIG_64BIT
- return oprofile_hwsampler_init(ops);
+
+ /*
+ * -ENODEV is not reported to the caller. The module itself
+ * will use the timer mode sampling as fallback and this is
+ * always available.
+ */
+ hwsampler_available = oprofile_hwsampler_init(ops) == 0;
+
+ return 0;
#else
return -ENODEV;
#endif
diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h
new file mode 100644
index 0000000..1a8d3ca
--- /dev/null
+++ b/arch/s390/oprofile/op_counter.h
@@ -0,0 +1,23 @@
+/**
+ * arch/s390/oprofile/op_counter.h
+ *
+ * Copyright (C) 2011 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ * Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
+ *
+ * @remark Copyright 2011 OProfile authors
+ */
+
+#ifndef OP_COUNTER_H
+#define OP_COUNTER_H
+
+struct op_counter_config {
+ /* `enabled' maps to the hwsampler_file variable. */
+ /* `count' maps to the oprofile_hw_interval variable. */
+ /* `event' and `unit_mask' are unused. */
+ unsigned long kernel;
+ unsigned long user;
+};
+
+extern struct op_counter_config counter_config;
+
+#endif /* OP_COUNTER_H */
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 7429b47..381edcd 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1181,13 +1181,11 @@
dp->rcv_buf_len = 4096;
- dp->ds_states = kzalloc(sizeof(ds_states_template),
- GFP_KERNEL);
+ dp->ds_states = kmemdup(ds_states_template,
+ sizeof(ds_states_template), GFP_KERNEL);
if (!dp->ds_states)
goto out_free_rcv_buf;
- memcpy(dp->ds_states, ds_states_template,
- sizeof(ds_states_template));
dp->num_ds_states = ARRAY_SIZE(ds_states_template);
for (i = 0; i < dp->num_ds_states; i++)
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
index 4661480..741df91 100644
--- a/arch/sparc/kernel/prom_common.c
+++ b/arch/sparc/kernel/prom_common.c
@@ -58,12 +58,10 @@
void *new_val;
int err;
- new_val = kmalloc(len, GFP_KERNEL);
+ new_val = kmemdup(val, len, GFP_KERNEL);
if (!new_val)
return -ENOMEM;
- memcpy(new_val, val, len);
-
err = -ENODEV;
mutex_lock(&of_set_property_mutex);
diff --git a/arch/sparc/mm/btfixup.c b/arch/sparc/mm/btfixup.c
index 5175ac2..8a7f817 100644
--- a/arch/sparc/mm/btfixup.c
+++ b/arch/sparc/mm/btfixup.c
@@ -302,8 +302,7 @@
case 'i': /* INT */
if ((insn & 0xc1c00000) == 0x01000000) /* %HI */
set_addr(addr, q[1], fmangled, (insn & 0xffc00000) | (p[1] >> 10));
- else if ((insn & 0x80002000) == 0x80002000 &&
- (insn & 0x01800000) != 0x01800000) /* %LO */
+ else if ((insn & 0x80002000) == 0x80002000) /* %LO */
set_addr(addr, q[1], fmangled, (insn & 0xffffe000) | (p[1] & 0x3ff));
else {
prom_printf(insn_i, p, addr, insn);
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index c954703..908b969 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -53,13 +53,6 @@
*/
#define E820_RESERVED_KERN 128
-/*
- * Address ranges that need to be mapped by the kernel direct
- * mapping. This is used to make sure regions such as
- * EFI_RUNTIME_SERVICES_DATA are directly mapped. See setup_arch().
- */
-#define E820_RESERVED_EFI 129
-
#ifndef __ASSEMBLY__
#include <linux/types.h>
struct e820entry {
@@ -122,7 +115,6 @@
}
#endif
-extern unsigned long e820_end_pfn(unsigned long limit_pfn, unsigned type);
extern unsigned long e820_end_of_ram_pfn(void);
extern unsigned long e820_end_of_low_ram_pfn(void);
extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b8d8bfc..7093e4a 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -33,6 +33,8 @@
#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \
efi_call_virt(f, a1, a2, a3, a4, a5, a6)
+#define efi_ioremap(addr, size, type) ioremap_cache(addr, size)
+
#else /* !CONFIG_X86_32 */
extern u64 efi_call0(void *fp);
@@ -82,6 +84,9 @@
efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
(u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
+ u32 type);
+
#endif /* CONFIG_X86_32 */
extern int add_efi_memmap;
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 88c765e..74df3f1 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -137,6 +137,13 @@
return (insn->vex_prefix.value != 0);
}
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+ return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+ insn->displacement.got && insn->immediate.got;
+}
+
static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
{
if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index f61c62f..096c975 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -57,6 +57,7 @@
(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6
+#define ARCH_PERFMON_EVENTS_COUNT 7
/*
* Intel "Architectural Performance Monitoring" CPUID
@@ -72,6 +73,19 @@
unsigned int full;
};
+union cpuid10_ebx {
+ struct {
+ unsigned int no_unhalted_core_cycles:1;
+ unsigned int no_instructions_retired:1;
+ unsigned int no_unhalted_reference_cycles:1;
+ unsigned int no_llc_reference:1;
+ unsigned int no_llc_misses:1;
+ unsigned int no_branch_instruction_retired:1;
+ unsigned int no_branch_misses_retired:1;
+ } split;
+ unsigned int full;
+};
+
union cpuid10_edx {
struct {
unsigned int num_counters_fixed:5;
@@ -81,6 +95,15 @@
unsigned int full;
};
+struct x86_pmu_capability {
+ int version;
+ int num_counters_gp;
+ int num_counters_fixed;
+ int bit_width_gp;
+ int bit_width_fixed;
+ unsigned int events_mask;
+ int events_mask_len;
+};
/*
* Fixed-purpose performance events:
@@ -89,23 +112,24 @@
/*
* All 3 fixed-mode PMCs are configured via this single MSR:
*/
-#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d
+#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d
/*
* The counts are available in three separate MSRs:
*/
/* Instr_Retired.Any: */
-#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309
-#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0)
+#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309
+#define X86_PMC_IDX_FIXED_INSTRUCTIONS (X86_PMC_IDX_FIXED + 0)
/* CPU_CLK_Unhalted.Core: */
-#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a
-#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1)
+#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a
+#define X86_PMC_IDX_FIXED_CPU_CYCLES (X86_PMC_IDX_FIXED + 1)
/* CPU_CLK_Unhalted.Ref: */
-#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b
-#define X86_PMC_IDX_FIXED_BUS_CYCLES (X86_PMC_IDX_FIXED + 2)
+#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b
+#define X86_PMC_IDX_FIXED_REF_CYCLES (X86_PMC_IDX_FIXED + 2)
+#define X86_PMC_MSK_FIXED_REF_CYCLES (1ULL << X86_PMC_IDX_FIXED_REF_CYCLES)
/*
* We model BTS tracing as another fixed-mode PMC.
@@ -202,6 +226,7 @@
};
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
+extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
#else
static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
{
@@ -209,6 +234,11 @@
return NULL;
}
+static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
+{
+ memset(cap, 0, sizeof(*cap));
+}
+
static inline void perf_events_lapic_init(void) { }
#endif
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bda212..5adce10 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -484,18 +484,195 @@
return event->pmu == &pmu;
}
+/*
+ * Event scheduler state:
+ *
+ * Assign events iterating over all events and counters, beginning
+ * with events with least weights first. Keep the current iterator
+ * state in struct sched_state.
+ */
+struct sched_state {
+ int weight;
+ int event; /* event index */
+ int counter; /* counter index */
+ int unassigned; /* number of events to be assigned left */
+ unsigned long used[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+};
+
+/* Total max is X86_PMC_IDX_MAX, but we are O(n!) limited */
+#define SCHED_STATES_MAX 2
+
+struct perf_sched {
+ int max_weight;
+ int max_events;
+ struct event_constraint **constraints;
+ struct sched_state state;
+ int saved_states;
+ struct sched_state saved[SCHED_STATES_MAX];
+};
+
+/*
+ * Initialize interator that runs through all events and counters.
+ */
+static void perf_sched_init(struct perf_sched *sched, struct event_constraint **c,
+ int num, int wmin, int wmax)
+{
+ int idx;
+
+ memset(sched, 0, sizeof(*sched));
+ sched->max_events = num;
+ sched->max_weight = wmax;
+ sched->constraints = c;
+
+ for (idx = 0; idx < num; idx++) {
+ if (c[idx]->weight == wmin)
+ break;
+ }
+
+ sched->state.event = idx; /* start with min weight */
+ sched->state.weight = wmin;
+ sched->state.unassigned = num;
+}
+
+static void perf_sched_save_state(struct perf_sched *sched)
+{
+ if (WARN_ON_ONCE(sched->saved_states >= SCHED_STATES_MAX))
+ return;
+
+ sched->saved[sched->saved_states] = sched->state;
+ sched->saved_states++;
+}
+
+static bool perf_sched_restore_state(struct perf_sched *sched)
+{
+ if (!sched->saved_states)
+ return false;
+
+ sched->saved_states--;
+ sched->state = sched->saved[sched->saved_states];
+
+ /* continue with next counter: */
+ clear_bit(sched->state.counter++, sched->state.used);
+
+ return true;
+}
+
+/*
+ * Select a counter for the current event to schedule. Return true on
+ * success.
+ */
+static bool __perf_sched_find_counter(struct perf_sched *sched)
+{
+ struct event_constraint *c;
+ int idx;
+
+ if (!sched->state.unassigned)
+ return false;
+
+ if (sched->state.event >= sched->max_events)
+ return false;
+
+ c = sched->constraints[sched->state.event];
+
+ /* Prefer fixed purpose counters */
+ if (x86_pmu.num_counters_fixed) {
+ idx = X86_PMC_IDX_FIXED;
+ for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_MAX) {
+ if (!__test_and_set_bit(idx, sched->state.used))
+ goto done;
+ }
+ }
+ /* Grab the first unused counter starting with idx */
+ idx = sched->state.counter;
+ for_each_set_bit_cont(idx, c->idxmsk, X86_PMC_IDX_FIXED) {
+ if (!__test_and_set_bit(idx, sched->state.used))
+ goto done;
+ }
+
+ return false;
+
+done:
+ sched->state.counter = idx;
+
+ if (c->overlap)
+ perf_sched_save_state(sched);
+
+ return true;
+}
+
+static bool perf_sched_find_counter(struct perf_sched *sched)
+{
+ while (!__perf_sched_find_counter(sched)) {
+ if (!perf_sched_restore_state(sched))
+ return false;
+ }
+
+ return true;
+}
+
+/*
+ * Go through all unassigned events and find the next one to schedule.
+ * Take events with the least weight first. Return true on success.
+ */
+static bool perf_sched_next_event(struct perf_sched *sched)
+{
+ struct event_constraint *c;
+
+ if (!sched->state.unassigned || !--sched->state.unassigned)
+ return false;
+
+ do {
+ /* next event */
+ sched->state.event++;
+ if (sched->state.event >= sched->max_events) {
+ /* next weight */
+ sched->state.event = 0;
+ sched->state.weight++;
+ if (sched->state.weight > sched->max_weight)
+ return false;
+ }
+ c = sched->constraints[sched->state.event];
+ } while (c->weight != sched->state.weight);
+
+ sched->state.counter = 0; /* start with first counter */
+
+ return true;
+}
+
+/*
+ * Assign a counter for each event.
+ */
+static int perf_assign_events(struct event_constraint **constraints, int n,
+ int wmin, int wmax, int *assign)
+{
+ struct perf_sched sched;
+
+ perf_sched_init(&sched, constraints, n, wmin, wmax);
+
+ do {
+ if (!perf_sched_find_counter(&sched))
+ break; /* failed */
+ if (assign)
+ assign[sched.state.event] = sched.state.counter;
+ } while (perf_sched_next_event(&sched));
+
+ return sched.state.unassigned;
+}
+
int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
{
struct event_constraint *c, *constraints[X86_PMC_IDX_MAX];
unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- int i, j, w, wmax, num = 0;
+ int i, wmin, wmax, num = 0;
struct hw_perf_event *hwc;
bitmap_zero(used_mask, X86_PMC_IDX_MAX);
- for (i = 0; i < n; i++) {
+ for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]);
constraints[i] = c;
+ wmin = min(wmin, c->weight);
+ wmax = max(wmax, c->weight);
}
/*
@@ -521,59 +698,11 @@
if (assign)
assign[i] = hwc->idx;
}
- if (i == n)
- goto done;
- /*
- * begin slow path
- */
+ /* slow path */
+ if (i != n)
+ num = perf_assign_events(constraints, n, wmin, wmax, assign);
- bitmap_zero(used_mask, X86_PMC_IDX_MAX);
-
- /*
- * weight = number of possible counters
- *
- * 1 = most constrained, only works on one counter
- * wmax = least constrained, works on any counter
- *
- * assign events to counters starting with most
- * constrained events.
- */
- wmax = x86_pmu.num_counters;
-
- /*
- * when fixed event counters are present,
- * wmax is incremented by 1 to account
- * for one more choice
- */
- if (x86_pmu.num_counters_fixed)
- wmax++;
-
- for (w = 1, num = n; num && w <= wmax; w++) {
- /* for each event */
- for (i = 0; num && i < n; i++) {
- c = constraints[i];
- hwc = &cpuc->event_list[i]->hw;
-
- if (c->weight != w)
- continue;
-
- for_each_set_bit(j, c->idxmsk, X86_PMC_IDX_MAX) {
- if (!test_bit(j, used_mask))
- break;
- }
-
- if (j == X86_PMC_IDX_MAX)
- break;
-
- __set_bit(j, used_mask);
-
- if (assign)
- assign[i] = j;
- num--;
- }
- }
-done:
/*
* scheduling failed or is just a simulation,
* free resources if necessary
@@ -1119,6 +1248,7 @@
static int __init init_hw_perf_events(void)
{
+ struct x86_pmu_quirk *quirk;
struct event_constraint *c;
int err;
@@ -1147,8 +1277,8 @@
pr_cont("%s PMU driver.\n", x86_pmu.name);
- if (x86_pmu.quirks)
- x86_pmu.quirks();
+ for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next)
+ quirk->func();
if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
@@ -1171,12 +1301,18 @@
unconstrained = (struct event_constraint)
__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
- 0, x86_pmu.num_counters);
+ 0, x86_pmu.num_counters, 0);
if (x86_pmu.event_constraints) {
+ /*
+ * event on fixed counter2 (REF_CYCLES) only works on this
+ * counter, so do not extend mask to generic counters
+ */
for_each_event_constraint(c, x86_pmu.event_constraints) {
- if (c->cmask != X86_RAW_EVENT_MASK)
+ if (c->cmask != X86_RAW_EVENT_MASK
+ || c->idxmsk64 == X86_PMC_MSK_FIXED_REF_CYCLES) {
continue;
+ }
c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
c->weight += x86_pmu.num_counters;
@@ -1566,3 +1702,15 @@
return misc;
}
+
+void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
+{
+ cap->version = x86_pmu.version;
+ cap->num_counters_gp = x86_pmu.num_counters;
+ cap->num_counters_fixed = x86_pmu.num_counters_fixed;
+ cap->bit_width_gp = x86_pmu.cntval_bits;
+ cap->bit_width_fixed = x86_pmu.cntval_bits;
+ cap->events_mask = (unsigned int)x86_pmu.events_maskl;
+ cap->events_mask_len = x86_pmu.events_mask_len;
+}
+EXPORT_SYMBOL_GPL(perf_get_x86_pmu_capability);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index b9698d4..8944062 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -45,6 +45,7 @@
u64 code;
u64 cmask;
int weight;
+ int overlap;
};
struct amd_nb {
@@ -151,15 +152,40 @@
void *kfree_on_online;
};
-#define __EVENT_CONSTRAINT(c, n, m, w) {\
+#define __EVENT_CONSTRAINT(c, n, m, w, o) {\
{ .idxmsk64 = (n) }, \
.code = (c), \
.cmask = (m), \
.weight = (w), \
+ .overlap = (o), \
}
#define EVENT_CONSTRAINT(c, n, m) \
- __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
+ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0)
+
+/*
+ * The overlap flag marks event constraints with overlapping counter
+ * masks. This is the case if the counter mask of such an event is not
+ * a subset of any other counter mask of a constraint with an equal or
+ * higher weight, e.g.:
+ *
+ * c_overlaps = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
+ * c_another1 = EVENT_CONSTRAINT(0, 0x07, 0);
+ * c_another2 = EVENT_CONSTRAINT(0, 0x38, 0);
+ *
+ * The event scheduler may not select the correct counter in the first
+ * cycle because it needs to know which subsequent events will be
+ * scheduled. It may fail to schedule the events then. So we set the
+ * overlap flag for such constraints to give the scheduler a hint which
+ * events to select for counter rescheduling.
+ *
+ * Care must be taken as the rescheduling algorithm is O(n!) which
+ * will increase scheduling cycles for an over-commited system
+ * dramatically. The number of such EVENT_CONSTRAINT_OVERLAP() macros
+ * and its counter masks must be kept at a minimum.
+ */
+#define EVENT_CONSTRAINT_OVERLAP(c, n, m) \
+ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1)
/*
* Constraint on the Event code.
@@ -235,6 +261,11 @@
u64 capabilities;
};
+struct x86_pmu_quirk {
+ struct x86_pmu_quirk *next;
+ void (*func)(void);
+};
+
/*
* struct x86_pmu - generic x86 pmu
*/
@@ -259,6 +290,11 @@
int num_counters_fixed;
int cntval_bits;
u64 cntval_mask;
+ union {
+ unsigned long events_maskl;
+ unsigned long events_mask[BITS_TO_LONGS(ARCH_PERFMON_EVENTS_COUNT)];
+ };
+ int events_mask_len;
int apic;
u64 max_period;
struct event_constraint *
@@ -268,7 +304,7 @@
void (*put_event_constraints)(struct cpu_hw_events *cpuc,
struct perf_event *event);
struct event_constraint *event_constraints;
- void (*quirks)(void);
+ struct x86_pmu_quirk *quirks;
int perfctr_second_write;
int (*cpu_prepare)(int cpu);
@@ -309,6 +345,15 @@
struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
};
+#define x86_add_quirk(func_) \
+do { \
+ static struct x86_pmu_quirk __quirk __initdata = { \
+ .func = func_, \
+ }; \
+ __quirk.next = x86_pmu.quirks; \
+ x86_pmu.quirks = &__quirk; \
+} while (0)
+
#define ERF_NO_HT_SHARING 1
#define ERF_HAS_RSP_1 2
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index aeefd45..0397b23 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -492,7 +492,7 @@
static struct event_constraint amd_f15_PMC0 = EVENT_CONSTRAINT(0, 0x01, 0);
static struct event_constraint amd_f15_PMC20 = EVENT_CONSTRAINT(0, 0x07, 0);
static struct event_constraint amd_f15_PMC3 = EVENT_CONSTRAINT(0, 0x08, 0);
-static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT(0, 0x09, 0);
+static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09, 0);
static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0);
static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 8d601b1..cbfaaa2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -28,6 +28,7 @@
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
[PERF_COUNT_HW_BUS_CYCLES] = 0x013c,
+ [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x0300, /* pseudo-encoding */
};
static struct event_constraint intel_core_event_constraints[] __read_mostly =
@@ -45,12 +46,7 @@
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- /*
- * Core2 has Fixed Counter 2 listed as CPU_CLK_UNHALTED.REF and event
- * 0x013c as CPU_CLK_UNHALTED.BUS and specifies there is a fixed
- * ratio between these counters.
- */
- /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x10, 0x1), /* FP_COMP_OPS_EXE */
INTEL_EVENT_CONSTRAINT(0x11, 0x2), /* FP_ASSIST */
INTEL_EVENT_CONSTRAINT(0x12, 0x2), /* MUL */
@@ -68,7 +64,7 @@
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x40, 0x3), /* L1D_CACHE_LD */
INTEL_EVENT_CONSTRAINT(0x41, 0x3), /* L1D_CACHE_ST */
INTEL_EVENT_CONSTRAINT(0x42, 0x3), /* L1D_CACHE_LOCK */
@@ -90,7 +86,7 @@
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */
INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */
INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */
@@ -102,7 +98,7 @@
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
@@ -125,7 +121,7 @@
{
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
- /* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
EVENT_CONSTRAINT_END
};
@@ -1519,7 +1515,7 @@
.guest_get_msrs = intel_guest_get_msrs,
};
-static void intel_clovertown_quirks(void)
+static __init void intel_clovertown_quirk(void)
{
/*
* PEBS is unreliable due to:
@@ -1545,19 +1541,60 @@
x86_pmu.pebs_constraints = NULL;
}
-static void intel_sandybridge_quirks(void)
+static __init void intel_sandybridge_quirk(void)
{
printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
x86_pmu.pebs = 0;
x86_pmu.pebs_constraints = NULL;
}
+static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
+ { PERF_COUNT_HW_CPU_CYCLES, "cpu cycles" },
+ { PERF_COUNT_HW_INSTRUCTIONS, "instructions" },
+ { PERF_COUNT_HW_BUS_CYCLES, "bus cycles" },
+ { PERF_COUNT_HW_CACHE_REFERENCES, "cache references" },
+ { PERF_COUNT_HW_CACHE_MISSES, "cache misses" },
+ { PERF_COUNT_HW_BRANCH_INSTRUCTIONS, "branch instructions" },
+ { PERF_COUNT_HW_BRANCH_MISSES, "branch misses" },
+};
+
+static __init void intel_arch_events_quirk(void)
+{
+ int bit;
+
+ /* disable event that reported as not presend by cpuid */
+ for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) {
+ intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0;
+ printk(KERN_WARNING "CPUID marked event: \'%s\' unavailable\n",
+ intel_arch_events_map[bit].name);
+ }
+}
+
+static __init void intel_nehalem_quirk(void)
+{
+ union cpuid10_ebx ebx;
+
+ ebx.full = x86_pmu.events_maskl;
+ if (ebx.split.no_branch_misses_retired) {
+ /*
+ * Erratum AAJ80 detected, we work it around by using
+ * the BR_MISP_EXEC.ANY event. This will over-count
+ * branch-misses, but it's still much better than the
+ * architectural event which is often completely bogus:
+ */
+ intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+ ebx.split.no_branch_misses_retired = 0;
+ x86_pmu.events_maskl = ebx.full;
+ printk(KERN_INFO "CPU erratum AAJ80 worked around\n");
+ }
+}
+
__init int intel_pmu_init(void)
{
union cpuid10_edx edx;
union cpuid10_eax eax;
+ union cpuid10_ebx ebx;
unsigned int unused;
- unsigned int ebx;
int version;
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
@@ -1574,8 +1611,8 @@
* Check whether the Architectural PerfMon supports
* Branch Misses Retired hw_event or not.
*/
- cpuid(10, &eax.full, &ebx, &unused, &edx.full);
- if (eax.split.mask_length <= ARCH_PERFMON_BRANCH_MISSES_RETIRED)
+ cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+ if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT)
return -ENODEV;
version = eax.split.version_id;
@@ -1589,6 +1626,9 @@
x86_pmu.cntval_bits = eax.split.bit_width;
x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
+ x86_pmu.events_maskl = ebx.full;
+ x86_pmu.events_mask_len = eax.split.mask_length;
+
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
* assume at least 3 events:
@@ -1608,6 +1648,8 @@
intel_ds_init();
+ x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
+
/*
* Install the hw-cache-events table:
*/
@@ -1617,7 +1659,7 @@
break;
case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
- x86_pmu.quirks = intel_clovertown_quirks;
+ x86_add_quirk(intel_clovertown_quirk);
case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
case 29: /* six-core 45 nm xeon "Dunnington" */
@@ -1651,17 +1693,8 @@
/* UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
- if (ebx & 0x40) {
- /*
- * Erratum AAJ80 detected, we work it around by using
- * the BR_MISP_EXEC.ANY event. This will over-count
- * branch-misses, but it's still much better than the
- * architectural event which is often completely bogus:
- */
- intel_perfmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x7f89;
+ x86_add_quirk(intel_nehalem_quirk);
- pr_cont("erratum AAJ80 worked around, ");
- }
pr_cont("Nehalem events, ");
break;
@@ -1701,7 +1734,7 @@
break;
case 42: /* SandyBridge */
- x86_pmu.quirks = intel_sandybridge_quirks;
+ x86_add_quirk(intel_sandybridge_quirk);
case 45: /* SandyBridge, "Romely-EP" */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -1738,5 +1771,6 @@
break;
}
}
+
return 0;
}
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 65ffd11..303a0e4 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -135,7 +135,6 @@
printk(KERN_CONT "(usable)");
break;
case E820_RESERVED:
- case E820_RESERVED_EFI:
printk(KERN_CONT "(reserved)");
break;
case E820_ACPI:
@@ -784,7 +783,7 @@
/*
* Find the highest page frame number we have available
*/
-unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
{
int i;
unsigned long last_pfn = 0;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index ea9d5f2f..2889b3d 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -50,7 +50,7 @@
put_online_cpus();
}
-void arch_jump_label_transform_static(struct jump_entry *entry,
+__init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type)
{
__jump_label_transform(entry, type, text_poke_early);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9a9e40f..cf0ef98 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -691,8 +691,6 @@
void __init setup_arch(char **cmdline_p)
{
- unsigned long end_pfn;
-
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
visws_early_detect();
@@ -934,24 +932,7 @@
init_gbpages();
/* max_pfn_mapped is updated here */
- end_pfn = max_low_pfn;
-
-#ifdef CONFIG_X86_64
- /*
- * There may be regions after the last E820_RAM region that we
- * want to include in the kernel direct mapping, such as
- * EFI_RUNTIME_SERVICES_DATA.
- */
- if (efi_enabled) {
- unsigned long efi_end;
-
- efi_end = e820_end_pfn(MAXMEM>>PAGE_SHIFT, E820_RESERVED_EFI);
- if (efi_end > max_low_pfn)
- end_pfn = efi_end;
- }
-#endif
-
- max_low_pfn_mapped = init_memory_mapping(0, end_pfn << PAGE_SHIFT);
+ max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
max_pfn_mapped = max_low_pfn_mapped;
#ifdef CONFIG_X86_64
diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c
index 46fc4ee..88ad5fb 100644
--- a/arch/x86/lib/inat.c
+++ b/arch/x86/lib/inat.c
@@ -82,9 +82,16 @@
const insn_attr_t *table;
if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
return 0;
- table = inat_avx_tables[vex_m][vex_p];
+ /* At first, this checks the master table */
+ table = inat_avx_tables[vex_m][0];
if (!table)
return 0;
+ if (!inat_is_group(table[opcode]) && vex_p) {
+ /* If this is not a group, get attribute directly */
+ table = inat_avx_tables[vex_m][vex_p];
+ if (!table)
+ return 0;
+ }
return table[opcode];
}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 374562e..5a1f9f3 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -202,7 +202,7 @@
m = insn_vex_m_bits(insn);
p = insn_vex_p_bits(insn);
insn->attr = inat_get_avx_attribute(op, m, p);
- if (!inat_accept_vex(insn->attr))
+ if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
insn->attr = 0; /* This instruction is bad */
goto end; /* VEX has only 1 byte for opcode */
}
@@ -249,6 +249,8 @@
pfx = insn_last_prefix(insn);
insn->attr = inat_get_group_attribute(mod, pfx,
insn->attr);
+ if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
+ insn->attr = 0; /* This is bad */
}
}
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index a793da5..5b83c51 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1,5 +1,11 @@
# x86 Opcode Maps
#
+# This is (mostly) based on following documentations.
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2
+# (#325383-040US, October 2011)
+# - Intel(R) Advanced Vector Extensions Programming Reference
+# (#319433-011,JUNE 2011).
+#
#<Opcode maps>
# Table: table-name
# Referrer: escaped-name
@@ -15,10 +21,13 @@
# EndTable
#
# AVX Superscripts
-# (VEX): this opcode can accept VEX prefix.
-# (oVEX): this opcode requires VEX prefix.
-# (o128): this opcode only supports 128bit VEX.
-# (o256): this opcode only supports 256bit VEX.
+# (v): this opcode requires VEX prefix.
+# (v1): this opcode only supports 128bit VEX.
+#
+# Last Prefix Superscripts
+# - (66): the last prefix is 0x66
+# - (F3): the last prefix is 0xF3
+# - (F2): the last prefix is 0xF2
#
Table: one byte opcode
@@ -199,8 +208,8 @@
a1: MOV rAX,Ov
a2: MOV Ob,AL
a3: MOV Ov,rAX
-a4: MOVS/B Xb,Yb
-a5: MOVS/W/D/Q Xv,Yv
+a4: MOVS/B Yb,Xb
+a5: MOVS/W/D/Q Yv,Xv
a6: CMPS/B Xb,Yb
a7: CMPS/W/D Xv,Yv
a8: TEST AL,Ib
@@ -233,8 +242,8 @@
c1: Grp2 Ev,Ib (1A)
c2: RETN Iw (f64)
c3: RETN
-c4: LES Gz,Mp (i64) | 3bytes-VEX (Prefix)
-c5: LDS Gz,Mp (i64) | 2bytes-VEX (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
c6: Grp11 Eb,Ib (1A)
c7: Grp11 Ev,Iz (1A)
c8: ENTER Iw,Ib
@@ -320,14 +329,19 @@
# 3DNow! uses the last imm byte as opcode extension.
0f: 3DNow! Pq,Qq,Ib
# 0x0f 0x10-0x1f
-10: movups Vps,Wps (VEX) | movss Vss,Wss (F3),(VEX),(o128) | movupd Vpd,Wpd (66),(VEX) | movsd Vsd,Wsd (F2),(VEX),(o128)
-11: movups Wps,Vps (VEX) | movss Wss,Vss (F3),(VEX),(o128) | movupd Wpd,Vpd (66),(VEX) | movsd Wsd,Vsd (F2),(VEX),(o128)
-12: movlps Vq,Mq (VEX),(o128) | movlpd Vq,Mq (66),(VEX),(o128) | movhlps Vq,Uq (VEX),(o128) | movddup Vq,Wq (F2),(VEX) | movsldup Vq,Wq (F3),(VEX)
-13: mpvlps Mq,Vq (VEX),(o128) | movlpd Mq,Vq (66),(VEX),(o128)
-14: unpcklps Vps,Wq (VEX) | unpcklpd Vpd,Wq (66),(VEX)
-15: unpckhps Vps,Wq (VEX) | unpckhpd Vpd,Wq (66),(VEX)
-16: movhps Vq,Mq (VEX),(o128) | movhpd Vq,Mq (66),(VEX),(o128) | movlsps Vq,Uq (VEX),(o128) | movshdup Vq,Wq (F3),(VEX)
-17: movhps Mq,Vq (VEX),(o128) | movhpd Mq,Vq (66),(VEX),(o128)
+# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
+# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
+# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
+# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
+# Reference A.1
+10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
+11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
+12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
+13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
+14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
+15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
+16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
+17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
18: Grp16 (1A)
19:
1a:
@@ -345,14 +359,14 @@
25:
26:
27:
-28: movaps Vps,Wps (VEX) | movapd Vpd,Wpd (66),(VEX)
-29: movaps Wps,Vps (VEX) | movapd Wpd,Vpd (66),(VEX)
-2a: cvtpi2ps Vps,Qpi | cvtsi2ss Vss,Ed/q (F3),(VEX),(o128) | cvtpi2pd Vpd,Qpi (66) | cvtsi2sd Vsd,Ed/q (F2),(VEX),(o128)
-2b: movntps Mps,Vps (VEX) | movntpd Mpd,Vpd (66),(VEX)
-2c: cvttps2pi Ppi,Wps | cvttss2si Gd/q,Wss (F3),(VEX),(o128) | cvttpd2pi Ppi,Wpd (66) | cvttsd2si Gd/q,Wsd (F2),(VEX),(o128)
-2d: cvtps2pi Ppi,Wps | cvtss2si Gd/q,Wss (F3),(VEX),(o128) | cvtpd2pi Qpi,Wpd (66) | cvtsd2si Gd/q,Wsd (F2),(VEX),(o128)
-2e: ucomiss Vss,Wss (VEX),(o128) | ucomisd Vsd,Wsd (66),(VEX),(o128)
-2f: comiss Vss,Wss (VEX),(o128) | comisd Vsd,Wsd (66),(VEX),(o128)
+28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
+29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
+2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
+2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
+2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
+2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
+2e: vucomiss Vss,Wss (v1) | vucomisd Vsd,Wsd (66),(v1)
+2f: vcomiss Vss,Wss (v1) | vcomisd Vsd,Wsd (66),(v1)
# 0x0f 0x30-0x3f
30: WRMSR
31: RDTSC
@@ -388,65 +402,66 @@
4e: CMOVLE/NG Gv,Ev
4f: CMOVNLE/G Gv,Ev
# 0x0f 0x50-0x5f
-50: movmskps Gd/q,Ups (VEX) | movmskpd Gd/q,Upd (66),(VEX)
-51: sqrtps Vps,Wps (VEX) | sqrtss Vss,Wss (F3),(VEX),(o128) | sqrtpd Vpd,Wpd (66),(VEX) | sqrtsd Vsd,Wsd (F2),(VEX),(o128)
-52: rsqrtps Vps,Wps (VEX) | rsqrtss Vss,Wss (F3),(VEX),(o128)
-53: rcpps Vps,Wps (VEX) | rcpss Vss,Wss (F3),(VEX),(o128)
-54: andps Vps,Wps (VEX) | andpd Vpd,Wpd (66),(VEX)
-55: andnps Vps,Wps (VEX) | andnpd Vpd,Wpd (66),(VEX)
-56: orps Vps,Wps (VEX) | orpd Vpd,Wpd (66),(VEX)
-57: xorps Vps,Wps (VEX) | xorpd Vpd,Wpd (66),(VEX)
-58: addps Vps,Wps (VEX) | addss Vss,Wss (F3),(VEX),(o128) | addpd Vpd,Wpd (66),(VEX) | addsd Vsd,Wsd (F2),(VEX),(o128)
-59: mulps Vps,Wps (VEX) | mulss Vss,Wss (F3),(VEX),(o128) | mulpd Vpd,Wpd (66),(VEX) | mulsd Vsd,Wsd (F2),(VEX),(o128)
-5a: cvtps2pd Vpd,Wps (VEX) | cvtss2sd Vsd,Wss (F3),(VEX),(o128) | cvtpd2ps Vps,Wpd (66),(VEX) | cvtsd2ss Vsd,Wsd (F2),(VEX),(o128)
-5b: cvtdq2ps Vps,Wdq (VEX) | cvtps2dq Vdq,Wps (66),(VEX) | cvttps2dq Vdq,Wps (F3),(VEX)
-5c: subps Vps,Wps (VEX) | subss Vss,Wss (F3),(VEX),(o128) | subpd Vpd,Wpd (66),(VEX) | subsd Vsd,Wsd (F2),(VEX),(o128)
-5d: minps Vps,Wps (VEX) | minss Vss,Wss (F3),(VEX),(o128) | minpd Vpd,Wpd (66),(VEX) | minsd Vsd,Wsd (F2),(VEX),(o128)
-5e: divps Vps,Wps (VEX) | divss Vss,Wss (F3),(VEX),(o128) | divpd Vpd,Wpd (66),(VEX) | divsd Vsd,Wsd (F2),(VEX),(o128)
-5f: maxps Vps,Wps (VEX) | maxss Vss,Wss (F3),(VEX),(o128) | maxpd Vpd,Wpd (66),(VEX) | maxsd Vsd,Wsd (F2),(VEX),(o128)
+50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
+51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
+52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
+53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
+54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
+55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
+56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
+57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
+58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
+59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
+5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
+5b: vcvtdq2ps Vps,Wdq | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
+5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
+5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
+5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
# 0x0f 0x60-0x6f
-60: punpcklbw Pq,Qd | punpcklbw Vdq,Wdq (66),(VEX),(o128)
-61: punpcklwd Pq,Qd | punpcklwd Vdq,Wdq (66),(VEX),(o128)
-62: punpckldq Pq,Qd | punpckldq Vdq,Wdq (66),(VEX),(o128)
-63: packsswb Pq,Qq | packsswb Vdq,Wdq (66),(VEX),(o128)
-64: pcmpgtb Pq,Qq | pcmpgtb Vdq,Wdq (66),(VEX),(o128)
-65: pcmpgtw Pq,Qq | pcmpgtw Vdq,Wdq (66),(VEX),(o128)
-66: pcmpgtd Pq,Qq | pcmpgtd Vdq,Wdq (66),(VEX),(o128)
-67: packuswb Pq,Qq | packuswb Vdq,Wdq (66),(VEX),(o128)
-68: punpckhbw Pq,Qd | punpckhbw Vdq,Wdq (66),(VEX),(o128)
-69: punpckhwd Pq,Qd | punpckhwd Vdq,Wdq (66),(VEX),(o128)
-6a: punpckhdq Pq,Qd | punpckhdq Vdq,Wdq (66),(VEX),(o128)
-6b: packssdw Pq,Qd | packssdw Vdq,Wdq (66),(VEX),(o128)
-6c: punpcklqdq Vdq,Wdq (66),(VEX),(o128)
-6d: punpckhqdq Vdq,Wdq (66),(VEX),(o128)
-6e: movd/q/ Pd,Ed/q | movd/q Vdq,Ed/q (66),(VEX),(o128)
-6f: movq Pq,Qq | movdqa Vdq,Wdq (66),(VEX) | movdqu Vdq,Wdq (F3),(VEX)
+60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
+61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
+62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
+63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
+64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
+65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
+66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
+67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
+68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
+69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
+6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
+6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
+6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
+6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
+6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqu Vx,Wx (F3)
# 0x0f 0x70-0x7f
-70: pshufw Pq,Qq,Ib | pshufd Vdq,Wdq,Ib (66),(VEX),(o128) | pshufhw Vdq,Wdq,Ib (F3),(VEX),(o128) | pshuflw VdqWdq,Ib (F2),(VEX),(o128)
+70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
71: Grp12 (1A)
72: Grp13 (1A)
73: Grp14 (1A)
-74: pcmpeqb Pq,Qq | pcmpeqb Vdq,Wdq (66),(VEX),(o128)
-75: pcmpeqw Pq,Qq | pcmpeqw Vdq,Wdq (66),(VEX),(o128)
-76: pcmpeqd Pq,Qq | pcmpeqd Vdq,Wdq (66),(VEX),(o128)
-77: emms/vzeroupper/vzeroall (VEX)
-78: VMREAD Ed/q,Gd/q
-79: VMWRITE Gd/q,Ed/q
+74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
+75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
+76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
+# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
+77: emms | vzeroupper | vzeroall
+78: VMREAD Ey,Gy
+79: VMWRITE Gy,Ey
7a:
7b:
-7c: haddps Vps,Wps (F2),(VEX) | haddpd Vpd,Wpd (66),(VEX)
-7d: hsubps Vps,Wps (F2),(VEX) | hsubpd Vpd,Wpd (66),(VEX)
-7e: movd/q Ed/q,Pd | movd/q Ed/q,Vdq (66),(VEX),(o128) | movq Vq,Wq (F3),(VEX),(o128)
-7f: movq Qq,Pq | movdqa Wdq,Vdq (66),(VEX) | movdqu Wdq,Vdq (F3),(VEX)
+7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
+7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
+7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
+7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3)
# 0x0f 0x80-0x8f
80: JO Jz (f64)
81: JNO Jz (f64)
-82: JB/JNAE/JC Jz (f64)
-83: JNB/JAE/JNC Jz (f64)
-84: JZ/JE Jz (f64)
-85: JNZ/JNE Jz (f64)
+82: JB/JC/JNAE Jz (f64)
+83: JAE/JNB/JNC Jz (f64)
+84: JE/JZ Jz (f64)
+85: JNE/JNZ Jz (f64)
86: JBE/JNA Jz (f64)
-87: JNBE/JA Jz (f64)
+87: JA/JNBE Jz (f64)
88: JS Jz (f64)
89: JNS Jz (f64)
8a: JP/JPE Jz (f64)
@@ -502,18 +517,18 @@
b9: Grp10 (1A)
ba: Grp8 Ev,Ib (1A)
bb: BTC Ev,Gv
-bc: BSF Gv,Ev
-bd: BSR Gv,Ev
+bc: BSF Gv,Ev | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev | LZCNT Gv,Ev (F3)
be: MOVSX Gv,Eb
bf: MOVSX Gv,Ew
# 0x0f 0xc0-0xcf
c0: XADD Eb,Gb
c1: XADD Ev,Gv
-c2: cmpps Vps,Wps,Ib (VEX) | cmpss Vss,Wss,Ib (F3),(VEX),(o128) | cmppd Vpd,Wpd,Ib (66),(VEX) | cmpsd Vsd,Wsd,Ib (F2),(VEX)
-c3: movnti Md/q,Gd/q
-c4: pinsrw Pq,Rd/q/Mw,Ib | pinsrw Vdq,Rd/q/Mw,Ib (66),(VEX),(o128)
-c5: pextrw Gd,Nq,Ib | pextrw Gd,Udq,Ib (66),(VEX),(o128)
-c6: shufps Vps,Wps,Ib (VEX) | shufpd Vpd,Wpd,Ib (66),(VEX)
+c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
+c3: movnti My,Gy
+c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
+c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
+c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
c7: Grp9 (1A)
c8: BSWAP RAX/EAX/R8/R8D
c9: BSWAP RCX/ECX/R9/R9D
@@ -524,55 +539,55 @@
ce: BSWAP RSI/ESI/R14/R14D
cf: BSWAP RDI/EDI/R15/R15D
# 0x0f 0xd0-0xdf
-d0: addsubps Vps,Wps (F2),(VEX) | addsubpd Vpd,Wpd (66),(VEX)
-d1: psrlw Pq,Qq | psrlw Vdq,Wdq (66),(VEX),(o128)
-d2: psrld Pq,Qq | psrld Vdq,Wdq (66),(VEX),(o128)
-d3: psrlq Pq,Qq | psrlq Vdq,Wdq (66),(VEX),(o128)
-d4: paddq Pq,Qq | paddq Vdq,Wdq (66),(VEX),(o128)
-d5: pmullw Pq,Qq | pmullw Vdq,Wdq (66),(VEX),(o128)
-d6: movq Wq,Vq (66),(VEX),(o128) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
-d7: pmovmskb Gd,Nq | pmovmskb Gd,Udq (66),(VEX),(o128)
-d8: psubusb Pq,Qq | psubusb Vdq,Wdq (66),(VEX),(o128)
-d9: psubusw Pq,Qq | psubusw Vdq,Wdq (66),(VEX),(o128)
-da: pminub Pq,Qq | pminub Vdq,Wdq (66),(VEX),(o128)
-db: pand Pq,Qq | pand Vdq,Wdq (66),(VEX),(o128)
-dc: paddusb Pq,Qq | paddusb Vdq,Wdq (66),(VEX),(o128)
-dd: paddusw Pq,Qq | paddusw Vdq,Wdq (66),(VEX),(o128)
-de: pmaxub Pq,Qq | pmaxub Vdq,Wdq (66),(VEX),(o128)
-df: pandn Pq,Qq | pandn Vdq,Wdq (66),(VEX),(o128)
+d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
+d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
+d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
+d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
+d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
+d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
+d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
+d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
+d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
+da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1)
+dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
+dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
+de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1)
# 0x0f 0xe0-0xef
-e0: pavgb Pq,Qq | pavgb Vdq,Wdq (66),(VEX),(o128)
-e1: psraw Pq,Qq | psraw Vdq,Wdq (66),(VEX),(o128)
-e2: psrad Pq,Qq | psrad Vdq,Wdq (66),(VEX),(o128)
-e3: pavgw Pq,Qq | pavgw Vdq,Wdq (66),(VEX),(o128)
-e4: pmulhuw Pq,Qq | pmulhuw Vdq,Wdq (66),(VEX),(o128)
-e5: pmulhw Pq,Qq | pmulhw Vdq,Wdq (66),(VEX),(o128)
-e6: cvtpd2dq Vdq,Wpd (F2),(VEX) | cvttpd2dq Vdq,Wpd (66),(VEX) | cvtdq2pd Vpd,Wdq (F3),(VEX)
-e7: movntq Mq,Pq | movntdq Mdq,Vdq (66),(VEX)
-e8: psubsb Pq,Qq | psubsb Vdq,Wdq (66),(VEX),(o128)
-e9: psubsw Pq,Qq | psubsw Vdq,Wdq (66),(VEX),(o128)
-ea: pminsw Pq,Qq | pminsw Vdq,Wdq (66),(VEX),(o128)
-eb: por Pq,Qq | por Vdq,Wdq (66),(VEX),(o128)
-ec: paddsb Pq,Qq | paddsb Vdq,Wdq (66),(VEX),(o128)
-ed: paddsw Pq,Qq | paddsw Vdq,Wdq (66),(VEX),(o128)
-ee: pmaxsw Pq,Qq | pmaxsw Vdq,Wdq (66),(VEX),(o128)
-ef: pxor Pq,Qq | pxor Vdq,Wdq (66),(VEX),(o128)
+e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
+e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
+e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
+e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
+e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
+e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtpd2dq Vx,Wpd (F2)
+e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
+e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
+e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
+ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1)
+ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
+ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
+ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1)
# 0x0f 0xf0-0xff
-f0: lddqu Vdq,Mdq (F2),(VEX)
-f1: psllw Pq,Qq | psllw Vdq,Wdq (66),(VEX),(o128)
-f2: pslld Pq,Qq | pslld Vdq,Wdq (66),(VEX),(o128)
-f3: psllq Pq,Qq | psllq Vdq,Wdq (66),(VEX),(o128)
-f4: pmuludq Pq,Qq | pmuludq Vdq,Wdq (66),(VEX),(o128)
-f5: pmaddwd Pq,Qq | pmaddwd Vdq,Wdq (66),(VEX),(o128)
-f6: psadbw Pq,Qq | psadbw Vdq,Wdq (66),(VEX),(o128)
-f7: maskmovq Pq,Nq | maskmovdqu Vdq,Udq (66),(VEX),(o128)
-f8: psubb Pq,Qq | psubb Vdq,Wdq (66),(VEX),(o128)
-f9: psubw Pq,Qq | psubw Vdq,Wdq (66),(VEX),(o128)
-fa: psubd Pq,Qq | psubd Vdq,Wdq (66),(VEX),(o128)
-fb: psubq Pq,Qq | psubq Vdq,Wdq (66),(VEX),(o128)
-fc: paddb Pq,Qq | paddb Vdq,Wdq (66),(VEX),(o128)
-fd: paddw Pq,Qq | paddw Vdq,Wdq (66),(VEX),(o128)
-fe: paddd Pq,Qq | paddd Vdq,Wdq (66),(VEX),(o128)
+f0: vlddqu Vx,Mx (F2)
+f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
+f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
+f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
+f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
+f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
+f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
+f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
+f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
+f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
+fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
+fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
+fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
+fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
+fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
ff:
EndTable
@@ -580,155 +595,193 @@
Referrer: 3-byte escape 1
AVXcode: 2
# 0x0f 0x38 0x00-0x0f
-00: pshufb Pq,Qq | pshufb Vdq,Wdq (66),(VEX),(o128)
-01: phaddw Pq,Qq | phaddw Vdq,Wdq (66),(VEX),(o128)
-02: phaddd Pq,Qq | phaddd Vdq,Wdq (66),(VEX),(o128)
-03: phaddsw Pq,Qq | phaddsw Vdq,Wdq (66),(VEX),(o128)
-04: pmaddubsw Pq,Qq | pmaddubsw Vdq,Wdq (66),(VEX),(o128)
-05: phsubw Pq,Qq | phsubw Vdq,Wdq (66),(VEX),(o128)
-06: phsubd Pq,Qq | phsubd Vdq,Wdq (66),(VEX),(o128)
-07: phsubsw Pq,Qq | phsubsw Vdq,Wdq (66),(VEX),(o128)
-08: psignb Pq,Qq | psignb Vdq,Wdq (66),(VEX),(o128)
-09: psignw Pq,Qq | psignw Vdq,Wdq (66),(VEX),(o128)
-0a: psignd Pq,Qq | psignd Vdq,Wdq (66),(VEX),(o128)
-0b: pmulhrsw Pq,Qq | pmulhrsw Vdq,Wdq (66),(VEX),(o128)
-0c: Vpermilps /r (66),(oVEX)
-0d: Vpermilpd /r (66),(oVEX)
-0e: vtestps /r (66),(oVEX)
-0f: vtestpd /r (66),(oVEX)
+00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
+01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
+02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
+03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
+04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
+05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
+06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
+07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
+08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
+09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
+0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
+0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
+0c: vpermilps Vx,Hx,Wx (66),(v)
+0d: vpermilpd Vx,Hx,Wx (66),(v)
+0e: vtestps Vx,Wx (66),(v)
+0f: vtestpd Vx,Wx (66),(v)
# 0x0f 0x38 0x10-0x1f
10: pblendvb Vdq,Wdq (66)
11:
12:
-13:
+13: vcvtph2ps Vx,Wx,Ib (66),(v)
14: blendvps Vdq,Wdq (66)
15: blendvpd Vdq,Wdq (66)
-16:
-17: ptest Vdq,Wdq (66),(VEX)
-18: vbroadcastss /r (66),(oVEX)
-19: vbroadcastsd /r (66),(oVEX),(o256)
-1a: vbroadcastf128 /r (66),(oVEX),(o256)
+16: vpermps Vqq,Hqq,Wqq (66),(v)
+17: vptest Vx,Wx (66)
+18: vbroadcastss Vx,Wd (66),(v)
+19: vbroadcastsd Vqq,Wq (66),(v)
+1a: vbroadcastf128 Vqq,Mdq (66),(v)
1b:
-1c: pabsb Pq,Qq | pabsb Vdq,Wdq (66),(VEX),(o128)
-1d: pabsw Pq,Qq | pabsw Vdq,Wdq (66),(VEX),(o128)
-1e: pabsd Pq,Qq | pabsd Vdq,Wdq (66),(VEX),(o128)
+1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
+1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
+1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
1f:
# 0x0f 0x38 0x20-0x2f
-20: pmovsxbw Vdq,Udq/Mq (66),(VEX),(o128)
-21: pmovsxbd Vdq,Udq/Md (66),(VEX),(o128)
-22: pmovsxbq Vdq,Udq/Mw (66),(VEX),(o128)
-23: pmovsxwd Vdq,Udq/Mq (66),(VEX),(o128)
-24: pmovsxwq Vdq,Udq/Md (66),(VEX),(o128)
-25: pmovsxdq Vdq,Udq/Mq (66),(VEX),(o128)
+20: vpmovsxbw Vx,Ux/Mq (66),(v1)
+21: vpmovsxbd Vx,Ux/Md (66),(v1)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1)
+24: vpmovsxwq Vx,Ux/Md (66),(v1)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1)
26:
27:
-28: pmuldq Vdq,Wdq (66),(VEX),(o128)
-29: pcmpeqq Vdq,Wdq (66),(VEX),(o128)
-2a: movntdqa Vdq,Mdq (66),(VEX),(o128)
-2b: packusdw Vdq,Wdq (66),(VEX),(o128)
-2c: vmaskmovps(ld) /r (66),(oVEX)
-2d: vmaskmovpd(ld) /r (66),(oVEX)
-2e: vmaskmovps(st) /r (66),(oVEX)
-2f: vmaskmovpd(st) /r (66),(oVEX)
+28: vpmuldq Vx,Hx,Wx (66),(v1)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1)
+2a: vmovntdqa Vx,Mx (66),(v1)
+2b: vpackusdw Vx,Hx,Wx (66),(v1)
+2c: vmaskmovps Vx,Hx,Mx (66),(v)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v)
+2e: vmaskmovps Mx,Hx,Vx (66),(v)
+2f: vmaskmovpd Mx,Hx,Vx (66),(v)
# 0x0f 0x38 0x30-0x3f
-30: pmovzxbw Vdq,Udq/Mq (66),(VEX),(o128)
-31: pmovzxbd Vdq,Udq/Md (66),(VEX),(o128)
-32: pmovzxbq Vdq,Udq/Mw (66),(VEX),(o128)
-33: pmovzxwd Vdq,Udq/Mq (66),(VEX),(o128)
-34: pmovzxwq Vdq,Udq/Md (66),(VEX),(o128)
-35: pmovzxdq Vdq,Udq/Mq (66),(VEX),(o128)
-36:
-37: pcmpgtq Vdq,Wdq (66),(VEX),(o128)
-38: pminsb Vdq,Wdq (66),(VEX),(o128)
-39: pminsd Vdq,Wdq (66),(VEX),(o128)
-3a: pminuw Vdq,Wdq (66),(VEX),(o128)
-3b: pminud Vdq,Wdq (66),(VEX),(o128)
-3c: pmaxsb Vdq,Wdq (66),(VEX),(o128)
-3d: pmaxsd Vdq,Wdq (66),(VEX),(o128)
-3e: pmaxuw Vdq,Wdq (66),(VEX),(o128)
-3f: pmaxud Vdq,Wdq (66),(VEX),(o128)
+30: vpmovzxbw Vx,Ux/Mq (66),(v1)
+31: vpmovzxbd Vx,Ux/Md (66),(v1)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1)
+34: vpmovzxwq Vx,Ux/Md (66),(v1)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1)
+36: vpermd Vqq,Hqq,Wqq (66),(v)
+37: vpcmpgtq Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1)
+39: vpminsd Vx,Hx,Wx (66),(v1)
+3a: vpminuw Vx,Hx,Wx (66),(v1)
+3b: vpminud Vx,Hx,Wx (66),(v1)
+3c: vpmaxsb Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1)
+3e: vpmaxuw Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1)
# 0x0f 0x38 0x40-0x8f
-40: pmulld Vdq,Wdq (66),(VEX),(o128)
-41: phminposuw Vdq,Wdq (66),(VEX),(o128)
-80: INVEPT Gd/q,Mdq (66)
-81: INVPID Gd/q,Mdq (66)
+40: vpmulld Vx,Hx,Wx (66),(v1)
+41: vphminposuw Vdq,Wdq (66),(v1)
+42:
+43:
+44:
+45: vpsrlvd/q Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v)
+47: vpsllvd/q Vx,Hx,Wx (66),(v)
+# Skip 0x48-0x57
+58: vpbroadcastd Vx,Wx (66),(v)
+59: vpbroadcastq Vx,Wx (66),(v)
+5a: vbroadcasti128 Vqq,Mdq (66),(v)
+# Skip 0x5b-0x77
+78: vpbroadcastb Vx,Wx (66),(v)
+79: vpbroadcastw Vx,Wx (66),(v)
+# Skip 0x7a-0x7f
+80: INVEPT Gy,Mdq (66)
+81: INVPID Gy,Mdq (66)
+82: INVPCID Gy,Mdq (66)
+8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
# 0x0f 0x38 0x90-0xbf (FMA)
-96: vfmaddsub132pd/ps /r (66),(VEX)
-97: vfmsubadd132pd/ps /r (66),(VEX)
-98: vfmadd132pd/ps /r (66),(VEX)
-99: vfmadd132sd/ss /r (66),(VEX),(o128)
-9a: vfmsub132pd/ps /r (66),(VEX)
-9b: vfmsub132sd/ss /r (66),(VEX),(o128)
-9c: vfnmadd132pd/ps /r (66),(VEX)
-9d: vfnmadd132sd/ss /r (66),(VEX),(o128)
-9e: vfnmsub132pd/ps /r (66),(VEX)
-9f: vfnmsub132sd/ss /r (66),(VEX),(o128)
-a6: vfmaddsub213pd/ps /r (66),(VEX)
-a7: vfmsubadd213pd/ps /r (66),(VEX)
-a8: vfmadd213pd/ps /r (66),(VEX)
-a9: vfmadd213sd/ss /r (66),(VEX),(o128)
-aa: vfmsub213pd/ps /r (66),(VEX)
-ab: vfmsub213sd/ss /r (66),(VEX),(o128)
-ac: vfnmadd213pd/ps /r (66),(VEX)
-ad: vfnmadd213sd/ss /r (66),(VEX),(o128)
-ae: vfnmsub213pd/ps /r (66),(VEX)
-af: vfnmsub213sd/ss /r (66),(VEX),(o128)
-b6: vfmaddsub231pd/ps /r (66),(VEX)
-b7: vfmsubadd231pd/ps /r (66),(VEX)
-b8: vfmadd231pd/ps /r (66),(VEX)
-b9: vfmadd231sd/ss /r (66),(VEX),(o128)
-ba: vfmsub231pd/ps /r (66),(VEX)
-bb: vfmsub231sd/ss /r (66),(VEX),(o128)
-bc: vfnmadd231pd/ps /r (66),(VEX)
-bd: vfnmadd231sd/ss /r (66),(VEX),(o128)
-be: vfnmsub231pd/ps /r (66),(VEX)
-bf: vfnmsub231sd/ss /r (66),(VEX),(o128)
+90: vgatherdd/q Vx,Hx,Wx (66),(v)
+91: vgatherqd/q Vx,Hx,Wx (66),(v)
+92: vgatherdps/d Vx,Hx,Wx (66),(v)
+93: vgatherqps/d Vx,Hx,Wx (66),(v)
+94:
+95:
+96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
+97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
+98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
+99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
+9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
+9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
+a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
+a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
+a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
+ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
+af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
+b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
+b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
+b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
+bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
+bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
+bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
# 0x0f 0x38 0xc0-0xff
-db: aesimc Vdq,Wdq (66),(VEX),(o128)
-dc: aesenc Vdq,Wdq (66),(VEX),(o128)
-dd: aesenclast Vdq,Wdq (66),(VEX),(o128)
-de: aesdec Vdq,Wdq (66),(VEX),(o128)
-df: aesdeclast Vdq,Wdq (66),(VEX),(o128)
-f0: MOVBE Gv,Mv | CRC32 Gd,Eb (F2)
-f1: MOVBE Mv,Gv | CRC32 Gd,Ev (F2)
+db: VAESIMC Vdq,Wdq (66),(v1)
+dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
+dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
+de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
+df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
+f3: ANDN Gy,By,Ey (v)
+f4: Grp17 (1A)
+f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
+f6: MULX By,Gy,rDX,Ey (F2),(v)
+f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
EndTable
Table: 3-byte opcode 2 (0x0f 0x3a)
Referrer: 3-byte escape 2
AVXcode: 3
# 0x0f 0x3a 0x00-0xff
-04: vpermilps /r,Ib (66),(oVEX)
-05: vpermilpd /r,Ib (66),(oVEX)
-06: vperm2f128 /r,Ib (66),(oVEX),(o256)
-08: roundps Vdq,Wdq,Ib (66),(VEX)
-09: roundpd Vdq,Wdq,Ib (66),(VEX)
-0a: roundss Vss,Wss,Ib (66),(VEX),(o128)
-0b: roundsd Vsd,Wsd,Ib (66),(VEX),(o128)
-0c: blendps Vdq,Wdq,Ib (66),(VEX)
-0d: blendpd Vdq,Wdq,Ib (66),(VEX)
-0e: pblendw Vdq,Wdq,Ib (66),(VEX),(o128)
-0f: palignr Pq,Qq,Ib | palignr Vdq,Wdq,Ib (66),(VEX),(o128)
-14: pextrb Rd/Mb,Vdq,Ib (66),(VEX),(o128)
-15: pextrw Rd/Mw,Vdq,Ib (66),(VEX),(o128)
-16: pextrd/pextrq Ed/q,Vdq,Ib (66),(VEX),(o128)
-17: extractps Ed,Vdq,Ib (66),(VEX),(o128)
-18: vinsertf128 /r,Ib (66),(oVEX),(o256)
-19: vextractf128 /r,Ib (66),(oVEX),(o256)
-20: pinsrb Vdq,Rd/q/Mb,Ib (66),(VEX),(o128)
-21: insertps Vdq,Udq/Md,Ib (66),(VEX),(o128)
-22: pinsrd/pinsrq Vdq,Ed/q,Ib (66),(VEX),(o128)
-40: dpps Vdq,Wdq,Ib (66),(VEX)
-41: dppd Vdq,Wdq,Ib (66),(VEX),(o128)
-42: mpsadbw Vdq,Wdq,Ib (66),(VEX),(o128)
-44: pclmulq Vdq,Wdq,Ib (66),(VEX),(o128)
-4a: vblendvps /r,Ib (66),(oVEX)
-4b: vblendvpd /r,Ib (66),(oVEX)
-4c: vpblendvb /r,Ib (66),(oVEX),(o128)
-60: pcmpestrm Vdq,Wdq,Ib (66),(VEX),(o128)
-61: pcmpestri Vdq,Wdq,Ib (66),(VEX),(o128)
-62: pcmpistrm Vdq,Wdq,Ib (66),(VEX),(o128)
-63: pcmpistri Vdq,Wdq,Ib (66),(VEX),(o128)
-df: aeskeygenassist Vdq,Wdq,Ib (66),(VEX),(o128)
+00: vpermq Vqq,Wqq,Ib (66),(v)
+01: vpermpd Vqq,Wqq,Ib (66),(v)
+02: vpblendd Vx,Hx,Wx,Ib (66),(v)
+03:
+04: vpermilps Vx,Wx,Ib (66),(v)
+05: vpermilpd Vx,Wx,Ib (66),(v)
+06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
+07:
+08: vroundps Vx,Wx,Ib (66)
+09: vroundpd Vx,Wx,Ib (66)
+0a: vroundss Vss,Wss,Ib (66),(v1)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1)
+0c: vblendps Vx,Hx,Wx,Ib (66)
+0d: vblendpd Vx,Hx,Wx,Ib (66)
+0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
+0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
+14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
+15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
+16: vpextrd/q Ey,Vdq,Ib (66),(v1)
+17: vextractps Ed,Vdq,Ib (66),(v1)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v)
+19: vextractf128 Wdq,Vqq,Ib (66),(v)
+1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
+21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
+22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
+39: vextracti128 Wdq,Vqq,Ib (66),(v)
+40: vdpps Vx,Hx,Wx,Ib (66)
+41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1)
+44: vpclmulqdq Vdq,Hdq,Wdq,Ib (66),(v1)
+46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
+4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
+4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
+4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
+61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
+62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
+63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
+f0: RORX Gy,Ey,Ib (F2),(v)
EndTable
GrpTable: Grp1
@@ -790,7 +843,7 @@
2: CALLN Ev (f64)
3: CALLF Ep
4: JMPN Ev (f64)
-5: JMPF Ep
+5: JMPF Mp
6: PUSH Ev (d64)
7:
EndTable
@@ -807,7 +860,7 @@
GrpTable: Grp7
0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B)
3: LIDT Ms
4: SMSW Mw/Rv
5:
@@ -824,44 +877,45 @@
GrpTable: Grp9
1: CMPXCHG8B/16B Mq/Mdq
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3)
-7: VMPTRST Mq
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
+7: VMPTRST Mq | VMPTRST Mq (F3)
EndTable
GrpTable: Grp10
EndTable
GrpTable: Grp11
+# Note: the operands are given by group opcode
0: MOV
EndTable
GrpTable: Grp12
-2: psrlw Nq,Ib (11B) | psrlw Udq,Ib (66),(11B),(VEX),(o128)
-4: psraw Nq,Ib (11B) | psraw Udq,Ib (66),(11B),(VEX),(o128)
-6: psllw Nq,Ib (11B) | psllw Udq,Ib (66),(11B),(VEX),(o128)
+2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
+4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
+6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
EndTable
GrpTable: Grp13
-2: psrld Nq,Ib (11B) | psrld Udq,Ib (66),(11B),(VEX),(o128)
-4: psrad Nq,Ib (11B) | psrad Udq,Ib (66),(11B),(VEX),(o128)
-6: pslld Nq,Ib (11B) | pslld Udq,Ib (66),(11B),(VEX),(o128)
+2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1)
+6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
EndTable
GrpTable: Grp14
-2: psrlq Nq,Ib (11B) | psrlq Udq,Ib (66),(11B),(VEX),(o128)
-3: psrldq Udq,Ib (66),(11B),(VEX),(o128)
-6: psllq Nq,Ib (11B) | psllq Udq,Ib (66),(11B),(VEX),(o128)
-7: pslldq Udq,Ib (66),(11B),(VEX),(o128)
+2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
+3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
+6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
+7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
EndTable
GrpTable: Grp15
-0: fxsave
-1: fxstor
-2: ldmxcsr (VEX)
-3: stmxcsr (VEX)
+0: fxsave | RDFSBASE Ry (F3),(11B)
+1: fxstor | RDGSBASE Ry (F3),(11B)
+2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
+3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
4: XSAVE
5: XRSTOR | lfence (11B)
-6: mfence (11B)
+6: XSAVEOPT | mfence (11B)
7: clflush | sfence (11B)
EndTable
@@ -872,6 +926,12 @@
3: prefetch T2
EndTable
+GrpTable: Grp17
+1: BLSR By,Ey (v)
+2: BLSMSK By,Ey (v)
+3: BLSI By,Ey (v)
+EndTable
+
# AMD's Prefetch Group
GrpTable: GrpP
0: PREFETCH
diff --git a/arch/x86/oprofile/Makefile b/arch/x86/oprofile/Makefile
index 446902b..1599f56 100644
--- a/arch/x86/oprofile/Makefile
+++ b/arch/x86/oprofile/Makefile
@@ -4,9 +4,8 @@
oprof.o cpu_buffer.o buffer_sync.o \
event_buffer.o oprofile_files.o \
oprofilefs.o oprofile_stats.o \
- timer_int.o )
+ timer_int.o nmi_timer_int.o )
oprofile-y := $(DRIVER_OBJS) init.o backtrace.o
oprofile-$(CONFIG_X86_LOCAL_APIC) += nmi_int.o op_model_amd.o \
op_model_ppro.o op_model_p4.o
-oprofile-$(CONFIG_X86_IO_APIC) += nmi_timer_int.o
diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c
index f148cf6..9e138d0 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -16,37 +16,23 @@
* with the NMI mode driver.
*/
+#ifdef CONFIG_X86_LOCAL_APIC
extern int op_nmi_init(struct oprofile_operations *ops);
-extern int op_nmi_timer_init(struct oprofile_operations *ops);
extern void op_nmi_exit(void);
-extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
+#else
+static int op_nmi_init(struct oprofile_operations *ops) { return -ENODEV; }
+static void op_nmi_exit(void) { }
+#endif
-static int nmi_timer;
+extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
int __init oprofile_arch_init(struct oprofile_operations *ops)
{
- int ret;
-
- ret = -ENODEV;
-
-#ifdef CONFIG_X86_LOCAL_APIC
- ret = op_nmi_init(ops);
-#endif
- nmi_timer = (ret != 0);
-#ifdef CONFIG_X86_IO_APIC
- if (nmi_timer)
- ret = op_nmi_timer_init(ops);
-#endif
ops->backtrace = x86_backtrace;
-
- return ret;
+ return op_nmi_init(ops);
}
-
void oprofile_arch_exit(void)
{
-#ifdef CONFIG_X86_LOCAL_APIC
- if (!nmi_timer)
- op_nmi_exit();
-#endif
+ op_nmi_exit();
}
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 75f9528..26b8a85 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -595,24 +595,36 @@
return 0;
}
-static int force_arch_perfmon;
-static int force_cpu_type(const char *str, struct kernel_param *kp)
+enum __force_cpu_type {
+ reserved = 0, /* do not force */
+ timer,
+ arch_perfmon,
+};
+
+static int force_cpu_type;
+
+static int set_cpu_type(const char *str, struct kernel_param *kp)
{
- if (!strcmp(str, "arch_perfmon")) {
- force_arch_perfmon = 1;
+ if (!strcmp(str, "timer")) {
+ force_cpu_type = timer;
+ printk(KERN_INFO "oprofile: forcing NMI timer mode\n");
+ } else if (!strcmp(str, "arch_perfmon")) {
+ force_cpu_type = arch_perfmon;
printk(KERN_INFO "oprofile: forcing architectural perfmon\n");
+ } else {
+ force_cpu_type = 0;
}
return 0;
}
-module_param_call(cpu_type, force_cpu_type, NULL, NULL, 0);
+module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
static int __init ppro_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
struct op_x86_model_spec *spec = &op_ppro_spec; /* default */
- if (force_arch_perfmon && cpu_has_arch_perfmon)
+ if (force_cpu_type == arch_perfmon && cpu_has_arch_perfmon)
return 0;
/*
@@ -679,6 +691,9 @@
if (!cpu_has_apic)
return -ENODEV;
+ if (force_cpu_type == timer)
+ return -ENODEV;
+
switch (vendor) {
case X86_VENDOR_AMD:
/* Needs to be at least an Athlon (or hammer in 32bit mode) */
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
deleted file mode 100644
index 7f8052c..0000000
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/**
- * @file nmi_timer_int.c
- *
- * @remark Copyright 2003 OProfile authors
- * @remark Read the file COPYING
- *
- * @author Zwane Mwaikambo <zwane@linuxpower.ca>
- */
-
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/oprofile.h>
-#include <linux/rcupdate.h>
-#include <linux/kdebug.h>
-
-#include <asm/nmi.h>
-#include <asm/apic.h>
-#include <asm/ptrace.h>
-
-static int profile_timer_exceptions_notify(unsigned int val, struct pt_regs *regs)
-{
- oprofile_add_sample(regs, 0);
- return NMI_HANDLED;
-}
-
-static int timer_start(void)
-{
- if (register_nmi_handler(NMI_LOCAL, profile_timer_exceptions_notify,
- 0, "oprofile-timer"))
- return 1;
- return 0;
-}
-
-
-static void timer_stop(void)
-{
- unregister_nmi_handler(NMI_LOCAL, "oprofile-timer");
- synchronize_sched(); /* Allow already-started NMIs to complete. */
-}
-
-
-int __init op_nmi_timer_init(struct oprofile_operations *ops)
-{
- ops->start = timer_start;
- ops->stop = timer_stop;
- ops->cpu_type = "timer";
- printk(KERN_INFO "oprofile: using NMI timer interrupt.\n");
- return 0;
-}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index c9718a1..37718f0 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -323,13 +323,10 @@
case EFI_UNUSABLE_MEMORY:
e820_type = E820_UNUSABLE;
break;
- case EFI_RUNTIME_SERVICES_DATA:
- e820_type = E820_RESERVED_EFI;
- break;
default:
/*
* EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE
- * EFI_MEMORY_MAPPED_IO
+ * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO
* EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE
*/
e820_type = E820_RESERVED;
@@ -674,21 +671,10 @@
end_pfn = PFN_UP(end);
if (end_pfn <= max_low_pfn_mapped
|| (end_pfn > (1UL << (32 - PAGE_SHIFT))
- && end_pfn <= max_pfn_mapped)) {
+ && end_pfn <= max_pfn_mapped))
va = __va(md->phys_addr);
-
- if (!(md->attribute & EFI_MEMORY_WB)) {
- addr = (u64) (unsigned long)va;
- npages = md->num_pages;
- memrange_efi_to_native(&addr, &npages);
- set_memory_uc(addr, npages);
- }
- } else {
- if (!(md->attribute & EFI_MEMORY_WB))
- va = ioremap_nocache(md->phys_addr, size);
- else
- va = ioremap_cache(md->phys_addr, size);
- }
+ else
+ va = efi_ioremap(md->phys_addr, size, md->type);
md->virt_addr = (u64) (unsigned long) va;
@@ -698,6 +684,13 @@
continue;
}
+ if (!(md->attribute & EFI_MEMORY_WB)) {
+ addr = md->virt_addr;
+ npages = md->num_pages;
+ memrange_efi_to_native(&addr, &npages);
+ set_memory_uc(addr, npages);
+ }
+
systab = (u64) (unsigned long) efi_phys.systab;
if (md->phys_addr <= systab && systab < end) {
systab += md->virt_addr - md->phys_addr;
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index e36bf71..40e4469 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -39,43 +39,14 @@
*/
static unsigned long efi_rt_eflags;
-static pgd_t efi_bak_pg_dir_pointer[2];
void efi_call_phys_prelog(void)
{
- unsigned long cr4;
- unsigned long temp;
struct desc_ptr gdt_descr;
local_irq_save(efi_rt_eflags);
- /*
- * If I don't have PAE, I should just duplicate two entries in page
- * directory. If I have PAE, I just need to duplicate one entry in
- * page directory.
- */
- cr4 = read_cr4_safe();
-
- if (cr4 & X86_CR4_PAE) {
- efi_bak_pg_dir_pointer[0].pgd =
- swapper_pg_dir[pgd_index(0)].pgd;
- swapper_pg_dir[0].pgd =
- swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
- } else {
- efi_bak_pg_dir_pointer[0].pgd =
- swapper_pg_dir[pgd_index(0)].pgd;
- efi_bak_pg_dir_pointer[1].pgd =
- swapper_pg_dir[pgd_index(0x400000)].pgd;
- swapper_pg_dir[pgd_index(0)].pgd =
- swapper_pg_dir[pgd_index(PAGE_OFFSET)].pgd;
- temp = PAGE_OFFSET + 0x400000;
- swapper_pg_dir[pgd_index(0x400000)].pgd =
- swapper_pg_dir[pgd_index(temp)].pgd;
- }
-
- /*
- * After the lock is released, the original page table is restored.
- */
+ load_cr3(initial_page_table);
__flush_tlb_all();
gdt_descr.address = __pa(get_cpu_gdt_table(0));
@@ -85,28 +56,13 @@
void efi_call_phys_epilog(void)
{
- unsigned long cr4;
struct desc_ptr gdt_descr;
gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
gdt_descr.size = GDT_SIZE - 1;
load_gdt(&gdt_descr);
- cr4 = read_cr4_safe();
-
- if (cr4 & X86_CR4_PAE) {
- swapper_pg_dir[pgd_index(0)].pgd =
- efi_bak_pg_dir_pointer[0].pgd;
- } else {
- swapper_pg_dir[pgd_index(0)].pgd =
- efi_bak_pg_dir_pointer[0].pgd;
- swapper_pg_dir[pgd_index(0x400000)].pgd =
- efi_bak_pg_dir_pointer[1].pgd;
- }
-
- /*
- * After the lock is released, the original page table is restored.
- */
+ load_cr3(swapper_pg_dir);
__flush_tlb_all();
local_irq_restore(efi_rt_eflags);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 312250c..ac3aa54 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -80,3 +80,20 @@
local_irq_restore(efi_flags);
early_code_mapping_set_exec(0);
}
+
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
+ u32 type)
+{
+ unsigned long last_map_pfn;
+
+ if (type == EFI_MEMORY_MAPPED_IO)
+ return ioremap(phys_addr, size);
+
+ last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
+ if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size) {
+ unsigned long top = last_map_pfn << PAGE_SHIFT;
+ efi_ioremap(top, size - (top - phys_addr), type);
+ }
+
+ return (void __iomem *)__va(phys_addr);
+}
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index f820826..d511aa9 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -18,14 +18,21 @@
quiet_cmd_posttest = TEST $@
cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(distill_awk) | $(obj)/test_get_len $(posttest_64bit) $(posttest_verbose)
-posttest: $(obj)/test_get_len vmlinux
- $(call cmd,posttest)
+quiet_cmd_sanitytest = TEST $@
+ cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000
-hostprogs-y := test_get_len
+posttest: $(obj)/test_get_len vmlinux $(obj)/insn_sanity
+ $(call cmd,posttest)
+ $(call cmd,sanitytest)
+
+hostprogs-y += test_get_len insn_sanity
# -I needed for generated C source and C source which in the kernel tree.
HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+
# Dependencies are also needed.
$(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+$(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index eaf11f5..5f6a5b6 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -47,7 +47,7 @@
sep_expr = "^\\|$"
group_expr = "^Grp[0-9A-Za-z]+"
- imm_expr = "^[IJAO][a-z]"
+ imm_expr = "^[IJAOL][a-z]"
imm_flag["Ib"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
imm_flag["Jb"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
imm_flag["Iw"] = "INAT_MAKE_IMM(INAT_IMM_WORD)"
@@ -59,6 +59,7 @@
imm_flag["Iv"] = "INAT_MAKE_IMM(INAT_IMM_VWORD)"
imm_flag["Ob"] = "INAT_MOFFSET"
imm_flag["Ov"] = "INAT_MOFFSET"
+ imm_flag["Lx"] = "INAT_MAKE_IMM(INAT_IMM_BYTE)"
modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
force64_expr = "\\([df]64\\)"
@@ -70,8 +71,12 @@
lprefix3_expr = "\\(F2\\)"
max_lprefix = 4
- vexok_expr = "\\(VEX\\)"
- vexonly_expr = "\\(oVEX\\)"
+ # All opcodes starting with lower-case 'v' or with (v1) superscript
+ # accepts VEX prefix
+ vexok_opcode_expr = "^v.*"
+ vexok_expr = "\\(v1\\)"
+ # All opcodes with (v) superscript supports *only* VEX prefix
+ vexonly_expr = "\\(v\\)"
prefix_expr = "\\(Prefix\\)"
prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
@@ -85,8 +90,8 @@
prefix_num["SEG=GS"] = "INAT_PFX_GS"
prefix_num["SEG=SS"] = "INAT_PFX_SS"
prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
- prefix_num["2bytes-VEX"] = "INAT_PFX_VEX2"
- prefix_num["3bytes-VEX"] = "INAT_PFX_VEX3"
+ prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
+ prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
clear_vars()
}
@@ -310,12 +315,10 @@
if (match(opcode, fpu_expr))
flags = add_flags(flags, "INAT_MODRM")
- # check VEX only code
+ # check VEX codes
if (match(ext, vexonly_expr))
flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
-
- # check VEX only code
- if (match(ext, vexok_expr))
+ else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
flags = add_flags(flags, "INAT_VEXOK")
# check prefixes
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
new file mode 100644
index 0000000..cc2f8c1
--- /dev/null
+++ b/arch/x86/tools/insn_sanity.c
@@ -0,0 +1,275 @@
+/*
+ * x86 decoder sanity test - based on test_get_insn.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2009
+ * Copyright (C) Hitachi, Ltd., 2011
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <assert.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#define unlikely(cond) (cond)
+#define ARRAY_SIZE(a) (sizeof(a)/sizeof(a[0]))
+
+#include <asm/insn.h>
+#include <inat.c>
+#include <insn.c>
+
+/*
+ * Test of instruction analysis against tampering.
+ * Feed random binary to instruction decoder and ensure not to
+ * access out-of-instruction-buffer.
+ */
+
+#define DEFAULT_MAX_ITER 10000
+#define INSN_NOP 0x90
+
+static const char *prog; /* Program name */
+static int verbose; /* Verbosity */
+static int x86_64; /* x86-64 bit mode flag */
+static unsigned int seed; /* Random seed */
+static unsigned long iter_start; /* Start of iteration number */
+static unsigned long iter_end = DEFAULT_MAX_ITER; /* End of iteration number */
+static FILE *input_file; /* Input file name */
+
+static void usage(const char *err)
+{
+ if (err)
+ fprintf(stderr, "Error: %s\n\n", err);
+ fprintf(stderr, "Usage: %s [-y|-n|-v] [-s seed[,no]] [-m max] [-i input]\n", prog);
+ fprintf(stderr, "\t-y 64bit mode\n");
+ fprintf(stderr, "\t-n 32bit mode\n");
+ fprintf(stderr, "\t-v Verbosity(-vv dumps any decoded result)\n");
+ fprintf(stderr, "\t-s Give a random seed (and iteration number)\n");
+ fprintf(stderr, "\t-m Give a maximum iteration number\n");
+ fprintf(stderr, "\t-i Give an input file with decoded binary\n");
+ exit(1);
+}
+
+static void dump_field(FILE *fp, const char *name, const char *indent,
+ struct insn_field *field)
+{
+ fprintf(fp, "%s.%s = {\n", indent, name);
+ fprintf(fp, "%s\t.value = %d, bytes[] = {%x, %x, %x, %x},\n",
+ indent, field->value, field->bytes[0], field->bytes[1],
+ field->bytes[2], field->bytes[3]);
+ fprintf(fp, "%s\t.got = %d, .nbytes = %d},\n", indent,
+ field->got, field->nbytes);
+}
+
+static void dump_insn(FILE *fp, struct insn *insn)
+{
+ fprintf(fp, "Instruction = {\n");
+ dump_field(fp, "prefixes", "\t", &insn->prefixes);
+ dump_field(fp, "rex_prefix", "\t", &insn->rex_prefix);
+ dump_field(fp, "vex_prefix", "\t", &insn->vex_prefix);
+ dump_field(fp, "opcode", "\t", &insn->opcode);
+ dump_field(fp, "modrm", "\t", &insn->modrm);
+ dump_field(fp, "sib", "\t", &insn->sib);
+ dump_field(fp, "displacement", "\t", &insn->displacement);
+ dump_field(fp, "immediate1", "\t", &insn->immediate1);
+ dump_field(fp, "immediate2", "\t", &insn->immediate2);
+ fprintf(fp, "\t.attr = %x, .opnd_bytes = %d, .addr_bytes = %d,\n",
+ insn->attr, insn->opnd_bytes, insn->addr_bytes);
+ fprintf(fp, "\t.length = %d, .x86_64 = %d, .kaddr = %p}\n",
+ insn->length, insn->x86_64, insn->kaddr);
+}
+
+static void dump_stream(FILE *fp, const char *msg, unsigned long nr_iter,
+ unsigned char *insn_buf, struct insn *insn)
+{
+ int i;
+
+ fprintf(fp, "%s:\n", msg);
+
+ dump_insn(fp, insn);
+
+ fprintf(fp, "You can reproduce this with below command(s);\n");
+
+ /* Input a decoded instruction sequence directly */
+ fprintf(fp, " $ echo ");
+ for (i = 0; i < MAX_INSN_SIZE; i++)
+ fprintf(fp, " %02x", insn_buf[i]);
+ fprintf(fp, " | %s -i -\n", prog);
+
+ if (!input_file) {
+ fprintf(fp, "Or \n");
+ /* Give a seed and iteration number */
+ fprintf(fp, " $ %s -s 0x%x,%lu\n", prog, seed, nr_iter);
+ }
+}
+
+static void init_random_seed(void)
+{
+ int fd;
+
+ fd = open("/dev/urandom", O_RDONLY);
+ if (fd < 0)
+ goto fail;
+
+ if (read(fd, &seed, sizeof(seed)) != sizeof(seed))
+ goto fail;
+
+ close(fd);
+ return;
+fail:
+ usage("Failed to open /dev/urandom");
+}
+
+/* Read given instruction sequence from the input file */
+static int read_next_insn(unsigned char *insn_buf)
+{
+ char buf[256] = "", *tmp;
+ int i;
+
+ tmp = fgets(buf, ARRAY_SIZE(buf), input_file);
+ if (tmp == NULL || feof(input_file))
+ return 0;
+
+ for (i = 0; i < MAX_INSN_SIZE; i++) {
+ insn_buf[i] = (unsigned char)strtoul(tmp, &tmp, 16);
+ if (*tmp != ' ')
+ break;
+ }
+
+ return i;
+}
+
+static int generate_insn(unsigned char *insn_buf)
+{
+ int i;
+
+ if (input_file)
+ return read_next_insn(insn_buf);
+
+ /* Fills buffer with random binary up to MAX_INSN_SIZE */
+ for (i = 0; i < MAX_INSN_SIZE - 1; i += 2)
+ *(unsigned short *)(&insn_buf[i]) = random() & 0xffff;
+
+ while (i < MAX_INSN_SIZE)
+ insn_buf[i++] = random() & 0xff;
+
+ return i;
+}
+
+static void parse_args(int argc, char **argv)
+{
+ int c;
+ char *tmp = NULL;
+ int set_seed = 0;
+
+ prog = argv[0];
+ while ((c = getopt(argc, argv, "ynvs:m:i:")) != -1) {
+ switch (c) {
+ case 'y':
+ x86_64 = 1;
+ break;
+ case 'n':
+ x86_64 = 0;
+ break;
+ case 'v':
+ verbose++;
+ break;
+ case 'i':
+ if (strcmp("-", optarg) == 0)
+ input_file = stdin;
+ else
+ input_file = fopen(optarg, "r");
+ if (!input_file)
+ usage("Failed to open input file");
+ break;
+ case 's':
+ seed = (unsigned int)strtoul(optarg, &tmp, 0);
+ if (*tmp == ',') {
+ optarg = tmp + 1;
+ iter_start = strtoul(optarg, &tmp, 0);
+ }
+ if (*tmp != '\0' || tmp == optarg)
+ usage("Failed to parse seed");
+ set_seed = 1;
+ break;
+ case 'm':
+ iter_end = strtoul(optarg, &tmp, 0);
+ if (*tmp != '\0' || tmp == optarg)
+ usage("Failed to parse max_iter");
+ break;
+ default:
+ usage(NULL);
+ }
+ }
+
+ /* Check errors */
+ if (iter_end < iter_start)
+ usage("Max iteration number must be bigger than iter-num");
+
+ if (set_seed && input_file)
+ usage("Don't use input file (-i) with random seed (-s)");
+
+ /* Initialize random seed */
+ if (!input_file) {
+ if (!set_seed) /* No seed is given */
+ init_random_seed();
+ srand(seed);
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct insn insn;
+ int insns = 0;
+ int errors = 0;
+ unsigned long i;
+ unsigned char insn_buf[MAX_INSN_SIZE * 2];
+
+ parse_args(argc, argv);
+
+ /* Prepare stop bytes with NOPs */
+ memset(insn_buf + MAX_INSN_SIZE, INSN_NOP, MAX_INSN_SIZE);
+
+ for (i = 0; i < iter_end; i++) {
+ if (generate_insn(insn_buf) <= 0)
+ break;
+
+ if (i < iter_start) /* Skip to given iteration number */
+ continue;
+
+ /* Decode an instruction */
+ insn_init(&insn, insn_buf, x86_64);
+ insn_get_length(&insn);
+
+ if (insn.next_byte <= insn.kaddr ||
+ insn.kaddr + MAX_INSN_SIZE < insn.next_byte) {
+ /* Access out-of-range memory */
+ dump_stream(stderr, "Error: Found an access violation", i, insn_buf, &insn);
+ errors++;
+ } else if (verbose && !insn_complete(&insn))
+ dump_stream(stdout, "Info: Found an undecodable input", i, insn_buf, &insn);
+ else if (verbose >= 2)
+ dump_insn(stdout, &insn);
+ insns++;
+ }
+
+ fprintf(stdout, "%s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n", (errors) ? "Failure" : "Success", insns, (input_file) ? "given" : "random", errors, seed);
+
+ return errors ? 1 : 0;
+}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1093f80..b2c7179 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -173,9 +173,21 @@
domid_t domid = DOMID_SELF;
int ret;
- ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
- if (ret > 0)
- max_pages = ret;
+ /*
+ * For the initial domain we use the maximum reservation as
+ * the maximum page.
+ *
+ * For guest domains the current maximum reservation reflects
+ * the current maximum rather than the static maximum. In this
+ * case the e820 map provided to us will cover the static
+ * maximum region.
+ */
+ if (xen_initial_domain()) {
+ ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
+ if (ret > 0)
+ max_pages = ret;
+ }
+
return min(max_pages, MAX_DOMAIN_PAGES);
}
diff --git a/block/blk-core.c b/block/blk-core.c
index ea70e6c..15de223 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -366,7 +366,14 @@
if (drain_all)
blk_throtl_drain(q);
- __blk_run_queue(q);
+ /*
+ * This function might be called on a queue which failed
+ * driver init after queue creation. Some drivers
+ * (e.g. fd) get unhappy in such cases. Kick queue iff
+ * dispatch queue has something on it.
+ */
+ if (!list_empty(&q->queue_head))
+ __blk_run_queue(q);
if (drain_all)
nr_rqs = q->rq.count[0] + q->rq.count[1];
@@ -467,6 +474,7 @@
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
q->backing_dev_info.name = "block";
+ q->node = node_id;
err = bdi_init(&q->backing_dev_info);
if (err) {
@@ -551,7 +559,7 @@
if (!uninit_q)
return NULL;
- q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id);
+ q = blk_init_allocated_queue(uninit_q, rfn, lock);
if (!q)
blk_cleanup_queue(uninit_q);
@@ -563,18 +571,9 @@
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
spinlock_t *lock)
{
- return blk_init_allocated_queue_node(q, rfn, lock, -1);
-}
-EXPORT_SYMBOL(blk_init_allocated_queue);
-
-struct request_queue *
-blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn,
- spinlock_t *lock, int node_id)
-{
if (!q)
return NULL;
- q->node = node_id;
if (blk_init_free_list(q))
return NULL;
@@ -604,7 +603,7 @@
return NULL;
}
-EXPORT_SYMBOL(blk_init_allocated_queue_node);
+EXPORT_SYMBOL(blk_init_allocated_queue);
int blk_get_queue(struct request_queue *q)
{
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 16ace89..4c12869 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3184,7 +3184,7 @@
}
}
- if (ret)
+ if (ret && ret != -EEXIST)
printk(KERN_ERR "cfq: cic link failed!\n");
return ret;
@@ -3200,6 +3200,7 @@
{
struct io_context *ioc = NULL;
struct cfq_io_context *cic;
+ int ret;
might_sleep_if(gfp_mask & __GFP_WAIT);
@@ -3207,6 +3208,7 @@
if (!ioc)
return NULL;
+retry:
cic = cfq_cic_lookup(cfqd, ioc);
if (cic)
goto out;
@@ -3215,7 +3217,12 @@
if (cic == NULL)
goto err;
- if (cfq_cic_link(cfqd, ioc, cic, gfp_mask))
+ ret = cfq_cic_link(cfqd, ioc, cic, gfp_mask);
+ if (ret == -EEXIST) {
+ /* someone has linked cic to ioc already */
+ cfq_cic_free(cic);
+ goto retry;
+ } else if (ret)
goto err_free;
out:
@@ -4036,6 +4043,11 @@
if (blkio_alloc_blkg_stats(&cfqg->blkg)) {
kfree(cfqg);
+
+ spin_lock(&cic_index_lock);
+ ida_remove(&cic_index_ida, cfqd->cic_index);
+ spin_unlock(&cic_index_lock);
+
kfree(cfqd);
return NULL;
}
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 8004ac3..587cce5 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -2601,6 +2601,8 @@
c->Request.Timeout = 0;
c->Request.CDB[0] = BMIC_WRITE;
c->Request.CDB[6] = BMIC_CACHE_FLUSH;
+ c->Request.CDB[7] = (size >> 8) & 0xFF;
+ c->Request.CDB[8] = size & 0xFF;
break;
case TEST_UNIT_READY:
c->Request.CDBLen = 6;
@@ -4880,7 +4882,7 @@
{
if (h->msix_vector || h->msi_vector) {
if (!request_irq(h->intr[h->intr_mode], msixhandler,
- IRQF_DISABLED, h->devname, h))
+ 0, h->devname, h))
return 0;
dev_err(&h->pdev->dev, "Unable to get msi irq %d"
" for %s\n", h->intr[h->intr_mode],
@@ -4889,7 +4891,7 @@
}
if (!request_irq(h->intr[h->intr_mode], intxhandler,
- IRQF_DISABLED, h->devname, h))
+ IRQF_SHARED, h->devname, h))
return 0;
dev_err(&h->pdev->dev, "Unable to get irq %d for %s\n",
h->intr[h->intr_mode], h->devname);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 68b205a..1e888c9 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -422,7 +422,7 @@
/*
* We use punch hole to reclaim the free space used by the
- * image a.k.a. discard. However we do support discard if
+ * image a.k.a. discard. However we do not support discard if
* encryption is enabled, because it may give an attacker
* useful information.
*/
@@ -797,7 +797,7 @@
}
q->limits.discard_granularity = inode->i_sb->s_blocksize;
- q->limits.discard_alignment = inode->i_sb->s_blocksize;
+ q->limits.discard_alignment = 0;
q->limits.max_discard_sectors = UINT_MAX >> 9;
q->limits.discard_zeroes_data = 1;
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 65cc424..148ab94 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -183,10 +183,6 @@
static int __rbd_init_snaps_header(struct rbd_device *rbd_dev);
static void rbd_dev_release(struct device *dev);
-static ssize_t rbd_snap_rollback(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t size);
static ssize_t rbd_snap_add(struct device *dev,
struct device_attribute *attr,
const char *buf,
@@ -461,6 +457,10 @@
u32 snap_count = le32_to_cpu(ondisk->snap_count);
int ret = -ENOMEM;
+ if (memcmp(ondisk, RBD_HEADER_TEXT, sizeof(RBD_HEADER_TEXT))) {
+ return -ENXIO;
+ }
+
init_rwsem(&header->snap_rwsem);
header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
@@ -1356,32 +1356,6 @@
}
/*
- * Request sync osd rollback
- */
-static int rbd_req_sync_rollback_obj(struct rbd_device *dev,
- u64 snapid,
- const char *obj)
-{
- struct ceph_osd_req_op *ops;
- int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_ROLLBACK, 0);
- if (ret < 0)
- return ret;
-
- ops[0].snap.snapid = snapid;
-
- ret = rbd_req_sync_op(dev, NULL,
- CEPH_NOSNAP,
- 0,
- CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
- ops,
- 1, obj, 0, 0, NULL, NULL, NULL);
-
- rbd_destroy_ops(ops);
-
- return ret;
-}
-
-/*
* Request sync osd read
*/
static int rbd_req_sync_exec(struct rbd_device *dev,
@@ -1610,8 +1584,13 @@
goto out_dh;
rc = rbd_header_from_disk(header, dh, snap_count, GFP_KERNEL);
- if (rc < 0)
+ if (rc < 0) {
+ if (rc == -ENXIO) {
+ pr_warning("unrecognized header format"
+ " for image %s", rbd_dev->obj);
+ }
goto out_dh;
+ }
if (snap_count != header->total_snaps) {
snap_count = header->total_snaps;
@@ -1882,7 +1861,6 @@
static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh);
static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL);
static DEVICE_ATTR(create_snap, S_IWUSR, NULL, rbd_snap_add);
-static DEVICE_ATTR(rollback_snap, S_IWUSR, NULL, rbd_snap_rollback);
static struct attribute *rbd_attrs[] = {
&dev_attr_size.attr,
@@ -1893,7 +1871,6 @@
&dev_attr_current_snap.attr,
&dev_attr_refresh.attr,
&dev_attr_create_snap.attr,
- &dev_attr_rollback_snap.attr,
NULL
};
@@ -2424,64 +2401,6 @@
return ret;
}
-static ssize_t rbd_snap_rollback(struct device *dev,
- struct device_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct rbd_device *rbd_dev = dev_to_rbd(dev);
- int ret;
- u64 snapid;
- u64 cur_ofs;
- char *seg_name = NULL;
- char *snap_name = kmalloc(count + 1, GFP_KERNEL);
- ret = -ENOMEM;
- if (!snap_name)
- return ret;
-
- /* parse snaps add command */
- snprintf(snap_name, count, "%s", buf);
- seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
- if (!seg_name)
- goto done;
-
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- ret = snap_by_name(&rbd_dev->header, snap_name, &snapid, NULL);
- if (ret < 0)
- goto done_unlock;
-
- dout("snapid=%lld\n", snapid);
-
- cur_ofs = 0;
- while (cur_ofs < rbd_dev->header.image_size) {
- cur_ofs += rbd_get_segment(&rbd_dev->header,
- rbd_dev->obj,
- cur_ofs, (u64)-1,
- seg_name, NULL);
- dout("seg_name=%s\n", seg_name);
-
- ret = rbd_req_sync_rollback_obj(rbd_dev, snapid, seg_name);
- if (ret < 0)
- pr_warning("could not roll back obj %s err=%d\n",
- seg_name, ret);
- }
-
- ret = __rbd_update_snaps(rbd_dev);
- if (ret < 0)
- goto done_unlock;
-
- ret = count;
-
-done_unlock:
- mutex_unlock(&ctl_mutex);
-done:
- kfree(seg_name);
- kfree(snap_name);
-
- return ret;
-}
-
static struct bus_attribute rbd_bus_attrs[] = {
__ATTR(add, S_IWUSR, NULL, rbd_add),
__ATTR(remove, S_IWUSR, NULL, rbd_remove),
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index ae3e167..89ddab1 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -16,6 +16,8 @@
* handle GCR disks
*/
+#undef DEBUG
+
#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/sched.h>
@@ -36,13 +38,11 @@
#include <asm/machdep.h>
#include <asm/pmac_feature.h>
-static DEFINE_MUTEX(swim3_mutex);
-static struct request_queue *swim3_queue;
-static struct gendisk *disks[2];
-static struct request *fd_req;
-
#define MAX_FLOPPIES 2
+static DEFINE_MUTEX(swim3_mutex);
+static struct gendisk *disks[MAX_FLOPPIES];
+
enum swim_state {
idle,
locating,
@@ -177,7 +177,6 @@
struct floppy_state {
enum swim_state state;
- spinlock_t lock;
struct swim3 __iomem *swim3; /* hardware registers */
struct dbdma_regs __iomem *dma; /* DMA controller registers */
int swim3_intr; /* interrupt number for SWIM3 */
@@ -204,8 +203,20 @@
int wanted;
struct macio_dev *mdev;
char dbdma_cmd_space[5 * sizeof(struct dbdma_cmd)];
+ int index;
+ struct request *cur_req;
};
+#define swim3_err(fmt, arg...) dev_err(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+#define swim3_warn(fmt, arg...) dev_warn(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+#define swim3_info(fmt, arg...) dev_info(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+
+#ifdef DEBUG
+#define swim3_dbg(fmt, arg...) dev_dbg(&fs->mdev->ofdev.dev, "[fd%d] " fmt, fs->index, arg)
+#else
+#define swim3_dbg(fmt, arg...) do { } while(0)
+#endif
+
static struct floppy_state floppy_states[MAX_FLOPPIES];
static int floppy_count = 0;
static DEFINE_SPINLOCK(swim3_lock);
@@ -224,17 +235,8 @@
0, 0, 0, 0, 0, 0
};
-static void swim3_select(struct floppy_state *fs, int sel);
-static void swim3_action(struct floppy_state *fs, int action);
-static int swim3_readbit(struct floppy_state *fs, int bit);
-static void do_fd_request(struct request_queue * q);
-static void start_request(struct floppy_state *fs);
-static void set_timeout(struct floppy_state *fs, int nticks,
- void (*proc)(unsigned long));
-static void scan_track(struct floppy_state *fs);
static void seek_track(struct floppy_state *fs, int n);
static void init_dma(struct dbdma_cmd *cp, int cmd, void *buf, int count);
-static void setup_transfer(struct floppy_state *fs);
static void act(struct floppy_state *fs);
static void scan_timeout(unsigned long data);
static void seek_timeout(unsigned long data);
@@ -254,20 +256,23 @@
unsigned int clearing);
static int floppy_revalidate(struct gendisk *disk);
-static bool swim3_end_request(int err, unsigned int nr_bytes)
+static bool swim3_end_request(struct floppy_state *fs, int err, unsigned int nr_bytes)
{
- if (__blk_end_request(fd_req, err, nr_bytes))
+ struct request *req = fs->cur_req;
+ int rc;
+
+ swim3_dbg(" end request, err=%d nr_bytes=%d, cur_req=%p\n",
+ err, nr_bytes, req);
+
+ if (err)
+ nr_bytes = blk_rq_cur_bytes(req);
+ rc = __blk_end_request(req, err, nr_bytes);
+ if (rc)
return true;
-
- fd_req = NULL;
+ fs->cur_req = NULL;
return false;
}
-static bool swim3_end_request_cur(int err)
-{
- return swim3_end_request(err, blk_rq_cur_bytes(fd_req));
-}
-
static void swim3_select(struct floppy_state *fs, int sel)
{
struct swim3 __iomem *sw = fs->swim3;
@@ -303,50 +308,53 @@
return (stat & DATA) == 0;
}
-static void do_fd_request(struct request_queue * q)
-{
- int i;
-
- for(i=0; i<floppy_count; i++) {
- struct floppy_state *fs = &floppy_states[i];
- if (fs->mdev->media_bay &&
- check_media_bay(fs->mdev->media_bay) != MB_FD)
- continue;
- start_request(fs);
- }
-}
-
static void start_request(struct floppy_state *fs)
{
struct request *req;
unsigned long x;
+ swim3_dbg("start request, initial state=%d\n", fs->state);
+
if (fs->state == idle && fs->wanted) {
fs->state = available;
wake_up(&fs->wait);
return;
}
while (fs->state == idle) {
- if (!fd_req) {
- fd_req = blk_fetch_request(swim3_queue);
- if (!fd_req)
+ swim3_dbg("start request, idle loop, cur_req=%p\n", fs->cur_req);
+ if (!fs->cur_req) {
+ fs->cur_req = blk_fetch_request(disks[fs->index]->queue);
+ swim3_dbg(" fetched request %p\n", fs->cur_req);
+ if (!fs->cur_req)
break;
}
- req = fd_req;
-#if 0
- printk("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%u buf=%p\n",
- req->rq_disk->disk_name, req->cmd,
- (long)blk_rq_pos(req), blk_rq_sectors(req), req->buffer);
- printk(" errors=%d current_nr_sectors=%u\n",
- req->errors, blk_rq_cur_sectors(req));
+ req = fs->cur_req;
+
+ if (fs->mdev->media_bay &&
+ check_media_bay(fs->mdev->media_bay) != MB_FD) {
+ swim3_dbg("%s", " media bay absent, dropping req\n");
+ swim3_end_request(fs, -ENODEV, 0);
+ continue;
+ }
+
+#if 0 /* This is really too verbose */
+ swim3_dbg("do_fd_req: dev=%s cmd=%d sec=%ld nr_sec=%u buf=%p\n",
+ req->rq_disk->disk_name, req->cmd,
+ (long)blk_rq_pos(req), blk_rq_sectors(req),
+ req->buffer);
+ swim3_dbg(" errors=%d current_nr_sectors=%u\n",
+ req->errors, blk_rq_cur_sectors(req));
#endif
if (blk_rq_pos(req) >= fs->total_secs) {
- swim3_end_request_cur(-EIO);
+ swim3_dbg(" pos out of bounds (%ld, max is %ld)\n",
+ (long)blk_rq_pos(req), (long)fs->total_secs);
+ swim3_end_request(fs, -EIO, 0);
continue;
}
if (fs->ejected) {
- swim3_end_request_cur(-EIO);
+ swim3_dbg("%s", " disk ejected\n");
+ swim3_end_request(fs, -EIO, 0);
continue;
}
@@ -354,7 +362,8 @@
if (fs->write_prot < 0)
fs->write_prot = swim3_readbit(fs, WRITE_PROT);
if (fs->write_prot) {
- swim3_end_request_cur(-EIO);
+ swim3_dbg("%s", " try to write, disk write protected\n");
+ swim3_end_request(fs, -EIO, 0);
continue;
}
}
@@ -369,7 +378,6 @@
x = ((long)blk_rq_pos(req)) % fs->secpercyl;
fs->head = x / fs->secpertrack;
fs->req_sector = x % fs->secpertrack + 1;
- fd_req = req;
fs->state = do_transfer;
fs->retries = 0;
@@ -377,12 +385,14 @@
}
}
+static void do_fd_request(struct request_queue * q)
+{
+ start_request(q->queuedata);
+}
+
static void set_timeout(struct floppy_state *fs, int nticks,
void (*proc)(unsigned long))
{
- unsigned long flags;
-
- spin_lock_irqsave(&fs->lock, flags);
if (fs->timeout_pending)
del_timer(&fs->timeout);
fs->timeout.expires = jiffies + nticks;
@@ -390,7 +400,6 @@
fs->timeout.data = (unsigned long) fs;
add_timer(&fs->timeout);
fs->timeout_pending = 1;
- spin_unlock_irqrestore(&fs->lock, flags);
}
static inline void scan_track(struct floppy_state *fs)
@@ -442,40 +451,45 @@
struct swim3 __iomem *sw = fs->swim3;
struct dbdma_cmd *cp = fs->dma_cmd;
struct dbdma_regs __iomem *dr = fs->dma;
+ struct request *req = fs->cur_req;
- if (blk_rq_cur_sectors(fd_req) <= 0) {
- printk(KERN_ERR "swim3: transfer 0 sectors?\n");
+ if (blk_rq_cur_sectors(req) <= 0) {
+ swim3_warn("%s", "Transfer 0 sectors ?\n");
return;
}
- if (rq_data_dir(fd_req) == WRITE)
+ if (rq_data_dir(req) == WRITE)
n = 1;
else {
n = fs->secpertrack - fs->req_sector + 1;
- if (n > blk_rq_cur_sectors(fd_req))
- n = blk_rq_cur_sectors(fd_req);
+ if (n > blk_rq_cur_sectors(req))
+ n = blk_rq_cur_sectors(req);
}
+
+ swim3_dbg(" setup xfer at sect %d (of %d) head %d for %d\n",
+ fs->req_sector, fs->secpertrack, fs->head, n);
+
fs->scount = n;
swim3_select(fs, fs->head? READ_DATA_1: READ_DATA_0);
out_8(&sw->sector, fs->req_sector);
out_8(&sw->nsect, n);
out_8(&sw->gap3, 0);
out_le32(&dr->cmdptr, virt_to_bus(cp));
- if (rq_data_dir(fd_req) == WRITE) {
+ if (rq_data_dir(req) == WRITE) {
/* Set up 3 dma commands: write preamble, data, postamble */
init_dma(cp, OUTPUT_MORE, write_preamble, sizeof(write_preamble));
++cp;
- init_dma(cp, OUTPUT_MORE, fd_req->buffer, 512);
+ init_dma(cp, OUTPUT_MORE, req->buffer, 512);
++cp;
init_dma(cp, OUTPUT_LAST, write_postamble, sizeof(write_postamble));
} else {
- init_dma(cp, INPUT_LAST, fd_req->buffer, n * 512);
+ init_dma(cp, INPUT_LAST, req->buffer, n * 512);
}
++cp;
out_le16(&cp->command, DBDMA_STOP);
out_8(&sw->control_bic, DO_ACTION | WRITE_SECTORS);
in_8(&sw->error);
out_8(&sw->control_bic, DO_ACTION | WRITE_SECTORS);
- if (rq_data_dir(fd_req) == WRITE)
+ if (rq_data_dir(req) == WRITE)
out_8(&sw->control_bis, WRITE_SECTORS);
in_8(&sw->intr);
out_le32(&dr->control, (RUN << 16) | RUN);
@@ -488,12 +502,16 @@
static void act(struct floppy_state *fs)
{
for (;;) {
+ swim3_dbg(" act loop, state=%d, req_cyl=%d, cur_cyl=%d\n",
+ fs->state, fs->req_cyl, fs->cur_cyl);
+
switch (fs->state) {
case idle:
return; /* XXX shouldn't get here */
case locating:
if (swim3_readbit(fs, TRACK_ZERO)) {
+ swim3_dbg("%s", " locate track 0\n");
fs->cur_cyl = 0;
if (fs->req_cyl == 0)
fs->state = do_transfer;
@@ -511,7 +529,7 @@
break;
}
if (fs->req_cyl == fs->cur_cyl) {
- printk("whoops, seeking 0\n");
+ swim3_warn("%s", "Whoops, seeking 0\n");
fs->state = do_transfer;
break;
}
@@ -527,7 +545,9 @@
case do_transfer:
if (fs->cur_cyl != fs->req_cyl) {
if (fs->retries > 5) {
- swim3_end_request_cur(-EIO);
+ swim3_err("Wrong cylinder in transfer, want: %d got %d\n",
+ fs->req_cyl, fs->cur_cyl);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
return;
}
@@ -542,7 +562,7 @@
return;
default:
- printk(KERN_ERR"swim3: unknown state %d\n", fs->state);
+ swim3_err("Unknown state %d\n", fs->state);
return;
}
}
@@ -552,59 +572,75 @@
{
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
+ unsigned long flags;
+ swim3_dbg("* scan timeout, state=%d\n", fs->state);
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
out_8(&sw->control_bic, DO_ACTION | WRITE_SECTORS);
out_8(&sw->select, RELAX);
out_8(&sw->intr_enable, 0);
fs->cur_cyl = -1;
if (fs->retries > 5) {
- swim3_end_request_cur(-EIO);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
} else {
fs->state = jogging;
act(fs);
}
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static void seek_timeout(unsigned long data)
{
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
+ unsigned long flags;
+ swim3_dbg("* seek timeout, state=%d\n", fs->state);
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
out_8(&sw->control_bic, DO_SEEK);
out_8(&sw->select, RELAX);
out_8(&sw->intr_enable, 0);
- printk(KERN_ERR "swim3: seek timeout\n");
- swim3_end_request_cur(-EIO);
+ swim3_err("%s", "Seek timeout\n");
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static void settle_timeout(unsigned long data)
{
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
+ unsigned long flags;
+ swim3_dbg("* settle timeout, state=%d\n", fs->state);
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
if (swim3_readbit(fs, SEEK_COMPLETE)) {
out_8(&sw->select, RELAX);
fs->state = locating;
act(fs);
- return;
+ goto unlock;
}
out_8(&sw->select, RELAX);
if (fs->settle_time < 2*HZ) {
++fs->settle_time;
set_timeout(fs, 1, settle_timeout);
- return;
+ goto unlock;
}
- printk(KERN_ERR "swim3: seek settle timeout\n");
- swim3_end_request_cur(-EIO);
+ swim3_err("%s", "Seek settle timeout\n");
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
+ unlock:
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static void xfer_timeout(unsigned long data)
@@ -612,8 +648,12 @@
struct floppy_state *fs = (struct floppy_state *) data;
struct swim3 __iomem *sw = fs->swim3;
struct dbdma_regs __iomem *dr = fs->dma;
+ unsigned long flags;
int n;
+ swim3_dbg("* xfer timeout, state=%d\n", fs->state);
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->timeout_pending = 0;
out_le32(&dr->control, RUN << 16);
/* We must wait a bit for dbdma to stop */
@@ -622,12 +662,13 @@
out_8(&sw->intr_enable, 0);
out_8(&sw->control_bic, WRITE_SECTORS | DO_ACTION);
out_8(&sw->select, RELAX);
- printk(KERN_ERR "swim3: timeout %sing sector %ld\n",
- (rq_data_dir(fd_req)==WRITE? "writ": "read"),
- (long)blk_rq_pos(fd_req));
- swim3_end_request_cur(-EIO);
+ swim3_err("Timeout %sing sector %ld\n",
+ (rq_data_dir(fs->cur_req)==WRITE? "writ": "read"),
+ (long)blk_rq_pos(fs->cur_req));
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static irqreturn_t swim3_interrupt(int irq, void *dev_id)
@@ -638,12 +679,17 @@
int stat, resid;
struct dbdma_regs __iomem *dr;
struct dbdma_cmd *cp;
+ unsigned long flags;
+ struct request *req = fs->cur_req;
+ swim3_dbg("* interrupt, state=%d\n", fs->state);
+
+ spin_lock_irqsave(&swim3_lock, flags);
intr = in_8(&sw->intr);
err = (intr & ERROR_INTR)? in_8(&sw->error): 0;
if ((intr & ERROR_INTR) && fs->state != do_transfer)
- printk(KERN_ERR "swim3_interrupt, state=%d, dir=%x, intr=%x, err=%x\n",
- fs->state, rq_data_dir(fd_req), intr, err);
+ swim3_err("Non-transfer error interrupt: state=%d, dir=%x, intr=%x, err=%x\n",
+ fs->state, rq_data_dir(req), intr, err);
switch (fs->state) {
case locating:
if (intr & SEEN_SECTOR) {
@@ -653,10 +699,10 @@
del_timer(&fs->timeout);
fs->timeout_pending = 0;
if (sw->ctrack == 0xff) {
- printk(KERN_ERR "swim3: seen sector but cyl=ff?\n");
+ swim3_err("%s", "Seen sector but cyl=ff?\n");
fs->cur_cyl = -1;
if (fs->retries > 5) {
- swim3_end_request_cur(-EIO);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
} else {
@@ -668,8 +714,8 @@
fs->cur_cyl = sw->ctrack;
fs->cur_sector = sw->csect;
if (fs->expect_cyl != -1 && fs->expect_cyl != fs->cur_cyl)
- printk(KERN_ERR "swim3: expected cyl %d, got %d\n",
- fs->expect_cyl, fs->cur_cyl);
+ swim3_err("Expected cyl %d, got %d\n",
+ fs->expect_cyl, fs->cur_cyl);
fs->state = do_transfer;
act(fs);
}
@@ -704,7 +750,7 @@
fs->timeout_pending = 0;
dr = fs->dma;
cp = fs->dma_cmd;
- if (rq_data_dir(fd_req) == WRITE)
+ if (rq_data_dir(req) == WRITE)
++cp;
/*
* Check that the main data transfer has finished.
@@ -729,31 +775,32 @@
if (intr & ERROR_INTR) {
n = fs->scount - 1 - resid / 512;
if (n > 0) {
- blk_update_request(fd_req, 0, n << 9);
+ blk_update_request(req, 0, n << 9);
fs->req_sector += n;
}
if (fs->retries < 5) {
++fs->retries;
act(fs);
} else {
- printk("swim3: error %sing block %ld (err=%x)\n",
- rq_data_dir(fd_req) == WRITE? "writ": "read",
- (long)blk_rq_pos(fd_req), err);
- swim3_end_request_cur(-EIO);
+ swim3_err("Error %sing block %ld (err=%x)\n",
+ rq_data_dir(req) == WRITE? "writ": "read",
+ (long)blk_rq_pos(req), err);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
}
} else {
if ((stat & ACTIVE) == 0 || resid != 0) {
/* musta been an error */
- printk(KERN_ERR "swim3: fd dma: stat=%x resid=%d\n", stat, resid);
- printk(KERN_ERR " state=%d, dir=%x, intr=%x, err=%x\n",
- fs->state, rq_data_dir(fd_req), intr, err);
- swim3_end_request_cur(-EIO);
+ swim3_err("fd dma error: stat=%x resid=%d\n", stat, resid);
+ swim3_err(" state=%d, dir=%x, intr=%x, err=%x\n",
+ fs->state, rq_data_dir(req), intr, err);
+ swim3_end_request(fs, -EIO, 0);
fs->state = idle;
start_request(fs);
break;
}
- if (swim3_end_request(0, fs->scount << 9)) {
+ fs->retries = 0;
+ if (swim3_end_request(fs, 0, fs->scount << 9)) {
fs->req_sector += fs->scount;
if (fs->req_sector > fs->secpertrack) {
fs->req_sector -= fs->secpertrack;
@@ -770,8 +817,9 @@
start_request(fs);
break;
default:
- printk(KERN_ERR "swim3: don't know what to do in state %d\n", fs->state);
+ swim3_err("Don't know what to do in state %d\n", fs->state);
}
+ spin_unlock_irqrestore(&swim3_lock, flags);
return IRQ_HANDLED;
}
@@ -781,26 +829,31 @@
}
*/
+/* Called under the mutex to grab exclusive access to a drive */
static int grab_drive(struct floppy_state *fs, enum swim_state state,
int interruptible)
{
unsigned long flags;
- spin_lock_irqsave(&fs->lock, flags);
- if (fs->state != idle) {
+ swim3_dbg("%s", "-> grab drive\n");
+
+ spin_lock_irqsave(&swim3_lock, flags);
+ if (fs->state != idle && fs->state != available) {
++fs->wanted;
while (fs->state != available) {
+ spin_unlock_irqrestore(&swim3_lock, flags);
if (interruptible && signal_pending(current)) {
--fs->wanted;
- spin_unlock_irqrestore(&fs->lock, flags);
return -EINTR;
}
interruptible_sleep_on(&fs->wait);
+ spin_lock_irqsave(&swim3_lock, flags);
}
--fs->wanted;
}
fs->state = state;
- spin_unlock_irqrestore(&fs->lock, flags);
+ spin_unlock_irqrestore(&swim3_lock, flags);
+
return 0;
}
@@ -808,10 +861,12 @@
{
unsigned long flags;
- spin_lock_irqsave(&fs->lock, flags);
+ swim3_dbg("%s", "-> release drive\n");
+
+ spin_lock_irqsave(&swim3_lock, flags);
fs->state = idle;
start_request(fs);
- spin_unlock_irqrestore(&fs->lock, flags);
+ spin_unlock_irqrestore(&swim3_lock, flags);
}
static int fd_eject(struct floppy_state *fs)
@@ -966,6 +1021,7 @@
{
struct floppy_state *fs = disk->private_data;
struct swim3 __iomem *sw = fs->swim3;
+
mutex_lock(&swim3_mutex);
if (fs->ref_count > 0 && --fs->ref_count == 0) {
swim3_action(fs, MOTOR_OFF);
@@ -1031,30 +1087,48 @@
.revalidate_disk= floppy_revalidate,
};
+static void swim3_mb_event(struct macio_dev* mdev, int mb_state)
+{
+ struct floppy_state *fs = macio_get_drvdata(mdev);
+ struct swim3 __iomem *sw = fs->swim3;
+
+ if (!fs)
+ return;
+ if (mb_state != MB_FD)
+ return;
+
+ /* Clear state */
+ out_8(&sw->intr_enable, 0);
+ in_8(&sw->intr);
+ in_8(&sw->error);
+}
+
static int swim3_add_device(struct macio_dev *mdev, int index)
{
struct device_node *swim = mdev->ofdev.dev.of_node;
struct floppy_state *fs = &floppy_states[index];
int rc = -EBUSY;
+ /* Do this first for message macros */
+ memset(fs, 0, sizeof(*fs));
+ fs->mdev = mdev;
+ fs->index = index;
+
/* Check & Request resources */
if (macio_resource_count(mdev) < 2) {
- printk(KERN_WARNING "ifd%d: no address for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "No address in device-tree\n");
return -ENXIO;
}
- if (macio_irq_count(mdev) < 2) {
- printk(KERN_WARNING "fd%d: no intrs for device %s\n",
- index, swim->full_name);
+ if (macio_irq_count(mdev) < 1) {
+ swim3_err("%s", "No interrupt in device-tree\n");
+ return -ENXIO;
}
if (macio_request_resource(mdev, 0, "swim3 (mmio)")) {
- printk(KERN_ERR "fd%d: can't request mmio resource for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Can't request mmio resource\n");
return -EBUSY;
}
if (macio_request_resource(mdev, 1, "swim3 (dma)")) {
- printk(KERN_ERR "fd%d: can't request dma resource for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Can't request dma resource\n");
macio_release_resource(mdev, 0);
return -EBUSY;
}
@@ -1063,22 +1137,18 @@
if (mdev->media_bay == NULL)
pmac_call_feature(PMAC_FTR_SWIM3_ENABLE, swim, 0, 1);
- memset(fs, 0, sizeof(*fs));
- spin_lock_init(&fs->lock);
fs->state = idle;
fs->swim3 = (struct swim3 __iomem *)
ioremap(macio_resource_start(mdev, 0), 0x200);
if (fs->swim3 == NULL) {
- printk("fd%d: couldn't map registers for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Couldn't map mmio registers\n");
rc = -ENOMEM;
goto out_release;
}
fs->dma = (struct dbdma_regs __iomem *)
ioremap(macio_resource_start(mdev, 1), 0x200);
if (fs->dma == NULL) {
- printk("fd%d: couldn't map DMA for %s\n",
- index, swim->full_name);
+ swim3_err("%s", "Couldn't map dma registers\n");
iounmap(fs->swim3);
rc = -ENOMEM;
goto out_release;
@@ -1090,31 +1160,25 @@
fs->secpercyl = 36;
fs->secpertrack = 18;
fs->total_secs = 2880;
- fs->mdev = mdev;
init_waitqueue_head(&fs->wait);
fs->dma_cmd = (struct dbdma_cmd *) DBDMA_ALIGN(fs->dbdma_cmd_space);
memset(fs->dma_cmd, 0, 2 * sizeof(struct dbdma_cmd));
st_le16(&fs->dma_cmd[1].command, DBDMA_STOP);
+ if (mdev->media_bay == NULL || check_media_bay(mdev->media_bay) == MB_FD)
+ swim3_mb_event(mdev, MB_FD);
+
if (request_irq(fs->swim3_intr, swim3_interrupt, 0, "SWIM3", fs)) {
- printk(KERN_ERR "fd%d: couldn't request irq %d for %s\n",
- index, fs->swim3_intr, swim->full_name);
+ swim3_err("%s", "Couldn't request interrupt\n");
pmac_call_feature(PMAC_FTR_SWIM3_ENABLE, swim, 0, 0);
goto out_unmap;
return -EBUSY;
}
-/*
- if (request_irq(fs->dma_intr, fd_dma_interrupt, 0, "SWIM3-dma", fs)) {
- printk(KERN_ERR "Couldn't get irq %d for SWIM3 DMA",
- fs->dma_intr);
- return -EBUSY;
- }
-*/
init_timer(&fs->timeout);
- printk(KERN_INFO "fd%d: SWIM3 floppy controller %s\n", floppy_count,
+ swim3_info("SWIM3 floppy controller %s\n",
mdev->media_bay ? "in media bay" : "");
return 0;
@@ -1132,41 +1196,42 @@
static int __devinit swim3_attach(struct macio_dev *mdev, const struct of_device_id *match)
{
- int i, rc;
struct gendisk *disk;
+ int index, rc;
+
+ index = floppy_count++;
+ if (index >= MAX_FLOPPIES)
+ return -ENXIO;
/* Add the drive */
- rc = swim3_add_device(mdev, floppy_count);
+ rc = swim3_add_device(mdev, index);
if (rc)
return rc;
+ /* Now register that disk. Same comment about failure handling */
+ disk = disks[index] = alloc_disk(1);
+ if (disk == NULL)
+ return -ENOMEM;
+ disk->queue = blk_init_queue(do_fd_request, &swim3_lock);
+ if (disk->queue == NULL) {
+ put_disk(disk);
+ return -ENOMEM;
+ }
+ disk->queue->queuedata = &floppy_states[index];
- /* Now create the queue if not there yet */
- if (swim3_queue == NULL) {
+ if (index == 0) {
/* If we failed, there isn't much we can do as the driver is still
* too dumb to remove the device, just bail out
*/
if (register_blkdev(FLOPPY_MAJOR, "fd"))
return 0;
- swim3_queue = blk_init_queue(do_fd_request, &swim3_lock);
- if (swim3_queue == NULL) {
- unregister_blkdev(FLOPPY_MAJOR, "fd");
- return 0;
- }
}
- /* Now register that disk. Same comment about failure handling */
- i = floppy_count++;
- disk = disks[i] = alloc_disk(1);
- if (disk == NULL)
- return 0;
-
disk->major = FLOPPY_MAJOR;
- disk->first_minor = i;
+ disk->first_minor = index;
disk->fops = &floppy_fops;
- disk->private_data = &floppy_states[i];
- disk->queue = swim3_queue;
+ disk->private_data = &floppy_states[index];
disk->flags |= GENHD_FL_REMOVABLE;
- sprintf(disk->disk_name, "fd%d", i);
+ sprintf(disk->disk_name, "fd%d", index);
set_capacity(disk, 2880);
add_disk(disk);
@@ -1194,6 +1259,9 @@
.of_match_table = swim3_match,
},
.probe = swim3_attach,
+#ifdef CONFIG_PMAC_MEDIABAY
+ .mediabay_event = swim3_mb_event,
+#endif
#if 0
.suspend = swim3_suspend,
.resume = swim3_resume,
diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 11b41fd..5ccf142 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -188,7 +188,7 @@
The core driver to support Marvell Bluetooth devices.
This driver is required if you want to support
- Marvell Bluetooth devices, such as 8688/8787.
+ Marvell Bluetooth devices, such as 8688/8787/8797.
Say Y here to compile Marvell Bluetooth driver
into the kernel or say M to compile it as module.
@@ -201,8 +201,8 @@
The driver for Marvell Bluetooth chipsets with SDIO interface.
This driver is required if you want to use Marvell Bluetooth
- devices with SDIO interface. Currently SD8688/SD8787 chipsets are
- supported.
+ devices with SDIO interface. Currently SD8688/SD8787/SD8797
+ chipsets are supported.
Say Y here to compile support for Marvell BT-over-SDIO driver
into the kernel or say M to compile it as module.
diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 9ef4816..27b74b0 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -65,7 +65,7 @@
.io_port_1 = 0x01,
.io_port_2 = 0x02,
};
-static const struct btmrvl_sdio_card_reg btmrvl_reg_8787 = {
+static const struct btmrvl_sdio_card_reg btmrvl_reg_87xx = {
.cfg = 0x00,
.host_int_mask = 0x02,
.host_intstatus = 0x03,
@@ -92,7 +92,14 @@
static const struct btmrvl_sdio_device btmrvl_sdio_sd8787 = {
.helper = NULL,
.firmware = "mrvl/sd8787_uapsta.bin",
- .reg = &btmrvl_reg_8787,
+ .reg = &btmrvl_reg_87xx,
+ .sd_blksz_fw_dl = 256,
+};
+
+static const struct btmrvl_sdio_device btmrvl_sdio_sd8797 = {
+ .helper = NULL,
+ .firmware = "mrvl/sd8797_uapsta.bin",
+ .reg = &btmrvl_reg_87xx,
.sd_blksz_fw_dl = 256,
};
@@ -103,6 +110,9 @@
/* Marvell SD8787 Bluetooth device */
{ SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, 0x911A),
.driver_data = (unsigned long) &btmrvl_sdio_sd8787 },
+ /* Marvell SD8797 Bluetooth device */
+ { SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, 0x912A),
+ .driver_data = (unsigned long) &btmrvl_sdio_sd8797 },
{ } /* Terminating entry */
};
@@ -1076,3 +1086,4 @@
MODULE_FIRMWARE("sd8688_helper.bin");
MODULE_FIRMWARE("sd8688.bin");
MODULE_FIRMWARE("mrvl/sd8787_uapsta.bin");
+MODULE_FIRMWARE("mrvl/sd8797_uapsta.bin");
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index fe4ebc3..eabc437 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -777,9 +777,8 @@
usb_mark_last_busy(data->udev);
}
- usb_free_urb(urb);
-
done:
+ usb_free_urb(urb);
return err;
}
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index c811cb1..2cce44a 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -746,6 +746,37 @@
ibft_cleanup();
}
+#ifdef CONFIG_ACPI
+static const struct {
+ char *sign;
+} ibft_signs[] = {
+ /*
+ * One spec says "IBFT", the other says "iBFT". We have to check
+ * for both.
+ */
+ { ACPI_SIG_IBFT },
+ { "iBFT" },
+};
+
+static void __init acpi_find_ibft_region(void)
+{
+ int i;
+ struct acpi_table_header *table = NULL;
+
+ if (acpi_disabled)
+ return;
+
+ for (i = 0; i < ARRAY_SIZE(ibft_signs) && !ibft_addr; i++) {
+ acpi_get_table(ibft_signs[i].sign, 0, &table);
+ ibft_addr = (struct acpi_table_ibft *)table;
+ }
+}
+#else
+static void __init acpi_find_ibft_region(void)
+{
+}
+#endif
+
/*
* ibft_init() - creates sysfs tree entries for the iBFT data.
*/
@@ -753,9 +784,16 @@
{
int rc = 0;
+ /*
+ As on UEFI systems the setup_arch()/find_ibft_region()
+ is called before ACPI tables are parsed and it only does
+ legacy finding.
+ */
+ if (!ibft_addr)
+ acpi_find_ibft_region();
+
if (ibft_addr) {
- printk(KERN_INFO "iBFT detected at 0x%llx.\n",
- (u64)isa_virt_to_bus(ibft_addr));
+ pr_info("iBFT detected.\n");
rc = ibft_check_device();
if (rc)
diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c
index bfe7232..4da4eb9a 100644
--- a/drivers/firmware/iscsi_ibft_find.c
+++ b/drivers/firmware/iscsi_ibft_find.c
@@ -45,13 +45,6 @@
static const struct {
char *sign;
} ibft_signs[] = {
-#ifdef CONFIG_ACPI
- /*
- * One spec says "IBFT", the other says "iBFT". We have to check
- * for both.
- */
- { ACPI_SIG_IBFT },
-#endif
{ "iBFT" },
{ "BIFT" }, /* Broadcom iSCSI Offload */
};
@@ -62,14 +55,6 @@
#define VGA_MEM 0xA0000 /* VGA buffer */
#define VGA_SIZE 0x20000 /* 128kB */
-#ifdef CONFIG_ACPI
-static int __init acpi_find_ibft(struct acpi_table_header *header)
-{
- ibft_addr = (struct acpi_table_ibft *)header;
- return 0;
-}
-#endif /* CONFIG_ACPI */
-
static int __init find_ibft_in_mem(void)
{
unsigned long pos;
@@ -94,6 +79,7 @@
* the table cannot be valid. */
if (pos + len <= (IBFT_END-1)) {
ibft_addr = (struct acpi_table_ibft *)virt;
+ pr_info("iBFT found at 0x%lx.\n", pos);
goto done;
}
}
@@ -108,20 +94,12 @@
*/
unsigned long __init find_ibft_region(unsigned long *sizep)
{
-#ifdef CONFIG_ACPI
- int i;
-#endif
ibft_addr = NULL;
-#ifdef CONFIG_ACPI
- for (i = 0; i < ARRAY_SIZE(ibft_signs) && !ibft_addr; i++)
- acpi_table_parse(ibft_signs[i].sign, acpi_find_ibft);
-#endif /* CONFIG_ACPI */
-
/* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will
* only use ACPI for this */
- if (!ibft_addr && !efi_enabled)
+ if (!efi_enabled)
find_ibft_in_mem();
if (ibft_addr) {
diff --git a/drivers/gpio/gpio-da9052.c b/drivers/gpio/gpio-da9052.c
index 038f5eb8..f8ce29e 100644
--- a/drivers/gpio/gpio-da9052.c
+++ b/drivers/gpio/gpio-da9052.c
@@ -22,7 +22,6 @@
#include <linux/mfd/da9052/da9052.h>
#include <linux/mfd/da9052/reg.h>
#include <linux/mfd/da9052/pdata.h>
-#include <linux/mfd/da9052/gpio.h>
#define DA9052_INPUT 1
#define DA9052_OUTPUT_OPENDRAIN 2
@@ -43,6 +42,9 @@
#define DA9052_GPIO_MASK_UPPER_NIBBLE 0xF0
#define DA9052_GPIO_MASK_LOWER_NIBBLE 0x0F
#define DA9052_GPIO_NIBBLE_SHIFT 4
+#define DA9052_IRQ_GPI0 16
+#define DA9052_GPIO_ODD_SHIFT 7
+#define DA9052_GPIO_EVEN_SHIFT 3
struct da9052_gpio {
struct da9052 *da9052;
@@ -104,33 +106,26 @@
static void da9052_gpio_set(struct gpio_chip *gc, unsigned offset, int value)
{
struct da9052_gpio *gpio = to_da9052_gpio(gc);
- unsigned char register_value = 0;
int ret;
if (da9052_gpio_port_odd(offset)) {
- if (value) {
- register_value = DA9052_GPIO_ODD_PORT_MODE;
ret = da9052_reg_update(gpio->da9052, (offset >> 1) +
DA9052_GPIO_0_1_REG,
DA9052_GPIO_ODD_PORT_MODE,
- register_value);
+ value << DA9052_GPIO_ODD_SHIFT);
if (ret != 0)
dev_err(gpio->da9052->dev,
"Failed to updated gpio odd reg,%d",
ret);
- }
} else {
- if (value) {
- register_value = DA9052_GPIO_EVEN_PORT_MODE;
ret = da9052_reg_update(gpio->da9052, (offset >> 1) +
DA9052_GPIO_0_1_REG,
DA9052_GPIO_EVEN_PORT_MODE,
- register_value);
+ value << DA9052_GPIO_EVEN_SHIFT);
if (ret != 0)
dev_err(gpio->da9052->dev,
"Failed to updated gpio even reg,%d",
ret);
- }
}
}
@@ -201,9 +196,9 @@
.direction_input = da9052_gpio_direction_input,
.direction_output = da9052_gpio_direction_output,
.to_irq = da9052_gpio_to_irq,
- .can_sleep = 1;
- .ngpio = 16;
- .base = -1;
+ .can_sleep = 1,
+ .ngpio = 16,
+ .base = -1,
};
static int __devinit da9052_gpio_probe(struct platform_device *pdev)
diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c
index ea8e738..461958f 100644
--- a/drivers/gpio/gpio-ml-ioh.c
+++ b/drivers/gpio/gpio-ml-ioh.c
@@ -332,6 +332,34 @@
&chip->reg->regs[chip->ch].imask);
}
+static void ioh_irq_disable(struct irq_data *d)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+ struct ioh_gpio *chip = gc->private;
+ unsigned long flags;
+ u32 ien;
+
+ spin_lock_irqsave(&chip->spinlock, flags);
+ ien = ioread32(&chip->reg->regs[chip->ch].ien);
+ ien &= ~(1 << (d->irq - chip->irq_base));
+ iowrite32(ien, &chip->reg->regs[chip->ch].ien);
+ spin_unlock_irqrestore(&chip->spinlock, flags);
+}
+
+static void ioh_irq_enable(struct irq_data *d)
+{
+ struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+ struct ioh_gpio *chip = gc->private;
+ unsigned long flags;
+ u32 ien;
+
+ spin_lock_irqsave(&chip->spinlock, flags);
+ ien = ioread32(&chip->reg->regs[chip->ch].ien);
+ ien |= 1 << (d->irq - chip->irq_base);
+ iowrite32(ien, &chip->reg->regs[chip->ch].ien);
+ spin_unlock_irqrestore(&chip->spinlock, flags);
+}
+
static irqreturn_t ioh_gpio_handler(int irq, void *dev_id)
{
struct ioh_gpio *chip = dev_id;
@@ -339,7 +367,7 @@
int i, j;
int ret = IRQ_NONE;
- for (i = 0; i < 8; i++) {
+ for (i = 0; i < 8; i++, chip++) {
reg_val = ioread32(&chip->reg->regs[i].istatus);
for (j = 0; j < num_ports[i]; j++) {
if (reg_val & BIT(j)) {
@@ -370,6 +398,8 @@
ct->chip.irq_mask = ioh_irq_mask;
ct->chip.irq_unmask = ioh_irq_unmask;
ct->chip.irq_set_type = ioh_irq_type;
+ ct->chip.irq_disable = ioh_irq_disable;
+ ct->chip.irq_enable = ioh_irq_enable;
irq_setup_generic_chip(gc, IRQ_MSK(num), IRQ_GC_INIT_MASK_CACHE,
IRQ_NOREQUEST | IRQ_NOPROBE, 0);
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index ec3fcf0..5cd04b6 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -132,6 +132,15 @@
return 0;
}
+static int mpc5121_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
+{
+ /* GPIO 28..31 are input only on MPC5121 */
+ if (gpio >= 28)
+ return -EINVAL;
+
+ return mpc8xxx_gpio_dir_out(gc, gpio, val);
+}
+
static int mpc8xxx_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
{
struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
@@ -340,11 +349,10 @@
mm_gc->save_regs = mpc8xxx_gpio_save_regs;
gc->ngpio = MPC8XXX_GPIO_PINS;
gc->direction_input = mpc8xxx_gpio_dir_in;
- gc->direction_output = mpc8xxx_gpio_dir_out;
- if (of_device_is_compatible(np, "fsl,mpc8572-gpio"))
- gc->get = mpc8572_gpio_get;
- else
- gc->get = mpc8xxx_gpio_get;
+ gc->direction_output = of_device_is_compatible(np, "fsl,mpc5121-gpio") ?
+ mpc5121_gpio_dir_out : mpc8xxx_gpio_dir_out;
+ gc->get = of_device_is_compatible(np, "fsl,mpc8572-gpio") ?
+ mpc8572_gpio_get : mpc8xxx_gpio_get;
gc->set = mpc8xxx_gpio_set;
gc->to_irq = mpc8xxx_gpio_to_irq;
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 093c90b..4102f63 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -238,10 +238,6 @@
int ret, irq, i;
static DECLARE_BITMAP(init_irq, NR_IRQS);
- pdata = dev->dev.platform_data;
- if (pdata == NULL)
- return -ENODEV;
-
chip = kzalloc(sizeof(*chip), GFP_KERNEL);
if (chip == NULL)
return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index d09a6e0..004b048 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -62,6 +62,7 @@
const struct intel_device_info *info = INTEL_INFO(dev);
seq_printf(m, "gen: %d\n", info->gen);
+ seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev));
#define B(x) seq_printf(m, #x ": %s\n", yesno(info->x))
B(is_mobile);
B(is_i85x);
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index a9533c5..a9ae374 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1454,6 +1454,14 @@
diff1 = now - dev_priv->last_time1;
+ /* Prevent division-by-zero if we are asking too fast.
+ * Also, we don't get interesting results if we are polling
+ * faster than once in 10ms, so just return the saved value
+ * in such cases.
+ */
+ if (diff1 <= 10)
+ return dev_priv->chipset_power;
+
count1 = I915_READ(DMIEC);
count2 = I915_READ(DDREC);
count3 = I915_READ(CSIEC);
@@ -1484,6 +1492,8 @@
dev_priv->last_count1 = total_count;
dev_priv->last_time1 = now;
+ dev_priv->chipset_power = ret;
+
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 15bfa91..a1103fc 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -58,15 +58,15 @@
MODULE_PARM_DESC(powersave,
"Enable powersavings, fbc, downclocking, etc. (default: true)");
-unsigned int i915_semaphores __read_mostly = 0;
+int i915_semaphores __read_mostly = -1;
module_param_named(semaphores, i915_semaphores, int, 0600);
MODULE_PARM_DESC(semaphores,
- "Use semaphores for inter-ring sync (default: false)");
+ "Use semaphores for inter-ring sync (default: -1 (use per-chip defaults))");
-unsigned int i915_enable_rc6 __read_mostly = 0;
+int i915_enable_rc6 __read_mostly = -1;
module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
MODULE_PARM_DESC(i915_enable_rc6,
- "Enable power-saving render C-state 6 (default: true)");
+ "Enable power-saving render C-state 6 (default: -1 (use per-chip default)");
int i915_enable_fbc __read_mostly = -1;
module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
@@ -328,7 +328,7 @@
}
}
-static void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv)
{
int count;
@@ -344,6 +344,22 @@
udelay(10);
}
+void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv)
+{
+ int count;
+
+ count = 0;
+ while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_MT_ACK) & 1))
+ udelay(10);
+
+ I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 1);
+ POSTING_READ(FORCEWAKE_MT);
+
+ count = 0;
+ while (count++ < 50 && (I915_READ_NOTRACE(FORCEWAKE_MT_ACK) & 1) == 0)
+ udelay(10);
+}
+
/*
* Generally this is called implicitly by the register read function. However,
* if some sequence requires the GT to not power down then this function should
@@ -356,15 +372,21 @@
/* Forcewake is atomic in case we get in here without the lock */
if (atomic_add_return(1, &dev_priv->forcewake_count) == 1)
- __gen6_gt_force_wake_get(dev_priv);
+ dev_priv->display.force_wake_get(dev_priv);
}
-static void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
+void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv)
{
I915_WRITE_NOTRACE(FORCEWAKE, 0);
POSTING_READ(FORCEWAKE);
}
+void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv)
+{
+ I915_WRITE_NOTRACE(FORCEWAKE_MT, (1<<16) | 0);
+ POSTING_READ(FORCEWAKE_MT);
+}
+
/*
* see gen6_gt_force_wake_get()
*/
@@ -373,7 +395,7 @@
WARN_ON(!mutex_is_locked(&dev_priv->dev->struct_mutex));
if (atomic_dec_and_test(&dev_priv->forcewake_count))
- __gen6_gt_force_wake_put(dev_priv);
+ dev_priv->display.force_wake_put(dev_priv);
}
void __gen6_gt_wait_for_fifo(struct drm_i915_private *dev_priv)
@@ -903,8 +925,9 @@
/* We give fast paths for the really cool registers */
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
(((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE))
+ ((reg) < 0x40000) && \
+ ((reg) != FORCEWAKE) && \
+ ((reg) != ECOBUS))
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg) { \
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a9c1b9..554bef7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -107,6 +107,7 @@
struct opregion_acpi;
struct opregion_swsci;
struct opregion_asle;
+struct drm_i915_private;
struct intel_opregion {
struct opregion_header *header;
@@ -221,6 +222,8 @@
struct drm_i915_gem_object *obj);
int (*update_plane)(struct drm_crtc *crtc, struct drm_framebuffer *fb,
int x, int y);
+ void (*force_wake_get)(struct drm_i915_private *dev_priv);
+ void (*force_wake_put)(struct drm_i915_private *dev_priv);
/* clock updates for mode set */
/* cursor updates */
/* render clock increase/decrease */
@@ -710,6 +713,7 @@
u64 last_count1;
unsigned long last_time1;
+ unsigned long chipset_power;
u64 last_count2;
struct timespec last_time2;
unsigned long gfx_power;
@@ -998,11 +1002,11 @@
extern unsigned int i915_fbpercrtc __always_unused;
extern int i915_panel_ignore_lid __read_mostly;
extern unsigned int i915_powersave __read_mostly;
-extern unsigned int i915_semaphores __read_mostly;
+extern int i915_semaphores __read_mostly;
extern unsigned int i915_lvds_downclock __read_mostly;
extern int i915_panel_use_ssc __read_mostly;
extern int i915_vbt_sdvo_panel_type __read_mostly;
-extern unsigned int i915_enable_rc6 __read_mostly;
+extern int i915_enable_rc6 __read_mostly;
extern int i915_enable_fbc __read_mostly;
extern bool i915_enable_hangcheck __read_mostly;
@@ -1308,6 +1312,11 @@
extern void intel_detect_pch(struct drm_device *dev);
extern int intel_trans_dp_port_sel(struct drm_crtc *crtc);
+extern void __gen6_gt_force_wake_get(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_mt_get(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_put(struct drm_i915_private *dev_priv);
+extern void __gen6_gt_force_wake_mt_put(struct drm_i915_private *dev_priv);
+
/* overlay */
#ifdef CONFIG_DEBUG_FS
extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
@@ -1352,8 +1361,9 @@
/* We give fast paths for the really cool registers */
#define NEEDS_FORCE_WAKE(dev_priv, reg) \
(((dev_priv)->info->gen >= 6) && \
- ((reg) < 0x40000) && \
- ((reg) != FORCEWAKE))
+ ((reg) < 0x40000) && \
+ ((reg) != FORCEWAKE) && \
+ ((reg) != ECOBUS))
#define __i915_read(x, y) \
u##x i915_read##x(struct drm_i915_private *dev_priv, u32 reg);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 60ff1b6..8359dc7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2026,13 +2026,8 @@
* to handle this, the waiter on a request often wants an associated
* buffer to have made it to the inactive list, and we would need
* a separate wait queue to handle that.
- *
- * To avoid a recursion with the ilk VT-d workaround (that calls
- * gpu_idle when unbinding objects with interruptible==false) don't
- * retire requests in that case (because it might call unbind if the
- * active list holds the last reference to the object).
*/
- if (ret == 0 && dev_priv->mm.interruptible)
+ if (ret == 0)
i915_gem_retire_requests_ring(ring);
return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3693e83..c681dc1 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -32,6 +32,7 @@
#include "i915_drv.h"
#include "i915_trace.h"
#include "intel_drv.h"
+#include <linux/dma_remapping.h>
struct change_domains {
uint32_t invalidate_domains;
@@ -746,6 +747,22 @@
return 0;
}
+static bool
+intel_enable_semaphores(struct drm_device *dev)
+{
+ if (INTEL_INFO(dev)->gen < 6)
+ return 0;
+
+ if (i915_semaphores >= 0)
+ return i915_semaphores;
+
+ /* Enable semaphores on SNB when IO remapping is off */
+ if (INTEL_INFO(dev)->gen == 6)
+ return !intel_iommu_enabled;
+
+ return 1;
+}
+
static int
i915_gem_execbuffer_sync_rings(struct drm_i915_gem_object *obj,
struct intel_ring_buffer *to)
@@ -758,7 +775,7 @@
return 0;
/* XXX gpu semaphores are implicated in various hard hangs on SNB */
- if (INTEL_INFO(obj->base.dev)->gen < 6 || !i915_semaphores)
+ if (!intel_enable_semaphores(obj->base.dev))
return i915_gem_object_wait_rendering(obj);
idx = intel_ring_sync_index(from, to);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b080cc8..a26d5b0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3303,10 +3303,10 @@
/* or SDVOB */
#define HDMIB 0xe1140
#define PORT_ENABLE (1 << 31)
-#define TRANSCODER_A (0)
-#define TRANSCODER_B (1 << 30)
-#define TRANSCODER(pipe) ((pipe) << 30)
-#define TRANSCODER_MASK (1 << 30)
+#define TRANSCODER(pipe) ((pipe) << 30)
+#define TRANSCODER_CPT(pipe) ((pipe) << 29)
+#define TRANSCODER_MASK (1 << 30)
+#define TRANSCODER_MASK_CPT (3 << 29)
#define COLOR_FORMAT_8bpc (0)
#define COLOR_FORMAT_12bpc (3 << 26)
#define SDVOB_HOTPLUG_ENABLE (1 << 23)
@@ -3447,8 +3447,30 @@
#define EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B (0x38<<22)
#define EDP_LINK_TRAIN_VOL_EMP_MASK_SNB (0x3f<<22)
+/* IVB */
+#define EDP_LINK_TRAIN_400MV_0DB_IVB (0x24 <<22)
+#define EDP_LINK_TRAIN_400MV_3_5DB_IVB (0x2a <<22)
+#define EDP_LINK_TRAIN_400MV_6DB_IVB (0x2f <<22)
+#define EDP_LINK_TRAIN_600MV_0DB_IVB (0x30 <<22)
+#define EDP_LINK_TRAIN_600MV_3_5DB_IVB (0x36 <<22)
+#define EDP_LINK_TRAIN_800MV_0DB_IVB (0x38 <<22)
+#define EDP_LINK_TRAIN_800MV_3_5DB_IVB (0x33 <<22)
+
+/* legacy values */
+#define EDP_LINK_TRAIN_500MV_0DB_IVB (0x00 <<22)
+#define EDP_LINK_TRAIN_1000MV_0DB_IVB (0x20 <<22)
+#define EDP_LINK_TRAIN_500MV_3_5DB_IVB (0x02 <<22)
+#define EDP_LINK_TRAIN_1000MV_3_5DB_IVB (0x22 <<22)
+#define EDP_LINK_TRAIN_1000MV_6DB_IVB (0x23 <<22)
+
+#define EDP_LINK_TRAIN_VOL_EMP_MASK_IVB (0x3f<<22)
+
#define FORCEWAKE 0xA18C
#define FORCEWAKE_ACK 0x130090
+#define FORCEWAKE_MT 0xa188 /* multi-threaded */
+#define FORCEWAKE_MT_ACK 0x130040
+#define ECOBUS 0xa180
+#define FORCEWAKE_MT_ENABLE (1<<5)
#define GT_FIFO_FREE_ENTRIES 0x120008
#define GT_FIFO_NUM_RESERVED_ENTRIES 20
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e77a863..d809b03 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -38,8 +38,8 @@
#include "i915_drv.h"
#include "i915_trace.h"
#include "drm_dp_helper.h"
-
#include "drm_crtc_helper.h"
+#include <linux/dma_remapping.h>
#define HAS_eDP (intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))
@@ -4670,6 +4670,7 @@
/**
* intel_choose_pipe_bpp_dither - figure out what color depth the pipe should send
* @crtc: CRTC structure
+ * @mode: requested mode
*
* A pipe may be connected to one or more outputs. Based on the depth of the
* attached framebuffer, choose a good color depth to use on the pipe.
@@ -4681,13 +4682,15 @@
* HDMI supports only 8bpc or 12bpc, so clamp to 8bpc with dither for 10bpc
* Displays may support a restricted set as well, check EDID and clamp as
* appropriate.
+ * DP may want to dither down to 6bpc to fit larger modes
*
* RETURNS:
* Dithering requirement (i.e. false if display bpc and pipe bpc match,
* true if they don't match).
*/
static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
- unsigned int *pipe_bpp)
+ unsigned int *pipe_bpp,
+ struct drm_display_mode *mode)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4758,6 +4761,11 @@
}
}
+ if (mode->private_flags & INTEL_MODE_DP_FORCE_6BPC) {
+ DRM_DEBUG_KMS("Dithering DP to 6bpc\n");
+ display_bpc = 6;
+ }
+
/*
* We could just drive the pipe at the highest bpc all the time and
* enable dithering as needed, but that costs bandwidth. So choose
@@ -5019,6 +5027,16 @@
pipeconf &= ~PIPECONF_DOUBLE_WIDE;
}
+ /* default to 8bpc */
+ pipeconf &= ~(PIPECONF_BPP_MASK | PIPECONF_DITHER_EN);
+ if (is_dp) {
+ if (mode->private_flags & INTEL_MODE_DP_FORCE_6BPC) {
+ pipeconf |= PIPECONF_BPP_6 |
+ PIPECONF_DITHER_EN |
+ PIPECONF_DITHER_TYPE_SP;
+ }
+ }
+
dpll |= DPLL_VCO_ENABLE;
DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe == 0 ? 'A' : 'B');
@@ -5480,7 +5498,7 @@
/* determine panel color depth */
temp = I915_READ(PIPECONF(pipe));
temp &= ~PIPE_BPC_MASK;
- dither = intel_choose_pipe_bpp_dither(crtc, &pipe_bpp);
+ dither = intel_choose_pipe_bpp_dither(crtc, &pipe_bpp, mode);
switch (pipe_bpp) {
case 18:
temp |= PIPE_6BPC;
@@ -7189,11 +7207,16 @@
work->old_fb_obj = intel_fb->obj;
INIT_WORK(&work->work, intel_unpin_work_fn);
+ ret = drm_vblank_get(dev, intel_crtc->pipe);
+ if (ret)
+ goto free_work;
+
/* We borrow the event spin lock for protecting unpin_work */
spin_lock_irqsave(&dev->event_lock, flags);
if (intel_crtc->unpin_work) {
spin_unlock_irqrestore(&dev->event_lock, flags);
kfree(work);
+ drm_vblank_put(dev, intel_crtc->pipe);
DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
return -EBUSY;
@@ -7212,10 +7235,6 @@
crtc->fb = fb;
- ret = drm_vblank_get(dev, intel_crtc->pipe);
- if (ret)
- goto cleanup_objs;
-
work->pending_flip_obj = obj;
work->enable_stall_check = true;
@@ -7238,7 +7257,6 @@
cleanup_pending:
atomic_sub(1 << intel_crtc->plane, &work->old_fb_obj->pending_flip);
-cleanup_objs:
drm_gem_object_unreference(&work->old_fb_obj->base);
drm_gem_object_unreference(&obj->base);
mutex_unlock(&dev->struct_mutex);
@@ -7247,6 +7265,8 @@
intel_crtc->unpin_work = NULL;
spin_unlock_irqrestore(&dev->event_lock, flags);
+ drm_vblank_put(dev, intel_crtc->pipe);
+free_work:
kfree(work);
return ret;
@@ -7887,6 +7907,33 @@
dev_priv->corr = (lcfuse & LCFUSE_HIV_MASK);
}
+static bool intel_enable_rc6(struct drm_device *dev)
+{
+ /*
+ * Respect the kernel parameter if it is set
+ */
+ if (i915_enable_rc6 >= 0)
+ return i915_enable_rc6;
+
+ /*
+ * Disable RC6 on Ironlake
+ */
+ if (INTEL_INFO(dev)->gen == 5)
+ return 0;
+
+ /*
+ * Enable rc6 on Sandybridge if DMA remapping is disabled
+ */
+ if (INTEL_INFO(dev)->gen == 6) {
+ DRM_DEBUG_DRIVER("Sandybridge: intel_iommu_enabled %s -- RC6 %sabled\n",
+ intel_iommu_enabled ? "true" : "false",
+ !intel_iommu_enabled ? "en" : "dis");
+ return !intel_iommu_enabled;
+ }
+ DRM_DEBUG_DRIVER("RC6 enabled\n");
+ return 1;
+}
+
void gen6_enable_rps(struct drm_i915_private *dev_priv)
{
u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
@@ -7923,7 +7970,7 @@
I915_WRITE(GEN6_RC6p_THRESHOLD, 100000);
I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
- if (i915_enable_rc6)
+ if (intel_enable_rc6(dev_priv->dev))
rc6_mask = GEN6_RC_CTL_RC6p_ENABLE |
GEN6_RC_CTL_RC6_ENABLE;
@@ -8372,7 +8419,7 @@
/* rc6 disabled by default due to repeated reports of hanging during
* boot and resume.
*/
- if (!i915_enable_rc6)
+ if (!intel_enable_rc6(dev))
return;
mutex_lock(&dev->struct_mutex);
@@ -8491,6 +8538,28 @@
/* For FIFO watermark updates */
if (HAS_PCH_SPLIT(dev)) {
+ dev_priv->display.force_wake_get = __gen6_gt_force_wake_get;
+ dev_priv->display.force_wake_put = __gen6_gt_force_wake_put;
+
+ /* IVB configs may use multi-threaded forcewake */
+ if (IS_IVYBRIDGE(dev)) {
+ u32 ecobus;
+
+ mutex_lock(&dev->struct_mutex);
+ __gen6_gt_force_wake_mt_get(dev_priv);
+ ecobus = I915_READ(ECOBUS);
+ __gen6_gt_force_wake_mt_put(dev_priv);
+ mutex_unlock(&dev->struct_mutex);
+
+ if (ecobus & FORCEWAKE_MT_ENABLE) {
+ DRM_DEBUG_KMS("Using MT version of forcewake\n");
+ dev_priv->display.force_wake_get =
+ __gen6_gt_force_wake_mt_get;
+ dev_priv->display.force_wake_put =
+ __gen6_gt_force_wake_mt_put;
+ }
+ }
+
if (HAS_PCH_IBX(dev))
dev_priv->display.init_pch_clock_gating = ibx_init_clock_gating;
else if (HAS_PCH_CPT(dev))
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 4d0358f..92b041b 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -208,13 +208,15 @@
*/
static int
-intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock)
+intel_dp_link_required(struct intel_dp *intel_dp, int pixel_clock, int check_bpp)
{
struct drm_crtc *crtc = intel_dp->base.base.crtc;
struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
int bpp = 24;
- if (intel_crtc)
+ if (check_bpp)
+ bpp = check_bpp;
+ else if (intel_crtc)
bpp = intel_crtc->bpp;
return (pixel_clock * bpp + 9) / 10;
@@ -233,6 +235,7 @@
struct intel_dp *intel_dp = intel_attached_dp(connector);
int max_link_clock = intel_dp_link_clock(intel_dp_max_link_bw(intel_dp));
int max_lanes = intel_dp_max_lane_count(intel_dp);
+ int max_rate, mode_rate;
if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) {
if (mode->hdisplay > intel_dp->panel_fixed_mode->hdisplay)
@@ -242,9 +245,17 @@
return MODE_PANEL;
}
- if (intel_dp_link_required(intel_dp, mode->clock)
- > intel_dp_max_data_rate(max_link_clock, max_lanes))
- return MODE_CLOCK_HIGH;
+ mode_rate = intel_dp_link_required(intel_dp, mode->clock, 0);
+ max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
+
+ if (mode_rate > max_rate) {
+ mode_rate = intel_dp_link_required(intel_dp,
+ mode->clock, 18);
+ if (mode_rate > max_rate)
+ return MODE_CLOCK_HIGH;
+ else
+ mode->private_flags |= INTEL_MODE_DP_FORCE_6BPC;
+ }
if (mode->clock < 10000)
return MODE_CLOCK_LOW;
@@ -362,8 +373,8 @@
* clock divider.
*/
if (is_cpu_edp(intel_dp)) {
- if (IS_GEN6(dev))
- aux_clock_divider = 200; /* SNB eDP input clock at 400Mhz */
+ if (IS_GEN6(dev) || IS_GEN7(dev))
+ aux_clock_divider = 200; /* SNB & IVB eDP input clock at 400Mhz */
else
aux_clock_divider = 225; /* eDP input clock at 450Mhz */
} else if (HAS_PCH_SPLIT(dev))
@@ -672,6 +683,7 @@
int lane_count, clock;
int max_lane_count = intel_dp_max_lane_count(intel_dp);
int max_clock = intel_dp_max_link_bw(intel_dp) == DP_LINK_BW_2_7 ? 1 : 0;
+ int bpp = mode->private_flags & INTEL_MODE_DP_FORCE_6BPC ? 18 : 0;
static int bws[2] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7 };
if (is_edp(intel_dp) && intel_dp->panel_fixed_mode) {
@@ -689,7 +701,7 @@
for (clock = 0; clock <= max_clock; clock++) {
int link_avail = intel_dp_max_data_rate(intel_dp_link_clock(bws[clock]), lane_count);
- if (intel_dp_link_required(intel_dp, mode->clock)
+ if (intel_dp_link_required(intel_dp, mode->clock, bpp)
<= link_avail) {
intel_dp->link_bw = bws[clock];
intel_dp->lane_count = lane_count;
@@ -817,10 +829,11 @@
}
/*
- * There are three kinds of DP registers:
+ * There are four kinds of DP registers:
*
* IBX PCH
- * CPU
+ * SNB CPU
+ * IVB CPU
* CPT PCH
*
* IBX PCH and CPU are the same for almost everything,
@@ -873,7 +886,25 @@
/* Split out the IBX/CPU vs CPT settings */
- if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
+ if (is_cpu_edp(intel_dp) && IS_GEN7(dev)) {
+ if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+ intel_dp->DP |= DP_SYNC_HS_HIGH;
+ if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+ intel_dp->DP |= DP_SYNC_VS_HIGH;
+ intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
+
+ if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
+ intel_dp->DP |= DP_ENHANCED_FRAMING;
+
+ intel_dp->DP |= intel_crtc->pipe << 29;
+
+ /* don't miss out required setting for eDP */
+ intel_dp->DP |= DP_PLL_ENABLE;
+ if (adjusted_mode->clock < 200000)
+ intel_dp->DP |= DP_PLL_FREQ_160MHZ;
+ else
+ intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+ } else if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
intel_dp->DP |= intel_dp->color_range;
if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
@@ -1375,34 +1406,59 @@
* These are source-specific values; current Intel hardware supports
* a maximum voltage of 800mV and a maximum pre-emphasis of 6dB
*/
-#define I830_DP_VOLTAGE_MAX DP_TRAIN_VOLTAGE_SWING_800
-#define I830_DP_VOLTAGE_MAX_CPT DP_TRAIN_VOLTAGE_SWING_1200
static uint8_t
-intel_dp_pre_emphasis_max(uint8_t voltage_swing)
+intel_dp_voltage_max(struct intel_dp *intel_dp)
{
- switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
- case DP_TRAIN_VOLTAGE_SWING_400:
- return DP_TRAIN_PRE_EMPHASIS_6;
- case DP_TRAIN_VOLTAGE_SWING_600:
- return DP_TRAIN_PRE_EMPHASIS_6;
- case DP_TRAIN_VOLTAGE_SWING_800:
- return DP_TRAIN_PRE_EMPHASIS_3_5;
- case DP_TRAIN_VOLTAGE_SWING_1200:
- default:
- return DP_TRAIN_PRE_EMPHASIS_0;
+ struct drm_device *dev = intel_dp->base.base.dev;
+
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp))
+ return DP_TRAIN_VOLTAGE_SWING_800;
+ else if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ return DP_TRAIN_VOLTAGE_SWING_1200;
+ else
+ return DP_TRAIN_VOLTAGE_SWING_800;
+}
+
+static uint8_t
+intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
+{
+ struct drm_device *dev = intel_dp->base.base.dev;
+
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+ switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
+ case DP_TRAIN_VOLTAGE_SWING_400:
+ return DP_TRAIN_PRE_EMPHASIS_6;
+ case DP_TRAIN_VOLTAGE_SWING_600:
+ case DP_TRAIN_VOLTAGE_SWING_800:
+ return DP_TRAIN_PRE_EMPHASIS_3_5;
+ default:
+ return DP_TRAIN_PRE_EMPHASIS_0;
+ }
+ } else {
+ switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
+ case DP_TRAIN_VOLTAGE_SWING_400:
+ return DP_TRAIN_PRE_EMPHASIS_6;
+ case DP_TRAIN_VOLTAGE_SWING_600:
+ return DP_TRAIN_PRE_EMPHASIS_6;
+ case DP_TRAIN_VOLTAGE_SWING_800:
+ return DP_TRAIN_PRE_EMPHASIS_3_5;
+ case DP_TRAIN_VOLTAGE_SWING_1200:
+ default:
+ return DP_TRAIN_PRE_EMPHASIS_0;
+ }
}
}
static void
intel_get_adjust_train(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
{
- struct drm_device *dev = intel_dp->base.base.dev;
uint8_t v = 0;
uint8_t p = 0;
int lane;
uint8_t *adjust_request = link_status + (DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS);
- int voltage_max;
+ uint8_t voltage_max;
+ uint8_t preemph_max;
for (lane = 0; lane < intel_dp->lane_count; lane++) {
uint8_t this_v = intel_get_adjust_request_voltage(adjust_request, lane);
@@ -1414,15 +1470,13 @@
p = this_p;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
- voltage_max = I830_DP_VOLTAGE_MAX_CPT;
- else
- voltage_max = I830_DP_VOLTAGE_MAX;
+ voltage_max = intel_dp_voltage_max(intel_dp);
if (v >= voltage_max)
v = voltage_max | DP_TRAIN_MAX_SWING_REACHED;
- if (p >= intel_dp_pre_emphasis_max(v))
- p = intel_dp_pre_emphasis_max(v) | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
+ preemph_max = intel_dp_pre_emphasis_max(intel_dp, v);
+ if (p >= preemph_max)
+ p = preemph_max | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
for (lane = 0; lane < 4; lane++)
intel_dp->train_set[lane] = v | p;
@@ -1494,6 +1548,37 @@
}
}
+/* Gen7's DP voltage swing and pre-emphasis control */
+static uint32_t
+intel_gen7_edp_signal_levels(uint8_t train_set)
+{
+ int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
+ DP_TRAIN_PRE_EMPHASIS_MASK);
+ switch (signal_levels) {
+ case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_0:
+ return EDP_LINK_TRAIN_400MV_0DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_3_5:
+ return EDP_LINK_TRAIN_400MV_3_5DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_6:
+ return EDP_LINK_TRAIN_400MV_6DB_IVB;
+
+ case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_0:
+ return EDP_LINK_TRAIN_600MV_0DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_3_5:
+ return EDP_LINK_TRAIN_600MV_3_5DB_IVB;
+
+ case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_0:
+ return EDP_LINK_TRAIN_800MV_0DB_IVB;
+ case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_3_5:
+ return EDP_LINK_TRAIN_800MV_3_5DB_IVB;
+
+ default:
+ DRM_DEBUG_KMS("Unsupported voltage swing/pre-emphasis level:"
+ "0x%x\n", signal_levels);
+ return EDP_LINK_TRAIN_500MV_0DB_IVB;
+ }
+}
+
static uint8_t
intel_get_lane_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
int lane)
@@ -1599,7 +1684,8 @@
DP_LINK_CONFIGURATION_SIZE);
DP |= DP_PORT_EN;
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
DP &= ~DP_LINK_TRAIN_MASK_CPT;
else
DP &= ~DP_LINK_TRAIN_MASK;
@@ -1613,7 +1699,11 @@
uint8_t link_status[DP_LINK_STATUS_SIZE];
uint32_t signal_levels;
- if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
+
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+ signal_levels = intel_gen7_edp_signal_levels(intel_dp->train_set[0]);
+ DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_IVB) | signal_levels;
+ } else if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
} else {
@@ -1622,7 +1712,7 @@
DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
reg = DP | DP_LINK_TRAIN_PAT_1_CPT;
else
reg = DP | DP_LINK_TRAIN_PAT_1;
@@ -1703,7 +1793,10 @@
break;
}
- if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
+ if (IS_GEN7(dev) && is_cpu_edp(intel_dp)) {
+ signal_levels = intel_gen7_edp_signal_levels(intel_dp->train_set[0]);
+ DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_IVB) | signal_levels;
+ } else if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
} else {
@@ -1711,7 +1804,7 @@
DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
reg = DP | DP_LINK_TRAIN_PAT_2_CPT;
else
reg = DP | DP_LINK_TRAIN_PAT_2;
@@ -1752,7 +1845,7 @@
++tries;
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
reg = DP | DP_LINK_TRAIN_OFF_CPT;
else
reg = DP | DP_LINK_TRAIN_OFF;
@@ -1782,7 +1875,7 @@
udelay(100);
}
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp)) {
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp))) {
DP &= ~DP_LINK_TRAIN_MASK_CPT;
I915_WRITE(intel_dp->output_reg, DP | DP_LINK_TRAIN_PAT_IDLE_CPT);
} else {
@@ -1794,7 +1887,7 @@
msleep(17);
if (is_edp(intel_dp)) {
- if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+ if (HAS_PCH_CPT(dev) && (IS_GEN7(dev) || !is_cpu_edp(intel_dp)))
DP |= DP_LINK_TRAIN_OFF_CPT;
else
DP |= DP_LINK_TRAIN_OFF;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index bd9a604..a1b4343 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -110,6 +110,7 @@
/* drm_display_mode->private_flags */
#define INTEL_MODE_PIXEL_MULTIPLIER_SHIFT (0x0)
#define INTEL_MODE_PIXEL_MULTIPLIER_MASK (0xf << INTEL_MODE_PIXEL_MULTIPLIER_SHIFT)
+#define INTEL_MODE_DP_FORCE_6BPC (0x10)
static inline void
intel_mode_set_pixel_multiplier(struct drm_display_mode *mode,
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 42f165a..e441911 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -715,6 +715,14 @@
DMI_MATCH(DMI_PRODUCT_NAME, "EB1007"),
},
},
+ {
+ .callback = intel_no_lvds_dmi_callback,
+ .ident = "Asus AT5NM10T-I",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "AT5NM10T-I"),
+ },
+ },
{ } /* terminating entry */
};
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 21f60b7..04d79fd 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -178,13 +178,10 @@
if (HAS_PCH_SPLIT(dev)) {
max >>= 16;
} else {
- if (IS_PINEVIEW(dev)) {
+ if (INTEL_INFO(dev)->gen < 4)
max >>= 17;
- } else {
+ else
max >>= 16;
- if (INTEL_INFO(dev)->gen < 4)
- max &= ~1;
- }
if (is_backlight_combination_mode(dev))
max *= 0xff;
@@ -203,13 +200,12 @@
val = I915_READ(BLC_PWM_CPU_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
} else {
val = I915_READ(BLC_PWM_CTL) & BACKLIGHT_DUTY_CYCLE_MASK;
- if (IS_PINEVIEW(dev))
+ if (INTEL_INFO(dev)->gen < 4)
val >>= 1;
if (is_backlight_combination_mode(dev)) {
u8 lbpc;
- val &= ~1;
pci_read_config_byte(dev->pdev, PCI_LBPC, &lbpc);
val *= lbpc;
}
@@ -246,11 +242,9 @@
}
tmp = I915_READ(BLC_PWM_CTL);
- if (IS_PINEVIEW(dev)) {
- tmp &= ~(BACKLIGHT_DUTY_CYCLE_MASK - 1);
+ if (INTEL_INFO(dev)->gen < 4)
level <<= 1;
- } else
- tmp &= ~BACKLIGHT_DUTY_CYCLE_MASK;
+ tmp &= ~BACKLIGHT_DUTY_CYCLE_MASK;
I915_WRITE(BLC_PWM_CTL, tmp | level);
}
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 3003fb2..f7b9268 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -50,6 +50,7 @@
#define IS_TMDS(c) (c->output_flag & SDVO_TMDS_MASK)
#define IS_LVDS(c) (c->output_flag & SDVO_LVDS_MASK)
#define IS_TV_OR_LVDS(c) (c->output_flag & (SDVO_TV_MASK | SDVO_LVDS_MASK))
+#define IS_DIGITAL(c) (c->output_flag & (SDVO_TMDS_MASK | SDVO_LVDS_MASK))
static const char *tv_format_names[] = {
@@ -1086,8 +1087,12 @@
}
sdvox |= (9 << 19) | SDVO_BORDER_ENABLE;
}
- if (intel_crtc->pipe == 1)
- sdvox |= SDVO_PIPE_B_SELECT;
+
+ if (INTEL_PCH_TYPE(dev) >= PCH_CPT)
+ sdvox |= TRANSCODER_CPT(intel_crtc->pipe);
+ else
+ sdvox |= TRANSCODER(intel_crtc->pipe);
+
if (intel_sdvo->has_hdmi_audio)
sdvox |= SDVO_AUDIO_ENABLE;
@@ -1314,6 +1319,18 @@
return status;
}
+static bool
+intel_sdvo_connector_matches_edid(struct intel_sdvo_connector *sdvo,
+ struct edid *edid)
+{
+ bool monitor_is_digital = !!(edid->input & DRM_EDID_INPUT_DIGITAL);
+ bool connector_is_digital = !!IS_DIGITAL(sdvo);
+
+ DRM_DEBUG_KMS("connector_is_digital? %d, monitor_is_digital? %d\n",
+ connector_is_digital, monitor_is_digital);
+ return connector_is_digital == monitor_is_digital;
+}
+
static enum drm_connector_status
intel_sdvo_detect(struct drm_connector *connector, bool force)
{
@@ -1358,10 +1375,12 @@
if (edid == NULL)
edid = intel_sdvo_get_analog_edid(connector);
if (edid != NULL) {
- if (edid->input & DRM_EDID_INPUT_DIGITAL)
- ret = connector_status_disconnected;
- else
+ if (intel_sdvo_connector_matches_edid(intel_sdvo_connector,
+ edid))
ret = connector_status_connected;
+ else
+ ret = connector_status_disconnected;
+
connector->display_info.raw_edid = NULL;
kfree(edid);
} else
@@ -1402,11 +1421,8 @@
edid = intel_sdvo_get_analog_edid(connector);
if (edid != NULL) {
- struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector);
- bool monitor_is_digital = !!(edid->input & DRM_EDID_INPUT_DIGITAL);
- bool connector_is_digital = !!IS_TMDS(intel_sdvo_connector);
-
- if (connector_is_digital == monitor_is_digital) {
+ if (intel_sdvo_connector_matches_edid(to_intel_sdvo_connector(connector),
+ edid)) {
drm_mode_connector_update_edid_property(connector, edid);
drm_add_edid_modes(connector, edid);
}
diff --git a/drivers/hwmon/jz4740-hwmon.c b/drivers/hwmon/jz4740-hwmon.c
index 7a48b1e..5253d23 100644
--- a/drivers/hwmon/jz4740-hwmon.c
+++ b/drivers/hwmon/jz4740-hwmon.c
@@ -59,7 +59,7 @@
{
struct jz4740_hwmon *hwmon = dev_get_drvdata(dev);
struct completion *completion = &hwmon->read_completion;
- unsigned long t;
+ long t;
unsigned long val;
int ret;
@@ -203,7 +203,7 @@
return 0;
}
-struct platform_driver jz4740_hwmon_driver = {
+static struct platform_driver jz4740_hwmon_driver = {
.probe = jz4740_hwmon_probe,
.remove = __devexit_p(jz4740_hwmon_remove),
.driver = {
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a004c39..bdc447f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -405,6 +405,9 @@
int dmar_disabled = 1;
#endif /*CONFIG_INTEL_IOMMU_DEFAULT_ON*/
+int intel_iommu_enabled = 0;
+EXPORT_SYMBOL_GPL(intel_iommu_enabled);
+
static int dmar_map_gfx = 1;
static int dmar_forcedac;
static int intel_iommu_strict;
@@ -3647,6 +3650,8 @@
bus_register_notifier(&pci_bus_type, &device_nb);
+ intel_iommu_enabled = 1;
+
return 0;
}
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index a1cb21f..1e0e27c 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1606,6 +1606,14 @@
MMC_QUIRK_BLK_NO_CMD23),
MMC_FIXUP("MMC32G", 0x11, CID_OEMID_ANY, add_quirk_mmc,
MMC_QUIRK_BLK_NO_CMD23),
+
+ /*
+ * Some Micron MMC cards needs longer data read timeout than
+ * indicated in CSD.
+ */
+ MMC_FIXUP(CID_NAME_ANY, 0x13, 0x200, add_quirk_mmc,
+ MMC_QUIRK_LONG_READ_TIME),
+
END_FIXUP
};
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 5278ffb..950b97d 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -529,6 +529,18 @@
data->timeout_clks = 0;
}
}
+
+ /*
+ * Some cards require longer data read timeout than indicated in CSD.
+ * Address this by setting the read timeout to a "reasonably high"
+ * value. For the cards tested, 300ms has proven enough. If necessary,
+ * this value can be increased if other problematic cards require this.
+ */
+ if (mmc_card_long_read_time(card) && data->flags & MMC_DATA_READ) {
+ data->timeout_ns = 300000000;
+ data->timeout_clks = 0;
+ }
+
/*
* Some cards need very high timeouts if driven in SPI mode.
* The worst observed timeout was 900ms after writing a
@@ -1213,6 +1225,46 @@
mmc_host_clk_release(host);
}
+static void mmc_poweroff_notify(struct mmc_host *host)
+{
+ struct mmc_card *card;
+ unsigned int timeout;
+ unsigned int notify_type = EXT_CSD_NO_POWER_NOTIFICATION;
+ int err = 0;
+
+ card = host->card;
+
+ /*
+ * Send power notify command only if card
+ * is mmc and notify state is powered ON
+ */
+ if (card && mmc_card_mmc(card) &&
+ (card->poweroff_notify_state == MMC_POWERED_ON)) {
+
+ if (host->power_notify_type == MMC_HOST_PW_NOTIFY_SHORT) {
+ notify_type = EXT_CSD_POWER_OFF_SHORT;
+ timeout = card->ext_csd.generic_cmd6_time;
+ card->poweroff_notify_state = MMC_POWEROFF_SHORT;
+ } else {
+ notify_type = EXT_CSD_POWER_OFF_LONG;
+ timeout = card->ext_csd.power_off_longtime;
+ card->poweroff_notify_state = MMC_POWEROFF_LONG;
+ }
+
+ err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+ EXT_CSD_POWER_OFF_NOTIFICATION,
+ notify_type, timeout);
+
+ if (err && err != -EBADMSG)
+ pr_err("Device failed to respond within %d poweroff "
+ "time. Forcefully powering down the device\n",
+ timeout);
+
+ /* Set the card state to no notification after the poweroff */
+ card->poweroff_notify_state = MMC_NO_POWER_NOTIFICATION;
+ }
+}
+
/*
* Apply power to the MMC stack. This is a two-stage process.
* First, we enable power to the card without the clock running.
@@ -1269,42 +1321,12 @@
void mmc_power_off(struct mmc_host *host)
{
- struct mmc_card *card;
- unsigned int notify_type;
- unsigned int timeout;
- int err;
-
mmc_host_clk_hold(host);
- card = host->card;
host->ios.clock = 0;
host->ios.vdd = 0;
- if (card && mmc_card_mmc(card) &&
- (card->poweroff_notify_state == MMC_POWERED_ON)) {
-
- if (host->power_notify_type == MMC_HOST_PW_NOTIFY_SHORT) {
- notify_type = EXT_CSD_POWER_OFF_SHORT;
- timeout = card->ext_csd.generic_cmd6_time;
- card->poweroff_notify_state = MMC_POWEROFF_SHORT;
- } else {
- notify_type = EXT_CSD_POWER_OFF_LONG;
- timeout = card->ext_csd.power_off_longtime;
- card->poweroff_notify_state = MMC_POWEROFF_LONG;
- }
-
- err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
- EXT_CSD_POWER_OFF_NOTIFICATION,
- notify_type, timeout);
-
- if (err && err != -EBADMSG)
- pr_err("Device failed to respond within %d poweroff "
- "time. Forcefully powering down the device\n",
- timeout);
-
- /* Set the card state to no notification after the poweroff */
- card->poweroff_notify_state = MMC_NO_POWER_NOTIFICATION;
- }
+ mmc_poweroff_notify(host);
/*
* Reset ocr mask to be the highest possible voltage supported for
@@ -2196,7 +2218,7 @@
mmc_bus_get(host);
- if (host->bus_ops && !host->bus_dead && host->bus_ops->awake)
+ if (host->bus_ops && !host->bus_dead && host->bus_ops->sleep)
err = host->bus_ops->sleep(host);
mmc_bus_put(host);
@@ -2302,8 +2324,17 @@
* pre-claim the host.
*/
if (mmc_try_claim_host(host)) {
- if (host->bus_ops->suspend)
+ if (host->bus_ops->suspend) {
+ /*
+ * For eMMC 4.5 device send notify command
+ * before sleep, because in sleep state eMMC 4.5
+ * devices respond to only RESET and AWAKE cmd
+ */
+ mmc_poweroff_notify(host);
err = host->bus_ops->suspend(host);
+ }
+ mmc_do_release_host(host);
+
if (err == -ENOSYS || !host->bus_ops->resume) {
/*
* We simply "remove" the card in this case.
@@ -2318,7 +2349,6 @@
host->pm_flags = 0;
err = 0;
}
- mmc_do_release_host(host);
} else {
err = -EBUSY;
}
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index dbf421a..d240427 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -876,17 +876,21 @@
* set the notification byte in the ext_csd register of device
*/
if ((host->caps2 & MMC_CAP2_POWEROFF_NOTIFY) &&
- (card->poweroff_notify_state == MMC_NO_POWER_NOTIFICATION)) {
+ (card->ext_csd.rev >= 6)) {
err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
EXT_CSD_POWER_OFF_NOTIFICATION,
EXT_CSD_POWER_ON,
card->ext_csd.generic_cmd6_time);
if (err && err != -EBADMSG)
goto free_card;
- }
- if (!err)
- card->poweroff_notify_state = MMC_POWERED_ON;
+ /*
+ * The err can be -EBADMSG or 0,
+ * so check for success and update the flag
+ */
+ if (!err)
+ card->poweroff_notify_state = MMC_POWERED_ON;
+ }
/*
* Activate high speed (if supported)
diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c
index 325ea61..8e0fbe9 100644
--- a/drivers/mmc/host/mxcmmc.c
+++ b/drivers/mmc/host/mxcmmc.c
@@ -732,6 +732,7 @@
"failed to config DMA channel. Falling back to PIO\n");
dma_release_channel(host->dma);
host->do_dma = 0;
+ host->dma = NULL;
}
}
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 101cd31..d5fe43d 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -1010,6 +1010,7 @@
host->data->sg_len,
omap_hsmmc_get_dma_dir(host, host->data));
omap_free_dma(dma_ch);
+ host->data->host_cookie = 0;
}
host->data = NULL;
}
@@ -1575,8 +1576,10 @@
struct mmc_data *data = mrq->data;
if (host->use_dma) {
- dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
- omap_hsmmc_get_dma_dir(host, data));
+ if (data->host_cookie)
+ dma_unmap_sg(mmc_dev(host->mmc), data->sg,
+ data->sg_len,
+ omap_hsmmc_get_dma_dir(host, data));
data->host_cookie = 0;
}
}
diff --git a/drivers/mmc/host/sdhci-cns3xxx.c b/drivers/mmc/host/sdhci-cns3xxx.c
index 4b920b7..87b6f07 100644
--- a/drivers/mmc/host/sdhci-cns3xxx.c
+++ b/drivers/mmc/host/sdhci-cns3xxx.c
@@ -15,6 +15,7 @@
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/mmc/host.h>
+#include <linux/module.h>
#include <mach/cns3xxx.h>
#include "sdhci-pltfm.h"
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index 3d00e72..cb60c41 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -644,8 +644,6 @@
static struct platform_driver sdhci_s3c_driver = {
.probe = sdhci_s3c_probe,
.remove = __devexit_p(sdhci_s3c_remove),
- .suspend = sdhci_s3c_suspend,
- .resume = sdhci_s3c_resume,
.driver = {
.owner = THIS_MODULE,
.name = "s3c-sdhci",
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 369366c..d5505f3 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -908,7 +908,7 @@
if (host->power) {
pm_runtime_put(&host->pd->dev);
host->power = false;
- if (p->down_pwr)
+ if (p->down_pwr && ios->power_mode == MMC_POWER_OFF)
p->down_pwr(host->pd);
}
host->state = STATE_IDLE;
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index d85a60c..4208b39 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -798,7 +798,7 @@
/* start bus clock */
tmio_mmc_clk_start(host);
} else if (ios->power_mode != MMC_POWER_UP) {
- if (host->set_pwr)
+ if (host->set_pwr && ios->power_mode == MMC_POWER_OFF)
host->set_pwr(host->pdev, 0);
if ((pdata->flags & TMIO_MMC_HAS_COLD_CD) &&
pdata->power) {
diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c
index 1124ce0..c136230 100644
--- a/drivers/net/ethernet/freescale/fec.c
+++ b/drivers/net/ethernet/freescale/fec.c
@@ -232,6 +232,7 @@
struct platform_device *pdev;
int opened;
+ int dev_id;
/* Phylib and MDIO interface */
struct mii_bus *mii_bus;
@@ -837,7 +838,7 @@
/* Adjust MAC if using macaddr */
if (iap == macaddr)
- ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->pdev->id;
+ ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id;
}
/* ------------------------------------------------------------------------- */
@@ -953,7 +954,7 @@
char mdio_bus_id[MII_BUS_ID_SIZE];
char phy_name[MII_BUS_ID_SIZE + 3];
int phy_id;
- int dev_id = fep->pdev->id;
+ int dev_id = fep->dev_id;
fep->phy_dev = NULL;
@@ -1031,7 +1032,7 @@
* mdio interface in board design, and need to be configured by
* fec0 mii_bus.
*/
- if ((id_entry->driver_data & FEC_QUIRK_ENET_MAC) && pdev->id > 0) {
+ if ((id_entry->driver_data & FEC_QUIRK_ENET_MAC) && fep->dev_id > 0) {
/* fec1 uses fec0 mii_bus */
fep->mii_bus = fec0_mii_bus;
return 0;
@@ -1063,7 +1064,7 @@
fep->mii_bus->read = fec_enet_mdio_read;
fep->mii_bus->write = fec_enet_mdio_write;
fep->mii_bus->reset = fec_enet_mdio_reset;
- snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id + 1);
+ snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", fep->dev_id + 1);
fep->mii_bus->priv = fep;
fep->mii_bus->parent = &pdev->dev;
@@ -1521,6 +1522,7 @@
int i, irq, ret = 0;
struct resource *r;
const struct of_device_id *of_id;
+ static int dev_id;
of_id = of_match_device(fec_dt_ids, &pdev->dev);
if (of_id)
@@ -1548,6 +1550,7 @@
fep->hwp = ioremap(r->start, resource_size(r));
fep->pdev = pdev;
+ fep->dev_id = dev_id++;
if (!fep->hwp) {
ret = -ENOMEM;
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 52f4e8a..4d9f84b 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -183,28 +183,10 @@
}
EXPORT_SYMBOL_GPL(fsl_pq_mdio_bus_name);
-/* Scan the bus in reverse, looking for an empty spot */
-static int fsl_pq_mdio_find_free(struct mii_bus *new_bus)
-{
- int i;
- for (i = PHY_MAX_ADDR; i > 0; i--) {
- u32 phy_id;
-
- if (get_phy_id(new_bus, i, &phy_id))
- return -1;
-
- if (phy_id == 0xffffffff)
- break;
- }
-
- return i;
-}
-
-
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np)
{
+#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
struct gfar __iomem *enet_regs;
/*
@@ -220,15 +202,15 @@
} else if (of_device_is_compatible(np, "fsl,etsec2-mdio") ||
of_device_is_compatible(np, "fsl,etsec2-tbi")) {
return of_iomap(np, 1);
- } else
- return NULL;
-}
+ }
#endif
+ return NULL;
+}
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id)
{
+#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
struct device_node *np = NULL;
int err = 0;
@@ -261,9 +243,10 @@
return err;
else
return -EINVAL;
-}
+#else
+ return -ENODEV;
#endif
-
+}
static int fsl_pq_mdio_probe(struct platform_device *ofdev)
{
@@ -339,19 +322,13 @@
of_device_is_compatible(np, "fsl,etsec2-mdio") ||
of_device_is_compatible(np, "fsl,etsec2-tbi") ||
of_device_is_compatible(np, "gianfar")) {
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
tbipa = get_gfar_tbipa(regs, np);
if (!tbipa) {
err = -EINVAL;
goto err_free_irqs;
}
-#else
- err = -ENODEV;
- goto err_free_irqs;
-#endif
} else if (of_device_is_compatible(np, "fsl,ucc-mdio") ||
of_device_is_compatible(np, "ucc_geth_phy")) {
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
u32 id;
static u32 mii_mng_master;
@@ -364,10 +341,6 @@
mii_mng_master = id;
ucc_set_qe_mux_mii_mng(id - 1);
}
-#else
- err = -ENODEV;
- goto err_free_irqs;
-#endif
} else {
err = -ENODEV;
goto err_free_irqs;
@@ -386,16 +359,6 @@
}
if (tbiaddr == -1) {
- out_be32(tbipa, 0);
-
- tbiaddr = fsl_pq_mdio_find_free(new_bus);
- }
-
- /*
- * We define TBIPA at 0 to be illegal, opting to fail for boards that
- * have PHYs at 1-31, rather than change tbipa and rescan.
- */
- if (tbiaddr == 0) {
err = -EBUSY;
goto err_free_irqs;
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 89f829f..f8a6853 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -423,10 +423,8 @@
lock_sock(sk);
opt->src_addr = sp->sa_addr.pptp;
- if (add_chan(po)) {
- release_sock(sk);
+ if (add_chan(po))
error = -EBUSY;
- }
release_sock(sk);
return error;
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 93fbe6f..d2348a5 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -286,7 +286,7 @@
ath_start_ani(common);
}
- if (ath9k_hw_ops(ah)->antdiv_comb_conf_get && sc->ant_rx != 3) {
+ if ((ah->caps.hw_caps & ATH9K_HW_CAP_ANT_DIV_COMB) && sc->ant_rx != 3) {
struct ath_hw_antcomb_conf div_ant_conf;
u8 lna_conf;
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/phy.c b/drivers/net/wireless/rtlwifi/rtl8192ce/phy.c
index 592a10a..3b585aa 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/phy.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/phy.c
@@ -569,7 +569,7 @@
}
case ERFSLEEP:{
if (ppsc->rfpwr_state == ERFOFF)
- break;
+ return false;
for (queue_id = 0, i = 0;
queue_id < RTL_PCI_MAX_TX_QUEUE_COUNT;) {
ring = &pcipriv->dev.tx_ring[queue_id];
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/phy.c b/drivers/net/wireless/rtlwifi/rtl8192cu/phy.c
index 7285290..e49cf22 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/phy.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/phy.c
@@ -548,7 +548,7 @@
break;
case ERFSLEEP:
if (ppsc->rfpwr_state == ERFOFF)
- break;
+ return false;
for (queue_id = 0, i = 0;
queue_id < RTL_PCI_MAX_TX_QUEUE_COUNT;) {
ring = &pcipriv->dev.tx_ring[queue_id];
diff --git a/drivers/net/wireless/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/rtlwifi/rtl8192de/phy.c
index 3ac7af1..0883349 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192de/phy.c
@@ -3374,7 +3374,7 @@
break;
case ERFSLEEP:
if (ppsc->rfpwr_state == ERFOFF)
- break;
+ return false;
for (queue_id = 0, i = 0;
queue_id < RTL_PCI_MAX_TX_QUEUE_COUNT;) {
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/phy.c b/drivers/net/wireless/rtlwifi/rtl8192se/phy.c
index f27171a..f10ac1a 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/phy.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/phy.c
@@ -602,7 +602,7 @@
}
case ERFSLEEP:
if (ppsc->rfpwr_state == ERFOFF)
- break;
+ return false;
for (queue_id = 0, i = 0;
queue_id < RTL_PCI_MAX_TX_QUEUE_COUNT;) {
diff --git a/drivers/oprofile/nmi_timer_int.c b/drivers/oprofile/nmi_timer_int.c
new file mode 100644
index 0000000..76f1c93
--- /dev/null
+++ b/drivers/oprofile/nmi_timer_int.c
@@ -0,0 +1,173 @@
+/**
+ * @file nmi_timer_int.c
+ *
+ * @remark Copyright 2011 Advanced Micro Devices, Inc.
+ *
+ * @author Robert Richter <robert.richter@amd.com>
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/oprofile.h>
+#include <linux/perf_event.h>
+
+#ifdef CONFIG_OPROFILE_NMI_TIMER
+
+static DEFINE_PER_CPU(struct perf_event *, nmi_timer_events);
+static int ctr_running;
+
+static struct perf_event_attr nmi_timer_attr = {
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ .size = sizeof(struct perf_event_attr),
+ .pinned = 1,
+ .disabled = 1,
+};
+
+static void nmi_timer_callback(struct perf_event *event,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
+{
+ event->hw.interrupts = 0; /* don't throttle interrupts */
+ oprofile_add_sample(regs, 0);
+}
+
+static int nmi_timer_start_cpu(int cpu)
+{
+ struct perf_event *event = per_cpu(nmi_timer_events, cpu);
+
+ if (!event) {
+ event = perf_event_create_kernel_counter(&nmi_timer_attr, cpu, NULL,
+ nmi_timer_callback, NULL);
+ if (IS_ERR(event))
+ return PTR_ERR(event);
+ per_cpu(nmi_timer_events, cpu) = event;
+ }
+
+ if (event && ctr_running)
+ perf_event_enable(event);
+
+ return 0;
+}
+
+static void nmi_timer_stop_cpu(int cpu)
+{
+ struct perf_event *event = per_cpu(nmi_timer_events, cpu);
+
+ if (event && ctr_running)
+ perf_event_disable(event);
+}
+
+static int nmi_timer_cpu_notifier(struct notifier_block *b, unsigned long action,
+ void *data)
+{
+ int cpu = (unsigned long)data;
+ switch (action) {
+ case CPU_DOWN_FAILED:
+ case CPU_ONLINE:
+ nmi_timer_start_cpu(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ nmi_timer_stop_cpu(cpu);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block nmi_timer_cpu_nb = {
+ .notifier_call = nmi_timer_cpu_notifier
+};
+
+static int nmi_timer_start(void)
+{
+ int cpu;
+
+ get_online_cpus();
+ ctr_running = 1;
+ for_each_online_cpu(cpu)
+ nmi_timer_start_cpu(cpu);
+ put_online_cpus();
+
+ return 0;
+}
+
+static void nmi_timer_stop(void)
+{
+ int cpu;
+
+ get_online_cpus();
+ for_each_online_cpu(cpu)
+ nmi_timer_stop_cpu(cpu);
+ ctr_running = 0;
+ put_online_cpus();
+}
+
+static void nmi_timer_shutdown(void)
+{
+ struct perf_event *event;
+ int cpu;
+
+ get_online_cpus();
+ unregister_cpu_notifier(&nmi_timer_cpu_nb);
+ for_each_possible_cpu(cpu) {
+ event = per_cpu(nmi_timer_events, cpu);
+ if (!event)
+ continue;
+ perf_event_disable(event);
+ per_cpu(nmi_timer_events, cpu) = NULL;
+ perf_event_release_kernel(event);
+ }
+
+ put_online_cpus();
+}
+
+static int nmi_timer_setup(void)
+{
+ int cpu, err;
+ u64 period;
+
+ /* clock cycles per tick: */
+ period = (u64)cpu_khz * 1000;
+ do_div(period, HZ);
+ nmi_timer_attr.sample_period = period;
+
+ get_online_cpus();
+ err = register_cpu_notifier(&nmi_timer_cpu_nb);
+ if (err)
+ goto out;
+ /* can't attach events to offline cpus: */
+ for_each_online_cpu(cpu) {
+ err = nmi_timer_start_cpu(cpu);
+ if (err)
+ break;
+ }
+ if (err)
+ nmi_timer_shutdown();
+out:
+ put_online_cpus();
+ return err;
+}
+
+int __init op_nmi_timer_init(struct oprofile_operations *ops)
+{
+ int err = 0;
+
+ err = nmi_timer_setup();
+ if (err)
+ return err;
+ nmi_timer_shutdown(); /* only check, don't alloc */
+
+ ops->create_files = NULL;
+ ops->setup = nmi_timer_setup;
+ ops->shutdown = nmi_timer_shutdown;
+ ops->start = nmi_timer_start;
+ ops->stop = nmi_timer_stop;
+ ops->cpu_type = "timer";
+
+ printk(KERN_INFO "oprofile: using NMI timer interrupt.\n");
+
+ return 0;
+}
+
+#endif
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index f8c752e..ed2c3ec 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -246,37 +246,31 @@
int err;
/* always init architecture to setup backtrace support */
+ timer_mode = 0;
err = oprofile_arch_init(&oprofile_ops);
+ if (!err) {
+ if (!timer && !oprofilefs_register())
+ return 0;
+ oprofile_arch_exit();
+ }
- timer_mode = err || timer; /* fall back to timer mode on errors */
- if (timer_mode) {
- if (!err)
- oprofile_arch_exit();
+ /* setup timer mode: */
+ timer_mode = 1;
+ /* no nmi timer mode if oprofile.timer is set */
+ if (timer || op_nmi_timer_init(&oprofile_ops)) {
err = oprofile_timer_init(&oprofile_ops);
if (err)
return err;
}
- err = oprofilefs_register();
- if (!err)
- return 0;
-
- /* failed */
- if (timer_mode)
- oprofile_timer_exit();
- else
- oprofile_arch_exit();
-
- return err;
+ return oprofilefs_register();
}
static void __exit oprofile_exit(void)
{
oprofilefs_unregister();
- if (timer_mode)
- oprofile_timer_exit();
- else
+ if (!timer_mode)
oprofile_arch_exit();
}
diff --git a/drivers/oprofile/oprof.h b/drivers/oprofile/oprof.h
index 177b73d..d32ef81 100644
--- a/drivers/oprofile/oprof.h
+++ b/drivers/oprofile/oprof.h
@@ -35,7 +35,15 @@
void oprofile_create_files(struct super_block *sb, struct dentry *root);
int oprofile_timer_init(struct oprofile_operations *ops);
-void oprofile_timer_exit(void);
+#ifdef CONFIG_OPROFILE_NMI_TIMER
+int op_nmi_timer_init(struct oprofile_operations *ops);
+#else
+static inline int op_nmi_timer_init(struct oprofile_operations *ops)
+{
+ return -ENODEV;
+}
+#endif
+
int oprofile_set_ulong(unsigned long *addr, unsigned long val);
int oprofile_set_timeout(unsigned long time);
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 878fba1..93404f7 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -97,24 +97,24 @@
.notifier_call = oprofile_cpu_notify,
};
-int oprofile_timer_init(struct oprofile_operations *ops)
+static int oprofile_hrtimer_setup(void)
{
- int rc;
-
- rc = register_hotcpu_notifier(&oprofile_cpu_notifier);
- if (rc)
- return rc;
- ops->create_files = NULL;
- ops->setup = NULL;
- ops->shutdown = NULL;
- ops->start = oprofile_hrtimer_start;
- ops->stop = oprofile_hrtimer_stop;
- ops->cpu_type = "timer";
- printk(KERN_INFO "oprofile: using timer interrupt.\n");
- return 0;
+ return register_hotcpu_notifier(&oprofile_cpu_notifier);
}
-void oprofile_timer_exit(void)
+static void oprofile_hrtimer_shutdown(void)
{
unregister_hotcpu_notifier(&oprofile_cpu_notifier);
}
+
+int oprofile_timer_init(struct oprofile_operations *ops)
+{
+ ops->create_files = NULL;
+ ops->setup = oprofile_hrtimer_setup;
+ ops->shutdown = oprofile_hrtimer_shutdown;
+ ops->start = oprofile_hrtimer_start;
+ ops->stop = oprofile_hrtimer_stop;
+ ops->cpu_type = "timer";
+ printk(KERN_INFO "oprofile: using timer interrupt.\n");
+ return 0;
+}
diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c
index 5f94d22..5426682 100644
--- a/drivers/sbus/char/bbc_i2c.c
+++ b/drivers/sbus/char/bbc_i2c.c
@@ -233,13 +233,9 @@
int ret = 0;
while (len > 0) {
- int err = bbc_i2c_writeb(client, *buf, off);
-
- if (err < 0) {
- ret = err;
+ ret = bbc_i2c_writeb(client, *buf, off);
+ if (ret < 0)
break;
- }
-
len--;
buf++;
off++;
@@ -253,11 +249,9 @@
int ret = 0;
while (len > 0) {
- int err = bbc_i2c_readb(client, buf, off);
- if (err < 0) {
- ret = err;
+ ret = bbc_i2c_readb(client, buf, off);
+ if (ret < 0)
break;
- }
len--;
buf++;
off++;
@@ -422,17 +416,6 @@
.remove = __devexit_p(bbc_i2c_remove),
};
-static int __init bbc_i2c_init(void)
-{
- return platform_driver_register(&bbc_i2c_driver);
-}
-
-static void __exit bbc_i2c_exit(void)
-{
- platform_driver_unregister(&bbc_i2c_driver);
-}
-
-module_init(bbc_i2c_init);
-module_exit(bbc_i2c_exit);
+module_platform_driver(bbc_i2c_driver);
MODULE_LICENSE("GPL");
diff --git a/drivers/sbus/char/display7seg.c b/drivers/sbus/char/display7seg.c
index 965a1fc..4b99397 100644
--- a/drivers/sbus/char/display7seg.c
+++ b/drivers/sbus/char/display7seg.c
@@ -275,15 +275,4 @@
.remove = __devexit_p(d7s_remove),
};
-static int __init d7s_init(void)
-{
- return platform_driver_register(&d7s_driver);
-}
-
-static void __exit d7s_exit(void)
-{
- platform_driver_unregister(&d7s_driver);
-}
-
-module_init(d7s_init);
-module_exit(d7s_exit);
+module_platform_driver(d7s_driver);
diff --git a/drivers/sbus/char/envctrl.c b/drivers/sbus/char/envctrl.c
index be7b4e5..339fd6f 100644
--- a/drivers/sbus/char/envctrl.c
+++ b/drivers/sbus/char/envctrl.c
@@ -1138,16 +1138,6 @@
.remove = __devexit_p(envctrl_remove),
};
-static int __init envctrl_init(void)
-{
- return platform_driver_register(&envctrl_driver);
-}
+module_platform_driver(envctrl_driver);
-static void __exit envctrl_exit(void)
-{
- platform_driver_unregister(&envctrl_driver);
-}
-
-module_init(envctrl_init);
-module_exit(envctrl_exit);
MODULE_LICENSE("GPL");
diff --git a/drivers/sbus/char/flash.c b/drivers/sbus/char/flash.c
index 73dd4e7..826157f 100644
--- a/drivers/sbus/char/flash.c
+++ b/drivers/sbus/char/flash.c
@@ -216,16 +216,6 @@
.remove = __devexit_p(flash_remove),
};
-static int __init flash_init(void)
-{
- return platform_driver_register(&flash_driver);
-}
+module_platform_driver(flash_driver);
-static void __exit flash_cleanup(void)
-{
- platform_driver_unregister(&flash_driver);
-}
-
-module_init(flash_init);
-module_exit(flash_cleanup);
MODULE_LICENSE("GPL");
diff --git a/drivers/sbus/char/uctrl.c b/drivers/sbus/char/uctrl.c
index ebce963..0b31658 100644
--- a/drivers/sbus/char/uctrl.c
+++ b/drivers/sbus/char/uctrl.c
@@ -435,16 +435,6 @@
};
-static int __init uctrl_init(void)
-{
- return platform_driver_register(&uctrl_driver);
-}
+module_platform_driver(uctrl_driver);
-static void __exit uctrl_exit(void)
-{
- platform_driver_unregister(&uctrl_driver);
-}
-
-module_init(uctrl_init);
-module_exit(uctrl_exit);
MODULE_LICENSE("GPL");
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index 84c934c..520e828 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -517,10 +517,14 @@
static void __devinit ssb_pcicore_init_clientmode(struct ssb_pcicore *pc)
{
- ssb_pcicore_fix_sprom_core_index(pc);
+ struct ssb_device *pdev = pc->dev;
+ struct ssb_bus *bus = pdev->bus;
+
+ if (bus->bustype == SSB_BUSTYPE_PCI)
+ ssb_pcicore_fix_sprom_core_index(pc);
/* Disable PCI interrupts. */
- ssb_write32(pc->dev, SSB_INTVEC, 0);
+ ssb_write32(pdev, SSB_INTVEC, 0);
/* Additional PCIe always once-executed workarounds */
if (pc->dev->id.coreid == SSB_DEV_PCIE) {
diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c
index fb2e89c..5385da2 100644
--- a/drivers/staging/rtl8712/usb_intf.c
+++ b/drivers/staging/rtl8712/usb_intf.c
@@ -89,6 +89,7 @@
{USB_DEVICE(0x0DF6, 0x0045)},
{USB_DEVICE(0x0DF6, 0x0059)}, /* 11n mode disable */
{USB_DEVICE(0x0DF6, 0x004B)},
+ {USB_DEVICE(0x0DF6, 0x005D)},
{USB_DEVICE(0x0DF6, 0x0063)},
/* Sweex */
{USB_DEVICE(0x177F, 0x0154)},
diff --git a/drivers/staging/tidspbridge/core/dsp-clock.c b/drivers/staging/tidspbridge/core/dsp-clock.c
index 3d1279c..7eb5617 100644
--- a/drivers/staging/tidspbridge/core/dsp-clock.c
+++ b/drivers/staging/tidspbridge/core/dsp-clock.c
@@ -54,6 +54,7 @@
/* Bridge GPT id (1 - 4), DM Timer id (5 - 8) */
#define DMT_ID(id) ((id) + 4)
+#define DM_TIMER_CLOCKS 4
/* Bridge MCBSP id (6 - 10), OMAP Mcbsp id (0 - 4) */
#define MCBSP_ID(id) ((id) - 6)
@@ -114,8 +115,13 @@
*/
void dsp_clk_exit(void)
{
+ int i;
+
dsp_clock_disable_all(dsp_clocks);
+ for (i = 0; i < DM_TIMER_CLOCKS; i++)
+ omap_dm_timer_free(timer[i]);
+
clk_put(iva2_clk);
clk_put(ssi.sst_fck);
clk_put(ssi.ssr_fck);
@@ -130,9 +136,13 @@
void dsp_clk_init(void)
{
static struct platform_device dspbridge_device;
+ int i, id;
dspbridge_device.dev.bus = &platform_bus_type;
+ for (i = 0, id = 5; i < DM_TIMER_CLOCKS; i++, id++)
+ timer[i] = omap_dm_timer_request_specific(id);
+
iva2_clk = clk_get(&dspbridge_device.dev, "iva2_ck");
if (IS_ERR(iva2_clk))
dev_err(bridge, "failed to get iva2 clock %p\n", iva2_clk);
@@ -204,8 +214,7 @@
clk_enable(iva2_clk);
break;
case GPT_CLK:
- timer[clk_id - 1] =
- omap_dm_timer_request_specific(DMT_ID(clk_id));
+ status = omap_dm_timer_start(timer[clk_id - 1]);
break;
#ifdef CONFIG_OMAP_MCBSP
case MCBSP_CLK:
@@ -281,7 +290,7 @@
clk_disable(iva2_clk);
break;
case GPT_CLK:
- omap_dm_timer_free(timer[clk_id - 1]);
+ status = omap_dm_timer_stop(timer[clk_id - 1]);
break;
#ifdef CONFIG_OMAP_MCBSP
case MCBSP_CLK:
diff --git a/drivers/staging/tidspbridge/rmgr/drv_interface.c b/drivers/staging/tidspbridge/rmgr/drv_interface.c
index c43c7e3..76cfc6e 100644
--- a/drivers/staging/tidspbridge/rmgr/drv_interface.c
+++ b/drivers/staging/tidspbridge/rmgr/drv_interface.c
@@ -24,11 +24,7 @@
#include <linux/types.h>
#include <linux/platform_device.h>
#include <linux/pm.h>
-
-#ifdef MODULE
#include <linux/module.h>
-#endif
-
#include <linux/device.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index e8c564a..a8078d0 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1458,6 +1458,16 @@
},
{ USB_DEVICE(0x22b8, 0x6425), /* Motorola MOTOMAGX phones */
},
+ /* Motorola H24 HSPA module: */
+ { USB_DEVICE(0x22b8, 0x2d91) }, /* modem */
+ { USB_DEVICE(0x22b8, 0x2d92) }, /* modem + diagnostics */
+ { USB_DEVICE(0x22b8, 0x2d93) }, /* modem + AT port */
+ { USB_DEVICE(0x22b8, 0x2d95) }, /* modem + AT port + diagnostics */
+ { USB_DEVICE(0x22b8, 0x2d96) }, /* modem + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d97) }, /* modem + diagnostics + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d99) }, /* modem + AT port + NMEA */
+ { USB_DEVICE(0x22b8, 0x2d9a) }, /* modem + AT port + diagnostics + NMEA */
+
{ USB_DEVICE(0x0572, 0x1329), /* Hummingbird huc56s (Conexant) */
.driver_info = NO_UNION_NORMAL, /* union descriptor misplaced on
data interface instead of
diff --git a/drivers/usb/gadget/f_mass_storage.c b/drivers/usb/gadget/f_mass_storage.c
index c39d588..1a6f415 100644
--- a/drivers/usb/gadget/f_mass_storage.c
+++ b/drivers/usb/gadget/f_mass_storage.c
@@ -2975,6 +2975,7 @@
fsg_common_put(common);
usb_free_descriptors(fsg->function.descriptors);
usb_free_descriptors(fsg->function.hs_descriptors);
+ usb_free_descriptors(fsg->function.ss_descriptors);
kfree(fsg);
}
diff --git a/drivers/usb/renesas_usbhs/mod.c b/drivers/usb/renesas_usbhs/mod.c
index 053f86d..ad96a38 100644
--- a/drivers/usb/renesas_usbhs/mod.c
+++ b/drivers/usb/renesas_usbhs/mod.c
@@ -349,7 +349,7 @@
if (mod->irq_attch)
intenb1 |= ATTCHE;
- if (mod->irq_attch)
+ if (mod->irq_dtch)
intenb1 |= DTCHE;
if (mod->irq_sign)
diff --git a/drivers/usb/renesas_usbhs/mod_host.c b/drivers/usb/renesas_usbhs/mod_host.c
index bade761..7955de5 100644
--- a/drivers/usb/renesas_usbhs/mod_host.c
+++ b/drivers/usb/renesas_usbhs/mod_host.c
@@ -1267,6 +1267,7 @@
dev_err(dev, "Failed to create hcd\n");
return -ENOMEM;
}
+ hcd->has_tt = 1; /* for low/full speed */
pipe_info = kzalloc(sizeof(*pipe_info) * pipe_size, GFP_KERNEL);
if (!pipe_info) {
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index e342660..6dd6453 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -663,7 +663,12 @@
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x01) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x02) },
{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x03) },
- { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x08) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x10) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x12) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x13) },
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x01) }, /* E398 3G Modem */
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x02) }, /* E398 3G PC UI Interface */
+ { USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x02, 0x03) }, /* E398 3G Application Interface */
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V740) },
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 8e964b9..284798a 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -166,7 +166,7 @@
/*
* Get IO TLB memory from any location.
*/
- xen_io_tlb_start = alloc_bootmem(bytes);
+ xen_io_tlb_start = alloc_bootmem_pages(PAGE_ALIGN(bytes));
if (!xen_io_tlb_start) {
m = "Cannot allocate Xen-SWIOTLB buffer!\n";
goto error;
@@ -179,7 +179,7 @@
bytes,
xen_io_tlb_nslabs);
if (rc) {
- free_bootmem(__pa(xen_io_tlb_start), bytes);
+ free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes));
m = "Failed to get contiguous memory for DMA from Xen!\n"\
"You either: don't have the permissions, do not have"\
" enough free memory under 4GB, or the hypervisor memory"\
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 7ec1409..cb97174 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -64,6 +64,8 @@
int idle;
};
+static int __btrfs_start_workers(struct btrfs_workers *workers);
+
/*
* btrfs_start_workers uses kthread_run, which can block waiting for memory
* for a very long time. It will actually throttle on page writeback,
@@ -88,27 +90,10 @@
{
struct worker_start *start;
start = container_of(work, struct worker_start, work);
- btrfs_start_workers(start->queue, 1);
+ __btrfs_start_workers(start->queue);
kfree(start);
}
-static int start_new_worker(struct btrfs_workers *queue)
-{
- struct worker_start *start;
- int ret;
-
- start = kzalloc(sizeof(*start), GFP_NOFS);
- if (!start)
- return -ENOMEM;
-
- start->work.func = start_new_worker_func;
- start->queue = queue;
- ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
- if (ret)
- kfree(start);
- return ret;
-}
-
/*
* helper function to move a thread onto the idle list after it
* has finished some requests.
@@ -153,12 +138,20 @@
static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
{
struct btrfs_workers *workers = worker->workers;
+ struct worker_start *start;
unsigned long flags;
rmb();
if (!workers->atomic_start_pending)
return;
+ start = kzalloc(sizeof(*start), GFP_NOFS);
+ if (!start)
+ return;
+
+ start->work.func = start_new_worker_func;
+ start->queue = workers;
+
spin_lock_irqsave(&workers->lock, flags);
if (!workers->atomic_start_pending)
goto out;
@@ -170,10 +163,11 @@
workers->num_workers_starting += 1;
spin_unlock_irqrestore(&workers->lock, flags);
- start_new_worker(workers);
+ btrfs_queue_worker(workers->atomic_worker_start, &start->work);
return;
out:
+ kfree(start);
spin_unlock_irqrestore(&workers->lock, flags);
}
@@ -331,7 +325,7 @@
run_ordered_completions(worker->workers, work);
check_pending_worker_creates(worker);
-
+ cond_resched();
}
spin_lock_irq(&worker->lock);
@@ -462,56 +456,55 @@
* starts new worker threads. This does not enforce the max worker
* count in case you need to temporarily go past it.
*/
-static int __btrfs_start_workers(struct btrfs_workers *workers,
- int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers)
{
struct btrfs_worker_thread *worker;
int ret = 0;
- int i;
- for (i = 0; i < num_workers; i++) {
- worker = kzalloc(sizeof(*worker), GFP_NOFS);
- if (!worker) {
- ret = -ENOMEM;
- goto fail;
- }
-
- INIT_LIST_HEAD(&worker->pending);
- INIT_LIST_HEAD(&worker->prio_pending);
- INIT_LIST_HEAD(&worker->worker_list);
- spin_lock_init(&worker->lock);
-
- atomic_set(&worker->num_pending, 0);
- atomic_set(&worker->refs, 1);
- worker->workers = workers;
- worker->task = kthread_run(worker_loop, worker,
- "btrfs-%s-%d", workers->name,
- workers->num_workers + i);
- if (IS_ERR(worker->task)) {
- ret = PTR_ERR(worker->task);
- kfree(worker);
- goto fail;
- }
- spin_lock_irq(&workers->lock);
- list_add_tail(&worker->worker_list, &workers->idle_list);
- worker->idle = 1;
- workers->num_workers++;
- workers->num_workers_starting--;
- WARN_ON(workers->num_workers_starting < 0);
- spin_unlock_irq(&workers->lock);
+ worker = kzalloc(sizeof(*worker), GFP_NOFS);
+ if (!worker) {
+ ret = -ENOMEM;
+ goto fail;
}
+
+ INIT_LIST_HEAD(&worker->pending);
+ INIT_LIST_HEAD(&worker->prio_pending);
+ INIT_LIST_HEAD(&worker->worker_list);
+ spin_lock_init(&worker->lock);
+
+ atomic_set(&worker->num_pending, 0);
+ atomic_set(&worker->refs, 1);
+ worker->workers = workers;
+ worker->task = kthread_run(worker_loop, worker,
+ "btrfs-%s-%d", workers->name,
+ workers->num_workers + 1);
+ if (IS_ERR(worker->task)) {
+ ret = PTR_ERR(worker->task);
+ kfree(worker);
+ goto fail;
+ }
+ spin_lock_irq(&workers->lock);
+ list_add_tail(&worker->worker_list, &workers->idle_list);
+ worker->idle = 1;
+ workers->num_workers++;
+ workers->num_workers_starting--;
+ WARN_ON(workers->num_workers_starting < 0);
+ spin_unlock_irq(&workers->lock);
+
return 0;
fail:
- btrfs_stop_workers(workers);
+ spin_lock_irq(&workers->lock);
+ workers->num_workers_starting--;
+ spin_unlock_irq(&workers->lock);
return ret;
}
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+int btrfs_start_workers(struct btrfs_workers *workers)
{
spin_lock_irq(&workers->lock);
- workers->num_workers_starting += num_workers;
+ workers->num_workers_starting++;
spin_unlock_irq(&workers->lock);
- return __btrfs_start_workers(workers, num_workers);
+ return __btrfs_start_workers(workers);
}
/*
@@ -568,6 +561,7 @@
struct btrfs_worker_thread *worker;
unsigned long flags;
struct list_head *fallback;
+ int ret;
again:
spin_lock_irqsave(&workers->lock, flags);
@@ -584,7 +578,9 @@
workers->num_workers_starting++;
spin_unlock_irqrestore(&workers->lock, flags);
/* we're below the limit, start another worker */
- __btrfs_start_workers(workers, 1);
+ ret = __btrfs_start_workers(workers);
+ if (ret)
+ goto fallback;
goto again;
}
}
@@ -665,7 +661,7 @@
/*
* places a struct btrfs_work into the pending queue of one of the kthreads
*/
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
{
struct btrfs_worker_thread *worker;
unsigned long flags;
@@ -673,7 +669,7 @@
/* don't requeue something already on a list */
if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
- goto out;
+ return;
worker = find_worker(workers);
if (workers->ordered) {
@@ -712,7 +708,4 @@
if (wake)
wake_up_process(worker->task);
spin_unlock_irqrestore(&worker->lock, flags);
-
-out:
- return 0;
}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 5077746..f34cc31 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -109,8 +109,8 @@
char *name;
};
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
+int btrfs_start_workers(struct btrfs_workers *workers);
int btrfs_stop_workers(struct btrfs_workers *workers);
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
struct btrfs_workers *async_starter);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 50634abe..6738503 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2692,7 +2692,8 @@
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode, int flags);
+int btrfs_dirty_inode(struct inode *inode);
+int btrfs_update_time(struct file *file);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 5b16357..9c1eccc 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -640,8 +640,8 @@
* Now if src_rsv == delalloc_block_rsv we'll let it just steal since
* we're accounted for.
*/
- if (!trans->bytes_reserved &&
- src_rsv != &root->fs_info->delalloc_block_rsv) {
+ if (!src_rsv || (!trans->bytes_reserved &&
+ src_rsv != &root->fs_info->delalloc_block_rsv)) {
ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
/*
* Since we're under a transaction reserve_metadata_bytes could
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 632f8f3..f44b392 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2194,19 +2194,27 @@
fs_info->endio_meta_write_workers.idle_thresh = 2;
fs_info->readahead_workers.idle_thresh = 2;
- btrfs_start_workers(&fs_info->workers, 1);
- btrfs_start_workers(&fs_info->generic_worker, 1);
- btrfs_start_workers(&fs_info->submit_workers, 1);
- btrfs_start_workers(&fs_info->delalloc_workers, 1);
- btrfs_start_workers(&fs_info->fixup_workers, 1);
- btrfs_start_workers(&fs_info->endio_workers, 1);
- btrfs_start_workers(&fs_info->endio_meta_workers, 1);
- btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
- btrfs_start_workers(&fs_info->endio_write_workers, 1);
- btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
- btrfs_start_workers(&fs_info->delayed_workers, 1);
- btrfs_start_workers(&fs_info->caching_workers, 1);
- btrfs_start_workers(&fs_info->readahead_workers, 1);
+ /*
+ * btrfs_start_workers can really only fail because of ENOMEM so just
+ * return -ENOMEM if any of these fail.
+ */
+ ret = btrfs_start_workers(&fs_info->workers);
+ ret |= btrfs_start_workers(&fs_info->generic_worker);
+ ret |= btrfs_start_workers(&fs_info->submit_workers);
+ ret |= btrfs_start_workers(&fs_info->delalloc_workers);
+ ret |= btrfs_start_workers(&fs_info->fixup_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_write_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
+ ret |= btrfs_start_workers(&fs_info->delayed_workers);
+ ret |= btrfs_start_workers(&fs_info->caching_workers);
+ ret |= btrfs_start_workers(&fs_info->readahead_workers);
+ if (ret) {
+ ret = -ENOMEM;
+ goto fail_sb_buffer;
+ }
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2ad8136..f5fbe57 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2822,7 +2822,7 @@
btrfs_release_path(path);
out:
spin_lock(&block_group->lock);
- if (!ret)
+ if (!ret && dcs == BTRFS_DC_SETUP)
block_group->cache_generation = trans->transid;
block_group->disk_cache_state = dcs;
spin_unlock(&block_group->lock);
@@ -4204,12 +4204,17 @@
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
u64 to_reserve = 0;
+ u64 csum_bytes;
unsigned nr_extents = 0;
+ int extra_reserve = 0;
int flush = 1;
int ret;
+ /* Need to be holding the i_mutex here if we aren't free space cache */
if (btrfs_is_free_space_inode(root, inode))
flush = 0;
+ else
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
if (flush && btrfs_transaction_in_commit(root->fs_info))
schedule_timeout(1);
@@ -4220,11 +4225,9 @@
BTRFS_I(inode)->outstanding_extents++;
if (BTRFS_I(inode)->outstanding_extents >
- BTRFS_I(inode)->reserved_extents) {
+ BTRFS_I(inode)->reserved_extents)
nr_extents = BTRFS_I(inode)->outstanding_extents -
BTRFS_I(inode)->reserved_extents;
- BTRFS_I(inode)->reserved_extents += nr_extents;
- }
/*
* Add an item to reserve for updating the inode when we complete the
@@ -4232,11 +4235,12 @@
*/
if (!BTRFS_I(inode)->delalloc_meta_reserved) {
nr_extents++;
- BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ extra_reserve = 1;
}
to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+ csum_bytes = BTRFS_I(inode)->csum_bytes;
spin_unlock(&BTRFS_I(inode)->lock);
ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
@@ -4246,22 +4250,35 @@
spin_lock(&BTRFS_I(inode)->lock);
dropped = drop_outstanding_extent(inode);
- to_free = calc_csum_metadata_size(inode, num_bytes, 0);
- spin_unlock(&BTRFS_I(inode)->lock);
- to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
/*
- * Somebody could have come in and twiddled with the
- * reservation, so if we have to free more than we would have
- * reserved from this reservation go ahead and release those
- * bytes.
+ * If the inodes csum_bytes is the same as the original
+ * csum_bytes then we know we haven't raced with any free()ers
+ * so we can just reduce our inodes csum bytes and carry on.
+ * Otherwise we have to do the normal free thing to account for
+ * the case that the free side didn't free up its reserve
+ * because of this outstanding reservation.
*/
- to_free -= to_reserve;
+ if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+ calc_csum_metadata_size(inode, num_bytes, 0);
+ else
+ to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+ spin_unlock(&BTRFS_I(inode)->lock);
+ if (dropped)
+ to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
if (to_free)
btrfs_block_rsv_release(root, block_rsv, to_free);
return ret;
}
+ spin_lock(&BTRFS_I(inode)->lock);
+ if (extra_reserve) {
+ BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ nr_extents--;
+ }
+ BTRFS_I(inode)->reserved_extents += nr_extents;
+ spin_unlock(&BTRFS_I(inode)->lock);
+
block_rsv_add_bytes(block_rsv, to_reserve, 1);
return 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index dafdfa0..97fbe93 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1167,6 +1167,8 @@
nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
(sizeof(struct page *)));
+ nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
+ nrptrs = max(nrptrs, 8);
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
if (!pages)
return -ENOMEM;
@@ -1387,7 +1389,11 @@
goto out;
}
- file_update_time(file);
+ err = btrfs_update_time(file);
+ if (err) {
+ mutex_unlock(&inode->i_mutex);
+ goto out;
+ }
BTRFS_I(inode)->sequence++;
start_pos = round_down(pos, root->sectorsize);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2c984f7..0a6b928 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -38,6 +38,7 @@
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
+#include <linux/mount.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
@@ -2031,7 +2032,7 @@
/* insert an orphan item to track this unlinked/truncated file */
if (insert >= 1) {
ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
- BUG_ON(ret);
+ BUG_ON(ret && ret != -EEXIST);
}
/* insert an orphan item to track subvolume contains orphan files */
@@ -2158,6 +2159,38 @@
if (ret && ret != -ESTALE)
goto out;
+ if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ struct btrfs_root *dead_root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ int is_dead_root = 0;
+
+ /*
+ * this is an orphan in the tree root. Currently these
+ * could come from 2 sources:
+ * a) a snapshot deletion in progress
+ * b) a free space cache inode
+ * We need to distinguish those two, as the snapshot
+ * orphan must not get deleted.
+ * find_dead_roots already ran before us, so if this
+ * is a snapshot deletion, we should find the root
+ * in the dead_roots list
+ */
+ spin_lock(&fs_info->trans_lock);
+ list_for_each_entry(dead_root, &fs_info->dead_roots,
+ root_list) {
+ if (dead_root->root_key.objectid ==
+ found_key.objectid) {
+ is_dead_root = 1;
+ break;
+ }
+ }
+ spin_unlock(&fs_info->trans_lock);
+ if (is_dead_root) {
+ /* prevent this orphan from being found again */
+ key.offset = found_key.objectid - 1;
+ continue;
+ }
+ }
/*
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
@@ -2191,7 +2224,14 @@
continue;
}
nr_truncate++;
+ /*
+ * Need to hold the imutex for reservation purposes, not
+ * a huge deal here but I have a WARN_ON in
+ * btrfs_delalloc_reserve_space to catch offenders.
+ */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_truncate(inode);
+ mutex_unlock(&inode->i_mutex);
} else {
nr_unlink++;
}
@@ -3327,7 +3367,7 @@
u64 hint_byte = 0;
hole_size = last_byte - cur_offset;
- trans = btrfs_start_transaction(root, 2);
+ trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
break;
@@ -3337,6 +3377,7 @@
cur_offset + hole_size,
&hint_byte, 1);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
@@ -3346,6 +3387,7 @@
0, hole_size, 0, hole_size,
0, 0, 0);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
@@ -3353,6 +3395,7 @@
btrfs_drop_extent_cache(inode, hole_start,
last_byte - 1, 0);
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
}
free_extent_map(em);
@@ -3370,6 +3413,8 @@
static int btrfs_setsize(struct inode *inode, loff_t newsize)
{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_trans_handle *trans;
loff_t oldsize = i_size_read(inode);
int ret;
@@ -3377,16 +3422,19 @@
return 0;
if (newsize > oldsize) {
- i_size_write(inode, newsize);
- btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
truncate_pagecache(inode, oldsize, newsize);
ret = btrfs_cont_expand(inode, oldsize, newsize);
- if (ret) {
- btrfs_setsize(inode, oldsize);
+ if (ret)
return ret;
- }
- mark_inode_dirty(inode);
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ i_size_write(inode, newsize);
+ btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ ret = btrfs_update_inode(trans, root, inode);
+ btrfs_end_transaction_throttle(trans, root);
} else {
/*
@@ -3426,9 +3474,9 @@
if (attr->ia_valid) {
setattr_copy(inode, attr);
- mark_inode_dirty(inode);
+ err = btrfs_dirty_inode(inode);
- if (attr->ia_valid & ATTR_MODE)
+ if (!err && attr->ia_valid & ATTR_MODE)
err = btrfs_acl_chmod(inode);
}
@@ -4204,42 +4252,80 @@
* FIXME, needs more benchmarking...there are no reasons other than performance
* to keep or drop this code.
*/
-void btrfs_dirty_inode(struct inode *inode, int flags)
+int btrfs_dirty_inode(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret;
if (BTRFS_I(inode)->dummy_inode)
- return;
+ return 0;
trans = btrfs_join_transaction(root);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
if (ret && ret == -ENOSPC) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans, root);
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %ld\n",
- (unsigned long long)btrfs_ino(inode),
- PTR_ERR(trans));
- return;
- }
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
- if (ret) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %d\n",
- (unsigned long long)btrfs_ino(inode),
- ret);
- }
}
btrfs_end_transaction(trans, root);
if (BTRFS_I(inode)->delayed_node)
btrfs_balance_delayed_items(root);
+
+ return ret;
+}
+
+/*
+ * This is a copy of file_update_time. We need this so we can return error on
+ * ENOSPC for updating the inode in the case of file write and mmap writes.
+ */
+int btrfs_update_time(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct timespec now;
+ int ret;
+ enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+
+ /* First try to exhaust all avenues to not sync */
+ if (IS_NOCMTIME(inode))
+ return 0;
+
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_mtime, &now))
+ sync_it = S_MTIME;
+
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it |= S_CTIME;
+
+ if (IS_I_VERSION(inode))
+ sync_it |= S_VERSION;
+
+ if (!sync_it)
+ return 0;
+
+ /* Finally allowed to write? Takes lock. */
+ if (mnt_want_write_file(file))
+ return 0;
+
+ /* Only change inode inside the lock region */
+ if (sync_it & S_VERSION)
+ inode_inc_iversion(inode);
+ if (sync_it & S_CTIME)
+ inode->i_ctime = now;
+ if (sync_it & S_MTIME)
+ inode->i_mtime = now;
+ ret = btrfs_dirty_inode(inode);
+ if (!ret)
+ mark_inode_dirty_sync(inode);
+ mnt_drop_write(file->f_path.mnt);
+ return ret;
}
/*
@@ -4555,11 +4641,18 @@
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+
+ inode->i_op = &btrfs_special_inode_operations;
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
- inode->i_op = &btrfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
btrfs_update_inode(trans, root, inode);
}
@@ -4613,14 +4706,21 @@
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
out_unlock:
@@ -6303,7 +6403,12 @@
u64 page_start;
u64 page_end;
+ /* Need this to keep space reservations serialized */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
+ if (!ret)
+ ret = btrfs_update_time(vma->vm_file);
if (ret) {
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
@@ -6515,8 +6620,9 @@
/* Just need the 1 for updating the inode */
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- goto out;
+ ret = err = PTR_ERR(trans);
+ trans = NULL;
+ break;
}
}
@@ -7076,14 +7182,21 @@
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
if (drop_inode)
@@ -7353,6 +7466,7 @@
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = btrfs_getattr,
+ .setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 72d4616..c04f02c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -252,11 +252,11 @@
trans = btrfs_join_transaction(root);
BUG_ON(IS_ERR(trans));
+ btrfs_update_iflags(inode);
+ inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, inode);
BUG_ON(ret);
- btrfs_update_iflags(inode);
- inode->i_ctime = CURRENT_TIME;
btrfs_end_transaction(trans, root);
mnt_drop_write(file->f_path.mnt);
@@ -858,8 +858,10 @@
return 0;
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode,
num_pages << PAGE_CACHE_SHIFT);
+ mutex_unlock(&inode->i_mutex);
if (ret)
return ret;
again:
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index dff29d5..cfb5543 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2947,7 +2947,9 @@
index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
while (index <= last_index) {
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
if (ret)
goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index c27bcb6..ddf2c90 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1535,18 +1535,22 @@
static noinline_for_stack int scrub_workers_get(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ int ret = 0;
mutex_lock(&fs_info->scrub_lock);
if (fs_info->scrub_workers_refcnt == 0) {
btrfs_init_workers(&fs_info->scrub_workers, "scrub",
fs_info->thread_pool_size, &fs_info->generic_worker);
fs_info->scrub_workers.idle_thresh = 4;
- btrfs_start_workers(&fs_info->scrub_workers, 1);
+ ret = btrfs_start_workers(&fs_info->scrub_workers);
+ if (ret)
+ goto out;
}
++fs_info->scrub_workers_refcnt;
+out:
mutex_unlock(&fs_info->scrub_lock);
- return 0;
+ return ret;
}
static noinline_for_stack void scrub_workers_put(struct btrfs_root *root)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index e28ad4b..200f63b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -41,6 +41,7 @@
#include <linux/slab.h>
#include <linux/cleancache.h>
#include <linux/mnt_namespace.h>
+#include <linux/ratelimit.h>
#include "compat.h"
#include "delayed-inode.h"
#include "ctree.h"
@@ -1053,7 +1054,7 @@
u64 avail_space;
u64 used_space;
u64 min_stripe_size;
- int min_stripes = 1;
+ int min_stripes = 1, num_stripes = 1;
int i = 0, nr_devices;
int ret;
@@ -1067,12 +1068,16 @@
/* calc min stripe number for data space alloction */
type = btrfs_get_alloc_profile(root, 1);
- if (type & BTRFS_BLOCK_GROUP_RAID0)
+ if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID1)
+ num_stripes = nr_devices;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID1) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID10)
+ num_stripes = 2;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID10) {
min_stripes = 4;
+ num_stripes = 4;
+ }
if (type & BTRFS_BLOCK_GROUP_DUP)
min_stripe_size = 2 * BTRFS_STRIPE_LEN;
@@ -1141,13 +1146,16 @@
i = nr_devices - 1;
avail_space = 0;
while (nr_devices >= min_stripes) {
+ if (num_stripes > nr_devices)
+ num_stripes = nr_devices;
+
if (devices_info[i].max_avail >= min_stripe_size) {
int j;
u64 alloc_size;
- avail_space += devices_info[i].max_avail * min_stripes;
+ avail_space += devices_info[i].max_avail * num_stripes;
alloc_size = devices_info[i].max_avail;
- for (j = i + 1 - min_stripes; j <= i; j++)
+ for (j = i + 1 - num_stripes; j <= i; j++)
devices_info[j].max_avail -= alloc_size;
}
i--;
@@ -1264,6 +1272,16 @@
return 0;
}
+static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
+{
+ int ret;
+
+ ret = btrfs_dirty_inode(inode);
+ if (ret)
+ printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
+ "error %d\n", btrfs_ino(inode), ret);
+}
+
static const struct super_operations btrfs_super_ops = {
.drop_inode = btrfs_drop_inode,
.evict_inode = btrfs_evict_inode,
@@ -1271,7 +1289,7 @@
.sync_fs = btrfs_sync_fs,
.show_options = btrfs_show_options,
.write_inode = btrfs_write_inode,
- .dirty_inode = btrfs_dirty_inode,
+ .dirty_inode = btrfs_fs_dirty_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0a8c8f8..f4b839f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -295,6 +295,12 @@
btrfs_requeue_work(&device->work);
goto done;
}
+ /* unplug every 64 requests just for good measure */
+ if (batch_run % 64 == 0) {
+ blk_finish_plug(&plug);
+ blk_start_plug(&plug);
+ sync_pending = 0;
+ }
}
cond_resched();
@@ -3258,7 +3264,7 @@
*/
if (atomic_read(&bbio->error) > bbio->max_errors) {
err = -EIO;
- } else if (err) {
+ } else {
/*
* this bio is actually up to date, we didn't
* go over the max number of errors
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4144caf..173b1d2 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -87,7 +87,7 @@
snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
/* dirty the head */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_head_snapc == NULL)
ci->i_head_snapc = ceph_get_snap_context(snapc);
++ci->i_wrbuffer_ref_head;
@@ -100,7 +100,7 @@
ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
snapc, snapc->seq, snapc->num_snaps);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* now adjust page */
spin_lock_irq(&mapping->tree_lock);
@@ -391,7 +391,7 @@
struct ceph_snap_context *snapc = NULL;
struct ceph_cap_snap *capsnap = NULL;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
capsnap->context, capsnap->dirty_pages);
@@ -407,7 +407,7 @@
dout(" head snapc %p has %d dirty pages\n",
snapc, ci->i_wrbuffer_ref_head);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return snapc;
}
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0f327c6..8b53193 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -309,7 +309,7 @@
/*
* Find ceph_cap for given mds, if any.
*
- * Called with i_lock held.
+ * Called with i_ceph_lock held.
*/
static struct ceph_cap *__get_cap_for_mds(struct ceph_inode_info *ci, int mds)
{
@@ -332,9 +332,9 @@
{
struct ceph_cap *cap;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return cap;
}
@@ -361,15 +361,16 @@
int ceph_get_cap_mds(struct inode *inode)
{
+ struct ceph_inode_info *ci = ceph_inode(inode);
int mds;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
mds = __ceph_get_cap_mds(ceph_inode(inode));
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return mds;
}
/*
- * Called under i_lock.
+ * Called under i_ceph_lock.
*/
static void __insert_cap_node(struct ceph_inode_info *ci,
struct ceph_cap *new)
@@ -415,7 +416,7 @@
*
* If I_FLUSH is set, leave the inode at the front of the list.
*
- * Caller holds i_lock
+ * Caller holds i_ceph_lock
* -> we take mdsc->cap_delay_lock
*/
static void __cap_delay_requeue(struct ceph_mds_client *mdsc,
@@ -457,7 +458,7 @@
/*
* Cancel delayed work on cap.
*
- * Caller must hold i_lock.
+ * Caller must hold i_ceph_lock.
*/
static void __cap_delay_cancel(struct ceph_mds_client *mdsc,
struct ceph_inode_info *ci)
@@ -532,14 +533,14 @@
wanted |= ceph_caps_for_mode(fmode);
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
if (new_cap) {
cap = new_cap;
new_cap = NULL;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
new_cap = get_cap(mdsc, caps_reservation);
if (new_cap == NULL)
return -ENOMEM;
@@ -625,7 +626,7 @@
if (fmode >= 0)
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
wake_up_all(&ci->i_cap_wq);
return 0;
}
@@ -792,7 +793,7 @@
struct rb_node *p;
int ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
cap = rb_entry(p, struct ceph_cap, ci_node);
if (__cap_is_valid(cap) &&
@@ -801,7 +802,7 @@
break;
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("ceph_caps_revoking %p %s = %d\n", inode,
ceph_cap_string(mask), ret);
return ret;
@@ -855,7 +856,7 @@
}
/*
- * called under i_lock
+ * called under i_ceph_lock
*/
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
@@ -865,7 +866,7 @@
/*
* Remove a cap. Take steps to deal with a racing iterate_session_caps.
*
- * caller should hold i_lock.
+ * caller should hold i_ceph_lock.
* caller will not hold session s_mutex if called from destroy_inode.
*/
void __ceph_remove_cap(struct ceph_cap *cap)
@@ -1028,7 +1029,7 @@
/*
* Queue cap releases when an inode is dropped from our cache. Since
- * inode is about to be destroyed, there is no need for i_lock.
+ * inode is about to be destroyed, there is no need for i_ceph_lock.
*/
void ceph_queue_caps_release(struct inode *inode)
{
@@ -1049,7 +1050,7 @@
/*
* Send a cap msg on the given inode. Update our caps state, then
- * drop i_lock and send the message.
+ * drop i_ceph_lock and send the message.
*
* Make note of max_size reported/requested from mds, revoked caps
* that have now been implemented.
@@ -1061,13 +1062,13 @@
* Return non-zero if delayed release, or we experienced an error
* such that the caller should requeue + retry later.
*
- * called with i_lock, then drops it.
+ * called with i_ceph_lock, then drops it.
* caller should hold snap_rwsem (read), s_mutex.
*/
static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
int op, int used, int want, int retain, int flushing,
unsigned *pflush_tid)
- __releases(cap->ci->vfs_inode->i_lock)
+ __releases(cap->ci->i_ceph_lock)
{
struct ceph_inode_info *ci = cap->ci;
struct inode *inode = &ci->vfs_inode;
@@ -1170,7 +1171,7 @@
xattr_version = ci->i_xattrs.version;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ret = send_cap_msg(session, ceph_vino(inode).ino, cap_id,
op, keep, want, flushing, seq, flush_tid, issue_seq, mseq,
@@ -1198,13 +1199,13 @@
* Unless @again is true, skip cap_snaps that were already sent to
* the MDS (i.e., during this session).
*
- * Called under i_lock. Takes s_mutex as needed.
+ * Called under i_ceph_lock. Takes s_mutex as needed.
*/
void __ceph_flush_snaps(struct ceph_inode_info *ci,
struct ceph_mds_session **psession,
int again)
- __releases(ci->vfs_inode->i_lock)
- __acquires(ci->vfs_inode->i_lock)
+ __releases(ci->i_ceph_lock)
+ __acquires(ci->i_ceph_lock)
{
struct inode *inode = &ci->vfs_inode;
int mds;
@@ -1261,7 +1262,7 @@
session = NULL;
}
if (!session) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
mutex_lock(&mdsc->mutex);
session = __ceph_lookup_mds_session(mdsc, mds);
mutex_unlock(&mdsc->mutex);
@@ -1275,7 +1276,7 @@
* deletion or migration. retry, and we'll
* get a better @mds value next time.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
goto retry;
}
@@ -1285,7 +1286,7 @@
list_del_init(&capsnap->flushing_item);
list_add_tail(&capsnap->flushing_item,
&session->s_cap_snaps_flushing);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("flush_snaps %p cap_snap %p follows %lld tid %llu\n",
inode, capsnap, capsnap->follows, capsnap->flush_tid);
@@ -1302,7 +1303,7 @@
next_follows = capsnap->follows + 1;
ceph_put_cap_snap(capsnap);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
goto retry;
}
@@ -1322,11 +1323,9 @@
static void ceph_flush_snaps(struct ceph_inode_info *ci)
{
- struct inode *inode = &ci->vfs_inode;
-
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_flush_snaps(ci, NULL, 0);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
@@ -1373,7 +1372,7 @@
* Add dirty inode to the flushing list. Assigned a seq number so we
* can wait for caps to flush without starving.
*
- * Called under i_lock.
+ * Called under i_ceph_lock.
*/
static int __mark_caps_flushing(struct inode *inode,
struct ceph_mds_session *session)
@@ -1421,9 +1420,9 @@
struct ceph_inode_info *ci = ceph_inode(inode);
u32 invalidating_gen = ci->i_rdcache_gen;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
invalidate_mapping_pages(&inode->i_data, 0, -1);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (inode->i_data.nrpages == 0 &&
invalidating_gen == ci->i_rdcache_gen) {
@@ -1470,7 +1469,7 @@
if (mdsc->stopping)
is_delayed = 1;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_FLUSH)
flags |= CHECK_CAPS_FLUSH;
@@ -1480,7 +1479,7 @@
__ceph_flush_snaps(ci, &session, 0);
goto retry_locked;
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
retry_locked:
file_wanted = __ceph_caps_file_wanted(ci);
used = __ceph_caps_used(ci);
@@ -1634,7 +1633,7 @@
if (mutex_trylock(&session->s_mutex) == 0) {
dout("inverting session/ino locks on %p\n",
session);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (took_snap_rwsem) {
up_read(&mdsc->snap_rwsem);
took_snap_rwsem = 0;
@@ -1648,7 +1647,7 @@
if (down_read_trylock(&mdsc->snap_rwsem) == 0) {
dout("inverting snap/in locks on %p\n",
inode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
down_read(&mdsc->snap_rwsem);
took_snap_rwsem = 1;
goto retry;
@@ -1664,10 +1663,10 @@
mds = cap->mds; /* remember mds, so we don't repeat */
sent++;
- /* __send_cap drops i_lock */
+ /* __send_cap drops i_ceph_lock */
delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, used, want,
retain, flushing, NULL);
- goto retry; /* retake i_lock and restart our cap scan. */
+ goto retry; /* retake i_ceph_lock and restart our cap scan. */
}
/*
@@ -1681,7 +1680,7 @@
else if (!is_delayed || force_requeue)
__cap_delay_requeue(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (queue_invalidate)
ceph_queue_invalidate(inode);
@@ -1704,7 +1703,7 @@
int flushing = 0;
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
goto out;
@@ -1716,7 +1715,7 @@
int delayed;
if (!session) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
session = cap->session;
mutex_lock(&session->s_mutex);
goto retry;
@@ -1727,18 +1726,18 @@
flushing = __mark_caps_flushing(inode, session);
- /* __send_cap drops i_lock */
+ /* __send_cap drops i_ceph_lock */
delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, used, want,
cap->issued | cap->implemented, flushing,
flush_tid);
if (!delayed)
goto out_unlocked;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__cap_delay_requeue(mdsc, ci);
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
out_unlocked:
if (session && unlock_session)
mutex_unlock(&session->s_mutex);
@@ -1753,7 +1752,7 @@
struct ceph_inode_info *ci = ceph_inode(inode);
int i, ret = 1;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
for (i = 0; i < CEPH_CAP_BITS; i++)
if ((ci->i_flushing_caps & (1 << i)) &&
ci->i_cap_flush_tid[i] <= tid) {
@@ -1761,7 +1760,7 @@
ret = 0;
break;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ret;
}
@@ -1868,10 +1867,10 @@
struct ceph_mds_client *mdsc =
ceph_sb_to_client(inode->i_sb)->mdsc;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (__ceph_caps_dirty(ci))
__cap_delay_requeue_front(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
return err;
}
@@ -1894,7 +1893,7 @@
struct inode *inode = &ci->vfs_inode;
struct ceph_cap *cap;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = ci->i_auth_cap;
if (cap && cap->session == session) {
dout("kick_flushing_caps %p cap %p capsnap %p\n", inode,
@@ -1904,7 +1903,7 @@
pr_err("%p auth cap %p not mds%d ???\n", inode,
cap, session->s_mds);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
}
@@ -1921,7 +1920,7 @@
struct ceph_cap *cap;
int delayed = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = ci->i_auth_cap;
if (cap && cap->session == session) {
dout("kick_flushing_caps %p cap %p %s\n", inode,
@@ -1932,14 +1931,14 @@
cap->issued | cap->implemented,
ci->i_flushing_caps, NULL);
if (delayed) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__cap_delay_requeue(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
} else {
pr_err("%p auth cap %p not mds%d ???\n", inode,
cap, session->s_mds);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
}
}
@@ -1952,7 +1951,7 @@
struct ceph_cap *cap;
int delayed = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = ci->i_auth_cap;
dout("kick_flushing_inode_caps %p flushing %s flush_seq %lld\n", inode,
ceph_cap_string(ci->i_flushing_caps), ci->i_cap_flush_seq);
@@ -1964,12 +1963,12 @@
cap->issued | cap->implemented,
ci->i_flushing_caps, NULL);
if (delayed) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__cap_delay_requeue(mdsc, ci);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
}
@@ -1978,7 +1977,7 @@
* Take references to capabilities we hold, so that we don't release
* them to the MDS prematurely.
*
- * Protected by i_lock.
+ * Protected by i_ceph_lock.
*/
static void __take_cap_refs(struct ceph_inode_info *ci, int got)
{
@@ -2016,7 +2015,7 @@
dout("get_cap_refs %p need %s want %s\n", inode,
ceph_cap_string(need), ceph_cap_string(want));
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
/* make sure file is actually open */
file_wanted = __ceph_caps_file_wanted(ci);
@@ -2077,7 +2076,7 @@
ceph_cap_string(have), ceph_cap_string(need));
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("get_cap_refs %p ret %d got %s\n", inode,
ret, ceph_cap_string(*got));
return ret;
@@ -2094,7 +2093,7 @@
int check = 0;
/* do we need to explicitly request a larger max_size? */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if ((endoff >= ci->i_max_size ||
endoff > (inode->i_size << 1)) &&
endoff > ci->i_wanted_max_size) {
@@ -2103,7 +2102,7 @@
ci->i_wanted_max_size = endoff;
check = 1;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (check)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
}
@@ -2140,9 +2139,9 @@
*/
void ceph_get_cap_refs(struct ceph_inode_info *ci, int caps)
{
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
__take_cap_refs(ci, caps);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
@@ -2160,7 +2159,7 @@
int last = 0, put = 0, flushsnaps = 0, wake = 0;
struct ceph_cap_snap *capsnap;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (had & CEPH_CAP_PIN)
--ci->i_pin_ref;
if (had & CEPH_CAP_FILE_RD)
@@ -2193,7 +2192,7 @@
}
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
last ? " last" : "", put ? " put" : "");
@@ -2225,7 +2224,7 @@
int found = 0;
struct ceph_cap_snap *capsnap = NULL;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_wrbuffer_ref -= nr;
last = !ci->i_wrbuffer_ref;
@@ -2274,7 +2273,7 @@
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (last) {
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
@@ -2291,7 +2290,7 @@
* Handle a cap GRANT message from the MDS. (Note that a GRANT may
* actually be a revocation if it specifies a smaller cap set.)
*
- * caller holds s_mutex and i_lock, we drop both.
+ * caller holds s_mutex and i_ceph_lock, we drop both.
*
* return value:
* 0 - ok
@@ -2302,7 +2301,7 @@
struct ceph_mds_session *session,
struct ceph_cap *cap,
struct ceph_buffer *xattr_buf)
- __releases(inode->i_lock)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
@@ -2453,7 +2452,7 @@
}
BUG_ON(cap->issued & ~cap->implemented);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (writeback)
/*
* queue inode for writeback: we can't actually call
@@ -2483,7 +2482,7 @@
struct ceph_mds_caps *m,
struct ceph_mds_session *session,
struct ceph_cap *cap)
- __releases(inode->i_lock)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
@@ -2539,7 +2538,7 @@
wake_up_all(&ci->i_cap_wq);
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (drop)
iput(inode);
}
@@ -2562,7 +2561,7 @@
dout("handle_cap_flushsnap_ack inode %p ci %p mds%d follows %lld\n",
inode, ci, session->s_mds, follows);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
if (capsnap->follows == follows) {
if (capsnap->flush_tid != flush_tid) {
@@ -2585,7 +2584,7 @@
capsnap, capsnap->follows);
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (drop)
iput(inode);
}
@@ -2598,7 +2597,7 @@
static void handle_cap_trunc(struct inode *inode,
struct ceph_mds_caps *trunc,
struct ceph_mds_session *session)
- __releases(inode->i_lock)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
@@ -2617,7 +2616,7 @@
inode, mds, seq, truncate_size, truncate_seq);
queue_trunc = ceph_fill_file_size(inode, issued,
truncate_seq, truncate_size, size);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (queue_trunc)
ceph_queue_vmtruncate(inode);
@@ -2646,7 +2645,7 @@
dout("handle_cap_export inode %p ci %p mds%d mseq %d\n",
inode, ci, mds, mseq);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
/* make sure we haven't seen a higher mseq */
for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
@@ -2690,7 +2689,7 @@
}
/* else, we already released it */
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
@@ -2745,9 +2744,9 @@
up_read(&mdsc->snap_rwsem);
/* make sure we re-request max_size, if necessary */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_requested_max_size = 0;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
@@ -2762,6 +2761,7 @@
struct ceph_mds_client *mdsc = session->s_mdsc;
struct super_block *sb = mdsc->fsc->sb;
struct inode *inode;
+ struct ceph_inode_info *ci;
struct ceph_cap *cap;
struct ceph_mds_caps *h;
int mds = session->s_mds;
@@ -2815,6 +2815,7 @@
/* lookup ino */
inode = ceph_find_inode(sb, vino);
+ ci = ceph_inode(inode);
dout(" op %s ino %llx.%llx inode %p\n", ceph_cap_op_name(op), vino.ino,
vino.snap, inode);
if (!inode) {
@@ -2844,16 +2845,16 @@
}
/* the rest require a cap */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ceph_inode(inode), mds);
if (!cap) {
dout(" no cap on %p ino %llx.%llx from mds%d\n",
inode, ceph_ino(inode), ceph_snap(inode), mds);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
goto flush_cap_releases;
}
- /* note that each of these drops i_lock for us */
+ /* note that each of these drops i_ceph_lock for us */
switch (op) {
case CEPH_CAP_OP_REVOKE:
case CEPH_CAP_OP_GRANT:
@@ -2869,7 +2870,7 @@
break;
default:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
pr_err("ceph_handle_caps: unknown cap op %d %s\n", op,
ceph_cap_op_name(op));
}
@@ -2962,13 +2963,13 @@
struct inode *inode = &ci->vfs_inode;
int last = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("put_fmode %p fmode %d %d -> %d\n", inode, fmode,
ci->i_nr_by_mode[fmode], ci->i_nr_by_mode[fmode]-1);
BUG_ON(ci->i_nr_by_mode[fmode] == 0);
if (--ci->i_nr_by_mode[fmode] == 0)
last++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (last && ci->i_vino.snap == CEPH_NOSNAP)
ceph_check_caps(ci, 0, NULL);
@@ -2991,7 +2992,7 @@
int used, dirty;
int ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
used = __ceph_caps_used(ci);
dirty = __ceph_caps_dirty(ci);
@@ -3046,7 +3047,7 @@
inode, cap, ceph_cap_string(cap->issued));
}
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ret;
}
@@ -3061,7 +3062,7 @@
/*
* force an record for the directory caps if we have a dentry lease.
- * this is racy (can't take i_lock and d_lock together), but it
+ * this is racy (can't take i_ceph_lock and d_lock together), but it
* doesn't have to be perfect; the mds will revoke anything we don't
* release.
*/
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index bca3948..3eeb976 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -281,18 +281,18 @@
}
/* can we use the dcache? */
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if ((filp->f_pos == 2 || fi->dentry) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
ceph_dir_test_complete(inode) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = __dcache_readdir(filp, dirent, filldir);
if (err != -EAGAIN)
return err;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
if (fi->dentry) {
err = note_last_dentry(fi, fi->dentry->d_name.name,
@@ -428,12 +428,12 @@
* were released during the whole readdir, and we should have
* the complete dir contents in our cache.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_release_count == fi->dir_release_count) {
ceph_dir_set_complete(inode);
ci->i_max_offset = filp->f_pos;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("readdir %p filp %p done.\n", inode, filp);
return 0;
@@ -607,7 +607,7 @@
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
- spin_lock(&dir->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
if (strncmp(dentry->d_name.name,
fsc->mount_options->snapdir_name,
@@ -615,13 +615,13 @@
!is_root_ceph_dentry(dir, dentry) &&
ceph_dir_test_complete(dir) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
- spin_unlock(&dir->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout(" dir %p complete, -ENOENT\n", dir);
d_add(dentry, NULL);
di->lease_shared_gen = ci->i_shared_gen;
return NULL;
}
- spin_unlock(&dir->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
op = ceph_snap(dir) == CEPH_SNAPDIR ?
@@ -841,12 +841,12 @@
struct ceph_inode_info *ci = ceph_inode(inode);
int drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (inode->i_nlink == 1) {
drop |= ~(__ceph_caps_wanted(ci) | CEPH_CAP_PIN);
ci->i_ceph_flags |= CEPH_I_NODELAY;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return drop;
}
@@ -1015,10 +1015,10 @@
struct ceph_dentry_info *di = ceph_dentry(dentry);
int valid = 0;
- spin_lock(&dir->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_shared_gen == di->lease_shared_gen)
valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
- spin_unlock(&dir->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("dir_lease_is_valid dir %p v%u dentry %p v%u = %d\n",
dir, (unsigned)ci->i_shared_gen, dentry,
(unsigned)di->lease_shared_gen, valid);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ce549d3..ed72428 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -147,9 +147,9 @@
/* trivially open snapdir */
if (ceph_snap(inode) == CEPH_SNAPDIR) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
@@ -158,7 +158,7 @@
* write) or any MDS (for read). Update wanted set
* asynchronously.
*/
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (__ceph_is_any_real_caps(ci) &&
(((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
int mds_wanted = __ceph_caps_mds_wanted(ci);
@@ -168,7 +168,7 @@
inode, fmode, ceph_cap_string(wanted),
ceph_cap_string(issued));
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* adjust wanted? */
if ((issued & wanted) != wanted &&
@@ -180,10 +180,10 @@
} else if (ceph_snap(inode) != CEPH_NOSNAP &&
(ci->i_snap_caps & wanted) == wanted) {
__ceph_get_fmode(ci, fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ceph_init_file(inode, file, fmode);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
req = prepare_open_request(inode->i_sb, flags, 0);
@@ -743,9 +743,9 @@
*/
int dirty;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ceph_put_cap_refs(ci, got);
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
@@ -764,9 +764,9 @@
if (ret >= 0) {
int dirty;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
}
@@ -797,7 +797,8 @@
mutex_lock(&inode->i_mutex);
__ceph_do_pending_vmtruncate(inode);
- if (origin != SEEK_CUR || origin != SEEK_SET) {
+
+ if (origin == SEEK_END || origin == SEEK_DATA || origin == SEEK_HOLE) {
ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE);
if (ret < 0) {
offset = ret;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 116f365..87fb132 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -297,6 +297,8 @@
dout("alloc_inode %p\n", &ci->vfs_inode);
+ spin_lock_init(&ci->i_ceph_lock);
+
ci->i_version = 0;
ci->i_time_warp_seq = 0;
ci->i_ceph_flags = 0;
@@ -583,7 +585,7 @@
iinfo->xattr_len);
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
/*
* provided version will be odd if inode value is projected,
@@ -680,7 +682,7 @@
char *sym;
BUG_ON(symlen != inode->i_size);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = -ENOMEM;
sym = kmalloc(symlen+1, GFP_NOFS);
@@ -689,7 +691,7 @@
memcpy(sym, iinfo->symlink, symlen);
sym[symlen] = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (!ci->i_symlink)
ci->i_symlink = sym;
else
@@ -715,7 +717,7 @@
}
no_change:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* queue truncate if we saw i_size decrease */
if (queue_trunc)
@@ -750,13 +752,13 @@
info->cap.flags,
caps_reservation);
} else {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(le32_to_cpu(info->cap.caps)));
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
} else if (cap_fmode >= 0) {
pr_warning("mds issued no caps on %llx.%llx\n",
@@ -849,19 +851,20 @@
{
struct dentry *dir = dn->d_parent;
struct inode *inode = dir->d_inode;
+ struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_dentry_info *di;
BUG_ON(!inode);
di = ceph_dentry(dn);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (!ceph_dir_test_complete(inode)) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return;
}
di->offset = ceph_inode(inode)->i_max_offset++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
spin_lock(&dir->d_lock);
spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED);
@@ -1308,7 +1311,7 @@
struct ceph_inode_info *ci = ceph_inode(inode);
int ret = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
inode->i_size = size;
inode->i_blocks = (size + (1 << 9) - 1) >> 9;
@@ -1318,7 +1321,7 @@
(ci->i_reported_size << 1) < ci->i_max_size)
ret = 1;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return ret;
}
@@ -1376,20 +1379,20 @@
u32 orig_gen;
int check = 0;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("invalidate_pages %p gen %d revoking %d\n", inode,
ci->i_rdcache_gen, ci->i_rdcache_revoking);
if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
/* nevermind! */
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
goto out;
}
orig_gen = ci->i_rdcache_gen;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
truncate_inode_pages(&inode->i_data, 0);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
orig_gen == ci->i_rdcache_revoking) {
dout("invalidate_pages %p gen %d successful\n", inode,
@@ -1401,7 +1404,7 @@
inode, orig_gen, ci->i_rdcache_gen,
ci->i_rdcache_revoking);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (check)
ceph_check_caps(ci, 0, NULL);
@@ -1460,10 +1463,10 @@
int wrbuffer_refs, wake = 0;
retry:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_truncate_pending == 0) {
dout("__do_pending_vmtruncate %p none pending\n", inode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return;
}
@@ -1474,7 +1477,7 @@
if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) {
dout("__do_pending_vmtruncate %p flushing snaps first\n",
inode);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
filemap_write_and_wait_range(&inode->i_data, 0,
inode->i_sb->s_maxbytes);
goto retry;
@@ -1484,15 +1487,15 @@
wrbuffer_refs = ci->i_wrbuffer_ref;
dout("__do_pending_vmtruncate %p (%d) to %lld\n", inode,
ci->i_truncate_pending, to);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
truncate_inode_pages(inode->i_mapping, to);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_truncate_pending--;
if (ci->i_truncate_pending == 0)
wake = 1;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (wrbuffer_refs == 0)
ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
@@ -1547,7 +1550,7 @@
if (IS_ERR(req))
return PTR_ERR(req);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
dout("setattr %p issued %s\n", inode, ceph_cap_string(issued));
@@ -1695,7 +1698,7 @@
}
release &= issued;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (inode_dirty_flags)
__mark_inode_dirty(inode, inode_dirty_flags);
@@ -1717,7 +1720,7 @@
__ceph_do_pending_vmtruncate(inode);
return err;
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ceph_mdsc_put_request(req);
return err;
}
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 5a14c29..790914a59 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -241,11 +241,11 @@
struct ceph_inode_info *ci = ceph_inode(inode);
if ((fi->fmode & CEPH_FILE_MODE_LAZY) == 0) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_nr_by_mode[fi->fmode]--;
fi->fmode |= CEPH_FILE_MODE_LAZY;
ci->i_nr_by_mode[fi->fmode]++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout("ioctl_layzio: file %p marked lazy\n", file);
ceph_check_caps(ci, 0, NULL);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 264ab70..6203d80 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -732,21 +732,21 @@
}
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap = NULL;
if (mode == USE_AUTH_MDS)
cap = ci->i_auth_cap;
if (!cap && !RB_EMPTY_ROOT(&ci->i_caps))
cap = rb_entry(rb_first(&ci->i_caps), struct ceph_cap, ci_node);
if (!cap) {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
goto random;
}
mds = cap->session->s_mds;
dout("choose_mds %p %llx.%llx mds%d (%scap %p)\n",
inode, ceph_vinop(inode), mds,
cap == ci->i_auth_cap ? "auth " : "", cap);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return mds;
random:
@@ -951,7 +951,7 @@
dout("removing cap %p, ci is %p, inode is %p\n",
cap, ci, &ci->vfs_inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_remove_cap(cap);
if (!__ceph_is_any_real_caps(ci)) {
struct ceph_mds_client *mdsc =
@@ -984,7 +984,7 @@
}
spin_unlock(&mdsc->cap_dirty_lock);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
while (drop--)
iput(inode);
return 0;
@@ -1015,10 +1015,10 @@
wake_up_all(&ci->i_cap_wq);
if (arg) {
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
return 0;
}
@@ -1151,7 +1151,7 @@
if (session->s_trim_caps <= 0)
return -1;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
mine = cap->issued | cap->implemented;
used = __ceph_caps_used(ci);
oissued = __ceph_caps_issued_other(ci, cap);
@@ -1170,7 +1170,7 @@
__ceph_remove_cap(cap);
} else {
/* try to drop referring dentries */
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
d_prune_aliases(inode);
dout("trim_caps_cb %p cap %p pruned, count now %d\n",
inode, cap, atomic_read(&inode->i_count));
@@ -1178,7 +1178,7 @@
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return 0;
}
@@ -1296,7 +1296,7 @@
i_flushing_item);
struct inode *inode = &ci->vfs_inode;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_cap_flush_seq <= want_flush_seq) {
dout("check_cap_flush still flushing %p "
"seq %lld <= %lld to mds%d\n", inode,
@@ -1304,7 +1304,7 @@
session->s_mds);
ret = 0;
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
mutex_unlock(&session->s_mutex);
ceph_put_mds_session(session);
@@ -1495,6 +1495,7 @@
pos, temp);
} else if (stop_on_nosnap && inode &&
ceph_snap(inode) == CEPH_NOSNAP) {
+ spin_unlock(&temp->d_lock);
break;
} else {
pos -= temp->d_name.len;
@@ -2011,10 +2012,10 @@
struct ceph_inode_info *ci = ceph_inode(inode);
dout("invalidate_dir_request %p (D_COMPLETE, lease(s))\n", inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ceph_dir_clear_complete(inode);
ci->i_release_count++;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (req->r_dentry)
ceph_invalidate_dentry_lease(req->r_dentry);
@@ -2422,7 +2423,7 @@
if (err)
goto out_free;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
cap->seq = 0; /* reset cap seq */
cap->issue_seq = 0; /* and issue_seq */
@@ -2445,7 +2446,7 @@
rec.v1.pathbase = cpu_to_le64(pathbase);
reclen = sizeof(rec.v1);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (recon_state->flock) {
int num_fcntl_locks, num_flock_locks;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 4bb2399..a50ca0e 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -20,7 +20,7 @@
*
* mdsc->snap_rwsem
*
- * inode->i_lock
+ * ci->i_ceph_lock
* mdsc->snap_flush_lock
* mdsc->cap_delay_lock
*
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index e264371..a559c80 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -446,7 +446,7 @@
return;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
used = __ceph_caps_used(ci);
dirty = __ceph_caps_dirty(ci);
@@ -528,7 +528,7 @@
kfree(capsnap);
}
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
/*
@@ -537,7 +537,7 @@
*
* If capsnap can now be flushed, add to snap_flush list, and return 1.
*
- * Caller must hold i_lock.
+ * Caller must hold i_ceph_lock.
*/
int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
struct ceph_cap_snap *capsnap)
@@ -739,9 +739,9 @@
inode = &ci->vfs_inode;
ihold(inode);
spin_unlock(&mdsc->snap_flush_lock);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__ceph_flush_snaps(ci, &session, 0);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
iput(inode);
spin_lock(&mdsc->snap_flush_lock);
}
@@ -847,7 +847,7 @@
continue;
ci = ceph_inode(inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (!ci->i_snap_realm)
goto skip_inode;
/*
@@ -876,7 +876,7 @@
oldrealm = ci->i_snap_realm;
ci->i_snap_realm = realm;
spin_unlock(&realm->inodes_with_caps_lock);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
ceph_get_snap_realm(mdsc, realm);
ceph_put_snap_realm(mdsc, oldrealm);
@@ -885,7 +885,7 @@
continue;
skip_inode:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
iput(inode);
}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 8dc73a5..b48f15f 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -383,7 +383,7 @@
if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
seq_printf(m, ",rsize=%d", fsopt->rsize);
if (fsopt->rasize != CEPH_RASIZE_DEFAULT)
- seq_printf(m, ",rasize=%d", fsopt->rsize);
+ seq_printf(m, ",rasize=%d", fsopt->rasize);
if (fsopt->congestion_kb != default_congestion_kb())
seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 01bf189..edcbf37 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -220,7 +220,7 @@
* The locking for D_COMPLETE is a bit odd:
* - we can clear it at almost any time (see ceph_d_prune)
* - it is only meaningful if:
- * - we hold dir inode i_lock
+ * - we hold dir inode i_ceph_lock
* - we hold dir FILE_SHARED caps
* - the dentry D_COMPLETE is set
*/
@@ -250,6 +250,8 @@
struct ceph_inode_info {
struct ceph_vino i_vino; /* ceph ino + snap */
+ spinlock_t i_ceph_lock;
+
u64 i_version;
u32 i_time_warp_seq;
@@ -271,7 +273,7 @@
struct ceph_inode_xattrs_info i_xattrs;
- /* capabilities. protected _both_ by i_lock and cap->session's
+ /* capabilities. protected _both_ by i_ceph_lock and cap->session's
* s_mutex. */
struct rb_root i_caps; /* cap list */
struct ceph_cap *i_auth_cap; /* authoritative cap, if any */
@@ -437,18 +439,18 @@
{
struct ceph_inode_info *ci = ceph_inode(inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags &= ~mask;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
static inline void ceph_i_set(struct inode *inode, unsigned mask)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
ci->i_ceph_flags |= mask;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
}
static inline bool ceph_i_test(struct inode *inode, unsigned mask)
@@ -456,9 +458,9 @@
struct ceph_inode_info *ci = ceph_inode(inode);
bool r;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
r = (ci->i_ceph_flags & mask) == mask;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return r;
}
@@ -508,9 +510,9 @@
static inline int ceph_caps_issued(struct ceph_inode_info *ci)
{
int issued;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
issued = __ceph_caps_issued(ci, NULL);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return issued;
}
@@ -518,9 +520,9 @@
int touch)
{
int r;
- spin_lock(&ci->vfs_inode.i_lock);
+ spin_lock(&ci->i_ceph_lock);
r = __ceph_caps_issued_mask(ci, mask, touch);
- spin_unlock(&ci->vfs_inode.i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return r;
}
@@ -743,10 +745,9 @@
extern void __ceph_remove_cap(struct ceph_cap *cap);
static inline void ceph_remove_cap(struct ceph_cap *cap)
{
- struct inode *inode = &cap->ci->vfs_inode;
- spin_lock(&inode->i_lock);
+ spin_lock(&cap->ci->i_ceph_lock);
__ceph_remove_cap(cap);
- spin_unlock(&inode->i_lock);
+ spin_unlock(&cap->ci->i_ceph_lock);
}
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 96c6739..a5e36e4 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -343,8 +343,8 @@
}
static int __build_xattrs(struct inode *inode)
- __releases(inode->i_lock)
- __acquires(inode->i_lock)
+ __releases(ci->i_ceph_lock)
+ __acquires(ci->i_ceph_lock)
{
u32 namelen;
u32 numattr = 0;
@@ -372,7 +372,7 @@
end = p + ci->i_xattrs.blob->vec.iov_len;
ceph_decode_32_safe(&p, end, numattr, bad);
xattr_version = ci->i_xattrs.version;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
xattrs = kcalloc(numattr, sizeof(struct ceph_xattr *),
GFP_NOFS);
@@ -387,7 +387,7 @@
goto bad_lock;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_xattrs.version != xattr_version) {
/* lost a race, retry */
for (i = 0; i < numattr; i++)
@@ -418,7 +418,7 @@
return err;
bad_lock:
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
bad:
if (xattrs) {
for (i = 0; i < numattr; i++)
@@ -512,7 +512,7 @@
if (vxattrs)
vxattr = ceph_match_vxattr(vxattrs, name);
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("getxattr %p ver=%lld index_ver=%lld\n", inode,
ci->i_xattrs.version, ci->i_xattrs.index_version);
@@ -520,14 +520,14 @@
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto get_xattr;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
/* get xattrs from mds (if we don't already have them) */
err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
if (err)
return err;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (vxattr && vxattr->readonly) {
err = vxattr->getxattr_cb(ci, value, size);
@@ -558,7 +558,7 @@
memcpy(value, xattr->val, xattr->val_len);
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return err;
}
@@ -573,7 +573,7 @@
u32 len;
int i;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
dout("listxattr %p ver=%lld index_ver=%lld\n", inode,
ci->i_xattrs.version, ci->i_xattrs.index_version);
@@ -581,13 +581,13 @@
(ci->i_xattrs.index_version >= ci->i_xattrs.version)) {
goto list_xattr;
} else {
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = ceph_do_getattr(inode, CEPH_STAT_CAP_XATTR);
if (err)
return err;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
err = __build_xattrs(inode);
if (err < 0)
@@ -619,7 +619,7 @@
}
out:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
return err;
}
@@ -739,7 +739,7 @@
if (!xattr)
goto out;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
retry:
issued = __ceph_caps_issued(ci, NULL);
if (!(issued & CEPH_CAP_XATTR_EXCL))
@@ -752,12 +752,12 @@
required_blob_size > ci->i_xattrs.prealloc_blob->alloc_len) {
struct ceph_buffer *blob = NULL;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
dout(" preaallocating new blob size=%d\n", required_blob_size);
blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
if (!blob)
goto out;
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
if (ci->i_xattrs.prealloc_blob)
ceph_buffer_put(ci->i_xattrs.prealloc_blob);
ci->i_xattrs.prealloc_blob = blob;
@@ -770,13 +770,13 @@
dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
ci->i_xattrs.dirty = true;
inode->i_ctime = CURRENT_TIME;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
return err;
do_sync:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = ceph_sync_setxattr(dentry, name, value, size, flags);
out:
kfree(newname);
@@ -833,7 +833,7 @@
return -EOPNOTSUPP;
}
- spin_lock(&inode->i_lock);
+ spin_lock(&ci->i_ceph_lock);
__build_xattrs(inode);
issued = __ceph_caps_issued(ci, NULL);
dout("removexattr %p issued %s\n", inode, ceph_cap_string(issued));
@@ -846,12 +846,12 @@
ci->i_xattrs.dirty = true;
inode->i_ctime = CURRENT_TIME;
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
if (dirty)
__mark_inode_dirty(inode, dirty);
return err;
do_sync:
- spin_unlock(&inode->i_lock);
+ spin_unlock(&ci->i_ceph_lock);
err = ceph_send_removexattr(dentry, name);
return err;
}
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index ca418aa..9d8715c 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -292,7 +292,7 @@
return bdi_init(&configfs_backing_dev_info);
}
-void __exit configfs_inode_exit(void)
+void configfs_inode_exit(void)
{
bdi_destroy(&configfs_backing_dev_info);
}
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index ecc6217..276e15c 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -143,28 +143,26 @@
goto out;
config_kobj = kobject_create_and_add("config", kernel_kobj);
- if (!config_kobj) {
- kmem_cache_destroy(configfs_dir_cachep);
- configfs_dir_cachep = NULL;
- goto out;
- }
-
- err = register_filesystem(&configfs_fs_type);
- if (err) {
- printk(KERN_ERR "configfs: Unable to register filesystem!\n");
- kobject_put(config_kobj);
- kmem_cache_destroy(configfs_dir_cachep);
- configfs_dir_cachep = NULL;
- goto out;
- }
+ if (!config_kobj)
+ goto out2;
err = configfs_inode_init();
- if (err) {
- unregister_filesystem(&configfs_fs_type);
- kobject_put(config_kobj);
- kmem_cache_destroy(configfs_dir_cachep);
- configfs_dir_cachep = NULL;
- }
+ if (err)
+ goto out3;
+
+ err = register_filesystem(&configfs_fs_type);
+ if (err)
+ goto out4;
+
+ return 0;
+out4:
+ printk(KERN_ERR "configfs: Unable to register filesystem!\n");
+ configfs_inode_exit();
+out3:
+ kobject_put(config_kobj);
+out2:
+ kmem_cache_destroy(configfs_dir_cachep);
+ configfs_dir_cachep = NULL;
out:
return err;
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 61fa9e1..607b155 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -1095,7 +1095,7 @@
le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block),
ext4_idx_pblock(EXT_FIRST_INDEX(neh)));
- neh->eh_depth = cpu_to_le16(neh->eh_depth + 1);
+ neh->eh_depth = cpu_to_le16(le16_to_cpu(neh->eh_depth) + 1);
ext4_mark_inode_dirty(handle, inode);
out:
brelse(bh);
@@ -2955,7 +2955,6 @@
/* Pre-conditions */
BUG_ON(!ext4_ext_is_uninitialized(ex));
BUG_ON(!in_range(map->m_lblk, ee_block, ee_len));
- BUG_ON(map->m_lblk + map->m_len > ee_block + ee_len);
/*
* Attempt to transfer newly initialized blocks from the currently
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 848f436..92655fd 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1339,8 +1339,11 @@
clear_buffer_unwritten(bh);
}
- /* skip page if block allocation undone */
- if (buffer_delay(bh) || buffer_unwritten(bh))
+ /*
+ * skip page if block allocation undone and
+ * block is dirty
+ */
+ if (ext4_bh_delay_or_unwritten(NULL, bh))
skip_page = 1;
bh = bh->b_this_page;
block_start += bh->b_size;
@@ -2387,7 +2390,6 @@
pgoff_t index;
struct inode *inode = mapping->host;
handle_t *handle;
- loff_t page_len;
index = pos >> PAGE_CACHE_SHIFT;
@@ -2434,13 +2436,6 @@
*/
if (pos + len > inode->i_size)
ext4_truncate_failed_write(inode);
- } else {
- page_len = pos & (PAGE_CACHE_SIZE - 1);
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers_no_lock(handle,
- inode, page, pos - page_len, page_len,
- EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
- }
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
@@ -2483,7 +2478,6 @@
loff_t new_i_size;
unsigned long start, end;
int write_mode = (int)(unsigned long)fsdata;
- loff_t page_len;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
if (ext4_should_order_data(inode)) {
@@ -2508,7 +2502,7 @@
*/
new_i_size = pos + copied;
- if (new_i_size > EXT4_I(inode)->i_disksize) {
+ if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
if (ext4_da_should_update_i_disksize(page, end)) {
down_write(&EXT4_I(inode)->i_data_sem);
if (new_i_size > EXT4_I(inode)->i_disksize) {
@@ -2532,16 +2526,6 @@
}
ret2 = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
-
- page_len = PAGE_CACHE_SIZE -
- ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1));
-
- if (page_len > 0) {
- ret = ext4_discard_partial_page_buffers_no_lock(handle,
- inode, page, pos + copied - 1, page_len,
- EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED);
- }
-
copied = ret2;
if (ret2 < 0)
ret = ret2;
@@ -2781,10 +2765,11 @@
iocb->private, io_end->inode->i_ino, iocb, offset,
size);
+ iocb->private = NULL;
+
/* if not aio dio with unwritten extents, just free io and return */
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
ext4_free_io_end(io_end);
- iocb->private = NULL;
out:
if (is_async)
aio_complete(iocb, ret, 0);
@@ -2807,7 +2792,6 @@
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/* queue the work to convert unwritten extents to written */
- iocb->private = NULL;
queue_work(wq, &io_end->work);
/* XXX: probably should move into the real I/O completion handler */
@@ -3203,26 +3187,8 @@
iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
- if (!page_has_buffers(page)) {
- /*
- * If the range to be discarded covers a partial block
- * we need to get the page buffers. This is because
- * partial blocks cannot be released and the page needs
- * to be updated with the contents of the block before
- * we write the zeros on top of it.
- */
- if ((from & (blocksize - 1)) ||
- ((from + length) & (blocksize - 1))) {
- create_empty_buffers(page, blocksize, 0);
- } else {
- /*
- * If there are no partial blocks,
- * there is nothing to update,
- * so we can return now
- */
- return 0;
- }
- }
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, blocksize, 0);
/* Find the buffer that contains "offset" */
bh = page_buffers(page);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7ce1d0b..7e106c8 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -385,6 +385,18 @@
block_end = block_start + blocksize;
if (block_start >= len) {
+ /*
+ * Comments copied from block_write_full_page_endio:
+ *
+ * The page straddles i_size. It must be zeroed out on
+ * each and every writepage invocation because it may
+ * be mmapped. "A file is mapped in multiples of the
+ * page size. For a file that is not a multiple of
+ * the page size, the remaining memory is zeroed when
+ * mapped, and writes to that region are not written
+ * out to the file."
+ */
+ zero_user_segment(page, block_start, block_end);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3858767..3e1329e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1155,9 +1155,9 @@
seq_puts(seq, ",block_validity");
if (!test_opt(sb, INIT_INODE_TABLE))
- seq_puts(seq, ",noinit_inode_table");
+ seq_puts(seq, ",noinit_itable");
else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
- seq_printf(seq, ",init_inode_table=%u",
+ seq_printf(seq, ",init_itable=%u",
(unsigned) sbi->s_li_wait_mult);
ext4_show_quota_options(seq, sb);
@@ -1333,8 +1333,7 @@
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
- Opt_discard, Opt_nodiscard,
- Opt_init_inode_table, Opt_noinit_inode_table,
+ Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
};
static const match_table_t tokens = {
@@ -1407,9 +1406,9 @@
{Opt_dioread_lock, "dioread_lock"},
{Opt_discard, "discard"},
{Opt_nodiscard, "nodiscard"},
- {Opt_init_inode_table, "init_itable=%u"},
- {Opt_init_inode_table, "init_itable"},
- {Opt_noinit_inode_table, "noinit_itable"},
+ {Opt_init_itable, "init_itable=%u"},
+ {Opt_init_itable, "init_itable"},
+ {Opt_noinit_itable, "noinit_itable"},
{Opt_err, NULL},
};
@@ -1892,7 +1891,7 @@
case Opt_dioread_lock:
clear_opt(sb, DIOREAD_NOLOCK);
break;
- case Opt_init_inode_table:
+ case Opt_init_itable:
set_opt(sb, INIT_INODE_TABLE);
if (args[0].from) {
if (match_int(&args[0], &option))
@@ -1903,7 +1902,7 @@
return 0;
sbi->s_li_wait_mult = option;
break;
- case Opt_noinit_inode_table:
+ case Opt_noinit_itable:
clear_opt(sb, INIT_INODE_TABLE);
break;
default:
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 73c3992..ac86f8b 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -156,6 +156,7 @@
* bdi_start_writeback - start writeback
* @bdi: the backing device to write from
* @nr_pages: the number of pages to write
+ * @reason: reason why some writeback work was initiated
*
* Description:
* This does WB_SYNC_NONE opportunistic writeback. The IO is only
@@ -1223,6 +1224,7 @@
* writeback_inodes_sb_nr - writeback dirty inodes from given super_block
* @sb: the superblock
* @nr: the number of pages to write
+ * @reason: reason why some writeback work initiated
*
* Start writeback on some inodes on this super_block. No guarantees are made
* on how many (if any) will be written, and this function does not wait
@@ -1251,6 +1253,7 @@
/**
* writeback_inodes_sb - writeback dirty inodes from given super_block
* @sb: the superblock
+ * @reason: reason why some writeback work was initiated
*
* Start writeback on some inodes on this super_block. No guarantees are made
* on how many (if any) will be written, and this function does not wait
@@ -1265,6 +1268,7 @@
/**
* writeback_inodes_sb_if_idle - start writeback if none underway
* @sb: the superblock
+ * @reason: reason why some writeback work was initiated
*
* Invoke writeback_inodes_sb if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
@@ -1285,6 +1289,7 @@
* writeback_inodes_sb_if_idle - start writeback if none underway
* @sb: the superblock
* @nr: the number of pages to write
+ * @reason: reason why some writeback work was initiated
*
* Invoke writeback_inodes_sb if no writeback is currently underway.
* Returns 1 if writeback was started, 0 if not.
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 5cb8614..2aaf3ea 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1512,7 +1512,7 @@
else if (outarg->offset + num > file_size)
num = file_size - outarg->offset;
- while (num) {
+ while (num && req->num_pages < FUSE_MAX_PAGES_PER_REQ) {
struct page *page;
unsigned int this_num;
@@ -1526,6 +1526,7 @@
num -= this_num;
total_len += this_num;
+ index++;
}
req->misc.retrieve_in.offset = outarg->offset;
req->misc.retrieve_in.size = total_len;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 594f07a..0c84100 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1556,7 +1556,7 @@
struct inode *inode = file->f_path.dentry->d_inode;
mutex_lock(&inode->i_mutex);
- if (origin != SEEK_CUR || origin != SEEK_SET) {
+ if (origin != SEEK_CUR && origin != SEEK_SET) {
retval = fuse_update_attributes(inode, NULL, file, NULL);
if (retval)
goto exit;
@@ -1567,6 +1567,10 @@
offset += i_size_read(inode);
break;
case SEEK_CUR:
+ if (offset == 0) {
+ retval = file->f_pos;
+ goto exit;
+ }
offset += file->f_pos;
break;
case SEEK_DATA:
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 3e6d727..aa83109 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1138,28 +1138,28 @@
{
int err;
- err = register_filesystem(&fuse_fs_type);
- if (err)
- goto out;
-
- err = register_fuseblk();
- if (err)
- goto out_unreg;
-
fuse_inode_cachep = kmem_cache_create("fuse_inode",
sizeof(struct fuse_inode),
0, SLAB_HWCACHE_ALIGN,
fuse_inode_init_once);
err = -ENOMEM;
if (!fuse_inode_cachep)
- goto out_unreg2;
+ goto out;
+
+ err = register_fuseblk();
+ if (err)
+ goto out2;
+
+ err = register_filesystem(&fuse_fs_type);
+ if (err)
+ goto out3;
return 0;
- out_unreg2:
+ out3:
unregister_fuseblk();
- out_unreg:
- unregister_filesystem(&fuse_fs_type);
+ out2:
+ kmem_cache_destroy(fuse_inode_cachep);
out:
return err;
}
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 5b5fa33..cbd1a61 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -548,7 +548,7 @@
error = bdi_setup_and_register(&server->bdi, "ncpfs", BDI_CAP_MAP_COPY);
if (error)
- goto out_bdi;
+ goto out_fput;
server->ncp_filp = ncp_filp;
server->ncp_sock = sock;
@@ -559,7 +559,7 @@
error = -EBADF;
server->info_filp = fget(data.info_fd);
if (!server->info_filp)
- goto out_fput;
+ goto out_bdi;
error = -ENOTSOCK;
sock_inode = server->info_filp->f_path.dentry->d_inode;
if (!S_ISSOCK(sock_inode->i_mode))
@@ -746,9 +746,9 @@
out_fput2:
if (server->info_filp)
fput(server->info_filp);
-out_fput:
- bdi_destroy(&server->bdi);
out_bdi:
+ bdi_destroy(&server->bdi);
+out_fput:
/* 23/12/1998 Marcin Dalecki <dalecki@cs.net.pl>:
*
* The previously used put_filp(ncp_filp); was bogus, since
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 9a8a2b7..03102d9 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -91,20 +91,18 @@
void __init proc_root_init(void)
{
- struct vfsmount *mnt;
int err;
proc_init_inodecache();
err = register_filesystem(&proc_fs_type);
if (err)
return;
- mnt = kern_mount_data(&proc_fs_type, &init_pid_ns);
- if (IS_ERR(mnt)) {
+ err = pid_ns_prepare_proc(&init_pid_ns);
+ if (err) {
unregister_filesystem(&proc_fs_type);
return;
}
- init_pid_ns.proc_mnt = mnt;
proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
@@ -209,5 +207,5 @@
void pid_ns_release_proc(struct pid_namespace *ns)
{
- mntput(ns->proc_mnt);
+ kern_unmount(ns->proc_mnt);
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 20403dc..ae0e76b 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2264,19 +2264,12 @@
return -EINVAL;
}
- err = register_filesystem(&ubifs_fs_type);
- if (err) {
- ubifs_err("cannot register file system, error %d", err);
- return err;
- }
-
- err = -ENOMEM;
ubifs_inode_slab = kmem_cache_create("ubifs_inode_slab",
sizeof(struct ubifs_inode), 0,
SLAB_MEM_SPREAD | SLAB_RECLAIM_ACCOUNT,
&inode_slab_ctor);
if (!ubifs_inode_slab)
- goto out_reg;
+ return -ENOMEM;
register_shrinker(&ubifs_shrinker_info);
@@ -2288,15 +2281,20 @@
if (err)
goto out_compr;
+ err = register_filesystem(&ubifs_fs_type);
+ if (err) {
+ ubifs_err("cannot register file system, error %d", err);
+ goto out_dbg;
+ }
return 0;
+out_dbg:
+ dbg_debugfs_exit();
out_compr:
ubifs_compressors_exit();
out_shrinker:
unregister_shrinker(&ubifs_shrinker_info);
kmem_cache_destroy(ubifs_inode_slab);
-out_reg:
- unregister_filesystem(&ubifs_fs_type);
return err;
}
/* late_initcall to let compressors initialize first */
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 4e4fbb8..14b6cd0 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -182,8 +182,11 @@
{0x1002, 0x6748, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6749, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6750, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6751, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6758, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6759, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x675B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x675D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x675F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6760, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6761, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -195,8 +198,10 @@
{0x1002, 0x6767, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6768, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x6772, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x677B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6840, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6841, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
{0x1002, 0x6842, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -246,6 +251,7 @@
{0x1002, 0x68f2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68f8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68f9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
+ {0x1002, 0x68fa, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x68fe, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CEDAR|RADEON_NEW_MEMMAP}, \
{0x1002, 0x7100, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R520|RADEON_NEW_MEMMAP}, \
{0x1002, 0x7101, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R520|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -488,6 +494,8 @@
{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x964b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x964c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x964e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x964f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
{0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -502,6 +510,8 @@
{0x1002, 0x9805, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9806, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0x1002, 0x9807, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+ {0x1002, 0x9809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PALM|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
{0, 0, 0}
#define r128_PCI_IDS \
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index a3ef66a..3c1063a 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -22,8 +22,14 @@
#include <asm/bitops.h>
#define for_each_set_bit(bit, addr, size) \
- for ((bit) = find_first_bit((addr), (size)); \
- (bit) < (size); \
+ for ((bit) = find_first_bit((addr), (size)); \
+ (bit) < (size); \
+ (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_cont(bit, addr, size) \
+ for ((bit) = find_next_bit((addr), (size), (bit)); \
+ (bit) < (size); \
(bit) = find_next_bit((addr), (size), (bit) + 1))
static __inline__ int get_bitmask_order(unsigned int count)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c7a6d3b..94acd81 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -805,9 +805,6 @@
*/
extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
spinlock_t *lock, int node_id);
-extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *,
- request_fn_proc *,
- spinlock_t *, int node_id);
extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
request_fn_proc *, spinlock_t *);
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index ef90cbd..57c9a8a 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -31,6 +31,7 @@
extern int iommu_calculate_agaw(struct intel_iommu *iommu);
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled;
+extern int intel_iommu_enabled;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{
@@ -44,6 +45,7 @@
{
}
#define dmar_disabled (1)
+#define intel_iommu_enabled (0)
#endif
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 388b0d4..5ce8b14 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -3,6 +3,7 @@
#include <linux/types.h>
#include <linux/compiler.h>
+#include <linux/workqueue.h>
#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
@@ -14,6 +15,12 @@
#endif
};
+struct jump_label_key_deferred {
+ struct jump_label_key key;
+ unsigned long timeout;
+ struct delayed_work work;
+};
+
# include <asm/jump_label.h>
# define HAVE_JUMP_LABEL
#endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */
@@ -51,8 +58,11 @@
extern int jump_label_text_reserved(void *start, void *end);
extern void jump_label_inc(struct jump_label_key *key);
extern void jump_label_dec(struct jump_label_key *key);
+extern void jump_label_dec_deferred(struct jump_label_key_deferred *key);
extern bool jump_label_enabled(struct jump_label_key *key);
extern void jump_label_apply_nops(struct module *mod);
+extern void jump_label_rate_limit(struct jump_label_key_deferred *key,
+ unsigned long rl);
#else /* !HAVE_JUMP_LABEL */
@@ -68,6 +78,10 @@
{
}
+struct jump_label_key_deferred {
+ struct jump_label_key key;
+};
+
static __always_inline bool static_branch(struct jump_label_key *key)
{
if (unlikely(atomic_read(&key->enabled)))
@@ -85,6 +99,11 @@
atomic_dec(&key->enabled);
}
+static inline void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+ jump_label_dec(&key->key);
+}
+
static inline int jump_label_text_reserved(void *start, void *end)
{
return 0;
@@ -102,6 +121,14 @@
{
return 0;
}
+
+static inline void jump_label_rate_limit(struct jump_label_key_deferred *key,
+ unsigned long rl)
+{
+}
#endif /* HAVE_JUMP_LABEL */
+#define jump_label_key_enabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(1), })
+#define jump_label_key_disabled ((struct jump_label_key){ .enabled = ATOMIC_INIT(0), })
+
#endif /* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/log2.h b/include/linux/log2.h
index 25b8086..fd7ff3d 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -185,7 +185,6 @@
#define rounddown_pow_of_two(n) \
( \
__builtin_constant_p(n) ? ( \
- (n == 1) ? 0 : \
(1UL << ilog2(n))) : \
__rounddown_pow_of_two(n) \
)
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 415f2db..c8ef9bc 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -218,6 +218,7 @@
#define MMC_QUIRK_INAND_CMD38 (1<<6) /* iNAND devices have broken CMD38 */
#define MMC_QUIRK_BLK_NO_CMD23 (1<<7) /* Avoid CMD23 for regular multiblock */
#define MMC_QUIRK_BROKEN_BYTE_MODE_512 (1<<8) /* Avoid sending 512 bytes in */
+#define MMC_QUIRK_LONG_READ_TIME (1<<9) /* Data read time > CSD says */
/* byte mode */
unsigned int poweroff_notify_state; /* eMMC4.5 notify feature */
#define MMC_NO_POWER_NOTIFICATION 0
@@ -433,6 +434,11 @@
return c->quirks & MMC_QUIRK_BROKEN_BYTE_MODE_512;
}
+static inline int mmc_card_long_read_time(const struct mmc_card *c)
+{
+ return c->quirks & MMC_QUIRK_LONG_READ_TIME;
+}
+
#define mmc_card_name(c) ((c)->cid.prod_name)
#define mmc_card_id(c) (dev_name(&(c)->dev))
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b1f8912..0885561 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -54,6 +54,7 @@
PERF_COUNT_HW_BUS_CYCLES = 6,
PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7,
PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8,
+ PERF_COUNT_HW_REF_CPU_CYCLES = 9,
PERF_COUNT_HW_MAX, /* non-ABI */
};
@@ -890,6 +891,7 @@
int nr_active;
int is_active;
int nr_stat;
+ int nr_freq;
int rotate_disable;
atomic_t refcount;
struct task_struct *task;
@@ -1063,12 +1065,12 @@
}
}
-extern struct jump_label_key perf_sched_events;
+extern struct jump_label_key_deferred perf_sched_events;
static inline void perf_event_task_sched_in(struct task_struct *prev,
struct task_struct *task)
{
- if (static_branch(&perf_sched_events))
+ if (static_branch(&perf_sched_events.key))
__perf_event_task_sched_in(prev, task);
}
@@ -1077,7 +1079,7 @@
{
perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
- if (static_branch(&perf_sched_events))
+ if (static_branch(&perf_sched_events.key))
__perf_event_task_sched_out(prev, next);
}
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 2e0ecfc..5b4293d 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -1269,7 +1269,7 @@
void mq_put_mnt(struct ipc_namespace *ns)
{
- mntput(ns->mq_mnt);
+ kern_unmount(ns->mq_mnt);
}
static int __init init_mqueue_fs(void)
@@ -1291,11 +1291,9 @@
spin_lock_init(&mq_lock);
- init_ipc_ns.mq_mnt = kern_mount_data(&mqueue_fs_type, &init_ipc_ns);
- if (IS_ERR(init_ipc_ns.mq_mnt)) {
- error = PTR_ERR(init_ipc_ns.mq_mnt);
+ error = mq_init_ns(&init_ipc_ns);
+ if (error)
goto out_filesystem;
- }
return 0;
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 8b5ce5d3..5652101 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -27,11 +27,6 @@
*/
struct ipc_namespace init_ipc_ns = {
.count = ATOMIC_INIT(1),
-#ifdef CONFIG_POSIX_MQUEUE
- .mq_queues_max = DFLT_QUEUESMAX,
- .mq_msg_max = DFLT_MSGMAX,
- .mq_msgsize_max = DFLT_MSGSIZEMAX,
-#endif
.user_ns = &init_user_ns,
};
diff --git a/kernel/events/Makefile b/kernel/events/Makefile
index 89e5e8a..22d901f 100644
--- a/kernel/events/Makefile
+++ b/kernel/events/Makefile
@@ -2,5 +2,5 @@
CFLAGS_REMOVE_core.o = -pg
endif
-obj-y := core.o ring_buffer.o
+obj-y := core.o ring_buffer.o callchain.o
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
new file mode 100644
index 0000000..057e24b
--- /dev/null
+++ b/kernel/events/callchain.c
@@ -0,0 +1,191 @@
+/*
+ * Performance events callchain code, extracted from core.c:
+ *
+ * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar
+ * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * For licensing details see kernel-base/COPYING
+ */
+
+#include <linux/perf_event.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+struct callchain_cpus_entries {
+ struct rcu_head rcu_head;
+ struct perf_callchain_entry *cpu_entries[0];
+};
+
+static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
+static atomic_t nr_callchain_events;
+static DEFINE_MUTEX(callchain_mutex);
+static struct callchain_cpus_entries *callchain_cpus_entries;
+
+
+__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
+ struct pt_regs *regs)
+{
+}
+
+__weak void perf_callchain_user(struct perf_callchain_entry *entry,
+ struct pt_regs *regs)
+{
+}
+
+static void release_callchain_buffers_rcu(struct rcu_head *head)
+{
+ struct callchain_cpus_entries *entries;
+ int cpu;
+
+ entries = container_of(head, struct callchain_cpus_entries, rcu_head);
+
+ for_each_possible_cpu(cpu)
+ kfree(entries->cpu_entries[cpu]);
+
+ kfree(entries);
+}
+
+static void release_callchain_buffers(void)
+{
+ struct callchain_cpus_entries *entries;
+
+ entries = callchain_cpus_entries;
+ rcu_assign_pointer(callchain_cpus_entries, NULL);
+ call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
+}
+
+static int alloc_callchain_buffers(void)
+{
+ int cpu;
+ int size;
+ struct callchain_cpus_entries *entries;
+
+ /*
+ * We can't use the percpu allocation API for data that can be
+ * accessed from NMI. Use a temporary manual per cpu allocation
+ * until that gets sorted out.
+ */
+ size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
+
+ entries = kzalloc(size, GFP_KERNEL);
+ if (!entries)
+ return -ENOMEM;
+
+ size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
+
+ for_each_possible_cpu(cpu) {
+ entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
+ cpu_to_node(cpu));
+ if (!entries->cpu_entries[cpu])
+ goto fail;
+ }
+
+ rcu_assign_pointer(callchain_cpus_entries, entries);
+
+ return 0;
+
+fail:
+ for_each_possible_cpu(cpu)
+ kfree(entries->cpu_entries[cpu]);
+ kfree(entries);
+
+ return -ENOMEM;
+}
+
+int get_callchain_buffers(void)
+{
+ int err = 0;
+ int count;
+
+ mutex_lock(&callchain_mutex);
+
+ count = atomic_inc_return(&nr_callchain_events);
+ if (WARN_ON_ONCE(count < 1)) {
+ err = -EINVAL;
+ goto exit;
+ }
+
+ if (count > 1) {
+ /* If the allocation failed, give up */
+ if (!callchain_cpus_entries)
+ err = -ENOMEM;
+ goto exit;
+ }
+
+ err = alloc_callchain_buffers();
+ if (err)
+ release_callchain_buffers();
+exit:
+ mutex_unlock(&callchain_mutex);
+
+ return err;
+}
+
+void put_callchain_buffers(void)
+{
+ if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
+ release_callchain_buffers();
+ mutex_unlock(&callchain_mutex);
+ }
+}
+
+static struct perf_callchain_entry *get_callchain_entry(int *rctx)
+{
+ int cpu;
+ struct callchain_cpus_entries *entries;
+
+ *rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
+ if (*rctx == -1)
+ return NULL;
+
+ entries = rcu_dereference(callchain_cpus_entries);
+ if (!entries)
+ return NULL;
+
+ cpu = smp_processor_id();
+
+ return &entries->cpu_entries[cpu][*rctx];
+}
+
+static void
+put_callchain_entry(int rctx)
+{
+ put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
+}
+
+struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+{
+ int rctx;
+ struct perf_callchain_entry *entry;
+
+
+ entry = get_callchain_entry(&rctx);
+ if (rctx == -1)
+ return NULL;
+
+ if (!entry)
+ goto exit_put;
+
+ entry->nr = 0;
+
+ if (!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) {
+ perf_callchain_store(entry, PERF_CONTEXT_USER);
+ perf_callchain_user(entry, regs);
+ }
+
+exit_put:
+ put_callchain_entry(rctx);
+
+ return entry;
+}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3b9df5..2f8f3f1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -128,7 +128,7 @@
* perf_sched_events : >0 events exist
* perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
*/
-struct jump_label_key perf_sched_events __read_mostly;
+struct jump_label_key_deferred perf_sched_events __read_mostly;
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
static atomic_t nr_mmap_events __read_mostly;
@@ -1130,6 +1130,8 @@
if (!is_software_event(event))
cpuctx->active_oncpu--;
ctx->nr_active--;
+ if (event->attr.freq && event->attr.sample_freq)
+ ctx->nr_freq--;
if (event->attr.exclusive || !cpuctx->active_oncpu)
cpuctx->exclusive = 0;
}
@@ -1325,6 +1327,7 @@
}
raw_spin_unlock_irq(&ctx->lock);
}
+EXPORT_SYMBOL_GPL(perf_event_disable);
static void perf_set_shadow_time(struct perf_event *event,
struct perf_event_context *ctx,
@@ -1406,6 +1409,8 @@
if (!is_software_event(event))
cpuctx->active_oncpu++;
ctx->nr_active++;
+ if (event->attr.freq && event->attr.sample_freq)
+ ctx->nr_freq++;
if (event->attr.exclusive)
cpuctx->exclusive = 1;
@@ -1662,8 +1667,7 @@
* Note: this works for group members as well as group leaders
* since the non-leader members' sibling_lists will be empty.
*/
-static void __perf_event_mark_enabled(struct perf_event *event,
- struct perf_event_context *ctx)
+static void __perf_event_mark_enabled(struct perf_event *event)
{
struct perf_event *sub;
u64 tstamp = perf_event_time(event);
@@ -1701,7 +1705,7 @@
*/
perf_cgroup_set_timestamp(current, ctx);
- __perf_event_mark_enabled(event, ctx);
+ __perf_event_mark_enabled(event);
if (!event_filter_match(event)) {
if (is_cgroup_event(event))
@@ -1782,7 +1786,7 @@
retry:
if (!ctx->is_active) {
- __perf_event_mark_enabled(event, ctx);
+ __perf_event_mark_enabled(event);
goto out;
}
@@ -1809,6 +1813,7 @@
out:
raw_spin_unlock_irq(&ctx->lock);
}
+EXPORT_SYMBOL_GPL(perf_event_enable);
int perf_event_refresh(struct perf_event *event, int refresh)
{
@@ -2327,6 +2332,9 @@
u64 interrupts, now;
s64 delta;
+ if (!ctx->nr_freq)
+ return;
+
list_for_each_entry_rcu(event, &ctx->event_list, event_entry) {
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
@@ -2382,12 +2390,14 @@
{
u64 interval = (u64)cpuctx->jiffies_interval * TICK_NSEC;
struct perf_event_context *ctx = NULL;
- int rotate = 0, remove = 1;
+ int rotate = 0, remove = 1, freq = 0;
if (cpuctx->ctx.nr_events) {
remove = 0;
if (cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
rotate = 1;
+ if (cpuctx->ctx.nr_freq)
+ freq = 1;
}
ctx = cpuctx->task_ctx;
@@ -2395,33 +2405,40 @@
remove = 0;
if (ctx->nr_events != ctx->nr_active)
rotate = 1;
+ if (ctx->nr_freq)
+ freq = 1;
}
+ if (!rotate && !freq)
+ goto done;
+
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(cpuctx->ctx.pmu);
- perf_ctx_adjust_freq(&cpuctx->ctx, interval);
- if (ctx)
- perf_ctx_adjust_freq(ctx, interval);
- if (!rotate)
- goto done;
+ if (freq) {
+ perf_ctx_adjust_freq(&cpuctx->ctx, interval);
+ if (ctx)
+ perf_ctx_adjust_freq(ctx, interval);
+ }
- cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- if (ctx)
- ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
+ if (rotate) {
+ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+ if (ctx)
+ ctx_sched_out(ctx, cpuctx, EVENT_FLEXIBLE);
- rotate_ctx(&cpuctx->ctx);
- if (ctx)
- rotate_ctx(ctx);
+ rotate_ctx(&cpuctx->ctx);
+ if (ctx)
+ rotate_ctx(ctx);
- perf_event_sched_in(cpuctx, ctx, current);
+ perf_event_sched_in(cpuctx, ctx, current);
+ }
+
+ perf_pmu_enable(cpuctx->ctx.pmu);
+ perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
done:
if (remove)
list_del_init(&cpuctx->rotation_list);
-
- perf_pmu_enable(cpuctx->ctx.pmu);
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
void perf_event_task_tick(void)
@@ -2448,7 +2465,7 @@
if (event->state >= PERF_EVENT_STATE_INACTIVE)
return 0;
- __perf_event_mark_enabled(event, ctx);
+ __perf_event_mark_enabled(event);
return 1;
}
@@ -2480,13 +2497,7 @@
raw_spin_lock(&ctx->lock);
task_ctx_sched_out(ctx);
- list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
- ret = event_enable_on_exec(event, ctx);
- if (ret)
- enabled = 1;
- }
-
- list_for_each_entry(event, &ctx->flexible_groups, group_entry) {
+ list_for_each_entry(event, &ctx->event_list, event_entry) {
ret = event_enable_on_exec(event, ctx);
if (ret)
enabled = 1;
@@ -2574,215 +2585,6 @@
}
/*
- * Callchain support
- */
-
-struct callchain_cpus_entries {
- struct rcu_head rcu_head;
- struct perf_callchain_entry *cpu_entries[0];
-};
-
-static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
-static atomic_t nr_callchain_events;
-static DEFINE_MUTEX(callchain_mutex);
-struct callchain_cpus_entries *callchain_cpus_entries;
-
-
-__weak void perf_callchain_kernel(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
-{
-}
-
-__weak void perf_callchain_user(struct perf_callchain_entry *entry,
- struct pt_regs *regs)
-{
-}
-
-static void release_callchain_buffers_rcu(struct rcu_head *head)
-{
- struct callchain_cpus_entries *entries;
- int cpu;
-
- entries = container_of(head, struct callchain_cpus_entries, rcu_head);
-
- for_each_possible_cpu(cpu)
- kfree(entries->cpu_entries[cpu]);
-
- kfree(entries);
-}
-
-static void release_callchain_buffers(void)
-{
- struct callchain_cpus_entries *entries;
-
- entries = callchain_cpus_entries;
- rcu_assign_pointer(callchain_cpus_entries, NULL);
- call_rcu(&entries->rcu_head, release_callchain_buffers_rcu);
-}
-
-static int alloc_callchain_buffers(void)
-{
- int cpu;
- int size;
- struct callchain_cpus_entries *entries;
-
- /*
- * We can't use the percpu allocation API for data that can be
- * accessed from NMI. Use a temporary manual per cpu allocation
- * until that gets sorted out.
- */
- size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
-
- entries = kzalloc(size, GFP_KERNEL);
- if (!entries)
- return -ENOMEM;
-
- size = sizeof(struct perf_callchain_entry) * PERF_NR_CONTEXTS;
-
- for_each_possible_cpu(cpu) {
- entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL,
- cpu_to_node(cpu));
- if (!entries->cpu_entries[cpu])
- goto fail;
- }
-
- rcu_assign_pointer(callchain_cpus_entries, entries);
-
- return 0;
-
-fail:
- for_each_possible_cpu(cpu)
- kfree(entries->cpu_entries[cpu]);
- kfree(entries);
-
- return -ENOMEM;
-}
-
-static int get_callchain_buffers(void)
-{
- int err = 0;
- int count;
-
- mutex_lock(&callchain_mutex);
-
- count = atomic_inc_return(&nr_callchain_events);
- if (WARN_ON_ONCE(count < 1)) {
- err = -EINVAL;
- goto exit;
- }
-
- if (count > 1) {
- /* If the allocation failed, give up */
- if (!callchain_cpus_entries)
- err = -ENOMEM;
- goto exit;
- }
-
- err = alloc_callchain_buffers();
- if (err)
- release_callchain_buffers();
-exit:
- mutex_unlock(&callchain_mutex);
-
- return err;
-}
-
-static void put_callchain_buffers(void)
-{
- if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) {
- release_callchain_buffers();
- mutex_unlock(&callchain_mutex);
- }
-}
-
-static int get_recursion_context(int *recursion)
-{
- int rctx;
-
- if (in_nmi())
- rctx = 3;
- else if (in_irq())
- rctx = 2;
- else if (in_softirq())
- rctx = 1;
- else
- rctx = 0;
-
- if (recursion[rctx])
- return -1;
-
- recursion[rctx]++;
- barrier();
-
- return rctx;
-}
-
-static inline void put_recursion_context(int *recursion, int rctx)
-{
- barrier();
- recursion[rctx]--;
-}
-
-static struct perf_callchain_entry *get_callchain_entry(int *rctx)
-{
- int cpu;
- struct callchain_cpus_entries *entries;
-
- *rctx = get_recursion_context(__get_cpu_var(callchain_recursion));
- if (*rctx == -1)
- return NULL;
-
- entries = rcu_dereference(callchain_cpus_entries);
- if (!entries)
- return NULL;
-
- cpu = smp_processor_id();
-
- return &entries->cpu_entries[cpu][*rctx];
-}
-
-static void
-put_callchain_entry(int rctx)
-{
- put_recursion_context(__get_cpu_var(callchain_recursion), rctx);
-}
-
-static struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
- int rctx;
- struct perf_callchain_entry *entry;
-
-
- entry = get_callchain_entry(&rctx);
- if (rctx == -1)
- return NULL;
-
- if (!entry)
- goto exit_put;
-
- entry->nr = 0;
-
- if (!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) {
- perf_callchain_store(entry, PERF_CONTEXT_USER);
- perf_callchain_user(entry, regs);
- }
-
-exit_put:
- put_callchain_entry(rctx);
-
- return entry;
-}
-
-/*
* Initialize the perf_event context in a task_struct:
*/
static void __perf_event_init_context(struct perf_event_context *ctx)
@@ -2946,7 +2748,7 @@
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_dec(&perf_sched_events);
+ jump_label_dec_deferred(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
@@ -2957,7 +2759,7 @@
put_callchain_buffers();
if (is_cgroup_event(event)) {
atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
- jump_label_dec(&perf_sched_events);
+ jump_label_dec_deferred(&perf_sched_events);
}
}
@@ -4816,7 +4618,6 @@
struct hw_perf_event *hwc = &event->hw;
int throttle = 0;
- data->period = event->hw.last_period;
if (!overflow)
overflow = perf_swevent_set_period(event);
@@ -4850,6 +4651,12 @@
if (!is_sampling_event(event))
return;
+ if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) {
+ data->period = nr;
+ return perf_swevent_overflow(event, 1, data, regs);
+ } else
+ data->period = event->hw.last_period;
+
if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
return perf_swevent_overflow(event, 1, data, regs);
@@ -5977,7 +5784,7 @@
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_inc(&perf_sched_events);
+ jump_label_inc(&perf_sched_events.key);
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
@@ -6215,7 +6022,7 @@
* - that may need work on context switch
*/
atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
- jump_label_inc(&perf_sched_events);
+ jump_label_inc(&perf_sched_events.key);
}
/*
@@ -7061,6 +6868,9 @@
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
+
+ /* do not patch jump label more than once per second */
+ jump_label_rate_limit(&perf_sched_events, HZ);
}
static int __init perf_event_sysfs_init(void)
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 64568a6..b0b107f 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -1,6 +1,10 @@
#ifndef _KERNEL_EVENTS_INTERNAL_H
#define _KERNEL_EVENTS_INTERNAL_H
+#include <linux/hardirq.h>
+
+/* Buffer handling */
+
#define RING_BUFFER_WRITABLE 0x01
struct ring_buffer {
@@ -67,7 +71,7 @@
}
#endif
-static unsigned long perf_data_size(struct ring_buffer *rb)
+static inline unsigned long perf_data_size(struct ring_buffer *rb)
{
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
}
@@ -96,4 +100,37 @@
} while (len);
}
+/* Callchain handling */
+extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+extern int get_callchain_buffers(void);
+extern void put_callchain_buffers(void);
+
+static inline int get_recursion_context(int *recursion)
+{
+ int rctx;
+
+ if (in_nmi())
+ rctx = 3;
+ else if (in_irq())
+ rctx = 2;
+ else if (in_softirq())
+ rctx = 1;
+ else
+ rctx = 0;
+
+ if (recursion[rctx])
+ return -1;
+
+ recursion[rctx]++;
+ barrier();
+
+ return rctx;
+}
+
+static inline void put_recursion_context(int *recursion, int rctx)
+{
+ barrier();
+ recursion[rctx]--;
+}
+
#endif /* _KERNEL_EVENTS_INTERNAL_H */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 66ff710..30c3c77 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -72,15 +72,46 @@
jump_label_unlock();
}
-void jump_label_dec(struct jump_label_key *key)
+static void __jump_label_dec(struct jump_label_key *key,
+ unsigned long rate_limit, struct delayed_work *work)
{
if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex))
return;
- jump_label_update(key, JUMP_LABEL_DISABLE);
+ if (rate_limit) {
+ atomic_inc(&key->enabled);
+ schedule_delayed_work(work, rate_limit);
+ } else
+ jump_label_update(key, JUMP_LABEL_DISABLE);
+
jump_label_unlock();
}
+static void jump_label_update_timeout(struct work_struct *work)
+{
+ struct jump_label_key_deferred *key =
+ container_of(work, struct jump_label_key_deferred, work.work);
+ __jump_label_dec(&key->key, 0, NULL);
+}
+
+void jump_label_dec(struct jump_label_key *key)
+{
+ __jump_label_dec(key, 0, NULL);
+}
+
+void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+{
+ __jump_label_dec(&key->key, key->timeout, &key->work);
+}
+
+
+void jump_label_rate_limit(struct jump_label_key_deferred *key,
+ unsigned long rl)
+{
+ key->timeout = rl;
+ INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
+}
+
static int addr_conflict(struct jump_entry *entry, void *start, void *end)
{
if (entry->code <= (unsigned long)end &&
@@ -111,7 +142,7 @@
* running code can override this to make the non-live update case
* cheaper.
*/
-void __weak arch_jump_label_transform_static(struct jump_entry *entry,
+void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type)
{
arch_jump_label_transform(entry, type);
@@ -217,8 +248,13 @@
if (iter_start == iter_stop)
return;
- for (iter = iter_start; iter < iter_stop; iter++)
- arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE);
+ for (iter = iter_start; iter < iter_stop; iter++) {
+ struct jump_label_key *iterk;
+
+ iterk = (struct jump_label_key *)(unsigned long)iter->key;
+ arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
+ JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
+ }
}
static int jump_label_add_module(struct module *mod)
@@ -258,8 +294,7 @@
key->next = jlm;
if (jump_label_enabled(key))
- __jump_label_update(key, iter, iter_stop,
- JUMP_LABEL_ENABLE);
+ __jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE);
}
return 0;
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index b2e08c9..24f176c 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -499,36 +499,32 @@
usage[i] = '\0';
}
-static int __print_lock_name(struct lock_class *class)
+static void __print_lock_name(struct lock_class *class)
{
char str[KSYM_NAME_LEN];
const char *name;
name = class->name;
- if (!name)
- name = __get_key_name(class->key, str);
-
- return printk("%s", name);
-}
-
-static void print_lock_name(struct lock_class *class)
-{
- char str[KSYM_NAME_LEN], usage[LOCK_USAGE_CHARS];
- const char *name;
-
- get_usage_chars(class, usage);
-
- name = class->name;
if (!name) {
name = __get_key_name(class->key, str);
- printk(" (%s", name);
+ printk("%s", name);
} else {
- printk(" (%s", name);
+ printk("%s", name);
if (class->name_version > 1)
printk("#%d", class->name_version);
if (class->subclass)
printk("/%d", class->subclass);
}
+}
+
+static void print_lock_name(struct lock_class *class)
+{
+ char usage[LOCK_USAGE_CHARS];
+
+ get_usage_chars(class, usage);
+
+ printk(" (");
+ __print_lock_name(class);
printk("){%s}", usage);
}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f2bd275..7392070 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -338,7 +338,8 @@
/* trace_flags holds trace_options default values */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
- TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
+ TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE |
+ TRACE_ITER_IRQ_INFO;
static int trace_stop_count;
static DEFINE_RAW_SPINLOCK(tracing_start_lock);
@@ -426,6 +427,7 @@
"record-cmd",
"overwrite",
"disable_on_free",
+ "irq-info",
NULL
};
@@ -1843,6 +1845,33 @@
trace_event_read_unlock();
}
+static void
+get_total_entries(struct trace_array *tr, unsigned long *total, unsigned long *entries)
+{
+ unsigned long count;
+ int cpu;
+
+ *total = 0;
+ *entries = 0;
+
+ for_each_tracing_cpu(cpu) {
+ count = ring_buffer_entries_cpu(tr->buffer, cpu);
+ /*
+ * If this buffer has skipped entries, then we hold all
+ * entries for the trace and we need to ignore the
+ * ones before the time stamp.
+ */
+ if (tr->data[cpu]->skipped_entries) {
+ count -= tr->data[cpu]->skipped_entries;
+ /* total is the same as the entries */
+ *total += count;
+ } else
+ *total += count +
+ ring_buffer_overrun_cpu(tr->buffer, cpu);
+ *entries += count;
+ }
+}
+
static void print_lat_help_header(struct seq_file *m)
{
seq_puts(m, "# _------=> CPU# \n");
@@ -1855,12 +1884,35 @@
seq_puts(m, "# \\ / ||||| \\ | / \n");
}
-static void print_func_help_header(struct seq_file *m)
+static void print_event_info(struct trace_array *tr, struct seq_file *m)
{
- seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n");
+ unsigned long total;
+ unsigned long entries;
+
+ get_total_entries(tr, &total, &entries);
+ seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n",
+ entries, total, num_online_cpus());
+ seq_puts(m, "#\n");
+}
+
+static void print_func_help_header(struct trace_array *tr, struct seq_file *m)
+{
+ print_event_info(tr, m);
+ seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n");
seq_puts(m, "# | | | | |\n");
}
+static void print_func_help_header_irq(struct trace_array *tr, struct seq_file *m)
+{
+ print_event_info(tr, m);
+ seq_puts(m, "# _-----=> irqs-off\n");
+ seq_puts(m, "# / _----=> need-resched\n");
+ seq_puts(m, "# | / _---=> hardirq/softirq\n");
+ seq_puts(m, "# || / _--=> preempt-depth\n");
+ seq_puts(m, "# ||| / delay\n");
+ seq_puts(m, "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n");
+ seq_puts(m, "# | | | |||| | |\n");
+}
void
print_trace_header(struct seq_file *m, struct trace_iterator *iter)
@@ -1869,32 +1921,14 @@
struct trace_array *tr = iter->tr;
struct trace_array_cpu *data = tr->data[tr->cpu];
struct tracer *type = current_trace;
- unsigned long entries = 0;
- unsigned long total = 0;
- unsigned long count;
+ unsigned long entries;
+ unsigned long total;
const char *name = "preemption";
- int cpu;
if (type)
name = type->name;
-
- for_each_tracing_cpu(cpu) {
- count = ring_buffer_entries_cpu(tr->buffer, cpu);
- /*
- * If this buffer has skipped entries, then we hold all
- * entries for the trace and we need to ignore the
- * ones before the time stamp.
- */
- if (tr->data[cpu]->skipped_entries) {
- count -= tr->data[cpu]->skipped_entries;
- /* total is the same as the entries */
- total += count;
- } else
- total += count +
- ring_buffer_overrun_cpu(tr->buffer, cpu);
- entries += count;
- }
+ get_total_entries(tr, &total, &entries);
seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
name, UTS_RELEASE);
@@ -2140,6 +2174,21 @@
return print_trace_fmt(iter);
}
+void trace_latency_header(struct seq_file *m)
+{
+ struct trace_iterator *iter = m->private;
+
+ /* print nothing if the buffers are empty */
+ if (trace_empty(iter))
+ return;
+
+ if (iter->iter_flags & TRACE_FILE_LAT_FMT)
+ print_trace_header(m, iter);
+
+ if (!(trace_flags & TRACE_ITER_VERBOSE))
+ print_lat_help_header(m);
+}
+
void trace_default_header(struct seq_file *m)
{
struct trace_iterator *iter = m->private;
@@ -2155,8 +2204,12 @@
if (!(trace_flags & TRACE_ITER_VERBOSE))
print_lat_help_header(m);
} else {
- if (!(trace_flags & TRACE_ITER_VERBOSE))
- print_func_help_header(m);
+ if (!(trace_flags & TRACE_ITER_VERBOSE)) {
+ if (trace_flags & TRACE_ITER_IRQ_INFO)
+ print_func_help_header_irq(iter->tr, m);
+ else
+ print_func_help_header(iter->tr, m);
+ }
}
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 092e1f8..2c26574 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -370,6 +370,7 @@
unsigned long ip,
unsigned long parent_ip,
unsigned long flags, int pc);
+void trace_latency_header(struct seq_file *m);
void trace_default_header(struct seq_file *m);
void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
int trace_empty(struct trace_iterator *iter);
@@ -654,6 +655,7 @@
TRACE_ITER_RECORD_CMD = 0x100000,
TRACE_ITER_OVERWRITE = 0x200000,
TRACE_ITER_STOP_ON_FREE = 0x400000,
+ TRACE_ITER_IRQ_INFO = 0x800000,
};
/*
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 95dc31e..f04cc31 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -27,6 +27,12 @@
#include "trace.h"
#include "trace_output.h"
+#define DEFAULT_SYS_FILTER_MESSAGE \
+ "### global filter ###\n" \
+ "# Use this to set filters for multiple events.\n" \
+ "# Only events with the given fields will be affected.\n" \
+ "# If no events are modified, an error message will be displayed here"
+
enum filter_op_ids
{
OP_OR,
@@ -646,7 +652,7 @@
if (filter && filter->filter_string)
trace_seq_printf(s, "%s\n", filter->filter_string);
else
- trace_seq_printf(s, "none\n");
+ trace_seq_printf(s, DEFAULT_SYS_FILTER_MESSAGE "\n");
mutex_unlock(&event_mutex);
}
@@ -1838,7 +1844,10 @@
if (!filter)
goto out;
- replace_filter_string(filter, filter_string);
+ /* System filters just show a default message */
+ kfree(filter->filter_string);
+ filter->filter_string = NULL;
+
/*
* No event actually uses the system filter
* we can free it without synchronize_sched().
@@ -1848,14 +1857,12 @@
parse_init(ps, filter_ops, filter_string);
err = filter_parse(ps);
- if (err) {
- append_filter_err(ps, system->filter);
- goto out;
- }
+ if (err)
+ goto err_filter;
err = replace_system_preds(system, ps, filter_string);
if (err)
- append_filter_err(ps, system->filter);
+ goto err_filter;
out:
filter_opstack_clear(ps);
@@ -1865,6 +1872,11 @@
mutex_unlock(&event_mutex);
return err;
+
+err_filter:
+ replace_filter_string(filter, filter_string);
+ append_filter_err(ps, system->filter);
+ goto out;
}
#ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 20dad0d..99d20e9 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -280,9 +280,20 @@
}
static void irqsoff_graph_return(struct ftrace_graph_ret *trace) { }
-static void irqsoff_print_header(struct seq_file *s) { }
static void irqsoff_trace_open(struct trace_iterator *iter) { }
static void irqsoff_trace_close(struct trace_iterator *iter) { }
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void irqsoff_print_header(struct seq_file *s)
+{
+ trace_default_header(s);
+}
+#else
+static void irqsoff_print_header(struct seq_file *s)
+{
+ trace_latency_header(s);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
/*
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 5199930..0d6ff35 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -627,11 +627,23 @@
unsigned long usec_rem = do_div(t, USEC_PER_SEC);
unsigned long secs = (unsigned long)t;
char comm[TASK_COMM_LEN];
+ int ret;
trace_find_cmdline(entry->pid, comm);
- return trace_seq_printf(s, "%16s-%-5d [%03d] %5lu.%06lu: ",
- comm, entry->pid, iter->cpu, secs, usec_rem);
+ ret = trace_seq_printf(s, "%16s-%-5d [%03d] ",
+ comm, entry->pid, iter->cpu);
+ if (!ret)
+ return 0;
+
+ if (trace_flags & TRACE_ITER_IRQ_INFO) {
+ ret = trace_print_lat_fmt(s, entry);
+ if (!ret)
+ return 0;
+ }
+
+ return trace_seq_printf(s, " %5lu.%06lu: ",
+ secs, usec_rem);
}
int trace_print_lat_context(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index e4a70c0..ff791ea 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -280,9 +280,20 @@
}
static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
-static void wakeup_print_header(struct seq_file *s) { }
static void wakeup_trace_open(struct trace_iterator *iter) { }
static void wakeup_trace_close(struct trace_iterator *iter) { }
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void wakeup_print_header(struct seq_file *s)
+{
+ trace_default_header(s);
+}
+#else
+static void wakeup_print_header(struct seq_file *s)
+{
+ trace_latency_header(s);
+}
+#endif /* CONFIG_FUNCTION_TRACER */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
/*
diff --git a/mm/filemap.c b/mm/filemap.c
index c0018f2..c106d3b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2407,7 +2407,6 @@
iov_iter_count(i));
again:
-
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
@@ -2463,7 +2462,10 @@
written += copied;
balance_dirty_pages_ratelimited(mapping);
-
+ if (fatal_signal_pending(current)) {
+ status = -EINTR;
+ break;
+ }
} while (iov_iter_count(i));
return written ? written : status;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7125248..50f0824 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -411,8 +411,13 @@
*
* Returns @bdi's dirty limit in pages. The term "dirty" in the context of
* dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
- * And the "limit" in the name is not seriously taken as hard limit in
- * balance_dirty_pages().
+ *
+ * Note that balance_dirty_pages() will only seriously take it as a hard limit
+ * when sleeping max_pause per page is not enough to keep the dirty pages under
+ * control. For example, when the device is completely stalled due to some error
+ * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
+ * In the other normal situations, it acts more gently by throttling the tasks
+ * more (rather than completely block them) when the bdi dirty pages go high.
*
* It allocates high/low dirty limits to fast/slow devices, in order to prevent
* - starving fast devices
@@ -594,6 +599,13 @@
*/
if (unlikely(bdi_thresh > thresh))
bdi_thresh = thresh;
+ /*
+ * It's very possible that bdi_thresh is close to 0 not because the
+ * device is slow, but that it has remained inactive for long time.
+ * Honour such devices a reasonable good (hopefully IO efficient)
+ * threshold, so that the occasional writes won't be blocked and active
+ * writes can rampup the threshold quickly.
+ */
bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
/*
* scale global setpoint to bdi's:
@@ -977,8 +989,7 @@
*
* 8 serves as the safety ratio.
*/
- if (bdi_dirty)
- t = min(t, bdi_dirty * HZ / (8 * bw + 1));
+ t = min(t, bdi_dirty * HZ / (8 * bw + 1));
/*
* The pause time will be settled within range (max_pause/4, max_pause).
@@ -1136,6 +1147,19 @@
if (task_ratelimit)
break;
+ /*
+ * In the case of an unresponding NFS server and the NFS dirty
+ * pages exceeds dirty_thresh, give the other good bdi's a pipe
+ * to go through, so that tasks on them still remain responsive.
+ *
+ * In theory 1 page is enough to keep the comsumer-producer
+ * pipe going: the flusher cleans 1 page => the task dirties 1
+ * more page. However bdi_dirty has accounting errors. So use
+ * the larger and more IO friendly bdi_stat_error.
+ */
+ if (bdi_dirty <= bdi_stat_error(bdi))
+ break;
+
if (fatal_signal_pending(current))
break;
}
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index c7aafc7..5f09a57 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -245,9 +245,11 @@
if (tt_global_entry) {
/* This node is probably going to update its tt table */
tt_global_entry->orig_node->tt_poss_change = true;
- /* The global entry has to be marked as PENDING and has to be
+ /* The global entry has to be marked as ROAMING and has to be
* kept for consistency purpose */
- tt_global_entry->flags |= TT_CLIENT_PENDING;
+ tt_global_entry->flags |= TT_CLIENT_ROAM;
+ tt_global_entry->roam_at = jiffies;
+
send_roam_adv(bat_priv, tt_global_entry->addr,
tt_global_entry->orig_node);
}
@@ -694,6 +696,7 @@
const char *message, bool roaming)
{
struct tt_global_entry *tt_global_entry = NULL;
+ struct tt_local_entry *tt_local_entry = NULL;
tt_global_entry = tt_global_hash_find(bat_priv, addr);
if (!tt_global_entry)
@@ -701,15 +704,29 @@
if (tt_global_entry->orig_node == orig_node) {
if (roaming) {
- tt_global_entry->flags |= TT_CLIENT_ROAM;
- tt_global_entry->roam_at = jiffies;
- goto out;
+ /* if we are deleting a global entry due to a roam
+ * event, there are two possibilities:
+ * 1) the client roamed from node A to node B => we mark
+ * it with TT_CLIENT_ROAM, we start a timer and we
+ * wait for node B to claim it. In case of timeout
+ * the entry is purged.
+ * 2) the client roamed to us => we can directly delete
+ * the global entry, since it is useless now. */
+ tt_local_entry = tt_local_hash_find(bat_priv,
+ tt_global_entry->addr);
+ if (!tt_local_entry) {
+ tt_global_entry->flags |= TT_CLIENT_ROAM;
+ tt_global_entry->roam_at = jiffies;
+ goto out;
+ }
}
_tt_global_del(bat_priv, tt_global_entry, message);
}
out:
if (tt_global_entry)
tt_global_entry_free_ref(tt_global_entry);
+ if (tt_local_entry)
+ tt_local_entry_free_ref(tt_local_entry);
}
void tt_global_del_orig(struct bat_priv *bat_priv,
diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c
index 91bcd3a..1eea820 100644
--- a/net/bluetooth/bnep/core.c
+++ b/net/bluetooth/bnep/core.c
@@ -79,17 +79,12 @@
static void __bnep_link_session(struct bnep_session *s)
{
- /* It's safe to call __module_get() here because sessions are added
- by the socket layer which has to hold the reference to this module.
- */
- __module_get(THIS_MODULE);
list_add(&s->list, &bnep_session_list);
}
static void __bnep_unlink_session(struct bnep_session *s)
{
list_del(&s->list);
- module_put(THIS_MODULE);
}
static int bnep_send(struct bnep_session *s, void *data, size_t len)
@@ -530,6 +525,7 @@
up_write(&bnep_session_sem);
free_netdev(dev);
+ module_put_and_exit(0);
return 0;
}
@@ -616,9 +612,11 @@
__bnep_link_session(s);
+ __module_get(THIS_MODULE);
s->task = kthread_run(bnep_session, s, "kbnepd %s", dev->name);
if (IS_ERR(s->task)) {
/* Session thread start failed, gotta cleanup. */
+ module_put(THIS_MODULE);
unregister_netdev(dev);
__bnep_unlink_session(s);
err = PTR_ERR(s->task);
diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c
index 7d00ddf..5a6e634 100644
--- a/net/bluetooth/cmtp/core.c
+++ b/net/bluetooth/cmtp/core.c
@@ -67,14 +67,12 @@
static void __cmtp_link_session(struct cmtp_session *session)
{
- __module_get(THIS_MODULE);
list_add(&session->list, &cmtp_session_list);
}
static void __cmtp_unlink_session(struct cmtp_session *session)
{
list_del(&session->list);
- module_put(THIS_MODULE);
}
static void __cmtp_copy_session(struct cmtp_session *session, struct cmtp_conninfo *ci)
@@ -327,6 +325,7 @@
up_write(&cmtp_session_sem);
kfree(session);
+ module_put_and_exit(0);
return 0;
}
@@ -376,9 +375,11 @@
__cmtp_link_session(session);
+ __module_get(THIS_MODULE);
session->task = kthread_run(cmtp_session, session, "kcmtpd_ctr_%d",
session->num);
if (IS_ERR(session->task)) {
+ module_put(THIS_MODULE);
err = PTR_ERR(session->task);
goto unlink;
}
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d7d96b6..643a41b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -545,7 +545,7 @@
{
hci_setup_event_mask(hdev);
- if (hdev->lmp_ver > 1)
+ if (hdev->hci_ver > 1)
hci_send_cmd(hdev, HCI_OP_READ_LOCAL_COMMANDS, 0, NULL);
if (hdev->features[6] & LMP_SIMPLE_PAIR) {
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 42599e3..3a94eae 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -477,7 +477,6 @@
int i, j;
int numrep;
int firstn;
- int rc = -1;
BUG_ON(ruleno >= map->max_rules);
@@ -491,23 +490,18 @@
* that this may or may not correspond to the specific types
* referenced by the crush rule.
*/
- if (force >= 0) {
- if (force >= map->max_devices ||
- map->device_parents[force] == 0) {
- /*dprintk("CRUSH: forcefed device dne\n");*/
- rc = -1; /* force fed device dne */
- goto out;
- }
- if (!is_out(map, weight, force, x)) {
- while (1) {
- force_context[++force_pos] = force;
- if (force >= 0)
- force = map->device_parents[force];
- else
- force = map->bucket_parents[-1-force];
- if (force == 0)
- break;
- }
+ if (force >= 0 &&
+ force < map->max_devices &&
+ map->device_parents[force] != 0 &&
+ !is_out(map, weight, force, x)) {
+ while (1) {
+ force_context[++force_pos] = force;
+ if (force >= 0)
+ force = map->device_parents[force];
+ else
+ force = map->bucket_parents[-1-force];
+ if (force == 0)
+ break;
}
}
@@ -600,10 +594,7 @@
BUG_ON(1);
}
}
- rc = result_len;
-
-out:
- return rc;
+ return result_len;
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 065effd..0b2e732 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -285,6 +285,8 @@
if (register_netdevice(dev) < 0)
goto failed_free;
+ strcpy(nt->parms.name, dev->name);
+
dev_hold(dev);
ipip_tunnel_link(ipn, nt);
return nt;
@@ -759,7 +761,6 @@
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
@@ -825,6 +826,7 @@
static int __net_init ipip_init_net(struct net *net)
{
struct ipip_net *ipn = net_generic(net, ipip_net_id);
+ struct ip_tunnel *t;
int err;
ipn->tunnels[0] = ipn->tunnels_wc;
@@ -848,6 +850,9 @@
if ((err = register_netdev(ipn->fb_tunnel_dev)))
goto err_reg_dev;
+ t = netdev_priv(ipn->fb_tunnel_dev);
+
+ strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cf88df8..36806de 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1805,7 +1805,8 @@
return ERR_PTR(-EACCES);
/* Add default multicast route */
- addrconf_add_mroute(dev);
+ if (!(dev->flags & IFF_LOOPBACK))
+ addrconf_add_mroute(dev);
/* Add link local route */
addrconf_add_lroute(dev);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 3399dd3..b582a0a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -728,7 +728,7 @@
int attempts = !in_softirq();
if (!(rt->rt6i_flags&RTF_GATEWAY)) {
- if (rt->rt6i_dst.plen != 128 &&
+ if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
ipv6_addr_copy(&rt->rt6i_gateway, daddr);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a7a1860..96f3623 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -263,6 +263,8 @@
if (register_netdevice(dev) < 0)
goto failed_free;
+ strcpy(nt->parms.name, dev->name);
+
dev_hold(dev);
ipip6_tunnel_link(sitn, nt);
@@ -1144,7 +1146,6 @@
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
@@ -1207,6 +1208,7 @@
static int __net_init sit_init_net(struct net *net)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
+ struct ip_tunnel *t;
int err;
sitn->tunnels[0] = sitn->tunnels_wc;
@@ -1231,6 +1233,9 @@
if ((err = register_netdev(sitn->fb_tunnel_dev)))
goto err_reg_dev;
+ t = netdev_priv(sitn->fb_tunnel_dev);
+
+ strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index b064e4d..2e4b961 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -303,6 +303,38 @@
__release(agg_queue);
}
+/*
+ * splice packets from the STA's pending to the local pending,
+ * requires a call to ieee80211_agg_splice_finish later
+ */
+static void __acquires(agg_queue)
+ieee80211_agg_splice_packets(struct ieee80211_local *local,
+ struct tid_ampdu_tx *tid_tx, u16 tid)
+{
+ int queue = ieee80211_ac_from_tid(tid);
+ unsigned long flags;
+
+ ieee80211_stop_queue_agg(local, tid);
+
+ if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates"
+ " from the pending queue\n", tid))
+ return;
+
+ if (!skb_queue_empty(&tid_tx->pending)) {
+ spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
+ /* copy over remaining packets */
+ skb_queue_splice_tail_init(&tid_tx->pending,
+ &local->pending[queue]);
+ spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+ }
+}
+
+static void __releases(agg_queue)
+ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid)
+{
+ ieee80211_wake_queue_agg(local, tid);
+}
+
void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
{
struct tid_ampdu_tx *tid_tx;
@@ -314,19 +346,17 @@
tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
/*
- * While we're asking the driver about the aggregation,
- * stop the AC queue so that we don't have to worry
- * about frames that came in while we were doing that,
- * which would require us to put them to the AC pending
- * afterwards which just makes the code more complex.
+ * Start queuing up packets for this aggregation session.
+ * We're going to release them once the driver is OK with
+ * that.
*/
- ieee80211_stop_queue_agg(local, tid);
-
clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state);
/*
- * make sure no packets are being processed to get
- * valid starting sequence number
+ * Make sure no packets are being processed. This ensures that
+ * we have a valid starting sequence number and that in-flight
+ * packets have been flushed out and no packets for this TID
+ * will go into the driver during the ampdu_action call.
*/
synchronize_net();
@@ -340,17 +370,15 @@
" tid %d\n", tid);
#endif
spin_lock_bh(&sta->lock);
+ ieee80211_agg_splice_packets(local, tid_tx, tid);
ieee80211_assign_tid_tx(sta, tid, NULL);
+ ieee80211_agg_splice_finish(local, tid);
spin_unlock_bh(&sta->lock);
- ieee80211_wake_queue_agg(local, tid);
kfree_rcu(tid_tx, rcu_head);
return;
}
- /* we can take packets again now */
- ieee80211_wake_queue_agg(local, tid);
-
/* activate the timer for the recipient's addBA response */
mod_timer(&tid_tx->addba_resp_timer, jiffies + ADDBA_RESP_INTERVAL);
#ifdef CONFIG_MAC80211_HT_DEBUG
@@ -466,38 +494,6 @@
}
EXPORT_SYMBOL(ieee80211_start_tx_ba_session);
-/*
- * splice packets from the STA's pending to the local pending,
- * requires a call to ieee80211_agg_splice_finish later
- */
-static void __acquires(agg_queue)
-ieee80211_agg_splice_packets(struct ieee80211_local *local,
- struct tid_ampdu_tx *tid_tx, u16 tid)
-{
- int queue = ieee80211_ac_from_tid(tid);
- unsigned long flags;
-
- ieee80211_stop_queue_agg(local, tid);
-
- if (WARN(!tid_tx, "TID %d gone but expected when splicing aggregates"
- " from the pending queue\n", tid))
- return;
-
- if (!skb_queue_empty(&tid_tx->pending)) {
- spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
- /* copy over remaining packets */
- skb_queue_splice_tail_init(&tid_tx->pending,
- &local->pending[queue]);
- spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
- }
-}
-
-static void __releases(agg_queue)
-ieee80211_agg_splice_finish(struct ieee80211_local *local, u16 tid)
-{
- ieee80211_wake_queue_agg(local, tid);
-}
-
static void ieee80211_agg_tx_operational(struct ieee80211_local *local,
struct sta_info *sta, u16 tid)
{
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index b9493a0..6cd8ddf 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -385,7 +385,7 @@
struct gred_sched_data *q;
if (table->tab[dp] == NULL) {
- table->tab[dp] = kzalloc(sizeof(*q), GFP_KERNEL);
+ table->tab[dp] = kzalloc(sizeof(*q), GFP_ATOMIC);
if (table->tab[dp] == NULL)
return -ENOMEM;
}
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 7d98240..c2f79e6 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2507,6 +2507,7 @@
SND_PCI_QUIRK(0x1043, 0x813d, "ASUS P5AD2", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB),
+ SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS 1101HA", POS_FIX_LPIB),
SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1297, 0x3166, "Shuttle", POS_FIX_LPIB),
SND_PCI_QUIRK(0x1458, 0xa022, "ga-ma770-ud3", POS_FIX_LPIB),
@@ -2970,7 +2971,8 @@
/* SCH */
{ PCI_DEVICE(0x8086, 0x811b),
.driver_data = AZX_DRIVER_SCH | AZX_DCAPS_SCH_SNOOP |
- AZX_DCAPS_BUFSIZE},
+ AZX_DCAPS_BUFSIZE | AZX_DCAPS_POSFIX_LPIB }, /* Poulsbo */
+ /* ICH */
{ PCI_DEVICE(0x8086, 0x2668),
.driver_data = AZX_DRIVER_ICH | AZX_DCAPS_OLD_SSYNC |
AZX_DCAPS_BUFSIZE }, /* ICH6 */
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index eeb25d52..616678f 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -4929,6 +4929,12 @@
set_hp_led_gpio(codec);
return 1;
}
+ /* BIOS bug: unfilled OEM string */
+ if (strstr(dev->name, "HP_Mute_LED_P_G")) {
+ set_hp_led_gpio(codec);
+ spec->gpio_led_polarity = 1;
+ return 1;
+ }
}
/*
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 4584514..fa787d4 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -33,7 +33,7 @@
select SND_SOC_CX20442
select SND_SOC_DA7210 if I2C
select SND_SOC_DFBMCS320
- select SND_SOC_JZ4740_CODEC if SOC_JZ4740
+ select SND_SOC_JZ4740_CODEC
select SND_SOC_LM4857 if I2C
select SND_SOC_MAX98088 if I2C
select SND_SOC_MAX98095 if I2C
diff --git a/sound/soc/codecs/jz4740.c b/sound/soc/codecs/jz4740.c
index e373f8f..3e1f4e1 100644
--- a/sound/soc/codecs/jz4740.c
+++ b/sound/soc/codecs/jz4740.c
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/io.h>
#include <linux/delay.h>
diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c
index 0293763..5a14d5c 100644
--- a/sound/soc/codecs/wm8958-dsp2.c
+++ b/sound/soc/codecs/wm8958-dsp2.c
@@ -60,6 +60,8 @@
}
if (memcmp(fw->data, "WMFW", 4) != 0) {
+ memcpy(&data32, fw->data, sizeof(data32));
+ data32 = be32_to_cpu(data32);
dev_err(codec->dev, "%s: firmware has bad file magic %08x\n",
name, data32);
goto err;
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index 645c980..a33b04d 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -1968,6 +1968,7 @@
break;
case 24576000:
ratediv = WM8996_SYSCLK_DIV;
+ wm8996->sysclk /= 2;
case 12288000:
snd_soc_update_bits(codec, WM8996_AIF_RATE,
WM8996_SYSCLK_RATE, WM8996_SYSCLK_RATE);
diff --git a/sound/soc/mxs/mxs-pcm.c b/sound/soc/mxs/mxs-pcm.c
index dea5aa4..f39d7dd 100644
--- a/sound/soc/mxs/mxs-pcm.c
+++ b/sound/soc/mxs/mxs-pcm.c
@@ -357,3 +357,6 @@
platform_driver_unregister(&mxs_pcm_driver);
}
module_exit(snd_mxs_pcm_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mxs-pcm-audio");
diff --git a/sound/soc/mxs/mxs-sgtl5000.c b/sound/soc/mxs/mxs-sgtl5000.c
index 7fbeaec..1c57f66 100644
--- a/sound/soc/mxs/mxs-sgtl5000.c
+++ b/sound/soc/mxs/mxs-sgtl5000.c
@@ -171,3 +171,4 @@
MODULE_AUTHOR("Freescale Semiconductor, Inc.");
MODULE_DESCRIPTION("MXS ALSA SoC Machine driver");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mxs-sgtl5000");
diff --git a/sound/soc/pxa/hx4700.c b/sound/soc/pxa/hx4700.c
index 65c1248..c664e33 100644
--- a/sound/soc/pxa/hx4700.c
+++ b/sound/soc/pxa/hx4700.c
@@ -209,9 +209,10 @@
snd_soc_card_hx4700.dev = &pdev->dev;
ret = snd_soc_register_card(&snd_soc_card_hx4700);
if (ret)
- return ret;
+ gpio_free_array(hx4700_audio_gpios,
+ ARRAY_SIZE(hx4700_audio_gpios));
- return 0;
+ return ret;
}
static int __devexit hx4700_audio_remove(struct platform_device *pdev)
diff --git a/sound/soc/samsung/jive_wm8750.c b/sound/soc/samsung/jive_wm8750.c
index 1826acf..8e523fd 100644
--- a/sound/soc/samsung/jive_wm8750.c
+++ b/sound/soc/samsung/jive_wm8750.c
@@ -101,7 +101,6 @@
{
struct snd_soc_codec *codec = rtd->codec;
struct snd_soc_dapm_context *dapm = &codec->dapm;
- int err;
/* These endpoints are not being used. */
snd_soc_dapm_nc_pin(dapm, "LINPUT2");
@@ -131,7 +130,7 @@
.dai_link = &jive_dai,
.num_links = 1,
- .dapm_widgtets = wm8750_dapm_widgets,
+ .dapm_widgets = wm8750_dapm_widgets,
.num_dapm_widgets = ARRAY_SIZE(wm8750_dapm_widgets),
.dapm_routes = audio_map,
.num_dapm_routes = ARRAY_SIZE(audio_map),
diff --git a/sound/soc/samsung/smdk2443_wm9710.c b/sound/soc/samsung/smdk2443_wm9710.c
index 3a0dbfc..8bd1dc5 100644
--- a/sound/soc/samsung/smdk2443_wm9710.c
+++ b/sound/soc/samsung/smdk2443_wm9710.c
@@ -12,6 +12,7 @@
*
*/
+#include <linux/module.h>
#include <sound/soc.h>
static struct snd_soc_card smdk2443;
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index fe6762e..c89f9e1 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -22,7 +22,7 @@
-------
-i::
--input=::
- Input file name. (default: perf.data)
+ Input file name. (default: perf.data unless stdin is a fifo)
-d::
--dsos=<dso[,dso...]>::
@@ -66,7 +66,7 @@
used. This interfaces starts by centering on the line with more
samples, TAB/UNTAB cycles through the lines with more samples.
--c::
+-C::
--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
be provided as a comma-separated list with no space: 0,1. Ranges of
CPUs are specified with -: 0-2. Default is to report samples on all
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index cc22325..25c52ef 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -26,7 +26,7 @@
Show only DSOs with hits.
-i::
--input=::
- Input file name. (default: perf.data)
+ Input file name. (default: perf.data unless stdin is a fifo)
-f::
--force::
Don't do ownership validation.
diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt
index 0cada9e..0507ec7 100644
--- a/tools/perf/Documentation/perf-evlist.txt
+++ b/tools/perf/Documentation/perf-evlist.txt
@@ -18,7 +18,7 @@
-------
-i::
--input=::
- Input file name. (default: perf.data)
+ Input file name. (default: perf.data unless stdin is a fifo)
SEE ALSO
--------
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index a52fcde..7c8fbbf 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -23,7 +23,7 @@
-------
-i <file>::
--input=<file>::
- Select the input file (default: perf.data)
+ Select the input file (default: perf.data unless stdin is a fifo)
--caller::
Show per-callsite statistics
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index 4a26a2f..d6b2a4f 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -29,7 +29,7 @@
-i::
--input=<file>::
- Input file name.
+ Input file name. (default: perf.data unless stdin is a fifo)
-v::
--verbose::
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5a520f8..2937f7e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -89,7 +89,7 @@
-m::
--mmap-pages=::
- Number of mmap data pages.
+ Number of mmap data pages. Must be a power of two.
-g::
--call-graph::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 212f24d..9b430e9 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -19,7 +19,7 @@
-------
-i::
--input=::
- Input file name. (default: perf.data)
+ Input file name. (default: perf.data unless stdin is a fifo)
-v::
--verbose::
@@ -39,7 +39,7 @@
-T::
--threads::
Show per-thread event counters
--C::
+-c::
--comms=::
Only consider symbols in these comms. CSV that understands
file://filename entries.
@@ -80,9 +80,10 @@
--dump-raw-trace::
Dump raw trace in ASCII.
--g [type,min,order]::
+-g [type,min[,limit],order]::
--call-graph::
- Display call chains using type, min percent threshold and order.
+ Display call chains using type, min percent threshold, optional print
+ limit and order.
type can be either:
- flat: single column, linear exposure of call chains.
- graph: use a graph tree, displaying absolute overhead rates.
@@ -128,7 +129,7 @@
--symfs=<directory>::
Look for files with symbols relative to this directory.
--c::
+-C::
--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
be provided as a comma-separated list with no space: 0,1. Ranges of
CPUs are specified with -: 0-2. Default is to report samples on all
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 5b212b5..8ff4df9 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -40,7 +40,7 @@
-------
-i::
--input=<file>::
- Input file name. (default: perf.data)
+ Input file name. (default: perf.data unless stdin is a fifo)
-v::
--verbose::
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index dec87ec..2f6cef4 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -106,7 +106,7 @@
-i::
--input=::
- Input file name.
+ Input file name. (default: perf.data unless stdin is a fifo)
-d::
--debug-mode::
@@ -182,12 +182,17 @@
--hide-call-graph::
When printing symbols do not display call chain.
--c::
+-C::
--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
be provided as a comma-separated list with no space: 0,1. Ranges of
CPUs are specified with -: 0-2. Default is to report samples on all
CPUs.
+-c::
+--comms=::
+ Only display events for these comms. CSV that understands
+ file://filename entries.
+
-I::
--show-info::
Display extended information about the perf.data file. This adds
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 2c3b462..b24ac40 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -8,13 +8,19 @@
SYNOPSIS
--------
[verse]
-'perf test <options>'
+'perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]'
DESCRIPTION
-----------
This command does assorted sanity tests, initially through linked routines but
also will look for a directory with more tests in the form of scripts.
+To get a list of available tests use 'perf test list', specifying a test name
+fragment will show all tests that have it.
+
+To run just specific tests, inform test name fragments or the numbers obtained
+from 'perf test list'.
+
OPTIONS
-------
-v::
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index d7b79e2..1632b0e 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -27,7 +27,7 @@
Select the output file (default: output.svg)
-i::
--input=::
- Select the input file (default: perf.data)
+ Select the input file (default: perf.data unless stdin is a fifo)
-w::
--width=::
Select the width of the SVG file (default: 1000)
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index b98e307..ac86d67 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -278,6 +278,7 @@
LIB_H += util/strlist.h
LIB_H += util/strfilter.h
LIB_H += util/svghelper.h
+LIB_H += util/tool.h
LIB_H += util/run-command.h
LIB_H += util/sigchain.h
LIB_H += util/symbol.h
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 46b4c24..214ba7f 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -27,32 +27,32 @@
#include "util/sort.h"
#include "util/hist.h"
#include "util/session.h"
+#include "util/tool.h"
#include <linux/bitmap.h>
-static char const *input_name = "perf.data";
+struct perf_annotate {
+ struct perf_tool tool;
+ char const *input_name;
+ bool force, use_tui, use_stdio;
+ bool full_paths;
+ bool print_line;
+ const char *sym_hist_filter;
+ const char *cpu_list;
+ DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
-static bool force, use_tui, use_stdio;
-
-static bool full_paths;
-
-static bool print_line;
-
-static const char *sym_hist_filter;
-
-static const char *cpu_list;
-static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
-
-static int perf_evlist__add_sample(struct perf_evlist *evlist,
- struct perf_sample *sample,
- struct perf_evsel *evsel,
- struct addr_location *al)
+static int perf_evsel__add_sample(struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ struct addr_location *al,
+ struct perf_annotate *ann)
{
struct hist_entry *he;
int ret;
- if (sym_hist_filter != NULL &&
- (al->sym == NULL || strcmp(sym_hist_filter, al->sym->name) != 0)) {
+ if (ann->sym_hist_filter != NULL &&
+ (al->sym == NULL ||
+ strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
/* We're only interested in a symbol named sym_hist_filter */
if (al->sym != NULL) {
rb_erase(&al->sym->rb_node,
@@ -69,8 +69,7 @@
ret = 0;
if (he->ms.sym != NULL) {
struct annotation *notes = symbol__annotation(he->ms.sym);
- if (notes->src == NULL &&
- symbol__alloc_hist(he->ms.sym, evlist->nr_entries) < 0)
+ if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
return -ENOMEM;
ret = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
@@ -81,25 +80,26 @@
return ret;
}
-static int process_sample_event(union perf_event *event,
+static int process_sample_event(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
- struct perf_session *session)
+ struct machine *machine)
{
+ struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
struct addr_location al;
- if (perf_event__preprocess_sample(event, session, &al, sample,
+ if (perf_event__preprocess_sample(event, machine, &al, sample,
symbol__annotate_init) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
- if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+ if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
return 0;
- if (!al.filtered &&
- perf_evlist__add_sample(session->evlist, sample, evsel, &al)) {
+ if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
pr_warning("problem incrementing symbol count, "
"skipping event\n");
return -1;
@@ -108,14 +108,15 @@
return 0;
}
-static int hist_entry__tty_annotate(struct hist_entry *he, int evidx)
+static int hist_entry__tty_annotate(struct hist_entry *he, int evidx,
+ struct perf_annotate *ann)
{
return symbol__tty_annotate(he->ms.sym, he->ms.map, evidx,
- print_line, full_paths, 0, 0);
+ ann->print_line, ann->full_paths, 0, 0);
}
static void hists__find_annotations(struct hists *self, int evidx,
- int nr_events)
+ struct perf_annotate *ann)
{
struct rb_node *nd = rb_first(&self->entries), *next;
int key = K_RIGHT;
@@ -138,8 +139,7 @@
}
if (use_browser > 0) {
- key = hist_entry__tui_annotate(he, evidx, nr_events,
- NULL, NULL, 0);
+ key = hist_entry__tui_annotate(he, evidx, NULL, NULL, 0);
switch (key) {
case K_RIGHT:
next = rb_next(nd);
@@ -154,7 +154,7 @@
if (next != NULL)
nd = next;
} else {
- hist_entry__tty_annotate(he, evidx);
+ hist_entry__tty_annotate(he, evidx, ann);
nd = rb_next(nd);
/*
* Since we have a hist_entry per IP for the same
@@ -167,33 +167,26 @@
}
}
-static struct perf_event_ops event_ops = {
- .sample = process_sample_event,
- .mmap = perf_event__process_mmap,
- .comm = perf_event__process_comm,
- .fork = perf_event__process_task,
- .ordered_samples = true,
- .ordering_requires_timestamps = true,
-};
-
-static int __cmd_annotate(void)
+static int __cmd_annotate(struct perf_annotate *ann)
{
int ret;
struct perf_session *session;
struct perf_evsel *pos;
u64 total_nr_samples;
- session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
+ session = perf_session__new(ann->input_name, O_RDONLY,
+ ann->force, false, &ann->tool);
if (session == NULL)
return -ENOMEM;
- if (cpu_list) {
- ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+ if (ann->cpu_list) {
+ ret = perf_session__cpu_bitmap(session, ann->cpu_list,
+ ann->cpu_bitmap);
if (ret)
goto out_delete;
}
- ret = perf_session__process_events(session, &event_ops);
+ ret = perf_session__process_events(session, &ann->tool);
if (ret)
goto out_delete;
@@ -217,13 +210,12 @@
total_nr_samples += nr_samples;
hists__collapse_resort(hists);
hists__output_resort(hists);
- hists__find_annotations(hists, pos->idx,
- session->evlist->nr_entries);
+ hists__find_annotations(hists, pos->idx, ann);
}
}
if (total_nr_samples == 0) {
- ui__warning("The %s file has no samples!\n", input_name);
+ ui__warning("The %s file has no samples!\n", session->filename);
goto out_delete;
}
out_delete:
@@ -247,29 +239,41 @@
NULL
};
-static const struct option options[] = {
- OPT_STRING('i', "input", &input_name, "file",
+int cmd_annotate(int argc, const char **argv, const char *prefix __used)
+{
+ struct perf_annotate annotate = {
+ .tool = {
+ .sample = process_sample_event,
+ .mmap = perf_event__process_mmap,
+ .comm = perf_event__process_comm,
+ .fork = perf_event__process_task,
+ .ordered_samples = true,
+ .ordering_requires_timestamps = true,
+ },
+ };
+ const struct option options[] = {
+ OPT_STRING('i', "input", &annotate.input_name, "file",
"input file name"),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
- OPT_STRING('s', "symbol", &sym_hist_filter, "symbol",
+ OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
"symbol to annotate"),
- OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
- OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
- OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
+ OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"),
+ OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
- OPT_BOOLEAN('l', "print-line", &print_line,
+ OPT_BOOLEAN('l', "print-line", &annotate.print_line,
"print matching source lines (may be slow)"),
- OPT_BOOLEAN('P', "full-paths", &full_paths,
+ OPT_BOOLEAN('P', "full-paths", &annotate.full_paths,
"Don't shorten the displayed pathnames"),
- OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+ OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
@@ -279,15 +283,13 @@
OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
"Specify disassembler style (e.g. -M intel for intel syntax)"),
OPT_END()
-};
+ };
-int cmd_annotate(int argc, const char **argv, const char *prefix __used)
-{
argc = parse_options(argc, argv, options, annotate_usage, 0);
- if (use_stdio)
+ if (annotate.use_stdio)
use_browser = 0;
- else if (use_tui)
+ else if (annotate.use_tui)
use_browser = 1;
setup_browser(true);
@@ -308,7 +310,7 @@
if (argc > 1)
usage_with_options(annotate_usage, options);
- sym_hist_filter = argv[0];
+ annotate.sym_hist_filter = argv[0];
}
if (field_sep && *field_sep == '.') {
@@ -316,5 +318,5 @@
return -1;
}
- return __cmd_annotate();
+ return __cmd_annotate(&annotate);
}
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index cb690a6..5248046 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -18,7 +18,7 @@
#include <libelf.h>
-static char const *input_name = "perf.data";
+static const char *input_name;
static bool force;
static bool show_kernel;
static bool with_hits;
@@ -39,24 +39,6 @@
OPT_END()
};
-static int perf_session__list_build_ids(void)
-{
- struct perf_session *session;
-
- session = perf_session__new(input_name, O_RDONLY, force, false,
- &build_id__mark_dso_hit_ops);
- if (session == NULL)
- return -1;
-
- if (with_hits)
- perf_session__process_events(session, &build_id__mark_dso_hit_ops);
-
- perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
-
- perf_session__delete(session);
- return 0;
-}
-
static int sysfs__fprintf_build_id(FILE *fp)
{
u8 kallsyms_build_id[BUILD_ID_SIZE];
@@ -85,18 +67,37 @@
return fprintf(fp, "%s\n", sbuild_id);
}
+static int perf_session__list_build_ids(void)
+{
+ struct perf_session *session;
+
+ elf_version(EV_CURRENT);
+
+ session = perf_session__new(input_name, O_RDONLY, force, false,
+ &build_id__mark_dso_hit_ops);
+ if (session == NULL)
+ return -1;
+
+ /*
+ * See if this is an ELF file first:
+ */
+ if (filename__fprintf_build_id(session->filename, stdout))
+ goto out;
+
+ if (with_hits)
+ perf_session__process_events(session, &build_id__mark_dso_hit_ops);
+
+ perf_session__fprintf_dsos_buildid(session, stdout, with_hits);
+out:
+ perf_session__delete(session);
+ return 0;
+}
+
static int __cmd_buildid_list(void)
{
if (show_kernel)
return sysfs__fprintf_build_id(stdout);
- elf_version(EV_CURRENT);
- /*
- * See if this is an ELF file first:
- */
- if (filename__fprintf_build_id(input_name, stdout))
- return 0;
-
return perf_session__list_build_ids();
}
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index b39f3a1..4f19513 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -9,7 +9,9 @@
#include "util/debug.h"
#include "util/event.h"
#include "util/hist.h"
+#include "util/evsel.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/sort.h"
#include "util/symbol.h"
#include "util/util.h"
@@ -30,14 +32,15 @@
return -ENOMEM;
}
-static int diff__process_sample_event(union perf_event *event,
+static int diff__process_sample_event(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel __used,
- struct perf_session *session)
+ struct machine *machine)
{
struct addr_location al;
- if (perf_event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
+ if (perf_event__preprocess_sample(event, machine, &al, sample, NULL) < 0) {
pr_warning("problem processing %d event, skipping it.\n",
event->header.type);
return -1;
@@ -46,16 +49,16 @@
if (al.filtered || al.sym == NULL)
return 0;
- if (hists__add_entry(&session->hists, &al, sample->period)) {
+ if (hists__add_entry(&evsel->hists, &al, sample->period)) {
pr_warning("problem incrementing symbol period, skipping event\n");
return -1;
}
- session->hists.stats.total_period += sample->period;
+ evsel->hists.stats.total_period += sample->period;
return 0;
}
-static struct perf_event_ops event_ops = {
+static struct perf_tool perf_diff = {
.sample = diff__process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
@@ -145,13 +148,13 @@
int ret, i;
struct perf_session *session[2];
- session[0] = perf_session__new(input_old, O_RDONLY, force, false, &event_ops);
- session[1] = perf_session__new(input_new, O_RDONLY, force, false, &event_ops);
+ session[0] = perf_session__new(input_old, O_RDONLY, force, false, &perf_diff);
+ session[1] = perf_session__new(input_new, O_RDONLY, force, false, &perf_diff);
if (session[0] == NULL || session[1] == NULL)
return -ENOMEM;
for (i = 0; i < 2; ++i) {
- ret = perf_session__process_events(session[i], &event_ops);
+ ret = perf_session__process_events(session[i], &perf_diff);
if (ret)
goto out_delete;
}
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index 4c5e9e0..2676032 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -15,7 +15,7 @@
#include "util/parse-options.h"
#include "util/session.h"
-static char const *input_name = "perf.data";
+static const char *input_name;
static int __cmd_evlist(void)
{
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8dfc12b..09c1061 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -9,6 +9,7 @@
#include "perf.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/debug.h"
#include "util/parse-options.h"
@@ -16,8 +17,9 @@
static char const *input_name = "-";
static bool inject_build_ids;
-static int perf_event__repipe_synth(union perf_event *event,
- struct perf_session *session __used)
+static int perf_event__repipe_synth(struct perf_tool *tool __used,
+ union perf_event *event,
+ struct machine *machine __used)
{
uint32_t size;
void *buf = event;
@@ -36,41 +38,70 @@
return 0;
}
-static int perf_event__repipe(union perf_event *event,
- struct perf_sample *sample __used,
- struct perf_session *session)
+static int perf_event__repipe_op2_synth(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session __used)
{
- return perf_event__repipe_synth(event, session);
+ return perf_event__repipe_synth(tool, event, NULL);
}
-static int perf_event__repipe_sample(union perf_event *event,
+static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
+ union perf_event *event)
+{
+ return perf_event__repipe_synth(tool, event, NULL);
+}
+
+static int perf_event__repipe_tracing_data_synth(union perf_event *event,
+ struct perf_session *session __used)
+{
+ return perf_event__repipe_synth(NULL, event, NULL);
+}
+
+static int perf_event__repipe_attr(union perf_event *event,
+ struct perf_evlist **pevlist __used)
+{
+ return perf_event__repipe_synth(NULL, event, NULL);
+}
+
+static int perf_event__repipe(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample __used,
+ struct machine *machine)
+{
+ return perf_event__repipe_synth(tool, event, machine);
+}
+
+static int perf_event__repipe_sample(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample __used,
struct perf_evsel *evsel __used,
- struct perf_session *session)
+ struct machine *machine)
{
- return perf_event__repipe_synth(event, session);
+ return perf_event__repipe_synth(tool, event, machine);
}
-static int perf_event__repipe_mmap(union perf_event *event,
+static int perf_event__repipe_mmap(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample,
- struct perf_session *session)
+ struct machine *machine)
{
int err;
- err = perf_event__process_mmap(event, sample, session);
- perf_event__repipe(event, sample, session);
+ err = perf_event__process_mmap(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
return err;
}
-static int perf_event__repipe_task(union perf_event *event,
+static int perf_event__repipe_task(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample,
- struct perf_session *session)
+ struct machine *machine)
{
int err;
- err = perf_event__process_task(event, sample, session);
- perf_event__repipe(event, sample, session);
+ err = perf_event__process_task(tool, event, sample, machine);
+ perf_event__repipe(tool, event, sample, machine);
return err;
}
@@ -80,7 +111,7 @@
{
int err;
- perf_event__repipe_synth(event, session);
+ perf_event__repipe_synth(NULL, event, NULL);
err = perf_event__process_tracing_data(event, session);
return err;
@@ -100,10 +131,10 @@
return -1;
}
-static int dso__inject_build_id(struct dso *self, struct perf_session *session)
+static int dso__inject_build_id(struct dso *self, struct perf_tool *tool,
+ struct machine *machine)
{
u16 misc = PERF_RECORD_MISC_USER;
- struct machine *machine;
int err;
if (dso__read_build_id(self) < 0) {
@@ -111,17 +142,11 @@
return -1;
}
- machine = perf_session__find_host_machine(session);
- if (machine == NULL) {
- pr_err("Can't find machine for session\n");
- return -1;
- }
-
if (self->kernel)
misc = PERF_RECORD_MISC_KERNEL;
- err = perf_event__synthesize_build_id(self, misc, perf_event__repipe,
- machine, session);
+ err = perf_event__synthesize_build_id(tool, self, misc, perf_event__repipe,
+ machine);
if (err) {
pr_err("Can't synthesize build_id event for %s\n", self->long_name);
return -1;
@@ -130,10 +155,11 @@
return 0;
}
-static int perf_event__inject_buildid(union perf_event *event,
+static int perf_event__inject_buildid(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel __used,
- struct perf_session *session)
+ struct machine *machine)
{
struct addr_location al;
struct thread *thread;
@@ -141,21 +167,21 @@
cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- thread = perf_session__findnew(session, event->ip.pid);
+ thread = machine__findnew_thread(machine, event->ip.pid);
if (thread == NULL) {
pr_err("problem processing %d event, skipping it.\n",
event->header.type);
goto repipe;
}
- thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
- event->ip.pid, event->ip.ip, &al);
+ thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+ event->ip.ip, &al);
if (al.map != NULL) {
if (!al.map->dso->hit) {
al.map->dso->hit = 1;
if (map__load(al.map, NULL) >= 0) {
- dso__inject_build_id(al.map->dso, session);
+ dso__inject_build_id(al.map->dso, tool, machine);
/*
* If this fails, too bad, let the other side
* account this as unresolved.
@@ -168,24 +194,24 @@
}
repipe:
- perf_event__repipe(event, sample, session);
+ perf_event__repipe(tool, event, sample, machine);
return 0;
}
-struct perf_event_ops inject_ops = {
+struct perf_tool perf_inject = {
.sample = perf_event__repipe_sample,
.mmap = perf_event__repipe,
.comm = perf_event__repipe,
.fork = perf_event__repipe,
.exit = perf_event__repipe,
.lost = perf_event__repipe,
- .read = perf_event__repipe,
+ .read = perf_event__repipe_sample,
.throttle = perf_event__repipe,
.unthrottle = perf_event__repipe,
- .attr = perf_event__repipe_synth,
- .event_type = perf_event__repipe_synth,
- .tracing_data = perf_event__repipe_synth,
- .build_id = perf_event__repipe_synth,
+ .attr = perf_event__repipe_attr,
+ .event_type = perf_event__repipe_event_type_synth,
+ .tracing_data = perf_event__repipe_tracing_data_synth,
+ .build_id = perf_event__repipe_op2_synth,
};
extern volatile int session_done;
@@ -203,17 +229,17 @@
signal(SIGINT, sig_handler);
if (inject_build_ids) {
- inject_ops.sample = perf_event__inject_buildid;
- inject_ops.mmap = perf_event__repipe_mmap;
- inject_ops.fork = perf_event__repipe_task;
- inject_ops.tracing_data = perf_event__repipe_tracing_data;
+ perf_inject.sample = perf_event__inject_buildid;
+ perf_inject.mmap = perf_event__repipe_mmap;
+ perf_inject.fork = perf_event__repipe_task;
+ perf_inject.tracing_data = perf_event__repipe_tracing_data;
}
- session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops);
+ session = perf_session__new(input_name, O_RDONLY, false, true, &perf_inject);
if (session == NULL)
return -ENOMEM;
- ret = perf_session__process_events(session, &inject_ops);
+ ret = perf_session__process_events(session, &perf_inject);
perf_session__delete(session);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 225e963..fe1ad8f 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -7,6 +7,7 @@
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
@@ -18,7 +19,7 @@
struct alloc_stat;
typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
-static char const *input_name = "perf.data";
+static const char *input_name;
static int alloc_flag;
static int caller_flag;
@@ -303,12 +304,13 @@
}
}
-static int process_sample_event(union perf_event *event,
+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_session *session)
+ struct machine *machine)
{
- struct thread *thread = perf_session__findnew(session, event->ip.pid);
+ struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
if (thread == NULL) {
pr_debug("problem processing %d event, skipping it.\n",
@@ -324,7 +326,7 @@
return 0;
}
-static struct perf_event_ops event_ops = {
+static struct perf_tool perf_kmem = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
.ordered_samples = true,
@@ -483,7 +485,7 @@
{
int err = -EINVAL;
struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &event_ops);
+ 0, false, &perf_kmem);
if (session == NULL)
return -ENOMEM;
@@ -494,7 +496,7 @@
goto out_delete;
setup_pager();
- err = perf_session__process_events(session, &event_ops);
+ err = perf_session__process_events(session, &perf_kmem);
if (err != 0)
goto out_delete;
sort_result();
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 34d1e85..032324a 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -38,7 +38,7 @@
OPT_BOOLEAN(0, "guest", &perf_guest,
"Collect guest os data"),
OPT_BOOLEAN(0, "host", &perf_host,
- "Collect guest os data"),
+ "Collect host os data"),
OPT_STRING(0, "guestmount", &symbol_conf.guestmount, "directory",
"guest mount directory under which every guest os"
" instance has a subdir"),
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 899080a..2296c39 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -12,6 +12,7 @@
#include "util/debug.h"
#include "util/session.h"
+#include "util/tool.h"
#include <sys/types.h>
#include <sys/prctl.h>
@@ -325,7 +326,7 @@
die("memory allocation failed\n");
}
-static char const *input_name = "perf.data";
+static const char *input_name;
struct raw_event_sample {
u32 size;
@@ -845,12 +846,13 @@
die("Unknown type of information\n");
}
-static int process_sample_event(union perf_event *event,
+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_session *s)
+ struct machine *machine)
{
- struct thread *thread = perf_session__findnew(s, sample->tid);
+ struct thread *thread = machine__findnew_thread(machine, sample->tid);
if (thread == NULL) {
pr_debug("problem processing %d event, skipping it.\n",
@@ -863,7 +865,7 @@
return 0;
}
-static struct perf_event_ops eops = {
+static struct perf_tool eops = {
.sample = process_sample_event,
.comm = perf_event__process_comm,
.ordered_samples = true,
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 710ae3d..59d43ab 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -46,7 +46,6 @@
#define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
#define DEFAULT_FUNC_FILTER "!_*"
-#define MAX_PATH_LEN 256
/* Session management structure */
static struct {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6ab58cc..0abfb18 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -22,6 +22,7 @@
#include "util/evsel.h"
#include "util/debug.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/symbol.h"
#include "util/cpumap.h"
#include "util/thread_map.h"
@@ -35,55 +36,36 @@
WRITE_APPEND
};
-static u64 user_interval = ULLONG_MAX;
-static u64 default_interval = 0;
+struct perf_record {
+ struct perf_tool tool;
+ struct perf_record_opts opts;
+ u64 bytes_written;
+ const char *output_name;
+ struct perf_evlist *evlist;
+ struct perf_session *session;
+ const char *progname;
+ int output;
+ unsigned int page_size;
+ int realtime_prio;
+ enum write_mode_t write_mode;
+ bool no_buildid;
+ bool no_buildid_cache;
+ bool force;
+ bool file_new;
+ bool append_file;
+ long samples;
+ off_t post_processing_offset;
+};
-static unsigned int page_size;
-static unsigned int mmap_pages = UINT_MAX;
-static unsigned int user_freq = UINT_MAX;
-static int freq = 1000;
-static int output;
-static int pipe_output = 0;
-static const char *output_name = NULL;
-static bool group = false;
-static int realtime_prio = 0;
-static bool nodelay = false;
-static bool raw_samples = false;
-static bool sample_id_all_avail = true;
-static bool system_wide = false;
-static pid_t target_pid = -1;
-static pid_t target_tid = -1;
-static pid_t child_pid = -1;
-static bool no_inherit = false;
-static enum write_mode_t write_mode = WRITE_FORCE;
-static bool call_graph = false;
-static bool inherit_stat = false;
-static bool no_samples = false;
-static bool sample_address = false;
-static bool sample_time = false;
-static bool no_buildid = false;
-static bool no_buildid_cache = false;
-static struct perf_evlist *evsel_list;
-
-static long samples = 0;
-static u64 bytes_written = 0;
-
-static int file_new = 1;
-static off_t post_processing_offset;
-
-static struct perf_session *session;
-static const char *cpu_list;
-static const char *progname;
-
-static void advance_output(size_t size)
+static void advance_output(struct perf_record *rec, size_t size)
{
- bytes_written += size;
+ rec->bytes_written += size;
}
-static void write_output(void *buf, size_t size)
+static void write_output(struct perf_record *rec, void *buf, size_t size)
{
while (size) {
- int ret = write(output, buf, size);
+ int ret = write(rec->output, buf, size);
if (ret < 0)
die("failed to write");
@@ -91,30 +73,33 @@
size -= ret;
buf += ret;
- bytes_written += ret;
+ rec->bytes_written += ret;
}
}
-static int process_synthesized_event(union perf_event *event,
+static int process_synthesized_event(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *self __used)
+ struct machine *machine __used)
{
- write_output(event, event->header.size);
+ struct perf_record *rec = container_of(tool, struct perf_record, tool);
+ write_output(rec, event, event->header.size);
return 0;
}
-static void mmap_read(struct perf_mmap *md)
+static void perf_record__mmap_read(struct perf_record *rec,
+ struct perf_mmap *md)
{
unsigned int head = perf_mmap__read_head(md);
unsigned int old = md->prev;
- unsigned char *data = md->base + page_size;
+ unsigned char *data = md->base + rec->page_size;
unsigned long size;
void *buf;
if (old == head)
return;
- samples++;
+ rec->samples++;
size = head - old;
@@ -123,14 +108,14 @@
size = md->mask + 1 - (old & md->mask);
old += size;
- write_output(buf, size);
+ write_output(rec, buf, size);
}
buf = &data[old & md->mask];
size = head - old;
old += size;
- write_output(buf, size);
+ write_output(rec, buf, size);
md->prev = old;
perf_mmap__write_tail(md, old);
@@ -149,17 +134,18 @@
signr = sig;
}
-static void sig_atexit(void)
+static void perf_record__sig_exit(int exit_status __used, void *arg)
{
+ struct perf_record *rec = arg;
int status;
- if (child_pid > 0) {
+ if (rec->evlist->workload.pid > 0) {
if (!child_finished)
- kill(child_pid, SIGTERM);
+ kill(rec->evlist->workload.pid, SIGTERM);
wait(&status);
if (WIFSIGNALED(status))
- psignal(WTERMSIG(status), progname);
+ psignal(WTERMSIG(status), rec->progname);
}
if (signr == -1 || signr == SIGUSR1)
@@ -169,78 +155,6 @@
kill(getpid(), signr);
}
-static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
-{
- struct perf_event_attr *attr = &evsel->attr;
- int track = !evsel->idx; /* only the first counter needs these */
-
- attr->disabled = 1;
- attr->inherit = !no_inherit;
- attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
- PERF_FORMAT_TOTAL_TIME_RUNNING |
- PERF_FORMAT_ID;
-
- attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
-
- if (evlist->nr_entries > 1)
- attr->sample_type |= PERF_SAMPLE_ID;
-
- /*
- * We default some events to a 1 default interval. But keep
- * it a weak assumption overridable by the user.
- */
- if (!attr->sample_period || (user_freq != UINT_MAX &&
- user_interval != ULLONG_MAX)) {
- if (freq) {
- attr->sample_type |= PERF_SAMPLE_PERIOD;
- attr->freq = 1;
- attr->sample_freq = freq;
- } else {
- attr->sample_period = default_interval;
- }
- }
-
- if (no_samples)
- attr->sample_freq = 0;
-
- if (inherit_stat)
- attr->inherit_stat = 1;
-
- if (sample_address) {
- attr->sample_type |= PERF_SAMPLE_ADDR;
- attr->mmap_data = track;
- }
-
- if (call_graph)
- attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
-
- if (system_wide)
- attr->sample_type |= PERF_SAMPLE_CPU;
-
- if (sample_id_all_avail &&
- (sample_time || system_wide || !no_inherit || cpu_list))
- attr->sample_type |= PERF_SAMPLE_TIME;
-
- if (raw_samples) {
- attr->sample_type |= PERF_SAMPLE_TIME;
- attr->sample_type |= PERF_SAMPLE_RAW;
- attr->sample_type |= PERF_SAMPLE_CPU;
- }
-
- if (nodelay) {
- attr->watermark = 0;
- attr->wakeup_events = 1;
- }
-
- attr->mmap = track;
- attr->comm = track;
-
- if (target_pid == -1 && target_tid == -1 && !system_wide) {
- attr->disabled = 1;
- attr->enable_on_exec = 1;
- }
-}
-
static bool perf_evlist__equal(struct perf_evlist *evlist,
struct perf_evlist *other)
{
@@ -260,15 +174,17 @@
return true;
}
-static void open_counters(struct perf_evlist *evlist)
+static void perf_record__open(struct perf_record *rec)
{
struct perf_evsel *pos, *first;
-
- if (evlist->cpus->map[0] < 0)
- no_inherit = true;
+ 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);
+
list_for_each_entry(pos, &evlist->entries, node) {
struct perf_event_attr *attr = &pos->attr;
struct xyarray *group_fd = NULL;
@@ -286,29 +202,27 @@
*/
bool time_needed = attr->sample_type & PERF_SAMPLE_TIME;
- if (group && pos != first)
+ if (opts->group && pos != first)
group_fd = first->fd;
-
- config_attr(pos, evlist);
retry_sample_id:
- attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+ attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
try_again:
- if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
- group_fd) < 0) {
+ if (perf_evsel__open(pos, evlist->cpus, evlist->threads,
+ opts->group, group_fd) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
ui__error_paranoid();
exit(EXIT_FAILURE);
- } else if (err == ENODEV && cpu_list) {
+ } else if (err == ENODEV && opts->cpu_list) {
die("No such device - did you specify"
" an out-of-range profile CPU?\n");
- } else if (err == EINVAL && sample_id_all_avail) {
+ } else if (err == EINVAL && opts->sample_id_all_avail) {
/*
* Old kernel, no attr->sample_id_type_all field
*/
- sample_id_all_avail = false;
- if (!sample_time && !raw_samples && !time_needed)
+ opts->sample_id_all_avail = false;
+ if (!opts->sample_time && !opts->raw_samples && !time_needed)
attr->sample_type &= ~PERF_SAMPLE_TIME;
goto retry_sample_id;
@@ -358,10 +272,20 @@
exit(-1);
}
- if (perf_evlist__mmap(evlist, mmap_pages, false) < 0)
- die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+ if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+ if (errno == EPERM)
+ die("Permission error mapping pages.\n"
+ "Consider increasing "
+ "/proc/sys/kernel/perf_event_mlock_kb,\n"
+ "or try again with a smaller value of -m/--mmap_pages.\n"
+ "(current value: %d)\n", opts->mmap_pages);
+ else if (!is_power_of_2(opts->mmap_pages))
+ die("--mmap_pages/-m value must be a power of two.");
- if (file_new)
+ die("failed to mmap with %d (%s)\n", errno, strerror(errno));
+ }
+
+ if (rec->file_new)
session->evlist = evlist;
else {
if (!perf_evlist__equal(session->evlist, evlist)) {
@@ -373,29 +297,32 @@
perf_session__update_sample_type(session);
}
-static int process_buildids(void)
+static int process_buildids(struct perf_record *rec)
{
- u64 size = lseek(output, 0, SEEK_CUR);
+ u64 size = lseek(rec->output, 0, SEEK_CUR);
if (size == 0)
return 0;
- session->fd = output;
- return __perf_session__process_events(session, post_processing_offset,
- size - post_processing_offset,
+ rec->session->fd = rec->output;
+ return __perf_session__process_events(rec->session, rec->post_processing_offset,
+ size - rec->post_processing_offset,
size, &build_id__mark_dso_hit_ops);
}
-static void atexit_header(void)
+static void perf_record__exit(int status __used, void *arg)
{
- if (!pipe_output) {
- session->header.data_size += bytes_written;
+ struct perf_record *rec = arg;
- if (!no_buildid)
- process_buildids();
- perf_session__write_header(session, evsel_list, output, true);
- perf_session__delete(session);
- perf_evlist__delete(evsel_list);
+ if (!rec->opts.pipe_output) {
+ rec->session->header.data_size += rec->bytes_written;
+
+ if (!rec->no_buildid)
+ process_buildids(rec);
+ perf_session__write_header(rec->session, rec->evlist,
+ rec->output, true);
+ perf_session__delete(rec->session);
+ perf_evlist__delete(rec->evlist);
symbol__exit();
}
}
@@ -403,7 +330,7 @@
static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
{
int err;
- struct perf_session *psession = data;
+ struct perf_tool *tool = data;
if (machine__is_host(machine))
return;
@@ -416,8 +343,8 @@
*method is used to avoid symbol missing when the first addr is
*in module instead of in guest kernel.
*/
- err = perf_event__synthesize_modules(process_synthesized_event,
- psession, machine);
+ err = perf_event__synthesize_modules(tool, process_synthesized_event,
+ machine);
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
@@ -426,12 +353,11 @@
* We use _stext for guest kernel because guest kernel's /proc/kallsyms
* have no _text sometimes.
*/
- err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
- psession, machine, "_text");
+ err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+ machine, "_text");
if (err < 0)
- err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
- psession, machine,
- "_stext");
+ err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+ machine, "_stext");
if (err < 0)
pr_err("Couldn't record guest kernel [%d]'s reference"
" relocation symbol.\n", machine->pid);
@@ -442,73 +368,71 @@
.type = PERF_RECORD_FINISHED_ROUND,
};
-static void mmap_read_all(void)
+static void perf_record__mmap_read_all(struct perf_record *rec)
{
int i;
- for (i = 0; i < evsel_list->nr_mmaps; i++) {
- if (evsel_list->mmap[i].base)
- mmap_read(&evsel_list->mmap[i]);
+ for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+ if (rec->evlist->mmap[i].base)
+ perf_record__mmap_read(rec, &rec->evlist->mmap[i]);
}
- if (perf_header__has_feat(&session->header, HEADER_TRACE_INFO))
- write_output(&finished_round_event, sizeof(finished_round_event));
+ if (perf_header__has_feat(&rec->session->header, HEADER_TRACE_INFO))
+ write_output(rec, &finished_round_event, sizeof(finished_round_event));
}
-static int __cmd_record(int argc, const char **argv)
+static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
{
struct stat st;
int flags;
- int err;
+ int err, output;
unsigned long waking = 0;
- int child_ready_pipe[2], go_pipe[2];
const bool forks = argc > 0;
- char buf;
struct machine *machine;
+ struct perf_tool *tool = &rec->tool;
+ struct perf_record_opts *opts = &rec->opts;
+ struct perf_evlist *evsel_list = rec->evlist;
+ const char *output_name = rec->output_name;
+ struct perf_session *session;
- progname = argv[0];
+ rec->progname = argv[0];
- page_size = sysconf(_SC_PAGE_SIZE);
+ rec->page_size = sysconf(_SC_PAGE_SIZE);
- atexit(sig_atexit);
+ on_exit(perf_record__sig_exit, rec);
signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler);
signal(SIGUSR1, sig_handler);
- if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
- perror("failed to create pipes");
- exit(-1);
- }
-
if (!output_name) {
if (!fstat(STDOUT_FILENO, &st) && S_ISFIFO(st.st_mode))
- pipe_output = 1;
+ opts->pipe_output = true;
else
- output_name = "perf.data";
+ rec->output_name = output_name = "perf.data";
}
if (output_name) {
if (!strcmp(output_name, "-"))
- pipe_output = 1;
+ opts->pipe_output = true;
else if (!stat(output_name, &st) && st.st_size) {
- if (write_mode == WRITE_FORCE) {
+ if (rec->write_mode == WRITE_FORCE) {
char oldname[PATH_MAX];
snprintf(oldname, sizeof(oldname), "%s.old",
output_name);
unlink(oldname);
rename(output_name, oldname);
}
- } else if (write_mode == WRITE_APPEND) {
- write_mode = WRITE_FORCE;
+ } else if (rec->write_mode == WRITE_APPEND) {
+ rec->write_mode = WRITE_FORCE;
}
}
flags = O_CREAT|O_RDWR;
- if (write_mode == WRITE_APPEND)
- file_new = 0;
+ if (rec->write_mode == WRITE_APPEND)
+ rec->file_new = 0;
else
flags |= O_TRUNC;
- if (pipe_output)
+ if (opts->pipe_output)
output = STDOUT_FILENO;
else
output = open(output_name, flags, S_IRUSR | S_IWUSR);
@@ -517,17 +441,21 @@
exit(-1);
}
+ rec->output = output;
+
session = perf_session__new(output_name, O_WRONLY,
- write_mode == WRITE_FORCE, false, NULL);
+ rec->write_mode == WRITE_FORCE, false, NULL);
if (session == NULL) {
pr_err("Not enough memory for reading perf file header\n");
return -1;
}
- if (!no_buildid)
+ rec->session = session;
+
+ if (!rec->no_buildid)
perf_header__set_feat(&session->header, HEADER_BUILD_ID);
- if (!file_new) {
+ if (!rec->file_new) {
err = perf_session__read_header(session, output);
if (err < 0)
goto out_delete_session;
@@ -549,94 +477,57 @@
perf_header__set_feat(&session->header, HEADER_NUMA_TOPOLOGY);
perf_header__set_feat(&session->header, HEADER_CPUID);
- /* 512 kiB: default amount of unprivileged mlocked memory */
- if (mmap_pages == UINT_MAX)
- mmap_pages = (512 * 1024) / page_size;
-
if (forks) {
- child_pid = fork();
- if (child_pid < 0) {
- perror("failed to fork");
- exit(-1);
+ err = perf_evlist__prepare_workload(evsel_list, opts, argv);
+ if (err < 0) {
+ pr_err("Couldn't run the workload!\n");
+ goto out_delete_session;
}
-
- if (!child_pid) {
- if (pipe_output)
- dup2(2, 1);
- close(child_ready_pipe[0]);
- close(go_pipe[1]);
- fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
-
- /*
- * Do a dummy execvp to get the PLT entry resolved,
- * so we avoid the resolver overhead on the real
- * execvp call.
- */
- execvp("", (char **)argv);
-
- /*
- * Tell the parent we're ready to go
- */
- close(child_ready_pipe[1]);
-
- /*
- * Wait until the parent tells us to go.
- */
- if (read(go_pipe[0], &buf, 1) == -1)
- perror("unable to read pipe");
-
- execvp(argv[0], (char **)argv);
-
- perror(argv[0]);
- kill(getppid(), SIGUSR1);
- exit(-1);
- }
-
- if (!system_wide && target_tid == -1 && target_pid == -1)
- evsel_list->threads->map[0] = child_pid;
-
- close(child_ready_pipe[1]);
- close(go_pipe[0]);
- /*
- * wait for child to settle
- */
- if (read(child_ready_pipe[0], &buf, 1) == -1) {
- perror("unable to read pipe");
- exit(-1);
- }
- close(child_ready_pipe[0]);
}
- open_counters(evsel_list);
+ perf_record__open(rec);
/*
- * perf_session__delete(session) will be called at atexit_header()
+ * perf_session__delete(session) will be called at perf_record__exit()
*/
- atexit(atexit_header);
+ on_exit(perf_record__exit, rec);
- if (pipe_output) {
+ if (opts->pipe_output) {
err = perf_header__write_pipe(output);
if (err < 0)
return err;
- } else if (file_new) {
+ } else if (rec->file_new) {
err = perf_session__write_header(session, evsel_list,
output, false);
if (err < 0)
return err;
}
- post_processing_offset = lseek(output, 0, SEEK_CUR);
+ if (!!rec->no_buildid
+ && !perf_header__has_feat(&session->header, HEADER_BUILD_ID)) {
+ pr_err("Couldn't generating buildids. "
+ "Use --no-buildid to profile anyway.\n");
+ return -1;
+ }
- if (pipe_output) {
- err = perf_session__synthesize_attrs(session,
- process_synthesized_event);
+ rec->post_processing_offset = lseek(output, 0, SEEK_CUR);
+
+ machine = perf_session__find_host_machine(session);
+ if (!machine) {
+ pr_err("Couldn't find native kernel information.\n");
+ return -1;
+ }
+
+ if (opts->pipe_output) {
+ err = perf_event__synthesize_attrs(tool, session,
+ process_synthesized_event);
if (err < 0) {
pr_err("Couldn't synthesize attrs.\n");
return err;
}
- err = perf_event__synthesize_event_types(process_synthesized_event,
- session);
+ err = perf_event__synthesize_event_types(tool, process_synthesized_event,
+ machine);
if (err < 0) {
pr_err("Couldn't synthesize event_types.\n");
return err;
@@ -651,56 +542,49 @@
* return this more properly and also
* propagate errors that now are calling die()
*/
- err = perf_event__synthesize_tracing_data(output, evsel_list,
- process_synthesized_event,
- session);
+ err = perf_event__synthesize_tracing_data(tool, output, evsel_list,
+ process_synthesized_event);
if (err <= 0) {
pr_err("Couldn't record tracing data.\n");
return err;
}
- advance_output(err);
+ advance_output(rec, err);
}
}
- machine = perf_session__find_host_machine(session);
- if (!machine) {
- pr_err("Couldn't find native kernel information.\n");
- return -1;
- }
-
- err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
- session, machine, "_text");
+ err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+ machine, "_text");
if (err < 0)
- err = perf_event__synthesize_kernel_mmap(process_synthesized_event,
- session, machine, "_stext");
+ err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+ machine, "_stext");
if (err < 0)
pr_err("Couldn't record kernel reference relocation symbol\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/kallsyms permission or run as root.\n");
- err = perf_event__synthesize_modules(process_synthesized_event,
- session, machine);
+ err = perf_event__synthesize_modules(tool, process_synthesized_event,
+ machine);
if (err < 0)
pr_err("Couldn't record kernel module information.\n"
"Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
"Check /proc/modules permission or run as root.\n");
if (perf_guest)
- perf_session__process_machines(session,
+ perf_session__process_machines(session, tool,
perf_event__synthesize_guest_os);
- if (!system_wide)
- perf_event__synthesize_thread_map(evsel_list->threads,
+ if (!opts->system_wide)
+ perf_event__synthesize_thread_map(tool, evsel_list->threads,
process_synthesized_event,
- session);
+ machine);
else
- perf_event__synthesize_threads(process_synthesized_event,
- session);
+ perf_event__synthesize_threads(tool, process_synthesized_event,
+ machine);
- if (realtime_prio) {
+ if (rec->realtime_prio) {
struct sched_param param;
- param.sched_priority = realtime_prio;
+ param.sched_priority = rec->realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, ¶m)) {
pr_err("Could not set realtime priority.\n");
exit(-1);
@@ -713,14 +597,14 @@
* Let the child rip
*/
if (forks)
- close(go_pipe[1]);
+ perf_evlist__start_workload(evsel_list);
for (;;) {
- int hits = samples;
+ int hits = rec->samples;
- mmap_read_all();
+ perf_record__mmap_read_all(rec);
- if (hits == samples) {
+ if (hits == rec->samples) {
if (done)
break;
err = poll(evsel_list->pollfd, evsel_list->nr_fds, -1);
@@ -741,9 +625,9 @@
*/
fprintf(stderr,
"[ perf record: Captured and wrote %.3f MB %s (~%" PRIu64 " samples) ]\n",
- (double)bytes_written / 1024.0 / 1024.0,
+ (double)rec->bytes_written / 1024.0 / 1024.0,
output_name,
- bytes_written / 24);
+ rec->bytes_written / 24);
return 0;
@@ -758,58 +642,89 @@
NULL
};
-static bool force, append_file;
+/*
+ * XXX Ideally would be local to cmd_record() and passed to a perf_record__new
+ * because we need to have access to it in perf_record__exit, that is called
+ * after cmd_record() exits, but since record_options need to be accessible to
+ * builtin-script, leave it here.
+ *
+ * At least we don't ouch it in all the other functions here directly.
+ *
+ * Just say no to tons of global variables, sigh.
+ */
+static struct perf_record record = {
+ .opts = {
+ .target_pid = -1,
+ .target_tid = -1,
+ .mmap_pages = UINT_MAX,
+ .user_freq = UINT_MAX,
+ .user_interval = ULLONG_MAX,
+ .freq = 1000,
+ .sample_id_all_avail = true,
+ },
+ .write_mode = WRITE_FORCE,
+ .file_new = true,
+};
+/*
+ * XXX Will stay a global variable till we fix builtin-script.c to stop messing
+ * with it and switch to use the library functions in perf_evlist that came
+ * from builtin-record.c, i.e. use perf_record_opts,
+ * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
+ * using pipes, etc.
+ */
const struct option record_options[] = {
- OPT_CALLBACK('e', "event", &evsel_list, "event",
+ OPT_CALLBACK('e', "event", &record.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
- OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+ OPT_CALLBACK(0, "filter", &record.evlist, "filter",
"event filter", parse_filter),
- OPT_INTEGER('p', "pid", &target_pid,
+ OPT_INTEGER('p', "pid", &record.opts.target_pid,
"record events on existing process id"),
- OPT_INTEGER('t', "tid", &target_tid,
+ OPT_INTEGER('t', "tid", &record.opts.target_tid,
"record events on existing thread id"),
- OPT_INTEGER('r', "realtime", &realtime_prio,
+ OPT_INTEGER('r', "realtime", &record.realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
- OPT_BOOLEAN('D', "no-delay", &nodelay,
+ OPT_BOOLEAN('D', "no-delay", &record.opts.no_delay,
"collect data without buffering"),
- OPT_BOOLEAN('R', "raw-samples", &raw_samples,
+ OPT_BOOLEAN('R', "raw-samples", &record.opts.raw_samples,
"collect raw sample records from all opened counters"),
- OPT_BOOLEAN('a', "all-cpus", &system_wide,
+ OPT_BOOLEAN('a', "all-cpus", &record.opts.system_wide,
"system-wide collection from all CPUs"),
- OPT_BOOLEAN('A', "append", &append_file,
+ OPT_BOOLEAN('A', "append", &record.append_file,
"append to the output file to do incremental profiling"),
- OPT_STRING('C', "cpu", &cpu_list, "cpu",
+ OPT_STRING('C', "cpu", &record.opts.cpu_list, "cpu",
"list of cpus to monitor"),
- OPT_BOOLEAN('f', "force", &force,
+ OPT_BOOLEAN('f', "force", &record.force,
"overwrite existing data file (deprecated)"),
- OPT_U64('c', "count", &user_interval, "event period to sample"),
- OPT_STRING('o', "output", &output_name, "file",
+ OPT_U64('c', "count", &record.opts.user_interval, "event period to sample"),
+ OPT_STRING('o', "output", &record.output_name, "file",
"output file name"),
- OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+ OPT_BOOLEAN('i', "no-inherit", &record.opts.no_inherit,
"child tasks do not inherit counters"),
- OPT_UINTEGER('F', "freq", &user_freq, "profile at this frequency"),
- OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
- OPT_BOOLEAN(0, "group", &group,
+ OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
+ OPT_UINTEGER('m', "mmap-pages", &record.opts.mmap_pages,
+ "number of mmap data pages"),
+ OPT_BOOLEAN(0, "group", &record.opts.group,
"put the counters into a counter group"),
- OPT_BOOLEAN('g', "call-graph", &call_graph,
+ OPT_BOOLEAN('g', "call-graph", &record.opts.call_graph,
"do call-graph (stack chain/backtrace) recording"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
- OPT_BOOLEAN('s', "stat", &inherit_stat,
+ OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
"per thread counts"),
- OPT_BOOLEAN('d', "data", &sample_address,
+ OPT_BOOLEAN('d', "data", &record.opts.sample_address,
"Sample addresses"),
- OPT_BOOLEAN('T', "timestamp", &sample_time, "Sample timestamps"),
- OPT_BOOLEAN('n', "no-samples", &no_samples,
+ OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
+ OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
+ OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
"don't sample"),
- OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid_cache,
+ OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
"do not update the buildid cache"),
- OPT_BOOLEAN('B', "no-buildid", &no_buildid,
+ OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
"do not collect buildids in perf.data"),
- OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+ OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
"monitor event in cgroup name only",
parse_cgroups),
OPT_END()
@@ -819,6 +734,8 @@
{
int err = -ENOMEM;
struct perf_evsel *pos;
+ struct perf_evlist *evsel_list;
+ struct perf_record *rec = &record;
perf_header__set_cmdline(argc, argv);
@@ -826,23 +743,25 @@
if (evsel_list == NULL)
return -ENOMEM;
+ rec->evlist = evsel_list;
+
argc = parse_options(argc, argv, record_options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- if (!argc && target_pid == -1 && target_tid == -1 &&
- !system_wide && !cpu_list)
+ if (!argc && rec->opts.target_pid == -1 && rec->opts.target_tid == -1 &&
+ !rec->opts.system_wide && !rec->opts.cpu_list)
usage_with_options(record_usage, record_options);
- if (force && append_file) {
+ if (rec->force && rec->append_file) {
fprintf(stderr, "Can't overwrite and append at the same time."
" You need to choose between -f and -A");
usage_with_options(record_usage, record_options);
- } else if (append_file) {
- write_mode = WRITE_APPEND;
+ } else if (rec->append_file) {
+ rec->write_mode = WRITE_APPEND;
} else {
- write_mode = WRITE_FORCE;
+ rec->write_mode = WRITE_FORCE;
}
- if (nr_cgroups && !system_wide) {
+ if (nr_cgroups && !rec->opts.system_wide) {
fprintf(stderr, "cgroup monitoring only available in"
" system-wide mode\n");
usage_with_options(record_usage, record_options);
@@ -860,7 +779,7 @@
"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
"even with a suitable vmlinux or kallsyms file.\n\n");
- if (no_buildid_cache || no_buildid)
+ if (rec->no_buildid_cache || rec->no_buildid)
disable_buildid_cache();
if (evsel_list->nr_entries == 0 &&
@@ -869,43 +788,37 @@
goto out_symbol_exit;
}
- if (target_pid != -1)
- target_tid = target_pid;
+ if (rec->opts.target_pid != -1)
+ rec->opts.target_tid = rec->opts.target_pid;
- if (perf_evlist__create_maps(evsel_list, target_pid,
- target_tid, cpu_list) < 0)
+ if (perf_evlist__create_maps(evsel_list, rec->opts.target_pid,
+ rec->opts.target_tid, rec->opts.cpu_list) < 0)
usage_with_options(record_usage, record_options);
list_for_each_entry(pos, &evsel_list->entries, node) {
- if (perf_evsel__alloc_fd(pos, evsel_list->cpus->nr,
- evsel_list->threads->nr) < 0)
- goto out_free_fd;
if (perf_header__push_event(pos->attr.config, event_name(pos)))
goto out_free_fd;
}
- if (perf_evlist__alloc_pollfd(evsel_list) < 0)
- goto out_free_fd;
-
- if (user_interval != ULLONG_MAX)
- default_interval = user_interval;
- if (user_freq != UINT_MAX)
- freq = user_freq;
+ if (rec->opts.user_interval != ULLONG_MAX)
+ rec->opts.default_interval = rec->opts.user_interval;
+ if (rec->opts.user_freq != UINT_MAX)
+ rec->opts.freq = rec->opts.user_freq;
/*
* User specified count overrides default frequency.
*/
- if (default_interval)
- freq = 0;
- else if (freq) {
- default_interval = freq;
+ if (rec->opts.default_interval)
+ rec->opts.freq = 0;
+ else if (rec->opts.freq) {
+ rec->opts.default_interval = rec->opts.freq;
} else {
fprintf(stderr, "frequency and count are zero, aborting\n");
err = -EINVAL;
goto out_free_fd;
}
- err = __cmd_record(argc, argv);
+ err = __cmd_record(&record, argc, argv);
out_free_fd:
perf_evlist__delete_maps(evsel_list);
out_symbol_exit:
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4d7c834..25d34d4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -25,6 +25,7 @@
#include "util/evsel.h"
#include "util/header.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
@@ -35,38 +36,35 @@
#include <linux/bitmap.h>
-static char const *input_name = "perf.data";
+struct perf_report {
+ struct perf_tool tool;
+ struct perf_session *session;
+ char const *input_name;
+ bool force, use_tui, use_stdio;
+ bool hide_unresolved;
+ bool dont_use_callchains;
+ bool show_full_info;
+ bool show_threads;
+ bool inverted_callchain;
+ struct perf_read_values show_threads_values;
+ const char *pretty_printing_style;
+ symbol_filter_t annotate_init;
+ const char *cpu_list;
+ DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
-static bool force, use_tui, use_stdio;
-static bool hide_unresolved;
-static bool dont_use_callchains;
-static bool show_full_info;
-
-static bool show_threads;
-static struct perf_read_values show_threads_values;
-
-static const char default_pretty_printing_style[] = "normal";
-static const char *pretty_printing_style = default_pretty_printing_style;
-
-static char callchain_default_opt[] = "fractal,0.5,callee";
-static bool inverted_callchain;
-static symbol_filter_t annotate_init;
-
-static const char *cpu_list;
-static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
-
-static int perf_session__add_hist_entry(struct perf_session *session,
- struct addr_location *al,
- struct perf_sample *sample,
- struct perf_evsel *evsel)
+static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
+ struct addr_location *al,
+ struct perf_sample *sample,
+ struct machine *machine)
{
struct symbol *parent = NULL;
int err = 0;
struct hist_entry *he;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
- err = perf_session__resolve_callchain(session, al->thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al->thread,
+ sample->callchain, &parent);
if (err)
return err;
}
@@ -76,7 +74,8 @@
return -ENOMEM;
if (symbol_conf.use_callchain) {
- err = callchain_append(he->callchain, &session->callchain_cursor,
+ err = callchain_append(he->callchain,
+ &evsel->hists.callchain_cursor,
sample->period);
if (err)
return err;
@@ -92,8 +91,7 @@
assert(evsel != NULL);
err = -ENOMEM;
- if (notes->src == NULL &&
- symbol__alloc_hist(he->ms.sym, session->evlist->nr_entries) < 0)
+ if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
goto out;
err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
@@ -106,30 +104,32 @@
}
-static int process_sample_event(union perf_event *event,
+static int process_sample_event(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
- struct perf_session *session)
+ struct machine *machine)
{
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
struct addr_location al;
- if (perf_event__preprocess_sample(event, session, &al, sample,
- annotate_init) < 0) {
+ if (perf_event__preprocess_sample(event, machine, &al, sample,
+ rep->annotate_init) < 0) {
fprintf(stderr, "problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
- if (al.filtered || (hide_unresolved && al.sym == NULL))
+ if (al.filtered || (rep->hide_unresolved && al.sym == NULL))
return 0;
- if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+ if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
return 0;
if (al.map != NULL)
al.map->dso->hit = 1;
- if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
+ if (perf_evsel__add_hist_entry(evsel, &al, sample, machine)) {
pr_debug("problem incrementing symbol period, skipping event\n");
return -1;
}
@@ -137,15 +137,17 @@
return 0;
}
-static int process_read_event(union perf_event *event,
+static int process_read_event(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *session)
+ struct perf_evsel *evsel,
+ struct machine *machine __used)
{
- struct perf_evsel *evsel = perf_evlist__id2evsel(session->evlist,
- event->read.id);
- if (show_threads) {
+ struct perf_report *rep = container_of(tool, struct perf_report, tool);
+
+ if (rep->show_threads) {
const char *name = evsel ? event_name(evsel) : "unknown";
- perf_read_values_add_value(&show_threads_values,
+ perf_read_values_add_value(&rep->show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
name,
@@ -159,8 +161,10 @@
return 0;
}
-static int perf_session__setup_sample_type(struct perf_session *self)
+static int perf_report__setup_sample_type(struct perf_report *rep)
{
+ struct perf_session *self = rep->session;
+
if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
ui__warning("Selected --sort parent, but no "
@@ -173,7 +177,8 @@
"you call 'perf record' without -g?\n");
return -1;
}
- } else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
+ } else if (!rep->dont_use_callchains &&
+ callchain_param.mode != CHAIN_NONE &&
!symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
if (callchain_register_param(&callchain_param) < 0) {
@@ -186,22 +191,6 @@
return 0;
}
-static struct perf_event_ops event_ops = {
- .sample = process_sample_event,
- .mmap = perf_event__process_mmap,
- .comm = perf_event__process_comm,
- .exit = perf_event__process_task,
- .fork = perf_event__process_task,
- .lost = perf_event__process_lost,
- .read = process_read_event,
- .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;
static void sig_handler(int sig __used)
@@ -224,6 +213,7 @@
}
static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
+ struct perf_report *rep,
const char *help)
{
struct perf_evsel *pos;
@@ -241,18 +231,18 @@
parent_pattern == default_parent_pattern) {
fprintf(stdout, "#\n# (%s)\n#\n", help);
- if (show_threads) {
- bool style = !strcmp(pretty_printing_style, "raw");
- perf_read_values_display(stdout, &show_threads_values,
+ if (rep->show_threads) {
+ bool style = !strcmp(rep->pretty_printing_style, "raw");
+ perf_read_values_display(stdout, &rep->show_threads_values,
style);
- perf_read_values_destroy(&show_threads_values);
+ perf_read_values_destroy(&rep->show_threads_values);
}
}
return 0;
}
-static int __cmd_report(void)
+static int __cmd_report(struct perf_report *rep)
{
int ret = -EINVAL;
u64 nr_samples;
@@ -264,27 +254,31 @@
signal(SIGINT, sig_handler);
- session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
+ session = perf_session__new(rep->input_name, O_RDONLY,
+ rep->force, false, &rep->tool);
if (session == NULL)
return -ENOMEM;
- if (cpu_list) {
- ret = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+ rep->session = session;
+
+ if (rep->cpu_list) {
+ ret = perf_session__cpu_bitmap(session, rep->cpu_list,
+ rep->cpu_bitmap);
if (ret)
goto out_delete;
}
if (use_browser <= 0)
- perf_session__fprintf_info(session, stdout, show_full_info);
+ perf_session__fprintf_info(session, stdout, rep->show_full_info);
- if (show_threads)
- perf_read_values_init(&show_threads_values);
+ if (rep->show_threads)
+ perf_read_values_init(&rep->show_threads_values);
- ret = perf_session__setup_sample_type(session);
+ ret = perf_report__setup_sample_type(rep);
if (ret)
goto out_delete;
- ret = perf_session__process_events(session, &event_ops);
+ ret = perf_session__process_events(session, &rep->tool);
if (ret)
goto out_delete;
@@ -327,7 +321,7 @@
}
if (nr_samples == 0) {
- ui__warning("The %s file has no samples!\n", input_name);
+ ui__warning("The %s file has no samples!\n", session->filename);
goto out_delete;
}
@@ -335,7 +329,7 @@
perf_evlist__tui_browse_hists(session->evlist, help,
NULL, NULL, 0);
} else
- perf_evlist__tty_browse_hists(session->evlist, help);
+ perf_evlist__tty_browse_hists(session->evlist, rep, help);
out_delete:
/*
@@ -354,9 +348,9 @@
}
static int
-parse_callchain_opt(const struct option *opt __used, const char *arg,
- int unset)
+parse_callchain_opt(const struct option *opt, const char *arg, int unset)
{
+ struct perf_report *rep = (struct perf_report *)opt->value;
char *tok, *tok2;
char *endptr;
@@ -364,7 +358,7 @@
* --no-call-graph
*/
if (unset) {
- dont_use_callchains = true;
+ rep->dont_use_callchains = true;
return 0;
}
@@ -412,7 +406,7 @@
goto setup;
if (tok2[0] != 'c') {
- callchain_param.print_limit = strtod(tok2, &endptr);
+ callchain_param.print_limit = strtoul(tok2, &endptr, 0);
tok2 = strtok(NULL, ",");
if (!tok2)
goto setup;
@@ -433,13 +427,34 @@
return 0;
}
-static const char * const report_usage[] = {
- "perf report [<options>] <command>",
- NULL
-};
-
-static const struct option options[] = {
- OPT_STRING('i', "input", &input_name, "file",
+int cmd_report(int argc, const char **argv, const char *prefix __used)
+{
+ struct stat st;
+ char callchain_default_opt[] = "fractal,0.5,callee";
+ const char * const report_usage[] = {
+ "perf report [<options>]",
+ NULL
+ };
+ struct perf_report report = {
+ .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,
+ .lost = perf_event__process_lost,
+ .read = process_read_event,
+ .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,
+ },
+ .pretty_printing_style = "normal",
+ };
+ const struct option options[] = {
+ OPT_STRING('i', "input", &report.input_name, "file",
"input file name"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show symbol address, etc)"),
@@ -449,17 +464,18 @@
"file", "vmlinux pathname"),
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
"file", "kallsyms pathname"),
- OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+ OPT_BOOLEAN('f', "force", &report.force, "don't complain, do it"),
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
- OPT_BOOLEAN('T', "threads", &show_threads,
+ OPT_BOOLEAN('T', "threads", &report.show_threads,
"Show per-thread event counters"),
- OPT_STRING(0, "pretty", &pretty_printing_style, "key",
+ OPT_STRING(0, "pretty", &report.pretty_printing_style, "key",
"pretty printing style key: normal raw"),
- OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
- OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
+ OPT_BOOLEAN(0, "tui", &report.use_tui, "Use the TUI interface"),
+ OPT_BOOLEAN(0, "stdio", &report.use_stdio,
+ "Use the stdio interface"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
@@ -468,13 +484,14 @@
"regex filter to identify parent, see: '--sort parent'"),
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
"Only display entries with parent-match"),
- OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent, call_order",
- "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold and callchain order. "
+ OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
+ "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit and callchain order. "
"Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
- OPT_BOOLEAN('G', "inverted", &inverted_callchain, "alias for inverted call graph"),
+ OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
+ "alias for inverted call graph"),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
- OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+ OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
"only consider symbols in these comms"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
@@ -484,12 +501,13 @@
OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
- OPT_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
+ OPT_BOOLEAN('U', "hide-unresolved", &report.hide_unresolved,
"Only display entries resolved to a symbol"),
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
- OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
- OPT_BOOLEAN('I', "show-info", &show_full_info,
+ OPT_STRING('C', "cpu", &report.cpu_list, "cpu",
+ "list of cpus to profile"),
+ OPT_BOOLEAN('I', "show-info", &report.show_full_info,
"Display extended information about perf.data file"),
OPT_BOOLEAN(0, "source", &symbol_conf.annotate_src,
"Interleave source code with assembly code (default)"),
@@ -500,24 +518,30 @@
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
"Show a column with the sum of periods"),
OPT_END()
-};
+ };
-int cmd_report(int argc, const char **argv, const char *prefix __used)
-{
argc = parse_options(argc, argv, options, report_usage, 0);
- if (use_stdio)
+ if (report.use_stdio)
use_browser = 0;
- else if (use_tui)
+ else if (report.use_tui)
use_browser = 1;
- if (inverted_callchain)
+ if (report.inverted_callchain)
callchain_param.order = ORDER_CALLER;
- if (strcmp(input_name, "-") != 0)
+ if (!report.input_name || !strlen(report.input_name)) {
+ if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+ report.input_name = "-";
+ else
+ report.input_name = "perf.data";
+ }
+
+ if (strcmp(report.input_name, "-") != 0)
setup_browser(true);
else
use_browser = 0;
+
/*
* Only in the newt browser we are doing integrated annotation,
* so don't allocate extra space that won't be used in the stdio
@@ -525,7 +549,7 @@
*/
if (use_browser > 0) {
symbol_conf.priv_size = sizeof(struct annotation);
- annotate_init = symbol__annotate_init;
+ report.annotate_init = symbol__annotate_init;
/*
* For searching by name on the "Browse map details".
* providing it only in verbose mode not to bloat too
@@ -572,5 +596,5 @@
sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
- return __cmd_report();
+ return __cmd_report(&report);
}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5177964..fb8b5f8 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2,11 +2,14 @@
#include "perf.h"
#include "util/util.h"
+#include "util/evlist.h"
#include "util/cache.h"
+#include "util/evsel.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/header.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/parse-options.h"
#include "util/trace-event.h"
@@ -19,7 +22,7 @@
#include <pthread.h>
#include <math.h>
-static char const *input_name = "perf.data";
+static const char *input_name;
static char default_sort_order[] = "avg, max, switch, runtime";
static const char *sort_order = default_sort_order;
@@ -723,21 +726,21 @@
struct trace_sched_handler {
void (*switch_event)(struct trace_switch_event *,
- struct perf_session *,
+ struct machine *,
struct event *,
int cpu,
u64 timestamp,
struct thread *thread);
void (*runtime_event)(struct trace_runtime_event *,
- struct perf_session *,
+ struct machine *,
struct event *,
int cpu,
u64 timestamp,
struct thread *thread);
void (*wakeup_event)(struct trace_wakeup_event *,
- struct perf_session *,
+ struct machine *,
struct event *,
int cpu,
u64 timestamp,
@@ -750,7 +753,7 @@
struct thread *thread);
void (*migrate_task_event)(struct trace_migrate_task_event *,
- struct perf_session *session,
+ struct machine *machine,
struct event *,
int cpu,
u64 timestamp,
@@ -760,7 +763,7 @@
static void
replay_wakeup_event(struct trace_wakeup_event *wakeup_event,
- struct perf_session *session __used,
+ struct machine *machine __used,
struct event *event,
int cpu __used,
u64 timestamp __used,
@@ -787,7 +790,7 @@
static void
replay_switch_event(struct trace_switch_event *switch_event,
- struct perf_session *session __used,
+ struct machine *machine __used,
struct event *event,
int cpu,
u64 timestamp,
@@ -1021,7 +1024,7 @@
static void
latency_switch_event(struct trace_switch_event *switch_event,
- struct perf_session *session,
+ struct machine *machine,
struct event *event __used,
int cpu,
u64 timestamp,
@@ -1045,8 +1048,8 @@
die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
- sched_out = perf_session__findnew(session, switch_event->prev_pid);
- sched_in = perf_session__findnew(session, switch_event->next_pid);
+ sched_out = machine__findnew_thread(machine, switch_event->prev_pid);
+ sched_in = machine__findnew_thread(machine, switch_event->next_pid);
out_events = thread_atoms_search(&atom_root, sched_out, &cmp_pid);
if (!out_events) {
@@ -1074,13 +1077,13 @@
static void
latency_runtime_event(struct trace_runtime_event *runtime_event,
- struct perf_session *session,
+ struct machine *machine,
struct event *event __used,
int cpu,
u64 timestamp,
struct thread *this_thread __used)
{
- struct thread *thread = perf_session__findnew(session, runtime_event->pid);
+ struct thread *thread = machine__findnew_thread(machine, runtime_event->pid);
struct work_atoms *atoms = thread_atoms_search(&atom_root, thread, &cmp_pid);
BUG_ON(cpu >= MAX_CPUS || cpu < 0);
@@ -1097,7 +1100,7 @@
static void
latency_wakeup_event(struct trace_wakeup_event *wakeup_event,
- struct perf_session *session,
+ struct machine *machine,
struct event *__event __used,
int cpu __used,
u64 timestamp,
@@ -1111,7 +1114,7 @@
if (!wakeup_event->success)
return;
- wakee = perf_session__findnew(session, wakeup_event->pid);
+ wakee = machine__findnew_thread(machine, wakeup_event->pid);
atoms = thread_atoms_search(&atom_root, wakee, &cmp_pid);
if (!atoms) {
thread_atoms_insert(wakee);
@@ -1145,7 +1148,7 @@
static void
latency_migrate_task_event(struct trace_migrate_task_event *migrate_task_event,
- struct perf_session *session,
+ struct machine *machine,
struct event *__event __used,
int cpu __used,
u64 timestamp,
@@ -1161,7 +1164,7 @@
if (profile_cpu == -1)
return;
- migrant = perf_session__findnew(session, migrate_task_event->pid);
+ migrant = machine__findnew_thread(machine, migrate_task_event->pid);
atoms = thread_atoms_search(&atom_root, migrant, &cmp_pid);
if (!atoms) {
thread_atoms_insert(migrant);
@@ -1356,12 +1359,13 @@
static struct trace_sched_handler *trace_handler;
static void
-process_sched_wakeup_event(void *data, struct perf_session *session,
+process_sched_wakeup_event(struct perf_tool *tool __used,
struct event *event,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread)
{
+ void *data = sample->raw_data;
struct trace_wakeup_event wakeup_event;
FILL_COMMON_FIELDS(wakeup_event, event, data);
@@ -1373,8 +1377,8 @@
FILL_FIELD(wakeup_event, cpu, event, data);
if (trace_handler->wakeup_event)
- trace_handler->wakeup_event(&wakeup_event, session, event,
- cpu, timestamp, thread);
+ trace_handler->wakeup_event(&wakeup_event, machine, event,
+ sample->cpu, sample->time, thread);
}
/*
@@ -1392,7 +1396,7 @@
static void
map_switch_event(struct trace_switch_event *switch_event,
- struct perf_session *session,
+ struct machine *machine,
struct event *event __used,
int this_cpu,
u64 timestamp,
@@ -1420,8 +1424,8 @@
die("hm, delta: %" PRIu64 " < 0 ?\n", delta);
- sched_out = perf_session__findnew(session, switch_event->prev_pid);
- sched_in = perf_session__findnew(session, switch_event->next_pid);
+ sched_out = machine__findnew_thread(machine, switch_event->prev_pid);
+ sched_in = machine__findnew_thread(machine, switch_event->next_pid);
curr_thread[this_cpu] = sched_in;
@@ -1469,14 +1473,15 @@
}
}
-
static void
-process_sched_switch_event(void *data, struct perf_session *session,
+process_sched_switch_event(struct perf_tool *tool __used,
struct event *event,
- int this_cpu,
- u64 timestamp __used,
- struct thread *thread __used)
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread)
{
+ int this_cpu = sample->cpu;
+ void *data = sample->raw_data;
struct trace_switch_event switch_event;
FILL_COMMON_FIELDS(switch_event, event, data);
@@ -1498,19 +1503,20 @@
nr_context_switch_bugs++;
}
if (trace_handler->switch_event)
- trace_handler->switch_event(&switch_event, session, event,
- this_cpu, timestamp, thread);
+ trace_handler->switch_event(&switch_event, machine, event,
+ this_cpu, sample->time, thread);
curr_pid[this_cpu] = switch_event.next_pid;
}
static void
-process_sched_runtime_event(void *data, struct perf_session *session,
- struct event *event,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+process_sched_runtime_event(struct perf_tool *tool __used,
+ struct event *event,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread)
{
+ void *data = sample->raw_data;
struct trace_runtime_event runtime_event;
FILL_ARRAY(runtime_event, comm, event, data);
@@ -1519,16 +1525,18 @@
FILL_FIELD(runtime_event, vruntime, event, data);
if (trace_handler->runtime_event)
- trace_handler->runtime_event(&runtime_event, session, event, cpu, timestamp, thread);
+ trace_handler->runtime_event(&runtime_event, machine, event,
+ sample->cpu, sample->time, thread);
}
static void
-process_sched_fork_event(void *data,
+process_sched_fork_event(struct perf_tool *tool __used,
struct event *event,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+ struct perf_sample *sample,
+ struct machine *machine __used,
+ struct thread *thread)
{
+ void *data = sample->raw_data;
struct trace_fork_event fork_event;
FILL_COMMON_FIELDS(fork_event, event, data);
@@ -1540,13 +1548,14 @@
if (trace_handler->fork_event)
trace_handler->fork_event(&fork_event, event,
- cpu, timestamp, thread);
+ sample->cpu, sample->time, thread);
}
static void
-process_sched_exit_event(struct event *event,
- int cpu __used,
- u64 timestamp __used,
+process_sched_exit_event(struct perf_tool *tool __used,
+ struct event *event,
+ struct perf_sample *sample __used,
+ struct machine *machine __used,
struct thread *thread __used)
{
if (verbose)
@@ -1554,12 +1563,13 @@
}
static void
-process_sched_migrate_task_event(void *data, struct perf_session *session,
- struct event *event,
- int cpu __used,
- u64 timestamp __used,
- struct thread *thread __used)
+process_sched_migrate_task_event(struct perf_tool *tool __used,
+ struct event *event,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread)
{
+ void *data = sample->raw_data;
struct trace_migrate_task_event migrate_task_event;
FILL_COMMON_FIELDS(migrate_task_event, event, data);
@@ -1570,67 +1580,47 @@
FILL_FIELD(migrate_task_event, cpu, event, data);
if (trace_handler->migrate_task_event)
- trace_handler->migrate_task_event(&migrate_task_event, session,
- event, cpu, timestamp, thread);
+ trace_handler->migrate_task_event(&migrate_task_event, machine,
+ event, sample->cpu,
+ sample->time, thread);
}
-static void process_raw_event(union perf_event *raw_event __used,
- struct perf_session *session, void *data, int cpu,
- u64 timestamp, struct thread *thread)
+typedef void (*tracepoint_handler)(struct perf_tool *tool, struct event *event,
+ struct perf_sample *sample,
+ struct machine *machine,
+ struct thread *thread);
+
+static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
+ union perf_event *event __used,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine)
{
- struct event *event;
- int type;
+ struct thread *thread = machine__findnew_thread(machine, sample->pid);
-
- type = trace_parse_common_type(data);
- event = trace_find_event(type);
-
- if (!strcmp(event->name, "sched_switch"))
- process_sched_switch_event(data, session, event, cpu, timestamp, thread);
- if (!strcmp(event->name, "sched_stat_runtime"))
- process_sched_runtime_event(data, session, event, cpu, timestamp, thread);
- if (!strcmp(event->name, "sched_wakeup"))
- process_sched_wakeup_event(data, session, event, cpu, timestamp, thread);
- if (!strcmp(event->name, "sched_wakeup_new"))
- process_sched_wakeup_event(data, session, event, cpu, timestamp, thread);
- if (!strcmp(event->name, "sched_process_fork"))
- process_sched_fork_event(data, event, cpu, timestamp, thread);
- if (!strcmp(event->name, "sched_process_exit"))
- process_sched_exit_event(event, cpu, timestamp, thread);
- if (!strcmp(event->name, "sched_migrate_task"))
- process_sched_migrate_task_event(data, session, event, cpu, timestamp, thread);
-}
-
-static int process_sample_event(union perf_event *event,
- struct perf_sample *sample,
- struct perf_evsel *evsel __used,
- struct perf_session *session)
-{
- struct thread *thread;
-
- if (!(session->sample_type & PERF_SAMPLE_RAW))
- return 0;
-
- thread = perf_session__findnew(session, sample->pid);
if (thread == NULL) {
- pr_debug("problem processing %d event, skipping it.\n",
- event->header.type);
+ pr_debug("problem processing %s event, skipping it.\n",
+ evsel->name);
return -1;
}
- dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+ evsel->hists.stats.total_period += sample->period;
+ hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
- if (profile_cpu != -1 && profile_cpu != (int)sample->cpu)
- return 0;
+ if (evsel->handler.func != NULL) {
+ tracepoint_handler f = evsel->handler.func;
- process_raw_event(event, session, sample->raw_data, sample->cpu,
- sample->time, thread);
+ if (evsel->handler.data == NULL)
+ evsel->handler.data = trace_find_event(evsel->attr.config);
+
+ f(tool, evsel->handler.data, sample, machine, thread);
+ }
return 0;
}
-static struct perf_event_ops event_ops = {
- .sample = process_sample_event,
+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,
@@ -1640,13 +1630,25 @@
static void read_events(bool destroy, struct perf_session **psession)
{
int err = -EINVAL;
+ const struct perf_evsel_str_handler handlers[] = {
+ { "sched:sched_switch", process_sched_switch_event, },
+ { "sched:sched_stat_runtime", process_sched_runtime_event, },
+ { "sched:sched_wakeup", process_sched_wakeup_event, },
+ { "sched:sched_wakeup_new", process_sched_wakeup_event, },
+ { "sched:sched_process_fork", process_sched_fork_event, },
+ { "sched:sched_process_exit", process_sched_exit_event, },
+ { "sched:sched_migrate_task", process_sched_migrate_task_event, },
+ };
struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &event_ops);
+ 0, false, &perf_sched);
if (session == NULL)
die("No Memory");
+ err = perf_evlist__set_tracepoints_handlers_array(session->evlist, handlers);
+ assert(err == 0);
+
if (perf_session__has_traces(session, "record -R")) {
- err = perf_session__process_events(session, &event_ops);
+ err = perf_session__process_events(session, &perf_sched);
if (err)
die("Failed to process events, error %d", err);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f62a29..fd1909a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -7,6 +7,7 @@
#include "util/header.h"
#include "util/parse-options.h"
#include "util/session.h"
+#include "util/tool.h"
#include "util/symbol.h"
#include "util/thread.h"
#include "util/trace-event.h"
@@ -23,6 +24,7 @@
extern const struct option record_options[];
static bool no_callchain;
static bool show_full_info;
+static bool system_wide;
static const char *cpu_list;
static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -315,7 +317,7 @@
static void print_sample_addr(union perf_event *event,
struct perf_sample *sample,
- struct perf_session *session,
+ struct machine *machine,
struct thread *thread,
struct perf_event_attr *attr)
{
@@ -328,11 +330,11 @@
if (!sample_addr_correlates_sym(attr))
return;
- thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
- event->ip.pid, sample->addr, &al);
+ thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+ sample->addr, &al);
if (!al.map)
- thread__find_addr_map(thread, session, cpumode, MAP__VARIABLE,
- event->ip.pid, sample->addr, &al);
+ thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+ sample->addr, &al);
al.cpu = sample->cpu;
al.sym = NULL;
@@ -362,7 +364,7 @@
static void process_event(union perf_event *event __unused,
struct perf_sample *sample,
struct perf_evsel *evsel,
- struct perf_session *session,
+ struct machine *machine,
struct thread *thread)
{
struct perf_event_attr *attr = &evsel->attr;
@@ -377,15 +379,15 @@
sample->raw_size);
if (PRINT_FIELD(ADDR))
- print_sample_addr(event, sample, session, thread, attr);
+ print_sample_addr(event, sample, machine, thread, attr);
if (PRINT_FIELD(IP)) {
if (!symbol_conf.use_callchain)
printf(" ");
else
printf("\n");
- perf_session__print_ip(event, sample, session,
- PRINT_FIELD(SYM), PRINT_FIELD(DSO));
+ perf_event__print_ip(event, sample, machine, evsel,
+ PRINT_FIELD(SYM), PRINT_FIELD(DSO));
}
printf("\n");
@@ -432,14 +434,16 @@
return scripting_ops->stop_script();
}
-static char const *input_name = "perf.data";
+static const char *input_name;
-static int process_sample_event(union perf_event *event,
+static int process_sample_event(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
- struct perf_session *session)
+ struct machine *machine)
{
- struct thread *thread = perf_session__findnew(session, event->ip.pid);
+ struct addr_location al;
+ struct thread *thread = machine__findnew_thread(machine, event->ip.tid);
if (thread == NULL) {
pr_debug("problem processing %d event, skipping it.\n",
@@ -458,16 +462,25 @@
return 0;
}
+ if (perf_event__preprocess_sample(event, machine, &al, sample, 0) < 0) {
+ pr_err("problem processing %d event, skipping it.\n",
+ event->header.type);
+ return -1;
+ }
+
+ if (al.filtered)
+ return 0;
+
if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
return 0;
- scripting_ops->process_event(event, sample, evsel, session, thread);
+ scripting_ops->process_event(event, sample, evsel, machine, thread);
- session->hists.stats.total_period += sample->period;
+ evsel->hists.stats.total_period += sample->period;
return 0;
}
-static struct perf_event_ops event_ops = {
+static struct perf_tool perf_script = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
@@ -494,7 +507,7 @@
signal(SIGINT, sig_handler);
- ret = perf_session__process_events(session, &event_ops);
+ ret = perf_session__process_events(session, &perf_script);
if (debug_mode)
pr_err("Misordered timestamps: %" PRIu64 "\n", nr_unordered);
@@ -523,12 +536,6 @@
return s;
}
-static void script_spec__delete(struct script_spec *s)
-{
- free(s->spec);
- free(s);
-}
-
static void script_spec__add(struct script_spec *s)
{
list_add_tail(&s->node, &script_specs);
@@ -554,16 +561,11 @@
s = script_spec__new(spec, ops);
if (!s)
- goto out_delete_spec;
+ return NULL;
script_spec__add(s);
return s;
-
-out_delete_spec:
- script_spec__delete(s);
-
- return NULL;
}
int script_spec_register(const char *spec, struct scripting_ops *ops)
@@ -681,7 +683,8 @@
type = PERF_TYPE_RAW;
else {
fprintf(stderr, "Invalid event type in field string.\n");
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
if (output[type].user_set)
@@ -923,6 +926,24 @@
return 0;
}
+static char *get_script_root(struct dirent *script_dirent, const char *suffix)
+{
+ char *script_root, *str;
+
+ script_root = strdup(script_dirent->d_name);
+ if (!script_root)
+ return NULL;
+
+ str = (char *)ends_with(script_root, suffix);
+ if (!str) {
+ free(script_root);
+ return NULL;
+ }
+
+ *str = '\0';
+ return script_root;
+}
+
static int list_available_scripts(const struct option *opt __used,
const char *s __used, int unset __used)
{
@@ -934,7 +955,6 @@
struct script_desc *desc;
char first_half[BUFSIZ];
char *script_root;
- char *str;
snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
@@ -950,16 +970,14 @@
continue;
for_each_script(lang_path, lang_dir, script_dirent, script_next) {
- script_root = strdup(script_dirent.d_name);
- str = (char *)ends_with(script_root, REPORT_SUFFIX);
- if (str) {
- *str = '\0';
+ script_root = get_script_root(&script_dirent, REPORT_SUFFIX);
+ if (script_root) {
desc = script_desc__findnew(script_root);
snprintf(script_path, MAXPATHLEN, "%s/%s",
lang_path, script_dirent.d_name);
read_script_info(desc, script_path);
+ free(script_root);
}
- free(script_root);
}
}
@@ -981,8 +999,7 @@
char script_path[MAXPATHLEN];
DIR *scripts_dir, *lang_dir;
char lang_path[MAXPATHLEN];
- char *str, *__script_root;
- char *path = NULL;
+ char *__script_root;
snprintf(scripts_path, MAXPATHLEN, "%s/scripts", perf_exec_path());
@@ -998,23 +1015,18 @@
continue;
for_each_script(lang_path, lang_dir, script_dirent, script_next) {
- __script_root = strdup(script_dirent.d_name);
- str = (char *)ends_with(__script_root, suffix);
- if (str) {
- *str = '\0';
- if (strcmp(__script_root, script_root))
- continue;
+ __script_root = get_script_root(&script_dirent, suffix);
+ if (__script_root && !strcmp(script_root, __script_root)) {
+ free(__script_root);
snprintf(script_path, MAXPATHLEN, "%s/%s",
lang_path, script_dirent.d_name);
- path = strdup(script_path);
- free(__script_root);
- break;
+ return strdup(script_path);
}
free(__script_root);
}
}
- return path;
+ return NULL;
}
static bool is_top_script(const char *script_path)
@@ -1083,7 +1095,11 @@
OPT_CALLBACK('f', "fields", NULL, "str",
"comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw. Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr",
parse_output_fields),
- OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+ OPT_BOOLEAN('a', "all-cpus", &system_wide,
+ "system-wide collection from all CPUs"),
+ OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+ OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
+ "only display events for these comms"),
OPT_BOOLEAN('I', "show-info", &show_full_info,
"display extended information from perf.data file"),
OPT_END()
@@ -1110,7 +1126,6 @@
struct perf_session *session;
char *script_path = NULL;
const char **__argv;
- bool system_wide;
int i, j, err;
setup_scripting();
@@ -1178,15 +1193,17 @@
}
if (!pid) {
- system_wide = true;
j = 0;
dup2(live_pipe[1], 1);
close(live_pipe[0]);
- if (!is_top_script(argv[0]))
+ if (is_top_script(argv[0])) {
+ system_wide = true;
+ } else if (!system_wide) {
system_wide = !have_cmd(argc - rep_args,
&argv[rep_args]);
+ }
__argv = malloc((argc + 6) * sizeof(const char *));
if (!__argv)
@@ -1234,10 +1251,11 @@
script_path = rep_script_path;
if (script_path) {
- system_wide = false;
j = 0;
- if (rec_script_path)
+ if (!rec_script_path)
+ system_wide = false;
+ else if (!system_wide)
system_wide = !have_cmd(argc - 1, &argv[1]);
__argv = malloc((argc + 2) * sizeof(const char *));
@@ -1261,7 +1279,7 @@
if (!script_name)
setup_pager();
- session = perf_session__new(input_name, O_RDONLY, 0, false, &event_ops);
+ session = perf_session__new(input_name, O_RDONLY, 0, false, &perf_script);
if (session == NULL)
return -ENOMEM;
@@ -1287,7 +1305,7 @@
return -1;
}
- input = open(input_name, O_RDONLY);
+ input = open(session->filename, O_RDONLY); /* input_name */
if (input < 0) {
perror("failed to open file");
exit(-1);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 955930e..f5d2a63 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -578,6 +578,33 @@
avg / avg_stats(&walltime_nsecs_stats));
}
+/* used for get_ratio_color() */
+enum grc_type {
+ GRC_STALLED_CYCLES_FE,
+ GRC_STALLED_CYCLES_BE,
+ GRC_CACHE_MISSES,
+ GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+ static const double grc_table[GRC_MAX_NR][3] = {
+ [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+ [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+ [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 },
+ };
+ const char *color = PERF_COLOR_NORMAL;
+
+ if (ratio > grc_table[type][0])
+ color = PERF_COLOR_RED;
+ else if (ratio > grc_table[type][1])
+ color = PERF_COLOR_MAGENTA;
+ else if (ratio > grc_table[type][2])
+ color = PERF_COLOR_YELLOW;
+
+ return color;
+}
+
static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
@@ -588,13 +615,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 50.0)
- color = PERF_COLOR_RED;
- else if (ratio > 30.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 10.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -611,13 +632,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 75.0)
- color = PERF_COLOR_RED;
- else if (ratio > 50.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 20.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -634,13 +649,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 20.0)
- color = PERF_COLOR_RED;
- else if (ratio > 10.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -657,13 +666,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 20.0)
- color = PERF_COLOR_RED;
- else if (ratio > 10.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -680,13 +683,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 20.0)
- color = PERF_COLOR_RED;
- else if (ratio > 10.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -703,13 +700,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 20.0)
- color = PERF_COLOR_RED;
- else if (ratio > 10.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -726,13 +717,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 20.0)
- color = PERF_COLOR_RED;
- else if (ratio > 10.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -749,13 +734,7 @@
if (total)
ratio = avg / total * 100.0;
- color = PERF_COLOR_NORMAL;
- if (ratio > 20.0)
- color = PERF_COLOR_RED;
- else if (ratio > 10.0)
- color = PERF_COLOR_MAGENTA;
- else if (ratio > 5.0)
- color = PERF_COLOR_YELLOW;
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
@@ -1108,22 +1087,13 @@
*/
static int add_default_attributes(void)
{
- struct perf_evsel *pos;
- size_t attr_nr = 0;
- size_t c;
-
/* Set attrs if no event is selected and !null_run: */
if (null_run)
return 0;
if (!evsel_list->nr_entries) {
- for (c = 0; c < ARRAY_SIZE(default_attrs); c++) {
- pos = perf_evsel__new(default_attrs + c, c + attr_nr);
- if (pos == NULL)
- return -1;
- perf_evlist__add(evsel_list, pos);
- }
- attr_nr += c;
+ if (perf_evlist__add_attrs_array(evsel_list, default_attrs) < 0)
+ return -1;
}
/* Detailed events get appended to the event list: */
@@ -1132,38 +1102,21 @@
return 0;
/* Append detailed run extra attributes: */
- for (c = 0; c < ARRAY_SIZE(detailed_attrs); c++) {
- pos = perf_evsel__new(detailed_attrs + c, c + attr_nr);
- if (pos == NULL)
- return -1;
- perf_evlist__add(evsel_list, pos);
- }
- attr_nr += c;
+ if (perf_evlist__add_attrs_array(evsel_list, detailed_attrs) < 0)
+ return -1;
if (detailed_run < 2)
return 0;
/* Append very detailed run extra attributes: */
- for (c = 0; c < ARRAY_SIZE(very_detailed_attrs); c++) {
- pos = perf_evsel__new(very_detailed_attrs + c, c + attr_nr);
- if (pos == NULL)
- return -1;
- perf_evlist__add(evsel_list, pos);
- }
+ if (perf_evlist__add_attrs_array(evsel_list, very_detailed_attrs) < 0)
+ return -1;
if (detailed_run < 3)
return 0;
/* Append very, very detailed run extra attributes: */
- for (c = 0; c < ARRAY_SIZE(very_very_detailed_attrs); c++) {
- pos = perf_evsel__new(very_very_detailed_attrs + c, c + attr_nr);
- if (pos == NULL)
- return -1;
- perf_evlist__add(evsel_list, pos);
- }
-
-
- return 0;
+ return perf_evlist__add_attrs_array(evsel_list, very_very_detailed_attrs);
}
int cmd_stat(int argc, const char **argv, const char *prefix __used)
@@ -1267,8 +1220,7 @@
list_for_each_entry(pos, &evsel_list->entries, node) {
if (perf_evsel__alloc_stat_priv(pos) < 0 ||
- perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0 ||
- perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, evsel_list->threads->nr) < 0)
+ perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0)
goto out_free_fd;
}
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 831d1ba..2b9a7f4 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -7,6 +7,7 @@
#include "util/cache.h"
#include "util/debug.h"
+#include "util/debugfs.h"
#include "util/evlist.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
@@ -14,8 +15,6 @@
#include "util/thread_map.h"
#include "../../include/linux/hw_breakpoint.h"
-static long page_size;
-
static int vmlinux_matches_kallsyms_filter(struct map *map __used, struct symbol *sym)
{
bool *visited = symbol__priv(sym);
@@ -31,6 +30,7 @@
struct map *kallsyms_map, *vmlinux_map;
struct machine kallsyms, vmlinux;
enum map_type type = MAP__FUNCTION;
+ long page_size = sysconf(_SC_PAGE_SIZE);
struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
/*
@@ -247,7 +247,7 @@
if (asprintf(&filename,
"%s/syscalls/%s/id",
- debugfs_path, evname) < 0)
+ tracing_events_path, evname) < 0)
return -1;
fd = open(filename, O_RDONLY);
@@ -603,7 +603,7 @@
#define TEST_ASSERT_VAL(text, cond) \
do { \
- if (!cond) { \
+ if (!(cond)) { \
pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
return -1; \
} \
@@ -759,6 +759,103 @@
return 0;
}
+static int test__checkevent_tracepoint_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ 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);
+
+ return test__checkevent_tracepoint(evlist);
+}
+
+static int
+test__checkevent_tracepoint_multi_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel;
+
+ TEST_ASSERT_VAL("wrong number of entries", evlist->nr_entries > 1);
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ 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);
+ }
+
+ return test__checkevent_tracepoint_multi(evlist);
+}
+
+static int test__checkevent_raw_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ 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);
+
+ return test__checkevent_raw(evlist);
+}
+
+static int test__checkevent_numeric_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ 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);
+
+ return test__checkevent_numeric(evlist);
+}
+
+static int test__checkevent_symbolic_name_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ 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);
+
+ return test__checkevent_symbolic_name(evlist);
+}
+
+static int test__checkevent_symbolic_alias_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ 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);
+
+ return test__checkevent_symbolic_alias(evlist);
+}
+
+static int test__checkevent_genhw_modifier(struct perf_evlist *evlist)
+{
+ struct perf_evsel *evsel = list_entry(evlist->entries.next,
+ struct perf_evsel, node);
+
+ 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);
+
+ return test__checkevent_genhw(evlist);
+}
+
static struct test__event_st {
const char *name;
__u32 type;
@@ -808,6 +905,34 @@
.name = "mem:0:w",
.check = test__checkevent_breakpoint_w,
},
+ {
+ .name = "syscalls:sys_enter_open:k",
+ .check = test__checkevent_tracepoint_modifier,
+ },
+ {
+ .name = "syscalls:*:u",
+ .check = test__checkevent_tracepoint_multi_modifier,
+ },
+ {
+ .name = "r1:kp",
+ .check = test__checkevent_raw_modifier,
+ },
+ {
+ .name = "1:1:hp",
+ .check = test__checkevent_numeric_modifier,
+ },
+ {
+ .name = "instructions:h",
+ .check = test__checkevent_symbolic_name_modifier,
+ },
+ {
+ .name = "faults:u",
+ .check = test__checkevent_symbolic_alias_modifier,
+ },
+ {
+ .name = "L1-dcache-load-miss:kp",
+ .check = test__checkevent_genhw_modifier,
+ },
};
#define TEST__EVENTS_CNT (sizeof(test__events) / sizeof(struct test__event_st))
@@ -841,6 +966,336 @@
return ret;
}
+
+static int sched__get_first_possible_cpu(pid_t pid, cpu_set_t **maskp,
+ size_t *sizep)
+{
+ cpu_set_t *mask;
+ size_t size;
+ int i, cpu = -1, nrcpus = 1024;
+realloc:
+ mask = CPU_ALLOC(nrcpus);
+ size = CPU_ALLOC_SIZE(nrcpus);
+ CPU_ZERO_S(size, mask);
+
+ if (sched_getaffinity(pid, size, mask) == -1) {
+ CPU_FREE(mask);
+ if (errno == EINVAL && nrcpus < (1024 << 8)) {
+ nrcpus = nrcpus << 2;
+ goto realloc;
+ }
+ perror("sched_getaffinity");
+ return -1;
+ }
+
+ for (i = 0; i < nrcpus; i++) {
+ if (CPU_ISSET_S(i, size, mask)) {
+ if (cpu == -1) {
+ cpu = i;
+ *maskp = mask;
+ *sizep = size;
+ } else
+ CPU_CLR_S(i, size, mask);
+ }
+ }
+
+ if (cpu == -1)
+ CPU_FREE(mask);
+
+ return cpu;
+}
+
+static int test__PERF_RECORD(void)
+{
+ struct perf_record_opts opts = {
+ .target_pid = -1,
+ .target_tid = -1,
+ .no_delay = true,
+ .freq = 10,
+ .mmap_pages = 256,
+ .sample_id_all_avail = true,
+ };
+ cpu_set_t *cpu_mask = NULL;
+ size_t cpu_mask_size = 0;
+ struct perf_evlist *evlist = perf_evlist__new(NULL, NULL);
+ struct perf_evsel *evsel;
+ struct perf_sample sample;
+ const char *cmd = "sleep";
+ const char *argv[] = { cmd, "1", NULL, };
+ char *bname;
+ u64 sample_type, prev_time = 0;
+ bool found_cmd_mmap = false,
+ found_libc_mmap = false,
+ found_vdso_mmap = false,
+ found_ld_mmap = false;
+ int err = -1, errs = 0, i, wakeups = 0, sample_size;
+ u32 cpu;
+ int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+
+ if (evlist == NULL || argv == NULL) {
+ pr_debug("Not enough memory to create evlist\n");
+ goto out;
+ }
+
+ /*
+ * We need at least one evsel in the evlist, use the default
+ * one: "cycles".
+ */
+ err = perf_evlist__add_default(evlist);
+ if (err < 0) {
+ pr_debug("Not enough memory to create evsel\n");
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Create maps of threads and cpus to monitor. In this case
+ * we start with all threads and cpus (-1, -1) but then in
+ * perf_evlist__prepare_workload we'll fill in the only thread
+ * we're monitoring, the one forked there.
+ */
+ err = perf_evlist__create_maps(evlist, opts.target_pid,
+ opts.target_tid, opts.cpu_list);
+ if (err < 0) {
+ pr_debug("Not enough memory to create thread/cpu maps\n");
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Prepare the workload in argv[] to run, it'll fork it, and then wait
+ * for perf_evlist__start_workload() to exec it. This is done this way
+ * so that we have time to open the evlist (calling sys_perf_event_open
+ * on all the fds) and then mmap them.
+ */
+ err = perf_evlist__prepare_workload(evlist, &opts, argv);
+ if (err < 0) {
+ pr_debug("Couldn't run the workload!\n");
+ goto out_delete_evlist;
+ }
+
+ /*
+ * Config the evsels, setting attr->comm on the first one, etc.
+ */
+ evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
+ evsel->attr.sample_type |= PERF_SAMPLE_CPU;
+ evsel->attr.sample_type |= PERF_SAMPLE_TID;
+ evsel->attr.sample_type |= PERF_SAMPLE_TIME;
+ perf_evlist__config_attrs(evlist, &opts);
+
+ err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask,
+ &cpu_mask_size);
+ if (err < 0) {
+ pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ cpu = err;
+
+ /*
+ * So that we can check perf_sample.cpu on all the samples.
+ */
+ if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, cpu_mask) < 0) {
+ pr_debug("sched_setaffinity: %s\n", strerror(errno));
+ goto out_free_cpu_mask;
+ }
+
+ /*
+ * 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);
+ if (err < 0) {
+ pr_debug("perf_evlist__open: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ /*
+ * mmap the first fd on a given CPU and ask for events for the other
+ * fds in the same CPU to be injected in the same mmap ring buffer
+ * (using ioctl(PERF_EVENT_IOC_SET_OUTPUT)).
+ */
+ err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+ if (err < 0) {
+ pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+ goto out_delete_evlist;
+ }
+
+ /*
+ * We'll need these two to parse the PERF_SAMPLE_* fields in each
+ * event.
+ */
+ sample_type = perf_evlist__sample_type(evlist);
+ sample_size = __perf_evsel__sample_size(sample_type);
+
+ /*
+ * Now that all is properly set up, enable the events, they will
+ * count just on workload.pid, which will start...
+ */
+ perf_evlist__enable(evlist);
+
+ /*
+ * Now!
+ */
+ perf_evlist__start_workload(evlist);
+
+ while (1) {
+ int before = total_events;
+
+ for (i = 0; i < evlist->nr_mmaps; i++) {
+ union perf_event *event;
+
+ while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+ const u32 type = event->header.type;
+ const char *name = perf_event__name(type);
+
+ ++total_events;
+ if (type < PERF_RECORD_MAX)
+ nr_events[type]++;
+
+ err = perf_event__parse_sample(event, sample_type,
+ sample_size, true,
+ &sample, false);
+ if (err < 0) {
+ if (verbose)
+ perf_event__fprintf(event, stderr);
+ pr_debug("Couldn't parse sample\n");
+ goto out_err;
+ }
+
+ if (verbose) {
+ pr_info("%" PRIu64" %d ", sample.time, sample.cpu);
+ perf_event__fprintf(event, stderr);
+ }
+
+ if (prev_time > sample.time) {
+ pr_debug("%s going backwards in time, prev=%" PRIu64 ", curr=%" PRIu64 "\n",
+ name, prev_time, sample.time);
+ ++errs;
+ }
+
+ prev_time = sample.time;
+
+ if (sample.cpu != cpu) {
+ pr_debug("%s with unexpected cpu, expected %d, got %d\n",
+ name, cpu, sample.cpu);
+ ++errs;
+ }
+
+ if ((pid_t)sample.pid != evlist->workload.pid) {
+ pr_debug("%s with unexpected pid, expected %d, got %d\n",
+ name, evlist->workload.pid, sample.pid);
+ ++errs;
+ }
+
+ if ((pid_t)sample.tid != evlist->workload.pid) {
+ pr_debug("%s with unexpected tid, expected %d, got %d\n",
+ name, evlist->workload.pid, sample.tid);
+ ++errs;
+ }
+
+ if ((type == PERF_RECORD_COMM ||
+ type == PERF_RECORD_MMAP ||
+ type == PERF_RECORD_FORK ||
+ type == PERF_RECORD_EXIT) &&
+ (pid_t)event->comm.pid != evlist->workload.pid) {
+ pr_debug("%s with unexpected pid/tid\n", name);
+ ++errs;
+ }
+
+ if ((type == PERF_RECORD_COMM ||
+ type == PERF_RECORD_MMAP) &&
+ event->comm.pid != event->comm.tid) {
+ pr_debug("%s with different pid/tid!\n", name);
+ ++errs;
+ }
+
+ switch (type) {
+ case PERF_RECORD_COMM:
+ if (strcmp(event->comm.comm, cmd)) {
+ pr_debug("%s with unexpected comm!\n", name);
+ ++errs;
+ }
+ break;
+ case PERF_RECORD_EXIT:
+ goto found_exit;
+ case PERF_RECORD_MMAP:
+ bname = strrchr(event->mmap.filename, '/');
+ if (bname != NULL) {
+ if (!found_cmd_mmap)
+ found_cmd_mmap = !strcmp(bname + 1, cmd);
+ if (!found_libc_mmap)
+ found_libc_mmap = !strncmp(bname + 1, "libc", 4);
+ if (!found_ld_mmap)
+ found_ld_mmap = !strncmp(bname + 1, "ld", 2);
+ } else if (!found_vdso_mmap)
+ found_vdso_mmap = !strcmp(event->mmap.filename, "[vdso]");
+ break;
+
+ case PERF_RECORD_SAMPLE:
+ /* Just ignore samples for now */
+ break;
+ default:
+ pr_debug("Unexpected perf_event->header.type %d!\n",
+ type);
+ ++errs;
+ }
+ }
+ }
+
+ /*
+ * We don't use poll here because at least at 3.1 times the
+ * PERF_RECORD_{!SAMPLE} events don't honour
+ * perf_event_attr.wakeup_events, just PERF_EVENT_SAMPLE does.
+ */
+ if (total_events == before && false)
+ poll(evlist->pollfd, evlist->nr_fds, -1);
+
+ sleep(1);
+ if (++wakeups > 5) {
+ pr_debug("No PERF_RECORD_EXIT event!\n");
+ break;
+ }
+ }
+
+found_exit:
+ if (nr_events[PERF_RECORD_COMM] > 1) {
+ pr_debug("Excessive number of PERF_RECORD_COMM events!\n");
+ ++errs;
+ }
+
+ if (nr_events[PERF_RECORD_COMM] == 0) {
+ pr_debug("Missing PERF_RECORD_COMM for %s!\n", cmd);
+ ++errs;
+ }
+
+ if (!found_cmd_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", cmd);
+ ++errs;
+ }
+
+ if (!found_libc_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", "libc");
+ ++errs;
+ }
+
+ if (!found_ld_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", "ld");
+ ++errs;
+ }
+
+ if (!found_vdso_mmap) {
+ pr_debug("PERF_RECORD_MMAP for %s missing!\n", "[vdso]");
+ ++errs;
+ }
+out_err:
+ perf_evlist__munmap(evlist);
+out_free_cpu_mask:
+ CPU_FREE(cpu_mask);
+out_delete_evlist:
+ perf_evlist__delete(evlist);
+out:
+ return (err < 0 || errs > 0) ? -1 : 0;
+}
+
static struct test {
const char *desc;
int (*func)(void);
@@ -866,45 +1321,89 @@
.func = test__parse_events,
},
{
+ .desc = "Validate PERF_RECORD_* events & perf_sample fields",
+ .func = test__PERF_RECORD,
+ },
+ {
.func = NULL,
},
};
-static int __cmd_test(void)
+static bool perf_test__matches(int curr, int argc, const char *argv[])
+{
+ int i;
+
+ if (argc == 0)
+ return true;
+
+ for (i = 0; i < argc; ++i) {
+ char *end;
+ long nr = strtoul(argv[i], &end, 10);
+
+ if (*end == '\0') {
+ if (nr == curr + 1)
+ return true;
+ continue;
+ }
+
+ if (strstr(tests[curr].desc, argv[i]))
+ return true;
+ }
+
+ return false;
+}
+
+static int __cmd_test(int argc, const char *argv[])
{
int i = 0;
- page_size = sysconf(_SC_PAGE_SIZE);
-
while (tests[i].func) {
- int err;
- pr_info("%2d: %s:", i + 1, tests[i].desc);
+ int curr = i++, err;
+
+ if (!perf_test__matches(curr, argc, argv))
+ continue;
+
+ pr_info("%2d: %s:", i, tests[curr].desc);
pr_debug("\n--- start ---\n");
- err = tests[i].func();
- pr_debug("---- end ----\n%s:", tests[i].desc);
+ err = tests[curr].func();
+ pr_debug("---- end ----\n%s:", tests[curr].desc);
pr_info(" %s\n", err ? "FAILED!\n" : "Ok");
- ++i;
}
return 0;
}
-static const char * const test_usage[] = {
- "perf test [<options>]",
- NULL,
-};
+static int perf_test__list(int argc, const char **argv)
+{
+ int i = 0;
-static const struct option test_options[] = {
- OPT_INTEGER('v', "verbose", &verbose,
- "be more verbose (show symbol address, etc)"),
- OPT_END()
-};
+ while (tests[i].func) {
+ int curr = i++;
+
+ if (argc > 1 && !strstr(tests[curr].desc, argv[1]))
+ continue;
+
+ pr_info("%2d: %s\n", i, tests[curr].desc);
+ }
+
+ return 0;
+}
int cmd_test(int argc, const char **argv, const char *prefix __used)
{
+ const char * const test_usage[] = {
+ "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
+ NULL,
+ };
+ const struct option test_options[] = {
+ OPT_INTEGER('v', "verbose", &verbose,
+ "be more verbose (show symbol address, etc)"),
+ OPT_END()
+ };
+
argc = parse_options(argc, argv, test_options, test_usage, 0);
- if (argc)
- usage_with_options(test_usage, test_options);
+ if (argc >= 1 && !strcmp(argv[0], "list"))
+ return perf_test__list(argc, argv);
symbol_conf.priv_size = sizeof(int);
symbol_conf.sort_by_name = true;
@@ -915,5 +1414,5 @@
setup_pager();
- return __cmd_test();
+ return __cmd_test(argc, argv);
}
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index aa26f4d..3b75b2e 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -19,6 +19,7 @@
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
+#include "util/evsel.h"
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "util/callchain.h"
@@ -31,13 +32,14 @@
#include "util/event.h"
#include "util/session.h"
#include "util/svghelper.h"
+#include "util/tool.h"
#define SUPPORT_OLD_POWER_EVENTS 1
#define PWR_EVENT_EXIT -1
-static char const *input_name = "perf.data";
-static char const *output_name = "output.svg";
+static const char *input_name;
+static const char *output_name = "output.svg";
static unsigned int numcpus;
static u64 min_freq; /* Lowest CPU frequency seen */
@@ -273,25 +275,28 @@
static u64 cpus_pstate_start_times[MAX_CPUS];
static u64 cpus_pstate_state[MAX_CPUS];
-static int process_comm_event(union perf_event *event,
+static int process_comm_event(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *session __used)
+ struct machine *machine __used)
{
pid_set_comm(event->comm.tid, event->comm.comm);
return 0;
}
-static int process_fork_event(union perf_event *event,
+static int process_fork_event(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *session __used)
+ struct machine *machine __used)
{
pid_fork(event->fork.pid, event->fork.ppid, event->fork.time);
return 0;
}
-static int process_exit_event(union perf_event *event,
+static int process_exit_event(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *session __used)
+ struct machine *machine __used)
{
pid_exit(event->fork.pid, event->fork.time);
return 0;
@@ -486,14 +491,15 @@
}
-static int process_sample_event(union perf_event *event __used,
+static int process_sample_event(struct perf_tool *tool __used,
+ union perf_event *event __used,
struct perf_sample *sample,
- struct perf_evsel *evsel __used,
- struct perf_session *session)
+ struct perf_evsel *evsel,
+ struct machine *machine __used)
{
struct trace_entry *te;
- if (session->sample_type & PERF_SAMPLE_TIME) {
+ if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
if (!first_time || first_time > sample->time)
first_time = sample->time;
if (last_time < sample->time)
@@ -501,7 +507,7 @@
}
te = (void *)sample->raw_data;
- if (session->sample_type & PERF_SAMPLE_RAW && sample->raw_size > 0) {
+ if ((evsel->attr.sample_type & PERF_SAMPLE_RAW) && sample->raw_size > 0) {
char *event_str;
#ifdef SUPPORT_OLD_POWER_EVENTS
struct power_entry_old *peo;
@@ -974,7 +980,7 @@
svg_close();
}
-static struct perf_event_ops event_ops = {
+static struct perf_tool perf_timechart = {
.comm = process_comm_event,
.fork = process_fork_event,
.exit = process_exit_event,
@@ -985,7 +991,7 @@
static int __cmd_timechart(void)
{
struct perf_session *session = perf_session__new(input_name, O_RDONLY,
- 0, false, &event_ops);
+ 0, false, &perf_timechart);
int ret = -EINVAL;
if (session == NULL)
@@ -994,7 +1000,7 @@
if (!perf_session__has_traces(session, "timechart record"))
goto out_delete;
- ret = perf_session__process_events(session, &event_ops);
+ ret = perf_session__process_events(session, &perf_timechart);
if (ret)
goto out_delete;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c9cdedb..4f81eeb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -64,44 +64,6 @@
#include <linux/unistd.h>
#include <linux/types.h>
-static struct perf_top top = {
- .count_filter = 5,
- .delay_secs = 2,
- .target_pid = -1,
- .target_tid = -1,
- .freq = 1000, /* 1 KHz */
-};
-
-static bool system_wide = false;
-
-static bool use_tui, use_stdio;
-
-static bool sort_has_symbols;
-
-static bool dont_use_callchains;
-static char callchain_default_opt[] = "fractal,0.5,callee";
-
-
-static int default_interval = 0;
-
-static bool kptr_restrict_warned;
-static bool vmlinux_warned;
-static bool inherit = false;
-static int realtime_prio = 0;
-static bool group = false;
-static bool sample_id_all_avail = true;
-static unsigned int mmap_pages = 128;
-
-static bool dump_symtab = false;
-
-static struct winsize winsize;
-
-static const char *sym_filter = NULL;
-static int sym_pcnt_filter = 5;
-
-/*
- * Source functions
- */
void get_term_dimensions(struct winsize *ws)
{
@@ -125,21 +87,23 @@
ws->ws_col = 80;
}
-static void update_print_entries(struct winsize *ws)
+static void perf_top__update_print_entries(struct perf_top *top)
{
- top.print_entries = ws->ws_row;
+ top->print_entries = top->winsize.ws_row;
- if (top.print_entries > 9)
- top.print_entries -= 9;
+ if (top->print_entries > 9)
+ top->print_entries -= 9;
}
-static void sig_winch_handler(int sig __used)
+static void perf_top__sig_winch(int sig __used, siginfo_t *info __used, void *arg)
{
- get_term_dimensions(&winsize);
- update_print_entries(&winsize);
+ struct perf_top *top = arg;
+
+ get_term_dimensions(&top->winsize);
+ perf_top__update_print_entries(top);
}
-static int parse_source(struct hist_entry *he)
+static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
{
struct symbol *sym;
struct annotation *notes;
@@ -170,7 +134,7 @@
pthread_mutex_lock(¬es->lock);
- if (symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
+ if (symbol__alloc_hist(sym) < 0) {
pthread_mutex_unlock(¬es->lock);
pr_err("Not enough memory for annotating '%s' symbol!\n",
sym->name);
@@ -181,7 +145,7 @@
err = symbol__annotate(sym, map, 0);
if (err == 0) {
out_assign:
- top.sym_filter_entry = he;
+ top->sym_filter_entry = he;
}
pthread_mutex_unlock(¬es->lock);
@@ -194,14 +158,16 @@
symbol__annotate_zero_histograms(sym);
}
-static void record_precise_ip(struct hist_entry *he, int counter, u64 ip)
+static void perf_top__record_precise_ip(struct perf_top *top,
+ struct hist_entry *he,
+ int counter, u64 ip)
{
struct annotation *notes;
struct symbol *sym;
if (he == NULL || he->ms.sym == NULL ||
- ((top.sym_filter_entry == NULL ||
- top.sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
+ ((top->sym_filter_entry == NULL ||
+ top->sym_filter_entry->ms.sym != he->ms.sym) && use_browser != 1))
return;
sym = he->ms.sym;
@@ -210,8 +176,7 @@
if (pthread_mutex_trylock(¬es->lock))
return;
- if (notes->src == NULL &&
- symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
+ if (notes->src == NULL && symbol__alloc_hist(sym) < 0) {
pthread_mutex_unlock(¬es->lock);
pr_err("Not enough memory for annotating '%s' symbol!\n",
sym->name);
@@ -225,8 +190,9 @@
pthread_mutex_unlock(¬es->lock);
}
-static void show_details(struct hist_entry *he)
+static void perf_top__show_details(struct perf_top *top)
{
+ struct hist_entry *he = top->sym_filter_entry;
struct annotation *notes;
struct symbol *symbol;
int more;
@@ -242,15 +208,15 @@
if (notes->src == NULL)
goto out_unlock;
- printf("Showing %s for %s\n", event_name(top.sym_evsel), symbol->name);
- printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter);
+ printf("Showing %s for %s\n", event_name(top->sym_evsel), symbol->name);
+ printf(" Events Pcnt (>=%d%%)\n", top->sym_pcnt_filter);
- more = symbol__annotate_printf(symbol, he->ms.map, top.sym_evsel->idx,
- 0, sym_pcnt_filter, top.print_entries, 4);
- if (top.zero)
- symbol__annotate_zero_histogram(symbol, top.sym_evsel->idx);
+ more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel->idx,
+ 0, top->sym_pcnt_filter, top->print_entries, 4);
+ if (top->zero)
+ symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
else
- symbol__annotate_decay_histogram(symbol, top.sym_evsel->idx);
+ symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
if (more != 0)
printf("%d lines not displayed, maybe increase display entries [e]\n", more);
out_unlock:
@@ -259,11 +225,9 @@
static const char CONSOLE_CLEAR[] = "[H[2J";
-static struct hist_entry *
- perf_session__add_hist_entry(struct perf_session *session,
- struct addr_location *al,
- struct perf_sample *sample,
- struct perf_evsel *evsel)
+static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
+ struct addr_location *al,
+ struct perf_sample *sample)
{
struct hist_entry *he;
@@ -271,50 +235,51 @@
if (he == NULL)
return NULL;
- session->hists.stats.total_period += sample->period;
+ evsel->hists.stats.total_period += sample->period;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
return he;
}
-static void print_sym_table(void)
+static void perf_top__print_sym_table(struct perf_top *top)
{
char bf[160];
int printed = 0;
- const int win_width = winsize.ws_col - 1;
+ const int win_width = top->winsize.ws_col - 1;
puts(CONSOLE_CLEAR);
- perf_top__header_snprintf(&top, bf, sizeof(bf));
+ perf_top__header_snprintf(top, bf, sizeof(bf));
printf("%s\n", bf);
- perf_top__reset_sample_counters(&top);
+ perf_top__reset_sample_counters(top);
printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
- if (top.sym_evsel->hists.stats.nr_lost_warned !=
- top.sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
- top.sym_evsel->hists.stats.nr_lost_warned =
- top.sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
+ if (top->sym_evsel->hists.stats.nr_lost_warned !=
+ top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST]) {
+ top->sym_evsel->hists.stats.nr_lost_warned =
+ top->sym_evsel->hists.stats.nr_events[PERF_RECORD_LOST];
color_fprintf(stdout, PERF_COLOR_RED,
"WARNING: LOST %d chunks, Check IO/CPU overload",
- top.sym_evsel->hists.stats.nr_lost_warned);
+ top->sym_evsel->hists.stats.nr_lost_warned);
++printed;
}
- if (top.sym_filter_entry) {
- show_details(top.sym_filter_entry);
+ if (top->sym_filter_entry) {
+ perf_top__show_details(top);
return;
}
- hists__collapse_resort_threaded(&top.sym_evsel->hists);
- hists__output_resort_threaded(&top.sym_evsel->hists);
- hists__decay_entries_threaded(&top.sym_evsel->hists,
- top.hide_user_symbols,
- top.hide_kernel_symbols);
- hists__output_recalc_col_len(&top.sym_evsel->hists, winsize.ws_row - 3);
+ hists__collapse_resort_threaded(&top->sym_evsel->hists);
+ hists__output_resort_threaded(&top->sym_evsel->hists);
+ hists__decay_entries_threaded(&top->sym_evsel->hists,
+ top->hide_user_symbols,
+ top->hide_kernel_symbols);
+ hists__output_recalc_col_len(&top->sym_evsel->hists,
+ top->winsize.ws_row - 3);
putchar('\n');
- hists__fprintf(&top.sym_evsel->hists, NULL, false, false,
- winsize.ws_row - 4 - printed, win_width, stdout);
+ hists__fprintf(&top->sym_evsel->hists, NULL, false, false,
+ top->winsize.ws_row - 4 - printed, win_width, stdout);
}
static void prompt_integer(int *target, const char *msg)
@@ -352,17 +317,17 @@
*target = tmp;
}
-static void prompt_symbol(struct hist_entry **target, const char *msg)
+static void perf_top__prompt_symbol(struct perf_top *top, const char *msg)
{
char *buf = malloc(0), *p;
- struct hist_entry *syme = *target, *n, *found = NULL;
+ struct hist_entry *syme = top->sym_filter_entry, *n, *found = NULL;
struct rb_node *next;
size_t dummy = 0;
/* zero counters of active symbol */
if (syme) {
__zero_source_counters(syme);
- *target = NULL;
+ top->sym_filter_entry = NULL;
}
fprintf(stdout, "\n%s: ", msg);
@@ -373,7 +338,7 @@
if (p)
*p = 0;
- next = rb_first(&top.sym_evsel->hists.entries);
+ next = rb_first(&top->sym_evsel->hists.entries);
while (next) {
n = rb_entry(next, struct hist_entry, rb_node);
if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {
@@ -386,47 +351,46 @@
if (!found) {
fprintf(stderr, "Sorry, %s is not active.\n", buf);
sleep(1);
- return;
} else
- parse_source(found);
+ perf_top__parse_source(top, found);
out_free:
free(buf);
}
-static void print_mapped_keys(void)
+static void perf_top__print_mapped_keys(struct perf_top *top)
{
char *name = NULL;
- if (top.sym_filter_entry) {
- struct symbol *sym = top.sym_filter_entry->ms.sym;
+ if (top->sym_filter_entry) {
+ struct symbol *sym = top->sym_filter_entry->ms.sym;
name = sym->name;
}
fprintf(stdout, "\nMapped keys:\n");
- fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top.delay_secs);
- fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top.print_entries);
+ fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top->delay_secs);
+ fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top->print_entries);
- if (top.evlist->nr_entries > 1)
- fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top.sym_evsel));
+ if (top->evlist->nr_entries > 1)
+ fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top->sym_evsel));
- fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top.count_filter);
+ fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top->count_filter);
- fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
+ fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", top->sym_pcnt_filter);
fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL");
fprintf(stdout, "\t[S] stop annotation.\n");
fprintf(stdout,
"\t[K] hide kernel_symbols symbols. \t(%s)\n",
- top.hide_kernel_symbols ? "yes" : "no");
+ top->hide_kernel_symbols ? "yes" : "no");
fprintf(stdout,
"\t[U] hide user symbols. \t(%s)\n",
- top.hide_user_symbols ? "yes" : "no");
- fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", top.zero ? 1 : 0);
+ top->hide_user_symbols ? "yes" : "no");
+ fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", top->zero ? 1 : 0);
fprintf(stdout, "\t[qQ] quit.\n");
}
-static int key_mapped(int c)
+static int perf_top__key_mapped(struct perf_top *top, int c)
{
switch (c) {
case 'd':
@@ -442,7 +406,7 @@
case 'S':
return 1;
case 'E':
- return top.evlist->nr_entries > 1 ? 1 : 0;
+ return top->evlist->nr_entries > 1 ? 1 : 0;
default:
break;
}
@@ -450,13 +414,13 @@
return 0;
}
-static void handle_keypress(int c)
+static void perf_top__handle_keypress(struct perf_top *top, int c)
{
- if (!key_mapped(c)) {
+ if (!perf_top__key_mapped(top, c)) {
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
struct termios tc, save;
- print_mapped_keys();
+ perf_top__print_mapped_keys(top);
fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
fflush(stdout);
@@ -471,81 +435,86 @@
c = getc(stdin);
tcsetattr(0, TCSAFLUSH, &save);
- if (!key_mapped(c))
+ if (!perf_top__key_mapped(top, c))
return;
}
switch (c) {
case 'd':
- prompt_integer(&top.delay_secs, "Enter display delay");
- if (top.delay_secs < 1)
- top.delay_secs = 1;
+ prompt_integer(&top->delay_secs, "Enter display delay");
+ if (top->delay_secs < 1)
+ top->delay_secs = 1;
break;
case 'e':
- prompt_integer(&top.print_entries, "Enter display entries (lines)");
- if (top.print_entries == 0) {
- sig_winch_handler(SIGWINCH);
- signal(SIGWINCH, sig_winch_handler);
+ prompt_integer(&top->print_entries, "Enter display entries (lines)");
+ if (top->print_entries == 0) {
+ struct sigaction act = {
+ .sa_sigaction = perf_top__sig_winch,
+ .sa_flags = SA_SIGINFO,
+ };
+ perf_top__sig_winch(SIGWINCH, NULL, top);
+ sigaction(SIGWINCH, &act, NULL);
} else
signal(SIGWINCH, SIG_DFL);
break;
case 'E':
- if (top.evlist->nr_entries > 1) {
+ if (top->evlist->nr_entries > 1) {
/* Select 0 as the default event: */
int counter = 0;
fprintf(stderr, "\nAvailable events:");
- list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
- fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel));
+ list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+ fprintf(stderr, "\n\t%d %s", top->sym_evsel->idx, event_name(top->sym_evsel));
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);
- fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel));
+ if (counter >= top->evlist->nr_entries) {
+ top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node);
+ fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top->sym_evsel));
sleep(1);
break;
}
- list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
- if (top.sym_evsel->idx == counter)
+ list_for_each_entry(top->sym_evsel, &top->evlist->entries, node)
+ if (top->sym_evsel->idx == counter)
break;
} else
- top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
+ top->sym_evsel = list_entry(top->evlist->entries.next, struct perf_evsel, node);
break;
case 'f':
- prompt_integer(&top.count_filter, "Enter display event count filter");
+ prompt_integer(&top->count_filter, "Enter display event count filter");
break;
case 'F':
- prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)");
+ prompt_percent(&top->sym_pcnt_filter,
+ "Enter details display event filter (percent)");
break;
case 'K':
- top.hide_kernel_symbols = !top.hide_kernel_symbols;
+ top->hide_kernel_symbols = !top->hide_kernel_symbols;
break;
case 'q':
case 'Q':
printf("exiting.\n");
- if (dump_symtab)
- perf_session__fprintf_dsos(top.session, stderr);
+ if (top->dump_symtab)
+ perf_session__fprintf_dsos(top->session, stderr);
exit(0);
case 's':
- prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
+ perf_top__prompt_symbol(top, "Enter details symbol");
break;
case 'S':
- if (!top.sym_filter_entry)
+ if (!top->sym_filter_entry)
break;
else {
- struct hist_entry *syme = top.sym_filter_entry;
+ struct hist_entry *syme = top->sym_filter_entry;
- top.sym_filter_entry = NULL;
+ top->sym_filter_entry = NULL;
__zero_source_counters(syme);
}
break;
case 'U':
- top.hide_user_symbols = !top.hide_user_symbols;
+ top->hide_user_symbols = !top->hide_user_symbols;
break;
case 'z':
- top.zero = !top.zero;
+ top->zero = !top->zero;
break;
default:
break;
@@ -563,28 +532,30 @@
hists__collapse_resort_threaded(&t->sym_evsel->hists);
hists__output_resort_threaded(&t->sym_evsel->hists);
hists__decay_entries_threaded(&t->sym_evsel->hists,
- top.hide_user_symbols,
- top.hide_kernel_symbols);
+ t->hide_user_symbols,
+ t->hide_kernel_symbols);
}
-static void *display_thread_tui(void *arg __used)
+static void *display_thread_tui(void *arg)
{
+ struct perf_top *top = arg;
const char *help = "For a higher level overview, try: perf top --sort comm,dso";
- perf_top__sort_new_samples(&top);
- perf_evlist__tui_browse_hists(top.evlist, help,
+ perf_top__sort_new_samples(top);
+ perf_evlist__tui_browse_hists(top->evlist, help,
perf_top__sort_new_samples,
- &top, top.delay_secs);
+ top, top->delay_secs);
exit_browser(0);
exit(0);
return NULL;
}
-static void *display_thread(void *arg __used)
+static void *display_thread(void *arg)
{
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
struct termios tc, save;
+ struct perf_top *top = arg;
int delay_msecs, c;
tcgetattr(0, &save);
@@ -595,13 +566,13 @@
pthread__unblock_sigwinch();
repeat:
- delay_msecs = top.delay_secs * 1000;
+ delay_msecs = top->delay_secs * 1000;
tcsetattr(0, TCSANOW, &tc);
/* trash return*/
getc(stdin);
while (1) {
- print_sym_table();
+ perf_top__print_sym_table(top);
/*
* Either timeout expired or we got an EINTR due to SIGWINCH,
* refresh screen in both cases.
@@ -621,7 +592,7 @@
c = getc(stdin);
tcsetattr(0, TCSAFLUSH, &save);
- handle_keypress(c);
+ perf_top__handle_keypress(top, c);
goto repeat;
return NULL;
@@ -673,47 +644,17 @@
return 0;
}
-static void perf_event__process_sample(const union perf_event *event,
+static void perf_event__process_sample(struct perf_tool *tool,
+ const union perf_event *event,
struct perf_evsel *evsel,
struct perf_sample *sample,
- struct perf_session *session)
+ struct machine *machine)
{
+ struct perf_top *top = container_of(tool, struct perf_top, tool);
struct symbol *parent = NULL;
u64 ip = event->ip.ip;
struct addr_location al;
- struct machine *machine;
int err;
- u8 origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-
- ++top.samples;
-
- switch (origin) {
- case PERF_RECORD_MISC_USER:
- ++top.us_samples;
- if (top.hide_user_symbols)
- return;
- machine = perf_session__find_host_machine(session);
- break;
- case PERF_RECORD_MISC_KERNEL:
- ++top.kernel_samples;
- if (top.hide_kernel_symbols)
- return;
- machine = perf_session__find_host_machine(session);
- break;
- case PERF_RECORD_MISC_GUEST_KERNEL:
- ++top.guest_kernel_samples;
- machine = perf_session__find_machine(session, event->ip.pid);
- break;
- case PERF_RECORD_MISC_GUEST_USER:
- ++top.guest_us_samples;
- /*
- * TODO: we don't process guest user from host side
- * except simple counting.
- */
- return;
- default:
- return;
- }
if (!machine && perf_guest) {
pr_err("Can't find guest [%d]'s kernel information\n",
@@ -722,14 +663,14 @@
}
if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
- top.exact_samples++;
+ top->exact_samples++;
- if (perf_event__preprocess_sample(event, session, &al, sample,
+ if (perf_event__preprocess_sample(event, machine, &al, sample,
symbol_filter) < 0 ||
al.filtered)
return;
- if (!kptr_restrict_warned &&
+ if (!top->kptr_restrict_warned &&
symbol_conf.kptr_restrict &&
al.cpumode == PERF_RECORD_MISC_KERNEL) {
ui__warning(
@@ -740,7 +681,7 @@
" modules" : "");
if (use_browser <= 0)
sleep(5);
- kptr_restrict_warned = true;
+ top->kptr_restrict_warned = true;
}
if (al.sym == NULL) {
@@ -756,7 +697,7 @@
* --hide-kernel-symbols, even if the user specifies an
* invalid --vmlinux ;-)
*/
- if (!kptr_restrict_warned && !vmlinux_warned &&
+ if (!top->kptr_restrict_warned && !top->vmlinux_warned &&
al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
if (symbol_conf.vmlinux_name) {
@@ -769,7 +710,7 @@
if (use_browser <= 0)
sleep(5);
- vmlinux_warned = true;
+ top->vmlinux_warned = true;
}
}
@@ -778,70 +719,109 @@
if ((sort__has_parent || symbol_conf.use_callchain) &&
sample->callchain) {
- err = perf_session__resolve_callchain(session, al.thread,
- sample->callchain, &parent);
+ err = machine__resolve_callchain(machine, evsel, al.thread,
+ sample->callchain, &parent);
if (err)
return;
}
- he = perf_session__add_hist_entry(session, &al, sample, evsel);
+ he = perf_evsel__add_hist_entry(evsel, &al, sample);
if (he == NULL) {
pr_err("Problem incrementing symbol period, skipping event\n");
return;
}
if (symbol_conf.use_callchain) {
- err = callchain_append(he->callchain, &session->callchain_cursor,
+ err = callchain_append(he->callchain, &evsel->hists.callchain_cursor,
sample->period);
if (err)
return;
}
- if (sort_has_symbols)
- record_precise_ip(he, evsel->idx, ip);
+ if (top->sort_has_symbols)
+ perf_top__record_precise_ip(top, he, evsel->idx, ip);
}
return;
}
-static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
+static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
{
struct perf_sample sample;
struct perf_evsel *evsel;
+ struct perf_session *session = top->session;
union perf_event *event;
+ struct machine *machine;
+ u8 origin;
int ret;
- while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
- ret = perf_session__parse_sample(self, event, &sample);
+ while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
+ ret = perf_session__parse_sample(session, event, &sample);
if (ret) {
pr_err("Can't parse sample, err = %d\n", ret);
continue;
}
- evsel = perf_evlist__id2evsel(self->evlist, sample.id);
+ evsel = perf_evlist__id2evsel(session->evlist, sample.id);
assert(evsel != NULL);
+ origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
if (event->header.type == PERF_RECORD_SAMPLE)
- perf_event__process_sample(event, evsel, &sample, self);
- else if (event->header.type < PERF_RECORD_MAX) {
+ ++top->samples;
+
+ switch (origin) {
+ case PERF_RECORD_MISC_USER:
+ ++top->us_samples;
+ if (top->hide_user_symbols)
+ continue;
+ machine = perf_session__find_host_machine(session);
+ break;
+ case PERF_RECORD_MISC_KERNEL:
+ ++top->kernel_samples;
+ if (top->hide_kernel_symbols)
+ continue;
+ machine = perf_session__find_host_machine(session);
+ break;
+ case PERF_RECORD_MISC_GUEST_KERNEL:
+ ++top->guest_kernel_samples;
+ machine = perf_session__find_machine(session, event->ip.pid);
+ break;
+ case PERF_RECORD_MISC_GUEST_USER:
+ ++top->guest_us_samples;
+ /*
+ * TODO: we don't process guest user from host side
+ * except simple counting.
+ */
+ /* Fall thru */
+ default:
+ continue;
+ }
+
+
+ if (event->header.type == PERF_RECORD_SAMPLE) {
+ perf_event__process_sample(&top->tool, event, evsel,
+ &sample, machine);
+ } else if (event->header.type < PERF_RECORD_MAX) {
hists__inc_nr_events(&evsel->hists, event->header.type);
- perf_event__process(event, &sample, self);
+ perf_event__process(&top->tool, event, &sample, machine);
} else
- ++self->hists.stats.nr_unknown_events;
+ ++session->hists.stats.nr_unknown_events;
}
}
-static void perf_session__mmap_read(struct perf_session *self)
+static void perf_top__mmap_read(struct perf_top *top)
{
int i;
- for (i = 0; i < top.evlist->nr_mmaps; i++)
- perf_session__mmap_read_idx(self, i);
+ for (i = 0; i < top->evlist->nr_mmaps; i++)
+ perf_top__mmap_read_idx(top, i);
}
-static void start_counters(struct perf_evlist *evlist)
+static void perf_top__start_counters(struct perf_top *top)
{
struct perf_evsel *counter, *first;
+ struct perf_evlist *evlist = top->evlist;
first = list_entry(evlist->entries.next, struct perf_evsel, node);
@@ -849,15 +829,15 @@
struct perf_event_attr *attr = &counter->attr;
struct xyarray *group_fd = NULL;
- if (group && counter != first)
+ if (top->group && counter != first)
group_fd = first->fd;
attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
- if (top.freq) {
+ if (top->freq) {
attr->sample_type |= PERF_SAMPLE_PERIOD;
attr->freq = 1;
- attr->sample_freq = top.freq;
+ attr->sample_freq = top->freq;
}
if (evlist->nr_entries > 1) {
@@ -870,23 +850,23 @@
attr->mmap = 1;
attr->comm = 1;
- attr->inherit = inherit;
+ attr->inherit = top->inherit;
retry_sample_id:
- attr->sample_id_all = sample_id_all_avail ? 1 : 0;
+ attr->sample_id_all = top->sample_id_all_avail ? 1 : 0;
try_again:
- if (perf_evsel__open(counter, top.evlist->cpus,
- top.evlist->threads, group,
+ if (perf_evsel__open(counter, top->evlist->cpus,
+ top->evlist->threads, top->group,
group_fd) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
ui__error_paranoid();
goto out_err;
- } else if (err == EINVAL && sample_id_all_avail) {
+ } else if (err == EINVAL && top->sample_id_all_avail) {
/*
* Old kernel, no attr->sample_id_type_all field
*/
- sample_id_all_avail = false;
+ top->sample_id_all_avail = false;
goto retry_sample_id;
}
/*
@@ -920,7 +900,7 @@
}
}
- if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) {
+ if (perf_evlist__mmap(evlist, top->mmap_pages, false) < 0) {
ui__warning("Failed to mmap with %d (%s)\n",
errno, strerror(errno));
goto out_err;
@@ -933,14 +913,14 @@
exit(0);
}
-static int setup_sample_type(void)
+static int perf_top__setup_sample_type(struct perf_top *top)
{
- if (!sort_has_symbols) {
+ if (!top->sort_has_symbols) {
if (symbol_conf.use_callchain) {
ui__warning("Selected -g but \"sym\" not present in --sort/-s.");
return -EINVAL;
}
- } else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE) {
+ } else if (!top->dont_use_callchains && callchain_param.mode != CHAIN_NONE) {
if (callchain_register_param(&callchain_param) < 0) {
ui__warning("Can't register callchain params.\n");
return -EINVAL;
@@ -950,7 +930,7 @@
return 0;
}
-static int __cmd_top(void)
+static int __cmd_top(struct perf_top *top)
{
pthread_t thread;
int ret;
@@ -958,39 +938,40 @@
* FIXME: perf_session__new should allow passing a O_MMAP, so that all this
* mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
*/
- top.session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
- if (top.session == NULL)
+ top->session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
+ if (top->session == NULL)
return -ENOMEM;
- ret = setup_sample_type();
+ ret = perf_top__setup_sample_type(top);
if (ret)
goto out_delete;
- if (top.target_tid != -1)
- perf_event__synthesize_thread_map(top.evlist->threads,
- perf_event__process, top.session);
+ if (top->target_tid != -1)
+ perf_event__synthesize_thread_map(&top->tool, top->evlist->threads,
+ perf_event__process,
+ &top->session->host_machine);
else
- perf_event__synthesize_threads(perf_event__process, top.session);
-
- start_counters(top.evlist);
- top.session->evlist = top.evlist;
- perf_session__update_sample_type(top.session);
+ perf_event__synthesize_threads(&top->tool, perf_event__process,
+ &top->session->host_machine);
+ perf_top__start_counters(top);
+ top->session->evlist = top->evlist;
+ perf_session__update_sample_type(top->session);
/* Wait for a minimal set of events before starting the snapshot */
- poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
+ poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
- perf_session__mmap_read(top.session);
+ perf_top__mmap_read(top);
if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
- display_thread), NULL)) {
+ display_thread), top)) {
printf("Could not create display thread.\n");
exit(-1);
}
- if (realtime_prio) {
+ if (top->realtime_prio) {
struct sched_param param;
- param.sched_priority = realtime_prio;
+ param.sched_priority = top->realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, ¶m)) {
printf("Could not set realtime priority.\n");
exit(-1);
@@ -998,25 +979,25 @@
}
while (1) {
- u64 hits = top.samples;
+ u64 hits = top->samples;
- perf_session__mmap_read(top.session);
+ perf_top__mmap_read(top);
- if (hits == top.samples)
- ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
+ if (hits == top->samples)
+ ret = poll(top->evlist->pollfd, top->evlist->nr_fds, 100);
}
out_delete:
- perf_session__delete(top.session);
- top.session = NULL;
+ perf_session__delete(top->session);
+ top->session = NULL;
return 0;
}
static int
-parse_callchain_opt(const struct option *opt __used, const char *arg,
- int unset)
+parse_callchain_opt(const struct option *opt, const char *arg, int unset)
{
+ struct perf_top *top = (struct perf_top *)opt->value;
char *tok, *tok2;
char *endptr;
@@ -1024,7 +1005,7 @@
* --no-call-graph
*/
if (unset) {
- dont_use_callchains = true;
+ top->dont_use_callchains = true;
return 0;
}
@@ -1052,9 +1033,7 @@
symbol_conf.use_callchain = false;
return 0;
- }
-
- else
+ } else
return -1;
/* get the min percentage */
@@ -1098,17 +1077,32 @@
NULL
};
-static const struct option options[] = {
+int cmd_top(int argc, const char **argv, const char *prefix __used)
+{
+ struct perf_evsel *pos;
+ int status = -ENOMEM;
+ struct perf_top top = {
+ .count_filter = 5,
+ .delay_secs = 2,
+ .target_pid = -1,
+ .target_tid = -1,
+ .freq = 1000, /* 1 KHz */
+ .sample_id_all_avail = true,
+ .mmap_pages = 128,
+ .sym_pcnt_filter = 5,
+ };
+ char callchain_default_opt[] = "fractal,0.5,callee";
+ const struct option options[] = {
OPT_CALLBACK('e', "event", &top.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
- OPT_INTEGER('c', "count", &default_interval,
+ OPT_INTEGER('c', "count", &top.default_interval,
"event period to sample"),
OPT_INTEGER('p', "pid", &top.target_pid,
"profile events on existing process id"),
OPT_INTEGER('t', "tid", &top.target_tid,
"profile events on existing thread id"),
- OPT_BOOLEAN('a', "all-cpus", &system_wide,
+ OPT_BOOLEAN('a', "all-cpus", &top.system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &top.cpu_list, "cpu",
"list of cpus to monitor"),
@@ -1116,20 +1110,20 @@
"file", "vmlinux pathname"),
OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
"hide kernel symbols"),
- OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
- OPT_INTEGER('r', "realtime", &realtime_prio,
+ OPT_UINTEGER('m', "mmap-pages", &top.mmap_pages, "number of mmap data pages"),
+ OPT_INTEGER('r', "realtime", &top.realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_INTEGER('d', "delay", &top.delay_secs,
"number of seconds to delay between refreshes"),
- OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
+ OPT_BOOLEAN('D', "dump-symtab", &top.dump_symtab,
"dump the symbol table used for profiling"),
OPT_INTEGER('f', "count-filter", &top.count_filter,
"only display functions with more events than this"),
- OPT_BOOLEAN('g', "group", &group,
+ OPT_BOOLEAN('g', "group", &top.group,
"put the counters into a counter group"),
- OPT_BOOLEAN('i', "inherit", &inherit,
+ OPT_BOOLEAN('i', "inherit", &top.inherit,
"child tasks inherit counters"),
- OPT_STRING(0, "sym-annotate", &sym_filter, "symbol name",
+ OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name",
"symbol to annotate"),
OPT_BOOLEAN('z', "zero", &top.zero,
"zero history across updates"),
@@ -1139,15 +1133,15 @@
"display this many functions"),
OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
"hide user symbols"),
- OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
- OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
+ OPT_BOOLEAN(0, "tui", &top.use_tui, "Use the TUI interface"),
+ OPT_BOOLEAN(0, "stdio", &top.use_stdio, "Use the stdio interface"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
- OPT_CALLBACK_DEFAULT('G', "call-graph", NULL, "output_type,min_percent, call_order",
+ OPT_CALLBACK_DEFAULT('G', "call-graph", &top, "output_type,min_percent, call_order",
"Display callchains using output_type (graph, flat, fractal, or none), min percent threshold and callchain order. "
"Default: fractal,0.5,callee", &parse_callchain_opt,
callchain_default_opt),
@@ -1166,12 +1160,7 @@
OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
"Specify disassembler style (e.g. -M intel for intel syntax)"),
OPT_END()
-};
-
-int cmd_top(int argc, const char **argv, const char *prefix __used)
-{
- struct perf_evsel *pos;
- int status = -ENOMEM;
+ };
top.evlist = perf_evlist__new(NULL, NULL);
if (top.evlist == NULL)
@@ -1188,9 +1177,9 @@
setup_sorting(top_usage, options);
- if (use_stdio)
+ if (top.use_stdio)
use_browser = 0;
- else if (use_tui)
+ else if (top.use_tui)
use_browser = 1;
setup_browser(false);
@@ -1215,38 +1204,31 @@
return -ENOMEM;
}
+ symbol_conf.nr_events = top.evlist->nr_entries;
+
if (top.delay_secs < 1)
top.delay_secs = 1;
/*
* User specified count overrides default frequency.
*/
- if (default_interval)
+ if (top.default_interval)
top.freq = 0;
else if (top.freq) {
- default_interval = top.freq;
+ top.default_interval = top.freq;
} else {
fprintf(stderr, "frequency and count are zero, aborting\n");
exit(EXIT_FAILURE);
}
list_for_each_entry(pos, &top.evlist->entries, node) {
- if (perf_evsel__alloc_fd(pos, top.evlist->cpus->nr,
- top.evlist->threads->nr) < 0)
- goto out_free_fd;
/*
* Fill in the ones not specifically initialized via -c:
*/
- if (pos->attr.sample_period)
- continue;
-
- pos->attr.sample_period = default_interval;
+ if (!pos->attr.sample_period)
+ pos->attr.sample_period = top.default_interval;
}
- if (perf_evlist__alloc_pollfd(top.evlist) < 0 ||
- perf_evlist__alloc_mmap(top.evlist) < 0)
- goto out_free_fd;
-
top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
symbol_conf.priv_size = sizeof(struct annotation);
@@ -1263,16 +1245,20 @@
* Avoid annotation data structures overhead when symbols aren't on the
* sort list.
*/
- sort_has_symbols = sort_sym.list.next != NULL;
+ top.sort_has_symbols = sort_sym.list.next != NULL;
- get_term_dimensions(&winsize);
+ get_term_dimensions(&top.winsize);
if (top.print_entries == 0) {
- update_print_entries(&winsize);
- signal(SIGWINCH, sig_winch_handler);
+ struct sigaction act = {
+ .sa_sigaction = perf_top__sig_winch,
+ .sa_flags = SA_SIGINFO,
+ };
+ perf_top__update_print_entries(&top);
+ sigaction(SIGWINCH, &act, NULL);
}
- status = __cmd_top();
-out_free_fd:
+ status = __cmd_top(&top);
+
perf_evlist__delete(top.evlist);
return status;
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 73d0cac..2b2e225 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -29,8 +29,6 @@
int val;
};
-static char debugfs_mntpt[MAXPATHLEN];
-
static int pager_command_config(const char *var, const char *value, void *data)
{
struct pager_config *c = data;
@@ -81,15 +79,6 @@
}
}
-static void set_debugfs_path(void)
-{
- char *path;
-
- path = getenv(PERF_DEBUGFS_ENVIRONMENT);
- snprintf(debugfs_path, MAXPATHLEN, "%s/%s", path ?: debugfs_mntpt,
- "tracing/events");
-}
-
static int handle_options(const char ***argv, int *argc, int *envchanged)
{
int handled = 0;
@@ -161,15 +150,14 @@
fprintf(stderr, "No directory given for --debugfs-dir.\n");
usage(perf_usage_string);
}
- strncpy(debugfs_mntpt, (*argv)[1], MAXPATHLEN);
- debugfs_mntpt[MAXPATHLEN - 1] = '\0';
+ debugfs_set_path((*argv)[1]);
if (envchanged)
*envchanged = 1;
(*argv)++;
(*argc)--;
} else if (!prefixcmp(cmd, CMD_DEBUGFS_DIR)) {
- strncpy(debugfs_mntpt, cmd + strlen(CMD_DEBUGFS_DIR), MAXPATHLEN);
- debugfs_mntpt[MAXPATHLEN - 1] = '\0';
+ debugfs_set_path(cmd + strlen(CMD_DEBUGFS_DIR));
+ fprintf(stderr, "dir: %s\n", debugfs_mountpoint);
if (envchanged)
*envchanged = 1;
} else {
@@ -281,7 +269,6 @@
if (use_pager == -1 && p->option & USE_PAGER)
use_pager = 1;
commit_pager_choice();
- set_debugfs_path();
status = p->fn(argc, argv, prefix);
exit_browser(status);
@@ -416,17 +403,6 @@
return done_alias;
}
-/* mini /proc/mounts parser: searching for "^blah /mount/point debugfs" */
-static void get_debugfs_mntpt(void)
-{
- const char *path = debugfs_mount(NULL);
-
- if (path)
- strncpy(debugfs_mntpt, path, sizeof(debugfs_mntpt));
- else
- debugfs_mntpt[0] = '\0';
-}
-
static void pthread__block_sigwinch(void)
{
sigset_t set;
@@ -453,7 +429,7 @@
if (!cmd)
cmd = "perf-help";
/* get debugfs mount point from /proc/mounts */
- get_debugfs_mntpt();
+ debugfs_mount(NULL);
/*
* "perf-xxxx" is the same as "perf xxxx", but we obviously:
*
@@ -476,7 +452,6 @@
argc--;
handle_options(&argv, &argc, NULL);
commit_pager_choice();
- set_debugfs_path();
set_buildid_dir();
if (argc > 0) {
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 914c895..64f8bee 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -185,4 +185,28 @@
void pthread__unblock_sigwinch(void);
+struct perf_record_opts {
+ pid_t target_pid;
+ pid_t target_tid;
+ bool call_graph;
+ bool group;
+ bool inherit_stat;
+ bool no_delay;
+ bool no_inherit;
+ bool no_samples;
+ bool pipe_output;
+ bool raw_samples;
+ bool sample_address;
+ bool sample_time;
+ bool sample_id_all_avail;
+ bool system_wide;
+ bool period;
+ unsigned int freq;
+ unsigned int mmap_pages;
+ unsigned int user_freq;
+ u64 default_interval;
+ u64 user_interval;
+ const char *cpu_list;
+};
+
#endif
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 119e996..011ed26 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,17 +25,17 @@
return 0;
}
-int symbol__alloc_hist(struct symbol *sym, int nevents)
+int symbol__alloc_hist(struct symbol *sym)
{
struct annotation *notes = symbol__annotation(sym);
size_t sizeof_sym_hist = (sizeof(struct sym_hist) +
(sym->end - sym->start) * sizeof(u64));
- notes->src = zalloc(sizeof(*notes->src) + nevents * sizeof_sym_hist);
+ notes->src = zalloc(sizeof(*notes->src) + symbol_conf.nr_events * sizeof_sym_hist);
if (notes->src == NULL)
return -1;
notes->src->sizeof_sym_hist = sizeof_sym_hist;
- notes->src->nr_histograms = nevents;
+ notes->src->nr_histograms = symbol_conf.nr_events;
INIT_LIST_HEAD(¬es->src->source);
return 0;
}
@@ -334,7 +334,7 @@
disassembler_style ? "-M " : "",
disassembler_style ? disassembler_style : "",
map__rip_2objdump(map, sym->start),
- map__rip_2objdump(map, sym->end),
+ map__rip_2objdump(map, sym->end+1),
symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
symbol_conf.annotate_src ? "-S" : "",
symfs_filename, filename);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index d907252..efa5dc8 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -72,7 +72,7 @@
int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
int evidx, u64 addr);
-int symbol__alloc_hist(struct symbol *sym, int nevents);
+int symbol__alloc_hist(struct symbol *sym);
void symbol__annotate_zero_histograms(struct symbol *sym);
int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
@@ -99,8 +99,7 @@
}
#else
int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
- int nr_events, void(*timer)(void *arg), void *arg,
- int delay_secs);
+ void(*timer)(void *arg), void *arg, int delay_secs);
#endif
extern const char *disassembler_style;
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a91cd99..dff9c7a 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -13,15 +13,18 @@
#include "symbol.h"
#include <linux/kernel.h>
#include "debug.h"
+#include "session.h"
+#include "tool.h"
-static int build_id__mark_dso_hit(union perf_event *event,
+static int build_id__mark_dso_hit(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample __used,
struct perf_evsel *evsel __used,
- struct perf_session *session)
+ struct machine *machine)
{
struct addr_location al;
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- struct thread *thread = perf_session__findnew(session, event->ip.pid);
+ struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
if (thread == NULL) {
pr_err("problem processing %d event, skipping it.\n",
@@ -29,8 +32,8 @@
return -1;
}
- thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
- event->ip.pid, event->ip.ip, &al);
+ thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+ event->ip.ip, &al);
if (al.map != NULL)
al.map->dso->hit = 1;
@@ -38,25 +41,26 @@
return 0;
}
-static int perf_event__exit_del_thread(union perf_event *event,
+static int perf_event__exit_del_thread(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *session)
+ struct machine *machine)
{
- struct thread *thread = perf_session__findnew(session, event->fork.tid);
+ struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
event->fork.ppid, event->fork.ptid);
if (thread) {
- rb_erase(&thread->rb_node, &session->threads);
- session->last_match = NULL;
+ rb_erase(&thread->rb_node, &machine->threads);
+ machine->last_match = NULL;
thread__delete(thread);
}
return 0;
}
-struct perf_event_ops build_id__mark_dso_hit_ops = {
+struct perf_tool build_id__mark_dso_hit_ops = {
.sample = build_id__mark_dso_hit,
.mmap = perf_event__process_mmap,
.fork = perf_event__process_task,
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 5dafb00..a993ba8 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -3,7 +3,7 @@
#include "session.h"
-extern struct perf_event_ops build_id__mark_dso_hit_ops;
+extern struct perf_tool build_id__mark_dso_hit_ops;
char *dso__build_id_filename(struct dso *self, char *bf, size_t size);
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 9b4ff16c..7f9c0f1 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -101,6 +101,9 @@
int callchain_merge(struct callchain_cursor *cursor,
struct callchain_root *dst, struct callchain_root *src);
+struct ip_callchain;
+union perf_event;
+
bool ip_callchain__valid(struct ip_callchain *chain,
const union perf_event *event);
/*
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 96bee5c..dbe2f16 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -3,7 +3,6 @@
#include "parse-options.h"
#include "evsel.h"
#include "cgroup.h"
-#include "debugfs.h" /* MAX_PATH, STR() */
#include "evlist.h"
int nr_cgroups;
@@ -12,7 +11,7 @@
cgroupfs_find_mountpoint(char *buf, size_t maxlen)
{
FILE *fp;
- char mountpoint[MAX_PATH+1], tokens[MAX_PATH+1], type[MAX_PATH+1];
+ char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1];
char *token, *saved_ptr = NULL;
int found = 0;
@@ -25,8 +24,8 @@
* and inspect every cgroupfs mount point to find one that has
* perf_event subsystem
*/
- while (fscanf(fp, "%*s %"STR(MAX_PATH)"s %"STR(MAX_PATH)"s %"
- STR(MAX_PATH)"s %*d %*d\n",
+ while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %"
+ STR(PATH_MAX)"s %*d %*d\n",
mountpoint, type, tokens) == 3) {
if (!strcmp(type, "cgroup")) {
@@ -57,15 +56,15 @@
static int open_cgroup(char *name)
{
- char path[MAX_PATH+1];
- char mnt[MAX_PATH+1];
+ char path[PATH_MAX + 1];
+ char mnt[PATH_MAX + 1];
int fd;
- if (cgroupfs_find_mountpoint(mnt, MAX_PATH+1))
+ if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
return -1;
- snprintf(path, MAX_PATH, "%s/%s", mnt, name);
+ snprintf(path, PATH_MAX, "%s/%s", mnt, name);
fd = open(path, O_RDONLY);
if (fd == -1)
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 80d9598..0deac6a 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -1,5 +1,8 @@
/*
- * GIT - The information manager from hell
+ * config.c
+ *
+ * Helper functions for parsing config items.
+ * Originally copied from GIT source.
*
* Copyright (C) Linus Torvalds, 2005
* Copyright (C) Johannes Schindelin, 2005
diff --git a/tools/perf/util/debugfs.c b/tools/perf/util/debugfs.c
index a88fefc..ffc35e7 100644
--- a/tools/perf/util/debugfs.c
+++ b/tools/perf/util/debugfs.c
@@ -2,8 +2,12 @@
#include "debugfs.h"
#include "cache.h"
+#include <linux/kernel.h>
+#include <sys/mount.h>
+
static int debugfs_premounted;
-static char debugfs_mountpoint[MAX_PATH+1];
+char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
+char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
static const char *debugfs_known_mountpoints[] = {
"/sys/kernel/debug/",
@@ -62,11 +66,9 @@
/* give up and parse /proc/mounts */
fp = fopen("/proc/mounts", "r");
if (fp == NULL)
- die("Can't open /proc/mounts for read");
+ return NULL;
- while (fscanf(fp, "%*s %"
- STR(MAX_PATH)
- "s %99s %*s %*d %*d\n",
+ while (fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
debugfs_mountpoint, type) == 2) {
if (strcmp(type, "debugfs") == 0)
break;
@@ -106,6 +108,12 @@
return 0;
}
+static void debugfs_set_tracing_events_path(const char *mountpoint)
+{
+ snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
+ mountpoint, "tracing/events");
+}
+
/* mount the debugfs somewhere if it's not mounted */
char *debugfs_mount(const char *mountpoint)
@@ -113,7 +121,7 @@
/* see if it's already mounted */
if (debugfs_find_mountpoint()) {
debugfs_premounted = 1;
- return debugfs_mountpoint;
+ goto out;
}
/* if not mounted and no argument */
@@ -129,12 +137,19 @@
return NULL;
/* save the mountpoint */
- strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
debugfs_found = 1;
-
+ strncpy(debugfs_mountpoint, mountpoint, sizeof(debugfs_mountpoint));
+out:
+ debugfs_set_tracing_events_path(debugfs_mountpoint);
return debugfs_mountpoint;
}
+void debugfs_set_path(const char *mountpoint)
+{
+ snprintf(debugfs_mountpoint, sizeof(debugfs_mountpoint), "%s", mountpoint);
+ debugfs_set_tracing_events_path(mountpoint);
+}
+
/* umount the debugfs */
int debugfs_umount(void)
@@ -158,7 +173,7 @@
int debugfs_write(const char *entry, const char *value)
{
- char path[MAX_PATH+1];
+ char path[PATH_MAX + 1];
int ret, count;
int fd;
@@ -203,7 +218,7 @@
*/
int debugfs_read(const char *entry, char *buffer, size_t size)
{
- char path[MAX_PATH+1];
+ char path[PATH_MAX + 1];
int ret;
int fd;
diff --git a/tools/perf/util/debugfs.h b/tools/perf/util/debugfs.h
index 83a0287..4a878f7 100644
--- a/tools/perf/util/debugfs.h
+++ b/tools/perf/util/debugfs.h
@@ -1,25 +1,18 @@
#ifndef __DEBUGFS_H__
#define __DEBUGFS_H__
-#include <sys/mount.h>
+const char *debugfs_find_mountpoint(void);
+int debugfs_valid_mountpoint(const char *debugfs);
+int debugfs_valid_entry(const char *path);
+char *debugfs_mount(const char *mountpoint);
+int debugfs_umount(void);
+void debugfs_set_path(const char *mountpoint);
+int debugfs_write(const char *entry, const char *value);
+int debugfs_read(const char *entry, char *buffer, size_t size);
+void debugfs_force_cleanup(void);
+int debugfs_make_path(const char *element, char *buffer, int size);
-#ifndef MAX_PATH
-# define MAX_PATH 256
-#endif
-
-#ifndef STR
-# define _STR(x) #x
-# define STR(x) _STR(x)
-#endif
-
-extern const char *debugfs_find_mountpoint(void);
-extern int debugfs_valid_mountpoint(const char *debugfs);
-extern int debugfs_valid_entry(const char *path);
-extern char *debugfs_mount(const char *mountpoint);
-extern int debugfs_umount(void);
-extern int debugfs_write(const char *entry, const char *value);
-extern int debugfs_read(const char *entry, char *buffer, size_t size);
-extern void debugfs_force_cleanup(void);
-extern int debugfs_make_path(const char *element, char *buffer, int size);
+extern char debugfs_mountpoint[];
+extern char tracing_events_path[];
#endif /* __DEBUGFS_H__ */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 437f8ca..73ddaf0 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,7 +1,6 @@
#include <linux/types.h>
#include "event.h"
#include "debug.h"
-#include "session.h"
#include "sort.h"
#include "string.h"
#include "strlist.h"
@@ -44,36 +43,27 @@
.period = 1,
};
-static pid_t perf_event__synthesize_comm(union perf_event *event, pid_t pid,
- int full, perf_event__handler_t process,
- struct perf_session *session)
+static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len)
{
char filename[PATH_MAX];
char bf[BUFSIZ];
FILE *fp;
size_t size = 0;
- DIR *tasks;
- struct dirent dirent, *next;
- pid_t tgid = 0;
+ pid_t tgid = -1;
snprintf(filename, sizeof(filename), "/proc/%d/status", pid);
fp = fopen(filename, "r");
if (fp == NULL) {
-out_race:
- /*
- * We raced with a task exiting - just return:
- */
pr_debug("couldn't open %s\n", filename);
return 0;
}
- memset(&event->comm, 0, sizeof(event->comm));
-
- while (!event->comm.comm[0] || !event->comm.pid) {
+ while (!comm[0] || (tgid < 0)) {
if (fgets(bf, sizeof(bf), fp) == NULL) {
- pr_warning("couldn't get COMM and pgid, malformed %s\n", filename);
- goto out;
+ pr_warning("couldn't get COMM and pgid, malformed %s\n",
+ filename);
+ break;
}
if (memcmp(bf, "Name:", 5) == 0) {
@@ -81,33 +71,65 @@
while (*name && isspace(*name))
++name;
size = strlen(name) - 1;
- memcpy(event->comm.comm, name, size++);
+ if (size >= len)
+ size = len - 1;
+ memcpy(comm, name, size);
+
} else if (memcmp(bf, "Tgid:", 5) == 0) {
char *tgids = bf + 5;
while (*tgids && isspace(*tgids))
++tgids;
- tgid = event->comm.pid = atoi(tgids);
+ tgid = atoi(tgids);
}
}
+ fclose(fp);
+
+ return tgid;
+}
+
+static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
+ union perf_event *event, pid_t pid,
+ int full,
+ perf_event__handler_t process,
+ struct machine *machine)
+{
+ char filename[PATH_MAX];
+ size_t size;
+ DIR *tasks;
+ struct dirent dirent, *next;
+ pid_t tgid;
+
+ memset(&event->comm, 0, sizeof(event->comm));
+
+ tgid = perf_event__get_comm_tgid(pid, event->comm.comm,
+ sizeof(event->comm.comm));
+ if (tgid < 0)
+ goto out;
+
+ event->comm.pid = tgid;
event->comm.header.type = PERF_RECORD_COMM;
+
+ size = strlen(event->comm.comm) + 1;
size = ALIGN(size, sizeof(u64));
- memset(event->comm.comm + size, 0, session->id_hdr_size);
+ memset(event->comm.comm + size, 0, machine->id_hdr_size);
event->comm.header.size = (sizeof(event->comm) -
(sizeof(event->comm.comm) - size) +
- session->id_hdr_size);
+ machine->id_hdr_size);
if (!full) {
event->comm.tid = pid;
- process(event, &synth_sample, session);
+ process(tool, event, &synth_sample, machine);
goto out;
}
snprintf(filename, sizeof(filename), "/proc/%d/task", pid);
tasks = opendir(filename);
- if (tasks == NULL)
- goto out_race;
+ if (tasks == NULL) {
+ pr_debug("couldn't open %s\n", filename);
+ return 0;
+ }
while (!readdir_r(tasks, &dirent, &next) && next) {
char *end;
@@ -115,22 +137,32 @@
if (*end)
continue;
+ /* already have tgid; jut want to update the comm */
+ (void) perf_event__get_comm_tgid(pid, event->comm.comm,
+ sizeof(event->comm.comm));
+
+ size = strlen(event->comm.comm) + 1;
+ size = ALIGN(size, sizeof(u64));
+ memset(event->comm.comm + size, 0, machine->id_hdr_size);
+ event->comm.header.size = (sizeof(event->comm) -
+ (sizeof(event->comm.comm) - size) +
+ machine->id_hdr_size);
+
event->comm.tid = pid;
- process(event, &synth_sample, session);
+ process(tool, event, &synth_sample, machine);
}
closedir(tasks);
out:
- fclose(fp);
-
return tgid;
}
-static int perf_event__synthesize_mmap_events(union perf_event *event,
+static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
+ union perf_event *event,
pid_t pid, pid_t tgid,
perf_event__handler_t process,
- struct perf_session *session)
+ struct machine *machine)
{
char filename[PATH_MAX];
FILE *fp;
@@ -193,12 +225,12 @@
event->mmap.len -= event->mmap.start;
event->mmap.header.size = (sizeof(event->mmap) -
(sizeof(event->mmap.filename) - size));
- memset(event->mmap.filename + size, 0, session->id_hdr_size);
- event->mmap.header.size += session->id_hdr_size;
+ memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+ event->mmap.header.size += machine->id_hdr_size;
event->mmap.pid = tgid;
event->mmap.tid = pid;
- process(event, &synth_sample, session);
+ process(tool, event, &synth_sample, machine);
}
}
@@ -206,14 +238,14 @@
return 0;
}
-int perf_event__synthesize_modules(perf_event__handler_t process,
- struct perf_session *session,
+int perf_event__synthesize_modules(struct perf_tool *tool,
+ perf_event__handler_t process,
struct machine *machine)
{
struct rb_node *nd;
struct map_groups *kmaps = &machine->kmaps;
union perf_event *event = zalloc((sizeof(event->mmap) +
- session->id_hdr_size));
+ machine->id_hdr_size));
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
@@ -243,15 +275,15 @@
event->mmap.header.type = PERF_RECORD_MMAP;
event->mmap.header.size = (sizeof(event->mmap) -
(sizeof(event->mmap.filename) - size));
- memset(event->mmap.filename + size, 0, session->id_hdr_size);
- event->mmap.header.size += session->id_hdr_size;
+ memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+ event->mmap.header.size += machine->id_hdr_size;
event->mmap.start = pos->start;
event->mmap.len = pos->end - pos->start;
event->mmap.pid = machine->pid;
memcpy(event->mmap.filename, pos->dso->long_name,
pos->dso->long_name_len + 1);
- process(event, &synth_sample, session);
+ process(tool, event, &synth_sample, machine);
}
free(event);
@@ -260,40 +292,69 @@
static int __event__synthesize_thread(union perf_event *comm_event,
union perf_event *mmap_event,
- pid_t pid, perf_event__handler_t process,
- struct perf_session *session)
+ pid_t pid, int full,
+ perf_event__handler_t process,
+ struct perf_tool *tool,
+ struct machine *machine)
{
- pid_t tgid = perf_event__synthesize_comm(comm_event, pid, 1, process,
- session);
+ pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full,
+ process, machine);
if (tgid == -1)
return -1;
- return perf_event__synthesize_mmap_events(mmap_event, pid, tgid,
- process, session);
+ return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+ process, machine);
}
-int perf_event__synthesize_thread_map(struct thread_map *threads,
+int perf_event__synthesize_thread_map(struct perf_tool *tool,
+ struct thread_map *threads,
perf_event__handler_t process,
- struct perf_session *session)
+ struct machine *machine)
{
union perf_event *comm_event, *mmap_event;
- int err = -1, thread;
+ int err = -1, thread, j;
- comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+ comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
if (comm_event == NULL)
goto out;
- mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+ mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
if (mmap_event == NULL)
goto out_free_comm;
err = 0;
for (thread = 0; thread < threads->nr; ++thread) {
if (__event__synthesize_thread(comm_event, mmap_event,
- threads->map[thread],
- process, session)) {
+ threads->map[thread], 0,
+ process, tool, machine)) {
err = -1;
break;
}
+
+ /*
+ * comm.pid is set to thread group id by
+ * perf_event__synthesize_comm
+ */
+ if ((int) comm_event->comm.pid != threads->map[thread]) {
+ bool need_leader = true;
+
+ /* is thread group leader in thread_map? */
+ for (j = 0; j < threads->nr; ++j) {
+ if ((int) comm_event->comm.pid == threads->map[j]) {
+ need_leader = false;
+ break;
+ }
+ }
+
+ /* if not, generate events for it */
+ if (need_leader &&
+ __event__synthesize_thread(comm_event,
+ mmap_event,
+ comm_event->comm.pid, 0,
+ process, tool, machine)) {
+ err = -1;
+ break;
+ }
+ }
}
free(mmap_event);
out_free_comm:
@@ -302,19 +363,20 @@
return err;
}
-int perf_event__synthesize_threads(perf_event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_threads(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine)
{
DIR *proc;
struct dirent dirent, *next;
union perf_event *comm_event, *mmap_event;
int err = -1;
- comm_event = malloc(sizeof(comm_event->comm) + session->id_hdr_size);
+ comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
if (comm_event == NULL)
goto out;
- mmap_event = malloc(sizeof(mmap_event->mmap) + session->id_hdr_size);
+ mmap_event = malloc(sizeof(mmap_event->mmap) + machine->id_hdr_size);
if (mmap_event == NULL)
goto out_free_comm;
@@ -329,8 +391,8 @@
if (*end) /* only interested in proper numerical dirents */
continue;
- __event__synthesize_thread(comm_event, mmap_event, pid,
- process, session);
+ __event__synthesize_thread(comm_event, mmap_event, pid, 1,
+ process, tool, machine);
}
closedir(proc);
@@ -365,8 +427,8 @@
return 1;
}
-int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
- struct perf_session *session,
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+ perf_event__handler_t process,
struct machine *machine,
const char *symbol_name)
{
@@ -383,7 +445,7 @@
*/
struct process_symbol_args args = { .name = symbol_name, };
union perf_event *event = zalloc((sizeof(event->mmap) +
- session->id_hdr_size));
+ machine->id_hdr_size));
if (event == NULL) {
pr_debug("Not enough memory synthesizing mmap event "
"for kernel modules\n");
@@ -417,25 +479,32 @@
size = ALIGN(size, sizeof(u64));
event->mmap.header.type = PERF_RECORD_MMAP;
event->mmap.header.size = (sizeof(event->mmap) -
- (sizeof(event->mmap.filename) - size) + session->id_hdr_size);
+ (sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
event->mmap.pgoff = args.start;
event->mmap.start = map->start;
event->mmap.len = map->end - event->mmap.start;
event->mmap.pid = machine->pid;
- err = process(event, &synth_sample, session);
+ err = process(tool, event, &synth_sample, machine);
free(event);
return err;
}
-int perf_event__process_comm(union perf_event *event,
- struct perf_sample *sample __used,
- struct perf_session *session)
+size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
{
- struct thread *thread = perf_session__findnew(session, event->comm.tid);
+ return fprintf(fp, ": %s:%d\n", event->comm.comm, event->comm.tid);
+}
- dump_printf(": %s:%d\n", event->comm.comm, event->comm.tid);
+int perf_event__process_comm(struct perf_tool *tool __used,
+ union perf_event *event,
+ struct perf_sample *sample __used,
+ struct machine *machine)
+{
+ struct thread *thread = machine__findnew_thread(machine, event->comm.tid);
+
+ if (dump_trace)
+ perf_event__fprintf_comm(event, stdout);
if (thread == NULL || thread__set_comm(thread, event->comm.comm)) {
dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
@@ -445,13 +514,13 @@
return 0;
}
-int perf_event__process_lost(union perf_event *event,
+int perf_event__process_lost(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_sample *sample __used,
- struct perf_session *session)
+ struct machine *machine __used)
{
dump_printf(": id:%" PRIu64 ": lost:%" PRIu64 "\n",
event->lost.id, event->lost.lost);
- session->hists.stats.total_lost += event->lost.lost;
return 0;
}
@@ -468,21 +537,15 @@
maps[MAP__FUNCTION]->end = ~0ULL;
}
-static int perf_event__process_kernel_mmap(union perf_event *event,
- struct perf_session *session)
+static int perf_event__process_kernel_mmap(struct perf_tool *tool __used,
+ union perf_event *event,
+ struct machine *machine)
{
struct map *map;
char kmmap_prefix[PATH_MAX];
- struct machine *machine;
enum dso_kernel_type kernel_type;
bool is_kernel_mmap;
- machine = perf_session__findnew_machine(session, event->mmap.pid);
- if (!machine) {
- pr_err("Can't find id %d's machine\n", event->mmap.pid);
- goto out_problem;
- }
-
machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
if (machine__is_host(machine))
kernel_type = DSO_TYPE_KERNEL;
@@ -549,9 +612,9 @@
* time /proc/sys/kernel/kptr_restrict was non zero.
*/
if (event->mmap.pgoff != 0) {
- perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
- symbol_name,
- event->mmap.pgoff);
+ maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+ symbol_name,
+ event->mmap.pgoff);
}
if (machine__is_default_guest(machine)) {
@@ -567,32 +630,35 @@
return -1;
}
-int perf_event__process_mmap(union perf_event *event,
- struct perf_sample *sample __used,
- struct perf_session *session)
+size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
{
- struct machine *machine;
+ return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
+ event->mmap.pid, event->mmap.tid, event->mmap.start,
+ event->mmap.len, event->mmap.pgoff, event->mmap.filename);
+}
+
+int perf_event__process_mmap(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample __used,
+ struct machine *machine)
+{
struct thread *thread;
struct map *map;
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
int ret = 0;
- dump_printf(" %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %s\n",
- event->mmap.pid, event->mmap.tid, event->mmap.start,
- event->mmap.len, event->mmap.pgoff, event->mmap.filename);
+ if (dump_trace)
+ perf_event__fprintf_mmap(event, stdout);
if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL ||
cpumode == PERF_RECORD_MISC_KERNEL) {
- ret = perf_event__process_kernel_mmap(event, session);
+ ret = perf_event__process_kernel_mmap(tool, event, machine);
if (ret < 0)
goto out_problem;
return 0;
}
- machine = perf_session__find_host_machine(session);
- if (machine == NULL)
- goto out_problem;
- thread = perf_session__findnew(session, event->mmap.pid);
+ thread = machine__findnew_thread(machine, event->mmap.pid);
if (thread == NULL)
goto out_problem;
map = map__new(&machine->user_dsos, event->mmap.start,
@@ -610,18 +676,26 @@
return 0;
}
-int perf_event__process_task(union perf_event *event,
- struct perf_sample *sample __used,
- struct perf_session *session)
+size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
{
- struct thread *thread = perf_session__findnew(session, event->fork.tid);
- struct thread *parent = perf_session__findnew(session, event->fork.ptid);
+ return fprintf(fp, "(%d:%d):(%d:%d)\n",
+ event->fork.pid, event->fork.tid,
+ event->fork.ppid, event->fork.ptid);
+}
- dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
- event->fork.ppid, event->fork.ptid);
+int perf_event__process_task(struct perf_tool *tool __used,
+ union perf_event *event,
+ struct perf_sample *sample __used,
+ struct machine *machine)
+{
+ struct thread *thread = machine__findnew_thread(machine, event->fork.tid);
+ struct thread *parent = machine__findnew_thread(machine, event->fork.ptid);
+
+ if (dump_trace)
+ perf_event__fprintf_task(event, stdout);
if (event->header.type == PERF_RECORD_EXIT) {
- perf_session__remove_thread(session, thread);
+ machine__remove_thread(machine, thread);
return 0;
}
@@ -634,22 +708,45 @@
return 0;
}
-int perf_event__process(union perf_event *event, struct perf_sample *sample,
- struct perf_session *session)
+size_t perf_event__fprintf(union perf_event *event, FILE *fp)
{
+ size_t ret = fprintf(fp, "PERF_RECORD_%s",
+ perf_event__name(event->header.type));
+
switch (event->header.type) {
case PERF_RECORD_COMM:
- perf_event__process_comm(event, sample, session);
- break;
- case PERF_RECORD_MMAP:
- perf_event__process_mmap(event, sample, session);
+ ret += perf_event__fprintf_comm(event, fp);
break;
case PERF_RECORD_FORK:
case PERF_RECORD_EXIT:
- perf_event__process_task(event, sample, session);
+ ret += perf_event__fprintf_task(event, fp);
+ break;
+ case PERF_RECORD_MMAP:
+ ret += perf_event__fprintf_mmap(event, fp);
+ break;
+ default:
+ ret += fprintf(fp, "\n");
+ }
+
+ return ret;
+}
+
+int perf_event__process(struct perf_tool *tool, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine)
+{
+ switch (event->header.type) {
+ case PERF_RECORD_COMM:
+ perf_event__process_comm(tool, event, sample, machine);
+ break;
+ case PERF_RECORD_MMAP:
+ perf_event__process_mmap(tool, event, sample, machine);
+ break;
+ case PERF_RECORD_FORK:
+ case PERF_RECORD_EXIT:
+ perf_event__process_task(tool, event, sample, machine);
break;
case PERF_RECORD_LOST:
- perf_event__process_lost(event, sample, session);
+ perf_event__process_lost(tool, event, sample, machine);
default:
break;
}
@@ -658,36 +755,29 @@
}
void thread__find_addr_map(struct thread *self,
- struct perf_session *session, u8 cpumode,
- enum map_type type, pid_t pid, u64 addr,
+ struct machine *machine, u8 cpumode,
+ enum map_type type, u64 addr,
struct addr_location *al)
{
struct map_groups *mg = &self->mg;
- struct machine *machine = NULL;
al->thread = self;
al->addr = addr;
al->cpumode = cpumode;
al->filtered = false;
+ if (machine == NULL) {
+ al->map = NULL;
+ return;
+ }
+
if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
al->level = 'k';
- machine = perf_session__find_host_machine(session);
- if (machine == NULL) {
- al->map = NULL;
- return;
- }
mg = &machine->kmaps;
} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
al->level = '.';
- machine = perf_session__find_host_machine(session);
} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
al->level = 'g';
- machine = perf_session__find_machine(session, pid);
- if (machine == NULL) {
- al->map = NULL;
- return;
- }
mg = &machine->kmaps;
} else {
/*
@@ -733,13 +823,12 @@
al->addr = al->map->map_ip(al->map, al->addr);
}
-void thread__find_addr_location(struct thread *self,
- struct perf_session *session, u8 cpumode,
- enum map_type type, pid_t pid, u64 addr,
+void thread__find_addr_location(struct thread *thread, struct machine *machine,
+ u8 cpumode, enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter)
{
- thread__find_addr_map(self, session, cpumode, type, pid, addr, al);
+ thread__find_addr_map(thread, machine, cpumode, type, addr, al);
if (al->map != NULL)
al->sym = map__find_symbol(al->map, al->addr, filter);
else
@@ -747,13 +836,13 @@
}
int perf_event__preprocess_sample(const union perf_event *event,
- struct perf_session *session,
+ struct machine *machine,
struct addr_location *al,
struct perf_sample *sample,
symbol_filter_t filter)
{
u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
- struct thread *thread = perf_session__findnew(session, event->ip.pid);
+ struct thread *thread = machine__findnew_thread(machine, event->ip.pid);
if (thread == NULL)
return -1;
@@ -764,18 +853,18 @@
dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
/*
- * Have we already created the kernel maps for the host machine?
+ * Have we already created the kernel maps for this machine?
*
* This should have happened earlier, when we processed the kernel MMAP
* events, but for older perf.data files there was no such thing, so do
* it now.
*/
if (cpumode == PERF_RECORD_MISC_KERNEL &&
- session->host_machine.vmlinux_maps[MAP__FUNCTION] == NULL)
- machine__create_kernel_maps(&session->host_machine);
+ machine->vmlinux_maps[MAP__FUNCTION] == NULL)
+ machine__create_kernel_maps(machine);
- thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
- event->ip.pid, event->ip.ip, al);
+ thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+ event->ip.ip, al);
dump_printf(" ...... dso: %s\n",
al->map ? al->map->dso->long_name :
al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -783,13 +872,14 @@
al->cpu = sample->cpu;
if (al->map) {
+ struct dso *dso = al->map->dso;
+
if (symbol_conf.dso_list &&
- (!al->map || !al->map->dso ||
- !(strlist__has_entry(symbol_conf.dso_list,
- al->map->dso->short_name) ||
- (al->map->dso->short_name != al->map->dso->long_name &&
- strlist__has_entry(symbol_conf.dso_list,
- al->map->dso->long_name)))))
+ (!dso || !(strlist__has_entry(symbol_conf.dso_list,
+ dso->short_name) ||
+ (dso->short_name != dso->long_name &&
+ strlist__has_entry(symbol_conf.dso_list,
+ dso->long_name)))))
goto out_filtered;
al->sym = map__find_symbol(al->map, al->addr, filter);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 357a85b..cbdeaad 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -2,6 +2,7 @@
#define __PERF_RECORD_H
#include <limits.h>
+#include <stdio.h>
#include "../perf.h"
#include "map.h"
@@ -141,43 +142,54 @@
void perf_event__print_totals(void);
-struct perf_session;
+struct perf_tool;
struct thread_map;
-typedef int (*perf_event__handler_synth_t)(union perf_event *event,
- struct perf_session *session);
-typedef int (*perf_event__handler_t)(union perf_event *event,
+typedef int (*perf_event__handler_t)(struct perf_tool *tool,
+ union perf_event *event,
struct perf_sample *sample,
- struct perf_session *session);
+ struct machine *machine);
-int perf_event__synthesize_thread_map(struct thread_map *threads,
+int perf_event__synthesize_thread_map(struct perf_tool *tool,
+ struct thread_map *threads,
perf_event__handler_t process,
- struct perf_session *session);
-int perf_event__synthesize_threads(perf_event__handler_t process,
- struct perf_session *session);
-int perf_event__synthesize_kernel_mmap(perf_event__handler_t process,
- struct perf_session *session,
+ struct machine *machine);
+int perf_event__synthesize_threads(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine);
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+ perf_event__handler_t process,
struct machine *machine,
const char *symbol_name);
-int perf_event__synthesize_modules(perf_event__handler_t process,
- struct perf_session *session,
+int perf_event__synthesize_modules(struct perf_tool *tool,
+ perf_event__handler_t process,
struct machine *machine);
-int perf_event__process_comm(union perf_event *event, struct perf_sample *sample,
- struct perf_session *session);
-int perf_event__process_lost(union perf_event *event, struct perf_sample *sample,
- struct perf_session *session);
-int perf_event__process_mmap(union perf_event *event, struct perf_sample *sample,
- struct perf_session *session);
-int perf_event__process_task(union perf_event *event, struct perf_sample *sample,
- struct perf_session *session);
-int perf_event__process(union perf_event *event, struct perf_sample *sample,
- struct perf_session *session);
+int perf_event__process_comm(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_lost(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_mmap(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process_task(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
+int perf_event__process(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_sample *sample,
+ struct machine *machine);
struct addr_location;
int perf_event__preprocess_sample(const union perf_event *self,
- struct perf_session *session,
+ struct machine *machine,
struct addr_location *al,
struct perf_sample *sample,
symbol_filter_t filter);
@@ -187,5 +199,13 @@
int perf_event__parse_sample(const union perf_event *event, u64 type,
int sample_size, bool sample_id_all,
struct perf_sample *sample, bool swapped);
+int perf_event__synthesize_sample(union perf_event *event, u64 type,
+ const struct perf_sample *sample,
+ bool swapped);
+
+size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf(union perf_event *event, FILE *fp);
#endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index fbb4b4a..fa18370 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -6,12 +6,16 @@
*
* Released under the GPL v2. (and only v2, not any later version)
*/
+#include "util.h"
+#include "debugfs.h"
#include <poll.h>
#include "cpumap.h"
#include "thread_map.h"
#include "evlist.h"
#include "evsel.h"
-#include "util.h"
+#include <unistd.h>
+
+#include "parse-events.h"
#include <sys/mman.h>
@@ -30,6 +34,7 @@
INIT_HLIST_HEAD(&evlist->heads[i]);
INIT_LIST_HEAD(&evlist->entries);
perf_evlist__set_maps(evlist, cpus, threads);
+ evlist->workload.pid = -1;
}
struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
@@ -43,6 +48,22 @@
return evlist;
}
+void perf_evlist__config_attrs(struct perf_evlist *evlist,
+ struct perf_record_opts *opts)
+{
+ struct perf_evsel *evsel;
+
+ if (evlist->cpus->map[0] < 0)
+ opts->no_inherit = true;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ perf_evsel__config(evsel, opts);
+
+ if (evlist->nr_entries > 1)
+ evsel->attr.sample_type |= PERF_SAMPLE_ID;
+ }
+}
+
static void perf_evlist__purge(struct perf_evlist *evlist)
{
struct perf_evsel *pos, *n;
@@ -76,6 +97,14 @@
++evlist->nr_entries;
}
+static void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
+ struct list_head *list,
+ int nr_entries)
+{
+ list_splice_tail(list, &evlist->entries);
+ evlist->nr_entries += nr_entries;
+}
+
int perf_evlist__add_default(struct perf_evlist *evlist)
{
struct perf_event_attr attr = {
@@ -100,6 +129,126 @@
return -ENOMEM;
}
+int perf_evlist__add_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs)
+{
+ struct perf_evsel *evsel, *n;
+ LIST_HEAD(head);
+ size_t i;
+
+ for (i = 0; i < nr_attrs; i++) {
+ evsel = perf_evsel__new(attrs + i, evlist->nr_entries + i);
+ if (evsel == NULL)
+ goto out_delete_partial_list;
+ list_add_tail(&evsel->node, &head);
+ }
+
+ perf_evlist__splice_list_tail(evlist, &head, nr_attrs);
+
+ return 0;
+
+out_delete_partial_list:
+ list_for_each_entry_safe(evsel, n, &head, node)
+ perf_evsel__delete(evsel);
+ return -1;
+}
+
+static int trace_event__id(const char *evname)
+{
+ char *filename, *colon;
+ int err = -1, fd;
+
+ if (asprintf(&filename, "%s/%s/id", tracing_events_path, evname) < 0)
+ return -1;
+
+ colon = strrchr(filename, ':');
+ if (colon != NULL)
+ *colon = '/';
+
+ fd = open(filename, O_RDONLY);
+ if (fd >= 0) {
+ char id[16];
+ if (read(fd, id, sizeof(id)) > 0)
+ err = atoi(id);
+ close(fd);
+ }
+
+ free(filename);
+ return err;
+}
+
+int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
+ const char *tracepoints[],
+ size_t nr_tracepoints)
+{
+ int err;
+ size_t i;
+ struct perf_event_attr *attrs = zalloc(nr_tracepoints * sizeof(*attrs));
+
+ if (attrs == NULL)
+ return -1;
+
+ for (i = 0; i < nr_tracepoints; i++) {
+ err = trace_event__id(tracepoints[i]);
+
+ if (err < 0)
+ goto out_free_attrs;
+
+ attrs[i].type = PERF_TYPE_TRACEPOINT;
+ attrs[i].config = err;
+ attrs[i].sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
+ PERF_SAMPLE_CPU);
+ attrs[i].sample_period = 1;
+ }
+
+ err = perf_evlist__add_attrs(evlist, attrs, nr_tracepoints);
+out_free_attrs:
+ free(attrs);
+ return err;
+}
+
+static struct perf_evsel *
+ perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
+{
+ struct perf_evsel *evsel;
+
+ list_for_each_entry(evsel, &evlist->entries, node) {
+ if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
+ (int)evsel->attr.config == id)
+ return evsel;
+ }
+
+ return NULL;
+}
+
+int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
+ const struct perf_evsel_str_handler *assocs,
+ size_t nr_assocs)
+{
+ struct perf_evsel *evsel;
+ int err;
+ size_t i;
+
+ for (i = 0; i < nr_assocs; i++) {
+ err = trace_event__id(assocs[i].name);
+ if (err < 0)
+ goto out;
+
+ evsel = perf_evlist__find_tracepoint_by_id(evlist, err);
+ if (evsel == NULL)
+ continue;
+
+ err = -EEXIST;
+ if (evsel->handler.func != NULL)
+ goto out;
+ evsel->handler.func = assocs[i].handler;
+ }
+
+ err = 0;
+out:
+ return err;
+}
+
void perf_evlist__disable(struct perf_evlist *evlist)
{
int cpu, thread;
@@ -126,7 +275,7 @@
}
}
-int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
{
int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
@@ -282,7 +431,7 @@
evlist->mmap = NULL;
}
-int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
{
evlist->nr_mmaps = evlist->cpus->nr;
if (evlist->cpus->map[0] == -1)
@@ -298,8 +447,10 @@
evlist->mmap[idx].mask = mask;
evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
MAP_SHARED, fd, 0);
- if (evlist->mmap[idx].base == MAP_FAILED)
+ if (evlist->mmap[idx].base == MAP_FAILED) {
+ evlist->mmap[idx].base = NULL;
return -1;
+ }
perf_evlist__add_pollfd(evlist, fd);
return 0;
@@ -400,14 +551,22 @@
*
* Using perf_evlist__read_on_cpu does this automatically.
*/
-int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite)
{
unsigned int page_size = sysconf(_SC_PAGE_SIZE);
- int mask = pages * page_size - 1;
struct perf_evsel *evsel;
const struct cpu_map *cpus = evlist->cpus;
const struct thread_map *threads = evlist->threads;
- int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+ int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE), mask;
+
+ /* 512 kiB: default amount of unprivileged mlocked memory */
+ if (pages == UINT_MAX)
+ pages = (512 * 1024) / page_size;
+ else if (!is_power_of_2(pages))
+ return -EINVAL;
+
+ mask = pages * page_size - 1;
if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
return -ENOMEM;
@@ -512,6 +671,38 @@
return first->attr.sample_type;
}
+u16 perf_evlist__id_hdr_size(const struct perf_evlist *evlist)
+{
+ struct perf_evsel *first;
+ 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;
+
+ sample_type = first->attr.sample_type;
+
+ if (sample_type & PERF_SAMPLE_TID)
+ size += sizeof(data->tid) * 2;
+
+ if (sample_type & PERF_SAMPLE_TIME)
+ size += sizeof(data->time);
+
+ if (sample_type & PERF_SAMPLE_ID)
+ size += sizeof(data->id);
+
+ if (sample_type & PERF_SAMPLE_STREAM_ID)
+ size += sizeof(data->stream_id);
+
+ if (sample_type & PERF_SAMPLE_CPU)
+ size += sizeof(data->cpu) * 2;
+out:
+ return size;
+}
+
bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
{
struct perf_evsel *pos, *first;
@@ -569,3 +760,97 @@
return err;
}
+
+int perf_evlist__prepare_workload(struct perf_evlist *evlist,
+ struct perf_record_opts *opts,
+ const char *argv[])
+{
+ int child_ready_pipe[2], go_pipe[2];
+ char bf;
+
+ if (pipe(child_ready_pipe) < 0) {
+ perror("failed to create 'ready' pipe");
+ return -1;
+ }
+
+ if (pipe(go_pipe) < 0) {
+ perror("failed to create 'go' pipe");
+ goto out_close_ready_pipe;
+ }
+
+ evlist->workload.pid = fork();
+ if (evlist->workload.pid < 0) {
+ perror("failed to fork");
+ goto out_close_pipes;
+ }
+
+ if (!evlist->workload.pid) {
+ if (opts->pipe_output)
+ dup2(2, 1);
+
+ close(child_ready_pipe[0]);
+ close(go_pipe[1]);
+ fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+
+ /*
+ * Do a dummy execvp to get the PLT entry resolved,
+ * so we avoid the resolver overhead on the real
+ * execvp call.
+ */
+ execvp("", (char **)argv);
+
+ /*
+ * Tell the parent we're ready to go
+ */
+ close(child_ready_pipe[1]);
+
+ /*
+ * Wait until the parent tells us to go.
+ */
+ if (read(go_pipe[0], &bf, 1) == -1)
+ perror("unable to read pipe");
+
+ execvp(argv[0], (char **)argv);
+
+ perror(argv[0]);
+ kill(getppid(), SIGUSR1);
+ exit(-1);
+ }
+
+ if (!opts->system_wide && opts->target_tid == -1 && opts->target_pid == -1)
+ evlist->threads->map[0] = evlist->workload.pid;
+
+ close(child_ready_pipe[1]);
+ close(go_pipe[0]);
+ /*
+ * wait for child to settle
+ */
+ if (read(child_ready_pipe[0], &bf, 1) == -1) {
+ perror("unable to read pipe");
+ goto out_close_pipes;
+ }
+
+ evlist->workload.cork_fd = go_pipe[1];
+ close(child_ready_pipe[0]);
+ return 0;
+
+out_close_pipes:
+ close(go_pipe[0]);
+ close(go_pipe[1]);
+out_close_ready_pipe:
+ close(child_ready_pipe[0]);
+ close(child_ready_pipe[1]);
+ return -1;
+}
+
+int perf_evlist__start_workload(struct perf_evlist *evlist)
+{
+ if (evlist->workload.cork_fd > 0) {
+ /*
+ * Remove the cork, let it rip!
+ */
+ return close(evlist->workload.cork_fd);
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 1779ffe..8922aee 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -2,12 +2,16 @@
#define __PERF_EVLIST_H 1
#include <linux/list.h>
+#include <stdio.h>
#include "../perf.h"
#include "event.h"
+#include "util.h"
+#include <unistd.h>
struct pollfd;
struct thread_map;
struct cpu_map;
+struct perf_record_opts;
#define PERF_EVLIST__HLIST_BITS 8
#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
@@ -19,6 +23,10 @@
int nr_fds;
int nr_mmaps;
int mmap_len;
+ struct {
+ int cork_fd;
+ pid_t pid;
+ } workload;
bool overwrite;
union perf_event event_copy;
struct perf_mmap *mmap;
@@ -28,6 +36,11 @@
struct perf_evsel *selected;
};
+struct perf_evsel_str_handler {
+ const char *name;
+ void *handler;
+};
+
struct perf_evsel;
struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
@@ -39,11 +52,26 @@
void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry);
int perf_evlist__add_default(struct perf_evlist *evlist);
+int perf_evlist__add_attrs(struct perf_evlist *evlist,
+ struct perf_event_attr *attrs, size_t nr_attrs);
+int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
+ const char *tracepoints[], size_t nr_tracepoints);
+int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
+ const struct perf_evsel_str_handler *assocs,
+ size_t nr_assocs);
+
+#define perf_evlist__add_attrs_array(evlist, array) \
+ perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
+
+#define perf_evlist__add_tracepoints_array(evlist, array) \
+ perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
+
+#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
+ perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
int cpu, int thread, u64 id);
-int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
@@ -52,8 +80,16 @@
int perf_evlist__open(struct perf_evlist *evlist, bool group);
-int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
-int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
+void perf_evlist__config_attrs(struct perf_evlist *evlist,
+ struct perf_record_opts *opts);
+
+int perf_evlist__prepare_workload(struct perf_evlist *evlist,
+ struct perf_record_opts *opts,
+ const char *argv[]);
+int perf_evlist__start_workload(struct perf_evlist *evlist);
+
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+ bool overwrite);
void perf_evlist__munmap(struct perf_evlist *evlist);
void perf_evlist__disable(struct perf_evlist *evlist);
@@ -77,6 +113,7 @@
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);
bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d7915d4..667f3b7 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -63,6 +63,79 @@
return evsel;
}
+void perf_evsel__config(struct perf_evsel *evsel, struct perf_record_opts *opts)
+{
+ struct perf_event_attr *attr = &evsel->attr;
+ int track = !evsel->idx; /* only the first counter needs these */
+
+ attr->sample_id_all = opts->sample_id_all_avail ? 1 : 0;
+ attr->inherit = !opts->no_inherit;
+ attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+ PERF_FORMAT_TOTAL_TIME_RUNNING |
+ PERF_FORMAT_ID;
+
+ attr->sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID;
+
+ /*
+ * We default some events to a 1 default interval. But keep
+ * it a weak assumption overridable by the user.
+ */
+ if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+ opts->user_interval != ULLONG_MAX)) {
+ if (opts->freq) {
+ attr->sample_type |= PERF_SAMPLE_PERIOD;
+ attr->freq = 1;
+ attr->sample_freq = opts->freq;
+ } else {
+ attr->sample_period = opts->default_interval;
+ }
+ }
+
+ if (opts->no_samples)
+ attr->sample_freq = 0;
+
+ if (opts->inherit_stat)
+ attr->inherit_stat = 1;
+
+ if (opts->sample_address) {
+ attr->sample_type |= PERF_SAMPLE_ADDR;
+ attr->mmap_data = track;
+ }
+
+ if (opts->call_graph)
+ attr->sample_type |= PERF_SAMPLE_CALLCHAIN;
+
+ if (opts->system_wide)
+ attr->sample_type |= PERF_SAMPLE_CPU;
+
+ if (opts->period)
+ attr->sample_type |= PERF_SAMPLE_PERIOD;
+
+ if (opts->sample_id_all_avail &&
+ (opts->sample_time || opts->system_wide ||
+ !opts->no_inherit || opts->cpu_list))
+ attr->sample_type |= PERF_SAMPLE_TIME;
+
+ if (opts->raw_samples) {
+ attr->sample_type |= PERF_SAMPLE_TIME;
+ attr->sample_type |= PERF_SAMPLE_RAW;
+ attr->sample_type |= PERF_SAMPLE_CPU;
+ }
+
+ if (opts->no_delay) {
+ attr->watermark = 0;
+ attr->wakeup_events = 1;
+ }
+
+ attr->mmap = track;
+ attr->comm = track;
+
+ if (opts->target_pid == -1 && opts->target_tid == -1 && !opts->system_wide) {
+ attr->disabled = 1;
+ attr->enable_on_exec = 1;
+ }
+}
+
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
int cpu, thread;
@@ -387,7 +460,7 @@
u32 val32[2];
} u;
-
+ memset(data, 0, sizeof(*data));
data->cpu = data->pid = data->tid = -1;
data->stream_id = data->id = data->time = -1ULL;
@@ -504,3 +577,82 @@
return 0;
}
+
+int perf_event__synthesize_sample(union perf_event *event, u64 type,
+ const struct perf_sample *sample,
+ bool swapped)
+{
+ u64 *array;
+
+ /*
+ * used for cross-endian analysis. See git commit 65014ab3
+ * for why this goofiness is needed.
+ */
+ union {
+ u64 val64;
+ u32 val32[2];
+ } u;
+
+ array = event->sample.array;
+
+ if (type & PERF_SAMPLE_IP) {
+ event->ip.ip = sample->ip;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_TID) {
+ u.val32[0] = sample->pid;
+ u.val32[1] = sample->tid;
+ if (swapped) {
+ /*
+ * Inverse of what is done in perf_event__parse_sample
+ */
+ u.val32[0] = bswap_32(u.val32[0]);
+ u.val32[1] = bswap_32(u.val32[1]);
+ u.val64 = bswap_64(u.val64);
+ }
+
+ *array = u.val64;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_TIME) {
+ *array = sample->time;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_ADDR) {
+ *array = sample->addr;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_ID) {
+ *array = sample->id;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_STREAM_ID) {
+ *array = sample->stream_id;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_CPU) {
+ u.val32[0] = sample->cpu;
+ if (swapped) {
+ /*
+ * Inverse of what is done in perf_event__parse_sample
+ */
+ u.val32[0] = bswap_32(u.val32[0]);
+ u.val64 = bswap_64(u.val64);
+ }
+ *array = u.val64;
+ array++;
+ }
+
+ if (type & PERF_SAMPLE_PERIOD) {
+ *array = sample->period;
+ array++;
+ }
+
+ return 0;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b1d15e6..326b8e4 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -61,12 +61,17 @@
off_t id_offset;
};
struct cgroup_sel *cgrp;
+ struct {
+ void *func;
+ void *data;
+ } handler;
bool supported;
};
struct cpu_map;
struct thread_map;
struct perf_evlist;
+struct perf_record_opts;
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
void perf_evsel__init(struct perf_evsel *evsel,
@@ -74,6 +79,9 @@
void perf_evsel__exit(struct perf_evsel *evsel);
void perf_evsel__delete(struct perf_evsel *evsel);
+void perf_evsel__config(struct perf_evsel *evsel,
+ struct perf_record_opts *opts);
+
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 33c17a2..3e7e0b0 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -8,6 +8,7 @@
#include <stdlib.h>
#include <linux/list.h>
#include <linux/kernel.h>
+#include <linux/bitops.h>
#include <sys/utsname.h>
#include "evlist.h"
@@ -28,9 +29,6 @@
static u32 header_argc;
static const char **header_argv;
-static int dsos__write_buildid_table(struct perf_header *header, int fd);
-static int perf_session__cache_build_ids(struct perf_session *session);
-
int perf_header__push_event(u64 id, const char *name)
{
if (strlen(name) > MAX_EVENT_NAME)
@@ -187,6 +185,252 @@
return 0;
}
+#define dsos__for_each_with_build_id(pos, head) \
+ list_for_each_entry(pos, head, node) \
+ if (!pos->has_build_id) \
+ continue; \
+ else
+
+static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
+ u16 misc, int fd)
+{
+ struct dso *pos;
+
+ dsos__for_each_with_build_id(pos, head) {
+ int err;
+ struct build_id_event b;
+ size_t len;
+
+ if (!pos->hit)
+ continue;
+ len = pos->long_name_len + 1;
+ len = ALIGN(len, NAME_ALIGN);
+ memset(&b, 0, sizeof(b));
+ memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
+ b.pid = pid;
+ b.header.misc = misc;
+ b.header.size = sizeof(b) + len;
+ err = do_write(fd, &b, sizeof(b));
+ if (err < 0)
+ return err;
+ err = write_padded(fd, pos->long_name,
+ pos->long_name_len + 1, len);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
+static int machine__write_buildid_table(struct machine *machine, int fd)
+{
+ int err;
+ u16 kmisc = PERF_RECORD_MISC_KERNEL,
+ umisc = PERF_RECORD_MISC_USER;
+
+ if (!machine__is_host(machine)) {
+ kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+ umisc = PERF_RECORD_MISC_GUEST_USER;
+ }
+
+ err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
+ kmisc, fd);
+ if (err == 0)
+ err = __dsos__write_buildid_table(&machine->user_dsos,
+ machine->pid, umisc, fd);
+ return err;
+}
+
+static int dsos__write_buildid_table(struct perf_header *header, int fd)
+{
+ struct perf_session *session = container_of(header,
+ struct perf_session, header);
+ struct rb_node *nd;
+ int err = machine__write_buildid_table(&session->host_machine, fd);
+
+ if (err)
+ return err;
+
+ for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+ struct machine *pos = rb_entry(nd, struct machine, rb_node);
+ err = machine__write_buildid_table(pos, fd);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+ const char *name, bool is_kallsyms)
+{
+ const size_t size = PATH_MAX;
+ char *realname, *filename = zalloc(size),
+ *linkname = zalloc(size), *targetname;
+ int len, err = -1;
+
+ if (is_kallsyms) {
+ if (symbol_conf.kptr_restrict) {
+ pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+ return 0;
+ }
+ realname = (char *)name;
+ } else
+ realname = realpath(name, NULL);
+
+ if (realname == NULL || filename == NULL || linkname == NULL)
+ goto out_free;
+
+ len = snprintf(filename, size, "%s%s%s",
+ debugdir, is_kallsyms ? "/" : "", realname);
+ if (mkdir_p(filename, 0755))
+ goto out_free;
+
+ snprintf(filename + len, sizeof(filename) - len, "/%s", sbuild_id);
+
+ if (access(filename, F_OK)) {
+ if (is_kallsyms) {
+ if (copyfile("/proc/kallsyms", filename))
+ goto out_free;
+ } else if (link(realname, filename) && copyfile(name, filename))
+ goto out_free;
+ }
+
+ len = snprintf(linkname, size, "%s/.build-id/%.2s",
+ debugdir, sbuild_id);
+
+ if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+ goto out_free;
+
+ snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+ targetname = filename + strlen(debugdir) - 5;
+ memcpy(targetname, "../..", 5);
+
+ if (symlink(targetname, linkname) == 0)
+ err = 0;
+out_free:
+ if (!is_kallsyms)
+ free(realname);
+ free(filename);
+ free(linkname);
+ return err;
+}
+
+static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+ const char *name, const char *debugdir,
+ bool is_kallsyms)
+{
+ char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+ build_id__sprintf(build_id, build_id_size, sbuild_id);
+
+ return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
+}
+
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
+{
+ const size_t size = PATH_MAX;
+ char *filename = zalloc(size),
+ *linkname = zalloc(size);
+ int err = -1;
+
+ if (filename == NULL || linkname == NULL)
+ goto out_free;
+
+ snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+ debugdir, sbuild_id, sbuild_id + 2);
+
+ if (access(linkname, F_OK))
+ goto out_free;
+
+ if (readlink(linkname, filename, size - 1) < 0)
+ goto out_free;
+
+ if (unlink(linkname))
+ goto out_free;
+
+ /*
+ * Since the link is relative, we must make it absolute:
+ */
+ snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+ debugdir, sbuild_id, filename);
+
+ if (unlink(linkname))
+ goto out_free;
+
+ err = 0;
+out_free:
+ free(filename);
+ free(linkname);
+ return err;
+}
+
+static int dso__cache_build_id(struct dso *dso, const char *debugdir)
+{
+ bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+
+ return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
+ dso->long_name, debugdir, is_kallsyms);
+}
+
+static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
+{
+ struct dso *pos;
+ int err = 0;
+
+ dsos__for_each_with_build_id(pos, head)
+ if (dso__cache_build_id(pos, debugdir))
+ err = -1;
+
+ return err;
+}
+
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
+{
+ int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
+ ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
+ return ret;
+}
+
+static int perf_session__cache_build_ids(struct perf_session *session)
+{
+ struct rb_node *nd;
+ int ret;
+ char debugdir[PATH_MAX];
+
+ snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
+
+ if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+ return -1;
+
+ ret = machine__cache_build_ids(&session->host_machine, debugdir);
+
+ for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+ struct machine *pos = rb_entry(nd, struct machine, rb_node);
+ ret |= machine__cache_build_ids(pos, debugdir);
+ }
+ return ret ? -1 : 0;
+}
+
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
+{
+ bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
+ ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
+ return ret;
+}
+
+static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
+{
+ struct rb_node *nd;
+ bool ret = machine__read_build_ids(&session->host_machine, with_hits);
+
+ for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
+ struct machine *pos = rb_entry(nd, struct machine, rb_node);
+ ret |= machine__read_build_ids(pos, with_hits);
+ }
+
+ return ret;
+}
+
static int write_trace_info(int fd, struct perf_header *h __used,
struct perf_evlist *evlist)
{
@@ -202,6 +446,9 @@
session = container_of(h, struct perf_session, header);
+ if (!perf_session__read_build_ids(session, true))
+ return -1;
+
err = dsos__write_buildid_table(h, fd);
if (err < 0) {
pr_debug("failed to write buildid table\n");
@@ -1065,26 +1312,30 @@
bool full_only;
};
-#define FEAT_OPA(n, w, p) \
- [n] = { .name = #n, .write = w, .print = p }
-#define FEAT_OPF(n, w, p) \
- [n] = { .name = #n, .write = w, .print = p, .full_only = true }
+#define FEAT_OPA(n, func) \
+ [n] = { .name = #n, .write = write_##func, .print = print_##func }
+#define FEAT_OPF(n, func) \
+ [n] = { .name = #n, .write = write_##func, .print = print_##func, .full_only = true }
+
+/* feature_ops not implemented: */
+#define print_trace_info NULL
+#define print_build_id NULL
static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
- FEAT_OPA(HEADER_TRACE_INFO, write_trace_info, NULL),
- FEAT_OPA(HEADER_BUILD_ID, write_build_id, NULL),
- FEAT_OPA(HEADER_HOSTNAME, write_hostname, print_hostname),
- FEAT_OPA(HEADER_OSRELEASE, write_osrelease, print_osrelease),
- FEAT_OPA(HEADER_VERSION, write_version, print_version),
- FEAT_OPA(HEADER_ARCH, write_arch, print_arch),
- FEAT_OPA(HEADER_NRCPUS, write_nrcpus, print_nrcpus),
- FEAT_OPA(HEADER_CPUDESC, write_cpudesc, print_cpudesc),
- FEAT_OPA(HEADER_CPUID, write_cpuid, print_cpuid),
- FEAT_OPA(HEADER_TOTAL_MEM, write_total_mem, print_total_mem),
- FEAT_OPA(HEADER_EVENT_DESC, write_event_desc, print_event_desc),
- FEAT_OPA(HEADER_CMDLINE, write_cmdline, print_cmdline),
- FEAT_OPF(HEADER_CPU_TOPOLOGY, write_cpu_topology, print_cpu_topology),
- FEAT_OPF(HEADER_NUMA_TOPOLOGY, write_numa_topology, print_numa_topology),
+ FEAT_OPA(HEADER_TRACE_INFO, trace_info),
+ FEAT_OPA(HEADER_BUILD_ID, build_id),
+ FEAT_OPA(HEADER_HOSTNAME, hostname),
+ FEAT_OPA(HEADER_OSRELEASE, osrelease),
+ FEAT_OPA(HEADER_VERSION, version),
+ FEAT_OPA(HEADER_ARCH, arch),
+ FEAT_OPA(HEADER_NRCPUS, nrcpus),
+ 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_OPA(HEADER_CMDLINE, cmdline),
+ FEAT_OPF(HEADER_CPU_TOPOLOGY, cpu_topology),
+ FEAT_OPF(HEADER_NUMA_TOPOLOGY, numa_topology),
};
struct header_print_data {
@@ -1103,9 +1354,9 @@
"%d, continuing...\n", section->offset, feat);
return 0;
}
- if (feat < HEADER_TRACE_INFO || feat >= HEADER_LAST_FEATURE) {
+ if (feat >= HEADER_LAST_FEATURE) {
pr_warning("unknown feature %d\n", feat);
- return -1;
+ return 0;
}
if (!feat_ops[feat].print)
return 0;
@@ -1132,252 +1383,6 @@
return 0;
}
-#define dsos__for_each_with_build_id(pos, head) \
- list_for_each_entry(pos, head, node) \
- if (!pos->has_build_id) \
- continue; \
- else
-
-static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
- u16 misc, int fd)
-{
- struct dso *pos;
-
- dsos__for_each_with_build_id(pos, head) {
- int err;
- struct build_id_event b;
- size_t len;
-
- if (!pos->hit)
- continue;
- len = pos->long_name_len + 1;
- len = ALIGN(len, NAME_ALIGN);
- memset(&b, 0, sizeof(b));
- memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
- b.pid = pid;
- b.header.misc = misc;
- b.header.size = sizeof(b) + len;
- err = do_write(fd, &b, sizeof(b));
- if (err < 0)
- return err;
- err = write_padded(fd, pos->long_name,
- pos->long_name_len + 1, len);
- if (err < 0)
- return err;
- }
-
- return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
- int err;
- u16 kmisc = PERF_RECORD_MISC_KERNEL,
- umisc = PERF_RECORD_MISC_USER;
-
- if (!machine__is_host(machine)) {
- kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
- umisc = PERF_RECORD_MISC_GUEST_USER;
- }
-
- err = __dsos__write_buildid_table(&machine->kernel_dsos, machine->pid,
- kmisc, fd);
- if (err == 0)
- err = __dsos__write_buildid_table(&machine->user_dsos,
- machine->pid, umisc, fd);
- return err;
-}
-
-static int dsos__write_buildid_table(struct perf_header *header, int fd)
-{
- struct perf_session *session = container_of(header,
- struct perf_session, header);
- struct rb_node *nd;
- int err = machine__write_buildid_table(&session->host_machine, fd);
-
- if (err)
- return err;
-
- for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
- struct machine *pos = rb_entry(nd, struct machine, rb_node);
- err = machine__write_buildid_table(pos, fd);
- if (err)
- break;
- }
- return err;
-}
-
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
- const char *name, bool is_kallsyms)
-{
- const size_t size = PATH_MAX;
- char *realname, *filename = zalloc(size),
- *linkname = zalloc(size), *targetname;
- int len, err = -1;
-
- if (is_kallsyms) {
- if (symbol_conf.kptr_restrict) {
- pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
- return 0;
- }
- realname = (char *)name;
- } else
- realname = realpath(name, NULL);
-
- if (realname == NULL || filename == NULL || linkname == NULL)
- goto out_free;
-
- len = snprintf(filename, size, "%s%s%s",
- debugdir, is_kallsyms ? "/" : "", realname);
- if (mkdir_p(filename, 0755))
- goto out_free;
-
- snprintf(filename + len, sizeof(filename) - len, "/%s", sbuild_id);
-
- if (access(filename, F_OK)) {
- if (is_kallsyms) {
- if (copyfile("/proc/kallsyms", filename))
- goto out_free;
- } else if (link(realname, filename) && copyfile(name, filename))
- goto out_free;
- }
-
- len = snprintf(linkname, size, "%s/.build-id/%.2s",
- debugdir, sbuild_id);
-
- if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
- goto out_free;
-
- snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
- targetname = filename + strlen(debugdir) - 5;
- memcpy(targetname, "../..", 5);
-
- if (symlink(targetname, linkname) == 0)
- err = 0;
-out_free:
- if (!is_kallsyms)
- free(realname);
- free(filename);
- free(linkname);
- return err;
-}
-
-static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
- const char *name, const char *debugdir,
- bool is_kallsyms)
-{
- char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
- build_id__sprintf(build_id, build_id_size, sbuild_id);
-
- return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
-}
-
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
-{
- const size_t size = PATH_MAX;
- char *filename = zalloc(size),
- *linkname = zalloc(size);
- int err = -1;
-
- if (filename == NULL || linkname == NULL)
- goto out_free;
-
- snprintf(linkname, size, "%s/.build-id/%.2s/%s",
- debugdir, sbuild_id, sbuild_id + 2);
-
- if (access(linkname, F_OK))
- goto out_free;
-
- if (readlink(linkname, filename, size - 1) < 0)
- goto out_free;
-
- if (unlink(linkname))
- goto out_free;
-
- /*
- * Since the link is relative, we must make it absolute:
- */
- snprintf(linkname, size, "%s/.build-id/%.2s/%s",
- debugdir, sbuild_id, filename);
-
- if (unlink(linkname))
- goto out_free;
-
- err = 0;
-out_free:
- free(filename);
- free(linkname);
- return err;
-}
-
-static int dso__cache_build_id(struct dso *dso, const char *debugdir)
-{
- bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
-
- return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
- dso->long_name, debugdir, is_kallsyms);
-}
-
-static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
-{
- struct dso *pos;
- int err = 0;
-
- dsos__for_each_with_build_id(pos, head)
- if (dso__cache_build_id(pos, debugdir))
- err = -1;
-
- return err;
-}
-
-static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
-{
- int ret = __dsos__cache_build_ids(&machine->kernel_dsos, debugdir);
- ret |= __dsos__cache_build_ids(&machine->user_dsos, debugdir);
- return ret;
-}
-
-static int perf_session__cache_build_ids(struct perf_session *session)
-{
- struct rb_node *nd;
- int ret;
- char debugdir[PATH_MAX];
-
- snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
- if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
- return -1;
-
- ret = machine__cache_build_ids(&session->host_machine, debugdir);
-
- for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
- struct machine *pos = rb_entry(nd, struct machine, rb_node);
- ret |= machine__cache_build_ids(pos, debugdir);
- }
- return ret ? -1 : 0;
-}
-
-static bool machine__read_build_ids(struct machine *machine, bool with_hits)
-{
- bool ret = __dsos__read_build_ids(&machine->kernel_dsos, with_hits);
- ret |= __dsos__read_build_ids(&machine->user_dsos, with_hits);
- return ret;
-}
-
-static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
-{
- struct rb_node *nd;
- bool ret = machine__read_build_ids(&session->host_machine, with_hits);
-
- for (nd = rb_first(&session->machines); nd; nd = rb_next(nd)) {
- struct machine *pos = rb_entry(nd, struct machine, rb_node);
- ret |= machine__read_build_ids(pos, with_hits);
- }
-
- return ret;
-}
-
static int do_write_feat(int fd, struct perf_header *h, int type,
struct perf_file_section **p,
struct perf_evlist *evlist)
@@ -1386,6 +1391,8 @@
int ret = 0;
if (perf_header__has_feat(h, type)) {
+ if (!feat_ops[type].write)
+ return -1;
(*p)->offset = lseek(fd, 0, SEEK_CUR);
@@ -1408,18 +1415,12 @@
struct perf_evlist *evlist, int fd)
{
int nr_sections;
- struct perf_session *session;
struct perf_file_section *feat_sec, *p;
int sec_size;
u64 sec_start;
+ int feat;
int err;
- session = container_of(header, struct perf_session, header);
-
- if (perf_header__has_feat(header, HEADER_BUILD_ID &&
- !perf_session__read_build_ids(session, true)))
- perf_header__clear_feat(header, HEADER_BUILD_ID);
-
nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
if (!nr_sections)
return 0;
@@ -1433,64 +1434,11 @@
sec_start = header->data_offset + header->data_size;
lseek(fd, sec_start + sec_size, SEEK_SET);
- err = do_write_feat(fd, header, HEADER_TRACE_INFO, &p, evlist);
- if (err)
- goto out_free;
-
- err = do_write_feat(fd, header, HEADER_BUILD_ID, &p, evlist);
- if (err) {
- perf_header__clear_feat(header, HEADER_BUILD_ID);
- goto out_free;
+ for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
+ if (do_write_feat(fd, header, feat, &p, evlist))
+ perf_header__clear_feat(header, feat);
}
- err = do_write_feat(fd, header, HEADER_HOSTNAME, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_HOSTNAME);
-
- err = do_write_feat(fd, header, HEADER_OSRELEASE, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_OSRELEASE);
-
- err = do_write_feat(fd, header, HEADER_VERSION, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_VERSION);
-
- err = do_write_feat(fd, header, HEADER_ARCH, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_ARCH);
-
- err = do_write_feat(fd, header, HEADER_NRCPUS, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_NRCPUS);
-
- err = do_write_feat(fd, header, HEADER_CPUDESC, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_CPUDESC);
-
- err = do_write_feat(fd, header, HEADER_CPUID, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_CPUID);
-
- err = do_write_feat(fd, header, HEADER_TOTAL_MEM, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_TOTAL_MEM);
-
- err = do_write_feat(fd, header, HEADER_CMDLINE, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_CMDLINE);
-
- err = do_write_feat(fd, header, HEADER_EVENT_DESC, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_EVENT_DESC);
-
- err = do_write_feat(fd, header, HEADER_CPU_TOPOLOGY, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_CPU_TOPOLOGY);
-
- err = do_write_feat(fd, header, HEADER_NUMA_TOPOLOGY, &p, evlist);
- if (err)
- perf_header__clear_feat(header, HEADER_NUMA_TOPOLOGY);
-
lseek(fd, sec_start, SEEK_SET);
/*
* may write more than needed due to dropped feature, but
@@ -1499,7 +1447,6 @@
err = do_write(fd, feat_sec, sec_size);
if (err < 0)
pr_debug("failed to write feature section\n");
-out_free:
free(feat_sec);
return err;
}
@@ -1637,20 +1584,20 @@
int perf_header__process_sections(struct perf_header *header, int fd,
void *data,
int (*process)(struct perf_file_section *section,
- struct perf_header *ph,
- int feat, int fd, void *data))
+ struct perf_header *ph,
+ int feat, int fd, void *data))
{
- struct perf_file_section *feat_sec;
+ struct perf_file_section *feat_sec, *sec;
int nr_sections;
int sec_size;
- int idx = 0;
- int err = -1, feat = 1;
+ int feat;
+ int err;
nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS);
if (!nr_sections)
return 0;
- feat_sec = calloc(sizeof(*feat_sec), nr_sections);
+ feat_sec = sec = calloc(sizeof(*feat_sec), nr_sections);
if (!feat_sec)
return -1;
@@ -1658,20 +1605,16 @@
lseek(fd, header->data_offset + header->data_size, SEEK_SET);
- if (perf_header__getbuffer64(header, fd, feat_sec, sec_size))
+ err = perf_header__getbuffer64(header, fd, feat_sec, sec_size);
+ if (err < 0)
goto out_free;
- err = 0;
- while (idx < nr_sections && feat < HEADER_LAST_FEATURE) {
- if (perf_header__has_feat(header, feat)) {
- struct perf_file_section *sec = &feat_sec[idx++];
-
- err = process(sec, header, feat, fd, data);
- if (err < 0)
- break;
- }
- ++feat;
+ for_each_set_bit(feat, header->adds_features, HEADER_LAST_FEATURE) {
+ err = process(sec++, header, feat, fd, data);
+ if (err < 0)
+ goto out_free;
}
+ err = 0;
out_free:
free(feat_sec);
return err;
@@ -1906,32 +1849,21 @@
return 0;
}
+ if (feat >= HEADER_LAST_FEATURE) {
+ pr_debug("unknown feature %d, continuing...\n", feat);
+ return 0;
+ }
+
switch (feat) {
case HEADER_TRACE_INFO:
trace_report(fd, false);
break;
-
case HEADER_BUILD_ID:
if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
pr_debug("Failed to read buildids, continuing...\n");
break;
-
- case HEADER_HOSTNAME:
- case HEADER_OSRELEASE:
- case HEADER_VERSION:
- case HEADER_ARCH:
- case HEADER_NRCPUS:
- case HEADER_CPUDESC:
- case HEADER_CPUID:
- case HEADER_TOTAL_MEM:
- case HEADER_CMDLINE:
- case HEADER_EVENT_DESC:
- case HEADER_CPU_TOPOLOGY:
- case HEADER_NUMA_TOPOLOGY:
- break;
-
default:
- pr_debug("unknown feature %d, continuing...\n", feat);
+ break;
}
return 0;
@@ -2041,6 +1973,8 @@
lseek(fd, tmp, SEEK_SET);
}
+ symbol_conf.nr_events = nr_attrs;
+
if (f_header.event_types.size) {
lseek(fd, f_header.event_types.offset, SEEK_SET);
events = malloc(f_header.event_types.size);
@@ -2068,9 +2002,9 @@
return -ENOMEM;
}
-int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
- perf_event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_attr(struct perf_tool *tool,
+ struct perf_event_attr *attr, u16 ids, u64 *id,
+ perf_event__handler_t process)
{
union perf_event *ev;
size_t size;
@@ -2092,22 +2026,23 @@
ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
ev->attr.header.size = size;
- err = process(ev, NULL, session);
+ err = process(tool, ev, NULL, NULL);
free(ev);
return err;
}
-int perf_session__synthesize_attrs(struct perf_session *session,
+int perf_event__synthesize_attrs(struct perf_tool *tool,
+ struct perf_session *session,
perf_event__handler_t process)
{
struct perf_evsel *attr;
int err = 0;
list_for_each_entry(attr, &session->evlist->entries, node) {
- err = perf_event__synthesize_attr(&attr->attr, attr->ids,
- attr->id, process, session);
+ err = perf_event__synthesize_attr(tool, &attr->attr, attr->ids,
+ attr->id, process);
if (err) {
pr_debug("failed to create perf header attribute\n");
return err;
@@ -2118,23 +2053,23 @@
}
int perf_event__process_attr(union perf_event *event,
- struct perf_session *session)
+ struct perf_evlist **pevlist)
{
unsigned int i, ids, n_ids;
struct perf_evsel *evsel;
+ struct perf_evlist *evlist = *pevlist;
- if (session->evlist == NULL) {
- session->evlist = perf_evlist__new(NULL, NULL);
- if (session->evlist == NULL)
+ if (evlist == NULL) {
+ *pevlist = evlist = perf_evlist__new(NULL, NULL);
+ if (evlist == NULL)
return -ENOMEM;
}
- evsel = perf_evsel__new(&event->attr.attr,
- session->evlist->nr_entries);
+ evsel = perf_evsel__new(&event->attr.attr, evlist->nr_entries);
if (evsel == NULL)
return -ENOMEM;
- perf_evlist__add(session->evlist, evsel);
+ perf_evlist__add(evlist, evsel);
ids = event->header.size;
ids -= (void *)&event->attr.id - (void *)event;
@@ -2148,18 +2083,16 @@
return -ENOMEM;
for (i = 0; i < n_ids; i++) {
- perf_evlist__id_add(session->evlist, evsel, 0, i,
- event->attr.id[i]);
+ perf_evlist__id_add(evlist, evsel, 0, i, event->attr.id[i]);
}
- perf_session__update_sample_type(session);
-
return 0;
}
-int perf_event__synthesize_event_type(u64 event_id, char *name,
+int perf_event__synthesize_event_type(struct perf_tool *tool,
+ u64 event_id, char *name,
perf_event__handler_t process,
- struct perf_session *session)
+ struct machine *machine)
{
union perf_event ev;
size_t size = 0;
@@ -2177,13 +2110,14 @@
ev.event_type.header.size = sizeof(ev.event_type) -
(sizeof(ev.event_type.event_type.name) - size);
- err = process(&ev, NULL, session);
+ err = process(tool, &ev, NULL, machine);
return err;
}
-int perf_event__synthesize_event_types(perf_event__handler_t process,
- struct perf_session *session)
+int perf_event__synthesize_event_types(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine)
{
struct perf_trace_event_type *type;
int i, err = 0;
@@ -2191,9 +2125,9 @@
for (i = 0; i < event_count; i++) {
type = &events[i];
- err = perf_event__synthesize_event_type(type->event_id,
+ err = perf_event__synthesize_event_type(tool, type->event_id,
type->name, process,
- session);
+ machine);
if (err) {
pr_debug("failed to create perf header event type\n");
return err;
@@ -2203,8 +2137,8 @@
return err;
}
-int perf_event__process_event_type(union perf_event *event,
- struct perf_session *session __unused)
+int perf_event__process_event_type(struct perf_tool *tool __unused,
+ union perf_event *event)
{
if (perf_header__push_event(event->event_type.event_type.event_id,
event->event_type.event_type.name) < 0)
@@ -2213,9 +2147,9 @@
return 0;
}
-int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
- perf_event__handler_t process,
- struct perf_session *session __unused)
+int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
+ struct perf_evlist *evlist,
+ perf_event__handler_t process)
{
union perf_event ev;
struct tracing_data *tdata;
@@ -2246,7 +2180,7 @@
ev.tracing_data.header.size = sizeof(ev.tracing_data);
ev.tracing_data.size = aligned_size;
- process(&ev, NULL, session);
+ process(tool, &ev, NULL, NULL);
/*
* The put function will copy all the tracing data
@@ -2288,10 +2222,10 @@
return size_read + padding;
}
-int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+int perf_event__synthesize_build_id(struct perf_tool *tool,
+ struct dso *pos, u16 misc,
perf_event__handler_t process,
- struct machine *machine,
- struct perf_session *session)
+ struct machine *machine)
{
union perf_event ev;
size_t len;
@@ -2311,12 +2245,13 @@
ev.build_id.header.size = sizeof(ev.build_id) + len;
memcpy(&ev.build_id.filename, pos->long_name, pos->long_name_len);
- err = process(&ev, NULL, session);
+ err = process(tool, &ev, NULL, machine);
return err;
}
-int perf_event__process_build_id(union perf_event *event,
+int perf_event__process_build_id(struct perf_tool *tool __used,
+ union perf_event *event,
struct perf_session *session)
{
__event_process_build_id(&event->build_id,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3d5a742..ac4ec95 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -10,7 +10,8 @@
#include <linux/bitmap.h>
enum {
- HEADER_TRACE_INFO = 1,
+ HEADER_RESERVED = 0, /* always cleared */
+ HEADER_TRACE_INFO = 1,
HEADER_BUILD_ID,
HEADER_HOSTNAME,
@@ -27,10 +28,9 @@
HEADER_NUMA_TOPOLOGY,
HEADER_LAST_FEATURE,
+ HEADER_FEAT_BITS = 256,
};
-#define HEADER_FEAT_BITS 256
-
struct perf_file_section {
u64 offset;
u64 size;
@@ -68,6 +68,7 @@
};
struct perf_evlist;
+struct perf_session;
int perf_session__read_header(struct perf_session *session, int fd);
int perf_session__write_header(struct perf_session *session,
@@ -96,32 +97,36 @@
const char *name, bool is_kallsyms);
int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
-int perf_event__synthesize_attr(struct perf_event_attr *attr, u16 ids, u64 *id,
- perf_event__handler_t process,
- struct perf_session *session);
-int perf_session__synthesize_attrs(struct perf_session *session,
- perf_event__handler_t process);
-int perf_event__process_attr(union perf_event *event, struct perf_session *session);
+int perf_event__synthesize_attr(struct perf_tool *tool,
+ struct perf_event_attr *attr, u16 ids, u64 *id,
+ perf_event__handler_t process);
+int perf_event__synthesize_attrs(struct perf_tool *tool,
+ struct perf_session *session,
+ perf_event__handler_t process);
+int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist);
-int perf_event__synthesize_event_type(u64 event_id, char *name,
+int perf_event__synthesize_event_type(struct perf_tool *tool,
+ u64 event_id, char *name,
perf_event__handler_t process,
- struct perf_session *session);
-int perf_event__synthesize_event_types(perf_event__handler_t process,
- struct perf_session *session);
-int perf_event__process_event_type(union perf_event *event,
- struct perf_session *session);
+ struct machine *machine);
+int perf_event__synthesize_event_types(struct perf_tool *tool,
+ perf_event__handler_t process,
+ struct machine *machine);
+int perf_event__process_event_type(struct perf_tool *tool,
+ union perf_event *event);
-int perf_event__synthesize_tracing_data(int fd, struct perf_evlist *evlist,
- perf_event__handler_t process,
- struct perf_session *session);
+int perf_event__synthesize_tracing_data(struct perf_tool *tool,
+ int fd, struct perf_evlist *evlist,
+ perf_event__handler_t process);
int perf_event__process_tracing_data(union perf_event *event,
struct perf_session *session);
-int perf_event__synthesize_build_id(struct dso *pos, u16 misc,
+int perf_event__synthesize_build_id(struct perf_tool *tool,
+ struct dso *pos, u16 misc,
perf_event__handler_t process,
- struct machine *machine,
- struct perf_session *session);
-int perf_event__process_build_id(union perf_event *event,
+ struct machine *machine);
+int perf_event__process_build_id(struct perf_tool *tool,
+ union perf_event *event,
struct perf_session *session);
/*
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 89289c8..ff6f9d5 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -117,7 +117,6 @@
static inline int hist_entry__tui_annotate(struct hist_entry *self __used,
int evidx __used,
- int nr_events __used,
void(*timer)(void *arg) __used,
void *arg __used,
int delay_secs __used)
@@ -128,7 +127,7 @@
#define K_RIGHT -2
#else
#include "ui/keysyms.h"
-int hist_entry__tui_annotate(struct hist_entry *he, int evidx, int nr_events,
+int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
void(*timer)(void *arg), void *arg, int delay_secs);
int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index 305c848..62cdee7 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -9,6 +9,17 @@
#define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
+#define for_each_set_bit(bit, addr, size) \
+ for ((bit) = find_first_bit((addr), (size)); \
+ (bit) < (size); \
+ (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_cont(bit, addr, size) \
+ for ((bit) = find_next_bit((addr), (size), (bit)); \
+ (bit) < (size); \
+ (bit) = find_next_bit((addr), (size), (bit) + 1))
+
static inline void set_bit(int nr, unsigned long *addr)
{
addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
@@ -30,4 +41,111 @@
return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
}
+#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+ int num = 0;
+
+#if BITS_PER_LONG == 64
+ if ((word & 0xffffffff) == 0) {
+ num += 32;
+ word >>= 32;
+ }
+#endif
+ if ((word & 0xffff) == 0) {
+ num += 16;
+ word >>= 16;
+ }
+ if ((word & 0xff) == 0) {
+ num += 8;
+ word >>= 8;
+ }
+ if ((word & 0xf) == 0) {
+ num += 4;
+ word >>= 4;
+ }
+ if ((word & 0x3) == 0) {
+ num += 2;
+ word >>= 2;
+ }
+ if ((word & 0x1) == 0)
+ num += 1;
+ return num;
+}
+
+/*
+ * Find the first set bit in a memory region.
+ */
+static inline unsigned long
+find_first_bit(const unsigned long *addr, unsigned long size)
+{
+ const unsigned long *p = addr;
+ unsigned long result = 0;
+ unsigned long tmp;
+
+ while (size & ~(BITS_PER_LONG-1)) {
+ if ((tmp = *(p++)))
+ goto found;
+ result += BITS_PER_LONG;
+ size -= BITS_PER_LONG;
+ }
+ if (!size)
+ return result;
+
+ tmp = (*p) & (~0UL >> (BITS_PER_LONG - size));
+ if (tmp == 0UL) /* Are any bits set? */
+ return result + size; /* Nope. */
+found:
+ return result + __ffs(tmp);
+}
+
+/*
+ * Find the next set bit in a memory region.
+ */
+static inline unsigned long
+find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset)
+{
+ const unsigned long *p = addr + BITOP_WORD(offset);
+ unsigned long result = offset & ~(BITS_PER_LONG-1);
+ unsigned long tmp;
+
+ if (offset >= size)
+ return size;
+ size -= result;
+ offset %= BITS_PER_LONG;
+ if (offset) {
+ tmp = *(p++);
+ tmp &= (~0UL << offset);
+ if (size < BITS_PER_LONG)
+ goto found_first;
+ if (tmp)
+ goto found_middle;
+ size -= BITS_PER_LONG;
+ result += BITS_PER_LONG;
+ }
+ while (size & ~(BITS_PER_LONG-1)) {
+ if ((tmp = *(p++)))
+ goto found_middle;
+ result += BITS_PER_LONG;
+ size -= BITS_PER_LONG;
+ }
+ if (!size)
+ return result;
+ tmp = *p;
+
+found_first:
+ tmp &= (~0UL >> (BITS_PER_LONG - size));
+ if (tmp == 0UL) /* Are any bits set? */
+ return result + size; /* Nope. */
+found_middle:
+ return result + __ffs(tmp);
+}
+
#endif
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 78284b1..316aa0a 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -562,6 +562,10 @@
INIT_LIST_HEAD(&self->user_dsos);
INIT_LIST_HEAD(&self->kernel_dsos);
+ self->threads = RB_ROOT;
+ INIT_LIST_HEAD(&self->dead_threads);
+ self->last_match = NULL;
+
self->kmaps.machine = self;
self->pid = pid;
self->root_dir = strdup(root_dir);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 890d855..2b8017f 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -18,9 +18,11 @@
extern const char *map_type__name[MAP__NR_TYPES];
struct dso;
+struct ip_callchain;
struct ref_reloc_sym;
struct map_groups;
struct machine;
+struct perf_evsel;
struct map {
union {
@@ -61,7 +63,11 @@
struct machine {
struct rb_node rb_node;
pid_t pid;
+ u16 id_hdr_size;
char *root_dir;
+ struct rb_root threads;
+ struct list_head dead_threads;
+ struct thread *last_match;
struct list_head user_dsos;
struct list_head kernel_dsos;
struct map_groups kmaps;
@@ -148,6 +154,13 @@
void machine__exit(struct machine *self);
void machine__delete(struct machine *self);
+int machine__resolve_callchain(struct machine *machine,
+ struct perf_evsel *evsel, struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent);
+int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
+ u64 addr);
+
/*
* Default guest kernel is defined by parameter --guestkallsyms
* and --guestmodules
@@ -190,6 +203,12 @@
struct map **mapp,
symbol_filter_t filter);
+
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+void machine__remove_thread(struct machine *machine, struct thread *th);
+
+size_t machine__fprintf(struct machine *machine, FILE *fp);
+
static inline
struct symbol *machine__find_kernel_symbol(struct machine *self,
enum map_type type, u64 addr,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 928918b..531c283 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -25,8 +25,6 @@
EVT_HANDLED_ALL
};
-char debugfs_path[MAXPATHLEN];
-
#define CHW(x) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_##x
#define CSW(x) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_##x
@@ -40,6 +38,7 @@
{ CHW(BRANCH_INSTRUCTIONS), "branch-instructions", "branches" },
{ CHW(BRANCH_MISSES), "branch-misses", "" },
{ CHW(BUS_CYCLES), "bus-cycles", "" },
+ { CHW(REF_CPU_CYCLES), "ref-cycles", "" },
{ CSW(CPU_CLOCK), "cpu-clock", "" },
{ CSW(TASK_CLOCK), "task-clock", "" },
@@ -70,6 +69,7 @@
"bus-cycles",
"stalled-cycles-frontend",
"stalled-cycles-backend",
+ "ref-cycles",
};
static const char *sw_event_names[PERF_COUNT_SW_MAX] = {
@@ -140,7 +140,7 @@
char evt_path[MAXPATHLEN];
int fd;
- snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
+ snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
sys_dir->d_name, evt_dir->d_name);
fd = open(evt_path, O_RDONLY);
if (fd < 0)
@@ -171,16 +171,16 @@
char evt_path[MAXPATHLEN];
char dir_path[MAXPATHLEN];
- if (debugfs_valid_mountpoint(debugfs_path))
+ if (debugfs_valid_mountpoint(tracing_events_path))
return NULL;
- sys_dir = opendir(debugfs_path);
+ sys_dir = opendir(tracing_events_path);
if (!sys_dir)
return NULL;
for_each_subsystem(sys_dir, sys_dirent, sys_next) {
- snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+ snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
sys_dirent.d_name);
evt_dir = opendir(dir_path);
if (!evt_dir)
@@ -447,7 +447,7 @@
u64 id;
int fd;
- snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", debugfs_path,
+ snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
sys_name, evt_name);
fd = open(evt_path, O_RDONLY);
@@ -485,7 +485,7 @@
struct dirent *evt_ent;
DIR *evt_dir;
- snprintf(evt_path, MAXPATHLEN, "%s/%s", debugfs_path, sys_name);
+ snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
evt_dir = opendir(evt_path);
if (!evt_dir) {
@@ -528,7 +528,7 @@
char sys_name[MAX_EVENT_LENGTH];
unsigned int sys_length, evt_length;
- if (debugfs_valid_mountpoint(debugfs_path))
+ if (debugfs_valid_mountpoint(tracing_events_path))
return 0;
evt_name = strchr(*strp, ':');
@@ -920,10 +920,10 @@
char evt_path[MAXPATHLEN];
char dir_path[MAXPATHLEN];
- if (debugfs_valid_mountpoint(debugfs_path))
+ if (debugfs_valid_mountpoint(tracing_events_path))
return;
- sys_dir = opendir(debugfs_path);
+ sys_dir = opendir(tracing_events_path);
if (!sys_dir)
return;
@@ -932,7 +932,7 @@
!strglobmatch(sys_dirent.d_name, subsys_glob))
continue;
- snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+ snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
sys_dirent.d_name);
evt_dir = opendir(dir_path);
if (!evt_dir)
@@ -964,16 +964,16 @@
char evt_path[MAXPATHLEN];
char dir_path[MAXPATHLEN];
- if (debugfs_valid_mountpoint(debugfs_path))
+ if (debugfs_valid_mountpoint(tracing_events_path))
return 0;
- sys_dir = opendir(debugfs_path);
+ sys_dir = opendir(tracing_events_path);
if (!sys_dir)
return 0;
for_each_subsystem(sys_dir, sys_dirent, sys_next) {
- snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+ snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
sys_dirent.d_name);
evt_dir = opendir(dir_path);
if (!evt_dir)
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 2f8e375..7e0cbe7 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -39,7 +39,6 @@
int print_hwcache_events(const char *event_glob);
extern int is_valid_tracepoint(const char *event_string);
-extern char debugfs_path[];
extern int valid_debugfs_mount(const char *debugfs);
#endif /* __PERF_PARSE_EVENTS_H */
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index 1132c8f..17e94d0 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -5,7 +5,6 @@
#include "util.h"
#include "probe-event.h"
-#define MAX_PATH_LEN 256
#define MAX_PROBE_BUFFER 1024
#define MAX_PROBES 128
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 74350ff..e30749e 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -27,7 +27,10 @@
#include "../../perf.h"
#include "../util.h"
+#include "../thread.h"
+#include "../event.h"
#include "../trace-event.h"
+#include "../evsel.h"
#include <EXTERN.h>
#include <perl.h>
@@ -245,11 +248,11 @@
return event;
}
-static void perl_process_event(union perf_event *pevent __unused,
- struct perf_sample *sample,
- struct perf_evsel *evsel,
- struct perf_session *session __unused,
- struct thread *thread)
+static void perl_process_tracepoint(union perf_event *pevent __unused,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine __unused,
+ struct thread *thread)
{
struct format_field *field;
static char handler[256];
@@ -265,6 +268,9 @@
dSP;
+ if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+ return;
+
type = trace_parse_common_type(data);
event = find_cache_event(type);
@@ -332,6 +338,42 @@
LEAVE;
}
+static void perl_process_event_generic(union perf_event *pevent __unused,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel __unused,
+ struct machine *machine __unused,
+ struct thread *thread __unused)
+{
+ dSP;
+
+ if (!get_cv("process_event", 0))
+ return;
+
+ ENTER;
+ SAVETMPS;
+ PUSHMARK(SP);
+ XPUSHs(sv_2mortal(newSVpvn((const char *)pevent, pevent->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)));
+ PUTBACK;
+ call_pv("process_event", G_SCALAR);
+ SPAGAIN;
+ PUTBACK;
+ FREETMPS;
+ LEAVE;
+}
+
+static void perl_process_event(union perf_event *pevent,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct machine *machine,
+ struct thread *thread)
+{
+ perl_process_tracepoint(pevent, sample, evsel, machine, thread);
+ perl_process_event_generic(pevent, sample, evsel, machine, thread);
+}
+
static void run_start_sub(void)
{
dSP; /* access to Perl stack */
@@ -553,7 +595,28 @@
fprintf(ofp, "sub print_header\n{\n"
"\tmy ($event_name, $cpu, $secs, $nsecs, $pid, $comm) = @_;\n\n"
"\tprintf(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \",\n\t "
- "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}");
+ "$event_name, $cpu, $secs, $nsecs, $pid, $comm);\n}\n");
+
+ fprintf(ofp,
+ "\n# Packed byte string args of process_event():\n"
+ "#\n"
+ "# $event:\tunion perf_event\tutil/event.h\n"
+ "# $attr:\tstruct perf_event_attr\tlinux/perf_event.h\n"
+ "# $sample:\tstruct perf_sample\tutil/event.h\n"
+ "# $raw_data:\tperf_sample->raw_data\tutil/event.h\n"
+ "\n"
+ "sub process_event\n"
+ "{\n"
+ "\tmy ($event, $attr, $sample, $raw_data) = @_;\n"
+ "\n"
+ "\tmy @event\t= unpack(\"LSS\", $event);\n"
+ "\tmy @attr\t= unpack(\"LLQQQQQLLQQ\", $attr);\n"
+ "\tmy @sample\t= unpack(\"QLLQQQQQLL\", $sample);\n"
+ "\tmy @raw_data\t= unpack(\"C*\", $raw_data);\n"
+ "\n"
+ "\tuse Data::Dumper;\n"
+ "\tprint Dumper \\@event, \\@attr, \\@sample, \\@raw_data;\n"
+ "}\n");
fclose(ofp);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 6ccf70e..0b2a487 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -29,6 +29,8 @@
#include "../../perf.h"
#include "../util.h"
+#include "../event.h"
+#include "../thread.h"
#include "../trace-event.h"
PyMODINIT_FUNC initperf_trace_context(void);
@@ -207,7 +209,7 @@
static void python_process_event(union perf_event *pevent __unused,
struct perf_sample *sample,
struct perf_evsel *evsel __unused,
- struct perf_session *session __unused,
+ struct machine *machine __unused,
struct thread *thread)
{
PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0f4555c..b5ca255 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -10,6 +10,7 @@
#include "evlist.h"
#include "evsel.h"
#include "session.h"
+#include "tool.h"
#include "sort.h"
#include "util.h"
#include "cpumap.h"
@@ -78,39 +79,13 @@
return -1;
}
-static void perf_session__id_header_size(struct perf_session *session)
-{
- struct perf_sample *data;
- u64 sample_type = session->sample_type;
- u16 size = 0;
-
- if (!session->sample_id_all)
- goto out;
-
- if (sample_type & PERF_SAMPLE_TID)
- size += sizeof(data->tid) * 2;
-
- if (sample_type & PERF_SAMPLE_TIME)
- size += sizeof(data->time);
-
- if (sample_type & PERF_SAMPLE_ID)
- size += sizeof(data->id);
-
- if (sample_type & PERF_SAMPLE_STREAM_ID)
- size += sizeof(data->stream_id);
-
- if (sample_type & PERF_SAMPLE_CPU)
- size += sizeof(data->cpu) * 2;
-out:
- session->id_hdr_size = size;
-}
-
void perf_session__update_sample_type(struct perf_session *self)
{
self->sample_type = perf_evlist__sample_type(self->evlist);
self->sample_size = __perf_evsel__sample_size(self->sample_type);
self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
- perf_session__id_header_size(self);
+ self->id_hdr_size = perf_evlist__id_hdr_size(self->evlist);
+ self->host_machine.id_hdr_size = self->id_hdr_size;
}
int perf_session__create_kernel_maps(struct perf_session *self)
@@ -130,18 +105,26 @@
struct perf_session *perf_session__new(const char *filename, int mode,
bool force, bool repipe,
- struct perf_event_ops *ops)
+ struct perf_tool *tool)
{
- size_t len = filename ? strlen(filename) + 1 : 0;
- struct perf_session *self = zalloc(sizeof(*self) + len);
+ struct perf_session *self;
+ struct stat st;
+ size_t len;
+
+ if (!filename || !strlen(filename)) {
+ if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+ filename = "-";
+ else
+ filename = "perf.data";
+ }
+
+ len = strlen(filename);
+ self = zalloc(sizeof(*self) + len);
if (self == NULL)
goto out;
memcpy(self->filename, filename, len);
- self->threads = RB_ROOT;
- INIT_LIST_HEAD(&self->dead_threads);
- self->last_match = NULL;
/*
* On 64bit we can mmap the data file in one go. No need for tiny mmap
* slices. On 32bit we use 32MB.
@@ -171,10 +154,10 @@
goto out_delete;
}
- if (ops && ops->ordering_requires_timestamps &&
- ops->ordered_samples && !self->sample_id_all) {
+ if (tool && tool->ordering_requires_timestamps &&
+ tool->ordered_samples && !self->sample_id_all) {
dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
- ops->ordered_samples = false;
+ tool->ordered_samples = false;
}
out:
@@ -184,17 +167,22 @@
return NULL;
}
-static void perf_session__delete_dead_threads(struct perf_session *self)
+static void machine__delete_dead_threads(struct machine *machine)
{
struct thread *n, *t;
- list_for_each_entry_safe(t, n, &self->dead_threads, node) {
+ list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
list_del(&t->node);
thread__delete(t);
}
}
-static void perf_session__delete_threads(struct perf_session *self)
+static void perf_session__delete_dead_threads(struct perf_session *session)
+{
+ machine__delete_dead_threads(&session->host_machine);
+}
+
+static void machine__delete_threads(struct machine *self)
{
struct rb_node *nd = rb_first(&self->threads);
@@ -207,6 +195,11 @@
}
}
+static void perf_session__delete_threads(struct perf_session *session)
+{
+ machine__delete_threads(&session->host_machine);
+}
+
void perf_session__delete(struct perf_session *self)
{
perf_session__destroy_kernel_maps(self);
@@ -217,7 +210,7 @@
free(self);
}
-void perf_session__remove_thread(struct perf_session *self, struct thread *th)
+void machine__remove_thread(struct machine *self, struct thread *th)
{
self->last_match = NULL;
rb_erase(&th->rb_node, &self->threads);
@@ -236,16 +229,16 @@
return 0;
}
-int perf_session__resolve_callchain(struct perf_session *self,
- struct thread *thread,
- struct ip_callchain *chain,
- struct symbol **parent)
+int machine__resolve_callchain(struct machine *self, struct perf_evsel *evsel,
+ struct thread *thread,
+ struct ip_callchain *chain,
+ struct symbol **parent)
{
u8 cpumode = PERF_RECORD_MISC_USER;
unsigned int i;
int err;
- callchain_cursor_reset(&self->callchain_cursor);
+ callchain_cursor_reset(&evsel->hists.callchain_cursor);
for (i = 0; i < chain->nr; i++) {
u64 ip;
@@ -272,7 +265,7 @@
al.filtered = false;
thread__find_addr_location(thread, self, cpumode,
- MAP__FUNCTION, thread->pid, ip, &al, NULL);
+ MAP__FUNCTION, ip, &al, NULL);
if (al.sym != NULL) {
if (sort__has_parent && !*parent &&
symbol__match_parent_regex(al.sym))
@@ -281,7 +274,7 @@
break;
}
- err = callchain_cursor_append(&self->callchain_cursor,
+ err = callchain_cursor_append(&evsel->hists.callchain_cursor,
ip, al.map, al.sym);
if (err)
return err;
@@ -290,75 +283,91 @@
return 0;
}
-static int process_event_synth_stub(union perf_event *event __used,
- struct perf_session *session __used)
+static int process_event_synth_tracing_data_stub(union perf_event *event __used,
+ struct perf_session *session __used)
{
dump_printf(": unhandled!\n");
return 0;
}
-static int process_event_sample_stub(union perf_event *event __used,
+static int process_event_synth_attr_stub(union perf_event *event __used,
+ struct perf_evlist **pevlist __used)
+{
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
+static int process_event_sample_stub(struct perf_tool *tool __used,
+ union perf_event *event __used,
struct perf_sample *sample __used,
struct perf_evsel *evsel __used,
- struct perf_session *session __used)
+ struct machine *machine __used)
{
dump_printf(": unhandled!\n");
return 0;
}
-static int process_event_stub(union perf_event *event __used,
+static int process_event_stub(struct perf_tool *tool __used,
+ union perf_event *event __used,
struct perf_sample *sample __used,
- struct perf_session *session __used)
+ struct machine *machine __used)
{
dump_printf(": unhandled!\n");
return 0;
}
-static int process_finished_round_stub(union perf_event *event __used,
- struct perf_session *session __used,
- struct perf_event_ops *ops __used)
+static int process_finished_round_stub(struct perf_tool *tool __used,
+ union perf_event *event __used,
+ struct perf_session *perf_session __used)
{
dump_printf(": unhandled!\n");
return 0;
}
-static int process_finished_round(union perf_event *event,
- struct perf_session *session,
- struct perf_event_ops *ops);
-
-static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
+static int process_event_type_stub(struct perf_tool *tool __used,
+ union perf_event *event __used)
{
- if (handler->sample == NULL)
- handler->sample = process_event_sample_stub;
- if (handler->mmap == NULL)
- handler->mmap = process_event_stub;
- if (handler->comm == NULL)
- handler->comm = process_event_stub;
- if (handler->fork == NULL)
- handler->fork = process_event_stub;
- if (handler->exit == NULL)
- handler->exit = process_event_stub;
- if (handler->lost == NULL)
- handler->lost = perf_event__process_lost;
- if (handler->read == NULL)
- handler->read = process_event_stub;
- if (handler->throttle == NULL)
- handler->throttle = process_event_stub;
- if (handler->unthrottle == NULL)
- handler->unthrottle = process_event_stub;
- if (handler->attr == NULL)
- handler->attr = process_event_synth_stub;
- if (handler->event_type == NULL)
- handler->event_type = process_event_synth_stub;
- if (handler->tracing_data == NULL)
- handler->tracing_data = process_event_synth_stub;
- if (handler->build_id == NULL)
- handler->build_id = process_event_synth_stub;
- if (handler->finished_round == NULL) {
- if (handler->ordered_samples)
- handler->finished_round = process_finished_round;
+ dump_printf(": unhandled!\n");
+ return 0;
+}
+
+static int process_finished_round(struct perf_tool *tool,
+ union perf_event *event,
+ struct perf_session *session);
+
+static void perf_tool__fill_defaults(struct perf_tool *tool)
+{
+ if (tool->sample == NULL)
+ tool->sample = process_event_sample_stub;
+ if (tool->mmap == NULL)
+ tool->mmap = process_event_stub;
+ if (tool->comm == NULL)
+ tool->comm = process_event_stub;
+ if (tool->fork == NULL)
+ tool->fork = process_event_stub;
+ if (tool->exit == NULL)
+ tool->exit = process_event_stub;
+ if (tool->lost == NULL)
+ tool->lost = perf_event__process_lost;
+ if (tool->read == NULL)
+ tool->read = process_event_sample_stub;
+ if (tool->throttle == NULL)
+ tool->throttle = process_event_stub;
+ if (tool->unthrottle == NULL)
+ tool->unthrottle = process_event_stub;
+ if (tool->attr == NULL)
+ tool->attr = process_event_synth_attr_stub;
+ if (tool->event_type == NULL)
+ tool->event_type = process_event_type_stub;
+ if (tool->tracing_data == NULL)
+ tool->tracing_data = process_event_synth_tracing_data_stub;
+ if (tool->build_id == NULL)
+ tool->build_id = process_finished_round_stub;
+ if (tool->finished_round == NULL) {
+ if (tool->ordered_samples)
+ tool->finished_round = process_finished_round;
else
- handler->finished_round = process_finished_round_stub;
+ tool->finished_round = process_finished_round_stub;
}
}
@@ -490,11 +499,11 @@
static int perf_session_deliver_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample,
- struct perf_event_ops *ops,
+ struct perf_tool *tool,
u64 file_offset);
static void flush_sample_queue(struct perf_session *s,
- struct perf_event_ops *ops)
+ struct perf_tool *tool)
{
struct ordered_samples *os = &s->ordered_samples;
struct list_head *head = &os->samples;
@@ -505,7 +514,7 @@
unsigned idx = 0, progress_next = os->nr_samples / 16;
int ret;
- if (!ops->ordered_samples || !limit)
+ if (!tool->ordered_samples || !limit)
return;
list_for_each_entry_safe(iter, tmp, head, list) {
@@ -516,7 +525,7 @@
if (ret)
pr_err("Can't parse sample, err = %d\n", ret);
else
- perf_session_deliver_event(s, iter->event, &sample, ops,
+ perf_session_deliver_event(s, iter->event, &sample, tool,
iter->file_offset);
os->last_flush = iter->timestamp;
@@ -578,11 +587,11 @@
* Flush every events below timestamp 7
* etc...
*/
-static int process_finished_round(union perf_event *event __used,
- struct perf_session *session,
- struct perf_event_ops *ops)
+static int process_finished_round(struct perf_tool *tool,
+ union perf_event *event __used,
+ struct perf_session *session)
{
- flush_sample_queue(session, ops);
+ flush_sample_queue(session, tool);
session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
return 0;
@@ -737,13 +746,26 @@
callchain__printf(sample);
}
+static struct machine *
+ perf_session__find_machine_for_cpumode(struct perf_session *session,
+ union perf_event *event)
+{
+ const u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+ if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest)
+ return perf_session__find_machine(session, event->ip.pid);
+
+ return perf_session__find_host_machine(session);
+}
+
static int perf_session_deliver_event(struct perf_session *session,
union perf_event *event,
struct perf_sample *sample,
- struct perf_event_ops *ops,
+ struct perf_tool *tool,
u64 file_offset)
{
struct perf_evsel *evsel;
+ struct machine *machine;
dump_event(session, event, file_offset, sample);
@@ -765,6 +787,8 @@
hists__inc_nr_events(&evsel->hists, event->header.type);
}
+ machine = perf_session__find_machine_for_cpumode(session, event);
+
switch (event->header.type) {
case PERF_RECORD_SAMPLE:
dump_sample(session, event, sample);
@@ -772,23 +796,25 @@
++session->hists.stats.nr_unknown_id;
return -1;
}
- return ops->sample(event, sample, evsel, session);
+ return tool->sample(tool, event, sample, evsel, machine);
case PERF_RECORD_MMAP:
- return ops->mmap(event, sample, session);
+ return tool->mmap(tool, event, sample, machine);
case PERF_RECORD_COMM:
- return ops->comm(event, sample, session);
+ return tool->comm(tool, event, sample, machine);
case PERF_RECORD_FORK:
- return ops->fork(event, sample, session);
+ return tool->fork(tool, event, sample, machine);
case PERF_RECORD_EXIT:
- return ops->exit(event, sample, session);
+ return tool->exit(tool, event, sample, machine);
case PERF_RECORD_LOST:
- return ops->lost(event, sample, session);
+ if (tool->lost == perf_event__process_lost)
+ session->hists.stats.total_lost += event->lost.lost;
+ return tool->lost(tool, event, sample, machine);
case PERF_RECORD_READ:
- return ops->read(event, sample, session);
+ return tool->read(tool, event, sample, evsel, machine);
case PERF_RECORD_THROTTLE:
- return ops->throttle(event, sample, session);
+ return tool->throttle(tool, event, sample, machine);
case PERF_RECORD_UNTHROTTLE:
- return ops->unthrottle(event, sample, session);
+ return tool->unthrottle(tool, event, sample, machine);
default:
++session->hists.stats.nr_unknown_events;
return -1;
@@ -812,24 +838,29 @@
}
static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
- struct perf_event_ops *ops, u64 file_offset)
+ struct perf_tool *tool, u64 file_offset)
{
+ int err;
+
dump_event(session, event, file_offset, NULL);
/* These events are processed right away */
switch (event->header.type) {
case PERF_RECORD_HEADER_ATTR:
- return ops->attr(event, session);
+ err = tool->attr(event, &session->evlist);
+ if (err == 0)
+ perf_session__update_sample_type(session);
+ return err;
case PERF_RECORD_HEADER_EVENT_TYPE:
- return ops->event_type(event, session);
+ return tool->event_type(tool, event);
case PERF_RECORD_HEADER_TRACING_DATA:
/* setup for reading amidst mmap */
lseek(session->fd, file_offset, SEEK_SET);
- return ops->tracing_data(event, session);
+ return tool->tracing_data(event, session);
case PERF_RECORD_HEADER_BUILD_ID:
- return ops->build_id(event, session);
+ return tool->build_id(tool, event, session);
case PERF_RECORD_FINISHED_ROUND:
- return ops->finished_round(event, session, ops);
+ return tool->finished_round(tool, event, session);
default:
return -EINVAL;
}
@@ -837,7 +868,7 @@
static int perf_session__process_event(struct perf_session *session,
union perf_event *event,
- struct perf_event_ops *ops,
+ struct perf_tool *tool,
u64 file_offset)
{
struct perf_sample sample;
@@ -853,7 +884,7 @@
hists__inc_nr_events(&session->hists, event->header.type);
if (event->header.type >= PERF_RECORD_USER_TYPE_START)
- return perf_session__process_user_event(session, event, ops, file_offset);
+ return perf_session__process_user_event(session, event, tool, file_offset);
/*
* For all kernel events we get the sample data
@@ -866,14 +897,14 @@
if (perf_session__preprocess_sample(session, event, &sample))
return 0;
- if (ops->ordered_samples) {
+ if (tool->ordered_samples) {
ret = perf_session_queue_event(session, event, &sample,
file_offset);
if (ret != -ETIME)
return ret;
}
- return perf_session_deliver_event(session, event, &sample, ops,
+ return perf_session_deliver_event(session, event, &sample, tool,
file_offset);
}
@@ -884,6 +915,11 @@
self->size = bswap_16(self->size);
}
+struct thread *perf_session__findnew(struct perf_session *session, pid_t pid)
+{
+ return machine__findnew_thread(&session->host_machine, pid);
+}
+
static struct thread *perf_session__register_idle_thread(struct perf_session *self)
{
struct thread *thread = perf_session__findnew(self, 0);
@@ -897,9 +933,9 @@
}
static void perf_session__warn_about_errors(const struct perf_session *session,
- const struct perf_event_ops *ops)
+ const struct perf_tool *tool)
{
- if (ops->lost == perf_event__process_lost &&
+ if (tool->lost == perf_event__process_lost &&
session->hists.stats.nr_events[PERF_RECORD_LOST] != 0) {
ui__warning("Processed %d events and lost %d chunks!\n\n"
"Check IO/CPU overload!\n\n",
@@ -934,7 +970,7 @@
volatile int session_done;
static int __perf_session__process_pipe_events(struct perf_session *self,
- struct perf_event_ops *ops)
+ struct perf_tool *tool)
{
union perf_event event;
uint32_t size;
@@ -943,7 +979,7 @@
int err;
void *p;
- perf_event_ops__fill_defaults(ops);
+ perf_tool__fill_defaults(tool);
head = 0;
more:
@@ -979,8 +1015,7 @@
}
}
- if (size == 0 ||
- (skip = perf_session__process_event(self, &event, ops, head)) < 0) {
+ if ((skip = perf_session__process_event(self, &event, tool, head)) < 0) {
dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n",
head, event.header.size, event.header.type);
/*
@@ -1003,7 +1038,7 @@
done:
err = 0;
out_err:
- perf_session__warn_about_errors(self, ops);
+ perf_session__warn_about_errors(self, tool);
perf_session_free_sample_buffers(self);
return err;
}
@@ -1034,7 +1069,7 @@
int __perf_session__process_events(struct perf_session *session,
u64 data_offset, u64 data_size,
- u64 file_size, struct perf_event_ops *ops)
+ u64 file_size, struct perf_tool *tool)
{
u64 head, page_offset, file_offset, file_pos, progress_next;
int err, mmap_prot, mmap_flags, map_idx = 0;
@@ -1043,7 +1078,7 @@
union perf_event *event;
uint32_t size;
- perf_event_ops__fill_defaults(ops);
+ perf_tool__fill_defaults(tool);
page_size = sysconf(_SC_PAGESIZE);
@@ -1098,7 +1133,7 @@
size = event->header.size;
if (size == 0 ||
- perf_session__process_event(session, event, ops, file_pos) < 0) {
+ perf_session__process_event(session, event, tool, file_pos) < 0) {
dump_printf("%#" PRIx64 " [%#x]: skipping unknown header type: %d\n",
file_offset + head, event->header.size,
event->header.type);
@@ -1127,15 +1162,15 @@
err = 0;
/* do the final flush for ordered samples */
session->ordered_samples.next_flush = ULLONG_MAX;
- flush_sample_queue(session, ops);
+ flush_sample_queue(session, tool);
out_err:
- perf_session__warn_about_errors(session, ops);
+ perf_session__warn_about_errors(session, tool);
perf_session_free_sample_buffers(session);
return err;
}
int perf_session__process_events(struct perf_session *self,
- struct perf_event_ops *ops)
+ struct perf_tool *tool)
{
int err;
@@ -1146,9 +1181,9 @@
err = __perf_session__process_events(self,
self->header.data_offset,
self->header.data_size,
- self->size, ops);
+ self->size, tool);
else
- err = __perf_session__process_pipe_events(self, ops);
+ err = __perf_session__process_pipe_events(self, tool);
return err;
}
@@ -1163,9 +1198,8 @@
return true;
}
-int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
- const char *symbol_name,
- u64 addr)
+int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
+ const char *symbol_name, u64 addr)
{
char *bracket;
enum map_type i;
@@ -1224,6 +1258,27 @@
return ret;
}
+size_t perf_session__fprintf(struct perf_session *session, FILE *fp)
+{
+ /*
+ * FIXME: Here we have to actually print all the machines in this
+ * session, not just the host...
+ */
+ return machine__fprintf(&session->host_machine, fp);
+}
+
+void perf_session__remove_thread(struct perf_session *session,
+ struct thread *th)
+{
+ /*
+ * FIXME: This one makes no sense, we need to remove the thread from
+ * the machine it belongs to, perf_session can have many machines, so
+ * doing it always on ->host_machine is wrong. Fix when auditing all
+ * the 'perf kvm' code.
+ */
+ machine__remove_thread(&session->host_machine, th);
+}
+
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type)
{
@@ -1236,17 +1291,16 @@
return NULL;
}
-void perf_session__print_ip(union perf_event *event,
- struct perf_sample *sample,
- struct perf_session *session,
- int print_sym, int print_dso)
+void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
+ struct machine *machine, struct perf_evsel *evsel,
+ int print_sym, int print_dso)
{
struct addr_location al;
const char *symname, *dsoname;
- struct callchain_cursor *cursor = &session->callchain_cursor;
+ struct callchain_cursor *cursor = &evsel->hists.callchain_cursor;
struct callchain_cursor_node *node;
- if (perf_event__preprocess_sample(event, session, &al, sample,
+ if (perf_event__preprocess_sample(event, machine, &al, sample,
NULL) < 0) {
error("problem processing %d event, skipping it.\n",
event->header.type);
@@ -1255,7 +1309,7 @@
if (symbol_conf.use_callchain && sample->callchain) {
- if (perf_session__resolve_callchain(session, al.thread,
+ if (machine__resolve_callchain(machine, evsel, al.thread,
sample->callchain, NULL) != 0) {
if (verbose)
error("Failed to resolve callchain. Skipping\n");
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 6e393c9..37bc383 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -30,9 +30,6 @@
struct perf_header header;
unsigned long size;
unsigned long mmap_window;
- struct rb_root threads;
- struct list_head dead_threads;
- struct thread *last_match;
struct machine host_machine;
struct rb_root machines;
struct perf_evlist *evlist;
@@ -53,65 +50,31 @@
int cwdlen;
char *cwd;
struct ordered_samples ordered_samples;
- struct callchain_cursor callchain_cursor;
- char filename[0];
+ char filename[1];
};
-struct perf_evsel;
-struct perf_event_ops;
-
-typedef int (*event_sample)(union perf_event *event, struct perf_sample *sample,
- struct perf_evsel *evsel, struct perf_session *session);
-typedef int (*event_op)(union perf_event *self, struct perf_sample *sample,
- struct perf_session *session);
-typedef int (*event_synth_op)(union perf_event *self,
- struct perf_session *session);
-typedef int (*event_op2)(union perf_event *self, struct perf_session *session,
- struct perf_event_ops *ops);
-
-struct perf_event_ops {
- event_sample sample;
- event_op mmap,
- comm,
- fork,
- exit,
- lost,
- read,
- throttle,
- unthrottle;
- event_synth_op attr,
- event_type,
- tracing_data,
- build_id;
- event_op2 finished_round;
- bool ordered_samples;
- bool ordering_requires_timestamps;
-};
+struct perf_tool;
struct perf_session *perf_session__new(const char *filename, int mode,
bool force, bool repipe,
- struct perf_event_ops *ops);
+ struct perf_tool *tool);
void perf_session__delete(struct perf_session *self);
void perf_event_header__bswap(struct perf_event_header *self);
int __perf_session__process_events(struct perf_session *self,
u64 data_offset, u64 data_size, u64 size,
- struct perf_event_ops *ops);
+ struct perf_tool *tool);
int perf_session__process_events(struct perf_session *self,
- struct perf_event_ops *event_ops);
+ struct perf_tool *tool);
-int perf_session__resolve_callchain(struct perf_session *self,
+int perf_session__resolve_callchain(struct perf_session *self, struct perf_evsel *evsel,
struct thread *thread,
struct ip_callchain *chain,
struct symbol **parent);
bool perf_session__has_traces(struct perf_session *self, const char *msg);
-int perf_session__set_kallsyms_ref_reloc_sym(struct map **maps,
- const char *symbol_name,
- u64 addr);
-
void mem_bswap_64(void *src, int byte_size);
void perf_event__attr_swap(struct perf_event_attr *attr);
@@ -144,12 +107,16 @@
static inline
void perf_session__process_machines(struct perf_session *self,
+ struct perf_tool *tool,
machine__process_t process)
{
- process(&self->host_machine, self);
- return machines__process(&self->machines, process, self);
+ process(&self->host_machine, tool);
+ return machines__process(&self->machines, process, tool);
}
+struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
+size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
+
size_t perf_session__fprintf_dsos(struct perf_session *self, FILE *fp);
size_t perf_session__fprintf_dsos_buildid(struct perf_session *self,
@@ -167,13 +134,20 @@
session->header.needs_swap);
}
+static inline int perf_session__synthesize_sample(struct perf_session *session,
+ union perf_event *event,
+ const struct perf_sample *sample)
+{
+ return perf_event__synthesize_sample(event, session->sample_type,
+ sample, session->header.needs_swap);
+}
+
struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
unsigned int type);
-void perf_session__print_ip(union perf_event *event,
- struct perf_sample *sample,
- struct perf_session *session,
- int print_sym, int print_dso);
+void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
+ struct machine *machine, struct perf_evsel *evsel,
+ int print_sym, int print_dso);
int perf_session__cpu_bitmap(struct perf_session *session,
const char *cpu_list, unsigned long *cpu_bitmap);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 95d3700..36d4c56 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -27,7 +27,8 @@
perf = Extension('perf',
sources = ['util/python.c', 'util/ctype.c', 'util/evlist.c',
'util/evsel.c', 'util/cpumap.c', 'util/thread_map.c',
- 'util/util.c', 'util/xyarray.c', 'util/cgroup.c'],
+ 'util/util.c', 'util/xyarray.c', 'util/cgroup.c',
+ 'util/debugfs.c'],
include_dirs = ['util/include'],
extra_compile_args = cflags,
)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 632b50c..215d50f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1757,7 +1757,7 @@
struct stat st;
/*sshfs might return bad dent->d_type, so we have to stat*/
- sprintf(path, "%s/%s", dir_name, dent->d_name);
+ snprintf(path, sizeof(path), "%s/%s", dir_name, dent->d_name);
if (stat(path, &st))
continue;
@@ -1766,8 +1766,6 @@
!strcmp(dent->d_name, ".."))
continue;
- snprintf(path, sizeof(path), "%s/%s",
- dir_name, dent->d_name);
ret = map_groups__set_modules_path_dir(mg, path);
if (ret < 0)
goto out;
@@ -1788,9 +1786,6 @@
if (map == NULL)
continue;
- snprintf(path, sizeof(path), "%s/%s",
- dir_name, dent->d_name);
-
long_name = strdup(path);
if (long_name == NULL) {
ret = -1;
@@ -2609,10 +2604,10 @@
symbol_conf.initialized = true;
return 0;
-out_free_dso_list:
- strlist__delete(symbol_conf.dso_list);
out_free_comm_list:
strlist__delete(symbol_conf.comm_list);
+out_free_dso_list:
+ strlist__delete(symbol_conf.dso_list);
return -1;
}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 29f8d74..123c2e1 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -68,6 +68,7 @@
struct symbol_conf {
unsigned short priv_size;
+ unsigned short nr_events;
bool try_vmlinux_path,
use_modules,
sort_by_name,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index d5d3b22..fb4b7ea 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -61,7 +61,7 @@
map_groups__fprintf(&self->mg, verbose, fp);
}
-struct thread *perf_session__findnew(struct perf_session *self, pid_t pid)
+struct thread *machine__findnew_thread(struct machine *self, pid_t pid)
{
struct rb_node **p = &self->threads.rb_node;
struct rb_node *parent = NULL;
@@ -125,12 +125,12 @@
return 0;
}
-size_t perf_session__fprintf(struct perf_session *self, FILE *fp)
+size_t machine__fprintf(struct machine *machine, FILE *fp)
{
size_t ret = 0;
struct rb_node *nd;
- for (nd = rb_first(&self->threads); nd; nd = rb_next(nd)) {
+ for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
struct thread *pos = rb_entry(nd, struct thread, rb_node);
ret += thread__fprintf(pos, fp);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index e5f2401..70c2c13 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -18,16 +18,14 @@
int comm_len;
};
-struct perf_session;
+struct machine;
void thread__delete(struct thread *self);
int thread__set_comm(struct thread *self, const char *comm);
int thread__comm_len(struct thread *self);
-struct thread *perf_session__findnew(struct perf_session *self, pid_t pid);
void thread__insert_map(struct thread *self, struct map *map);
int thread__fork(struct thread *self, struct thread *parent);
-size_t perf_session__fprintf(struct perf_session *self, FILE *fp);
static inline struct map *thread__find_map(struct thread *self,
enum map_type type, u64 addr)
@@ -35,14 +33,12 @@
return self ? map_groups__find(&self->mg, type, addr) : NULL;
}
-void thread__find_addr_map(struct thread *self,
- struct perf_session *session, u8 cpumode,
- enum map_type type, pid_t pid, u64 addr,
+void thread__find_addr_map(struct thread *thread, struct machine *machine,
+ u8 cpumode, enum map_type type, u64 addr,
struct addr_location *al);
-void thread__find_addr_location(struct thread *self,
- struct perf_session *session, u8 cpumode,
- enum map_type type, pid_t pid, u64 addr,
+void thread__find_addr_location(struct thread *thread, struct machine *machine,
+ u8 cpumode, enum map_type type, u64 addr,
struct addr_location *al,
symbol_filter_t filter);
#endif /* __PERF_THREAD_H */
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
new file mode 100644
index 0000000..b0e1aad
--- /dev/null
+++ b/tools/perf/util/tool.h
@@ -0,0 +1,50 @@
+#ifndef __PERF_TOOL_H
+#define __PERF_TOOL_H
+
+#include <stdbool.h>
+
+struct perf_session;
+union perf_event;
+struct perf_evlist;
+struct perf_evsel;
+struct perf_sample;
+struct perf_tool;
+struct machine;
+
+typedef int (*event_sample)(struct perf_tool *tool, union perf_event *event,
+ struct perf_sample *sample,
+ struct perf_evsel *evsel, struct machine *machine);
+
+typedef int (*event_op)(struct perf_tool *tool, union perf_event *event,
+ struct perf_sample *sample, struct machine *machine);
+
+typedef int (*event_attr_op)(union perf_event *event,
+ struct perf_evlist **pevlist);
+typedef int (*event_simple_op)(struct perf_tool *tool, union perf_event *event);
+
+typedef int (*event_synth_op)(union perf_event *event,
+ struct perf_session *session);
+
+typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
+ struct perf_session *session);
+
+struct perf_tool {
+ event_sample sample,
+ read;
+ event_op mmap,
+ comm,
+ fork,
+ exit,
+ lost,
+ throttle,
+ unthrottle;
+ event_attr_op attr;
+ event_synth_op tracing_data;
+ event_simple_op event_type;
+ event_op2 finished_round,
+ build_id;
+ bool ordered_samples;
+ bool ordering_requires_timestamps;
+};
+
+#endif /* __PERF_TOOL_H */
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index 3996509..a248f3c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -1,15 +1,17 @@
#ifndef __PERF_TOP_H
#define __PERF_TOP_H 1
+#include "tool.h"
#include "types.h"
-#include "../perf.h"
#include <stddef.h>
+#include <stdbool.h>
struct perf_evlist;
struct perf_evsel;
struct perf_session;
struct perf_top {
+ struct perf_tool tool;
struct perf_evlist *evlist;
/*
* Symbols will be added here in perf_event__process_sample and will
@@ -23,10 +25,26 @@
int freq;
pid_t target_pid, target_tid;
bool hide_kernel_symbols, hide_user_symbols, zero;
+ bool system_wide;
+ bool use_tui, use_stdio;
+ bool sort_has_symbols;
+ bool dont_use_callchains;
+ bool kptr_restrict_warned;
+ bool vmlinux_warned;
+ bool inherit;
+ bool group;
+ bool sample_id_all_avail;
+ bool dump_symtab;
const char *cpu_list;
struct hist_entry *sym_filter_entry;
struct perf_evsel *sym_evsel;
struct perf_session *session;
+ struct winsize winsize;
+ unsigned int mmap_pages;
+ int default_interval;
+ int realtime_prio;
+ int sym_pcnt_filter;
+ const char *sym_filter;
};
size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d2655f0..ac6830d 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -18,7 +18,8 @@
*
* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
-#define _GNU_SOURCE
+#include <ctype.h>
+#include "util.h"
#include <dirent.h>
#include <mntent.h>
#include <stdio.h>
@@ -31,7 +32,6 @@
#include <pthread.h>
#include <fcntl.h>
#include <unistd.h>
-#include <ctype.h>
#include <errno.h>
#include <stdbool.h>
#include <linux/list.h>
@@ -44,10 +44,6 @@
#define VERSION "0.5"
-#define _STR(x) #x
-#define STR(x) _STR(x)
-#define MAX_PATH 256
-
#define TRACE_CTRL "tracing_on"
#define TRACE "trace"
#define AVAILABLE "available_tracers"
@@ -73,26 +69,6 @@
};
-
-static void die(const char *fmt, ...)
-{
- va_list ap;
- int ret = errno;
-
- if (errno)
- perror("perf");
- else
- ret = -1;
-
- va_start(ap, fmt);
- fprintf(stderr, " ");
- vfprintf(stderr, fmt, ap);
- va_end(ap);
-
- fprintf(stderr, "\n");
- exit(ret);
-}
-
void *malloc_or_die(unsigned int size)
{
void *data;
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index c9dcbec..a3fdf55 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -39,7 +39,7 @@
static void process_event_unsupported(union perf_event *event __unused,
struct perf_sample *sample __unused,
struct perf_evsel *evsel __unused,
- struct perf_session *session __unused,
+ struct machine *machine __unused,
struct thread *thread __unused)
{
}
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index a841008..58ae14c 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -3,7 +3,11 @@
#include <stdbool.h>
#include "parse-events.h"
-#include "session.h"
+
+struct machine;
+struct perf_sample;
+union perf_event;
+struct thread;
#define __unused __attribute__((unused))
@@ -292,7 +296,7 @@
void (*process_event) (union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
- struct perf_session *session,
+ struct machine *machine,
struct thread *thread);
int (*generate_script) (const char *outfile);
};
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 0575905..295a9c9 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -224,7 +224,7 @@
}
static int annotate_browser__run(struct annotate_browser *self, int evidx,
- int nr_events, void(*timer)(void *arg),
+ void(*timer)(void *arg),
void *arg, int delay_secs)
{
struct rb_node *nd = NULL;
@@ -328,8 +328,7 @@
notes = symbol__annotation(target);
pthread_mutex_lock(¬es->lock);
- if (notes->src == NULL &&
- symbol__alloc_hist(target, nr_events) < 0) {
+ if (notes->src == NULL && symbol__alloc_hist(target) < 0) {
pthread_mutex_unlock(¬es->lock);
ui__warning("Not enough memory for annotating '%s' symbol!\n",
target->name);
@@ -337,7 +336,7 @@
}
pthread_mutex_unlock(¬es->lock);
- symbol__tui_annotate(target, ms->map, evidx, nr_events,
+ symbol__tui_annotate(target, ms->map, evidx,
timer, arg, delay_secs);
}
continue;
@@ -358,15 +357,15 @@
return key;
}
-int hist_entry__tui_annotate(struct hist_entry *he, int evidx, int nr_events,
+int hist_entry__tui_annotate(struct hist_entry *he, int evidx,
void(*timer)(void *arg), void *arg, int delay_secs)
{
- return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx, nr_events,
+ return symbol__tui_annotate(he->ms.sym, he->ms.map, evidx,
timer, arg, delay_secs);
}
int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
- int nr_events, void(*timer)(void *arg), void *arg,
+ void(*timer)(void *arg), void *arg,
int delay_secs)
{
struct objdump_line *pos, *n;
@@ -419,8 +418,7 @@
browser.b.nr_entries = browser.nr_entries;
browser.b.entries = ¬es->src->source,
browser.b.width += 18; /* Percentage */
- ret = annotate_browser__run(&browser, evidx, nr_events,
- timer, arg, delay_secs);
+ ret = annotate_browser__run(&browser, evidx, timer, arg, delay_secs);
list_for_each_entry_safe(pos, n, ¬es->src->source, node) {
list_del(&pos->node);
objdump_line__free(pos);
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index d0c94b4..1212a38 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -1020,7 +1020,7 @@
* Don't let this be freed, say, by hists__decay_entry.
*/
he->used = true;
- err = hist_entry__tui_annotate(he, evsel->idx, nr_events,
+ err = hist_entry__tui_annotate(he, evsel->idx,
timer, arg, delay_secs);
he->used = false;
ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
diff --git a/tools/perf/util/ui/progress.c b/tools/perf/util/ui/progress.c
index 295e366..13aa64e 100644
--- a/tools/perf/util/ui/progress.c
+++ b/tools/perf/util/ui/progress.c
@@ -14,6 +14,9 @@
if (use_browser <= 0)
return;
+ if (total == 0)
+ return;
+
ui__refresh_dimensions(true);
pthread_mutex_lock(&ui__lock);
y = SLtt_Screen_Rows / 2 - 2;
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index e16bf9a7..d76d1c0 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -1,5 +1,8 @@
/*
- * GIT - The information manager from hell
+ * usage.c
+ *
+ * Various reporting routines.
+ * Originally copied from GIT source.
*
* Copyright (C) Linus Torvalds, 2005
*/
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 0128906..37be34d 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -245,4 +245,15 @@
#define _STR(x) #x
#define STR(x) _STR(x)
+/*
+ * Determine whether some value is a power of two, where zero is
+ * *not* considered a power of two.
+ */
+
+static inline __attribute__((const))
+bool is_power_of_2(unsigned long n)
+{
+ return (n != 0 && ((n & (n - 1)) == 0));
+}
+
#endif
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index bdd3347..697c8b4 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -32,6 +32,7 @@
for (i = 0; i < values->threads; i++)
free(values->value[i]);
+ free(values->value);
free(values->pid);
free(values->tid);
free(values->counterrawid);