FB The frame buffer device is enabled.
HW Appropriate hardware is enabled.
IA-64 IA-64 architecture is enabled.
+ IMA Integrity measurement architecture is enabled.
IOSCHED More than one I/O scheduler is enabled.
IP_PNP IP DHCP, BOOTP, or RARP is enabled.
ISAPNP ISA PnP code is enabled.
ISDN Appropriate ISDN support is enabled.
JOY Appropriate joystick support is enabled.
+ KMEMTRACE kmemtrace is enabled.
LIBATA Libata driver is enabled
LP Printer support is enabled.
LOOP Loopback device support is enabled.
Range: 0 - 8192
Default: 64
+ dma_debug=off If the kernel is compiled with DMA_API_DEBUG support
+ this option disables the debugging code at boot.
+
+ dma_debug_entries=<number>
+ This option allows to tune the number of preallocated
+ entries for DMA-API debugging code. One entry is
+ required per DMA-API allocation. Use this if the
+ DMA-API debugging code disables itself because the
+ architectural default is too low.
+
hpet= [X86-32,HPET] option to control HPET usage
- Format: { enable (default) | disable | force }
+ Format: { enable (default) | disable | force |
+ verbose }
disable: disable HPET and use PIT instead
force: allow force enabled of undocumented chips (ICH4,
VIA, nVidia)
+ verbose: show contents of HPET registers during setup
com20020= [HW,NET] ARCnet - COM20020 chipset
Format:
hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
terminal devices. Valid values: 0..8
+ hvc_iucv_allow= [S390] Comma-separated list of z/VM user IDs.
+ If specified, z/VM IUCV HVC accepts connections
+ from listed z/VM user IDs only.
+
+ i2c_bus= [HW] Override the default board specific I2C bus speed
+ or register an additional I2C bus that is not
+ registered from board initialization code.
+ Format:
+ <bus_id>,<clkrate>
i8042.debug [HW] Toggle i8042 debug mode
i8042.direct [HW] Put keyboard port into non-translated mode
ihash_entries= [KNL]
Set number of hash buckets for inode cache.
+ ima_audit= [IMA]
+ Format: { "0" | "1" }
+ 0 -- integrity auditing messages. (Default)
+ 1 -- enable informational integrity auditing messages.
+
+ ima_hash= [IMA]
+ Formt: { "sha1" | "md5" }
+ default: "sha1"
+
in2000= [HW,SCSI]
See header of drivers/scsi/in2000.c.
use the HighMem zone if it exists, and the Normal
zone if it does not.
+ kmemtrace.enable= [KNL,KMEMTRACE] Format: { yes | no }
+ Controls whether kmemtrace is enabled
+ at boot-time.
+
+ kmemtrace.subbufs=n [KNL,KMEMTRACE] Overrides the number of
+ subbufs kmemtrace's relay channel has. Set this
+ higher than default (KMEMTRACE_N_SUBBUFS in code) if
+ you experience buffer overruns.
+
movablecore=nn[KMG] [KNL,X86-32,IA-64,PPC,X86-64] This parameter
is similar to kernelcore except it specifies the
amount of memory used for migratable allocations.
See also Documentation/blockdev/paride.txt.
pci=option[,option...] [PCI] various PCI subsystem options:
+ earlydump [X86] dump PCI config space before the kernel
+ changes anything
off [X86] don't probe for the PCI bus
bios [X86-32] force use of PCI BIOS, don't access
the hardware directly. Use this if your machine
cbmemsize=nn[KMG] The fixed amount of bus space which is
reserved for the CardBus bridge's memory
window. The default value is 64 megabytes.
+ resource_alignment=
+ Format:
+ [<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
+ Specifies alignment and device to reassign
+ aligned memory resources.
+ If <order of align> is not specified,
+ PAGE_SIZE is used as alignment.
+ PCI-PCI bridge can be specified, if resource
+ windows need to be expanded.
pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
Management.
autoconfiguration.
Ranges are in pairs (memory base and size).
- dynamic_printk Enables pr_debug()/dev_dbg() calls if
- CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled.
- These can also be switched on/off via
- <debugfs>/dynamic_printk/modules
-
print-fatal-signals=
[KNL] debug: print fatal signals
print-fatal-signals=1: print segfault info to
If enabled at boot time, /selinux/disable can be used
later to disable prior to initial policy load.
- selinux_compat_net =
- [SELINUX] Set initial selinux_compat_net flag value.
- Format: { "0" | "1" }
- 0 -- use new secmark-based packet controls
- 1 -- use legacy packet controls
- Default value is 0 (preferred).
- Value can be changed at runtime via
- /selinux/compat_net.
-
serialnumber [BUGS=X86-32]
shapers= [NET]
tp720= [HW,PS2]
+ trace_buf_size=nn[KMG] [ftrace] will set tracing buffer size.
+
trix= [HW,OSS] MediaTrix AudioTrix Pro
Format:
<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
'i' - Send a SIGKILL to all processes, except for init.
+'j' - Forcibly "Just thaw it" - filesystems frozen by the FIFREEZE ioctl.
+
'k' - Secure Access Key (SAK) Kills all programs on the current virtual
console. NOTE: See important comments below in SAK section.
'x' - Used by xmon interface on ppc/powerpc platforms.
+ 'z' - Dump the ftrace buffer
+
'0'-'9' - Sets the console log level, controlling which kernel messages
will be printed to your console. ('0', for example would make
it so that only emergency messages like PANICs or OOPSes would
are unable to kill any other way, especially if it's spawning other
processes.
+"'J'ust thaw it" is useful if your system becomes unresponsive due to a frozen
+(probably root) filesystem via the FIFREEZE ioctl.
+
* Sometimes SysRq seems to get 'stuck' after using it, what can I do?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
That happens to me, also. I've found that tapping shift, alt, and control
P: Ivan Kokshaysky
M: ink@jurassic.park.msu.ru
S: Maintained for 2.4; PCI support for 2.6.
+L: linux-alpha@vger.kernel.org
AMD GEODE CS5536 USB DEVICE CONTROLLER DRIVER
P: Thomas Dahlmann
M: rpurdie@rpsys.net
S: Maintained
+ARM/CORTINA SYSTEMS GEMINI ARM ARCHITECTURE
+P: Paulius Zaleckas
+M: paulius.zaleckas@teltonika.lt
+L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
+T: git gitorious.org/linux-gemini/mainline.git
+S: Maintained
+
ARM/EZX SMARTPHONES (A780, A910, A1200, E680, ROKR E2 and ROKR E6)
P: Daniel Ribeiro
M: drwyrm@gmail.com
W: http://www.openezx.org/
S: Maintained
+ARM/FARADAY FA526 PORT
+P: Paulius Zaleckas
+M: paulius.zaleckas@teltonika.lt
+L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
+S: Maintained
+
ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
P: Sascha Hauer
M: kernel@pengutronix.de
M: dirk@opfer-online.de
S: Maintained
-ARM/PALMTX SUPPORT
+ARM/PALMTX,PALMT5,PALMLD SUPPORT
P: Marek Vasut
M: marek.vasut@gmail.com
W: http://hackndev.com
L: ath9k-devel@lists.ath9k.org
S: Supported
+ATHEROS AR9170 WIRELESS DRIVER
+P: Christian Lamparter
+M: chunkeey@web.de
+L: linux-wireless@vger.kernel.org
+W: http://wireless.kernel.org/en/users/Drivers/ar9170
+S: Maintained
+F: drivers/net/wireless/ar9170/
+
ATI_REMOTE2 DRIVER
P: Ville Syrjala
M: syrjala@sci.fi
S: Supported
BROADCOM TG3 GIGABIT ETHERNET DRIVER
+P: Matt Carlson
+M: mcarlson@broadcom.com
P: Michael Chan
M: mchan@broadcom.com
L: netdev@vger.kernel.org
P: Mauro Carvalho Chehab
M: mchehab@infradead.org
L: linux-media@vger.kernel.org
-L: video4linux-list@redhat.com
W: http://linuxtv.org
T: git kernel.org:/pub/scm/linux/kernel/git/mchehab/linux-2.6.git
S: Maintained
T: git kernel.org:/pub/scm/linux/kernel/git/herbert/crypto-2.6.git
S: Maintained
+CRYPTOGRAPHIC RANDOM NUMBER GENERATOR
+P: Neil Horman
+M: nhorman@tuxdriver.com
+L: linux-crypto@vger.kernel.org
+S: Maintained
+
CS5535 Audio ALSA driver
P: Jaya Kumar
M: jayakumar.alsa@gmail.com
T: quilt kernel.org/pub/linux/kernel/people/bart/pata-2.6/
S: Maintained
-IDE/ATAPI CDROM DRIVER
+IDE/ATAPI DRIVERS
P: Borislav Petkov
M: petkovbb@gmail.com
L: linux-ide@vger.kernel.org
S: Maintained
-IDE/ATAPI FLOPPY DRIVERS
-P: Paul Bristow
-M: Paul Bristow <paul@paulbristow.net>
-W: http://paulbristow.net/linux/idefloppy.html
-L: linux-kernel@vger.kernel.org
-S: Maintained
-
-IDE/ATAPI TAPE DRIVERS
-P: Gadi Oxman
-M: Gadi Oxman <gadio@netvision.net.il>
-L: linux-kernel@vger.kernel.org
-S: Maintained
-
IDLE-I7300
P: Andy Henroid
M: andrew.d.henroid@intel.com
L: linux1394-devel@lists.sourceforge.net
S: Maintained
+INTEGRITY MEASUREMENT ARCHITECTURE (IMA)
+P: Mimi Zohar
+M: zohar@us.ibm.com
+S: Supported
+
IMS TWINTURBO FRAMEBUFFER DRIVER
L: linux-fbdev-devel@lists.sourceforge.net (moderated for non-subscribers)
S: Orphan
L: kgdb-bugreport@lists.sourceforge.net
S: Maintained
+ KMEMTRACE
+ P: Eduard - Gabriel Munteanu
+ M: eduard.munteanu@linux360.ro
+ L: linux-kernel@vger.kernel.org
+ S: Maintained
+
KPROBES
P: Ananth N Mavinakayanahalli
M: ananth@in.ibm.com
M: zippel@linux-m68k.org
L: linux-m68k@lists.linux-m68k.org
W: http://www.linux-m68k.org/
-W: http://linux-m68k-cvs.ubb.ca/
+T: git git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k.git
S: Maintained
M68K ON APPLE MACINTOSH
W: http://www.nongnu.org/orinoco/
S: Maintained
+OSD LIBRARY
+P: Boaz Harrosh
+M: bharrosh@panasas.com
+P: Benny Halevy
+M: bhalevy@panasas.com
+L: osd-dev@open-osd.org
+W: http://open-osd.org
+T: git://git.open-osd.org/open-osd.git
+S: Maintained
+
P54 WIRELESS DRIVER
P: Michael Wu
M: flamingice@sourmilk.net
L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
S: Maintained
+PXA168 SUPPORT
+P: Eric Miao
+M: eric.miao@marvell.com
+P: Jason Chagas
+M: jason.chagas@marvell.com
+L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
+T: git kernel.org:/pub/scm/linux/kernel/git/ycmiao/pxa-linux-2.6.git
+S: Supported
+
+PXA910 SUPPORT
+P: Eric Miao
+M: eric.miao@marvell.com
+L: linux-arm-kernel@lists.arm.linux.org.uk (subscribers-only)
+T: git kernel.org:/pub/scm/linux/kernel/git/ycmiao/pxa-linux-2.6.git
+S: Supported
+
PXA MMCI DRIVER
S: Orphan
RALINK RT2X00 WIRELESS LAN DRIVER
P: rt2x00 project
L: linux-wireless@vger.kernel.org
-L: rt2400-devel@lists.sourceforge.net
+L: users@rt2x00.serialmonkey.com
W: http://rt2x00.serialmonkey.com/
S: Maintained
T: git kernel.org:/pub/scm/linux/kernel/git/ivd/rt2x00.git
L: netdev@vger.kernel.org
S: Maintained
+RDS - RELIABLE DATAGRAM SOCKETS
+P: Andy Grover
+M: andy.grover@oracle.com
+L: rds-devel@oss.oracle.com
+S: Supported
+
READ-COPY UPDATE (RCU)
P: Dipankar Sarma
M: dipankar@in.ibm.com
W: http://www.ibm.com/developerworks/linux/linux390/
S: Supported
+S390 ZCRYPT DRIVER
+P: Felix Beck
+M: felix.beck@de.ibm.com
+P: Ralph Wuerthner
+M: ralph.wuerthner@de.ibm.com
+M: linux390@de.ibm.com
+L: linux-s390@vger.kernel.org
+S: Supported
+
S390 ZFCP DRIVER
P: Christof Schmitt
M: christof.schmitt@de.ibm.com
L: linux-kernel@vger.kernel.org
L: linux-security-module@vger.kernel.org (suggested Cc:)
T: git kernel.org:pub/scm/linux/kernel/git/jmorris/security-testing-2.6.git
+W: http://security.wiki.kernel.org/
S: Supported
SECURITY CONTACT
W: http://sourceforge.net/projects/tlan/
S: Maintained
+TOMOYO SECURITY MODULE
+P: Kentaro Takeda
+M: takedakn@nttdata.co.jp
+P: Tetsuo Handa
+M: penguin-kernel@I-love.SAKURA.ne.jp
+L: linux-kernel@vger.kernel.org (kernel issues)
+L: tomoyo-users-en@lists.sourceforge.jp (subscribers-only, for developers and users in English)
+L: tomoyo-dev@lists.sourceforge.jp (subscribers-only, for developers in Japanese)
+L: tomoyo-users@lists.sourceforge.jp (subscribers-only, for users in Japanese)
+W: http://tomoyo.sourceforge.jp/
+T: quilt http://svn.sourceforge.jp/svnroot/tomoyo/trunk/2.2.x/tomoyo-lsm/patches/
+S: Maintained
+
TOSHIBA ACPI EXTRAS DRIVER
P: John Belmonte
M: toshiba_acpi@memebeam.org
P: Mauro Carvalho Chehab
M: mchehab@infradead.org
L: linux-media@vger.kernel.org
-L: video4linux-list@redhat.com
W: http://linuxtv.org
T: git kernel.org:/pub/scm/linux/kernel/git/mchehab/linux-2.6.git
S: Maintained
tristate "OProfile system profiling (EXPERIMENTAL)"
depends on PROFILING
depends on HAVE_OPROFILE
+ depends on TRACING_SUPPORT
select TRACING
select RING_BUFFER
help
The <linux/clk.h> calls support software clock gating and
thus are a key power management tool on many systems.
+config HAVE_DMA_API_DEBUG
+ bool
# Makefile for the linux kernel.
#
+ ifdef CONFIG_DYNAMIC_FTRACE
+ CFLAGS_REMOVE_ftrace.o = -pg
+ endif
+
extra-y := head.o init_task.o vmlinux.lds
obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o \
irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o \
salinfo.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \
- unwind.o mca.o mca_asm.o topology.o
+ unwind.o mca.o mca_asm.o topology.o dma-mapping.o
obj-$(CONFIG_IA64_BRL_EMU) += brl_emu.o
obj-$(CONFIG_IA64_GENERIC) += acpi-ext.o
obj-$(CONFIG_CPU_FREQ) += cpufreq/
obj-$(CONFIG_IA64_MCA_RECOVERY) += mca_recovery.o
obj-$(CONFIG_KPROBES) += kprobes.o jprobes.o
+ obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR) += uncached.o
obj-y += esi_stub.o # must be in kernel proper
endif
obj-$(CONFIG_DMAR) += pci-dma.o
-ifeq ($(CONFIG_DMAR), y)
obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
-endif
# The gate DSO image is built using a special linker script.
targets += gate.so gate-syms.o
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
+ select HAVE_FTRACE_SYSCALLS
select HAVE_KVM
select HAVE_ARCH_KGDB
select HAVE_ARCH_TRACEHOOK
select HAVE_GENERIC_DMA_COHERENT if X86_32
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select USER_STACKTRACE_SUPPORT
+ select HAVE_DMA_API_DEBUG
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_LZMA
config ARCH_SUPPORTS_OPTIMIZED_INLINING
def_bool y
+config ARCH_SUPPORTS_DEBUG_PAGEALLOC
+ def_bool y
+
# Use the generic interrupt handling code in kernel/irq/:
config GENERIC_HARDIRQS
bool
default y
+config GENERIC_HARDIRQS_NO__DO_IRQ
+ def_bool y
+
config GENERIC_IRQ_PROBE
bool
default y
config NODES_SHIFT
int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
- range 1 9 if X86_64
+ range 1 9
default "9" if MAXSMP
default "6" if X86_64
default "4" if X86_NUMAQ
int set_memory_array_uc(unsigned long *addr, int addrinarray);
int set_memory_array_wb(unsigned long *addr, int addrinarray);
+int set_pages_array_uc(struct page **pages, int addrinarray);
+int set_pages_array_wb(struct page **pages, int addrinarray);
+
/*
* For legacy compatibility with the old APIs, a few functions
* are provided that work on a "struct page".
#ifdef CONFIG_DEBUG_RODATA
void mark_rodata_ro(void);
extern const int rodata_test_data;
+ void set_kernel_text_rw(void);
+ void set_kernel_text_ro(void);
+ #else
+ static inline void set_kernel_text_rw(void) { }
+ static inline void set_kernel_text_ro(void) { }
#endif
#ifdef CONFIG_DEBUG_RODATA_TEST
obj-y += apic/
obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
- obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
+ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
+ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o
obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o
-obj-$(CONFIG_X86_VSMP) += vsmp_64.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_MODULES) += module_$(BITS).o
obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o
obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
-obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64
+obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
###
# 64 bit specific files
obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o
obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o
+ obj-y += vsmp_64.o
endif
/*
- * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $)
+ * acpi-cpufreq.c - ACPI Processor P-States Driver
*
* Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>
- #include <linux/ftrace.h>
+ #include <trace/power.h>
#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+
#include <acpi/processor.h>
-#include <asm/io.h>
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
-#include <asm/delay.h>
-#include <asm/uaccess.h>
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg)
+#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
+ "acpi-cpufreq", msg)
MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+ DEFINE_TRACE(power_mark);
+
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance *acpi_perf_data;
perf = data->acpi_data;
- for (i=0; i<perf->state_count; i++) {
+ for (i = 0; i < perf->state_count; i++) {
if (value == perf->states[i].status)
return data->freq_table[i].frequency;
}
msr &= INTEL_MSR_RANGE;
perf = data->acpi_data;
- for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
+ for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
if (msr == perf->states[data->freq_table[i].index].status)
return data->freq_table[i].frequency;
}
u8 bit_width;
};
-typedef union {
- struct msr_addr msr;
- struct io_addr io;
-} drv_addr_union;
-
struct drv_cmd {
unsigned int type;
const struct cpumask *mask;
- drv_addr_union addr;
+ union {
+ struct msr_addr msr;
+ struct io_addr io;
+ } addr;
u32 val;
};
unsigned int cur_freq;
unsigned int i;
- for (i=0; i<100; i++) {
+ for (i = 0; i < 100; i++) {
cur_freq = extract_freq(get_cur_val(mask), data);
if (cur_freq == freq)
return 1;
unsigned long freq;
unsigned long freqn = perf->states[0].core_frequency * 1000;
- for (i=0; i<(perf->state_count-1); i++) {
+ for (i = 0; i < (perf->state_count-1); i++) {
freq = freqn;
freqn = perf->states[i+1].core_frequency * 1000;
if ((2 * cpu_khz) > (freqn + freq)) {
/* detect transition latency */
policy->cpuinfo.transition_latency = 0;
- for (i=0; i<perf->state_count; i++) {
+ for (i = 0; i < perf->state_count; i++) {
if ((perf->states[i].transition_latency * 1000) >
policy->cpuinfo.transition_latency)
policy->cpuinfo.transition_latency =
data->max_freq = perf->states[0].core_frequency * 1000;
/* table init */
- for (i=0; i<perf->state_count; i++) {
- if (i>0 && perf->states[i].core_frequency >=
+ for (i = 0; i < perf->state_count; i++) {
+ if (i > 0 && perf->states[i].core_frequency >=
data->freq_table[valid_states-1].frequency / 1000)
continue;
kprobe_opcode_t opcode;
kprobe_opcode_t *orig_opcodes = opcodes;
- if (search_exception_tables(opcodes))
+ if (search_exception_tables((unsigned long)opcodes))
return 0; /* Page fault may occur on this address. */
retry:
#else
" pushf\n"
/*
- * Skip cs, ip, orig_ax.
+ * Skip cs, ip, orig_ax and gs.
* trampoline_handler() will plug in these values
*/
- " subl $12, %esp\n"
+ " subl $16, %esp\n"
" pushl %fs\n"
- " pushl %ds\n"
" pushl %es\n"
+ " pushl %ds\n"
" pushl %eax\n"
" pushl %ebp\n"
" pushl %edi\n"
" movl %esp, %eax\n"
" call trampoline_handler\n"
/* Move flags to cs */
- " movl 52(%esp), %edx\n"
- " movl %edx, 48(%esp)\n"
+ " movl 56(%esp), %edx\n"
+ " movl %edx, 52(%esp)\n"
/* Replace saved flags with true return address. */
- " movl %eax, 52(%esp)\n"
+ " movl %eax, 56(%esp)\n"
" popl %ebx\n"
" popl %ecx\n"
" popl %edx\n"
" popl %edi\n"
" popl %ebp\n"
" popl %eax\n"
- /* Skip ip, orig_ax, es, ds, fs */
- " addl $20, %esp\n"
+ /* Skip ds, es, fs, gs, orig_ax and ip */
+ " addl $24, %esp\n"
" popf\n"
#endif
" ret\n");
regs->cs = __KERNEL_CS;
#else
regs->cs = __KERNEL_CS | get_kernel_rpl();
+ regs->gs = 0;
#endif
regs->ip = trampoline_address;
regs->orig_ax = ~0UL;
#include <linux/module.h>
#include <linux/pm.h>
#include <linux/clockchips.h>
- #include <linux/ftrace.h>
+ #include <trace/power.h>
#include <asm/system.h>
#include <asm/apic.h>
#include <asm/idle.h>
struct kmem_cache *task_xstate_cachep;
+ DEFINE_TRACE(power_start);
+ DEFINE_TRACE(power_end);
+
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
*dst = *src;
{
struct task_struct *me = current;
struct thread_struct *t = &me->thread;
+ unsigned long *bp = t->io_bitmap_ptr;
- if (me->thread.io_bitmap_ptr) {
+ if (bp) {
struct tss_struct *tss = &per_cpu(init_tss, get_cpu());
- kfree(t->io_bitmap_ptr);
t->io_bitmap_ptr = NULL;
clear_thread_flag(TIF_IO_BITMAP);
/*
memset(tss->io_bitmap, 0xff, t->io_bitmap_max);
t->io_bitmap_max = 0;
put_cpu();
+ kfree(bp);
}
ds_exit_thread(current);
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
+ #include <linux/ftrace.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
if (!cfg.signal)
return -EINVAL;
- return -EOPNOTSUPP;
-
child->thread.bts_ovfl_signal = cfg.signal;
+ return -EOPNOTSUPP;
}
if ((cfg.flags & PTRACE_BTS_O_ALLOC) &&
tracehook_report_syscall_entry(regs))
ret = -1L;
+ if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+ ftrace_syscall_enter(regs);
+
if (unlikely(current->audit_context)) {
if (IS_IA32)
audit_syscall_entry(AUDIT_ARCH_I386,
if (unlikely(current->audit_context))
audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
+ if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
+ ftrace_syscall_exit(regs);
+
if (test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, 0);
config HAVE_KVM
bool
+config HAVE_KVM_IRQCHIP
+ bool
+ default y
+
menuconfig VIRTUALIZATION
bool "Virtualization"
depends on HAVE_KVM || X86
config KVM_TRACE
bool "KVM trace support"
- depends on KVM && MARKERS && SYSFS
+ depends on KVM && SYSFS
+ select MARKERS
select RELAY
select DEBUG_FS
default n
#include <linux/vt_kern.h>
#include <linux/workqueue.h>
#include <linux/kexec.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
#include <linux/hrtimer.h>
#include <linux/oom.h>
}
static struct sysrq_key_op sysrq_ftrace_dump_op = {
.handler = sysrq_ftrace_dump,
- .help_msg = "dumpZ-ftrace-buffer",
+ .help_msg = "dump-ftrace-buffer(Z)",
.action_msg = "Dump ftrace buffer",
.enable_mask = SYSRQ_ENABLE_DUMP,
};
.enable_mask = SYSRQ_ENABLE_SIGNAL,
};
+#ifdef CONFIG_BLOCK
+static void sysrq_handle_thaw(int key, struct tty_struct *tty)
+{
+ emergency_thaw_all();
+}
+static struct sysrq_key_op sysrq_thaw_op = {
+ .handler = sysrq_handle_thaw,
+ .help_msg = "thaw-filesystems(J)",
+ .action_msg = "Emergency Thaw of all frozen filesystems",
+ .enable_mask = SYSRQ_ENABLE_SIGNAL,
+};
+#endif
+
static void sysrq_handle_kill(int key, struct tty_struct *tty)
{
send_sig_all(SIGKILL);
&sysrq_moom_op, /* f */
/* g: May be registered by ppc for kgdb */
NULL, /* g */
- NULL, /* h */
+ NULL, /* h - reserved for help */
&sysrq_kill_op, /* i */
+#ifdef CONFIG_BLOCK
+ &sysrq_thaw_op, /* j */
+#else
NULL, /* j */
+#endif
&sysrq_SAK_op, /* k */
#ifdef CONFIG_SMP
&sysrq_showallcpus_op, /* l */
#include <linux/kmod.h>
#include <linux/ctype.h>
#include <linux/genhd.h>
+ #include <linux/blktrace_api.h>
#include "check.h"
static struct attribute_group *part_attr_groups[] = {
&part_attr_group,
+ #ifdef CONFIG_BLK_DEV_IO_TRACE
+ &blk_trace_attr_group,
+ #endif
NULL
};
pdev->devt = devt;
/* delay uevent until 'holders' subdir is created */
- pdev->uevent_suppress = 1;
+ dev_set_uevent_suppress(pdev, 1);
err = device_add(pdev);
if (err)
goto out_put;
if (!p->holder_dir)
goto out_del;
- pdev->uevent_suppress = 0;
+ dev_set_uevent_suppress(pdev, 0);
if (flags & ADDPART_FLAG_WHOLEDISK) {
err = device_create_file(pdev, &dev_attr_whole_disk);
if (err)
rcu_assign_pointer(ptbl->part[partno], p);
/* suppress uevent if the disk supresses it */
- if (!ddev->uevent_suppress)
+ if (!dev_get_uevent_suppress(pdev))
kobject_uevent(&pdev->kobj, KOBJ_ADD);
return p;
dev_set_name(ddev, disk->disk_name);
/* delay uevents, until we scanned partition table */
- ddev->uevent_suppress = 1;
+ dev_set_uevent_suppress(ddev, 1);
if (device_add(ddev))
return;
exit:
/* announce disk after possible partitions are created */
- ddev->uevent_suppress = 0;
+ dev_set_uevent_suppress(ddev, 0);
kobject_uevent(&ddev->kobj, KOBJ_ADD);
/* announce possible partitions */
#define BRANCH_PROFILE()
#endif
+ #ifdef CONFIG_EVENT_TRACER
+ #define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .; \
+ *(_ftrace_events) \
+ VMLINUX_SYMBOL(__stop_ftrace_events) = .;
+ #else
+ #define FTRACE_EVENTS()
+ #endif
+
+ #ifdef CONFIG_TRACING
+ #define TRACE_PRINTKS() VMLINUX_SYMBOL(__start___trace_bprintk_fmt) = .; \
+ *(__trace_printk_fmt) /* Trace_printk fmt' pointer */ \
+ VMLINUX_SYMBOL(__stop___trace_bprintk_fmt) = .;
+ #else
+ #define TRACE_PRINTKS()
+ #endif
+
+ #ifdef CONFIG_FTRACE_SYSCALLS
+ #define TRACE_SYSCALLS() VMLINUX_SYMBOL(__start_syscalls_metadata) = .; \
+ *(__syscalls_metadata) \
+ VMLINUX_SYMBOL(__stop_syscalls_metadata) = .;
+ #else
+ #define TRACE_SYSCALLS()
+ #endif
+
/* .data section */
#define DATA_DATA \
*(.data) \
VMLINUX_SYMBOL(__start___tracepoints) = .; \
*(__tracepoints) \
VMLINUX_SYMBOL(__stop___tracepoints) = .; \
+ /* implement dynamic printk debug */ \
+ . = ALIGN(8); \
+ VMLINUX_SYMBOL(__start___verbose) = .; \
+ *(__verbose) \
+ VMLINUX_SYMBOL(__stop___verbose) = .; \
LIKELY_PROFILE() \
- BRANCH_PROFILE()
+ BRANCH_PROFILE() \
+ TRACE_PRINTKS() \
+ FTRACE_EVENTS() \
+ TRACE_SYSCALLS()
#define RO_DATA(align) \
. = ALIGN((align)); \
CPU_DISCARD(init.data) \
CPU_DISCARD(init.rodata) \
MEM_DISCARD(init.data) \
- MEM_DISCARD(init.rodata) \
- /* implement dynamic printk debug */ \
- VMLINUX_SYMBOL(__start___verbose_strings) = .; \
- *(__verbose_strings) \
- VMLINUX_SYMBOL(__stop___verbose_strings) = .; \
- . = ALIGN(8); \
- VMLINUX_SYMBOL(__start___verbose) = .; \
- *(__verbose) \
- VMLINUX_SYMBOL(__stop___verbose) = .;
+ MEM_DISCARD(init.rodata)
#define INIT_TEXT \
*(.init.text) \
typedef irqreturn_t (*irq_handler_t)(int, void *);
+/**
+ * struct irqaction - per interrupt action descriptor
+ * @handler: interrupt handler function
+ * @flags: flags (see IRQF_* above)
+ * @mask: no comment as it is useless and about to be removed
+ * @name: name of the device
+ * @dev_id: cookie to identify the device
+ * @next: pointer to the next irqaction for shared interrupts
+ * @irq: interrupt number
+ * @dir: pointer to the proc/irq/NN/name entry
+ */
struct irqaction {
irq_handler_t handler;
unsigned long flags;
extern void disable_irq(unsigned int irq);
extern void enable_irq(unsigned int irq);
+/* The following three functions are for the core kernel use only. */
+extern void suspend_device_irqs(void);
+extern void resume_device_irqs(void);
+#ifdef CONFIG_PM_SLEEP
+extern int check_wakeup_irqs(void);
+#else
+static inline int check_wakeup_irqs(void) { return 0; }
+#endif
+
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
extern cpumask_var_t irq_default_affinity;
NR_SOFTIRQS
};
+ /* map softirq index to softirq name. update 'softirq_to_name' in
+ * kernel/softirq.c when adding a new softirq.
+ */
+ extern char *softirq_to_name[NR_SOFTIRQS];
+
/* softirq mask and active fields moved to irq_cpustat_t in
* asm/hardirq.h to get better cache usage. KAO
*/
}
#endif
+#if defined(CONFIG_GENERIC_HARDIRQS) && defined(CONFIG_DEBUG_SHIRQ)
+extern void debug_poll_all_shared_irqs(void);
+#else
+static inline void debug_poll_all_shared_irqs(void) { }
+#endif
+
int show_interrupts(struct seq_file *p, void *v);
struct irq_desc;
#include <linux/log2.h>
#include <linux/typecheck.h>
#include <linux/ratelimit.h>
-#include <linux/dynamic_printk.h>
+#include <linux/dynamic_debug.h>
#include <asm/byteorder.h>
#include <asm/bug.h>
extern int printk_ratelimit(void);
extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
unsigned int interval_msec);
+
+ /*
+ * Print a one-time message (analogous to WARN_ONCE() et al):
+ */
+ #define printk_once(x...) ({ \
+ static int __print_once = 1; \
+ \
+ if (__print_once) { \
+ __print_once = 0; \
+ printk(x); \
+ } \
+ })
+
#else
static inline int vprintk(const char *s, va_list args)
__attribute__ ((format (printf, 1, 0)));
static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \
unsigned int interval_msec) \
{ return false; }
+
+ /* No effect, but we still get type checking even in the !PRINTK case: */
+ #define printk_once(x...) printk(x)
+
#endif
extern int printk_needs_cpu(int cpu);
printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
#define pr_info(fmt, ...) \
printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_cont(fmt, ...) \
+ printk(KERN_CONT fmt, ##__VA_ARGS__)
/* If you are writing a driver, please use dev_dbg instead */
#if defined(DEBUG)
#define pr_debug(fmt, ...) \
printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
-#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG)
+#elif defined(CONFIG_DYNAMIC_DEBUG)
+/* dynamic_pr_debug() uses pr_fmt() internally so we don't need it here */
#define pr_debug(fmt, ...) do { \
- dynamic_pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
+ dynamic_pr_debug(fmt, ##__VA_ARGS__); \
} while (0)
#else
#define pr_debug(fmt, ...) \
({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; })
#endif
+ /*
+ * General tracing related utility functions - trace_printk(),
+ * tracing_on/tracing_off and tracing_start()/tracing_stop
+ *
+ * Use tracing_on/tracing_off when you want to quickly turn on or off
+ * tracing. It simply enables or disables the recording of the trace events.
+ * This also corresponds to the user space debugfs/tracing/tracing_on
+ * file, which gives a means for the kernel and userspace to interact.
+ * Place a tracing_off() in the kernel where you want tracing to end.
+ * From user space, examine the trace, and then echo 1 > tracing_on
+ * to continue tracing.
+ *
+ * tracing_stop/tracing_start has slightly more overhead. It is used
+ * by things like suspend to ram where disabling the recording of the
+ * trace is not enough, but tracing must actually stop because things
+ * like calling smp_processor_id() may crash the system.
+ *
+ * Most likely, you want to use tracing_on/tracing_off.
+ */
+ #ifdef CONFIG_RING_BUFFER
+ void tracing_on(void);
+ void tracing_off(void);
+ /* trace_off_permanent stops recording with no way to bring it back */
+ void tracing_off_permanent(void);
+ int tracing_is_on(void);
+ #else
+ static inline void tracing_on(void) { }
+ static inline void tracing_off(void) { }
+ static inline void tracing_off_permanent(void) { }
+ static inline int tracing_is_on(void) { return 0; }
+ #endif
+ #ifdef CONFIG_TRACING
+ extern void tracing_start(void);
+ extern void tracing_stop(void);
+ extern void ftrace_off_permanent(void);
+
+ extern void
+ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+ static inline void __attribute__ ((format (printf, 1, 2)))
+ ____trace_printk_check_format(const char *fmt, ...)
+ {
+ }
+ #define __trace_printk_check_format(fmt, args...) \
+ do { \
+ if (0) \
+ ____trace_printk_check_format(fmt, ##args); \
+ } while (0)
+
+ /**
+ * trace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __trace_printk is an internal function for trace_printk and
+ * the @ip is passed in via the trace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving trace_printks scattered around in
+ * your code.
+ */
+
+ #define trace_printk(fmt, args...) \
+ do { \
+ __trace_printk_check_format(fmt, ##args); \
+ if (__builtin_constant_p(fmt)) { \
+ static const char *trace_printk_fmt \
+ __attribute__((section("__trace_printk_fmt"))) = \
+ __builtin_constant_p(fmt) ? fmt : NULL; \
+ \
+ __trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args); \
+ } else \
+ __trace_printk(_THIS_IP_, fmt, ##args); \
+ } while (0)
+
+ extern int
+ __trace_bprintk(unsigned long ip, const char *fmt, ...)
+ __attribute__ ((format (printf, 2, 3)));
+
+ extern int
+ __trace_printk(unsigned long ip, const char *fmt, ...)
+ __attribute__ ((format (printf, 2, 3)));
+
+ /*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement.
+ */
+ #define ftrace_vprintk(fmt, vargs) \
+ do { \
+ if (__builtin_constant_p(fmt)) { \
+ static const char *trace_printk_fmt \
+ __attribute__((section("__trace_printk_fmt"))) = \
+ __builtin_constant_p(fmt) ? fmt : NULL; \
+ \
+ __ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs); \
+ } else \
+ __ftrace_vprintk(_THIS_IP_, fmt, vargs); \
+ } while (0)
+
+ extern int
+ __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
+
+ extern int
+ __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
+
+ extern void ftrace_dump(void);
+ #else
+ static inline void
+ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+ static inline int
+ trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
+
+ static inline void tracing_start(void) { }
+ static inline void tracing_stop(void) { }
+ static inline void ftrace_off_permanent(void) { }
+ static inline int
+ trace_printk(const char *fmt, ...)
+ {
+ return 0;
+ }
+ static inline int
+ ftrace_vprintk(const char *fmt, va_list ap)
+ {
+ return 0;
+ }
+ static inline void ftrace_dump(void) { }
+ #endif /* CONFIG_TRACING */
+
/*
* Display an IP address in readable format.
*/
((unsigned char *)&addr)[3]
#define NIPQUAD_FMT "%u.%u.%u.%u"
-#if defined(__LITTLE_ENDIAN)
-#define HIPQUAD(addr) \
- ((unsigned char *)&addr)[3], \
- ((unsigned char *)&addr)[2], \
- ((unsigned char *)&addr)[1], \
- ((unsigned char *)&addr)[0]
-#elif defined(__BIG_ENDIAN)
-#define HIPQUAD NIPQUAD
-#else
-#error "Please fix asm/byteorder.h"
-#endif /* __LITTLE_ENDIAN */
-
/*
* min()/max()/clamp() macros that also do
* strict type-checking.. See the
extern unsigned long nr_active(void);
extern unsigned long nr_iowait(void);
+ extern unsigned long get_parent_ip(unsigned long addr);
+
struct seq_file;
struct cfs_rq;
struct task_group;
(mm)->hiwater_vm = (mm)->total_vm; \
} while (0)
-#define get_mm_hiwater_rss(mm) max((mm)->hiwater_rss, get_mm_rss(mm))
-#define get_mm_hiwater_vm(mm) max((mm)->hiwater_vm, (mm)->total_vm)
+static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
+{
+ return max(mm->hiwater_rss, get_mm_rss(mm));
+}
+
+static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
+{
+ return max(mm->hiwater_vm, mm->total_vm);
+}
extern void set_dumpable(struct mm_struct *mm, int value);
extern int get_dumpable(struct mm_struct *mm);
struct rq *busiest, struct sched_domain *sd,
enum cpu_idle_type idle);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
+ int (*needs_post_schedule) (struct rq *this_rq);
void (*post_schedule) (struct rq *this_rq);
void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
u64 last_wakeup;
u64 avg_overlap;
+ u64 start_runtime;
+ u64 avg_wakeup;
+ u64 nr_migrations;
+
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
u64 wait_max;
u64 exec_max;
u64 slice_max;
- u64 nr_migrations;
u64 nr_migrations_cold;
u64 nr_failed_migrations_affine;
u64 nr_failed_migrations_running;
#endif
struct list_head tasks;
+ struct plist_node pushable_tasks;
struct mm_struct *mm, *active_mm;
/* ??? */
unsigned int personality;
unsigned did_exec:1;
+ unsigned in_execve:1; /* Tell the LSMs that the process is doing an
+ * execve */
pid_t pid;
pid_t tgid;
int curr_ret_stack;
/* Stack of return addresses for return function tracing */
struct ftrace_ret_stack *ret_stack;
+ /* time stamp for last schedule */
+ unsigned long long ftrace_timestamp;
/*
* Number of functions that haven't been traced
* because of depth overrun.
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.h>
+ #include <trace/kmemtrace.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
struct kmem_cache_node {
spinlock_t list_lock; /* Protect partial list and nr_partial */
unsigned long nr_partial;
- unsigned long min_partial;
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
atomic_long_t nr_slabs;
void (*ctor)(void *);
int inuse; /* Offset to metadata */
int align; /* Alignment */
+ unsigned long min_partial;
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
#ifdef CONFIG_SLUB_DEBUG
* This should be dropped to PAGE_SIZE / 2 once the page allocator
* "fastpath" becomes competitive with the slab allocator fastpaths.
*/
-#define SLUB_MAX_SIZE (PAGE_SIZE)
+#define SLUB_MAX_SIZE (2 * PAGE_SIZE)
-#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 1)
+#define SLUB_PAGE_SHIFT (PAGE_SHIFT + 2)
/*
* We keep the general caches in an array of slab caches that are used for
void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
void *__kmalloc(size_t size, gfp_t flags);
+ #ifdef CONFIG_KMEMTRACE
+ extern void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags);
+ #else
+ static __always_inline void *
+ kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+ {
+ return kmem_cache_alloc(s, gfpflags);
+ }
+ #endif
+
static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
{
- return (void *)__get_free_pages(flags | __GFP_COMP, get_order(size));
+ unsigned int order = get_order(size);
+ void *ret = (void *) __get_free_pages(flags | __GFP_COMP, order);
+
+ kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _THIS_IP_, ret,
+ size, PAGE_SIZE << order, flags);
+
+ return ret;
}
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
+ void *ret;
+
if (__builtin_constant_p(size)) {
if (size > SLUB_MAX_SIZE)
return kmalloc_large(size, flags);
if (!s)
return ZERO_SIZE_PTR;
- return kmem_cache_alloc(s, flags);
+ ret = kmem_cache_alloc_notrace(s, flags);
+
+ kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC,
+ _THIS_IP_, ret,
+ size, s->size, flags);
+
+ return ret;
}
}
return __kmalloc(size, flags);
void *__kmalloc_node(size_t size, gfp_t flags, int node);
void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
+ #ifdef CONFIG_KMEMTRACE
+ extern void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+ gfp_t gfpflags,
+ int node);
+ #else
+ static __always_inline void *
+ kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+ gfp_t gfpflags,
+ int node)
+ {
+ return kmem_cache_alloc_node(s, gfpflags, node);
+ }
+ #endif
+
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
+ void *ret;
+
if (__builtin_constant_p(size) &&
size <= SLUB_MAX_SIZE && !(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
- return kmem_cache_alloc_node(s, flags, node);
+ ret = kmem_cache_alloc_node_notrace(s, flags, node);
+
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC,
+ _THIS_IP_, ret,
+ size, s->size, flags, node);
+
+ return ret;
}
return __kmalloc_node(size, flags, node);
}
#include <linux/compiler.h> /* for inline */
#include <linux/types.h> /* for size_t */
#include <linux/stddef.h> /* for NULL */
+ #include <stdarg.h>
extern char *strndup_user(const char __user *, long);
+extern void *memdup_user(const void __user *, size_t);
/*
* Include machine specific inline routines
extern bool sysfs_streq(const char *s1, const char *s2);
+ #ifdef CONFIG_BINARY_PRINTF
+ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args);
+ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf);
+ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4);
+ #endif
+
extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
const void *from, size_t available);
config MARKERS
bool "Activate markers"
- depends on TRACEPOINTS
+ select TRACEPOINTS
help
Place an empty function call at each marker site. Can be
dynamically changed for a probe function.
config RT_MUTEXES
boolean
- select PLIST
config BASE_SMALL
int
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
+ #include <trace/kmemtrace.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/smp.h>
* Set up the current CPU as possible to migrate to.
* The other ones will be done by cpu_up/cpu_down()
*/
- cpu = smp_processor_id();
- cpu_set(cpu, cpu_active_map);
+ set_cpu_active(smp_processor_id(), true);
/* FIXME: This should be done in userspace --RR */
for_each_present_cpu(cpu) {
enable_debug_pagealloc();
cpu_hotplug_init();
kmem_cache_init();
+ kmemtrace_init();
debug_objects_mem_init();
idr_init_cache();
setup_per_cpu_pageset();
{
rcu_init_sched(); /* needed by module_init stage. */
init_workqueues();
+ cpuset_init_smp();
usermodehelper_init();
driver_init();
init_irq_proc();
* makes it inline to init() and it becomes part of init.text section
*/
static noinline int init_post(void)
+ __releases(kernel_lock)
{
/* need to finish all async __init code before freeing the memory */
async_synchronize_full();
/*
* init can run on any cpu.
*/
- set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR);
+ set_cpus_allowed_ptr(current, cpu_all_mask);
/*
* Tell the world that we're going to be the grim
* reaper of innocent orphaned children.
smp_init();
sched_init_smp();
- cpuset_init_smp();
-
do_basic_setup();
/*
#include <linux/kernel_stat.h>
#include <linux/rculist.h>
#include <linux/hash.h>
+ #include <trace/irq.h>
#include <linux/bootmem.h>
#include "internals.h"
void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
{
- unsigned long bytes;
- char *ptr;
int node;
-
- /* Compute how many bytes we need per irq and allocate them */
- bytes = nr * sizeof(unsigned int);
+ void *ptr;
node = cpu_to_node(cpu);
- ptr = kzalloc_node(bytes, GFP_ATOMIC, node);
- printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n", cpu, node);
+ ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs), GFP_ATOMIC, node);
- if (ptr)
- desc->kstat_irqs = (unsigned int *)ptr;
+ /*
+ * don't overwite if can not get new one
+ * init_copy_kstat_irqs() could still use old one
+ */
+ if (ptr) {
+ printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n",
+ cpu, node);
+ desc->kstat_irqs = ptr;
+ }
}
static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
}
};
+static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
int __init early_irq_init(void)
{
struct irq_desc *desc;
for (i = 0; i < count; i++) {
desc[i].irq = i;
init_alloc_desc_masks(&desc[i], 0, true);
+ desc[i].kstat_irqs = kstat_irqs_all[i];
}
return arch_early_irq_init();
}
}
#endif /* !CONFIG_SPARSE_IRQ */
+void clear_kstat_irqs(struct irq_desc *desc)
+{
+ memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
+}
+
/*
* What should we do if we get a hw irq event on an illegal vector?
* Each architecture has to answer this themself.
return IRQ_NONE;
}
+ DEFINE_TRACE(irq_handler_entry);
+ DEFINE_TRACE(irq_handler_exit);
+
/**
* handle_IRQ_event - irq action chain handler
* @irq: the interrupt number
irqreturn_t ret, retval = IRQ_NONE;
unsigned int status = 0;
+ WARN_ONCE(!in_irq(), "BUG: IRQ handler called from non-hardirq context!");
+
if (!(action->flags & IRQF_DISABLED))
local_irq_enable_in_hardirq();
do {
+ trace_irq_handler_entry(irq, action);
ret = action->handler(irq, action->dev_id);
+ trace_irq_handler_exit(irq, action, ret);
if (ret == IRQ_HANDLED)
status |= action->flags;
retval |= ret;
}
#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+
+#ifdef CONFIG_ENABLE_WARN_DEPRECATED
+# warning __do_IRQ is deprecated. Please convert to proper flow handlers
+#endif
+
/**
* __do_IRQ - original all in one highlevel IRQ handler
* @irq: the interrupt number
}
}
-#ifdef CONFIG_SPARSE_IRQ
unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
{
struct irq_desc *desc = irq_to_desc(irq);
return desc ? desc->kstat_irqs[cpu] : 0;
}
-#endif
EXPORT_SYMBOL(kstat_irqs_cpu);
#include <linux/hash.h>
#include <linux/ftrace.h>
#include <linux/stringify.h>
+ #include <trace/lockdep.h>
#include <asm/sections.h>
atomic_t nr_find_usage_forwards_recursions;
atomic_t nr_find_usage_backwards_checks;
atomic_t nr_find_usage_backwards_recursions;
- # define debug_atomic_inc(ptr) atomic_inc(ptr)
- # define debug_atomic_dec(ptr) atomic_dec(ptr)
- # define debug_atomic_read(ptr) atomic_read(ptr)
- #else
- # define debug_atomic_inc(ptr) do { } while (0)
- # define debug_atomic_dec(ptr) do { } while (0)
- # define debug_atomic_read(ptr) 0
#endif
/*
curr->comm, task_pid_nr(curr));
print_lock(this);
if (forwards)
- printk("but this lock took another, %s-irq-unsafe lock in the past:\n", irqclass);
+ printk("but this lock took another, %s-unsafe lock in the past:\n", irqclass);
else
- printk("but this lock was taken by another, %s-irq-safe lock in the past:\n", irqclass);
+ printk("but this lock was taken by another, %s-safe lock in the past:\n", irqclass);
print_lock_name(other);
printk("\n\nand interrupts could create inverse lock ordering between them.\n\n");
enum lock_usage_bit bit, const char *name);
static int
- mark_lock_irq(struct task_struct *curr, struct held_lock *this, int new_bit)
+ mark_lock_irq(struct task_struct *curr, struct held_lock *this,
+ enum lock_usage_bit new_bit)
{
int excl_bit = exclusive_bit(new_bit);
int read = new_bit & 1;
* states.
*/
if ((!read || !dir || STRICT_READ_CHECKS) &&
- !usage(curr, this, excl_bit, state_name(new_bit)))
+ !usage(curr, this, excl_bit, state_name(new_bit & ~1)))
return 0;
/*
debug_atomic_inc(&redundant_softirqs_off);
}
-void lockdep_trace_alloc(gfp_t gfp_mask)
+static void __lockdep_trace_alloc(gfp_t gfp_mask, unsigned long flags)
{
struct task_struct *curr = current;
if (!(gfp_mask & __GFP_FS))
return;
- if (DEBUG_LOCKS_WARN_ON(irqs_disabled()))
+ if (DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)))
return;
mark_held_locks(curr, RECLAIM_FS);
}
+static void check_flags(unsigned long flags);
+
+void lockdep_trace_alloc(gfp_t gfp_mask)
+{
+ unsigned long flags;
+
+ if (unlikely(current->lockdep_recursion))
+ return;
+
+ raw_local_irq_save(flags);
+ check_flags(flags);
+ current->lockdep_recursion = 1;
+ __lockdep_trace_alloc(gfp_mask, flags);
+ current->lockdep_recursion = 0;
+ raw_local_irq_restore(flags);
+}
+
static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
{
/*
}
EXPORT_SYMBOL_GPL(lock_set_class);
+ DEFINE_TRACE(lock_acquire);
+
/*
* We are not always called with irqs disabled - do that here,
* and also avoid lockdep recursion:
{
unsigned long flags;
+ trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+
if (unlikely(current->lockdep_recursion))
return;
}
EXPORT_SYMBOL_GPL(lock_acquire);
+ DEFINE_TRACE(lock_release);
+
void lock_release(struct lockdep_map *lock, int nested,
unsigned long ip)
{
unsigned long flags;
+ trace_lock_release(lock, nested, ip);
+
if (unlikely(current->lockdep_recursion))
return;
lock->ip = ip;
}
+ DEFINE_TRACE(lock_contended);
+
void lock_contended(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
+ trace_lock_contended(lock, ip);
+
if (unlikely(!lock_stat))
return;
}
EXPORT_SYMBOL_GPL(lock_contended);
+ DEFINE_TRACE(lock_acquired);
+
void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
+ trace_lock_acquired(lock, ip);
+
if (unlikely(!lock_stat))
return;
mutex_lock(&module_mutex);
/* Store the name of the last unloaded module for diagnostic purposes */
strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
- unregister_dynamic_debug_module(mod->name);
+ ddebug_remove_module(mod->name);
free_module(mod);
out:
}
#endif /* CONFIG_KALLSYMS */
-static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num)
+static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num)
{
-#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG
- unsigned int i;
-
- for (i = 0; i < num; i++) {
- register_dynamic_debug_module(debug[i].modname,
- debug[i].type,
- debug[i].logical_modname,
- debug[i].flag_names,
- debug[i].hash, debug[i].hash2);
- }
-#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */
+#ifdef CONFIG_DYNAMIC_DEBUG
+ if (ddebug_add_module(debug, num, debug->modname))
+ printk(KERN_ERR "dynamic debug error adding module: %s\n",
+ debug->modname);
+#endif
}
static void *module_alloc_update_bounds(unsigned long size)
add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
if (!mod->taints) {
- struct mod_debug *debug;
+ struct _ddebug *debug;
unsigned int num_debug;
debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
sizeof(*debug), &num_debug);
- dynamic_printk_setup(debug, num_debug);
+ if (debug)
+ dynamic_debug_setup(debug, num_debug);
}
/* sechdrs[0].sh_size is always zero */
/* Is this a valid kernel address? */
- __notrace_funcgraph struct module *__module_text_address(unsigned long addr)
+ struct module *__module_text_address(unsigned long addr)
{
struct module *mod;
*/
for_each_online_cpu(i) {
if (unlikely(!chan->buf[i])) {
- printk(KERN_ERR "relay_late_setup_files: CPU %u "
- "has no buffer, it must have!\n", i);
- BUG();
+ WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n");
err = -EINVAL;
break;
}
* from the scheduler (trying to re-grab
* rq->lock), so defer it.
*/
- __mod_timer(&buf->timer, jiffies + 1);
+ mod_timer(&buf->timer, jiffies + 1);
}
old = buf->data;
*/
static DEFINE_SPINLOCK(task_group_lock);
+#ifdef CONFIG_SMP
+static int root_task_group_empty(void)
+{
+ return list_empty(&root_task_group.children);
+}
+#endif
+
#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else
+#ifdef CONFIG_SMP
+static int root_task_group_empty(void)
+{
+ return 1;
+}
+#endif
+
static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline struct task_group *task_group(struct task_struct *p)
{
struct rt_prio_array active;
unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- int highest_prio; /* highest queued rt task prio */
+ struct {
+ int curr; /* highest queued rt task prio */
+#ifdef CONFIG_SMP
+ int next; /* next highest */
+#endif
+ } highest_prio;
#endif
#ifdef CONFIG_SMP
unsigned long rt_nr_migratory;
int overloaded;
+ struct plist_head pushable_tasks;
#endif
int rt_throttled;
u64 rt_time;
unsigned long nr_running;
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
- unsigned char idle_at_tick;
#ifdef CONFIG_NO_HZ
unsigned long last_tick_seen;
unsigned char in_nohz_recently;
struct root_domain *rd;
struct sched_domain *sd;
+ unsigned char idle_at_tick;
/* For active balancing */
int active_balance;
int push_cpu;
/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
/* sys_sched_yield() stats */
- unsigned int yld_exp_empty;
- unsigned int yld_act_empty;
- unsigned int yld_both_empty;
unsigned int yld_count;
/* schedule() stats */
assert_spin_locked(&task_rq(p)->lock);
- if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+ if (test_tsk_need_resched(p))
return;
- set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+ set_tsk_need_resched(p);
cpu = task_cpu(p);
if (cpu == smp_processor_id())
* lockless. The worst case is that the other CPU runs the
* idle task through an additional NOOP schedule()
*/
- set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED);
+ set_tsk_need_resched(rq->idle);
/* NEED_RESCHED must be visible before we test polling */
smp_mb();
#endif
+#ifdef CONFIG_PREEMPT
+
/*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ * fair double_lock_balance: Safely acquires both rq->locks in a fair
+ * way at the expense of forcing extra atomic operations in all
+ * invocations. This assures that the double_lock is acquired using the
+ * same underlying policy as the spinlock_t on this architecture, which
+ * reduces latency compared to the unfair variant below. However, it
+ * also adds more overhead and therefore may reduce throughput.
*/
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
+ __releases(this_rq->lock)
+ __acquires(busiest->lock)
+ __acquires(this_rq->lock)
+{
+ spin_unlock(&this_rq->lock);
+ double_rq_lock(this_rq, busiest);
+
+ return 1;
+}
+
+#else
+/*
+ * Unfair double_lock_balance: Optimizes throughput at the expense of
+ * latency by eliminating extra atomic operations when the locks are
+ * already in proper order on entry. This favors lower cpu-ids and will
+ * grant the double lock to lower cpus over higher ids under contention,
+ * regardless of entry order into the function.
+ */
+static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
int ret = 0;
- if (unlikely(!irqs_disabled())) {
- /* printk() doesn't work good under rq->lock */
- spin_unlock(&this_rq->lock);
- BUG_ON(1);
- }
if (unlikely(!spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
spin_unlock(&this_rq->lock);
return ret;
}
+#endif /* CONFIG_PREEMPT */
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+{
+ if (unlikely(!irqs_disabled())) {
+ /* printk() doesn't work good under rq->lock */
+ spin_unlock(&this_rq->lock);
+ BUG_ON(1);
+ }
+
+ return _double_lock_balance(this_rq, busiest);
+}
+
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
+ if (wakeup)
+ p->se.start_runtime = p->se.sum_exec_runtime;
+
sched_info_queued(p);
p->sched_class->enqueue_task(rq, p, wakeup);
p->se.on_rq = 1;
static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
- if (sleep && p->se.last_wakeup) {
- update_avg(&p->se.avg_overlap,
- p->se.sum_exec_runtime - p->se.last_wakeup);
- p->se.last_wakeup = 0;
+ if (sleep) {
+ if (p->se.last_wakeup) {
+ update_avg(&p->se.avg_overlap,
+ p->se.sum_exec_runtime - p->se.last_wakeup);
+ p->se.last_wakeup = 0;
+ } else {
+ update_avg(&p->se.avg_wakeup,
+ sysctl_sched_wakeup_granularity);
+ }
}
sched_info_dequeued(p);
* it must be off the runqueue _entirely_, and not
* preempted!
*
- * So if it wa still runnable (but just not actively
+ * So if it was still runnable (but just not actively
* running right now), it's preempted, and we should
* yield - it could be a while.
*/
sync = 0;
#ifdef CONFIG_SMP
- if (sched_feat(LB_WAKEUP_UPDATE)) {
+ if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) {
struct sched_domain *sd;
this_cpu = raw_smp_processor_id();
activate_task(rq, p, 1);
success = 1;
+ /*
+ * Only attribute actual wakeups done by this task.
+ */
+ if (!in_interrupt()) {
+ struct sched_entity *se = ¤t->se;
+ u64 sample = se->sum_exec_runtime;
+
+ if (se->last_wakeup)
+ sample -= se->last_wakeup;
+ else
+ sample -= se->start_runtime;
+ update_avg(&se->avg_wakeup, sample);
+
+ se->last_wakeup = se->sum_exec_runtime;
+ }
+
out_running:
trace_sched_wakeup(rq, p, success);
check_preempt_curr(rq, p, sync);
p->sched_class->task_wake_up(rq, p);
#endif
out:
- current->se.last_wakeup = current->se.sum_exec_runtime;
-
task_rq_unlock(rq, &flags);
return success;
p->se.prev_sum_exec_runtime = 0;
p->se.last_wakeup = 0;
p->se.avg_overlap = 0;
+ p->se.start_runtime = 0;
+ p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;
#endif
+ plist_node_init(&p->pushable_tasks, MAX_PRIO);
+
put_cpu();
}
#ifdef CONFIG_PREEMPT_NOTIFIERS
/**
- * preempt_notifier_register - tell me when current is being being preempted & rescheduled
+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
* @notifier: notifier struct to register
*/
void preempt_notifier_register(struct preempt_notifier *notifier)
{
struct mm_struct *mm = rq->prev_mm;
long prev_state;
+#ifdef CONFIG_SMP
+ int post_schedule = 0;
+
+ if (current->sched_class->needs_post_schedule)
+ post_schedule = current->sched_class->needs_post_schedule(rq);
+#endif
rq->prev_mm = NULL;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
#ifdef CONFIG_SMP
- if (current->sched_class->post_schedule)
+ if (post_schedule)
current->sched_class->post_schedule(rq);
#endif
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
+ int tsk_cache_hot = 0;
/*
* We do not migrate tasks that are:
* 1) running (obviously), or
* 2) too many balance attempts have failed.
*/
- if (!task_hot(p, rq->clock, sd) ||
- sd->nr_balance_failed > sd->cache_nice_tries) {
+ tsk_cache_hot = task_hot(p, rq->clock, sd);
+ if (!tsk_cache_hot ||
+ sd->nr_balance_failed > sd->cache_nice_tries) {
#ifdef CONFIG_SCHEDSTATS
- if (task_hot(p, rq->clock, sd)) {
+ if (tsk_cache_hot) {
schedstat_inc(sd, lb_hot_gained[idle]);
schedstat_inc(p, se.nr_forced_migrations);
}
return 1;
}
- if (task_hot(p, rq->clock, sd)) {
+ if (tsk_cache_hot) {
schedstat_inc(p, se.nr_failed_migrations_hot);
return 0;
}
pulled++;
rem_load_move -= p->se.load.weight;
+#ifdef CONFIG_PREEMPT
+ /*
+ * NEWIDLE balancing is a source of latency, so preemptible kernels
+ * will stop after the first task is pulled to minimize the critical
+ * section.
+ */
+ if (idle == CPU_NEWLY_IDLE)
+ goto out;
+#endif
+
/*
* We only want to steal up to the prescribed amount of weighted load.
*/
sd, idle, all_pinned, &this_best_prio);
class = class->next;
+#ifdef CONFIG_PREEMPT
+ /*
+ * NEWIDLE balancing is a source of latency, so preemptible
+ * kernels will stop after the first task is pulled to minimize
+ * the critical section.
+ */
if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
break;
-
+#endif
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
return 0;
}
-
+/********** Helpers for find_busiest_group ************************/
/*
- * find_busiest_group finds and returns the busiest CPU group within the
- * domain. It calculates and returns the amount of weighted load which
- * should be moved to restore balance via the imbalance parameter.
+ * sd_lb_stats - Structure to store the statistics of a sched_domain
+ * during load balancing.
*/
-static struct sched_group *
-find_busiest_group(struct sched_domain *sd, int this_cpu,
- unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const struct cpumask *cpus, int *balance)
-{
- struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
- unsigned long max_load, avg_load, total_load, this_load, total_pwr;
- unsigned long max_pull;
- unsigned long busiest_load_per_task, busiest_nr_running;
- unsigned long this_load_per_task, this_nr_running;
- int load_idx, group_imb = 0;
+struct sd_lb_stats {
+ struct sched_group *busiest; /* Busiest group in this sd */
+ struct sched_group *this; /* Local group in this sd */
+ unsigned long total_load; /* Total load of all groups in sd */
+ unsigned long total_pwr; /* Total power of all groups in sd */
+ unsigned long avg_load; /* Average load across all groups in sd */
+
+ /** Statistics of this group */
+ unsigned long this_load;
+ unsigned long this_load_per_task;
+ unsigned long this_nr_running;
+
+ /* Statistics of the busiest group */
+ unsigned long max_load;
+ unsigned long busiest_load_per_task;
+ unsigned long busiest_nr_running;
+
+ int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
- int power_savings_balance = 1;
- unsigned long leader_nr_running = 0, min_load_per_task = 0;
- unsigned long min_nr_running = ULONG_MAX;
- struct sched_group *group_min = NULL, *group_leader = NULL;
+ int power_savings_balance; /* Is powersave balance needed for this sd */
+ struct sched_group *group_min; /* Least loaded group in sd */
+ struct sched_group *group_leader; /* Group which relieves group_min */
+ unsigned long min_load_per_task; /* load_per_task in group_min */
+ unsigned long leader_nr_running; /* Nr running of group_leader */
+ unsigned long min_nr_running; /* Nr running of group_min */
#endif
+};
+
+/*
+ * sg_lb_stats - stats of a sched_group required for load_balancing
+ */
+struct sg_lb_stats {
+ unsigned long avg_load; /*Avg load across the CPUs of the group */
+ unsigned long group_load; /* Total load over the CPUs of the group */
+ unsigned long sum_nr_running; /* Nr tasks running in the group */
+ unsigned long sum_weighted_load; /* Weighted load of group's tasks */
+ unsigned long group_capacity;
+ int group_imb; /* Is there an imbalance in the group ? */
+};
+
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+ return cpumask_first(sched_group_cpus(group));
+}
- max_load = this_load = total_load = total_pwr = 0;
- busiest_load_per_task = busiest_nr_running = 0;
- this_load_per_task = this_nr_running = 0;
+/**
+ * get_sd_load_idx - Obtain the load index for a given sched domain.
+ * @sd: The sched_domain whose load_idx is to be obtained.
+ * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ */
+static inline int get_sd_load_idx(struct sched_domain *sd,
+ enum cpu_idle_type idle)
+{
+ int load_idx;
- if (idle == CPU_NOT_IDLE)
+ switch (idle) {
+ case CPU_NOT_IDLE:
load_idx = sd->busy_idx;
- else if (idle == CPU_NEWLY_IDLE)
+ break;
+
+ case CPU_NEWLY_IDLE:
load_idx = sd->newidle_idx;
- else
+ break;
+ default:
load_idx = sd->idle_idx;
+ break;
+ }
- do {
- unsigned long load, group_capacity, max_cpu_load, min_cpu_load;
- int local_group;
- int i;
- int __group_imb = 0;
- unsigned int balance_cpu = -1, first_idle_cpu = 0;
- unsigned long sum_nr_running, sum_weighted_load;
- unsigned long sum_avg_load_per_task;
- unsigned long avg_load_per_task;
+ return load_idx;
+}
- local_group = cpumask_test_cpu(this_cpu,
- sched_group_cpus(group));
- if (local_group)
- balance_cpu = cpumask_first(sched_group_cpus(group));
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * init_sd_power_savings_stats - Initialize power savings statistics for
+ * the given sched_domain, during load balancing.
+ *
+ * @sd: Sched domain whose power-savings statistics are to be initialized.
+ * @sds: Variable containing the statistics for sd.
+ * @idle: Idle status of the CPU at which we're performing load-balancing.
+ */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+ struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+ /*
+ * Busy processors will not participate in power savings
+ * balance.
+ */
+ if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+ sds->power_savings_balance = 0;
+ else {
+ sds->power_savings_balance = 1;
+ sds->min_nr_running = ULONG_MAX;
+ sds->leader_nr_running = 0;
+ }
+}
- /* Tally up the load of all CPUs in the group */
- sum_weighted_load = sum_nr_running = avg_load = 0;
- sum_avg_load_per_task = avg_load_per_task = 0;
+/**
+ * update_sd_power_savings_stats - Update the power saving stats for a
+ * sched_domain while performing load balancing.
+ *
+ * @group: sched_group belonging to the sched_domain under consideration.
+ * @sds: Variable containing the statistics of the sched_domain
+ * @local_group: Does group contain the CPU for which we're performing
+ * load balancing ?
+ * @sgs: Variable containing the statistics of the group.
+ */
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+ struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
- max_cpu_load = 0;
- min_cpu_load = ~0UL;
+ if (!sds->power_savings_balance)
+ return;
- for_each_cpu_and(i, sched_group_cpus(group), cpus) {
- struct rq *rq = cpu_rq(i);
+ /*
+ * If the local group is idle or completely loaded
+ * no need to do power savings balance at this domain
+ */
+ if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
+ !sds->this_nr_running))
+ sds->power_savings_balance = 0;
- if (*sd_idle && rq->nr_running)
- *sd_idle = 0;
+ /*
+ * If a group is already running at full capacity or idle,
+ * don't include that group in power savings calculations
+ */
+ if (!sds->power_savings_balance ||
+ sgs->sum_nr_running >= sgs->group_capacity ||
+ !sgs->sum_nr_running)
+ return;
- /* Bias balancing toward cpus of our domain */
- if (local_group) {
- if (idle_cpu(i) && !first_idle_cpu) {
- first_idle_cpu = 1;
- balance_cpu = i;
- }
+ /*
+ * Calculate the group which has the least non-idle load.
+ * This is the group from where we need to pick up the load
+ * for saving power
+ */
+ if ((sgs->sum_nr_running < sds->min_nr_running) ||
+ (sgs->sum_nr_running == sds->min_nr_running &&
+ group_first_cpu(group) > group_first_cpu(sds->group_min))) {
+ sds->group_min = group;
+ sds->min_nr_running = sgs->sum_nr_running;
+ sds->min_load_per_task = sgs->sum_weighted_load /
+ sgs->sum_nr_running;
+ }
- load = target_load(i, load_idx);
- } else {
- load = source_load(i, load_idx);
- if (load > max_cpu_load)
- max_cpu_load = load;
- if (min_cpu_load > load)
- min_cpu_load = load;
- }
+ /*
+ * Calculate the group which is almost near its
+ * capacity but still has some space to pick up some load
+ * from other group and save more power
+ */
+ if (sgs->sum_nr_running > sgs->group_capacity - 1)
+ return;
- avg_load += load;
- sum_nr_running += rq->nr_running;
- sum_weighted_load += weighted_cpuload(i);
+ if (sgs->sum_nr_running > sds->leader_nr_running ||
+ (sgs->sum_nr_running == sds->leader_nr_running &&
+ group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
+ sds->group_leader = group;
+ sds->leader_nr_running = sgs->sum_nr_running;
+ }
+}
- sum_avg_load_per_task += cpu_avg_load_per_task(i);
- }
+/**
+ * check_power_save_busiest_group - see if there is potential for some power-savings balance
+ * @sds: Variable containing the statistics of the sched_domain
+ * under consideration.
+ * @this_cpu: Cpu at which we're currently performing load-balancing.
+ * @imbalance: Variable to store the imbalance.
+ *
+ * Description:
+ * Check if we have potential to perform some power-savings balance.
+ * If yes, set the busiest group to be the least loaded group in the
+ * sched_domain, so that it's CPUs can be put to idle.
+ *
+ * Returns 1 if there is potential to perform power-savings balance.
+ * Else returns 0.
+ */
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+ int this_cpu, unsigned long *imbalance)
+{
+ if (!sds->power_savings_balance)
+ return 0;
- /*
- * First idle cpu or the first cpu(busiest) in this sched group
- * is eligible for doing load balancing at this and above
- * domains. In the newly idle case, we will allow all the cpu's
- * to do the newly idle load balance.
- */
- if (idle != CPU_NEWLY_IDLE && local_group &&
- balance_cpu != this_cpu && balance) {
- *balance = 0;
- goto ret;
- }
+ if (sds->this != sds->group_leader ||
+ sds->group_leader == sds->group_min)
+ return 0;
- total_load += avg_load;
- total_pwr += group->__cpu_power;
+ *imbalance = sds->min_load_per_task;
+ sds->busiest = sds->group_min;
- /* Adjust by relative CPU power of the group */
- avg_load = sg_div_cpu_power(group,
- avg_load * SCHED_LOAD_SCALE);
+ if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+ cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+ group_first_cpu(sds->group_leader);
+ }
+ return 1;
- /*
- * Consider the group unbalanced when the imbalance is larger
- * than the average weight of two tasks.
- *
- * APZ: with cgroup the avg task weight can vary wildly and
- * might not be a suitable number - should we keep a
- * normalized nr_running number somewhere that negates
- * the hierarchy?
- */
- avg_load_per_task = sg_div_cpu_power(group,
- sum_avg_load_per_task * SCHED_LOAD_SCALE);
+}
+#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+ struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+ return;
+}
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
- __group_imb = 1;
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+ struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
+ return;
+}
+
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+ int this_cpu, unsigned long *imbalance)
+{
+ return 0;
+}
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+
+/**
+ * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @group: sched_group whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @load_idx: Load index of sched_domain of this_cpu for load calc.
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @local_group: Does group contain this_cpu.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sgs: variable to hold the statistics for this group.
+ */
+static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+ enum cpu_idle_type idle, int load_idx, int *sd_idle,
+ int local_group, const struct cpumask *cpus,
+ int *balance, struct sg_lb_stats *sgs)
+{
+ unsigned long load, max_cpu_load, min_cpu_load;
+ int i;
+ unsigned int balance_cpu = -1, first_idle_cpu = 0;
+ unsigned long sum_avg_load_per_task;
+ unsigned long avg_load_per_task;
- group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+ if (local_group)
+ balance_cpu = group_first_cpu(group);
+ /* Tally up the load of all CPUs in the group */
+ sum_avg_load_per_task = avg_load_per_task = 0;
+ max_cpu_load = 0;
+ min_cpu_load = ~0UL;
+
+ for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+ struct rq *rq = cpu_rq(i);
+
+ if (*sd_idle && rq->nr_running)
+ *sd_idle = 0;
+
+ /* Bias balancing toward cpus of our domain */
if (local_group) {
- this_load = avg_load;
- this = group;
- this_nr_running = sum_nr_running;
- this_load_per_task = sum_weighted_load;
- } else if (avg_load > max_load &&
- (sum_nr_running > group_capacity || __group_imb)) {
- max_load = avg_load;
- busiest = group;
- busiest_nr_running = sum_nr_running;
- busiest_load_per_task = sum_weighted_load;
- group_imb = __group_imb;
+ if (idle_cpu(i) && !first_idle_cpu) {
+ first_idle_cpu = 1;
+ balance_cpu = i;
+ }
+
+ load = target_load(i, load_idx);
+ } else {
+ load = source_load(i, load_idx);
+ if (load > max_cpu_load)
+ max_cpu_load = load;
+ if (min_cpu_load > load)
+ min_cpu_load = load;
}
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
- /*
- * Busy processors will not participate in power savings
- * balance.
- */
- if (idle == CPU_NOT_IDLE ||
- !(sd->flags & SD_POWERSAVINGS_BALANCE))
- goto group_next;
+ sgs->group_load += load;
+ sgs->sum_nr_running += rq->nr_running;
+ sgs->sum_weighted_load += weighted_cpuload(i);
- /*
- * If the local group is idle or completely loaded
- * no need to do power savings balance at this domain
- */
- if (local_group && (this_nr_running >= group_capacity ||
- !this_nr_running))
- power_savings_balance = 0;
+ sum_avg_load_per_task += cpu_avg_load_per_task(i);
+ }
- /*
- * If a group is already running at full capacity or idle,
- * don't include that group in power savings calculations
- */
- if (!power_savings_balance || sum_nr_running >= group_capacity
- || !sum_nr_running)
- goto group_next;
+ /*
+ * First idle cpu or the first cpu(busiest) in this sched group
+ * is eligible for doing load balancing at this and above
+ * domains. In the newly idle case, we will allow all the cpu's
+ * to do the newly idle load balance.
+ */
+ if (idle != CPU_NEWLY_IDLE && local_group &&
+ balance_cpu != this_cpu && balance) {
+ *balance = 0;
+ return;
+ }
- /*
- * Calculate the group which has the least non-idle load.
- * This is the group from where we need to pick up the load
- * for saving power
- */
- if ((sum_nr_running < min_nr_running) ||
- (sum_nr_running == min_nr_running &&
- cpumask_first(sched_group_cpus(group)) >
- cpumask_first(sched_group_cpus(group_min)))) {
- group_min = group;
- min_nr_running = sum_nr_running;
- min_load_per_task = sum_weighted_load /
- sum_nr_running;
- }
+ /* Adjust by relative CPU power of the group */
+ sgs->avg_load = sg_div_cpu_power(group,
+ sgs->group_load * SCHED_LOAD_SCALE);
- /*
- * Calculate the group which is almost near its
- * capacity but still has some space to pick up some load
- * from other group and save more power
- */
- if (sum_nr_running <= group_capacity - 1) {
- if (sum_nr_running > leader_nr_running ||
- (sum_nr_running == leader_nr_running &&
- cpumask_first(sched_group_cpus(group)) <
- cpumask_first(sched_group_cpus(group_leader)))) {
- group_leader = group;
- leader_nr_running = sum_nr_running;
- }
+
+ /*
+ * Consider the group unbalanced when the imbalance is larger
+ * than the average weight of two tasks.
+ *
+ * APZ: with cgroup the avg task weight can vary wildly and
+ * might not be a suitable number - should we keep a
+ * normalized nr_running number somewhere that negates
+ * the hierarchy?
+ */
+ avg_load_per_task = sg_div_cpu_power(group,
+ sum_avg_load_per_task * SCHED_LOAD_SCALE);
+
+ if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+ sgs->group_imb = 1;
+
+ sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+
+}
+
+/**
+ * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: sched_domain whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sds: variable to hold the statistics for this sched_domain.
+ */
+static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
+ enum cpu_idle_type idle, int *sd_idle,
+ const struct cpumask *cpus, int *balance,
+ struct sd_lb_stats *sds)
+{
+ struct sched_group *group = sd->groups;
+ struct sg_lb_stats sgs;
+ int load_idx;
+
+ init_sd_power_savings_stats(sd, sds, idle);
+ load_idx = get_sd_load_idx(sd, idle);
+
+ do {
+ int local_group;
+
+ local_group = cpumask_test_cpu(this_cpu,
+ sched_group_cpus(group));
+ memset(&sgs, 0, sizeof(sgs));
+ update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+ local_group, cpus, balance, &sgs);
+
+ if (local_group && balance && !(*balance))
+ return;
+
+ sds->total_load += sgs.group_load;
+ sds->total_pwr += group->__cpu_power;
+
+ if (local_group) {
+ sds->this_load = sgs.avg_load;
+ sds->this = group;
+ sds->this_nr_running = sgs.sum_nr_running;
+ sds->this_load_per_task = sgs.sum_weighted_load;
+ } else if (sgs.avg_load > sds->max_load &&
+ (sgs.sum_nr_running > sgs.group_capacity ||
+ sgs.group_imb)) {
+ sds->max_load = sgs.avg_load;
+ sds->busiest = group;
+ sds->busiest_nr_running = sgs.sum_nr_running;
+ sds->busiest_load_per_task = sgs.sum_weighted_load;
+ sds->group_imb = sgs.group_imb;
}
-group_next:
-#endif
+
+ update_sd_power_savings_stats(group, sds, local_group, &sgs);
group = group->next;
} while (group != sd->groups);
- if (!busiest || this_load >= max_load || busiest_nr_running == 0)
- goto out_balanced;
-
- avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
+}
- if (this_load >= avg_load ||
- 100*max_load <= sd->imbalance_pct*this_load)
- goto out_balanced;
+/**
+ * fix_small_imbalance - Calculate the minor imbalance that exists
+ * amongst the groups of a sched_domain, during
+ * load balancing.
+ * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
+ * @imbalance: Variable to store the imbalance.
+ */
+static inline void fix_small_imbalance(struct sd_lb_stats *sds,
+ int this_cpu, unsigned long *imbalance)
+{
+ unsigned long tmp, pwr_now = 0, pwr_move = 0;
+ unsigned int imbn = 2;
+
+ if (sds->this_nr_running) {
+ sds->this_load_per_task /= sds->this_nr_running;
+ if (sds->busiest_load_per_task >
+ sds->this_load_per_task)
+ imbn = 1;
+ } else
+ sds->this_load_per_task =
+ cpu_avg_load_per_task(this_cpu);
- busiest_load_per_task /= busiest_nr_running;
- if (group_imb)
- busiest_load_per_task = min(busiest_load_per_task, avg_load);
+ if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
+ sds->busiest_load_per_task * imbn) {
+ *imbalance = sds->busiest_load_per_task;
+ return;
+ }
/*
- * We're trying to get all the cpus to the average_load, so we don't
- * want to push ourselves above the average load, nor do we wish to
- * reduce the max loaded cpu below the average load, as either of these
- * actions would just result in more rebalancing later, and ping-pong
- * tasks around. Thus we look for the minimum possible imbalance.
- * Negative imbalances (*we* are more loaded than anyone else) will
- * be counted as no imbalance for these purposes -- we can't fix that
- * by pulling tasks to us. Be careful of negative numbers as they'll
- * appear as very large values with unsigned longs.
+ * OK, we don't have enough imbalance to justify moving tasks,
+ * however we may be able to increase total CPU power used by
+ * moving them.
*/
- if (max_load <= busiest_load_per_task)
- goto out_balanced;
+ pwr_now += sds->busiest->__cpu_power *
+ min(sds->busiest_load_per_task, sds->max_load);
+ pwr_now += sds->this->__cpu_power *
+ min(sds->this_load_per_task, sds->this_load);
+ pwr_now /= SCHED_LOAD_SCALE;
+
+ /* Amount of load we'd subtract */
+ tmp = sg_div_cpu_power(sds->busiest,
+ sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+ if (sds->max_load > tmp)
+ pwr_move += sds->busiest->__cpu_power *
+ min(sds->busiest_load_per_task, sds->max_load - tmp);
+
+ /* Amount of load we'd add */
+ if (sds->max_load * sds->busiest->__cpu_power <
+ sds->busiest_load_per_task * SCHED_LOAD_SCALE)
+ tmp = sg_div_cpu_power(sds->this,
+ sds->max_load * sds->busiest->__cpu_power);
+ else
+ tmp = sg_div_cpu_power(sds->this,
+ sds->busiest_load_per_task * SCHED_LOAD_SCALE);
+ pwr_move += sds->this->__cpu_power *
+ min(sds->this_load_per_task, sds->this_load + tmp);
+ pwr_move /= SCHED_LOAD_SCALE;
+
+ /* Move if we gain throughput */
+ if (pwr_move > pwr_now)
+ *imbalance = sds->busiest_load_per_task;
+}
+
+/**
+ * calculate_imbalance - Calculate the amount of imbalance present within the
+ * groups of a given sched_domain during load balance.
+ * @sds: statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: Cpu for which currently load balance is being performed.
+ * @imbalance: The variable to store the imbalance.
+ */
+static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
+ unsigned long *imbalance)
+{
+ unsigned long max_pull;
/*
* In the presence of smp nice balancing, certain scenarios can have
* max load less than avg load(as we skip the groups at or below
* its cpu_power, while calculating max_load..)
*/
- if (max_load < avg_load) {
+ if (sds->max_load < sds->avg_load) {
*imbalance = 0;
- goto small_imbalance;
+ return fix_small_imbalance(sds, this_cpu, imbalance);
}
/* Don't want to pull so many tasks that a group would go idle */
- max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
+ max_pull = min(sds->max_load - sds->avg_load,
+ sds->max_load - sds->busiest_load_per_task);
/* How much load to actually move to equalise the imbalance */
- *imbalance = min(max_pull * busiest->__cpu_power,
- (avg_load - this_load) * this->__cpu_power)
+ *imbalance = min(max_pull * sds->busiest->__cpu_power,
+ (sds->avg_load - sds->this_load) * sds->this->__cpu_power)
/ SCHED_LOAD_SCALE;
/*
* a think about bumping its value to force at least one task to be
* moved
*/
- if (*imbalance < busiest_load_per_task) {
- unsigned long tmp, pwr_now, pwr_move;
- unsigned int imbn;
-
-small_imbalance:
- pwr_move = pwr_now = 0;
- imbn = 2;
- if (this_nr_running) {
- this_load_per_task /= this_nr_running;
- if (busiest_load_per_task > this_load_per_task)
- imbn = 1;
- } else
- this_load_per_task = cpu_avg_load_per_task(this_cpu);
+ if (*imbalance < sds->busiest_load_per_task)
+ return fix_small_imbalance(sds, this_cpu, imbalance);
- if (max_load - this_load + busiest_load_per_task >=
- busiest_load_per_task * imbn) {
- *imbalance = busiest_load_per_task;
- return busiest;
- }
+}
+/******* find_busiest_group() helpers end here *********************/
- /*
- * OK, we don't have enough imbalance to justify moving tasks,
- * however we may be able to increase total CPU power used by
- * moving them.
- */
+/**
+ * find_busiest_group - Returns the busiest group within the sched_domain
+ * if there is an imbalance. If there isn't an imbalance, and
+ * the user has opted for power-savings, it returns a group whose
+ * CPUs can be put to idle by rebalancing those tasks elsewhere, if
+ * such a group exists.
+ *
+ * Also calculates the amount of weighted load which should be moved
+ * to restore balance.
+ *
+ * @sd: The sched_domain whose busiest group is to be returned.
+ * @this_cpu: The cpu for which load balancing is currently being performed.
+ * @imbalance: Variable which stores amount of weighted load which should
+ * be moved to restore balance/put a group to idle.
+ * @idle: The idle status of this_cpu.
+ * @sd_idle: The idleness of sd
+ * @cpus: The set of CPUs under consideration for load-balancing.
+ * @balance: Pointer to a variable indicating if this_cpu
+ * is the appropriate cpu to perform load balancing at this_level.
+ *
+ * Returns: - the busiest group if imbalance exists.
+ * - If no imbalance and user has opted for power-savings balance,
+ * return the least loaded group whose CPUs can be
+ * put to idle by rebalancing its tasks onto our group.
+ */
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+ unsigned long *imbalance, enum cpu_idle_type idle,
+ int *sd_idle, const struct cpumask *cpus, int *balance)
+{
+ struct sd_lb_stats sds;
- pwr_now += busiest->__cpu_power *
- min(busiest_load_per_task, max_load);
- pwr_now += this->__cpu_power *
- min(this_load_per_task, this_load);
- pwr_now /= SCHED_LOAD_SCALE;
-
- /* Amount of load we'd subtract */
- tmp = sg_div_cpu_power(busiest,
- busiest_load_per_task * SCHED_LOAD_SCALE);
- if (max_load > tmp)
- pwr_move += busiest->__cpu_power *
- min(busiest_load_per_task, max_load - tmp);
-
- /* Amount of load we'd add */
- if (max_load * busiest->__cpu_power <
- busiest_load_per_task * SCHED_LOAD_SCALE)
- tmp = sg_div_cpu_power(this,
- max_load * busiest->__cpu_power);
- else
- tmp = sg_div_cpu_power(this,
- busiest_load_per_task * SCHED_LOAD_SCALE);
- pwr_move += this->__cpu_power *
- min(this_load_per_task, this_load + tmp);
- pwr_move /= SCHED_LOAD_SCALE;
+ memset(&sds, 0, sizeof(sds));
- /* Move if we gain throughput */
- if (pwr_move > pwr_now)
- *imbalance = busiest_load_per_task;
- }
+ /*
+ * Compute the various statistics relavent for load balancing at
+ * this level.
+ */
+ update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
+ balance, &sds);
+
+ /* Cases where imbalance does not exist from POV of this_cpu */
+ /* 1) this_cpu is not the appropriate cpu to perform load balancing
+ * at this level.
+ * 2) There is no busy sibling group to pull from.
+ * 3) This group is the busiest group.
+ * 4) This group is more busy than the avg busieness at this
+ * sched_domain.
+ * 5) The imbalance is within the specified limit.
+ * 6) Any rebalance would lead to ping-pong
+ */
+ if (balance && !(*balance))
+ goto ret;
- return busiest;
+ if (!sds.busiest || sds.busiest_nr_running == 0)
+ goto out_balanced;
-out_balanced:
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
- if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
- goto ret;
+ if (sds.this_load >= sds.max_load)
+ goto out_balanced;
- if (this == group_leader && group_leader != group_min) {
- *imbalance = min_load_per_task;
- if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
- cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
- cpumask_first(sched_group_cpus(group_leader));
- }
- return group_min;
- }
-#endif
+ sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
+ if (sds.this_load >= sds.avg_load)
+ goto out_balanced;
+
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
+
+ sds.busiest_load_per_task /= sds.busiest_nr_running;
+ if (sds.group_imb)
+ sds.busiest_load_per_task =
+ min(sds.busiest_load_per_task, sds.avg_load);
+
+ /*
+ * We're trying to get all the cpus to the average_load, so we don't
+ * want to push ourselves above the average load, nor do we wish to
+ * reduce the max loaded cpu below the average load, as either of these
+ * actions would just result in more rebalancing later, and ping-pong
+ * tasks around. Thus we look for the minimum possible imbalance.
+ * Negative imbalances (*we* are more loaded than anyone else) will
+ * be counted as no imbalance for these purposes -- we can't fix that
+ * by pulling tasks to us. Be careful of negative numbers as they'll
+ * appear as very large values with unsigned longs.
+ */
+ if (sds.max_load <= sds.busiest_load_per_task)
+ goto out_balanced;
+
+ /* Looks like there is an imbalance. Compute it */
+ calculate_imbalance(&sds, this_cpu, imbalance);
+ return sds.busiest;
+
+out_balanced:
+ /*
+ * There is no obvious imbalance. But check if we can do some balancing
+ * to save power.
+ */
+ if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
+ return sds.busiest;
ret:
*imbalance = 0;
return NULL;
#endif
}
+static inline int on_null_domain(int cpu)
+{
+ return !rcu_dereference(cpu_rq(cpu)->sd);
+}
+
/*
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
*
cpumask_test_cpu(cpu, nohz.cpu_mask))
return;
#endif
- if (time_after_eq(jiffies, rq->next_balance))
+ /* Don't need to rebalance while attached to NULL domain */
+ if (time_after_eq(jiffies, rq->next_balance) &&
+ likely(!on_null_domain(cpu)))
raise_softirq(SCHED_SOFTIRQ);
}
#endif
}
- #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
- defined(CONFIG_PREEMPT_TRACER))
-
- static inline unsigned long get_parent_ip(unsigned long addr)
+ unsigned long get_parent_ip(unsigned long addr)
{
if (in_lock_functions(addr)) {
addr = CALLER_ADDR2;
return addr;
}
+ #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+ defined(CONFIG_PREEMPT_TRACER))
+
void __kprobes add_preempt_count(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
#endif
}
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+ if (prev->state == TASK_RUNNING) {
+ u64 runtime = prev->se.sum_exec_runtime;
+
+ runtime -= prev->se.prev_sum_exec_runtime;
+ runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
+
+ /*
+ * In order to avoid avg_overlap growing stale when we are
+ * indeed overlapping and hence not getting put to sleep, grow
+ * the avg_overlap on preemption.
+ *
+ * We use the average preemption runtime because that
+ * correlates to the amount of cache footprint a task can
+ * build up.
+ */
+ update_avg(&prev->se.avg_overlap, runtime);
+ }
+ prev->sched_class->put_prev_task(rq, prev);
+}
+
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev)
+pick_next_task(struct rq *rq)
{
const struct sched_class *class;
struct task_struct *p;
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
- prev->sched_class->put_prev_task(rq, prev);
- next = pick_next_task(rq, prev);
+ put_prev_task(rq, prev);
+ next = pick_next_task(rq);
if (likely(prev != next)) {
sched_info_switch(prev, next);
* between schedule and now.
*/
barrier();
- } while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+ } while (need_resched());
}
EXPORT_SYMBOL(preempt_schedule);
* between schedule and now.
*/
barrier();
- } while (unlikely(test_thread_flag(TIF_NEED_RESCHED)));
+ } while (need_resched());
}
#endif /* CONFIG_PREEMPT */
__wake_up_common(q, mode, 1, 0, NULL);
}
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+ __wake_up_common(q, mode, 1, 0, key);
+}
+
/**
- * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
* @q: the waitqueue
* @mode: which threads
* @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
*
* The sync wakeup differs that the waker knows that it will schedule
* away soon, so while the target thread will be woken up, it will not
*
* On UP it can prevent extra preemption.
*/
-void
-__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+ int nr_exclusive, void *key)
{
unsigned long flags;
int sync = 1;
sync = 0;
spin_lock_irqsave(&q->lock, flags);
- __wake_up_common(q, mode, nr_exclusive, sync, NULL);
+ __wake_up_common(q, mode, nr_exclusive, sync, key);
spin_unlock_irqrestore(&q->lock, flags);
}
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/*
+ * __wake_up_sync - see __wake_up_sync_key()
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+ __wake_up_sync_key(q, mode, nr_exclusive, NULL);
+}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
/**
if (increment > 40)
increment = 40;
- nice = PRIO_TO_NICE(current->static_prio) + increment;
+ nice = TASK_NICE(current) + increment;
if (nice < -20)
nice = -20;
if (nice > 19)
if (!rq->nr_running)
break;
update_rq_clock(rq);
- next = pick_next_task(rq, rq->curr);
+ next = pick_next_task(rq);
if (!next)
break;
next->sched_class->put_prev_task(rq, next);
__set_bit(MAX_RT_PRIO, array->bitmap);
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
- rt_rq->highest_prio = MAX_RT_PRIO;
+ rt_rq->highest_prio.curr = MAX_RT_PRIO;
+#ifdef CONFIG_SMP
+ rt_rq->highest_prio.next = MAX_RT_PRIO;
+#endif
#endif
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
+ plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;
struct cpuacct *ca;
int cpu;
- if (!cpuacct_subsys.active)
+ if (unlikely(!cpuacct_subsys.active))
return;
cpu = task_cpu(tsk);
* consistent between cpus (never more than 2 jiffies difference).
*/
#include <linux/spinlock.h>
+ #include <linux/hardirq.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/ktime.h>
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
__read_mostly int sched_clock_stable;
-#else
-static const int sched_clock_stable = 1;
-#endif
struct sched_clock_data {
/*
s64 delta = now - scd->tick_raw;
u64 clock, min_clock, max_clock;
- WARN_ON_ONCE(!irqs_disabled());
-
if (unlikely(delta < 0))
delta = 0;
- if (unlikely(!sched_clock_running))
- return 0ull;
-
/*
* scd->clock = clamp(scd->tick_gtod + delta,
* max(scd->tick_gtod, scd->clock),
return sched_clock();
scd = cpu_sdc(cpu);
+
+ /*
+ * Normally this is not called in NMI context - but if it is,
+ * trying to do any locking here is totally lethal.
+ */
+ if (unlikely(in_nmi()))
+ return scd->clock;
+
+ if (unlikely(!sched_clock_running))
+ return 0ull;
+
WARN_ON_ONCE(!irqs_disabled());
now = sched_clock();
return clock;
}
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-
void sched_clock_tick(void)
{
- struct sched_clock_data *scd = this_scd();
+ struct sched_clock_data *scd;
u64 now, now_gtod;
+ if (sched_clock_stable)
+ return;
+
if (unlikely(!sched_clock_running))
return;
WARN_ON_ONCE(!irqs_disabled());
+ scd = this_scd();
now_gtod = ktime_to_ns(ktime_get());
now = sched_clock();
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+
+void sched_clock_init(void)
+{
+ sched_clock_running = 1;
+}
+
+u64 sched_clock_cpu(int cpu)
+{
+ if (unlikely(!sched_clock_running))
+ return 0;
+
+ return sched_clock();
+}
+
#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
unsigned long long cpu_clock(int cpu)
#include <linux/kallsyms.h>
#include <linux/debug_locks.h>
#include <linux/lockdep.h>
+ #include <trace/workqueue.h>
/*
* The per-CPU workqueue (if single thread, we always use the first
return (void *) (atomic_long_read(&work->data) & WORK_STRUCT_WQ_DATA_MASK);
}
+ DEFINE_TRACE(workqueue_insertion);
+
static void insert_work(struct cpu_workqueue_struct *cwq,
struct work_struct *work, struct list_head *head)
{
+ trace_workqueue_insertion(cwq->thread, work);
+
set_wq_data(work, cwq);
/*
* Ensure that we get the right work->data if we see the
}
EXPORT_SYMBOL_GPL(queue_delayed_work_on);
+ DEFINE_TRACE(workqueue_execution);
+
static void run_workqueue(struct cpu_workqueue_struct *cwq)
{
spin_lock_irq(&cwq->lock);
*/
struct lockdep_map lockdep_map = work->lockdep_map;
#endif
-
+ trace_workqueue_execution(cwq->thread, work);
cwq->current_work = work;
list_del_init(cwq->worklist.next);
spin_unlock_irq(&cwq->lock);
might_sleep();
lock_map_acquire(&wq->lockdep_map);
lock_map_release(&wq->lockdep_map);
- for_each_cpu_mask_nr(cpu, *cpu_map)
+ for_each_cpu(cpu, cpu_map)
flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, cpu));
}
EXPORT_SYMBOL_GPL(flush_workqueue);
wq = cwq->wq;
cpu_map = wq_cpu_map(wq);
- for_each_cpu_mask_nr(cpu, *cpu_map)
+ for_each_cpu(cpu, cpu_map)
wait_on_cpu_work(per_cpu_ptr(wq->cpu_wq, cpu), work);
}
return cwq;
}
+ DEFINE_TRACE(workqueue_creation);
+
static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
cwq->thread = p;
+ trace_workqueue_creation(cwq->thread, cpu);
+
return 0;
}
}
EXPORT_SYMBOL_GPL(__create_workqueue_key);
+ DEFINE_TRACE(workqueue_destruction);
+
static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
{
/*
* checks list_empty(), and a "normal" queue_work() can't use
* a dead CPU.
*/
+ trace_workqueue_destruction(cwq->thread);
kthread_stop(cwq->thread);
cwq->thread = NULL;
}
list_del(&wq->list);
spin_unlock(&workqueue_lock);
- for_each_cpu_mask_nr(cpu, *cpu_map)
+ for_each_cpu(cpu, cpu_map)
cleanup_workqueue_thread(per_cpu_ptr(wq->cpu_wq, cpu));
cpu_maps_update_done();
# Library configuration
#
+ config BINARY_PRINTF
+ def_bool n
+
menu "Library routines"
config BITREVERSE
config TEXTSEARCH_FSM
tristate
-#
-# plist support is select#ed if needed
-#
-config PLIST
- boolean
-
config HAS_IOMEM
boolean
depends on !NO_IOMEM
bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
depends on EXPERIMENTAL && BROKEN
+#
+# Netlink attribute parsing support is select'ed if needed
+#
+config NLATTR
+ bool
+
endmenu
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
+ #include <trace/kmemtrace.h>
#include <asm/atomic.h>
/*
static LIST_HEAD(free_slob_large);
/*
- * slob_page: True for all slob pages (false for bigblock pages)
+ * is_slob_page: True for all slob pages (false for bigblock pages)
*/
-static inline int slob_page(struct slob_page *sp)
+static inline int is_slob_page(struct slob_page *sp)
{
return PageSlobPage((struct page *)sp);
}
__ClearPageSlobPage((struct page *)sp);
}
+static inline struct slob_page *slob_page(const void *addr)
+{
+ return (struct slob_page *)virt_to_page(addr);
+}
+
/*
* slob_page_free: true for pages on free_slob_pages list.
*/
return !((unsigned long)slob_next(s) & ~PAGE_MASK);
}
-static void *slob_new_page(gfp_t gfp, int order, int node)
+static void *slob_new_pages(gfp_t gfp, int order, int node)
{
void *page;
return page_address(page);
}
+static void slob_free_pages(void *b, int order)
+{
+ free_pages((unsigned long)b, order);
+}
+
/*
* Allocate a slob block within a given slob_page sp.
*/
static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
{
- slob_t *prev, *cur, *aligned = 0;
+ slob_t *prev, *cur, *aligned = NULL;
int delta = 0, units = SLOB_UNITS(size);
for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) {
/* Not enough space: must allocate a new page */
if (!b) {
- b = slob_new_page(gfp & ~__GFP_ZERO, 0, node);
+ b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
if (!b)
- return 0;
- sp = (struct slob_page *)virt_to_page(b);
+ return NULL;
+ sp = slob_page(b);
set_slob_page(sp);
spin_lock_irqsave(&slob_lock, flags);
return;
BUG_ON(!size);
- sp = (struct slob_page *)virt_to_page(block);
+ sp = slob_page(block);
units = SLOB_UNITS(size);
spin_lock_irqsave(&slob_lock, flags);
/* Go directly to page allocator. Do not pass slob allocator */
if (slob_page_free(sp))
clear_slob_page_free(sp);
+ spin_unlock_irqrestore(&slob_lock, flags);
clear_slob_page(sp);
free_slob_page(sp);
free_page((unsigned long)b);
- goto out;
+ return;
}
if (!slob_page_free(sp)) {
{
unsigned int *m;
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+ void *ret;
- lockdep_trace_alloc(flags);
+ lockdep_trace_alloc(gfp);
if (size < PAGE_SIZE - align) {
if (!size)
return ZERO_SIZE_PTR;
m = slob_alloc(size + align, gfp, align, node);
+
if (!m)
return NULL;
*m = size;
- return (void *)m + align;
+ ret = (void *)m + align;
+
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC,
+ _RET_IP_, ret,
+ size, size + align, gfp, node);
} else {
- void *ret;
+ unsigned int order = get_order(size);
- ret = slob_new_page(gfp | __GFP_COMP, order, node);
+ ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node);
if (ret) {
struct page *page;
page = virt_to_page(ret);
page->private = size;
}
- return ret;
+
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC,
+ _RET_IP_, ret,
+ size, PAGE_SIZE << order, gfp, node);
}
+
+ return ret;
}
EXPORT_SYMBOL(__kmalloc_node);
if (unlikely(ZERO_OR_NULL_PTR(block)))
return;
- sp = (struct slob_page *)virt_to_page(block);
- if (slob_page(sp)) {
+ sp = slob_page(block);
+ if (is_slob_page(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
slob_free(m, *m + align);
} else
put_page(&sp->page);
+
+ kmemtrace_mark_free(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, block);
}
EXPORT_SYMBOL(kfree);
if (unlikely(block == ZERO_SIZE_PTR))
return 0;
- sp = (struct slob_page *)virt_to_page(block);
- if (slob_page(sp)) {
+ sp = slob_page(block);
+ if (is_slob_page(sp)) {
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
return SLOB_UNITS(*m) * SLOB_UNIT;
{
void *b;
- if (c->size < PAGE_SIZE)
+ if (c->size < PAGE_SIZE) {
b = slob_alloc(c->size, flags, c->align, node);
- else
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE,
+ _RET_IP_, b, c->size,
+ SLOB_UNITS(c->size) * SLOB_UNIT,
+ flags, node);
+ } else {
- b = slob_new_page(flags, get_order(c->size), node);
+ b = slob_new_pages(flags, get_order(c->size), node);
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE,
+ _RET_IP_, b, c->size,
+ PAGE_SIZE << get_order(c->size),
+ flags, node);
+ }
if (c->ctor)
c->ctor(b);
if (size < PAGE_SIZE)
slob_free(b, size);
else
- free_pages((unsigned long)b, get_order(size));
+ slob_free_pages(b, get_order(size));
}
static void kmem_rcu_free(struct rcu_head *head)
} else {
__kmem_cache_free(b, c->size);
}
+
+ kmemtrace_mark_free(KMEMTRACE_TYPE_CACHE, _RET_IP_, b);
}
EXPORT_SYMBOL(kmem_cache_free);
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+ #include <trace/kmemtrace.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
static void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
- struct track *p;
-
- if (s->offset)
- p = object + s->offset + sizeof(void *);
- else
- p = object + s->inuse;
+ struct track *p = get_track(s, object, alloc);
- p += alloc;
if (addr) {
p->addr = addr;
p->cpu = smp_processor_id();
n = get_node(s, zone_to_nid(zone));
if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
- n->nr_partial > n->min_partial) {
+ n->nr_partial > s->min_partial) {
page = get_partial_node(n);
if (page)
return page;
slab_unlock(page);
} else {
stat(c, DEACTIVATE_EMPTY);
- if (n->nr_partial < n->min_partial) {
+ if (n->nr_partial < s->min_partial) {
/*
* Adding an empty slab to the partial slabs in order
* to avoid page allocator overhead. This slab needs
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
- return slab_alloc(s, gfpflags, -1, _RET_IP_);
+ void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_);
+
+ kmemtrace_mark_alloc(KMEMTRACE_TYPE_CACHE, _RET_IP_, ret,
+ s->objsize, s->size, gfpflags);
+
+ return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc);
+ #ifdef CONFIG_KMEMTRACE
+ void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+ {
+ return slab_alloc(s, gfpflags, -1, _RET_IP_);
+ }
+ EXPORT_SYMBOL(kmem_cache_alloc_notrace);
+ #endif
+
#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
{
- return slab_alloc(s, gfpflags, node, _RET_IP_);
+ void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_CACHE, _RET_IP_, ret,
+ s->objsize, s->size, gfpflags, node);
+
+ return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_node);
#endif
+ #ifdef CONFIG_KMEMTRACE
+ void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+ gfp_t gfpflags,
+ int node)
+ {
+ return slab_alloc(s, gfpflags, node, _RET_IP_);
+ }
+ EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+ #endif
+
/*
* Slow patch handling. This may still be called frequently since objects
* have a longer lifetime than the cpu slabs in most processing loads.
c = get_cpu_slab(s, smp_processor_id());
debug_check_no_locks_freed(object, c->objsize);
if (!(s->flags & SLAB_DEBUG_OBJECTS))
- debug_check_no_obj_freed(object, s->objsize);
+ debug_check_no_obj_freed(object, c->objsize);
if (likely(page == c->page && c->node >= 0)) {
object[c->offset] = c->freelist;
c->freelist = object;
page = virt_to_head_page(x);
slab_free(s, page, x, _RET_IP_);
+
+ kmemtrace_mark_free(KMEMTRACE_TYPE_CACHE, _RET_IP_, x);
}
EXPORT_SYMBOL(kmem_cache_free);
int order;
int min_objects;
int fraction;
+ int max_objects;
/*
* Attempt to find best configuration for a slab. This
min_objects = slub_min_objects;
if (!min_objects)
min_objects = 4 * (fls(nr_cpu_ids) + 1);
+ max_objects = (PAGE_SIZE << slub_max_order)/size;
+ min_objects = min(min_objects, max_objects);
+
while (min_objects > 1) {
fraction = 16;
while (fraction >= 4) {
return order;
fraction /= 2;
}
- min_objects /= 2;
+ min_objects --;
}
/*
init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
{
n->nr_partial = 0;
-
- /*
- * The larger the object size is, the more pages we want on the partial
- * list to avoid pounding the page allocator excessively.
- */
- n->min_partial = ilog2(s->size);
- if (n->min_partial < MIN_PARTIAL)
- n->min_partial = MIN_PARTIAL;
- else if (n->min_partial > MAX_PARTIAL)
- n->min_partial = MAX_PARTIAL;
-
spin_lock_init(&n->list_lock);
INIT_LIST_HEAD(&n->partial);
#ifdef CONFIG_SLUB_DEBUG
}
#endif
+static void set_min_partial(struct kmem_cache *s, unsigned long min)
+{
+ if (min < MIN_PARTIAL)
+ min = MIN_PARTIAL;
+ else if (min > MAX_PARTIAL)
+ min = MAX_PARTIAL;
+ s->min_partial = min;
+}
+
/*
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
if (!calculate_sizes(s, -1))
goto error;
+ /*
+ * The larger the object size is, the more pages we want on the partial
+ * list to avoid pounding the page allocator excessively.
+ */
+ set_min_partial(s, ilog2(s->size));
s->refcount = 1;
#ifdef CONFIG_NUMA
s->remote_node_defrag_ratio = 1000;
void *__kmalloc(size_t size, gfp_t flags)
{
struct kmem_cache *s;
+ void *ret;
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- return slab_alloc(s, flags, -1, _RET_IP_);
+ ret = slab_alloc(s, flags, -1, _RET_IP_);
+
+ kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, ret,
+ size, s->size, flags);
+
+ return ret;
}
EXPORT_SYMBOL(__kmalloc);
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
struct kmem_cache *s;
+ void *ret;
- if (unlikely(size > SLUB_MAX_SIZE))
- return kmalloc_large_node(size, flags, node);
+ if (unlikely(size > SLUB_MAX_SIZE)) {
+ ret = kmalloc_large_node(size, flags, node);
+
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC,
+ _RET_IP_, ret,
+ size, PAGE_SIZE << get_order(size),
+ flags, node);
+
+ return ret;
+ }
s = get_slab(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- return slab_alloc(s, flags, node, _RET_IP_);
+ ret = slab_alloc(s, flags, node, _RET_IP_);
+
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, ret,
+ size, s->size, flags, node);
+
+ return ret;
}
EXPORT_SYMBOL(__kmalloc_node);
#endif
return;
}
slab_free(page->slab, page, object, _RET_IP_);
+
+ kmemtrace_mark_free(KMEMTRACE_TYPE_KMALLOC, _RET_IP_, x);
}
EXPORT_SYMBOL(kfree);
void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
{
struct kmem_cache *s;
+ void *ret;
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large(size, gfpflags);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- return slab_alloc(s, gfpflags, -1, caller);
+ ret = slab_alloc(s, gfpflags, -1, caller);
+
+ /* Honor the call site pointer we recieved. */
+ kmemtrace_mark_alloc(KMEMTRACE_TYPE_KMALLOC, caller, ret, size,
+ s->size, gfpflags);
+
+ return ret;
}
void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
int node, unsigned long caller)
{
struct kmem_cache *s;
+ void *ret;
if (unlikely(size > SLUB_MAX_SIZE))
return kmalloc_large_node(size, gfpflags, node);
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- return slab_alloc(s, gfpflags, node, caller);
+ ret = slab_alloc(s, gfpflags, node, caller);
+
+ /* Honor the call site pointer we recieved. */
+ kmemtrace_mark_alloc_node(KMEMTRACE_TYPE_KMALLOC, caller, ret,
+ size, s->size, gfpflags, node);
+
+ return ret;
}
#ifdef CONFIG_SLUB_DEBUG
}
SLAB_ATTR(order);
+static ssize_t min_partial_show(struct kmem_cache *s, char *buf)
+{
+ return sprintf(buf, "%lu\n", s->min_partial);
+}
+
+static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
+ size_t length)
+{
+ unsigned long min;
+ int err;
+
+ err = strict_strtoul(buf, 10, &min);
+ if (err)
+ return err;
+
+ set_min_partial(s, min);
+ return length;
+}
+SLAB_ATTR(min_partial);
+
static ssize_t ctor_show(struct kmem_cache *s, char *buf)
{
if (s->ctor) {
&object_size_attr.attr,
&objs_per_slab_attr.attr,
&order_attr.attr,
+ &min_partial_attr.attr,
&objects_attr.attr,
&objects_partial_attr.attr,
&total_objects_attr.attr,