Run specified binary instead of /init from the ramdisk,
used for early userspace startup. See initrd.
- reboot= [BUGS=X86-32,BUGS=ARM,BUGS=IA-64] Rebooting mode
- Format: <reboot_mode>[,<reboot_mode2>[,...]]
- See arch/*/kernel/reboot.c or arch/*/kernel/process.c
+ reboot= [KNL]
+ Format (x86 or x86_64):
+ [w[arm] | c[old] | h[ard] | s[oft] | g[pio]] \
+ [[,]s[mp]#### \
+ [[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
+ [[,]f[orce]
+ Where reboot_mode is one of warm (soft) or cold (hard) or gpio,
+ reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
+ reboot_force is either force or not specified,
+ reboot_cpu is s[mp]#### with #### being the processor
+ to be used for rebooting.
relax_domain_level=
[KNL, SMP] Set scheduler's default relax_domain_level.
will select "node" order in following case.
(1) if the DMA zone does not exist or
(2) if the DMA zone comprises greater than 50% of the available memory or
-(3) if any node's DMA zone comprises greater than 60% of its local memory and
+(3) if any node's DMA zone comprises greater than 70% of its local memory and
the amount of local memory is big enough.
Otherwise, "zone" order will be selected. Default order is recommended unless
It's possible to disable huge zero page by writing 0 or enable it
back by writing 1:
-echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
-echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
+echo 0 >/sys/kernel/mm/transparent_hugepage/use_zero_page
+echo 1 >/sys/kernel/mm/transparent_hugepage/use_zero_page
khugepaged will be automatically started when
transparent_hugepage/enabled is set to "always" or "madvise, and it'll
uncompressed data should be determined using the standard magic
numbers. The currently supported compression formats are gzip
(magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A), LZMA
- (magic number 5D 00), and XZ (magic number FD 37). The uncompressed
- payload is currently always ELF (magic number 7F 45 4C 46).
-
+ (magic number 5D 00), XZ (magic number FD 37), and LZ4 (magic number
+ 02 21). The uncompressed payload is currently always ELF (magic
+ number 7F 45 4C 46).
+
Field name: payload_length
Type: read
Offset/size: 0x24c/4
F: drivers/net/hamradio/*scc.c
F: drivers/net/hamradio/z8530.h
+ZBUD COMPRESSED PAGE ALLOCATOR
+M: Seth Jennings <sjenning@linux.vnet.ibm.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: mm/zbud.c
+F: include/linux/zbud.h
+
ZD1211RW WIRELESS DRIVER
M: Daniel Drake <dsd@gentoo.org>
M: Ulrich Kunitz <kune@deine-taler.de>
S: Maintained
F: drivers/tty/serial/zs.*
+ZSWAP COMPRESSED SWAP CACHING
+M: Seth Jennings <sjenning@linux.vnet.ibm.com>
+L: linux-mm@kvack.org
+S: Maintained
+F: mm/zswap.c
+
THE REST
M: Linus Torvalds <torvalds@linux-foundation.org>
L: linux-kernel@vger.kernel.org
}
up_read(&mm->mmap_sem);
- if (user_mode(regs))
- do_group_exit(SIGKILL); /* This will never return */
+ if (user_mode(regs)) {
+ pagefault_out_of_memory();
+ return;
+ }
goto no_context;
select HAVE_IDE if PCI || ISA || PCMCIA
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_KERNEL_GZIP
+ select HAVE_KERNEL_LZ4
select HAVE_KERNEL_LZMA
select HAVE_KERNEL_LZO
select HAVE_KERNEL_XZ
piggy.lzo
piggy.lzma
piggy.xzkern
+piggy.lz4
vmlinux
vmlinux.lds
suffix_$(CONFIG_KERNEL_LZO) = lzo
suffix_$(CONFIG_KERNEL_LZMA) = lzma
suffix_$(CONFIG_KERNEL_XZ) = xzkern
+suffix_$(CONFIG_KERNEL_LZ4) = lz4
# Borrowed libfdt files for the ATAG compatibility mode
font.o font.c head.o misc.o $(OBJS)
# Make sure files are removed during clean
-extra-y += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
+extra-y += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern piggy.lz4 \
lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) \
hyp-stub.S
#include "../../../../lib/decompress_unxz.c"
#endif
+#ifdef CONFIG_KERNEL_LZ4
+#include "../../../../lib/decompress_unlz4.c"
+#endif
+
int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x))
{
return decompress(input, len, NULL, NULL, output, NULL, error);
--- /dev/null
+ .section .piggydata,#alloc
+ .globl input_data
+input_data:
+ .incbin "arch/arm/boot/compressed/piggy.lz4"
+ .globl input_data_end
+input_data_end:
#ifndef __ASSEMBLY__
#include <linux/types.h>
+#include <linux/reboot.h>
void iop3xx_map_io(void);
void iop_init_cp6_handler(void);
void iop_init_time(unsigned long tickrate);
-void iop3xx_restart(char, const char *);
+void iop3xx_restart(enum reboot_mode, const char *);
static inline u32 read_tmr0(void)
{
#include <linux/types.h>
#ifndef __ASSEMBLY__
+#include <linux/reboot.h>
struct tag;
struct meminfo;
unsigned char reserve_lp0 :1; /* never has lp0 */
unsigned char reserve_lp1 :1; /* never has lp1 */
unsigned char reserve_lp2 :1; /* never has lp2 */
- char restart_mode; /* default restart mode */
+ enum reboot_mode reboot_mode; /* default restart mode */
struct smp_operations *smp; /* SMP operations */
bool (*smp_init)(void);
void (*fixup)(struct tag *, char **,
#ifdef CONFIG_MULTI_IRQ_HANDLER
void (*handle_irq)(struct pt_regs *);
#endif
- void (*restart)(char, const char *);
+ void (*restart)(enum reboot_mode, const char *);
};
/*
#include <linux/compiler.h>
#include <linux/linkage.h>
#include <linux/irqflags.h>
+#include <linux/reboot.h>
extern void cpu_init(void);
void soft_restart(unsigned long);
-extern void (*arm_pm_restart)(char str, const char *cmd);
+extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
extern void (*arm_pm_idle)(void);
#define UDBG_UNDEFINED (1 << 0)
#include <linux/hw_breakpoint.h>
#include <linux/cpuidle.h>
#include <linux/leds.h>
+#include <linux/reboot.h>
#include <asm/cacheflush.h>
#include <asm/idmap.h>
BUG();
}
-static void null_restart(char mode, const char *cmd)
+static void null_restart(enum reboot_mode reboot_mode, const char *cmd)
{
}
void (*pm_power_off)(void);
EXPORT_SYMBOL(pm_power_off);
-void (*arm_pm_restart)(char str, const char *cmd) = null_restart;
+void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd) = null_restart;
EXPORT_SYMBOL_GPL(arm_pm_restart);
/*
default_idle();
}
-static char reboot_mode = 'h';
-
-int __init reboot_setup(char *str)
-{
- reboot_mode = str[0];
- return 1;
-}
-
-__setup("reboot=", reboot_setup);
-
/*
* Called by kexec, immediately prior to machine_kexec().
*
#ifdef CONFIG_HAVE_HW_BREAKPOINT
case PTRACE_GETHBPREGS:
- if (ptrace_get_breakpoints(child) < 0)
- return -ESRCH;
-
ret = ptrace_gethbpregs(child, addr,
(unsigned long __user *)data);
- ptrace_put_breakpoints(child);
break;
case PTRACE_SETHBPREGS:
- if (ptrace_get_breakpoints(child) < 0)
- return -ESRCH;
-
ret = ptrace_sethbpregs(child, addr,
(unsigned long __user *)data);
- ptrace_put_breakpoints(child);
break;
#endif
extern void paging_init(struct machine_desc *desc);
extern void sanity_check_meminfo(void);
-extern void reboot_setup(char *str);
+extern enum reboot_mode reboot_mode;
extern void setup_dma_zone(struct machine_desc *desc);
unsigned int processor_id;
setup_dma_zone(mdesc);
- if (mdesc->restart_mode)
- reboot_setup(&mdesc->restart_mode);
+ if (mdesc->reboot_mode != REBOOT_HARD)
+ reboot_mode = mdesc->reboot_mode;
init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
*/
#include <linux/module.h>
+#include <linux/reboot.h>
#include <asm/irq.h>
#include <asm/mach/arch.h>
at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK);
}
-static void at91rm9200_restart(char mode, const char *cmd)
+static void at91rm9200_restart(enum reboot_mode reboot_mode, const char *cmd)
{
/*
* Perform a hardware reset with the use of the Watchdog timer.
#include <linux/clkdev.h>
#include <linux/of.h>
+#include <linux/reboot.h>
/* Map io */
extern void __init at91_map_io(void);
/* reset */
extern void at91_ioremap_rstc(u32 base_addr);
-extern void at91sam9_alt_restart(char, const char *);
-extern void at91sam9g45_restart(char, const char *);
+extern void at91sam9_alt_restart(enum reboot_mode, const char *);
+extern void at91sam9g45_restart(enum reboot_mode, const char *);
/* shutdown */
extern void at91_ioremap_shdwc(u32 base_addr);
WARN(!wdt_regs, "failed to remap watchdog regs");
}
-static void bcm2835_restart(char mode, const char *cmd)
+static void bcm2835_restart(enum reboot_mode mode, const char *cmd)
{
u32 val;
writel_relaxed(val, wdt_regs + PM_RSTS);
/* Continue with normal reset mechanism */
- bcm2835_restart(0, "");
+ bcm2835_restart(REBOOT_HARD, "");
}
static struct map_desc io_map __initdata = {
setup_irq(IRQ_TC2OI, &clps711x_timer_irq);
}
-void clps711x_restart(char mode, const char *cmd)
+void clps711x_restart(enum reboot_mode mode, const char *cmd)
{
soft_restart(0);
}
* Common bits.
*/
+#include <linux/reboot.h>
+
#define CLPS711X_NR_IRQS (33)
#define CLPS711X_NR_GPIO (4 * 8 + 3)
#define CLPS711X_GPIO(prt, bit) ((prt) * 8 + (bit))
extern void clps711x_init_irq(void);
extern void clps711x_timer_init(void);
extern void clps711x_handle_irq(struct pt_regs *regs);
-extern void clps711x_restart(char mode, const char *cmd);
+extern void clps711x_restart(enum reboot_mode mode, const char *cmd);
extern void clps711x_init_early(void);
#ifndef __CNS3XXX_CORE_H
#define __CNS3XXX_CORE_H
+#include <linux/reboot.h>
+
extern void cns3xxx_timer_init(void);
#ifdef CONFIG_CACHE_L2X0
void __init cns3xxx_map_io(void);
void __init cns3xxx_init_irq(void);
void cns3xxx_power_off(void);
-void cns3xxx_restart(char, const char *);
+void cns3xxx_restart(enum reboot_mode, const char *);
#endif /* __CNS3XXX_CORE_H */
}
EXPORT_SYMBOL(cns3xxx_pwr_soft_rst);
-void cns3xxx_restart(char mode, const char *cmd)
+void cns3xxx_restart(enum reboot_mode mode, const char *cmd)
{
/*
* To reset, we hit the on-board reset register
#include <linux/serial_8250.h>
#include <linux/ahci_platform.h>
#include <linux/clk.h>
+#include <linux/reboot.h>
#include <mach/cputype.h>
#include <mach/common.h>
.resource = da8xx_watchdog_resources,
};
-void da8xx_restart(char mode, const char *cmd)
+void da8xx_restart(enum reboot_mode mode, const char *cmd)
{
struct device *dev;
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
#include <linux/io.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#include <linux/platform_data/i2c-davinci.h>
.resource = wdt_resources,
};
-void davinci_restart(char mode, const char *cmd)
+void davinci_restart(enum reboot_mode mode, const char *cmd)
{
davinci_watchdog_reset(&davinci_wdt_device);
}
#include <linux/compiler.h>
#include <linux/types.h>
+#include <linux/reboot.h>
extern void davinci_timer_init(void);
extern void davinci_common_init(struct davinci_soc_info *soc_info);
extern void davinci_init_ide(void);
-void davinci_restart(char mode, const char *cmd);
+void davinci_restart(enum reboot_mode mode, const char *cmd);
void davinci_init_late(void);
#ifdef CONFIG_DAVINCI_RESET_CLOCKS
#include <linux/davinci_emac.h>
#include <linux/spi/spi.h>
#include <linux/platform_data/davinci_asp.h>
+#include <linux/reboot.h>
#include <linux/videodev2.h>
#include <mach/serial.h>
(struct vpif_display_config *display_config);
int da850_register_vpif_capture
(struct vpif_capture_config *capture_config);
-void da8xx_restart(char mode, const char *cmd);
+void da8xx_restart(enum reboot_mode mode, const char *cmd);
void da8xx_rproc_reserve_cma(void);
int da8xx_register_rproc(void);
#include <linux/serial_8250.h>
#include <linux/input/matrix_keypad.h>
#include <linux/mfd/ti_ssp.h>
+#include <linux/reboot.h>
#include <linux/platform_data/mmc-davinci.h>
#include <linux/platform_data/mtd-davinci.h>
extern void tnetv107x_init(void);
extern void tnetv107x_devices_init(struct tnetv107x_device_info *);
extern void tnetv107x_irq_init(void);
-void tnetv107x_restart(char mode, const char *cmd);
+void tnetv107x_restart(enum reboot_mode mode, const char *cmd);
#endif
#include <linux/io.h>
#include <linux/err.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
#include <asm/mach/map.h>
__raw_writel(1, ®s->kick);
}
-void tnetv107x_restart(char mode, const char *cmd)
+void tnetv107x_restart(enum reboot_mode mode, const char *cmd)
{
tnetv107x_watchdog_reset(&tnetv107x_wdt_device);
}
dove_xor1_init();
}
-void dove_restart(char mode, const char *cmd)
+void dove_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Enable soft reset to assert RSTOUTn.
#ifndef __ARCH_DOVE_COMMON_H
#define __ARCH_DOVE_COMMON_H
+#include <linux/reboot.h>
+
struct mv643xx_eth_platform_data;
struct mv_sata_platform_data;
void dove_i2c_init(void);
void dove_sdio0_init(void);
void dove_sdio1_init(void);
-void dove_restart(char, const char *);
+void dove_restart(enum reboot_mode, const char *);
#endif
arch_initcall(ebsa110_init);
-static void ebsa110_restart(char mode, const char *cmd)
+static void ebsa110_restart(enum reboot_mode mode, const char *cmd)
{
soft_restart(0x80000000);
}
.atag_offset = 0x400,
.reserve_lp0 = 1,
.reserve_lp2 = 1,
- .restart_mode = 's',
.map_io = ebsa110_map_io,
.init_early = ebsa110_init_early,
.init_irq = ebsa110_init_irq,
#include <linux/spi/spi.h>
#include <linux/export.h>
#include <linux/irqchip/arm-vic.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#include <linux/platform_data/video-ep93xx.h>
gpio_led_register_device(-1, &ep93xx_led_data);
}
-void ep93xx_restart(char mode, const char *cmd)
+void ep93xx_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Set then clear the SWRST bit to initiate a software reset
#ifndef __ASSEMBLY__
+#include <linux/reboot.h>
+
struct i2c_gpio_platform_data;
struct i2c_board_info;
struct spi_board_info;
void ep93xx_init_devices(void);
extern void ep93xx_timer_init(void);
-void ep93xx_restart(char, const char *);
+void ep93xx_restart(enum reboot_mode, const char *);
void ep93xx_init_late(void);
#ifdef CONFIG_CRUNCH
},
};
-void exynos4_restart(char mode, const char *cmd)
+void exynos4_restart(enum reboot_mode mode, const char *cmd)
{
__raw_writel(0x1, S5P_SWRESET);
}
-void exynos5_restart(char mode, const char *cmd)
+void exynos5_restart(enum reboot_mode mode, const char *cmd)
{
struct device_node *np;
u32 val;
#ifndef __ARCH_ARM_MACH_EXYNOS_COMMON_H
#define __ARCH_ARM_MACH_EXYNOS_COMMON_H
+#include <linux/reboot.h>
#include <linux/of.h>
void mct_init(void __iomem *base, int irq_g0, int irq_l0, int irq_l1);
struct map_desc;
void exynos_init_io(void);
-void exynos4_restart(char mode, const char *cmd);
-void exynos5_restart(char mode, const char *cmd);
+void exynos4_restart(enum reboot_mode mode, const char *cmd);
+void exynos5_restart(enum reboot_mode mode, const char *cmd);
void exynos_init_late(void);
/* ToDo: remove these after migrating legacy exynos4 platforms to dt */
MACHINE_START(CATS, "Chalice-CATS")
/* Maintainer: Philip Blundell */
.atag_offset = 0x100,
- .restart_mode = 's',
+ .reboot_mode = REBOOT_SOFT,
.fixup = fixup_cats,
.map_io = footbridge_map_io,
.init_irq = footbridge_init_irq,
}
}
-void footbridge_restart(char mode, const char *cmd)
+void footbridge_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's') {
+ if (mode == REBOOT_SOFT) {
/* Jump into the ROM */
soft_restart(0x41000000);
} else {
+#include <linux/reboot.h>
extern void footbridge_timer_init(void);
extern void isa_timer_init(void);
extern void footbridge_init_irq(void);
extern void isa_init_irq(unsigned int irq);
-extern void footbridge_restart(char, const char *);
+extern void footbridge_restart(enum reboot_mode, const char *);
#endif
}
-static void netwinder_restart(char mode, const char *cmd)
+static void netwinder_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's') {
+ if (mode == REBOOT_SOFT) {
/* Jump into the ROM */
soft_restart(0x41000000);
} else {
#ifndef __HIGHBANK_CORE_H
#define __HIGHBANK_CORE_H
+#include <linux/reboot.h>
+
extern void highbank_set_cpu_jump(int cpu, void *jump_addr);
-extern void highbank_restart(char, const char *);
+extern void highbank_restart(enum reboot_mode, const char *);
extern void __iomem *scu_base_addr;
#ifdef CONFIG_PM_SLEEP
*/
#include <linux/io.h>
#include <asm/proc-fns.h>
+#include <linux/reboot.h>
#include "core.h"
#include "sysregs.h"
-void highbank_restart(char mode, const char *cmd)
+void highbank_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 'h')
+ if (mode == REBOOT_HARD)
highbank_set_pwr_hard_reset();
else
highbank_set_pwr_soft_reset();
#ifndef __ASM_ARCH_MXC_COMMON_H__
#define __ASM_ARCH_MXC_COMMON_H__
+#include <linux/reboot.h>
+
struct platform_device;
struct pt_regs;
struct clk;
extern struct platform_device *mxc_register_gpio(char *name, int id,
resource_size_t iobase, resource_size_t iosize, int irq, int irq_high);
extern void mxc_set_cpu_type(unsigned int type);
-extern void mxc_restart(char, const char *);
+extern void mxc_restart(enum reboot_mode, const char *);
extern void mxc_arch_reset_init(void __iomem *);
extern void mxc_arch_reset_init_dt(void);
extern int mx53_revision(void);
#include <linux/of_platform.h>
#include <linux/opp.h>
#include <linux/phy.h>
+#include <linux/reboot.h>
#include <linux/regmap.h>
#include <linux/micrel_phy.h>
#include <linux/mfd/syscon.h>
mxc_set_cpu_type(rev >> 16 & 0xff);
}
-static void imx6q_restart(char mode, const char *cmd)
+static void imx6q_restart(enum reboot_mode mode, const char *cmd)
{
struct device_node *np;
void __iomem *wdog_base;
/*
* Reset the system. It is called by machine_restart().
*/
-void mxc_restart(char mode, const char *cmd)
+void mxc_restart(enum reboot_mode mode, const char *cmd)
{
unsigned int wcr_enable;
+#include <linux/reboot.h>
#include <linux/amba/serial.h>
extern struct amba_pl010_data ap_uart_data;
void integrator_init_early(void);
int integrator_init(bool is_cp);
void integrator_reserve(void);
-void integrator_restart(char, const char *);
+void integrator_restart(enum reboot_mode, const char *);
void integrator_init_sysfs(struct device *parent, u32 id);
/*
* To reset, we hit the on-board reset register in the system FPGA
*/
-void integrator_restart(char mode, const char *cmd)
+void integrator_restart(enum reboot_mode mode, const char *cmd)
{
cm_control(CM_CTRL_RESET, CM_CTRL_RESET);
}
#define _IOP13XX_HW_H_
#ifndef __ASSEMBLY__
+
+#include <linux/reboot.h>
+
/* The ATU offsets can change based on the strapping */
extern u32 iop13xx_atux_pmmr_offset;
extern u32 iop13xx_atue_pmmr_offset;
void iop13xx_platform_init(void);
void iop13xx_add_tpmi_devices(void);
void iop13xx_init_irq(void);
-void iop13xx_restart(char, const char *);
+void iop13xx_restart(enum reboot_mode, const char *);
/* CPUID CP6 R0 Page 0 */
static inline int iop13xx_cpu_id(void)
__setup("iop13xx_init_uart", iop13xx_init_uart_setup);
__setup("iop13xx_init_i2c", iop13xx_init_i2c_setup);
-void iop13xx_restart(char mode, const char *cmd)
+void iop13xx_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Reset the internal bus (warning both cores are reset)
;
}
-static void n2100_restart(char mode, const char *cmd)
+static void n2100_restart(enum reboot_mode mode, const char *cmd)
{
gpio_line_set(N2100_HARDWARE_RESET, GPIO_LOW);
gpio_line_config(N2100_HARDWARE_RESET, GPIO_OUT);
0xf, 0xfffffffe);
}
-void ixp4xx_restart(char mode, const char *cmd)
+void ixp4xx_restart(enum reboot_mode mode, const char *cmd)
{
- if ( 1 && mode == 's') {
+ if ( 1 && mode == REBOOT_SOFT) {
/* Jump into ROM at address 0 */
soft_restart(0);
} else {
#include <linux/i2c.h>
#include <linux/i2c-gpio.h>
+#include <mach/hardware.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>
#include <asm/mach/flash.h>
#ifndef __ASSEMBLY__
+#include <linux/reboot.h>
+
#include <asm/types.h>
#ifndef __ARMEB__
extern void ixp4xx_init_irq(void);
extern void ixp4xx_sys_init(void);
extern void ixp4xx_timer_init(void);
-extern void ixp4xx_restart(char, const char *);
+extern void ixp4xx_restart(enum reboot_mode, const char *);
extern void ixp4xx_pci_preinit(void);
struct pci_sys_data;
extern int ixp4xx_setup(int nr, struct pci_sys_data *sys);
#include <linux/mv643xx_i2c.h>
#include <linux/timex.h>
#include <linux/kexec.h>
+#include <linux/reboot.h>
#include <net/dsa.h>
#include <asm/page.h>
#include <asm/mach/map.h>
#endif
}
-void kirkwood_restart(char mode, const char *cmd)
+void kirkwood_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Enable soft reset to assert RSTOUTn.
#ifndef __ARCH_KIRKWOOD_COMMON_H
#define __ARCH_KIRKWOOD_COMMON_H
+#include <linux/reboot.h>
+
struct dsa_platform_data;
struct mv643xx_eth_platform_data;
struct mv_sata_platform_data;
void kirkwood_cpuidle_init(void);
void kirkwood_cpufreq_init(void);
-void kirkwood_restart(char, const char *);
+void kirkwood_restart(enum reboot_mode, const char *);
void kirkwood_clk_init(void);
/* board init functions for boards not fully converted to fdt */
extern __init void ks8695_map_io(void);
extern __init void ks8695_init_irq(void);
-extern void ks8695_restart(char, const char *);
+extern void ks8695_restart(enum reboot_mode, const char *);
extern void ks8695_timer_init(void);
setup_irq(KS8695_IRQ_TIMER1, &ks8695_timer_irq);
}
-void ks8695_restart(char mode, const char *cmd)
+void ks8695_restart(enum reboot_mode reboot_mode, const char *cmd)
{
unsigned int reg;
- if (mode == 's')
+ if (reboot_mode == REBOOT_SOFT)
soft_restart(0);
/* disable timer0 */
iotable_init(lpc32xx_io_desc, ARRAY_SIZE(lpc32xx_io_desc));
}
-void lpc23xx_restart(char mode, const char *cmd)
+void lpc23xx_restart(enum reboot_mode mode, const char *cmd)
{
switch (mode) {
- case 's':
- case 'h':
+ case REBOOT_SOFT:
+ case REBOOT_HARD:
lpc32xx_watchdog_reset();
break;
#include <mach/board.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
/*
* Other arch specific structures and functions
extern void __init lpc32xx_init_irq(void);
extern void __init lpc32xx_map_io(void);
extern void __init lpc32xx_serial_init(void);
-extern void lpc23xx_restart(char, const char *);
+extern void lpc23xx_restart(enum reboot_mode, const char *);
/*
mmp_chip_id = __raw_readl(MMP_CHIPID);
}
-void mmp_restart(char mode, const char *cmd)
+void mmp_restart(enum reboot_mode mode, const char *cmd)
{
soft_restart(0);
}
+#include <linux/reboot.h>
#define ARRAY_AND_SIZE(x) (x), ARRAY_SIZE(x)
extern void timer_init(int irq);
extern void __init icu_init_irq(void);
extern void __init mmp_map_io(void);
-extern void mmp_restart(char, const char *);
+extern void mmp_restart(enum reboot_mode, const char *);
extern void __init pxa168_clk_init(void);
extern void __init pxa910_clk_init(void);
extern void __init mmp2_clk_init(void);
#ifndef __ASM_MACH_PXA168_H
#define __ASM_MACH_PXA168_H
+#include <linux/reboot.h>
+
extern void pxa168_timer_init(void);
extern void __init pxa168_init_irq(void);
-extern void pxa168_restart(char, const char *);
+extern void pxa168_restart(enum reboot_mode, const char *);
extern void pxa168_clear_keypad_wakeup(void);
#include <linux/i2c.h>
return platform_device_register(&pxa168_device_usb_host);
}
-void pxa168_restart(char mode, const char *cmd)
+void pxa168_restart(enum reboot_mode mode, const char *cmd)
{
soft_restart(0xffff0000);
}
clk_init();
}
-void mv78xx0_restart(char mode, const char *cmd)
+void mv78xx0_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Enable soft reset to assert RSTOUTn.
#ifndef __ARCH_MV78XX0_COMMON_H
#define __ARCH_MV78XX0_COMMON_H
+#include <linux/reboot.h>
+
struct mv643xx_eth_platform_data;
struct mv_sata_platform_data;
void mv78xx0_uart2_init(void);
void mv78xx0_uart3_init(void);
void mv78xx0_i2c_init(void);
-void mv78xx0_restart(char, const char *);
+void mv78xx0_restart(enum reboot_mode, const char *);
extern void mv78xx0_timer_init(void);
#define ARMADA_XP_MAX_CPUS 4
-void mvebu_restart(char mode, const char *cmd);
+#include <linux/reboot.h>
+
+void mvebu_restart(enum reboot_mode mode, const char *cmd);
void armada_370_xp_init_irq(void);
void armada_370_xp_handle_irq(struct pt_regs *regs);
#include <linux/init.h>
#include <linux/of_address.h>
#include <linux/io.h>
+#include <linux/reboot.h>
static void __iomem *system_controller_base;
{ /* end of list */ },
};
-void mvebu_restart(char mode, const char *cmd)
+void mvebu_restart(enum reboot_mode mode, const char *cmd)
{
if (!system_controller_base) {
pr_err("Cannot restart, system-controller not available: check the device tree\n");
#include <linux/gpio.h>
#include <linux/init.h>
#include <linux/irqchip/mxs.h>
+#include <linux/reboot.h>
#include <linux/micrel_phy.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
/*
* Reset the system. It is called by machine_restart().
*/
-static void mxs_restart(char mode, const char *cmd)
+static void mxs_restart(enum reboot_mode mode, const char *cmd)
{
struct device_node *np;
void __iomem *reset_addr;
#include <linux/platform_device.h>
#include <linux/io.h>
#include <linux/irqchip/arm-vic.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#include <asm/mach/map.h>
#include <mach/netx-regs.h>
subsys_initcall(netx_init);
-void netx_restart(char mode, const char *cmd)
+void netx_restart(enum reboot_mode mode, const char *cmd)
{
writel(NETX_SYSTEM_RES_CR_FIRMW_RES_EN | NETX_SYSTEM_RES_CR_FIRMW_RES,
NETX_SYSTEM_RES_CR);
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#include <linux/reboot.h>
+
extern void __init netx_map_io(void);
extern void __init netx_init_irq(void);
-extern void netx_restart(char, const char *);
+extern void netx_restart(enum reboot_mode, const char *);
extern void netx_timer_init(void);
iotable_init(cpu8815_io_desc, ARRAY_SIZE(cpu8815_io_desc));
}
-static void cpu8815_restart(char mode, const char *cmd)
+static void cpu8815_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *srcbase = ioremap(NOMADIK_SRC_BASE, SZ_4K);
#include <linux/serial_reg.h>
#include <linux/smc91x.h>
#include <linux/export.h>
+#include <linux/reboot.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>
gpio_set_value(0, wdt_gpio_state);
}
-static void voiceblue_restart(char mode, const char *cmd)
+static void voiceblue_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Workaround for 5912/1611b bug mentioned in sprz209d.pdf p. 28
#include <linux/mtd/mtd.h>
#include <linux/i2c-omap.h>
+#include <linux/reboot.h>
#include <plat/i2c.h>
void omap1_init_early(void);
void omap1_init_irq(void);
void omap1_init_late(void);
-void omap1_restart(char, const char *);
+void omap1_restart(enum reboot_mode, const char *);
extern void __init omap_check_revision(void);
*/
#include <linux/kernel.h>
#include <linux/io.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#define OMAP_EXTWARM_RST_SRC_ID_SHIFT 5
-void omap1_restart(char mode, const char *cmd)
+void omap1_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Workaround for 5912/1611b bug mentioned in sprz209d.pdf p. 28
* published by the Free Software Foundation.
*/
#include <linux/kernel.h>
+#include <linux/reboot.h>
#include "common.h"
#include "prm-regbits-33xx.h"
* Resets the SoC. For @cmd, see the 'reboot' syscall in
* kernel/sys.c. No return value.
*/
-void am33xx_restart(char mode, const char *cmd)
+void am33xx_restart(enum reboot_mode mode, const char *cmd)
{
/* TODO: Handle mode and cmd if necessary */
#include <linux/i2c.h>
#include <linux/i2c/twl.h>
#include <linux/i2c-omap.h>
+#include <linux/reboot.h>
#include <asm/proc-fns.h>
#endif
#if defined(CONFIG_SOC_OMAP2420) || defined(CONFIG_SOC_OMAP2430)
-void omap2xxx_restart(char mode, const char *cmd);
+void omap2xxx_restart(enum reboot_mode mode, const char *cmd);
#else
-static inline void omap2xxx_restart(char mode, const char *cmd)
+static inline void omap2xxx_restart(enum reboot_mode mode, const char *cmd)
{
}
#endif
#ifdef CONFIG_SOC_AM33XX
-void am33xx_restart(char mode, const char *cmd);
+void am33xx_restart(enum reboot_mode mode, const char *cmd);
#else
-static inline void am33xx_restart(char mode, const char *cmd)
+static inline void am33xx_restart(enum reboot_mode mode, const char *cmd)
{
}
#endif
#ifdef CONFIG_ARCH_OMAP3
-void omap3xxx_restart(char mode, const char *cmd);
+void omap3xxx_restart(enum reboot_mode mode, const char *cmd);
#else
-static inline void omap3xxx_restart(char mode, const char *cmd)
+static inline void omap3xxx_restart(enum reboot_mode mode, const char *cmd)
{
}
#endif
#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
-void omap44xx_restart(char mode, const char *cmd);
+void omap44xx_restart(enum reboot_mode mode, const char *cmd);
#else
-static inline void omap44xx_restart(char mode, const char *cmd)
+static inline void omap44xx_restart(enum reboot_mode mode, const char *cmd)
{
}
#endif
* Set the DPLL to bypass so that reboot completes successfully. No
* return value.
*/
-void omap2xxx_restart(char mode, const char *cmd)
+void omap2xxx_restart(enum reboot_mode mode, const char *cmd)
{
u32 rate;
*/
#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/reboot.h>
#include "iomap.h"
#include "common.h"
* Resets the SoC. For @cmd, see the 'reboot' syscall in
* kernel/sys.c. No return value.
*/
-void omap3xxx_restart(char mode, const char *cmd)
+void omap3xxx_restart(enum reboot_mode mode, const char *cmd)
{
omap3_ctrl_write_boot_mode((cmd ? (u8)*cmd : 0));
omap3xxx_prm_dpll3_reset(); /* never returns */
#include <linux/export.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/of_address.h>
+#include <linux/reboot.h>
#include <asm/hardware/cache-l2x0.h>
#include <asm/mach/map.h>
*/
#include <linux/types.h>
+#include <linux/reboot.h>
#include "prminst44xx.h"
/**
* Resets the SoC. For @cmd, see the 'reboot' syscall in
* kernel/sys.c. No return value.
*/
-void omap44xx_restart(char mode, const char *cmd)
+void omap44xx_restart(enum reboot_mode mode, const char *cmd)
{
/* XXX Should save 'cmd' into scratchpad for use after reboot */
omap4_prminst_global_warm_sw_reset(); /* never returns */
orion5x_wdt_init();
}
-void orion5x_restart(char mode, const char *cmd)
+void orion5x_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Enable and issue soft reset
#ifndef __ARCH_ORION5X_COMMON_H
#define __ARCH_ORION5X_COMMON_H
+#include <linux/reboot.h>
+
struct dsa_platform_data;
struct mv643xx_eth_platform_data;
struct mv_sata_platform_data;
void orion5x_uart0_init(void);
void orion5x_uart1_init(void);
void orion5x_xor_init(void);
-void orion5x_restart(char, const char *);
+void orion5x_restart(enum reboot_mode, const char *);
/*
* PCIe/PCI functions.
static void lschl_power_off(void)
{
- orion5x_restart('h', NULL);
+ orion5x_restart(REBOOT_HARD, NULL);
}
/*****************************************************************************
static void ls_hgl_power_off(void)
{
- orion5x_restart('h', NULL);
+ orion5x_restart(REBOOT_HARD, NULL);
}
static void lsmini_power_off(void)
{
- orion5x_restart('h', NULL);
+ orion5x_restart(REBOOT_HARD, NULL);
}
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_platform.h>
+#include <linux/reboot.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
NULL
};
-static void picoxcell_wdt_restart(char mode, const char *cmd)
+static void picoxcell_wdt_restart(enum reboot_mode mode, const char *cmd)
{
/*
* Configure the watchdog to reset with the shortest possible timeout
#define __MACH_PRIMA2_COMMON_H__
#include <linux/init.h>
+#include <linux/reboot.h>
+
#include <asm/mach/time.h>
#include <asm/exception.h>
extern void __init sirfsoc_of_irq_init(void);
extern void __init sirfsoc_of_clk_init(void);
-extern void sirfsoc_restart(char, const char *);
+extern void sirfsoc_restart(enum reboot_mode, const char *);
extern asmlinkage void __exception_irq_entry sirfsoc_handle_irq(struct pt_regs *regs);
#ifndef CONFIG_DEBUG_LL
#include <linux/device.h>
#include <linux/of.h>
#include <linux/of_address.h>
+#include <linux/reboot.h>
void __iomem *sirfsoc_rstc_base;
static DEFINE_MUTEX(rstc_lock);
#define SIRFSOC_SYS_RST_BIT BIT(31)
-void sirfsoc_restart(char mode, const char *cmd)
+void sirfsoc_restart(enum reboot_mode mode, const char *cmd)
{
writel(SIRFSOC_SYS_RST_BIT, sirfsoc_rstc_base);
}
/* Green LED off tells the bootloader to halt */
gpio_set_value(CORGI_GPIO_LED_GREEN, 0);
- pxa_restart('h', NULL);
+ pxa_restart(REBOOT_HARD, NULL);
}
-static void corgi_restart(char mode, const char *cmd)
+static void corgi_restart(enum reboot_mode mode, const char *cmd)
{
if (!machine_is_corgi())
/* Green LED on tells the bootloader to reboot */
gpio_set_value(CORGI_GPIO_LED_GREEN, 1);
- pxa_restart('h', cmd);
+ pxa_restart(REBOOT_HARD, cmd);
}
static void __init corgi_init(void)
* published by the Free Software Foundation.
*/
+#include <linux/reboot.h>
+
struct irq_data;
extern void pxa_timer_init(void);
void __init pxa_set_stuart_info(void *info);
void __init pxa_set_hwuart_info(void *info);
-void pxa_restart(char, const char *);
+void pxa_restart(enum reboot_mode, const char *);
#include <linux/wm97xx.h>
#include <linux/mtd/physmap.h>
#include <linux/usb/gpio_vbus.h>
+#include <linux/reboot.h>
#include <linux/regulator/max1586.h>
#include <linux/slab.h>
#include <linux/i2c/pxa-i2c.h>
static void mioa701_poweroff(void)
{
mioa701_machine_exit();
- pxa_restart('s', NULL);
+ pxa_restart(REBOOT_SOFT, NULL);
}
-static void mioa701_restart(char c, const char *cmd)
+static void mioa701_restart(enum reboot_mode c, const char *cmd)
{
mioa701_machine_exit();
- pxa_restart('s', cmd);
+ pxa_restart(REBOOT_SOFT, cmd);
}
static struct gpio global_gpios[] = {
MACHINE_START(MIOA701, "MIO A701")
.atag_offset = 0x100,
- .restart_mode = 's',
.map_io = &pxa27x_map_io,
.nr_irqs = PXA_NR_IRQS,
.init_irq = &pxa27x_init_irq,
static void poodle_poweroff(void)
{
- pxa_restart('h', NULL);
+ pxa_restart(REBOOT_HARD, NULL);
}
static void __init poodle_init(void)
writel_relaxed(readl_relaxed(OSCR) + 368640, OSMR3);
}
-void pxa_restart(char mode, const char *cmd)
+void pxa_restart(enum reboot_mode mode, const char *cmd)
{
local_irq_disable();
local_fiq_disable();
clear_reset_status(RESET_STATUS_ALL);
switch (mode) {
- case 's':
+ case REBOOT_SOFT:
/* Jump into ROM at address 0 */
soft_restart(0);
break;
- case 'g':
+ case REBOOT_GPIO:
do_gpio_reset();
break;
- case 'h':
+ case REBOOT_HARD:
default:
do_hw_reset();
break;
#include <linux/regulator/machine.h>
#include <linux/io.h>
#include <linux/module.h>
+#include <linux/reboot.h>
#include <asm/setup.h>
#include <asm/mach-types.h>
******************************************************************************/
static void spitz_poweroff(void)
{
- pxa_restart('g', NULL);
+ pxa_restart(REBOOT_GPIO, NULL);
}
-static void spitz_restart(char mode, const char *cmd)
+static void spitz_restart(enum reboot_mode mode, const char *cmd)
{
uint32_t msc0 = __raw_readl(MSC0);
/* Bootloader magic for a reboot */
#ifdef CONFIG_MACH_SPITZ
MACHINE_START(SPITZ, "SHARP Spitz")
- .restart_mode = 'g',
.fixup = spitz_fixup,
.map_io = pxa27x_map_io,
.nr_irqs = PXA_NR_IRQS,
#ifdef CONFIG_MACH_BORZOI
MACHINE_START(BORZOI, "SHARP Borzoi")
- .restart_mode = 'g',
.fixup = spitz_fixup,
.map_io = pxa27x_map_io,
.nr_irqs = PXA_NR_IRQS,
#ifdef CONFIG_MACH_AKITA
MACHINE_START(AKITA, "SHARP Akita")
- .restart_mode = 'g',
.fixup = spitz_fixup,
.map_io = pxa27x_map_io,
.nr_irqs = PXA_NR_IRQS,
#include <linux/input/matrix_keypad.h>
#include <linux/i2c/pxa-i2c.h>
#include <linux/usb/gpio_vbus.h>
+#include <linux/reboot.h>
#include <asm/setup.h>
#include <asm/mach-types.h>
static void tosa_poweroff(void)
{
- pxa_restart('g', NULL);
+ pxa_restart(REBOOT_GPIO, NULL);
}
-static void tosa_restart(char mode, const char *cmd)
+static void tosa_restart(enum reboot_mode mode, const char *cmd)
{
uint32_t msc0 = __raw_readl(MSC0);
}
MACHINE_START(TOSA, "SHARP Tosa")
- .restart_mode = 'g',
.fixup = fixup_tosa,
.map_io = pxa25x_map_io,
.nr_irqs = TOSA_NR_IRQS,
#include <linux/io.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/platform_data/clk-realview.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#include <asm/irq.h>
realview_eb_twd_init();
}
-static void realview_eb_restart(char mode, const char *cmd)
+static void realview_eb_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL);
void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK);
#include <linux/io.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/platform_data/clk-realview.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#include <asm/irq.h>
realview_timer_init(IRQ_DC1176_TIMER0);
}
-static void realview_pb1176_restart(char mode, const char *cmd)
+static void realview_pb1176_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL);
void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK);
#include <linux/io.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/platform_data/clk-realview.h>
+#include <linux/reboot.h>
#include <mach/hardware.h>
#include <asm/irq.h>
realview_pb11mp_twd_init();
}
-static void realview_pb11mp_restart(char mode, const char *cmd)
+static void realview_pb11mp_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL);
void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK);
#include <linux/io.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/platform_data/clk-realview.h>
+#include <linux/reboot.h>
#include <asm/irq.h>
#include <asm/mach-types.h>
realview_timer_init(IRQ_PBA8_TIMER0_1);
}
-static void realview_pba8_restart(char mode, const char *cmd)
+static void realview_pba8_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL);
void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK);
#include <linux/io.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/platform_data/clk-realview.h>
+#include <linux/reboot.h>
#include <asm/irq.h>
#include <asm/mach-types.h>
#endif
}
-static void realview_pbx_restart(char mode, const char *cmd)
+static void realview_pbx_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *reset_ctrl = __io_address(REALVIEW_SYS_RESETCTL);
void __iomem *lock_ctrl = __io_address(REALVIEW_SYS_LOCK);
#include <linux/ata_platform.h>
#include <linux/io.h>
#include <linux/i2c.h>
+#include <linux/reboot.h>
#include <asm/elf.h>
#include <asm/mach-types.h>
arch_initcall(rpc_init);
-static void rpc_restart(char mode, const char *cmd)
+static void rpc_restart(enum reboot_mode mode, const char *cmd)
{
iomd_writeb(0, IOMD_ROMCR0);
#ifndef __ARCH_ARM_MACH_S3C24XX_COMMON_H
#define __ARCH_ARM_MACH_S3C24XX_COMMON_H __FILE__
+#include <linux/reboot.h>
+
struct s3c2410_uartcfg;
#ifdef CONFIG_CPU_S3C2410
extern void s3c2410_map_io(void);
extern void s3c2410_init_uarts(struct s3c2410_uartcfg *cfg, int no);
extern void s3c2410_init_clocks(int xtal);
-extern void s3c2410_restart(char mode, const char *cmd);
+extern void s3c2410_restart(enum reboot_mode mode, const char *cmd);
extern void s3c2410_init_irq(void);
#else
#define s3c2410_init_clocks NULL
extern void s3c2412_init_uarts(struct s3c2410_uartcfg *cfg, int no);
extern void s3c2412_init_clocks(int xtal);
extern int s3c2412_baseclk_add(void);
-extern void s3c2412_restart(char mode, const char *cmd);
+extern void s3c2412_restart(enum reboot_mode mode, const char *cmd);
extern void s3c2412_init_irq(void);
#else
#define s3c2412_init_clocks NULL
extern void s3c2416_init_uarts(struct s3c2410_uartcfg *cfg, int no);
extern void s3c2416_init_clocks(int xtal);
extern int s3c2416_baseclk_add(void);
-extern void s3c2416_restart(char mode, const char *cmd);
+extern void s3c2416_restart(enum reboot_mode mode, const char *cmd);
extern void s3c2416_init_irq(void);
extern struct syscore_ops s3c2416_irq_syscore_ops;
extern void s3c244x_map_io(void);
extern void s3c244x_init_uarts(struct s3c2410_uartcfg *cfg, int no);
extern void s3c244x_init_clocks(int xtal);
-extern void s3c244x_restart(char mode, const char *cmd);
+extern void s3c244x_restart(enum reboot_mode mode, const char *cmd);
#else
#define s3c244x_init_clocks NULL
#define s3c244x_init_uarts NULL
extern void s3c2443_init_uarts(struct s3c2410_uartcfg *cfg, int no);
extern void s3c2443_init_clocks(int xtal);
extern int s3c2443_baseclk_add(void);
-extern void s3c2443_restart(char mode, const char *cmd);
+extern void s3c2443_restart(enum reboot_mode mode, const char *cmd);
extern void s3c2443_init_irq(void);
#else
#define s3c2443_init_clocks NULL
#include <linux/syscore_ops.h>
#include <linux/serial_core.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
#include <linux/io.h>
#include <asm/mach/arch.h>
return s3c2410_init();
}
-void s3c2410_restart(char mode, const char *cmd)
+void s3c2410_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's') {
+ if (mode == REBOOT_SOFT) {
soft_restart(0);
}
#include <linux/serial_core.h>
#include <linux/platform_device.h>
#include <linux/io.h>
+#include <linux/reboot.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
cpu_do_idle();
}
-void s3c2412_restart(char mode, const char *cmd)
+void s3c2412_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's')
+ if (mode == REBOOT_SOFT)
soft_restart(0);
/* errata "Watch-dog/Software Reset Problem" specifies that
#include <linux/syscore_ops.h>
#include <linux/clk.h>
#include <linux/io.h>
+#include <linux/reboot.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
.bus = &s3c2416_subsys,
};
-void s3c2416_restart(char mode, const char *cmd)
+void s3c2416_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's')
+ if (mode == REBOOT_SOFT)
soft_restart(0);
__raw_writel(S3C2443_SWRST_RESET, S3C2443_SWRST);
#include <linux/device.h>
#include <linux/clk.h>
#include <linux/io.h>
+#include <linux/reboot.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
.bus = &s3c2443_subsys,
};
-void s3c2443_restart(char mode, const char *cmd)
+void s3c2443_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's')
+ if (mode == REBOOT_SOFT)
soft_restart(0);
__raw_writel(S3C2443_SWRST_RESET, S3C2443_SWRST);
#include <linux/init.h>
#include <linux/serial_core.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
#include <linux/device.h>
#include <linux/syscore_ops.h>
#include <linux/clk.h>
.resume = s3c244x_resume,
};
-void s3c244x_restart(char mode, const char *cmd)
+void s3c244x_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's')
+ if (mode == REBOOT_SOFT)
soft_restart(0);
samsung_wdt_reset();
#include <linux/ioport.h>
#include <linux/serial_core.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
#include <linux/io.h>
#include <linux/dma-mapping.h>
#include <linux/irq.h>
}
arch_initcall(s3c64xx_init_irq_eint);
-void s3c64xx_restart(char mode, const char *cmd)
+void s3c64xx_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode != 's')
+ if (mode != REBOOT_SOFT)
samsung_wdt_reset();
/* if all else fails, or mode was for soft, jump to 0 */
#ifndef __ARCH_ARM_MACH_S3C64XX_COMMON_H
#define __ARCH_ARM_MACH_S3C64XX_COMMON_H
+#include <linux/reboot.h>
+
void s3c64xx_init_irq(u32 vic0, u32 vic1);
void s3c64xx_init_io(struct map_desc *mach_desc, int size);
void s3c64xx_register_clocks(unsigned long xtal, unsigned armclk_limit);
void s3c64xx_setup_clocks(void);
-void s3c64xx_restart(char mode, const char *cmd);
+void s3c64xx_restart(enum reboot_mode mode, const char *cmd);
void s3c64xx_init_late(void);
#ifdef CONFIG_CPU_S3C6400
#include <linux/dma-mapping.h>
#include <linux/gpio.h>
#include <linux/irq.h>
+#include <linux/reboot.h>
#include <asm/irq.h>
#include <asm/proc-fns.h>
}
arch_initcall(s5p64x0_init_irq_eint);
-void s5p64x0_restart(char mode, const char *cmd)
+void s5p64x0_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode != 's')
+ if (mode != REBOOT_SOFT)
samsung_wdt_reset();
soft_restart(0);
#ifndef __ARCH_ARM_MACH_S5P64X0_COMMON_H
#define __ARCH_ARM_MACH_S5P64X0_COMMON_H
+#include <linux/reboot.h>
+
void s5p6440_init_irq(void);
void s5p6450_init_irq(void);
void s5p64x0_init_io(struct map_desc *mach_desc, int size);
void s5p6450_register_clocks(void);
void s5p6450_setup_clocks(void);
-void s5p64x0_restart(char mode, const char *cmd);
+void s5p64x0_restart(enum reboot_mode mode, const char *cmd);
#ifdef CONFIG_CPU_S5P6440
#include <linux/serial_core.h>
#include <linux/platform_device.h>
#include <linux/sched.h>
+#include <linux/reboot.h>
#include <asm/irq.h>
#include <asm/proc-fns.h>
s3c24xx_init_uartdevs("s3c6400-uart", s5p_uart_resources, cfg, no);
}
-void s5pc100_restart(char mode, const char *cmd)
+void s5pc100_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode != 's')
+ if (mode != REBOOT_SOFT)
samsung_wdt_reset();
soft_restart(0);
#ifndef __ARCH_ARM_MACH_S5PC100_COMMON_H
#define __ARCH_ARM_MACH_S5PC100_COMMON_H
+#include <linux/reboot.h>
+
void s5pc100_init_io(struct map_desc *mach_desc, int size);
void s5pc100_init_irq(void);
void s5pc100_register_clocks(void);
void s5pc100_setup_clocks(void);
-void s5pc100_restart(char mode, const char *cmd);
+void s5pc100_restart(enum reboot_mode mode, const char *cmd);
extern int s5pc100_init(void);
extern void s5pc100_map_io(void);
}
};
-void s5pv210_restart(char mode, const char *cmd)
+void s5pv210_restart(enum reboot_mode mode, const char *cmd)
{
__raw_writel(0x1, S5P_SWRESET);
}
#ifndef __ARCH_ARM_MACH_S5PV210_COMMON_H
#define __ARCH_ARM_MACH_S5PV210_COMMON_H
+#include <linux/reboot.h>
+
void s5pv210_init_io(struct map_desc *mach_desc, int size);
void s5pv210_init_irq(void);
void s5pv210_register_clocks(void);
void s5pv210_setup_clocks(void);
-void s5pv210_restart(char mode, const char *cmd);
+void s5pv210_restart(enum reboot_mode mode, const char *cmd);
extern int s5pv210_init(void);
extern void s5pv210_map_io(void);
#include <linux/cpufreq.h>
#include <linux/ioport.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
#include <video/sa1100fb.h>
PMCR = PMCR_SF;
}
-void sa11x0_restart(char mode, const char *cmd)
+void sa11x0_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's') {
+ if (mode == REBOOT_SOFT) {
/* Jump into ROM at address 0 */
soft_restart(0);
} else {
*
* Author: Nicolas Pitre
*/
+#include <linux/reboot.h>
extern void sa1100_timer_init(void);
extern void __init sa1100_map_io(void);
extern void __init sa1100_init_irq(void);
extern void __init sa1100_init_gpio(void);
-extern void sa11x0_restart(char, const char *);
+extern void sa11x0_restart(enum reboot_mode, const char *);
extern void sa11x0_init_late(void);
#define SET_BANK(__nr,__start,__size) \
#include <linux/serial_8250.h>
#include <linux/io.h>
#include <linux/cpu.h>
+#include <linux/reboot.h>
#include <asm/setup.h>
#include <asm/mach-types.h>
#define ROMCARD_SIZE 0x08000000
#define ROMCARD_START 0x10000000
-static void shark_restart(char mode, const char *cmd)
+static void shark_restart(enum reboot_mode mode, const char *cmd)
{
short temp;
/* Reset the Machine via pc[3] of the sequoia chipset */
#include <linux/mmc/sh_mmcif.h>
#include <linux/mmc/sh_mobile_sdhi.h>
#include <linux/i2c-gpio.h>
+#include <linux/reboot.h>
#include <mach/common.h>
#include <mach/irqs.h>
#include <mach/r8a7740.h>
}
#define RESCNT2 IOMEM(0xe6188020)
-static void eva_restart(char mode, const char *cmd)
+static void eva_restart(enum reboot_mode mode, const char *cmd)
{
/* Do soft power on reset */
writel((1 << 31), RESCNT2);
#include <linux/pinctrl/machine.h>
#include <linux/pinctrl/pinconf-generic.h>
#include <linux/platform_device.h>
+#include <linux/reboot.h>
#include <linux/regulator/fixed.h>
#include <linux/regulator/machine.h>
#include <linux/smsc911x.h>
sh73a0_pm_init();
}
-static void kzm9g_restart(char mode, const char *cmd)
+static void kzm9g_restart(enum reboot_mode mode, const char *cmd)
{
#define RESCNT2 IOMEM(0xe6188020)
/* Do soft power on reset */
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
+#include <linux/reboot.h>
#include <asm/hardware/cache-l2x0.h>
#include <asm/mach/arch.h>
socfpga_sysmgr_init();
}
-static void socfpga_cyclone5_restart(char mode, const char *cmd)
+static void socfpga_cyclone5_restart(enum reboot_mode mode, const char *cmd)
{
u32 temp;
temp = readl(rst_manager_base_addr + SOCFPGA_RSTMGR_CTRL);
- if (mode == 'h')
+ if (mode == REBOOT_HARD)
temp |= RSTMGR_CTRL_SWCOLDRSTREQ;
else
temp |= RSTMGR_CTRL_SWWARMRSTREQ;
#include <linux/dmaengine.h>
#include <linux/amba/pl08x.h>
#include <linux/init.h>
+#include <linux/reboot.h>
+
#include <asm/mach/time.h>
extern void spear13xx_timer_init(void);
void __init spear13xx_map_io(void);
void __init spear13xx_l2x0_init(void);
-void spear_restart(char, const char *);
+void spear_restart(enum reboot_mode, const char *);
void spear13xx_secondary_startup(void);
void __cpuinit spear13xx_cpu_die(unsigned int cpu);
*/
#include <linux/io.h>
#include <linux/amba/sp810.h>
+#include <linux/reboot.h>
#include <asm/system_misc.h>
#include <mach/spear.h>
#include "generic.h"
#define SPEAR13XX_SYS_SW_RES (VA_MISC_BASE + 0x204)
-void spear_restart(char mode, const char *cmd)
+void spear_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's') {
+ if (mode == REBOOT_SOFT) {
/* software reset, Jump into ROM at address 0 */
soft_restart(0);
} else {
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/io.h>
+#include <linux/reboot.h>
#include <linux/clk/sunxi.h>
static void __iomem *wdt_base;
-static void sun4i_restart(char mode, const char *cmd)
+static void sun4i_restart(enum reboot_mode mode, const char *cmd)
{
if (!wdt_base)
return;
#define __MACH_TEGRA_BOARD_H
#include <linux/types.h>
+#include <linux/reboot.h>
-void tegra_assert_system_reset(char mode, const char *cmd);
+void tegra_assert_system_reset(enum reboot_mode mode, const char *cmd);
void __init tegra_init_early(void);
void __init tegra_map_common_io(void);
#include <linux/io.h>
#include <linux/clk.h>
#include <linux/delay.h>
+#include <linux/reboot.h>
#include <linux/irqchip.h>
#include <linux/clk-provider.h>
}
#endif
-void tegra_assert_system_reset(char mode, const char *cmd)
+void tegra_assert_system_reset(enum reboot_mode mode, const char *cmd)
{
void __iomem *reset = IO_ADDRESS(TEGRA_PMC_BASE + 0);
u32 reg;
/* Forward declare this function from the watchdog */
void coh901327_watchdog_reset(void);
-static void u300_restart(char mode, const char *cmd)
+static void u300_restart(enum reboot_mode mode, const char *cmd)
{
switch (mode) {
- case 's':
- case 'h':
+ case REBOOT_SOFT:
+ case REBOOT_HARD:
#ifdef CONFIG_COH901327_WATCHDOG
coh901327_watchdog_reset();
#endif
#include <linux/clkdev.h>
#include <linux/mtd/physmap.h>
#include <linux/bitops.h>
+#include <linux/reboot.h>
#include <asm/irq.h>
#include <asm/hardware/arm_timer.h>
}
#endif /* CONFIG_LEDS */
-void versatile_restart(char mode, const char *cmd)
+void versatile_restart(enum reboot_mode mode, const char *cmd)
{
void __iomem *sys = __io_address(VERSATILE_SYS_BASE);
u32 val;
#include <linux/amba/bus.h>
#include <linux/of_platform.h>
+#include <linux/reboot.h>
extern void __init versatile_init(void);
extern void __init versatile_init_early(void);
extern void __init versatile_init_irq(void);
extern void __init versatile_map_io(void);
extern void versatile_timer_init(void);
-extern void versatile_restart(char, const char *);
+extern void versatile_restart(enum reboot_mode, const char *);
extern unsigned int mmc_status(struct device *dev);
#ifdef CONFIG_OF
extern struct of_dev_auxdata versatile_auxdata_lookup[];
#include <linux/clocksource.h>
#include <linux/io.h>
#include <linux/pm.h>
+#include <linux/reboot.h>
#include <asm/mach-types.h>
#include <asm/mach/arch.h>
static void __iomem *pmc_base;
-void vt8500_restart(char mode, const char *cmd)
+void vt8500_restart(enum reboot_mode mode, const char *cmd)
{
if (pmc_base)
writel(1, pmc_base + VT8500_PMSR_REG);
#define WTE (1 << 7)
#define WTRE (1 << 1)
-void nuc9xx_restart(char mode, const char *cmd)
+void nuc9xx_restart(enum reboot_mode mode, const char *cmd)
{
- if (mode == 's') {
+ if (mode == REBOOT_SOFT) {
/* Jump into ROM at address 0 */
soft_restart(0);
} else {
* published by the Free Software Foundation.
*
*/
+
+#include <linux/reboot.h>
+
struct map_desc;
/* core initialisation functions */
extern void nuc900_init_irq(void);
extern void nuc900_timer_init(void);
-extern void nuc9xx_restart(char, const char *);
+extern void nuc9xx_restart(enum reboot_mode, const char *);
#include <linux/gpio.h>
#include <linux/export.h>
#include <asm/hardware/iop3xx.h>
+#include <mach/gpio.h>
void gpio_line_config(int line, int direction)
{
#include <asm/system_misc.h>
#include <mach/hardware.h>
-void iop3xx_restart(char mode, const char *cmd)
+void iop3xx_restart(enum reboot_mode mode, const char *cmd)
{
*IOP3XX_PCSR = 0x30;
*/
out_of_memory:
up_read(&mm->mmap_sem);
- if (user_mode(regs))
- do_group_exit(SIGKILL);
+ if (user_mode(regs)) {
+ pagefault_out_of_memory();
+ return 1;
+ }
no_context:
/* Are we prepared to handle this kernel fault? */
*/
out_of_memory:
up_read(&mm->mmap_sem);
- printk(KERN_ALERT "VM: killing process %s\n", tsk->comm);
- if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR)
- do_exit(SIGKILL);
+ if ((fault_code & MMUFCR_xFC_ACCESS) == MMUFCR_xFC_ACCESS_USR) {
+ pagefault_out_of_memory();
+ return;
+ }
goto no_context;
do_sigbus:
__asm__ __volatile__("l.nop 1");
up_read(&mm->mmap_sem);
- printk("VM: killing process %s\n", tsk->comm);
- if (user_mode(regs))
- do_exit(SIGKILL);
- goto no_context;
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
do_sigbus:
up_read(&mm->mmap_sem);
hw_brk.type = (data & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL;
hw_brk.len = 8;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
- if (ptrace_get_breakpoints(task) < 0)
- return -ESRCH;
-
bp = thread->ptrace_bps[0];
if ((!data) || !(hw_brk.type & HW_BRK_TYPE_RDWR)) {
if (bp) {
unregister_hw_breakpoint(bp);
thread->ptrace_bps[0] = NULL;
}
- ptrace_put_breakpoints(task);
return 0;
}
if (bp) {
ret = modify_user_hw_breakpoint(bp, &attr);
if (ret) {
- ptrace_put_breakpoints(task);
return ret;
}
thread->ptrace_bps[0] = bp;
- ptrace_put_breakpoints(task);
thread->hw_brk = hw_brk;
return 0;
}
ptrace_triggered, NULL, task);
if (IS_ERR(bp)) {
thread->ptrace_bps[0] = NULL;
- ptrace_put_breakpoints(task);
return PTR_ERR(bp);
}
- ptrace_put_breakpoints(task);
-
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
task->thread.hw_brk = hw_brk;
#else /* CONFIG_PPC_ADV_DEBUG_REGS */
if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
brk.type |= HW_BRK_TYPE_WRITE;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
- if (ptrace_get_breakpoints(child) < 0)
- return -ESRCH;
-
/*
* Check if the request is for 'range' breakpoints. We can
* support it if range < 8 bytes.
*/
- if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) {
+ if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE)
len = bp_info->addr2 - bp_info->addr;
- } else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+ else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
len = 1;
- else {
- ptrace_put_breakpoints(child);
+ else
return -EINVAL;
- }
bp = thread->ptrace_bps[0];
- if (bp) {
- ptrace_put_breakpoints(child);
+ if (bp)
return -ENOSPC;
- }
/* Create a new breakpoint request if one doesn't exist already */
hw_breakpoint_init(&attr);
ptrace_triggered, NULL, child);
if (IS_ERR(bp)) {
thread->ptrace_bps[0] = NULL;
- ptrace_put_breakpoints(child);
return PTR_ERR(bp);
}
- ptrace_put_breakpoints(child);
return 1;
#endif /* CONFIG_HAVE_HW_BREAKPOINT */
return -EINVAL;
#ifdef CONFIG_HAVE_HW_BREAKPOINT
- if (ptrace_get_breakpoints(child) < 0)
- return -ESRCH;
-
bp = thread->ptrace_bps[0];
if (bp) {
unregister_hw_breakpoint(bp);
thread->ptrace_bps[0] = NULL;
} else
ret = -ENOENT;
- ptrace_put_breakpoints(child);
return ret;
#else /* CONFIG_HAVE_HW_BREAKPOINT */
if (child->thread.hw_brk.address == 0)
down_read(&mm->mmap_sem);
goto survive;
}
- printk("VM: killing process %s\n", tsk->comm);
- if (user_mode(regs))
- do_group_exit(SIGKILL);
- goto no_context;
+ if (!user_mode(regs))
+ goto no_context;
+ pagefault_out_of_memory();
+ return;
do_sigbus:
up_read(&mm->mmap_sem);
set_tsk_thread_flag(child, TIF_SINGLESTEP);
- if (ptrace_get_breakpoints(child) < 0)
- return;
-
set_single_step(child, pc);
- ptrace_put_breakpoints(child);
}
void user_disable_single_step(struct task_struct *child)
down_read(&mm->mmap_sem);
goto survive;
}
- pr_alert("VM: killing process %s\n", tsk->comm);
- if (!is_kernel_mode)
- do_group_exit(SIGKILL);
- goto no_context;
+ if (is_kernel_mode)
+ goto no_context;
+ pagefault_out_of_memory();
+ return 0;
do_sigbus:
up_read(&mm->mmap_sem);
local_irq_enable();
}
-static char reboot_mode = 'h';
-
-int __init reboot_setup(char *str)
-{
- reboot_mode = str[0];
- return 1;
-}
-
-__setup("reboot=", reboot_setup);
-
void machine_halt(void)
{
gpio_set_value(GPO_SOFT_OFF, 0);
* we may need it to insert some 1:1 mappings so that
* soft boot works.
*/
- setup_mm_for_reboot(reboot_mode);
+ setup_mm_for_reboot();
/* Clean and invalidate caches */
flush_cache_all();
/*
* Now handle reboot code.
*/
- if (reboot_mode == 's') {
+ if (reboot_mode == REBOOT_SOFT) {
/* Jump into ROM at address 0xffff0000 */
cpu_reset(VECTORS_BASE);
} else {
extern void pci_puv3_preinit(void);
extern void __init puv3_init_gpio(void);
-extern void setup_mm_for_reboot(char mode);
+extern void setup_mm_for_reboot(void);
extern char __stubs_start[], __stubs_end[];
extern char __vectors_start[], __vectors_end[];
* the user-mode pages. This will then ensure that we have predictable
* results when turning the mmu off
*/
-void setup_mm_for_reboot(char mode)
+void setup_mm_for_reboot(void)
{
unsigned long base_pmdval;
pgd_t *pgd;
select HAVE_KERNEL_LZMA
select HAVE_KERNEL_XZ
select HAVE_KERNEL_LZO
+ select HAVE_KERNEL_LZ4
select HAVE_HW_BREAKPOINT
select HAVE_MIXED_BREAKPOINTS_REGS
select PERF_EVENTS
# create a compressed vmlinux image from the original vmlinux
#
-targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
+ vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
$(call if_changed,xzkern)
$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
$(call if_changed,lzo)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
+ $(call if_changed,lz4)
suffix-$(CONFIG_KERNEL_GZIP) := gz
suffix-$(CONFIG_KERNEL_BZIP2) := bz2
suffix-$(CONFIG_KERNEL_LZMA) := lzma
suffix-$(CONFIG_KERNEL_XZ) := xz
suffix-$(CONFIG_KERNEL_LZO) := lzo
+suffix-$(CONFIG_KERNEL_LZ4) := lz4
quiet_cmd_mkpiggy = MKPIGGY $@
cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
#include "../../../../lib/decompress_unlzo.c"
#endif
+#ifdef CONFIG_KERNEL_LZ4
+#include "../../../../lib/decompress_unlz4.c"
+#endif
+
static void scroll(void)
{
int i;
#ifndef _ASM_X86_EMERGENCY_RESTART_H
#define _ASM_X86_EMERGENCY_RESTART_H
-enum reboot_type {
- BOOT_TRIPLE = 't',
- BOOT_KBD = 'k',
- BOOT_BIOS = 'b',
- BOOT_ACPI = 'a',
- BOOT_EFI = 'e',
- BOOT_CF9 = 'p',
- BOOT_CF9_COND = 'q',
-};
-
-extern enum reboot_type reboot_type;
-
extern void machine_emergency_restart(void);
#endif /* _ASM_X86_EMERGENCY_RESTART_H */
#include <linux/kdebug.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
+#include <linux/reboot.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
#include <asm/ipi.h>
#include <asm/smp.h>
#include <asm/x86_init.h>
-#include <asm/emergency-restart.h>
#include <asm/nmi.h>
/* BMC sets a bit this MMR non-zero before sending an NMI */
unregister_hw_breakpoint(t->ptrace_bps[i]);
t->ptrace_bps[i] = NULL;
}
+
+ t->debugreg6 = 0;
+ t->ptrace_dr7 = 0;
}
void hw_breakpoint_restore(void)
return dr7;
}
-static int
-ptrace_modify_breakpoint(struct perf_event *bp, int len, int type,
- struct task_struct *tsk, int disabled)
+static int ptrace_fill_bp_fields(struct perf_event_attr *attr,
+ int len, int type, bool disabled)
+{
+ int err, bp_len, bp_type;
+
+ err = arch_bp_generic_fields(len, type, &bp_len, &bp_type);
+ if (!err) {
+ attr->bp_len = bp_len;
+ attr->bp_type = bp_type;
+ attr->disabled = disabled;
+ }
+
+ return err;
+}
+
+static struct perf_event *
+ptrace_register_breakpoint(struct task_struct *tsk, int len, int type,
+ unsigned long addr, bool disabled)
{
- int err;
- int gen_len, gen_type;
struct perf_event_attr attr;
+ int err;
- /*
- * We should have at least an inactive breakpoint at this
- * slot. It means the user is writing dr7 without having
- * written the address register first
- */
- if (!bp)
- return -EINVAL;
+ ptrace_breakpoint_init(&attr);
+ attr.bp_addr = addr;
- err = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
+ err = ptrace_fill_bp_fields(&attr, len, type, disabled);
if (err)
- return err;
+ return ERR_PTR(err);
+
+ return register_user_hw_breakpoint(&attr, ptrace_triggered,
+ NULL, tsk);
+}
- attr = bp->attr;
- attr.bp_len = gen_len;
- attr.bp_type = gen_type;
- attr.disabled = disabled;
+static int ptrace_modify_breakpoint(struct perf_event *bp, int len, int type,
+ int disabled)
+{
+ struct perf_event_attr attr = bp->attr;
+ int err;
+
+ err = ptrace_fill_bp_fields(&attr, len, type, disabled);
+ if (err)
+ return err;
return modify_user_hw_breakpoint(bp, &attr);
}
*/
static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
{
- struct thread_struct *thread = &(tsk->thread);
+ struct thread_struct *thread = &tsk->thread;
unsigned long old_dr7;
- int i, orig_ret = 0, rc = 0;
- int enabled, second_pass = 0;
- unsigned len, type;
- struct perf_event *bp;
-
- if (ptrace_get_breakpoints(tsk) < 0)
- return -ESRCH;
+ bool second_pass = false;
+ int i, rc, ret = 0;
data &= ~DR_CONTROL_RESERVED;
old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
+
restore:
- /*
- * Loop through all the hardware breakpoints, making the
- * appropriate changes to each.
- */
+ rc = 0;
for (i = 0; i < HBP_NUM; i++) {
- enabled = decode_dr7(data, i, &len, &type);
- bp = thread->ptrace_bps[i];
-
- if (!enabled) {
- if (bp) {
- /*
- * Don't unregister the breakpoints right-away,
- * unless all register_user_hw_breakpoint()
- * requests have succeeded. This prevents
- * any window of opportunity for debug
- * register grabbing by other users.
- */
- if (!second_pass)
- continue;
-
- rc = ptrace_modify_breakpoint(bp, len, type,
- tsk, 1);
- if (rc)
- break;
+ unsigned len, type;
+ bool disabled = !decode_dr7(data, i, &len, &type);
+ struct perf_event *bp = thread->ptrace_bps[i];
+
+ if (!bp) {
+ if (disabled)
+ continue;
+
+ bp = ptrace_register_breakpoint(tsk,
+ len, type, 0, disabled);
+ if (IS_ERR(bp)) {
+ rc = PTR_ERR(bp);
+ break;
}
+
+ thread->ptrace_bps[i] = bp;
continue;
}
- rc = ptrace_modify_breakpoint(bp, len, type, tsk, 0);
+ rc = ptrace_modify_breakpoint(bp, len, type, disabled);
if (rc)
break;
}
- /*
- * Make a second pass to free the remaining unused breakpoints
- * or to restore the original breakpoints if an error occurred.
- */
- if (!second_pass) {
- second_pass = 1;
- if (rc < 0) {
- orig_ret = rc;
- data = old_dr7;
- }
+
+ /* Restore if the first pass failed, second_pass shouldn't fail. */
+ if (rc && !WARN_ON(second_pass)) {
+ ret = rc;
+ data = old_dr7;
+ second_pass = true;
goto restore;
}
- ptrace_put_breakpoints(tsk);
-
- return ((orig_ret < 0) ? orig_ret : rc);
+ return ret;
}
/*
*/
static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
{
- struct thread_struct *thread = &(tsk->thread);
+ struct thread_struct *thread = &tsk->thread;
unsigned long val = 0;
if (n < HBP_NUM) {
- struct perf_event *bp;
+ struct perf_event *bp = thread->ptrace_bps[n];
- if (ptrace_get_breakpoints(tsk) < 0)
- return -ESRCH;
-
- bp = thread->ptrace_bps[n];
- if (!bp)
- val = 0;
- else
+ if (bp)
val = bp->hw.info.address;
-
- ptrace_put_breakpoints(tsk);
} else if (n == 6) {
val = thread->debugreg6;
- } else if (n == 7) {
+ } else if (n == 7) {
val = thread->ptrace_dr7;
}
return val;
static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
unsigned long addr)
{
- struct perf_event *bp;
struct thread_struct *t = &tsk->thread;
- struct perf_event_attr attr;
+ struct perf_event *bp = t->ptrace_bps[nr];
int err = 0;
- if (ptrace_get_breakpoints(tsk) < 0)
- return -ESRCH;
-
- if (!t->ptrace_bps[nr]) {
- ptrace_breakpoint_init(&attr);
- /*
- * Put stub len and type to register (reserve) an inactive but
- * correct bp
- */
- attr.bp_addr = addr;
- attr.bp_len = HW_BREAKPOINT_LEN_1;
- attr.bp_type = HW_BREAKPOINT_W;
- attr.disabled = 1;
-
- bp = register_user_hw_breakpoint(&attr, ptrace_triggered,
- NULL, tsk);
-
+ if (!bp) {
/*
+ * Put stub len and type to create an inactive but correct bp.
+ *
* CHECKME: the previous code returned -EIO if the addr wasn't
* a valid task virtual addr. The new one will return -EINVAL in
* this case.
* writing for the user. And anyway this is the previous
* behaviour.
*/
- if (IS_ERR(bp)) {
+ bp = ptrace_register_breakpoint(tsk,
+ X86_BREAKPOINT_LEN_1, X86_BREAKPOINT_WRITE,
+ addr, true);
+ if (IS_ERR(bp))
err = PTR_ERR(bp);
- goto put;
- }
-
- t->ptrace_bps[nr] = bp;
+ else
+ t->ptrace_bps[nr] = bp;
} else {
- bp = t->ptrace_bps[nr];
+ struct perf_event_attr attr = bp->attr;
- attr = bp->attr;
attr.bp_addr = addr;
err = modify_user_hw_breakpoint(bp, &attr);
}
-put:
- ptrace_put_breakpoints(tsk);
return err;
}
static int ptrace_set_debugreg(struct task_struct *tsk, int n,
unsigned long val)
{
- struct thread_struct *thread = &(tsk->thread);
- int rc = 0;
-
+ struct thread_struct *thread = &tsk->thread;
/* There are no DR4 or DR5 registers */
- if (n == 4 || n == 5)
- return -EIO;
+ int rc = -EIO;
- if (n == 6) {
- thread->debugreg6 = val;
- goto ret_path;
- }
if (n < HBP_NUM) {
rc = ptrace_set_breakpoint_addr(tsk, n, val);
- if (rc)
- return rc;
- }
- /* All that's left is DR7 */
- if (n == 7) {
+ } else if (n == 6) {
+ thread->debugreg6 = val;
+ rc = 0;
+ } else if (n == 7) {
rc = ptrace_write_dr7(tsk, val);
if (!rc)
thread->ptrace_dr7 = val;
}
-
-ret_path:
return rc;
}
EXPORT_SYMBOL(pm_power_off);
static const struct desc_ptr no_idt = {};
-static int reboot_mode;
-enum reboot_type reboot_type = BOOT_ACPI;
-int reboot_force;
-
-/*
- * This variable is used privately to keep track of whether or not
- * reboot_type is still set to its default value (i.e., reboot= hasn't
- * been set on the command line). This is needed so that we can
- * suppress DMI scanning for reboot quirks. Without it, it's
- * impossible to override a faulty reboot quirk without recompiling.
- */
-static int reboot_default = 1;
-
-#ifdef CONFIG_SMP
-static int reboot_cpu = -1;
-#endif
/*
* This is set if we need to go through the 'emergency' path.
/* This is set by the PCI code if either type 1 or type 2 PCI is detected */
bool port_cf9_safe = false;
-/*
- * reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci]
- * warm Don't set the cold reboot flag
- * cold Set the cold reboot flag
- * bios Reboot by jumping through the BIOS
- * smp Reboot by executing reset on BSP or other CPU
- * triple Force a triple fault (init)
- * kbd Use the keyboard controller. cold reset (default)
- * acpi Use the RESET_REG in the FADT
- * efi Use efi reset_system runtime service
- * pci Use the so-called "PCI reset register", CF9
- * force Avoid anything that could hang.
- */
-static int __init reboot_setup(char *str)
-{
- for (;;) {
- /*
- * Having anything passed on the command line via
- * reboot= will cause us to disable DMI checking
- * below.
- */
- reboot_default = 0;
-
- switch (*str) {
- case 'w':
- reboot_mode = 0x1234;
- break;
-
- case 'c':
- reboot_mode = 0;
- break;
-
-#ifdef CONFIG_SMP
- case 's':
- if (isdigit(*(str+1))) {
- reboot_cpu = (int) (*(str+1) - '0');
- if (isdigit(*(str+2)))
- reboot_cpu = reboot_cpu*10 + (int)(*(str+2) - '0');
- }
- /*
- * We will leave sorting out the final value
- * when we are ready to reboot, since we might not
- * have detected BSP APIC ID or smp_num_cpu
- */
- break;
-#endif /* CONFIG_SMP */
-
- case 'b':
- case 'a':
- case 'k':
- case 't':
- case 'e':
- case 'p':
- reboot_type = *str;
- break;
-
- case 'f':
- reboot_force = 1;
- break;
- }
-
- str = strchr(str, ',');
- if (str)
- str++;
- else
- break;
- }
- return 1;
-}
-
-__setup("reboot=", reboot_setup);
-
-
/*
* Reboot options and system auto-detection code provided by
* Dell Inc. so their systems "just work". :-)
int i;
int attempt = 0;
int orig_reboot_type = reboot_type;
+ unsigned short mode;
if (reboot_emergency)
emergency_vmx_disable_all();
tboot_shutdown(TB_SHUTDOWN_REBOOT);
/* Tell the BIOS if we want cold or warm reboot */
- *((unsigned short *)__va(0x472)) = reboot_mode;
+ mode = reboot_mode == REBOOT_WARM ? 0x1234 : 0;
+ *((unsigned short *)__va(0x472)) = mode;
for (;;) {
/* Could also try the reset bit in the Hammer NB */
case BOOT_EFI:
if (efi_enabled(EFI_RUNTIME_SERVICES))
- efi.reset_system(reboot_mode ?
+ efi.reset_system(reboot_mode == REBOOT_WARM ?
EFI_RESET_WARM :
EFI_RESET_COLD,
EFI_SUCCESS, 0, NULL);
{
/* Stop the cpus and apics */
#ifdef CONFIG_SMP
-
- /* The boot cpu is always logical cpu 0 */
- int reboot_cpu_id = 0;
-
- /* See if there has been given a command line override */
- if ((reboot_cpu != -1) && (reboot_cpu < nr_cpu_ids) &&
- cpu_online(reboot_cpu))
- reboot_cpu_id = reboot_cpu;
-
- /* Make certain the cpu I'm about to reboot on is online */
- if (!cpu_online(reboot_cpu_id))
- reboot_cpu_id = smp_processor_id();
-
- /* Make certain I only run on the appropriate processor */
- set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
-
/*
- * O.K Now that I'm on the appropriate processor, stop all of the
- * others. Also disable the local irq to not receive the per-cpu
- * timer interrupt which may trigger scheduler's load balance.
+ * Stop all of the others. Also disable the local irq to
+ * not receive the per-cpu timer interrupt which may trigger
+ * scheduler's load balance.
*/
local_irq_disable();
stop_other_cpus();
static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
{
pud_t *pud;
- unsigned long addr;
int i;
if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
pud = pud_offset(pgd, 0);
- for (addr = i = 0; i < PREALLOCATED_PMDS;
- i++, pud++, addr += PUD_SIZE) {
+ for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) {
pmd_t *pmd = pmds[i];
if (i >= KERNEL_PGD_BOUNDARY)
of machines called RISCiX. If you say 'Y' here, Linux will be able
to read disks partitioned under RISCiX.
+config AIX_PARTITION
+ bool "AIX basic partition table support" if PARTITION_ADVANCED
+ help
+ Say Y here if you would like to be able to read the hard disk
+ partition table format used by IBM or Motorola PowerPC machines
+ running AIX. AIX actually uses a Logical Volume Manager, where
+ "logical volumes" can be spread across one or multiple disks,
+ but this driver works only for the simple case of partitions which
+ are contiguous.
+ Otherwise, say N.
+
config OSF_PARTITION
bool "Alpha OSF partition support" if PARTITION_ADVANCED
default y if ALPHA
obj-$(CONFIG_ACORN_PARTITION) += acorn.o
obj-$(CONFIG_AMIGA_PARTITION) += amiga.o
obj-$(CONFIG_ATARI_PARTITION) += atari.o
+obj-$(CONFIG_AIX_PARTITION) += aix.o
obj-$(CONFIG_MAC_PARTITION) += mac.o
obj-$(CONFIG_LDM_PARTITION) += ldm.o
obj-$(CONFIG_MSDOS_PARTITION) += msdos.o
--- /dev/null
+/*
+ * fs/partitions/aix.c
+ *
+ * Copyright (C) 2012-2013 Philippe De Muyter <phdm@macqel.be>
+ */
+
+#include "check.h"
+#include "aix.h"
+
+struct lvm_rec {
+ char lvm_id[4]; /* "_LVM" */
+ char reserved4[16];
+ __be32 lvmarea_len;
+ __be32 vgda_len;
+ __be32 vgda_psn[2];
+ char reserved36[10];
+ __be16 pp_size; /* log2(pp_size) */
+ char reserved46[12];
+ __be16 version;
+ };
+
+struct vgda {
+ __be32 secs;
+ __be32 usec;
+ char reserved8[16];
+ __be16 numlvs;
+ __be16 maxlvs;
+ __be16 pp_size;
+ __be16 numpvs;
+ __be16 total_vgdas;
+ __be16 vgda_size;
+ };
+
+struct lvd {
+ __be16 lv_ix;
+ __be16 res2;
+ __be16 res4;
+ __be16 maxsize;
+ __be16 lv_state;
+ __be16 mirror;
+ __be16 mirror_policy;
+ __be16 num_lps;
+ __be16 res10[8];
+ };
+
+struct lvname {
+ char name[64];
+ };
+
+struct ppe {
+ __be16 lv_ix;
+ unsigned short res2;
+ unsigned short res4;
+ __be16 lp_ix;
+ unsigned short res8[12];
+ };
+
+struct pvd {
+ char reserved0[16];
+ __be16 pp_count;
+ char reserved18[2];
+ __be32 psn_part1;
+ char reserved24[8];
+ struct ppe ppe[1016];
+ };
+
+#define LVM_MAXLVS 256
+
+/**
+ * last_lba(): return number of last logical block of device
+ * @bdev: block device
+ *
+ * Description: Returns last LBA value on success, 0 on error.
+ * This is stored (by sd and ide-geometry) in
+ * the part[0] entry for this disk, and is the number of
+ * physical sectors available on the disk.
+ */
+static u64 last_lba(struct block_device *bdev)
+{
+ if (!bdev || !bdev->bd_inode)
+ return 0;
+ return (bdev->bd_inode->i_size >> 9) - 1ULL;
+}
+
+/**
+ * read_lba(): Read bytes from disk, starting at given LBA
+ * @state
+ * @lba
+ * @buffer
+ * @count
+ *
+ * Description: Reads @count bytes from @state->bdev into @buffer.
+ * Returns number of bytes read on success, 0 on error.
+ */
+static size_t read_lba(struct parsed_partitions *state, u64 lba, u8 *buffer,
+ size_t count)
+{
+ size_t totalreadcount = 0;
+
+ if (!buffer || lba + count / 512 > last_lba(state->bdev))
+ return 0;
+
+ while (count) {
+ int copied = 512;
+ Sector sect;
+ unsigned char *data = read_part_sector(state, lba++, §);
+ if (!data)
+ break;
+ if (copied > count)
+ copied = count;
+ memcpy(buffer, data, copied);
+ put_dev_sector(sect);
+ buffer += copied;
+ totalreadcount += copied;
+ count -= copied;
+ }
+ return totalreadcount;
+}
+
+/**
+ * alloc_pvd(): reads physical volume descriptor
+ * @state
+ * @lba
+ *
+ * Description: Returns pvd on success, NULL on error.
+ * Allocates space for pvd and fill it with disk blocks at @lba
+ * Notes: remember to free pvd when you're done!
+ */
+static struct pvd *alloc_pvd(struct parsed_partitions *state, u32 lba)
+{
+ size_t count = sizeof(struct pvd);
+ struct pvd *p;
+
+ p = kmalloc(count, GFP_KERNEL);
+ if (!p)
+ return NULL;
+
+ if (read_lba(state, lba, (u8 *) p, count) < count) {
+ kfree(p);
+ return NULL;
+ }
+ return p;
+}
+
+/**
+ * alloc_lvn(): reads logical volume names
+ * @state
+ * @lba
+ *
+ * Description: Returns lvn on success, NULL on error.
+ * Allocates space for lvn and fill it with disk blocks at @lba
+ * Notes: remember to free lvn when you're done!
+ */
+static struct lvname *alloc_lvn(struct parsed_partitions *state, u32 lba)
+{
+ size_t count = sizeof(struct lvname) * LVM_MAXLVS;
+ struct lvname *p;
+
+ p = kmalloc(count, GFP_KERNEL);
+ if (!p)
+ return NULL;
+
+ if (read_lba(state, lba, (u8 *) p, count) < count) {
+ kfree(p);
+ return NULL;
+ }
+ return p;
+}
+
+int aix_partition(struct parsed_partitions *state)
+{
+ int ret = 0;
+ Sector sect;
+ unsigned char *d;
+ u32 pp_bytes_size;
+ u32 pp_blocks_size = 0;
+ u32 vgda_sector = 0;
+ u32 vgda_len = 0;
+ int numlvs = 0;
+ struct pvd *pvd;
+ struct lv_info {
+ unsigned short pps_per_lv;
+ unsigned short pps_found;
+ unsigned char lv_is_contiguous;
+ } *lvip;
+ struct lvname *n = NULL;
+
+ d = read_part_sector(state, 7, §);
+ if (d) {
+ struct lvm_rec *p = (struct lvm_rec *)d;
+ u16 lvm_version = be16_to_cpu(p->version);
+ char tmp[64];
+
+ if (lvm_version == 1) {
+ int pp_size_log2 = be16_to_cpu(p->pp_size);
+
+ pp_bytes_size = 1 << pp_size_log2;
+ pp_blocks_size = pp_bytes_size / 512;
+ snprintf(tmp, sizeof(tmp),
+ " AIX LVM header version %u found\n",
+ lvm_version);
+ vgda_len = be32_to_cpu(p->vgda_len);
+ vgda_sector = be32_to_cpu(p->vgda_psn[0]);
+ } else {
+ snprintf(tmp, sizeof(tmp),
+ " unsupported AIX LVM version %d found\n",
+ lvm_version);
+ }
+ strlcat(state->pp_buf, tmp, PAGE_SIZE);
+ put_dev_sector(sect);
+ }
+ if (vgda_sector && (d = read_part_sector(state, vgda_sector, §))) {
+ struct vgda *p = (struct vgda *)d;
+
+ numlvs = be16_to_cpu(p->numlvs);
+ put_dev_sector(sect);
+ }
+ lvip = kzalloc(sizeof(struct lv_info) * state->limit, GFP_KERNEL);
+ if (!lvip)
+ return 0;
+ if (numlvs && (d = read_part_sector(state, vgda_sector + 1, §))) {
+ struct lvd *p = (struct lvd *)d;
+ int i;
+
+ n = alloc_lvn(state, vgda_sector + vgda_len - 33);
+ if (n) {
+ int foundlvs = 0;
+
+ for (i = 0; foundlvs < numlvs && i < state->limit; i += 1) {
+ lvip[i].pps_per_lv = be16_to_cpu(p[i].num_lps);
+ if (lvip[i].pps_per_lv)
+ foundlvs += 1;
+ }
+ }
+ put_dev_sector(sect);
+ }
+ pvd = alloc_pvd(state, vgda_sector + 17);
+ if (pvd) {
+ int numpps = be16_to_cpu(pvd->pp_count);
+ int psn_part1 = be32_to_cpu(pvd->psn_part1);
+ int i;
+ int cur_lv_ix = -1;
+ int next_lp_ix = 1;
+ int lp_ix;
+
+ for (i = 0; i < numpps; i += 1) {
+ struct ppe *p = pvd->ppe + i;
+ unsigned int lv_ix;
+
+ lp_ix = be16_to_cpu(p->lp_ix);
+ if (!lp_ix) {
+ next_lp_ix = 1;
+ continue;
+ }
+ lv_ix = be16_to_cpu(p->lv_ix) - 1;
+ if (lv_ix > state->limit) {
+ cur_lv_ix = -1;
+ continue;
+ }
+ lvip[lv_ix].pps_found += 1;
+ if (lp_ix == 1) {
+ cur_lv_ix = lv_ix;
+ next_lp_ix = 1;
+ } else if (lv_ix != cur_lv_ix || lp_ix != next_lp_ix) {
+ next_lp_ix = 1;
+ continue;
+ }
+ if (lp_ix == lvip[lv_ix].pps_per_lv) {
+ char tmp[70];
+
+ put_partition(state, lv_ix + 1,
+ (i + 1 - lp_ix) * pp_blocks_size + psn_part1,
+ lvip[lv_ix].pps_per_lv * pp_blocks_size);
+ snprintf(tmp, sizeof(tmp), " <%s>\n",
+ n[lv_ix].name);
+ strlcat(state->pp_buf, tmp, PAGE_SIZE);
+ lvip[lv_ix].lv_is_contiguous = 1;
+ ret = 1;
+ next_lp_ix = 1;
+ } else
+ next_lp_ix += 1;
+ }
+ for (i = 0; i < state->limit; i += 1)
+ if (lvip[i].pps_found && !lvip[i].lv_is_contiguous)
+ pr_warn("partition %s (%u pp's found) is "
+ "not contiguous\n",
+ n[i].name, lvip[i].pps_found);
+ kfree(pvd);
+ }
+ kfree(n);
+ kfree(lvip);
+ return ret;
+}
--- /dev/null
+extern int aix_partition(struct parsed_partitions *state);
#include "check.h"
#include "msdos.h"
#include "efi.h"
+#include "aix.h"
/*
* Many architectures don't like unaligned accesses, while
if (d[0] == '_' && d[1] == 'L' && d[2] == 'V' && d[3] == 'M')
ret = 1;
put_dev_sector(sect);
- };
+ }
return ret;
}
return;
if (!msdos_magic_present(data + 510))
- goto done;
+ goto done;
p = (struct partition *) (data + 0x1be);
* and OS/2 seems to use all four entries.
*/
- /*
+ /*
* First process the data partition(s)
*/
for (i=0; i<4; i++, p++) {
}
#if defined(CONFIG_BSD_DISKLABEL)
-/*
+/*
* Create devices for BSD partitions listed in a disklabel, under a
* dos-like partition. See parse_extended() for more information.
*/
if (state->next == state->limit)
break;
- if (p->p_fstype == BSD_FS_UNUSED)
+ if (p->p_fstype == BSD_FS_UNUSED)
continue;
bsd_start = le32_to_cpu(p->p_offset);
bsd_size = le32_to_cpu(p->p_size);
{NEW_SOLARIS_X86_PARTITION, parse_solaris_x86},
{0, NULL},
};
-
+
int msdos_partition(struct parsed_partitions *state)
{
sector_t sector_size = bdev_logical_block_size(state->bdev) / 512;
*/
if (aix_magic_present(state, data)) {
put_dev_sector(sect);
+#ifdef CONFIG_AIX_PARTITION
+ return aix_partition(state);
+#else
strlcat(state->pp_buf, " [AIX]", PAGE_SIZE);
return 0;
+#endif
}
if (!msdos_magic_present(data + 510)) {
help
This is the 842 algorithm.
+config CRYPTO_LZ4
+ tristate "LZ4 compression algorithm"
+ select CRYPTO_ALGAPI
+ select LZ4_COMPRESS
+ select LZ4_DECOMPRESS
+ help
+ This is the LZ4 algorithm.
+
+config CRYPTO_LZ4HC
+ tristate "LZ4HC compression algorithm"
+ select CRYPTO_ALGAPI
+ select LZ4HC_COMPRESS
+ select LZ4_DECOMPRESS
+ help
+ This is the LZ4 high compression mode algorithm.
+
comment "Random Number Generation"
config CRYPTO_ANSI_CPRNG
obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif.o
obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
obj-$(CONFIG_CRYPTO_LZO) += lzo.o
+obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
+obj-$(CONFIG_CRYPTO_LZ4HC) += lz4hc.o
obj-$(CONFIG_CRYPTO_842) += 842.o
obj-$(CONFIG_CRYPTO_RNG2) += rng.o
obj-$(CONFIG_CRYPTO_RNG2) += krng.o
--- /dev/null
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2013 Chanho Min <chanho.min@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 51
+ * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/vmalloc.h>
+#include <linux/lz4.h>
+
+struct lz4_ctx {
+ void *lz4_comp_mem;
+};
+
+static int lz4_init(struct crypto_tfm *tfm)
+{
+ struct lz4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->lz4_comp_mem = vmalloc(LZ4_MEM_COMPRESS);
+ if (!ctx->lz4_comp_mem)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void lz4_exit(struct crypto_tfm *tfm)
+{
+ struct lz4_ctx *ctx = crypto_tfm_ctx(tfm);
+ vfree(ctx->lz4_comp_mem);
+}
+
+static int lz4_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ struct lz4_ctx *ctx = crypto_tfm_ctx(tfm);
+ size_t tmp_len = *dlen;
+ int err;
+
+ err = lz4_compress(src, slen, dst, &tmp_len, ctx->lz4_comp_mem);
+
+ if (err < 0)
+ return -EINVAL;
+
+ *dlen = tmp_len;
+ return 0;
+}
+
+static int lz4_decompress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ int err;
+ size_t tmp_len = *dlen;
+ size_t __slen = slen;
+
+ err = lz4_decompress(src, &__slen, dst, tmp_len);
+ if (err < 0)
+ return -EINVAL;
+
+ *dlen = tmp_len;
+ return err;
+}
+
+static struct crypto_alg alg_lz4 = {
+ .cra_name = "lz4",
+ .cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
+ .cra_ctxsize = sizeof(struct lz4_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(alg_lz4.cra_list),
+ .cra_init = lz4_init,
+ .cra_exit = lz4_exit,
+ .cra_u = { .compress = {
+ .coa_compress = lz4_compress_crypto,
+ .coa_decompress = lz4_decompress_crypto } }
+};
+
+static int __init lz4_mod_init(void)
+{
+ return crypto_register_alg(&alg_lz4);
+}
+
+static void __exit lz4_mod_fini(void)
+{
+ crypto_unregister_alg(&alg_lz4);
+}
+
+module_init(lz4_mod_init);
+module_exit(lz4_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 Compression Algorithm");
--- /dev/null
+/*
+ * Cryptographic API.
+ *
+ * Copyright (c) 2013 Chanho Min <chanho.min@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 51
+ * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ *
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/vmalloc.h>
+#include <linux/lz4.h>
+
+struct lz4hc_ctx {
+ void *lz4hc_comp_mem;
+};
+
+static int lz4hc_init(struct crypto_tfm *tfm)
+{
+ struct lz4hc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ ctx->lz4hc_comp_mem = vmalloc(LZ4HC_MEM_COMPRESS);
+ if (!ctx->lz4hc_comp_mem)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void lz4hc_exit(struct crypto_tfm *tfm)
+{
+ struct lz4hc_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ vfree(ctx->lz4hc_comp_mem);
+}
+
+static int lz4hc_compress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ struct lz4hc_ctx *ctx = crypto_tfm_ctx(tfm);
+ size_t tmp_len = *dlen;
+ int err;
+
+ err = lz4hc_compress(src, slen, dst, &tmp_len, ctx->lz4hc_comp_mem);
+
+ if (err < 0)
+ return -EINVAL;
+
+ *dlen = tmp_len;
+ return 0;
+}
+
+static int lz4hc_decompress_crypto(struct crypto_tfm *tfm, const u8 *src,
+ unsigned int slen, u8 *dst, unsigned int *dlen)
+{
+ int err;
+ size_t tmp_len = *dlen;
+ size_t __slen = slen;
+
+ err = lz4_decompress(src, &__slen, dst, tmp_len);
+ if (err < 0)
+ return -EINVAL;
+
+ *dlen = tmp_len;
+ return err;
+}
+
+static struct crypto_alg alg_lz4hc = {
+ .cra_name = "lz4hc",
+ .cra_flags = CRYPTO_ALG_TYPE_COMPRESS,
+ .cra_ctxsize = sizeof(struct lz4hc_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(alg_lz4hc.cra_list),
+ .cra_init = lz4hc_init,
+ .cra_exit = lz4hc_exit,
+ .cra_u = { .compress = {
+ .coa_compress = lz4hc_compress_crypto,
+ .coa_decompress = lz4hc_decompress_crypto } }
+};
+
+static int __init lz4hc_mod_init(void)
+{
+ return crypto_register_alg(&alg_lz4hc);
+}
+
+static void __exit lz4hc_mod_fini(void)
+{
+ crypto_unregister_alg(&alg_lz4hc);
+}
+
+module_init(lz4hc_mod_init);
+module_exit(lz4hc_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4HC Compression Algorithm");
PRINTK_2(TRACE_TP3780I,
"tp3780i::tp3780I_QueryAbilities entry pBDData %p\n", pBDData);
+ memset(pAbilities, 0, sizeof(*pAbilities));
/* fill out standard constant fields */
pAbilities->instr_per_sec = pBDData->rDspSettings.uIps;
pAbilities->data_size = pBDData->rDspSettings.uDStoreSize;
return sg_nents;
}
-/**
- * sg_copy_end_to_buffer - Copy end data from SG list to a linear buffer
- * @sgl: The SG list
- * @nents: Number of SG entries
- * @buf: Where to copy to
- * @buflen: The number of bytes to copy
- * @skip: The number of bytes to skip before copying.
- * Note: skip + buflen should equal SG total size.
- *
- * Returns the number of copied bytes.
- *
- **/
-static size_t sg_copy_end_to_buffer(struct scatterlist *sgl, unsigned int nents,
- void *buf, size_t buflen, unsigned int skip)
-{
- unsigned int offset = 0;
- unsigned int boffset = 0;
- struct sg_mapping_iter miter;
- unsigned long flags;
- unsigned int sg_flags = SG_MITER_ATOMIC;
- size_t total_buffer = buflen + skip;
-
- sg_flags |= SG_MITER_FROM_SG;
-
- sg_miter_start(&miter, sgl, nents, sg_flags);
-
- local_irq_save(flags);
-
- while (sg_miter_next(&miter) && offset < total_buffer) {
- unsigned int len;
- unsigned int ignore;
-
- if ((offset + miter.length) > skip) {
- if (offset < skip) {
- /* Copy part of this segment */
- ignore = skip - offset;
- len = miter.length - ignore;
- if (boffset + len > buflen)
- len = buflen - boffset;
- memcpy(buf + boffset, miter.addr + ignore, len);
- } else {
- /* Copy all of this segment (up to buflen) */
- len = miter.length;
- if (boffset + len > buflen)
- len = buflen - boffset;
- memcpy(buf + boffset, miter.addr, len);
- }
- boffset += len;
- }
- offset += miter.length;
- }
-
- sg_miter_stop(&miter);
-
- local_irq_restore(flags);
- return boffset;
-}
-
/*
* allocate and map the extended descriptor
*/
if (to_hash_later) {
int nents = sg_count(areq->src, nbytes, &chained);
- sg_copy_end_to_buffer(areq->src, nents,
+ sg_pcopy_to_buffer(areq->src, nents,
req_ctx->bufnext,
to_hash_later,
nbytes - to_hash_later);
struct page *xor_srcs[IOP_ADMA_NUM_SRC_TEST];
struct page *zero_sum_srcs[IOP_ADMA_NUM_SRC_TEST + 1];
dma_addr_t dma_srcs[IOP_ADMA_NUM_SRC_TEST + 1];
- dma_addr_t dma_addr, dest_dma;
+ dma_addr_t dest_dma;
struct dma_async_tx_descriptor *tx;
struct dma_chan *dma_chan;
dma_cookie_t cookie;
goto err_free_iop_chan;
}
- dev_info(&pdev->dev, "Intel(R) IOP: ( %s%s%s%s%s%s%s)\n",
+ dev_info(&pdev->dev, "Intel(R) IOP: ( %s%s%s%s%s%s)\n",
dma_has_cap(DMA_PQ, dma_dev->cap_mask) ? "pq " : "",
dma_has_cap(DMA_PQ_VAL, dma_dev->cap_mask) ? "pq_val " : "",
dma_has_cap(DMA_XOR, dma_dev->cap_mask) ? "xor " : "",
{
struct msm_iommu_ctx_dev *c = pdev->dev.platform_data;
struct msm_iommu_drvdata *drvdata;
- struct msm_iommu_ctx_drvdata *ctx_drvdata = NULL;
+ struct msm_iommu_ctx_drvdata *ctx_drvdata;
int i, ret;
- if (!c || !pdev->dev.parent) {
- ret = -EINVAL;
- goto fail;
- }
- drvdata = dev_get_drvdata(pdev->dev.parent);
+ if (!c || !pdev->dev.parent)
+ return -EINVAL;
- if (!drvdata) {
- ret = -ENODEV;
- goto fail;
- }
+ drvdata = dev_get_drvdata(pdev->dev.parent);
+ if (!drvdata)
+ return -ENODEV;
ctx_drvdata = kzalloc(sizeof(*ctx_drvdata), GFP_KERNEL);
- if (!ctx_drvdata) {
- ret = -ENOMEM;
- goto fail;
- }
+ if (!ctx_drvdata)
+ return -ENOMEM;
+
ctx_drvdata->num = c->num;
ctx_drvdata->pdev = pdev;
ret = platform_driver_register(&msm_iommu_ctx_driver);
if (ret != 0) {
+ platform_driver_unregister(&msm_iommu_driver);
pr_err("Failed to register IOMMU context driver\n");
goto error;
}
#include <linux/platform_device.h>
#include <linux/of_platform.h>
#include <linux/module.h>
+#include <linux/reboot.h>
#include <asm/system_misc.h>
static void restart_poweroff_do_poweroff(void)
{
- arm_pm_restart('h', NULL);
+ arm_pm_restart(REBOOT_HARD, NULL);
}
static int restart_poweroff_probe(struct platform_device *pdev)
static struct device *vexpress_restart_device;
-static void vexpress_restart(char str, const char *cmd)
+static void vexpress_restart(enum reboot_mode reboot_mode, const char *cmd)
{
vexpress_reset_do(vexpress_restart_device, "restart");
}
platform_set_drvdata(pdev, rtc_data);
- stmp_reset_block(rtc_data->io);
+ err = stmp_reset_block(rtc_data->io);
+ if (err) {
+ dev_err(&pdev->dev, "stmp_reset_block failed: %d\n", err);
+ return err;
+ }
+
writel(STMP3XXX_RTC_PERSISTENT0_ALARM_EN |
STMP3XXX_RTC_PERSISTENT0_ALARM_WAKE_EN |
STMP3XXX_RTC_PERSISTENT0_ALARM_WAKE,
act_len = sg_copy_from_buffer(sdb->table.sgl, sdb->table.nents,
arr, arr_len);
- if (sdb->resid)
- sdb->resid -= act_len;
- else
- sdb->resid = scsi_bufflen(scp) - act_len;
+ sdb->resid = scsi_bufflen(scp) - act_len;
return 0;
}
return 0;
}
+/* Returns number of bytes copied or -1 if error. */
static int do_device_access(struct scsi_cmnd *scmd,
struct sdebug_dev_info *devi,
unsigned long long lba, unsigned int num, int write)
{
int ret;
unsigned long long block, rest = 0;
- int (*func)(struct scsi_cmnd *, unsigned char *, int);
+ struct scsi_data_buffer *sdb;
+ enum dma_data_direction dir;
+ size_t (*func)(struct scatterlist *, unsigned int, void *, size_t,
+ off_t);
+
+ if (write) {
+ sdb = scsi_out(scmd);
+ dir = DMA_TO_DEVICE;
+ func = sg_pcopy_to_buffer;
+ } else {
+ sdb = scsi_in(scmd);
+ dir = DMA_FROM_DEVICE;
+ func = sg_pcopy_from_buffer;
+ }
- func = write ? fetch_to_dev_buffer : fill_from_dev_buffer;
+ if (!sdb->length)
+ return 0;
+ if (!(scsi_bidi_cmnd(scmd) || scmd->sc_data_direction == dir))
+ return -1;
block = do_div(lba, sdebug_store_sectors);
if (block + num > sdebug_store_sectors)
rest = block + num - sdebug_store_sectors;
- ret = func(scmd, fake_storep + (block * scsi_debug_sector_size),
- (num - rest) * scsi_debug_sector_size);
- if (!ret && rest)
- ret = func(scmd, fake_storep, rest * scsi_debug_sector_size);
+ ret = func(sdb->table.sgl, sdb->table.nents,
+ fake_storep + (block * scsi_debug_sector_size),
+ (num - rest) * scsi_debug_sector_size, 0);
+ if (ret != (num - rest) * scsi_debug_sector_size)
+ return ret;
+
+ if (rest) {
+ ret += func(sdb->table.sgl, sdb->table.nents,
+ fake_storep, rest * scsi_debug_sector_size,
+ (num - rest) * scsi_debug_sector_size);
+ }
return ret;
}
read_lock_irqsave(&atomic_rw, iflags);
ret = do_device_access(SCpnt, devip, lba, num, 0);
read_unlock_irqrestore(&atomic_rw, iflags);
- return ret;
+ if (ret == -1)
+ return DID_ERROR << 16;
+
+ scsi_in(SCpnt)->resid = scsi_bufflen(SCpnt) - ret;
+
+ return 0;
}
void dump_sector(unsigned char *buf, int len)
const void *dir_ops; /* Opaque; default directory operations */
int dir_per_block; /* dir entries per block */
int dir_per_block_bits; /* log2(dir_per_block) */
+ unsigned int vol_id; /*volume ID*/
int fatent_shift;
struct fatent_operations *fatent_ops;
return err;
}
+static int fat_ioctl_get_volume_id(struct inode *inode, u32 __user *user_attr)
+{
+ struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+ return put_user(sbi->vol_id, user_attr);
+}
+
long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
return fat_ioctl_get_attributes(inode, user_attr);
case FAT_IOCTL_SET_ATTRIBUTES:
return fat_ioctl_set_attributes(filp, user_attr);
+ case FAT_IOCTL_GET_VOLUME_ID:
+ return fat_ioctl_get_volume_id(inode, user_attr);
default:
return -ENOTTY; /* Inappropriate ioctl for device */
}
brelse(fsinfo_bh);
}
+ /* interpret volume ID as a little endian 32 bit integer */
+ if (sbi->fat_bits == 32)
+ sbi->vol_id = (((u32)b->fat32.vol_id[0]) |
+ ((u32)b->fat32.vol_id[1] << 8) |
+ ((u32)b->fat32.vol_id[2] << 16) |
+ ((u32)b->fat32.vol_id[3] << 24));
+ else /* fat 16 or 12 */
+ sbi->vol_id = (((u32)b->fat16.vol_id[0]) |
+ ((u32)b->fat16.vol_id[1] << 8) |
+ ((u32)b->fat16.vol_id[2] << 16) |
+ ((u32)b->fat16.vol_id[3] << 24));
+
sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;
/*
* Retrieve work items and do the writeback they describe
*/
-long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+static long wb_do_writeback(struct bdi_writeback *wb)
{
struct backing_dev_info *bdi = wb->bdi;
struct wb_writeback_work *work;
set_bit(BDI_writeback_running, &wb->bdi->state);
while ((work = get_next_work_item(bdi)) != NULL) {
- /*
- * Override sync mode, in case we must wait for completion
- * because this thread is exiting now.
- */
- if (force_wait)
- work->sync_mode = WB_SYNC_ALL;
trace_writeback_exec(bdi, work);
* rescuer as work_list needs to be drained.
*/
do {
- pages_written = wb_do_writeback(wb, 0);
+ pages_written = wb_do_writeback(wb);
trace_writeback_pages_written(pages_written);
} while (!list_empty(&bdi->work_list));
} else {
static struct kmem_cache *dnotify_struct_cache __read_mostly;
static struct kmem_cache *dnotify_mark_cache __read_mostly;
static struct fsnotify_group *dnotify_group __read_mostly;
-static DEFINE_MUTEX(dnotify_mark_mutex);
/*
* dnotify will attach one of these to each inode (i_fsnotify_marks) which
return;
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
- mutex_lock(&dnotify_mark_mutex);
+ mutex_lock(&dnotify_group->mark_mutex);
spin_lock(&fsn_mark->lock);
prev = &dn_mark->dn;
spin_unlock(&fsn_mark->lock);
- /* nothing else could have found us thanks to the dnotify_mark_mutex */
+ /* nothing else could have found us thanks to the dnotify_groups
+ mark_mutex */
if (dn_mark->dn == NULL)
- fsnotify_destroy_mark(fsn_mark, dnotify_group);
+ fsnotify_destroy_mark_locked(fsn_mark, dnotify_group);
- mutex_unlock(&dnotify_mark_mutex);
+ mutex_unlock(&dnotify_group->mark_mutex);
fsnotify_put_mark(fsn_mark);
}
new_dn_mark->dn = NULL;
/* this is needed to prevent the fcntl/close race described below */
- mutex_lock(&dnotify_mark_mutex);
+ mutex_lock(&dnotify_group->mark_mutex);
/* add the new_fsn_mark or find an old one. */
fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode);
dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
spin_lock(&fsn_mark->lock);
} else {
- fsnotify_add_mark(new_fsn_mark, dnotify_group, inode, NULL, 0);
+ fsnotify_add_mark_locked(new_fsn_mark, dnotify_group, inode,
+ NULL, 0);
spin_lock(&new_fsn_mark->lock);
fsn_mark = new_fsn_mark;
dn_mark = new_dn_mark;
/* if (f != filp) means that we lost a race and another task/thread
* actually closed the fd we are still playing with before we grabbed
- * the dnotify_mark_mutex and fsn_mark->lock. Since closing the fd is the
- * only time we clean up the marks we need to get our mark off
- * the list. */
+ * the dnotify_groups mark_mutex and fsn_mark->lock. Since closing the
+ * fd is the only time we clean up the marks we need to get our mark
+ * off the list. */
if (f != filp) {
/* if we added ourselves, shoot ourselves, it's possible that
* the flush actually did shoot this fsn_mark. That's fine too
spin_unlock(&fsn_mark->lock);
if (destroy)
- fsnotify_destroy_mark(fsn_mark, dnotify_group);
+ fsnotify_destroy_mark_locked(fsn_mark, dnotify_group);
- mutex_unlock(&dnotify_mark_mutex);
+ mutex_unlock(&dnotify_group->mark_mutex);
fsnotify_put_mark(fsn_mark);
out_err:
if (new_fsn_mark)
metadata->event_len = FAN_EVENT_METADATA_LEN;
metadata->metadata_len = FAN_EVENT_METADATA_LEN;
metadata->vers = FANOTIFY_METADATA_VERSION;
+ metadata->reserved = 0;
metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
metadata->pid = pid_vnr(event->tgid);
if (unlikely(event->mask & FAN_Q_OVERFLOW))
__u32 removed;
int destroy_mark;
+ mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
- if (!fsn_mark)
+ if (!fsn_mark) {
+ mutex_unlock(&group->mark_mutex);
return -ENOENT;
+ }
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (destroy_mark)
- fsnotify_destroy_mark(fsn_mark, group);
+ fsnotify_destroy_mark_locked(fsn_mark, group);
+ mutex_unlock(&group->mark_mutex);
fsnotify_put_mark(fsn_mark);
if (removed & real_mount(mnt)->mnt_fsnotify_mask)
__u32 removed;
int destroy_mark;
+ mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_inode_mark(group, inode);
- if (!fsn_mark)
+ if (!fsn_mark) {
+ mutex_unlock(&group->mark_mutex);
return -ENOENT;
+ }
removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
&destroy_mark);
if (destroy_mark)
- fsnotify_destroy_mark(fsn_mark, group);
+ fsnotify_destroy_mark_locked(fsn_mark, group);
+ mutex_unlock(&group->mark_mutex);
+
/* matches the fsnotify_find_inode_mark() */
fsnotify_put_mark(fsn_mark);
if (removed & inode->i_fsnotify_mask)
return mask & ~oldmask;
}
+static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
+ struct inode *inode,
+ struct vfsmount *mnt)
+{
+ struct fsnotify_mark *mark;
+ int ret;
+
+ if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
+ return ERR_PTR(-ENOSPC);
+
+ mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
+ if (!mark)
+ return ERR_PTR(-ENOMEM);
+
+ fsnotify_init_mark(mark, fanotify_free_mark);
+ ret = fsnotify_add_mark_locked(mark, group, inode, mnt, 0);
+ if (ret) {
+ fsnotify_put_mark(mark);
+ return ERR_PTR(ret);
+ }
+
+ return mark;
+}
+
+
static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
struct vfsmount *mnt, __u32 mask,
unsigned int flags)
{
struct fsnotify_mark *fsn_mark;
__u32 added;
- int ret = 0;
+ mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
if (!fsn_mark) {
- if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
- return -ENOSPC;
-
- fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
- if (!fsn_mark)
- return -ENOMEM;
-
- fsnotify_init_mark(fsn_mark, fanotify_free_mark);
- ret = fsnotify_add_mark(fsn_mark, group, NULL, mnt, 0);
- if (ret)
- goto err;
+ fsn_mark = fanotify_add_new_mark(group, NULL, mnt);
+ if (IS_ERR(fsn_mark)) {
+ mutex_unlock(&group->mark_mutex);
+ return PTR_ERR(fsn_mark);
+ }
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+ mutex_unlock(&group->mark_mutex);
if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
fsnotify_recalc_vfsmount_mask(mnt);
-err:
+
fsnotify_put_mark(fsn_mark);
- return ret;
+ return 0;
}
static int fanotify_add_inode_mark(struct fsnotify_group *group,
{
struct fsnotify_mark *fsn_mark;
__u32 added;
- int ret = 0;
pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
(atomic_read(&inode->i_writecount) > 0))
return 0;
+ mutex_lock(&group->mark_mutex);
fsn_mark = fsnotify_find_inode_mark(group, inode);
if (!fsn_mark) {
- if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
- return -ENOSPC;
-
- fsn_mark = kmem_cache_alloc(fanotify_mark_cache, GFP_KERNEL);
- if (!fsn_mark)
- return -ENOMEM;
-
- fsnotify_init_mark(fsn_mark, fanotify_free_mark);
- ret = fsnotify_add_mark(fsn_mark, group, inode, NULL, 0);
- if (ret)
- goto err;
+ fsn_mark = fanotify_add_new_mark(group, inode, NULL);
+ if (IS_ERR(fsn_mark)) {
+ mutex_unlock(&group->mark_mutex);
+ return PTR_ERR(fsn_mark);
+ }
}
added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
+ mutex_unlock(&group->mark_mutex);
if (added & ~inode->i_fsnotify_mask)
fsnotify_recalc_inode_mask(inode);
-err:
+
fsnotify_put_mark(fsn_mark);
- return ret;
+ return 0;
}
/* fanotify syscalls */
goto out_err;
/* we are on the idr, now get on the inode */
- ret = fsnotify_add_mark(&tmp_i_mark->fsn_mark, group, inode, NULL, 0);
+ ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
+ NULL, 0);
if (ret) {
/* we failed to get on the inode, get off the idr */
inotify_remove_from_idr(group, tmp_i_mark);
{
int ret = 0;
-retry:
+ mutex_lock(&group->mark_mutex);
/* try to update and existing watch with the new arg */
ret = inotify_update_existing_watch(group, inode, arg);
/* no mark present, try to add a new one */
if (ret == -ENOENT)
ret = inotify_new_watch(group, inode, arg);
- /*
- * inotify_new_watch could race with another thread which did an
- * inotify_new_watch between the update_existing and the add watch
- * here, go back and try to update an existing mark again.
- */
- if (ret == -EEXIST)
- goto retry;
+ mutex_unlock(&group->mark_mutex);
return ret;
}
* fsnotify inode mark locking/lifetime/and refcnting
*
* REFCNT:
- * The mark->refcnt tells how many "things" in the kernel currently are
- * referencing this object. The object typically will live inside the kernel
- * with a refcnt of 2, one for each list it is on (i_list, g_list). Any task
- * which can find this object holding the appropriete locks, can take a reference
- * and the object itself is guaranteed to survive until the reference is dropped.
+ * The group->recnt and mark->refcnt tell how many "things" in the kernel
+ * currently are referencing the objects. Both kind of objects typically will
+ * live inside the kernel with a refcnt of 2, one for its creation and one for
+ * the reference a group and a mark hold to each other.
+ * If you are holding the appropriate locks, you can take a reference and the
+ * object itself is guaranteed to survive until the reference is dropped.
*
* LOCKING:
- * There are 3 spinlocks involved with fsnotify inode marks and they MUST
- * be taken in order as follows:
+ * There are 3 locks involved with fsnotify inode marks and they MUST be taken
+ * in order as follows:
*
+ * group->mark_mutex
* mark->lock
- * group->mark_lock
* inode->i_lock
*
- * mark->lock protects 2 things, mark->group and mark->inode. You must hold
- * that lock to dereference either of these things (they could be NULL even with
- * the lock)
- *
- * group->mark_lock protects the marks_list anchored inside a given group
- * and each mark is hooked via the g_list. It also sorta protects the
- * free_g_list, which when used is anchored by a private list on the stack of the
- * task which held the group->mark_lock.
+ * group->mark_mutex protects the marks_list anchored inside a given group and
+ * each mark is hooked via the g_list. It also protects the groups private
+ * data (i.e group limits).
+
+ * mark->lock protects the marks attributes like its masks and flags.
+ * Furthermore it protects the access to a reference of the group that the mark
+ * is assigned to as well as the access to a reference of the inode/vfsmount
+ * that is being watched by the mark.
*
* inode->i_lock protects the i_fsnotify_marks list anchored inside a
* given inode and each mark is hooked via the i_list. (and sorta the
* inode. We take i_lock and walk the i_fsnotify_marks safely. For each
* mark on the list we take a reference (so the mark can't disappear under us).
* We remove that mark form the inode's list of marks and we add this mark to a
- * private list anchored on the stack using i_free_list; At this point we no
- * longer fear anything finding the mark using the inode's list of marks.
- *
- * We can safely and locklessly run the private list on the stack of everything
- * we just unattached from the original inode. For each mark on the private list
- * we grab the mark-> and can thus dereference mark->group and mark->inode. If
- * we see the group and inode are not NULL we take those locks. Now holding all
- * 3 locks we can completely remove the mark from other tasks finding it in the
- * future. Remember, 10 things might already be referencing this mark, but they
- * better be holding a ref. We drop our reference we took before we unhooked it
- * from the inode. When the ref hits 0 we can free the mark.
- *
+ * private list anchored on the stack using i_free_list; we walk i_free_list
+ * and before we destroy the mark we make sure that we dont race with a
+ * concurrent destroy_group by getting a ref to the marks group and taking the
+ * groups mutex.
+
* Very similarly for freeing by group, except we use free_g_list.
*
* This has the very interesting property of being able to run concurrently with
extern struct filename *__audit_reusename(const __user char *uptr);
extern void __audit_getname(struct filename *name);
extern void audit_putname(struct filename *name);
+
+#define AUDIT_INODE_PARENT 1 /* dentry represents the parent */
+#define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */
extern void __audit_inode(struct filename *name, const struct dentry *dentry,
- unsigned int parent);
+ unsigned int flags);
extern void __audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
const unsigned char type);
if (unlikely(!audit_dummy_context()))
__audit_getname(name);
}
-static inline void audit_inode(struct filename *name, const struct dentry *dentry,
+static inline void audit_inode(struct filename *name,
+ const struct dentry *dentry,
unsigned int parent) {
+ if (unlikely(!audit_dummy_context())) {
+ unsigned int flags = 0;
+ if (parent)
+ flags |= AUDIT_INODE_PARENT;
+ __audit_inode(name, dentry, flags);
+ }
+}
+static inline void audit_inode_parent_hidden(struct filename *name,
+ const struct dentry *dentry)
+{
if (unlikely(!audit_dummy_context()))
- __audit_inode(name, dentry, parent);
+ __audit_inode(name, dentry,
+ AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN);
}
static inline void audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
{ }
static inline void __audit_inode(struct filename *name,
const struct dentry *dentry,
- unsigned int parent)
+ unsigned int flags)
{ }
static inline void __audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
const struct dentry *dentry,
unsigned int parent)
{ }
+static inline void audit_inode_parent_hidden(struct filename *name,
+ const struct dentry *dentry)
+{ }
static inline void audit_inode_child(const struct inode *parent,
const struct dentry *dentry,
const unsigned char type)
--- /dev/null
+#ifndef DECOMPRESS_UNLZ4_H
+#define DECOMPRESS_UNLZ4_H
+
+int unlz4(unsigned char *inbuf, int len,
+ int(*fill)(void*, unsigned int),
+ int(*flush)(void*, unsigned int),
+ unsigned char *output,
+ int *pos,
+ void(*error)(char *x));
+#endif
int (*get_xip_mem)(struct address_space *, pgoff_t, int,
void **, unsigned long *);
/*
- * migrate the contents of a page to the specified target. If sync
- * is false, it must not block.
+ * migrate the contents of a page to the specified target. If
+ * migrate_mode is MIGRATE_ASYNC, it must not block.
*/
int (*migratepage) (struct address_space *,
struct page *, struct page *, enum migrate_mode);
* 0x9 => DMA or NORMAL (MOVABLE+DMA)
* 0xa => MOVABLE (Movable is valid only if HIGHMEM is set too)
* 0xb => BAD (MOVABLE+HIGHMEM+DMA)
- * 0xc => DMA32 (MOVABLE+HIGHMEM+DMA32)
+ * 0xc => DMA32 (MOVABLE+DMA32)
* 0xd => BAD (MOVABLE+DMA32+DMA)
* 0xe => BAD (MOVABLE+DMA32+HIGHMEM)
* 0xf => BAD (MOVABLE+DMA32+HIGHMEM+DMA)
--- /dev/null
+#ifndef __LZ4_H__
+#define __LZ4_H__
+/*
+ * LZ4 Kernel Interface
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#define LZ4_MEM_COMPRESS (4096 * sizeof(unsigned char *))
+#define LZ4HC_MEM_COMPRESS (65538 * sizeof(unsigned char *))
+
+/*
+ * lz4_compressbound()
+ * Provides the maximum size that LZ4 may output in a "worst case" scenario
+ * (input data not compressible)
+ */
+static inline size_t lz4_compressbound(size_t isize)
+{
+ return isize + (isize / 255) + 16;
+}
+
+/*
+ * lz4_compress()
+ * src : source address of the original data
+ * src_len : size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len : is the output size, which is returned after compress done
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem);
+
+ /*
+ * lz4hc_compress()
+ * src : source address of the original data
+ * src_len : size of the original data
+ * dst : output buffer address of the compressed data
+ * This requires 'dst' of size LZ4_COMPRESSBOUND.
+ * dst_len : is the output size, which is returned after compress done
+ * workmem : address of the working memory.
+ * This requires 'workmem' of size LZ4HC_MEM_COMPRESS.
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer and workmem must be already allocated with
+ * the defined size.
+ */
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem);
+
+/*
+ * lz4_decompress()
+ * src : source address of the compressed data
+ * src_len : is the input size, whcih is returned after decompress done
+ * dest : output buffer address of the decompressed data
+ * actual_dest_len: is the size of uncompressed data, supposing it's known
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ * slightly faster than lz4_decompress_unknownoutputsize()
+ */
+int lz4_decompress(const char *src, size_t *src_len, char *dest,
+ size_t actual_dest_len);
+
+/*
+ * lz4_decompress_unknownoutputsize()
+ * src : source address of the compressed data
+ * src_len : is the input size, therefore the compressed size
+ * dest : output buffer address of the decompressed data
+ * dest_len: is the max size of the destination buffer, which is
+ * returned with actual size of decompressed data after
+ * decompress done
+ * return : Success if return 0
+ * Error if return (< 0)
+ * note : Destination buffer must be already allocated.
+ */
+int lz4_decompress_unknownoutputsize(const char *src, size_t src_len,
+ char *dest, size_t *dest_len);
+#endif
#define VM_STACK_FLAGS (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#endif
-#define VM_READHINTMASK (VM_SEQ_READ | VM_RAND_READ)
-#define VM_ClearReadHint(v) (v)->vm_flags &= ~VM_READHINTMASK
-#define VM_NormalReadHint(v) (!((v)->vm_flags & VM_READHINTMASK))
-#define VM_SequentialReadHint(v) ((v)->vm_flags & VM_SEQ_READ)
-#define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ)
-
/*
* Special vmas that are non-mergable, non-mlock()able.
* Note: mm/huge_memory.c VM_NO_THP depends on this definition.
#endif
}
-static inline int is_normal_idx(enum zone_type idx)
-{
- return (idx == ZONE_NORMAL);
-}
-
/**
* is_highmem - helper function to quickly check if a struct zone is a
* highmem zone or not. This is an attempt to keep references
#endif
}
-static inline int is_normal(struct zone *zone)
-{
- return zone == zone->zone_pgdat->node_zones + ZONE_NORMAL;
-}
-
-static inline int is_dma32(struct zone *zone)
-{
-#ifdef CONFIG_ZONE_DMA32
- return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
-#else
- return 0;
-#endif
-}
-
-static inline int is_dma(struct zone *zone)
-{
-#ifdef CONFIG_ZONE_DMA
- return zone == zone->zone_pgdat->node_zones + ZONE_DMA;
-#else
- return 0;
-#endif
-}
-
/* These two functions are used to setup the per zone pages min values */
struct ctl_table;
int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
{
INIT_LIST_HEAD(&child->ptrace_entry);
INIT_LIST_HEAD(&child->ptraced);
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- atomic_set(&child->ptrace_bp_refcnt, 1);
-#endif
child->jobctl = 0;
child->ptrace = 0;
child->parent = child->real_parent;
unsigned long args[6], unsigned int maxargs,
unsigned long *sp, unsigned long *pc);
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-extern int ptrace_get_breakpoints(struct task_struct *tsk);
-extern void ptrace_put_breakpoints(struct task_struct *tsk);
-#else
-static inline void ptrace_put_breakpoints(struct task_struct *tsk) { }
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
-
#endif
#define SYS_HALT 0x0002 /* Notify of system halt */
#define SYS_POWER_OFF 0x0003 /* Notify of system power off */
+enum reboot_mode {
+ REBOOT_COLD = 0,
+ REBOOT_WARM,
+ REBOOT_HARD,
+ REBOOT_SOFT,
+ REBOOT_GPIO,
+};
+extern enum reboot_mode reboot_mode;
+
+enum reboot_type {
+ BOOT_TRIPLE = 't',
+ BOOT_KBD = 'k',
+ BOOT_BIOS = 'b',
+ BOOT_ACPI = 'a',
+ BOOT_EFI = 'e',
+ BOOT_CF9 = 'p',
+ BOOT_CF9_COND = 'q',
+};
+extern enum reboot_type reboot_type;
+
+extern int reboot_default;
+extern int reboot_cpu;
+extern int reboot_force;
+
+
extern int register_reboot_notifier(struct notifier_block *);
extern int unregister_reboot_notifier(struct notifier_block *);
struct pt_regs;
extern void machine_crash_shutdown(struct pt_regs *);
-/*
+/*
* Architecture independent implemenations of sys_reboot commands.
*/
size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
void *buf, size_t buflen);
+size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
+ void *buf, size_t buflen, off_t skip);
+size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
+ void *buf, size_t buflen, off_t skip);
+
/*
* Maximum number of entries that will be allocated in one piece, if
* a list larger than this is required then chaining will be utilized.
} memcg_batch;
unsigned int memcg_kmem_skip_account;
#endif
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
- atomic_t ptrace_bp_refcnt;
-#endif
#ifdef CONFIG_UPROBES
struct uprobe_task *utask;
#endif
struct sem_array {
struct kern_ipc_perm ____cacheline_aligned_in_smp
sem_perm; /* permissions .. see ipc.h */
- time_t sem_otime; /* last semop time */
time_t sem_ctime; /* last change time */
struct sem *sem_base; /* ptr to first semaphore in array */
- struct list_head sem_pending; /* pending operations to be processed */
+ struct list_head pending_alter; /* pending operations */
+ /* that alter the array */
+ struct list_head pending_const; /* pending complex operations */
+ /* that do not alter semvals */
struct list_head list_id; /* undo requests on this array */
int sem_nsems; /* no. of semaphores in array */
int complex_count; /* pending complex operations */
#define _LINUX_VEXPRESS_H
#include <linux/device.h>
+#include <linux/reboot.h>
#define VEXPRESS_SITE_MB 0
#define VEXPRESS_SITE_DB1 1
struct vm_area_struct; /* vma defining user mapping in mm_types.h */
/* bits in flags of vmalloc's vm_struct below */
-#define VM_IOREMAP 0x00000001 /* ioremap() and friends */
-#define VM_ALLOC 0x00000002 /* vmalloc() */
-#define VM_MAP 0x00000004 /* vmap()ed pages */
-#define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */
-#define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */
-#define VM_UNLIST 0x00000020 /* vm_struct is not listed in vmlist */
+#define VM_IOREMAP 0x00000001 /* ioremap() and friends */
+#define VM_ALLOC 0x00000002 /* vmalloc() */
+#define VM_MAP 0x00000004 /* vmap()ed pages */
+#define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */
+#define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */
+#define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */
/* bits [20..32] reserved for arch specific ioremap internals */
/*
WB_REASON_LAPTOP_TIMER,
WB_REASON_FREE_MORE_MEM,
WB_REASON_FS_FREE_SPACE,
+ /*
+ * There is no bdi forker thread any more and works are done
+ * by emergency worker, however, this is TPs userland visible
+ * and we'll be exposing exactly the same information,
+ * so it has a mismatch name.
+ */
WB_REASON_FORKER_THREAD,
WB_REASON_MAX,
};
-extern const char *wb_reason_name[];
/*
* A control structure which tells the writeback code what to do. These are
void sync_inodes_sb(struct super_block *);
long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
enum wb_reason reason);
-long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
/* <linux/videotext.h> has used 0x72 ('r') in collision, so skip a few */
#define FAT_IOCTL_GET_ATTRIBUTES _IOR('r', 0x10, __u32)
#define FAT_IOCTL_SET_ATTRIBUTES _IOW('r', 0x11, __u32)
+/*Android kernel has used 0x12, so we use 0x13*/
+#define FAT_IOCTL_GET_VOLUME_ID _IOR('r', 0x13, __u32)
struct fat_boot_sector {
__u8 ignored[3]; /* Boot strap short or near jump */
__u8 drive_number; /* Physical drive number */
__u8 state; /* undocumented, but used
for mount state. */
+ __u8 signature; /* extended boot signature */
+ __u8 vol_id[4]; /* volume ID */
+ __u8 vol_label[11]; /* volume label */
+ __u8 fs_type[8]; /* file system type */
/* other fiealds are not added here */
} fat16;
__u8 drive_number; /* Physical drive number */
__u8 state; /* undocumented, but used
for mount state. */
+ __u8 signature; /* extended boot signature */
+ __u8 vol_id[4]; /* volume ID */
+ __u8 vol_label[11]; /* volume label */
+ __u8 fs_type[8]; /* file system type */
/* other fiealds are not added here */
} fat32;
};
config HAVE_KERNEL_LZO
bool
+config HAVE_KERNEL_LZ4
+ bool
+
choice
prompt "Kernel compression mode"
default KERNEL_GZIP
- depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO
+ depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
help
The linux kernel is a kind of self-extracting executable.
Several compression algorithms are available, which differ
size is about 10% bigger than gzip; however its speed
(both compression and decompression) is the fastest.
+config KERNEL_LZ4
+ bool "LZ4"
+ depends on HAVE_KERNEL_LZ4
+ help
+ LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
+ A preliminary version of LZ4 de/compression tool is available at
+ <https://code.google.com/p/lz4/>.
+
+ Its compression ratio is worse than LZO. The size of the kernel
+ is about 8% bigger than LZO. But the decompression speed is
+ faster than LZO.
+
endchoice
config DEFAULT_HOSTNAME
error = ro;
goto out;
}
+ audit_inode_parent_hidden(name, root);
filp = do_create(ipc_ns, root->d_inode,
&path, oflag, mode,
u_attr ? &attr : NULL);
if (IS_ERR(name))
return PTR_ERR(name);
+ audit_inode_parent_hidden(name, mnt->mnt_root);
err = mnt_want_write(mnt);
if (err)
goto out_name;
IPC_MSG_IDS, sysvipc_msg_proc_show);
}
-/*
- * msg_lock_(check_) routines are called in the paths where the rw_mutex
- * is not held.
- */
-static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id)
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
{
- struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
if (IS_ERR(ipcp))
- return (struct msg_queue *)ipcp;
+ return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
-static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
- int id)
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+ int id)
{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
if (IS_ERR(ipcp))
- return (struct msg_queue *)ipcp;
+ return ERR_CAST(ipcp);
return container_of(ipcp, struct msg_queue, q_perm);
}
return retval;
}
- /*
- * ipc_addid() locks msq
- */
+ /* ipc_addid() locks msq upon success. */
id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
if (id < 0) {
security_msg_queue_free(msq);
INIT_LIST_HEAD(&msq->q_receivers);
INIT_LIST_HEAD(&msq->q_senders);
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
return msq->q_perm.id;
}
return -EFAULT;
}
- ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
- &msqid64.msg_perm, msqid64.msg_qbytes);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ down_write(&msg_ids(ns).rw_mutex);
+ rcu_read_lock();
+
+ ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
+ &msqid64.msg_perm, msqid64.msg_qbytes);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
msq = container_of(ipcp, struct msg_queue, q_perm);
err = security_msg_queue_msgctl(msq, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock1;
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&msq->q_perm);
+ /* freeque unlocks the ipc object and rcu */
freeque(ns, ipcp);
goto out_up;
case IPC_SET:
if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
!capable(CAP_SYS_RESOURCE)) {
err = -EPERM;
- goto out_unlock;
+ goto out_unlock1;
}
+ ipc_lock_object(&msq->q_perm);
err = ipc_update_perm(&msqid64.msg_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
msq->q_qbytes = msqid64.msg_qbytes;
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
-out_unlock:
- msg_unlock(msq);
+
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
out_up:
up_write(&msg_ids(ns).rw_mutex);
return err;
}
-SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct msg_queue *msq;
- int err, version;
- struct ipc_namespace *ns;
-
- if (msqid < 0 || cmd < 0)
- return -EINVAL;
-
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
switch (cmd) {
case IPC_INFO:
if (!buf)
return -EFAULT;
+
/*
* We must not return kernel stack data.
* due to padding, it's not enough
return -EFAULT;
return (max_id < 0) ? 0 : max_id;
}
- case MSG_STAT: /* msqid is an index rather than a msg queue id */
+
+ case MSG_STAT:
case IPC_STAT:
{
struct msqid64_ds tbuf;
if (!buf)
return -EFAULT;
+ memset(&tbuf, 0, sizeof(tbuf));
+
+ rcu_read_lock();
if (cmd == MSG_STAT) {
- msq = msg_lock(ns, msqid);
- if (IS_ERR(msq))
- return PTR_ERR(msq);
+ msq = msq_obtain_object(ns, msqid);
+ if (IS_ERR(msq)) {
+ err = PTR_ERR(msq);
+ goto out_unlock;
+ }
success_return = msq->q_perm.id;
} else {
- msq = msg_lock_check(ns, msqid);
- if (IS_ERR(msq))
- return PTR_ERR(msq);
+ msq = msq_obtain_object_check(ns, msqid);
+ if (IS_ERR(msq)) {
+ err = PTR_ERR(msq);
+ goto out_unlock;
+ }
success_return = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
goto out_unlock;
if (err)
goto out_unlock;
- memset(&tbuf, 0, sizeof(tbuf));
-
kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
tbuf.msg_stime = msq->q_stime;
tbuf.msg_rtime = msq->q_rtime;
tbuf.msg_qbytes = msq->q_qbytes;
tbuf.msg_lspid = msq->q_lspid;
tbuf.msg_lrpid = msq->q_lrpid;
- msg_unlock(msq);
+ rcu_read_unlock();
+
if (copy_msqid_to_user(buf, &tbuf, version))
return -EFAULT;
return success_return;
}
- case IPC_SET:
- case IPC_RMID:
- err = msgctl_down(ns, msqid, cmd, buf, version);
- return err;
+
default:
- return -EINVAL;
+ return -EINVAL;
}
+ return err;
out_unlock:
- msg_unlock(msq);
+ rcu_read_unlock();
return err;
}
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+ int version;
+ struct ipc_namespace *ns;
+
+ if (msqid < 0 || cmd < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case MSG_INFO:
+ case MSG_STAT: /* msqid is an index rather than a msg queue id */
+ case IPC_STAT:
+ return msgctl_nolock(ns, msqid, cmd, version, buf);
+ case IPC_SET:
+ case IPC_RMID:
+ return msgctl_down(ns, msqid, cmd, buf, version);
+ default:
+ return -EINVAL;
+ }
+}
+
static int testmsg(struct msg_msg *msg, long type, int mode)
{
switch(mode)
msg->m_type = mtype;
msg->m_ts = msgsz;
- msq = msg_lock_check(ns, msqid);
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
err = PTR_ERR(msq);
- goto out_free;
+ goto out_unlock1;
}
for (;;) {
err = -EACCES;
if (ipcperms(ns, &msq->q_perm, S_IWUGO))
- goto out_unlock_free;
+ goto out_unlock1;
err = security_msg_queue_msgsnd(msq, msg, msgflg);
if (err)
- goto out_unlock_free;
+ goto out_unlock1;
if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
1 + msq->q_qnum <= msq->q_qbytes) {
/* queue full, wait: */
if (msgflg & IPC_NOWAIT) {
err = -EAGAIN;
- goto out_unlock_free;
+ goto out_unlock1;
}
+
+ ipc_lock_object(&msq->q_perm);
ss_add(msq, &s);
if (!ipc_rcu_getref(msq)) {
err = -EIDRM;
- goto out_unlock_free;
+ goto out_unlock0;
}
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
- ipc_lock_by_ptr(&msq->q_perm);
+ rcu_read_lock();
+ ipc_lock_object(&msq->q_perm);
+
ipc_rcu_putref(msq);
if (msq->q_perm.deleted) {
err = -EIDRM;
- goto out_unlock_free;
+ goto out_unlock0;
}
+
ss_del(&s);
if (signal_pending(current)) {
err = -ERESTARTNOHAND;
- goto out_unlock_free;
+ goto out_unlock0;
}
+
+ ipc_unlock_object(&msq->q_perm);
}
+ ipc_lock_object(&msq->q_perm);
msq->q_lspid = task_tgid_vnr(current);
msq->q_stime = get_seconds();
err = 0;
msg = NULL;
-out_unlock_free:
- msg_unlock(msq);
-out_free:
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
if (msg != NULL)
free_msg(msg);
return err;
return ERR_PTR(-EAGAIN);
}
-
-long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
- int msgflg,
+long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
long (*msg_handler)(void __user *, struct msg_msg *, size_t))
{
- struct msg_queue *msq;
- struct msg_msg *msg;
int mode;
+ struct msg_queue *msq;
struct ipc_namespace *ns;
- struct msg_msg *copy = NULL;
+ struct msg_msg *msg, *copy = NULL;
ns = current->nsproxy->ipc_ns;
if (msqid < 0 || (long) bufsz < 0)
return -EINVAL;
+
if (msgflg & MSG_COPY) {
copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
if (IS_ERR(copy))
}
mode = convert_mode(&msgtyp, msgflg);
- msq = msg_lock_check(ns, msqid);
+ rcu_read_lock();
+ msq = msq_obtain_object_check(ns, msqid);
if (IS_ERR(msq)) {
+ rcu_read_unlock();
free_copy(copy);
return PTR_ERR(msq);
}
msg = ERR_PTR(-EACCES);
if (ipcperms(ns, &msq->q_perm, S_IRUGO))
- goto out_unlock;
+ goto out_unlock1;
+ ipc_lock_object(&msq->q_perm);
msg = find_msg(msq, &msgtyp, mode);
-
if (!IS_ERR(msg)) {
/*
* Found a suitable message.
*/
if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
msg = ERR_PTR(-E2BIG);
- goto out_unlock;
+ goto out_unlock0;
}
/*
* If we are copying, then do not unlink message and do
*/
if (msgflg & MSG_COPY) {
msg = copy_msg(msg, copy);
- goto out_unlock;
+ goto out_unlock0;
}
+
list_del(&msg->m_list);
msq->q_qnum--;
msq->q_rtime = get_seconds();
atomic_sub(msg->m_ts, &ns->msg_bytes);
atomic_dec(&ns->msg_hdrs);
ss_wakeup(&msq->q_senders, 0);
- msg_unlock(msq);
- break;
+
+ goto out_unlock0;
}
+
/* No message waiting. Wait for a message */
if (msgflg & IPC_NOWAIT) {
msg = ERR_PTR(-ENOMSG);
- goto out_unlock;
+ goto out_unlock0;
}
+
list_add_tail(&msr_d.r_list, &msq->q_receivers);
msr_d.r_tsk = current;
msr_d.r_msgtype = msgtyp;
msr_d.r_maxsize = bufsz;
msr_d.r_msg = ERR_PTR(-EAGAIN);
current->state = TASK_INTERRUPTIBLE;
- msg_unlock(msq);
+ ipc_unlock_object(&msq->q_perm);
+ rcu_read_unlock();
schedule();
/* Lockless receive, part 1:
* Prior to destruction, expunge_all(-EIRDM) changes r_msg.
* Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
* rcu_read_lock() prevents preemption between reading r_msg
- * and the spin_lock() inside ipc_lock_by_ptr().
+ * and acquiring the q_perm.lock in ipc_lock_object().
*/
rcu_read_lock();
* If there is a message or an error then accept it without
* locking.
*/
- if (msg != ERR_PTR(-EAGAIN)) {
- rcu_read_unlock();
- break;
- }
+ if (msg != ERR_PTR(-EAGAIN))
+ goto out_unlock1;
/* Lockless receive, part 3:
* Acquire the queue spinlock.
*/
- ipc_lock_by_ptr(&msq->q_perm);
- rcu_read_unlock();
+ ipc_lock_object(&msq->q_perm);
/* Lockless receive, part 4:
* Repeat test after acquiring the spinlock.
*/
msg = (struct msg_msg*)msr_d.r_msg;
if (msg != ERR_PTR(-EAGAIN))
- goto out_unlock;
+ goto out_unlock0;
list_del(&msr_d.r_list);
if (signal_pending(current)) {
msg = ERR_PTR(-ERESTARTNOHAND);
-out_unlock:
- msg_unlock(msq);
- break;
+ goto out_unlock0;
}
+
+ ipc_unlock_object(&msq->q_perm);
}
+
+out_unlock0:
+ ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+ rcu_read_unlock();
if (IS_ERR(msg)) {
free_copy(copy);
return PTR_ERR(msg);
int semval; /* current value */
int sempid; /* pid of last operation */
spinlock_t lock; /* spinlock for fine-grained semtimedop */
- struct list_head sem_pending; /* pending single-sop operations */
-};
+ struct list_head pending_alter; /* pending single-sop operations */
+ /* that alter the semaphore */
+ struct list_head pending_const; /* pending single-sop operations */
+ /* that do not alter the semaphore*/
+ time_t sem_otime; /* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
/* One queue for each sleeping process in the system. */
struct sem_queue {
#define SEMOPM_FAST 64 /* ~ 372 bytes on stack */
/*
- * linked list protection:
+ * Locking:
* sem_undo.id_next,
- * sem_array.sem_pending{,last},
- * sem_array.sem_undo: sem_lock() for read/write
+ * sem_array.complex_count,
+ * sem_array.pending{_alter,_cont},
+ * sem_array.sem_undo: global sem_lock() for read/write
* sem_undo.proc_next: only "current" is allowed to read/write that field.
*
+ * sem_array.sem_base[i].pending_{const,alter}:
+ * global or semaphore sem_lock() for read/write
*/
#define sc_semmsl sem_ctls[0]
IPC_SEM_IDS, sysvipc_sem_proc_show);
}
+/**
+ * unmerge_queues - unmerge queues, if possible.
+ * @sma: semaphore array
+ *
+ * The function unmerges the wait queues if complex_count is 0.
+ * It must be called prior to dropping the global semaphore array lock.
+ */
+static void unmerge_queues(struct sem_array *sma)
+{
+ struct sem_queue *q, *tq;
+
+ /* complex operations still around? */
+ if (sma->complex_count)
+ return;
+ /*
+ * We will switch back to simple mode.
+ * Move all pending operation back into the per-semaphore
+ * queues.
+ */
+ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+ struct sem *curr;
+ curr = &sma->sem_base[q->sops[0].sem_num];
+
+ list_add_tail(&q->list, &curr->pending_alter);
+ }
+ INIT_LIST_HEAD(&sma->pending_alter);
+}
+
+/**
+ * merge_queues - Merge single semop queues into global queue
+ * @sma: semaphore array
+ *
+ * This function merges all per-semaphore queues into the global queue.
+ * It is necessary to achieve FIFO ordering for the pending single-sop
+ * operations when a multi-semop operation must sleep.
+ * Only the alter operations must be moved, the const operations can stay.
+ */
+static void merge_queues(struct sem_array *sma)
+{
+ int i;
+ for (i = 0; i < sma->sem_nsems; i++) {
+ struct sem *sem = sma->sem_base + i;
+
+ list_splice_init(&sem->pending_alter, &sma->pending_alter);
+ }
+}
+
/*
* If the request contains only one semaphore operation, and there are
* no complex transactions pending, lock only the semaphore involved.
* their critical section while the array lock is held.
*/
lock_array:
- spin_lock(&sma->sem_perm.lock);
+ ipc_lock_object(&sma->sem_perm);
for (i = 0; i < sma->sem_nsems; i++) {
struct sem *sem = sma->sem_base + i;
spin_unlock_wait(&sem->lock);
static inline void sem_unlock(struct sem_array *sma, int locknum)
{
if (locknum == -1) {
- spin_unlock(&sma->sem_perm.lock);
+ unmerge_queues(sma);
+ ipc_unlock_object(&sma->sem_perm);
} else {
struct sem *sem = sma->sem_base + locknum;
spin_unlock(&sem->lock);
* Without the check/retry algorithm a lockless wakeup is possible:
* - queue.status is initialized to -EINTR before blocking.
* - wakeup is performed by
- * * unlinking the queue entry from sma->sem_pending
+ * * unlinking the queue entry from the pending list
* * setting queue.status to IN_WAKEUP
* This is the notification for the blocked thread that a
* result value is imminent.
sma->sem_base = (struct sem *) &sma[1];
for (i = 0; i < nsems; i++) {
- INIT_LIST_HEAD(&sma->sem_base[i].sem_pending);
+ INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
+ INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
spin_lock_init(&sma->sem_base[i].lock);
}
sma->complex_count = 0;
- INIT_LIST_HEAD(&sma->sem_pending);
+ INIT_LIST_HEAD(&sma->pending_alter);
+ INIT_LIST_HEAD(&sma->pending_const);
INIT_LIST_HEAD(&sma->list_id);
sma->sem_nsems = nsems;
sma->sem_ctime = get_seconds();
return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
}
-/*
- * Determine whether a sequence of semaphore operations would succeed
- * all at once. Return 0 if yes, 1 if need to sleep, else return error code.
+/** perform_atomic_semop - Perform (if possible) a semaphore operation
+ * @sma: semaphore array
+ * @sops: array with operations that should be checked
+ * @nsems: number of sops
+ * @un: undo array
+ * @pid: pid that did the change
+ *
+ * Returns 0 if the operation was possible.
+ * Returns 1 if the operation is impossible, the caller must sleep.
+ * Negative values are error codes.
*/
-static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops,
+static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
int nsops, struct sem_undo *un, int pid)
{
int result, sem_op;
* update_queue is O(N^2) when it restarts scanning the whole queue of
* waiting operations. Therefore this function checks if the restart is
* really necessary. It is called after a previously waiting operation
- * was completed.
+ * modified the array.
+ * Note that wait-for-zero operations are handled without restart.
*/
static int check_restart(struct sem_array *sma, struct sem_queue *q)
{
- struct sem *curr;
- struct sem_queue *h;
-
- /* if the operation didn't modify the array, then no restart */
- if (q->alter == 0)
- return 0;
-
- /* pending complex operations are too difficult to analyse */
- if (sma->complex_count)
+ /* pending complex alter operations are too difficult to analyse */
+ if (!list_empty(&sma->pending_alter))
return 1;
/* we were a sleeping complex operation. Too difficult */
if (q->nsops > 1)
return 1;
- curr = sma->sem_base + q->sops[0].sem_num;
+ /* It is impossible that someone waits for the new value:
+ * - complex operations always restart.
+ * - wait-for-zero are handled seperately.
+ * - q is a previously sleeping simple operation that
+ * altered the array. It must be a decrement, because
+ * simple increments never sleep.
+ * - If there are older (higher priority) decrements
+ * in the queue, then they have observed the original
+ * semval value and couldn't proceed. The operation
+ * decremented to value - thus they won't proceed either.
+ */
+ return 0;
+}
+
+/**
+ * wake_const_ops(sma, semnum, pt) - Wake up non-alter tasks
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * wake_const_ops must be called after a semaphore in a semaphore array
+ * was set to 0. If complex const operations are pending, wake_const_ops must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int wake_const_ops(struct sem_array *sma, int semnum,
+ struct list_head *pt)
+{
+ struct sem_queue *q;
+ struct list_head *walk;
+ struct list_head *pending_list;
+ int semop_completed = 0;
- /* No-one waits on this queue */
- if (list_empty(&curr->sem_pending))
- return 0;
+ if (semnum == -1)
+ pending_list = &sma->pending_const;
+ else
+ pending_list = &sma->sem_base[semnum].pending_const;
+
+ walk = pending_list->next;
+ while (walk != pending_list) {
+ int error;
+
+ q = container_of(walk, struct sem_queue, list);
+ walk = walk->next;
+
+ error = perform_atomic_semop(sma, q->sops, q->nsops,
+ q->undo, q->pid);
- /* the new semaphore value */
- if (curr->semval) {
- /* It is impossible that someone waits for the new value:
- * - q is a previously sleeping simple operation that
- * altered the array. It must be a decrement, because
- * simple increments never sleep.
- * - The value is not 0, thus wait-for-zero won't proceed.
- * - If there are older (higher priority) decrements
- * in the queue, then they have observed the original
- * semval value and couldn't proceed. The operation
- * decremented to value - thus they won't proceed either.
+ if (error <= 0) {
+ /* operation completed, remove from queue & wakeup */
+
+ unlink_queue(sma, q);
+
+ wake_up_sem_queue_prepare(pt, q, error);
+ if (error == 0)
+ semop_completed = 1;
+ }
+ }
+ return semop_completed;
+}
+
+/**
+ * do_smart_wakeup_zero(sma, sops, nsops, pt) - wakeup all wait for zero tasks
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * do_smart_wakeup_zero() checks all required queue for wait-for-zero
+ * operations, based on the actual changes that were performed on the
+ * semaphore array.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
+ int nsops, struct list_head *pt)
+{
+ int i;
+ int semop_completed = 0;
+ int got_zero = 0;
+
+ /* first: the per-semaphore queues, if known */
+ if (sops) {
+ for (i = 0; i < nsops; i++) {
+ int num = sops[i].sem_num;
+
+ if (sma->sem_base[num].semval == 0) {
+ got_zero = 1;
+ semop_completed |= wake_const_ops(sma, num, pt);
+ }
+ }
+ } else {
+ /*
+ * No sops means modified semaphores not known.
+ * Assume all were changed.
*/
- BUG_ON(q->sops[0].sem_op >= 0);
- return 0;
+ for (i = 0; i < sma->sem_nsems; i++) {
+ if (sma->sem_base[i].semval == 0) {
+ got_zero = 1;
+ semop_completed |= wake_const_ops(sma, i, pt);
+ }
+ }
}
/*
- * semval is 0. Check if there are wait-for-zero semops.
- * They must be the first entries in the per-semaphore queue
+ * If one of the modified semaphores got 0,
+ * then check the global queue, too.
*/
- h = list_first_entry(&curr->sem_pending, struct sem_queue, list);
- BUG_ON(h->nsops != 1);
- BUG_ON(h->sops[0].sem_num != q->sops[0].sem_num);
-
- /* Yes, there is a wait-for-zero semop. Restart */
- if (h->sops[0].sem_op == 0)
- return 1;
+ if (got_zero)
+ semop_completed |= wake_const_ops(sma, -1, pt);
- /* Again - no-one is waiting for the new value. */
- return 0;
+ return semop_completed;
}
* semaphore.
* The tasks that must be woken up are added to @pt. The return code
* is stored in q->pid.
+ * The function internally checks if const operations can now succeed.
+ *
* The function return 1 if at least one semop was completed successfully.
*/
static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
int semop_completed = 0;
if (semnum == -1)
- pending_list = &sma->sem_pending;
+ pending_list = &sma->pending_alter;
else
- pending_list = &sma->sem_base[semnum].sem_pending;
+ pending_list = &sma->sem_base[semnum].pending_alter;
again:
walk = pending_list->next;
/* If we are scanning the single sop, per-semaphore list of
* one semaphore and that semaphore is 0, then it is not
- * necessary to scan the "alter" entries: simple increments
+ * necessary to scan further: simple increments
* that affect only one entry succeed immediately and cannot
* be in the per semaphore pending queue, and decrements
* cannot be successful if the value is already 0.
*/
- if (semnum != -1 && sma->sem_base[semnum].semval == 0 &&
- q->alter)
+ if (semnum != -1 && sma->sem_base[semnum].semval == 0)
break;
- error = try_atomic_semop(sma, q->sops, q->nsops,
+ error = perform_atomic_semop(sma, q->sops, q->nsops,
q->undo, q->pid);
/* Does q->sleeper still need to sleep? */
restart = 0;
} else {
semop_completed = 1;
+ do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
restart = check_restart(sma, q);
}
* @otime: force setting otime
* @pt: list head of the tasks that must be woken up.
*
- * do_smart_update() does the required called to update_queue, based on the
- * actual changes that were performed on the semaphore array.
+ * do_smart_update() does the required calls to update_queue and wakeup_zero,
+ * based on the actual changes that were performed on the semaphore array.
* Note that the function does not do the actual wake-up: the caller is
* responsible for calling wake_up_sem_queue_do(@pt).
* It is safe to perform this call after dropping all locks.
int otime, struct list_head *pt)
{
int i;
- int progress;
-
- progress = 1;
-retry_global:
- if (sma->complex_count) {
- if (update_queue(sma, -1, pt)) {
- progress = 1;
- otime = 1;
- sops = NULL;
- }
- }
- if (!progress)
- goto done;
- if (!sops) {
- /* No semops; something special is going on. */
- for (i = 0; i < sma->sem_nsems; i++) {
- if (update_queue(sma, i, pt)) {
- otime = 1;
- progress = 1;
- }
- }
- goto done_checkretry;
- }
+ otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
- /* Check the semaphores that were modified. */
- for (i = 0; i < nsops; i++) {
- if (sops[i].sem_op > 0 ||
- (sops[i].sem_op < 0 &&
- sma->sem_base[sops[i].sem_num].semval == 0))
- if (update_queue(sma, sops[i].sem_num, pt)) {
- otime = 1;
- progress = 1;
+ if (!list_empty(&sma->pending_alter)) {
+ /* semaphore array uses the global queue - just process it. */
+ otime |= update_queue(sma, -1, pt);
+ } else {
+ if (!sops) {
+ /*
+ * No sops, thus the modified semaphores are not
+ * known. Check all.
+ */
+ for (i = 0; i < sma->sem_nsems; i++)
+ otime |= update_queue(sma, i, pt);
+ } else {
+ /*
+ * Check the semaphores that were increased:
+ * - No complex ops, thus all sleeping ops are
+ * decrease.
+ * - if we decreased the value, then any sleeping
+ * semaphore ops wont be able to run: If the
+ * previous value was too small, then the new
+ * value will be too small, too.
+ */
+ for (i = 0; i < nsops; i++) {
+ if (sops[i].sem_op > 0) {
+ otime |= update_queue(sma,
+ sops[i].sem_num, pt);
+ }
}
+ }
}
-done_checkretry:
- if (progress) {
- progress = 0;
- goto retry_global;
+ if (otime) {
+ if (sops == NULL) {
+ sma->sem_base[0].sem_otime = get_seconds();
+ } else {
+ sma->sem_base[sops[0].sem_num].sem_otime =
+ get_seconds();
+ }
}
-done:
- if (otime)
- sma->sem_otime = get_seconds();
}
struct sem_queue * q;
semncnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+ list_for_each_entry(q, &sma->sem_base[semnum].pending_alter, list) {
struct sembuf * sops = q->sops;
BUG_ON(sops->sem_num != semnum);
if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT))
semncnt++;
}
- list_for_each_entry(q, &sma->sem_pending, list) {
+ list_for_each_entry(q, &sma->pending_alter, list) {
struct sembuf * sops = q->sops;
int nsops = q->nsops;
int i;
struct sem_queue * q;
semzcnt = 0;
- list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+ list_for_each_entry(q, &sma->sem_base[semnum].pending_const, list) {
struct sembuf * sops = q->sops;
BUG_ON(sops->sem_num != semnum);
if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT))
semzcnt++;
}
- list_for_each_entry(q, &sma->sem_pending, list) {
+ list_for_each_entry(q, &sma->pending_const, list) {
struct sembuf * sops = q->sops;
int nsops = q->nsops;
int i;
int i;
/* Free the existing undo structures for this semaphore set. */
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
list_del(&un->list_id);
spin_lock(&un->ulp->lock);
/* Wake up all pending processes and let them fail with EIDRM. */
INIT_LIST_HEAD(&tasks);
- list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+ list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
+ unlink_queue(sma, q);
+ wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+ }
+
+ list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
unlink_queue(sma, q);
wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
}
for (i = 0; i < sma->sem_nsems; i++) {
struct sem *sem = sma->sem_base + i;
- list_for_each_entry_safe(q, tq, &sem->sem_pending, list) {
+ list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
+ unlink_queue(sma, q);
+ wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+ }
+ list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
unlink_queue(sma, q);
wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
}
}
}
+static time_t get_semotime(struct sem_array *sma)
+{
+ int i;
+ time_t res;
+
+ res = sma->sem_base[0].sem_otime;
+ for (i = 1; i < sma->sem_nsems; i++) {
+ time_t to = sma->sem_base[i].sem_otime;
+
+ if (to > res)
+ res = to;
+ }
+ return res;
+}
+
static int semctl_nolock(struct ipc_namespace *ns, int semid,
int cmd, int version, void __user *p)
{
goto out_unlock;
kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
- tbuf.sem_otime = sma->sem_otime;
- tbuf.sem_ctime = sma->sem_ctime;
- tbuf.sem_nsems = sma->sem_nsems;
+ tbuf.sem_otime = get_semotime(sma);
+ tbuf.sem_ctime = sma->sem_ctime;
+ tbuf.sem_nsems = sma->sem_nsems;
rcu_read_unlock();
if (copy_semid_to_user(p, &tbuf, version))
return -EFAULT;
curr = &sma->sem_base[semnum];
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry(un, &sma->list_id, list_id)
un->semadj[semnum] = 0;
for (i = 0; i < nsems; i++)
sma->sem_base[i].semval = sem_io[i];
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_for_each_entry(un, &sma->list_id, list_id) {
for (i = 0; i < nsems; i++)
un->semadj[i] = 0;
return -EFAULT;
}
+ down_write(&sem_ids(ns).rw_mutex);
+ rcu_read_lock();
+
ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
&semid64.sem_perm, 0);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ goto out_unlock1;
+ }
sma = container_of(ipcp, struct sem_array, sem_perm);
err = security_sem_semctl(sma, cmd);
- if (err) {
- rcu_read_unlock();
- goto out_up;
- }
+ if (err)
+ goto out_unlock1;
- switch(cmd){
+ switch (cmd) {
case IPC_RMID:
sem_lock(sma, NULL, -1);
+ /* freeary unlocks the ipc object and rcu */
freeary(ns, ipcp);
goto out_up;
case IPC_SET:
sem_lock(sma, NULL, -1);
err = ipc_update_perm(&semid64.sem_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
sma->sem_ctime = get_seconds();
break;
default:
- rcu_read_unlock();
err = -EINVAL;
- goto out_up;
+ goto out_unlock1;
}
-out_unlock:
+out_unlock0:
sem_unlock(sma, -1);
+out_unlock1:
rcu_read_unlock();
out_up:
up_write(&sem_ids(ns).rw_mutex);
new->semid = semid;
assert_spin_locked(&ulp->lock);
list_add_rcu(&new->list_proc, &ulp->list_proc);
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_add(&new->list_id, &sma->list_id);
un = new;
return error;
}
-
SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
unsigned, nsops, const struct timespec __user *, timeout)
{
if (un && un->semid == -1)
goto out_unlock_free;
- error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current));
+ error = perform_atomic_semop(sma, sops, nsops, un,
+ task_tgid_vnr(current));
if (error <= 0) {
if (alter && error == 0)
do_smart_update(sma, sops, nsops, 1, &tasks);
struct sem *curr;
curr = &sma->sem_base[sops->sem_num];
- if (alter)
- list_add_tail(&queue.list, &curr->sem_pending);
- else
- list_add(&queue.list, &curr->sem_pending);
+ if (alter) {
+ if (sma->complex_count) {
+ list_add_tail(&queue.list,
+ &sma->pending_alter);
+ } else {
+
+ list_add_tail(&queue.list,
+ &curr->pending_alter);
+ }
+ } else {
+ list_add_tail(&queue.list, &curr->pending_const);
+ }
} else {
+ if (!sma->complex_count)
+ merge_queues(sma);
+
if (alter)
- list_add_tail(&queue.list, &sma->sem_pending);
+ list_add_tail(&queue.list, &sma->pending_alter);
else
- list_add(&queue.list, &sma->sem_pending);
+ list_add_tail(&queue.list, &sma->pending_const);
+
sma->complex_count++;
}
}
/* remove un from the linked lists */
- assert_spin_locked(&sma->sem_perm.lock);
+ ipc_assert_locked_object(&sma->sem_perm);
list_del(&un->list_id);
spin_lock(&ulp->lock);
{
struct user_namespace *user_ns = seq_user_ns(s);
struct sem_array *sma = it;
+ time_t sem_otime;
+
+ sem_otime = get_semotime(sma);
return seq_printf(s,
"%10d %10d %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
from_kgid_munged(user_ns, sma->sem_perm.gid),
from_kuid_munged(user_ns, sma->sem_perm.cuid),
from_kgid_munged(user_ns, sma->sem_perm.cgid),
- sma->sem_otime,
+ sem_otime,
sma->sem_ctime);
}
#endif
static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
{
rcu_read_lock();
- spin_lock(&ipcp->shm_perm.lock);
+ ipc_lock_object(&ipcp->shm_perm);
}
static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
sprintf (name, "SYSV%08x", key);
if (shmflg & SHM_HUGETLB) {
- struct hstate *hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT)
- & SHM_HUGE_MASK);
+ struct hstate *hs;
size_t hugesize;
+ hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
if (!hs) {
error = -EINVAL;
goto no_file;
shp->shm_nattch = 0;
shp->shm_file = file;
shp->shm_creator = current;
+
/*
* shmid gets reported as "inode#" in /proc/pid/maps.
* proc-ps tools use this. Changing this will break them.
ns->shm_tot += numpages;
error = shp->shm_perm.id;
- shm_unlock(shp);
+
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
return error;
no_id:
return -EFAULT;
}
+ down_write(&shm_ids(ns).rw_mutex);
+ rcu_read_lock();
+
ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
&shmid64.shm_perm, 0);
- if (IS_ERR(ipcp))
- return PTR_ERR(ipcp);
+ if (IS_ERR(ipcp)) {
+ err = PTR_ERR(ipcp);
+ /* the ipc lock is not held upon failure */
+ goto out_unlock1;
+ }
shp = container_of(ipcp, struct shmid_kernel, shm_perm);
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock;
+ goto out_unlock0;
+
switch (cmd) {
case IPC_RMID:
+ /* do_shm_rmid unlocks the ipc object and rcu */
do_shm_rmid(ns, ipcp);
goto out_up;
case IPC_SET:
err = ipc_update_perm(&shmid64.shm_perm, ipcp);
if (err)
- goto out_unlock;
+ goto out_unlock0;
shp->shm_ctim = get_seconds();
break;
default:
err = -EINVAL;
}
-out_unlock:
- shm_unlock(shp);
+
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
out_up:
up_write(&shm_ids(ns).rw_mutex);
return err;
* is returned. The 'new' entry is returned in a locked state on success.
* On failure the entry is not locked and a negative err-code is returned.
*
- * Called with ipc_ids.rw_mutex held as a writer.
+ * Called with writer ipc_ids.rw_mutex held.
*/
-
int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
{
kuid_t euid;
struct ipc_rcu {
struct rcu_head rcu;
atomic_t refcount;
- /* "void *" makes sure alignment of following data is sane. */
- void *data[0];
-};
+} ____cacheline_aligned_in_smp;
/**
* ipc_rcu_alloc - allocate ipc and rcu space
if (unlikely(!out))
return NULL;
atomic_set(&out->refcount, 1);
- return out->data;
+ return out + 1;
}
int ipc_rcu_getref(void *ptr)
{
- return atomic_inc_not_zero(&container_of(ptr, struct ipc_rcu, data)->refcount);
+ struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
+
+ return atomic_inc_not_zero(&p->refcount);
}
/**
void ipc_rcu_putref(void *ptr)
{
- struct ipc_rcu *p = container_of(ptr, struct ipc_rcu, data);
+ struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
if (!atomic_dec_and_test(&p->refcount))
return;
* It must be called without any lock held and
* - retrieves the ipc with the given id in the given table.
* - performs some audit and permission check, depending on the given cmd
- * - returns the ipc with both ipc and rw_mutex locks held in case of success
+ * - returns the ipc with the ipc lock held in case of success
* or an err-code without any lock held otherwise.
+ *
+ * Call holding the both the rw_mutex and the rcu read lock.
*/
struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
struct ipc_ids *ids, int id, int cmd,
int err = -EPERM;
struct kern_ipc_perm *ipcp;
- down_write(&ids->rw_mutex);
- rcu_read_lock();
-
ipcp = ipc_obtain_object_check(ids, id);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
- goto out_up;
+ goto err;
}
audit_ipc_obj(ipcp);
euid = current_euid();
if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) ||
ns_capable(ns->user_ns, CAP_SYS_ADMIN))
- return ipcp;
-
-out_up:
- /*
- * Unsuccessful lookup, unlock and return
- * the corresponding error.
- */
- rcu_read_unlock();
- up_write(&ids->rw_mutex);
-
+ return ipcp; /* successful lookup */
+err:
return ERR_PTR(err);
}
return uid / SEQ_MULTIPLIER != ipcp->seq;
}
-static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+static inline void ipc_lock_object(struct kern_ipc_perm *perm)
{
- rcu_read_lock();
spin_lock(&perm->lock);
}
-static inline void ipc_unlock(struct kern_ipc_perm *perm)
+static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
{
spin_unlock(&perm->lock);
- rcu_read_unlock();
}
-static inline void ipc_lock_object(struct kern_ipc_perm *perm)
+static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
{
- spin_lock(&perm->lock);
+ assert_spin_locked(&perm->lock);
+}
+
+static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+{
+ rcu_read_lock();
+ ipc_lock_object(perm);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+ ipc_unlock_object(perm);
+ rcu_read_unlock();
}
struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);
rcupdate.o extable.o params.o posix-timers.o \
kthread.o wait.o sys_ni.o posix-cpu-timers.o mutex.o \
hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
- notifier.o ksysfs.o cred.o \
+ notifier.o ksysfs.o cred.o reboot.o \
async.o range.o groups.o lglock.o smpboot.o
ifdef CONFIG_FUNCTION_TRACER
struct filename *name;
int name_len; /* number of chars to log */
+ bool hidden; /* don't log this record */
bool name_put; /* call __putname()? */
unsigned long ino;
f->lsm_rule = NULL;
/* Support legacy tests for a valid loginuid */
- if ((f->type == AUDIT_LOGINUID) && (f->val == 4294967295)) {
+ if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) {
f->type = AUDIT_LOGINUID_SET;
f->val = 0;
}
err = audit_add_watch(&entry->rule, &list);
if (err) {
mutex_unlock(&audit_filter_mutex);
+ /*
+ * normally audit_add_tree_rule() will free it
+ * on failure
+ */
+ if (tree)
+ audit_put_tree(tree);
goto error;
}
}
}
i = 0;
- list_for_each_entry(n, &context->names_list, list)
+ list_for_each_entry(n, &context->names_list, list) {
+ if (n->hidden)
+ continue;
audit_log_name(context, n, NULL, i++, &call_panic);
+ }
/* Send end of event record to help user space know we are finished */
ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
* __audit_inode - store the inode and device from a lookup
* @name: name being audited
* @dentry: dentry being audited
- * @parent: does this dentry represent the parent?
+ * @flags: attributes for this particular entry
*/
void __audit_inode(struct filename *name, const struct dentry *dentry,
- unsigned int parent)
+ unsigned int flags)
{
struct audit_context *context = current->audit_context;
const struct inode *inode = dentry->d_inode;
struct audit_names *n;
+ bool parent = flags & AUDIT_INODE_PARENT;
if (!context->in_syscall)
return;
if (parent) {
n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL;
n->type = AUDIT_TYPE_PARENT;
+ if (flags & AUDIT_INODE_HIDDEN)
+ n->hidden = true;
} else {
n->name_len = AUDIT_NAME_FULL;
n->type = AUDIT_TYPE_NORMAL;
/*
* FIXME: do that only when needed, using sched_exit tracepoint
*/
- ptrace_put_breakpoints(tsk);
+ flush_ptrace_hw_breakpoint(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
static void warn_slowpath_common(const char *file, int line, void *caller,
unsigned taint, struct slowpath_args *args)
{
- printk(KERN_WARNING "------------[ cut here ]------------\n");
- printk(KERN_WARNING "WARNING: at %s:%d %pS()\n", file, line, caller);
+ pr_warn("------------[ cut here ]------------\n");
+ pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS()\n",
+ raw_smp_processor_id(), current->pid, file, line, caller);
if (args)
vprintk(args->fmt, args->args);
/* Architecture-specific hardware disable .. */
ptrace_disable(child);
clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
+ flush_ptrace_hw_breakpoint(child);
write_lock_irq(&tasklist_lock);
/*
return ret;
}
#endif /* CONFIG_COMPAT */
-
-#ifdef CONFIG_HAVE_HW_BREAKPOINT
-int ptrace_get_breakpoints(struct task_struct *tsk)
-{
- if (atomic_inc_not_zero(&tsk->ptrace_bp_refcnt))
- return 0;
-
- return -1;
-}
-
-void ptrace_put_breakpoints(struct task_struct *tsk)
-{
- if (atomic_dec_and_test(&tsk->ptrace_bp_refcnt))
- flush_ptrace_hw_breakpoint(tsk);
-}
-#endif /* CONFIG_HAVE_HW_BREAKPOINT */
--- /dev/null
+/*
+ * linux/kernel/reboot.c
+ *
+ * Copyright (C) 2013 Linus Torvalds
+ */
+
+#define pr_fmt(fmt) "reboot: " fmt
+
+#include <linux/ctype.h>
+#include <linux/export.h>
+#include <linux/kexec.h>
+#include <linux/kmod.h>
+#include <linux/kmsg_dump.h>
+#include <linux/reboot.h>
+#include <linux/suspend.h>
+#include <linux/syscalls.h>
+#include <linux/syscore_ops.h>
+#include <linux/uaccess.h>
+
+/*
+ * this indicates whether you can reboot with ctrl-alt-del: the default is yes
+ */
+
+int C_A_D = 1;
+struct pid *cad_pid;
+EXPORT_SYMBOL(cad_pid);
+
+#if defined(CONFIG_ARM) || defined(CONFIG_UNICORE32)
+#define DEFAULT_REBOOT_MODE = REBOOT_HARD
+#else
+#define DEFAULT_REBOOT_MODE
+#endif
+enum reboot_mode reboot_mode DEFAULT_REBOOT_MODE;
+
+int reboot_default;
+int reboot_cpu;
+enum reboot_type reboot_type = BOOT_ACPI;
+int reboot_force;
+
+/*
+ * If set, this is used for preparing the system to power off.
+ */
+
+void (*pm_power_off_prepare)(void);
+
+/**
+ * emergency_restart - reboot the system
+ *
+ * Without shutting down any hardware or taking any locks
+ * reboot the system. This is called when we know we are in
+ * trouble so this is our best effort to reboot. This is
+ * safe to call in interrupt context.
+ */
+void emergency_restart(void)
+{
+ kmsg_dump(KMSG_DUMP_EMERG);
+ machine_emergency_restart();
+}
+EXPORT_SYMBOL_GPL(emergency_restart);
+
+void kernel_restart_prepare(char *cmd)
+{
+ blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
+ system_state = SYSTEM_RESTART;
+ usermodehelper_disable();
+ device_shutdown();
+}
+
+/**
+ * register_reboot_notifier - Register function to be called at reboot time
+ * @nb: Info about notifier function to be called
+ *
+ * Registers a function with the list of functions
+ * to be called at reboot time.
+ *
+ * Currently always returns zero, as blocking_notifier_chain_register()
+ * always returns zero.
+ */
+int register_reboot_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_register(&reboot_notifier_list, nb);
+}
+EXPORT_SYMBOL(register_reboot_notifier);
+
+/**
+ * unregister_reboot_notifier - Unregister previously registered reboot notifier
+ * @nb: Hook to be unregistered
+ *
+ * Unregisters a previously registered reboot
+ * notifier function.
+ *
+ * Returns zero on success, or %-ENOENT on failure.
+ */
+int unregister_reboot_notifier(struct notifier_block *nb)
+{
+ return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
+}
+EXPORT_SYMBOL(unregister_reboot_notifier);
+
+static void migrate_to_reboot_cpu(void)
+{
+ /* The boot cpu is always logical cpu 0 */
+ int cpu = reboot_cpu;
+
+ cpu_hotplug_disable();
+
+ /* Make certain the cpu I'm about to reboot on is online */
+ if (!cpu_online(cpu))
+ cpu = cpumask_first(cpu_online_mask);
+
+ /* Prevent races with other tasks migrating this task */
+ current->flags |= PF_NO_SETAFFINITY;
+
+ /* Make certain I only run on the appropriate processor */
+ set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
+/**
+ * kernel_restart - reboot the system
+ * @cmd: pointer to buffer containing command to execute for restart
+ * or %NULL
+ *
+ * Shutdown everything and perform a clean reboot.
+ * This is not safe to call in interrupt context.
+ */
+void kernel_restart(char *cmd)
+{
+ kernel_restart_prepare(cmd);
+ migrate_to_reboot_cpu();
+ syscore_shutdown();
+ if (!cmd)
+ pr_emerg("Restarting system\n");
+ else
+ pr_emerg("Restarting system with command '%s'\n", cmd);
+ kmsg_dump(KMSG_DUMP_RESTART);
+ machine_restart(cmd);
+}
+EXPORT_SYMBOL_GPL(kernel_restart);
+
+static void kernel_shutdown_prepare(enum system_states state)
+{
+ blocking_notifier_call_chain(&reboot_notifier_list,
+ (state == SYSTEM_HALT) ? SYS_HALT : SYS_POWER_OFF, NULL);
+ system_state = state;
+ usermodehelper_disable();
+ device_shutdown();
+}
+/**
+ * kernel_halt - halt the system
+ *
+ * Shutdown everything and perform a clean system halt.
+ */
+void kernel_halt(void)
+{
+ kernel_shutdown_prepare(SYSTEM_HALT);
+ migrate_to_reboot_cpu();
+ syscore_shutdown();
+ pr_emerg("System halted\n");
+ kmsg_dump(KMSG_DUMP_HALT);
+ machine_halt();
+}
+EXPORT_SYMBOL_GPL(kernel_halt);
+
+/**
+ * kernel_power_off - power_off the system
+ *
+ * Shutdown everything and perform a clean system power_off.
+ */
+void kernel_power_off(void)
+{
+ kernel_shutdown_prepare(SYSTEM_POWER_OFF);
+ if (pm_power_off_prepare)
+ pm_power_off_prepare();
+ migrate_to_reboot_cpu();
+ syscore_shutdown();
+ pr_emerg("Power down\n");
+ kmsg_dump(KMSG_DUMP_POWEROFF);
+ machine_power_off();
+}
+EXPORT_SYMBOL_GPL(kernel_power_off);
+
+static DEFINE_MUTEX(reboot_mutex);
+
+/*
+ * Reboot system call: for obvious reasons only root may call it,
+ * and even root needs to set up some magic numbers in the registers
+ * so that some mistake won't make this reboot the whole machine.
+ * You can also set the meaning of the ctrl-alt-del-key here.
+ *
+ * reboot doesn't sync: do that yourself before calling this.
+ */
+SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
+ void __user *, arg)
+{
+ struct pid_namespace *pid_ns = task_active_pid_ns(current);
+ char buffer[256];
+ int ret = 0;
+
+ /* We only trust the superuser with rebooting the system. */
+ if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT))
+ return -EPERM;
+
+ /* For safety, we require "magic" arguments. */
+ if (magic1 != LINUX_REBOOT_MAGIC1 ||
+ (magic2 != LINUX_REBOOT_MAGIC2 &&
+ magic2 != LINUX_REBOOT_MAGIC2A &&
+ magic2 != LINUX_REBOOT_MAGIC2B &&
+ magic2 != LINUX_REBOOT_MAGIC2C))
+ return -EINVAL;
+
+ /*
+ * If pid namespaces are enabled and the current task is in a child
+ * pid_namespace, the command is handled by reboot_pid_ns() which will
+ * call do_exit().
+ */
+ ret = reboot_pid_ns(pid_ns, cmd);
+ if (ret)
+ return ret;
+
+ /* Instead of trying to make the power_off code look like
+ * halt when pm_power_off is not set do it the easy way.
+ */
+ if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
+ cmd = LINUX_REBOOT_CMD_HALT;
+
+ mutex_lock(&reboot_mutex);
+ switch (cmd) {
+ case LINUX_REBOOT_CMD_RESTART:
+ kernel_restart(NULL);
+ break;
+
+ case LINUX_REBOOT_CMD_CAD_ON:
+ C_A_D = 1;
+ break;
+
+ case LINUX_REBOOT_CMD_CAD_OFF:
+ C_A_D = 0;
+ break;
+
+ case LINUX_REBOOT_CMD_HALT:
+ kernel_halt();
+ do_exit(0);
+ panic("cannot halt");
+
+ case LINUX_REBOOT_CMD_POWER_OFF:
+ kernel_power_off();
+ do_exit(0);
+ break;
+
+ case LINUX_REBOOT_CMD_RESTART2:
+ ret = strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1);
+ if (ret < 0) {
+ ret = -EFAULT;
+ break;
+ }
+ buffer[sizeof(buffer) - 1] = '\0';
+
+ kernel_restart(buffer);
+ break;
+
+#ifdef CONFIG_KEXEC
+ case LINUX_REBOOT_CMD_KEXEC:
+ ret = kernel_kexec();
+ break;
+#endif
+
+#ifdef CONFIG_HIBERNATION
+ case LINUX_REBOOT_CMD_SW_SUSPEND:
+ ret = hibernate();
+ break;
+#endif
+
+ default:
+ ret = -EINVAL;
+ break;
+ }
+ mutex_unlock(&reboot_mutex);
+ return ret;
+}
+
+static void deferred_cad(struct work_struct *dummy)
+{
+ kernel_restart(NULL);
+}
+
+/*
+ * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
+ * As it's called within an interrupt, it may NOT sync: the only choice
+ * is whether to reboot at once, or just ignore the ctrl-alt-del.
+ */
+void ctrl_alt_del(void)
+{
+ static DECLARE_WORK(cad_work, deferred_cad);
+
+ if (C_A_D)
+ schedule_work(&cad_work);
+ else
+ kill_cad_pid(SIGINT, 1);
+}
+
+char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
+
+static int __orderly_poweroff(bool force)
+{
+ char **argv;
+ static char *envp[] = {
+ "HOME=/",
+ "PATH=/sbin:/bin:/usr/sbin:/usr/bin",
+ NULL
+ };
+ int ret;
+
+ argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
+ if (argv) {
+ ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+ argv_free(argv);
+ } else {
+ ret = -ENOMEM;
+ }
+
+ if (ret && force) {
+ pr_warn("Failed to start orderly shutdown: forcing the issue\n");
+ /*
+ * I guess this should try to kick off some daemon to sync and
+ * poweroff asap. Or not even bother syncing if we're doing an
+ * emergency shutdown?
+ */
+ emergency_sync();
+ kernel_power_off();
+ }
+
+ return ret;
+}
+
+static bool poweroff_force;
+
+static void poweroff_work_func(struct work_struct *work)
+{
+ __orderly_poweroff(poweroff_force);
+}
+
+static DECLARE_WORK(poweroff_work, poweroff_work_func);
+
+/**
+ * orderly_poweroff - Trigger an orderly system poweroff
+ * @force: force poweroff if command execution fails
+ *
+ * This may be called from any context to trigger a system shutdown.
+ * If the orderly shutdown fails, it will force an immediate shutdown.
+ */
+int orderly_poweroff(bool force)
+{
+ if (force) /* do not override the pending "true" */
+ poweroff_force = true;
+ schedule_work(&poweroff_work);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(orderly_poweroff);
+
+static int __init reboot_setup(char *str)
+{
+ for (;;) {
+ /*
+ * Having anything passed on the command line via
+ * reboot= will cause us to disable DMI checking
+ * below.
+ */
+ reboot_default = 0;
+
+ switch (*str) {
+ case 'w':
+ reboot_mode = REBOOT_WARM;
+ break;
+
+ case 'c':
+ reboot_mode = REBOOT_COLD;
+ break;
+
+ case 'h':
+ reboot_mode = REBOOT_HARD;
+ break;
+
+ case 's':
+ if (isdigit(*(str+1)))
+ reboot_cpu = simple_strtoul(str+1, NULL, 0);
+ else if (str[1] == 'm' && str[2] == 'p' &&
+ isdigit(*(str+3)))
+ reboot_cpu = simple_strtoul(str+3, NULL, 0);
+ else
+ reboot_mode = REBOOT_SOFT;
+ break;
+
+ case 'g':
+ reboot_mode = REBOOT_GPIO;
+ break;
+
+ case 'b':
+ case 'a':
+ case 'k':
+ case 't':
+ case 'e':
+ case 'p':
+ reboot_type = *str;
+ break;
+
+ case 'f':
+ reboot_force = 1;
+ break;
+ }
+
+ str = strchr(str, ',');
+ if (str)
+ str++;
+ else
+ break;
+ }
+ return 1;
+}
+__setup("reboot=", reboot_setup);
EXPORT_SYMBOL(fs_overflowuid);
EXPORT_SYMBOL(fs_overflowgid);
-/*
- * this indicates whether you can reboot with ctrl-alt-del: the default is yes
- */
-
-int C_A_D = 1;
-struct pid *cad_pid;
-EXPORT_SYMBOL(cad_pid);
-
-/*
- * If set, this is used for preparing the system to power off.
- */
-
-void (*pm_power_off_prepare)(void);
-
/*
* Returns true if current's euid is same as p's uid or euid,
* or has CAP_SYS_NICE to p's user_ns.
return retval;
}
-/**
- * emergency_restart - reboot the system
- *
- * Without shutting down any hardware or taking any locks
- * reboot the system. This is called when we know we are in
- * trouble so this is our best effort to reboot. This is
- * safe to call in interrupt context.
- */
-void emergency_restart(void)
-{
- kmsg_dump(KMSG_DUMP_EMERG);
- machine_emergency_restart();
-}
-EXPORT_SYMBOL_GPL(emergency_restart);
-
-void kernel_restart_prepare(char *cmd)
-{
- blocking_notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
- system_state = SYSTEM_RESTART;
- usermodehelper_disable();
- device_shutdown();
-}
-
-/**
- * register_reboot_notifier - Register function to be called at reboot time
- * @nb: Info about notifier function to be called
- *
- * Registers a function with the list of functions
- * to be called at reboot time.
- *
- * Currently always returns zero, as blocking_notifier_chain_register()
- * always returns zero.
- */
-int register_reboot_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_register(&reboot_notifier_list, nb);
-}
-EXPORT_SYMBOL(register_reboot_notifier);
-
-/**
- * unregister_reboot_notifier - Unregister previously registered reboot notifier
- * @nb: Hook to be unregistered
- *
- * Unregisters a previously registered reboot
- * notifier function.
- *
- * Returns zero on success, or %-ENOENT on failure.
- */
-int unregister_reboot_notifier(struct notifier_block *nb)
-{
- return blocking_notifier_chain_unregister(&reboot_notifier_list, nb);
-}
-EXPORT_SYMBOL(unregister_reboot_notifier);
-
-/* Add backwards compatibility for stable trees. */
-#ifndef PF_NO_SETAFFINITY
-#define PF_NO_SETAFFINITY PF_THREAD_BOUND
-#endif
-
-static void migrate_to_reboot_cpu(void)
-{
- /* The boot cpu is always logical cpu 0 */
- int cpu = 0;
-
- cpu_hotplug_disable();
-
- /* Make certain the cpu I'm about to reboot on is online */
- if (!cpu_online(cpu))
- cpu = cpumask_first(cpu_online_mask);
-
- /* Prevent races with other tasks migrating this task */
- current->flags |= PF_NO_SETAFFINITY;
-
- /* Make certain I only run on the appropriate processor */
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
-}
-
-/**
- * kernel_restart - reboot the system
- * @cmd: pointer to buffer containing command to execute for restart
- * or %NULL
- *
- * Shutdown everything and perform a clean reboot.
- * This is not safe to call in interrupt context.
- */
-void kernel_restart(char *cmd)
-{
- kernel_restart_prepare(cmd);
- migrate_to_reboot_cpu();
- syscore_shutdown();
- if (!cmd)
- printk(KERN_EMERG "Restarting system.\n");
- else
- printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
- kmsg_dump(KMSG_DUMP_RESTART);
- machine_restart(cmd);
-}
-EXPORT_SYMBOL_GPL(kernel_restart);
-
-static void kernel_shutdown_prepare(enum system_states state)
-{
- blocking_notifier_call_chain(&reboot_notifier_list,
- (state == SYSTEM_HALT)?SYS_HALT:SYS_POWER_OFF, NULL);
- system_state = state;
- usermodehelper_disable();
- device_shutdown();
-}
-/**
- * kernel_halt - halt the system
- *
- * Shutdown everything and perform a clean system halt.
- */
-void kernel_halt(void)
-{
- kernel_shutdown_prepare(SYSTEM_HALT);
- migrate_to_reboot_cpu();
- syscore_shutdown();
- printk(KERN_EMERG "System halted.\n");
- kmsg_dump(KMSG_DUMP_HALT);
- machine_halt();
-}
-
-EXPORT_SYMBOL_GPL(kernel_halt);
-
-/**
- * kernel_power_off - power_off the system
- *
- * Shutdown everything and perform a clean system power_off.
- */
-void kernel_power_off(void)
-{
- kernel_shutdown_prepare(SYSTEM_POWER_OFF);
- if (pm_power_off_prepare)
- pm_power_off_prepare();
- migrate_to_reboot_cpu();
- syscore_shutdown();
- printk(KERN_EMERG "Power down.\n");
- kmsg_dump(KMSG_DUMP_POWEROFF);
- machine_power_off();
-}
-EXPORT_SYMBOL_GPL(kernel_power_off);
-
-static DEFINE_MUTEX(reboot_mutex);
-
-/*
- * Reboot system call: for obvious reasons only root may call it,
- * and even root needs to set up some magic numbers in the registers
- * so that some mistake won't make this reboot the whole machine.
- * You can also set the meaning of the ctrl-alt-del-key here.
- *
- * reboot doesn't sync: do that yourself before calling this.
- */
-SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
- void __user *, arg)
-{
- struct pid_namespace *pid_ns = task_active_pid_ns(current);
- char buffer[256];
- int ret = 0;
-
- /* We only trust the superuser with rebooting the system. */
- if (!ns_capable(pid_ns->user_ns, CAP_SYS_BOOT))
- return -EPERM;
-
- /* For safety, we require "magic" arguments. */
- if (magic1 != LINUX_REBOOT_MAGIC1 ||
- (magic2 != LINUX_REBOOT_MAGIC2 &&
- magic2 != LINUX_REBOOT_MAGIC2A &&
- magic2 != LINUX_REBOOT_MAGIC2B &&
- magic2 != LINUX_REBOOT_MAGIC2C))
- return -EINVAL;
-
- /*
- * If pid namespaces are enabled and the current task is in a child
- * pid_namespace, the command is handled by reboot_pid_ns() which will
- * call do_exit().
- */
- ret = reboot_pid_ns(pid_ns, cmd);
- if (ret)
- return ret;
-
- /* Instead of trying to make the power_off code look like
- * halt when pm_power_off is not set do it the easy way.
- */
- if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
- cmd = LINUX_REBOOT_CMD_HALT;
-
- mutex_lock(&reboot_mutex);
- switch (cmd) {
- case LINUX_REBOOT_CMD_RESTART:
- kernel_restart(NULL);
- break;
-
- case LINUX_REBOOT_CMD_CAD_ON:
- C_A_D = 1;
- break;
-
- case LINUX_REBOOT_CMD_CAD_OFF:
- C_A_D = 0;
- break;
-
- case LINUX_REBOOT_CMD_HALT:
- kernel_halt();
- do_exit(0);
- panic("cannot halt.\n");
-
- case LINUX_REBOOT_CMD_POWER_OFF:
- kernel_power_off();
- do_exit(0);
- break;
-
- case LINUX_REBOOT_CMD_RESTART2:
- if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
- ret = -EFAULT;
- break;
- }
- buffer[sizeof(buffer) - 1] = '\0';
-
- kernel_restart(buffer);
- break;
-
-#ifdef CONFIG_KEXEC
- case LINUX_REBOOT_CMD_KEXEC:
- ret = kernel_kexec();
- break;
-#endif
-
-#ifdef CONFIG_HIBERNATION
- case LINUX_REBOOT_CMD_SW_SUSPEND:
- ret = hibernate();
- break;
-#endif
-
- default:
- ret = -EINVAL;
- break;
- }
- mutex_unlock(&reboot_mutex);
- return ret;
-}
-
-static void deferred_cad(struct work_struct *dummy)
-{
- kernel_restart(NULL);
-}
-
-/*
- * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
- * As it's called within an interrupt, it may NOT sync: the only choice
- * is whether to reboot at once, or just ignore the ctrl-alt-del.
- */
-void ctrl_alt_del(void)
-{
- static DECLARE_WORK(cad_work, deferred_cad);
-
- if (C_A_D)
- schedule_work(&cad_work);
- else
- kill_cad_pid(SIGINT, 1);
-}
-
/*
* Unprivileged users may change the real gid to the effective gid
* or vice versa. (BSD-style)
return err ? -EFAULT : 0;
}
-char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff";
-
-static int __orderly_poweroff(bool force)
-{
- char **argv;
- static char *envp[] = {
- "HOME=/",
- "PATH=/sbin:/bin:/usr/sbin:/usr/bin",
- NULL
- };
- int ret;
-
- argv = argv_split(GFP_KERNEL, poweroff_cmd, NULL);
- if (argv) {
- ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
- argv_free(argv);
- } else {
- printk(KERN_WARNING "%s failed to allocate memory for \"%s\"\n",
- __func__, poweroff_cmd);
- ret = -ENOMEM;
- }
-
- if (ret && force) {
- printk(KERN_WARNING "Failed to start orderly shutdown: "
- "forcing the issue\n");
- /*
- * I guess this should try to kick off some daemon to sync and
- * poweroff asap. Or not even bother syncing if we're doing an
- * emergency shutdown?
- */
- emergency_sync();
- kernel_power_off();
- }
-
- return ret;
-}
-
-static bool poweroff_force;
-
-static void poweroff_work_func(struct work_struct *work)
-{
- __orderly_poweroff(poweroff_force);
-}
-
-static DECLARE_WORK(poweroff_work, poweroff_work_func);
-
-/**
- * orderly_poweroff - Trigger an orderly system poweroff
- * @force: force poweroff if command execution fails
- *
- * This may be called from any context to trigger a system shutdown.
- * If the orderly shutdown fails, it will force an immediate shutdown.
- */
-int orderly_poweroff(bool force)
-{
- if (force) /* do not override the pending "true" */
- poweroff_force = true;
- schedule_work(&poweroff_work);
- return 0;
-}
-EXPORT_SYMBOL_GPL(orderly_poweroff);
-
/**
* do_sysinfo - fill in sysinfo struct
* @info: pointer to buffer to fill
config LZO_DECOMPRESS
tristate
+config LZ4_COMPRESS
+ tristate
+
+config LZ4HC_COMPRESS
+ tristate
+
+config LZ4_DECOMPRESS
+ tristate
+
source "lib/xz/Kconfig"
#
select LZO_DECOMPRESS
tristate
+config DECOMPRESS_LZ4
+ select LZ4_DECOMPRESS
+ tristate
+
#
# Generic allocator support is selected if needed
#
obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
- gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o \
+ gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \
bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o
obj-y += string_helpers.o
obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
obj-$(CONFIG_BCH) += bch.o
obj-$(CONFIG_LZO_COMPRESS) += lzo/
obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
+obj-$(CONFIG_LZ4_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4/
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4/
obj-$(CONFIG_XZ_DEC) += xz/
obj-$(CONFIG_RAID6_PQ) += raid6/
lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
+lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
obj-$(CONFIG_TEXTSEARCH) += textsearch.o
obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
--- /dev/null
+/*
+ * lib/clz_ctz.c
+ *
+ * Copyright (C) 2013 Chanho Min <chanho.min@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * __c[lt]z[sd]i2 can be overridden by linking arch-specific versions.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+
+int __weak __ctzsi2(int val)
+{
+ return __ffs(val);
+}
+EXPORT_SYMBOL(__ctzsi2);
+
+int __weak __clzsi2(int val)
+{
+ return 32 - fls(val);
+}
+EXPORT_SYMBOL(__clzsi2);
+
+#if BITS_PER_LONG == 32
+
+int __weak __clzdi2(long val)
+{
+ return 32 - fls((int)val);
+}
+EXPORT_SYMBOL(__clzdi2);
+
+int __weak __ctzdi2(long val)
+{
+ return __ffs((u32)val);
+}
+EXPORT_SYMBOL(__ctzdi2);
+
+#elif BITS_PER_LONG == 64
+
+int __weak __clzdi2(long val)
+{
+ return 64 - fls64((u64)val);
+}
+EXPORT_SYMBOL(__clzdi2);
+
+int __weak __ctzdi2(long val)
+{
+ return __ffs64((u64)val);
+}
+EXPORT_SYMBOL(__ctzdi2);
+
+#else
+#error BITS_PER_LONG not 32 or 64
+#endif
#include <linux/decompress/unxz.h>
#include <linux/decompress/inflate.h>
#include <linux/decompress/unlzo.h>
+#include <linux/decompress/unlz4.h>
#include <linux/types.h>
#include <linux/string.h>
#ifndef CONFIG_DECOMPRESS_LZO
# define unlzo NULL
#endif
+#ifndef CONFIG_DECOMPRESS_LZ4
+# define unlz4 NULL
+#endif
struct compress_format {
unsigned char magic[2];
{ {0x5d, 0x00}, "lzma", unlzma },
{ {0xfd, 0x37}, "xz", unxz },
{ {0x89, 0x4c}, "lzo", unlzo },
+ { {0x02, 0x21}, "lz4", unlz4 },
{ {0, 0}, NULL, NULL }
};
--- /dev/null
+/*
+ * Wrapper for decompressing LZ4-compressed kernel, initramfs, and initrd
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifdef STATIC
+#define PREBOOT
+#include "lz4/lz4_decompress.c"
+#else
+#include <linux/decompress/unlz4.h>
+#endif
+#include <linux/types.h>
+#include <linux/lz4.h>
+#include <linux/decompress/mm.h>
+#include <linux/compiler.h>
+
+#include <asm/unaligned.h>
+
+/*
+ * Note: Uncompressed chunk size is used in the compressor side
+ * (userspace side for compression).
+ * It is hardcoded because there is not proper way to extract it
+ * from the binary stream which is generated by the preliminary
+ * version of LZ4 tool so far.
+ */
+#define LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE (8 << 20)
+#define ARCHIVE_MAGICNUMBER 0x184C2102
+
+STATIC inline int INIT unlz4(u8 *input, int in_len,
+ int (*fill) (void *, unsigned int),
+ int (*flush) (void *, unsigned int),
+ u8 *output, int *posp,
+ void (*error) (char *x))
+{
+ int ret = -1;
+ size_t chunksize = 0;
+ size_t uncomp_chunksize = LZ4_DEFAULT_UNCOMPRESSED_CHUNK_SIZE;
+ u8 *inp;
+ u8 *inp_start;
+ u8 *outp;
+ int size = in_len;
+#ifdef PREBOOT
+ size_t out_len = get_unaligned_le32(input + in_len);
+#endif
+ size_t dest_len;
+
+
+ if (output) {
+ outp = output;
+ } else if (!flush) {
+ error("NULL output pointer and no flush function provided");
+ goto exit_0;
+ } else {
+ outp = large_malloc(uncomp_chunksize);
+ if (!outp) {
+ error("Could not allocate output buffer");
+ goto exit_0;
+ }
+ }
+
+ if (input && fill) {
+ error("Both input pointer and fill function provided,");
+ goto exit_1;
+ } else if (input) {
+ inp = input;
+ } else if (!fill) {
+ error("NULL input pointer and missing fill function");
+ goto exit_1;
+ } else {
+ inp = large_malloc(lz4_compressbound(uncomp_chunksize));
+ if (!inp) {
+ error("Could not allocate input buffer");
+ goto exit_1;
+ }
+ }
+ inp_start = inp;
+
+ if (posp)
+ *posp = 0;
+
+ if (fill)
+ fill(inp, 4);
+
+ chunksize = get_unaligned_le32(inp);
+ if (chunksize == ARCHIVE_MAGICNUMBER) {
+ inp += 4;
+ size -= 4;
+ } else {
+ error("invalid header");
+ goto exit_2;
+ }
+
+ if (posp)
+ *posp += 4;
+
+ for (;;) {
+
+ if (fill)
+ fill(inp, 4);
+
+ chunksize = get_unaligned_le32(inp);
+ if (chunksize == ARCHIVE_MAGICNUMBER) {
+ inp += 4;
+ size -= 4;
+ if (posp)
+ *posp += 4;
+ continue;
+ }
+ inp += 4;
+ size -= 4;
+
+ if (posp)
+ *posp += 4;
+
+ if (fill) {
+ if (chunksize > lz4_compressbound(uncomp_chunksize)) {
+ error("chunk length is longer than allocated");
+ goto exit_2;
+ }
+ fill(inp, chunksize);
+ }
+#ifdef PREBOOT
+ if (out_len >= uncomp_chunksize) {
+ dest_len = uncomp_chunksize;
+ out_len -= dest_len;
+ } else
+ dest_len = out_len;
+ ret = lz4_decompress(inp, &chunksize, outp, dest_len);
+#else
+ dest_len = uncomp_chunksize;
+ ret = lz4_decompress_unknownoutputsize(inp, chunksize, outp,
+ &dest_len);
+#endif
+ if (ret < 0) {
+ error("Decoding failed");
+ goto exit_2;
+ }
+
+ if (flush && flush(outp, dest_len) != dest_len)
+ goto exit_2;
+ if (output)
+ outp += dest_len;
+ if (posp)
+ *posp += chunksize;
+
+ size -= chunksize;
+
+ if (size == 0)
+ break;
+ else if (size < 0) {
+ error("data corrupted");
+ goto exit_2;
+ }
+
+ inp += chunksize;
+ if (fill)
+ inp = inp_start;
+ }
+
+ ret = 0;
+exit_2:
+ if (!input)
+ large_free(inp_start);
+exit_1:
+ if (!output)
+ large_free(outp);
+exit_0:
+ return ret;
+}
+
+#ifdef PREBOOT
+STATIC int INIT decompress(unsigned char *buf, int in_len,
+ int(*fill)(void*, unsigned int),
+ int(*flush)(void*, unsigned int),
+ unsigned char *output,
+ int *posp,
+ void(*error)(char *x)
+ )
+{
+ return unlz4(buf, in_len - 4, fill, flush, output, posp, error);
+}
+#endif
--- /dev/null
+obj-$(CONFIG_LZ4_COMPRESS) += lz4_compress.o
+obj-$(CONFIG_LZ4HC_COMPRESS) += lz4hc_compress.o
+obj-$(CONFIG_LZ4_DECOMPRESS) += lz4_decompress.o
--- /dev/null
+/*
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ *
+ * Changed for kernel use by:
+ * Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lz4.h>
+#include <asm/unaligned.h>
+#include "lz4defs.h"
+
+/*
+ * LZ4_compressCtx :
+ * -----------------
+ * Compress 'isize' bytes from 'source' into an output buffer 'dest' of
+ * maximum size 'maxOutputSize'. * If it cannot achieve it, compression
+ * will stop, and result of the function will be zero.
+ * return : the number of bytes written in buffer 'dest', or 0 if the
+ * compression fails
+ */
+static inline int lz4_compressctx(void *ctx,
+ const char *source,
+ char *dest,
+ int isize,
+ int maxoutputsize)
+{
+ HTYPE *hashtable = (HTYPE *)ctx;
+ const u8 *ip = (u8 *)source;
+#if LZ4_ARCH64
+ const BYTE * const base = ip;
+#else
+ const int base = 0;
+#endif
+ const u8 *anchor = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ #define MATCHLIMIT (iend - LASTLITERALS)
+
+ u8 *op = (u8 *) dest;
+ u8 *const oend = op + maxoutputsize;
+ int length;
+ const int skipstrength = SKIPSTRENGTH;
+ u32 forwardh;
+ int lastrun;
+
+ /* Init */
+ if (isize < MINLENGTH)
+ goto _last_literals;
+
+ memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+
+ /* First Byte */
+ hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
+ ip++;
+ forwardh = LZ4_HASH_VALUE(ip);
+
+ /* Main Loop */
+ for (;;) {
+ int findmatchattempts = (1U << skipstrength) + 3;
+ const u8 *forwardip = ip;
+ const u8 *ref;
+ u8 *token;
+
+ /* Find a match */
+ do {
+ u32 h = forwardh;
+ int step = findmatchattempts++ >> skipstrength;
+ ip = forwardip;
+ forwardip = ip + step;
+
+ if (unlikely(forwardip > mflimit))
+ goto _last_literals;
+
+ forwardh = LZ4_HASH_VALUE(forwardip);
+ ref = base + hashtable[h];
+ hashtable[h] = ip - base;
+ } while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip)));
+
+ /* Catch up */
+ while ((ip > anchor) && (ref > (u8 *)source) &&
+ unlikely(ip[-1] == ref[-1])) {
+ ip--;
+ ref--;
+ }
+
+ /* Encode Literal length */
+ length = (int)(ip - anchor);
+ token = op++;
+ /* check output limit */
+ if (unlikely(op + length + (2 + 1 + LASTLITERALS) +
+ (length >> 8) > oend))
+ return 0;
+
+ if (length >= (int)RUN_MASK) {
+ int len;
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *op++ = 255;
+ *op++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(anchor, op, length);
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+
+ /* Start Counting */
+ ip += MINMATCH;
+ /* MinMatch verified */
+ ref += MINMATCH;
+ anchor = ip;
+ while (likely(ip < MATCHLIMIT - (STEPSIZE - 1))) {
+ #if LZ4_ARCH64
+ u64 diff = A64(ref) ^ A64(ip);
+ #else
+ u32 diff = A32(ref) ^ A32(ip);
+ #endif
+ if (!diff) {
+ ip += STEPSIZE;
+ ref += STEPSIZE;
+ continue;
+ }
+ ip += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
+ ip += 4;
+ ref += 4;
+ }
+ #endif
+ if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
+ ip += 2;
+ ref += 2;
+ }
+ if ((ip < MATCHLIMIT) && (*ref == *ip))
+ ip++;
+_endcount:
+ /* Encode MatchLength */
+ length = (int)(ip - anchor);
+ /* Check output limit */
+ if (unlikely(op + (1 + LASTLITERALS) + (length >> 8) > oend))
+ return 0;
+ if (length >= (int)ML_MASK) {
+ *token += ML_MASK;
+ length -= ML_MASK;
+ for (; length > 509 ; length -= 510) {
+ *op++ = 255;
+ *op++ = 255;
+ }
+ if (length > 254) {
+ length -= 255;
+ *op++ = 255;
+ }
+ *op++ = (u8)length;
+ } else
+ *token += length;
+
+ /* Test end of chunk */
+ if (ip > mflimit) {
+ anchor = ip;
+ break;
+ }
+
+ /* Fill table */
+ hashtable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base;
+
+ /* Test next position */
+ ref = base + hashtable[LZ4_HASH_VALUE(ip)];
+ hashtable[LZ4_HASH_VALUE(ip)] = ip - base;
+ if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ anchor = ip++;
+ forwardh = LZ4_HASH_VALUE(ip);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (((char *)op - dest) + lastrun + 1
+ + ((lastrun + 255 - RUN_MASK) / 255) > (u32)maxoutputsize)
+ return 0;
+
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8)lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+
+ /* End */
+ return (int)(((char *)op) - dest);
+}
+
+static inline int lz4_compress64kctx(void *ctx,
+ const char *source,
+ char *dest,
+ int isize,
+ int maxoutputsize)
+{
+ u16 *hashtable = (u16 *)ctx;
+ const u8 *ip = (u8 *) source;
+ const u8 *anchor = ip;
+ const u8 *const base = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ #define MATCHLIMIT (iend - LASTLITERALS)
+
+ u8 *op = (u8 *) dest;
+ u8 *const oend = op + maxoutputsize;
+ int len, length;
+ const int skipstrength = SKIPSTRENGTH;
+ u32 forwardh;
+ int lastrun;
+
+ /* Init */
+ if (isize < MINLENGTH)
+ goto _last_literals;
+
+ memset((void *)hashtable, 0, LZ4_MEM_COMPRESS);
+
+ /* First Byte */
+ ip++;
+ forwardh = LZ4_HASH64K_VALUE(ip);
+
+ /* Main Loop */
+ for (;;) {
+ int findmatchattempts = (1U << skipstrength) + 3;
+ const u8 *forwardip = ip;
+ const u8 *ref;
+ u8 *token;
+
+ /* Find a match */
+ do {
+ u32 h = forwardh;
+ int step = findmatchattempts++ >> skipstrength;
+ ip = forwardip;
+ forwardip = ip + step;
+
+ if (forwardip > mflimit)
+ goto _last_literals;
+
+ forwardh = LZ4_HASH64K_VALUE(forwardip);
+ ref = base + hashtable[h];
+ hashtable[h] = (u16)(ip - base);
+ } while (A32(ref) != A32(ip));
+
+ /* Catch up */
+ while ((ip > anchor) && (ref > (u8 *)source)
+ && (ip[-1] == ref[-1])) {
+ ip--;
+ ref--;
+ }
+
+ /* Encode Literal length */
+ length = (int)(ip - anchor);
+ token = op++;
+ /* Check output limit */
+ if (unlikely(op + length + (2 + 1 + LASTLITERALS)
+ + (length >> 8) > oend))
+ return 0;
+ if (length >= (int)RUN_MASK) {
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *op++ = 255;
+ *op++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(anchor, op, length);
+
+_next_match:
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(op, (u16)(ip - ref));
+
+ /* Start Counting */
+ ip += MINMATCH;
+ /* MinMatch verified */
+ ref += MINMATCH;
+ anchor = ip;
+
+ while (ip < MATCHLIMIT - (STEPSIZE - 1)) {
+ #if LZ4_ARCH64
+ u64 diff = A64(ref) ^ A64(ip);
+ #else
+ u32 diff = A32(ref) ^ A32(ip);
+ #endif
+
+ if (!diff) {
+ ip += STEPSIZE;
+ ref += STEPSIZE;
+ continue;
+ }
+ ip += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ip < (MATCHLIMIT - 3)) && (A32(ref) == A32(ip))) {
+ ip += 4;
+ ref += 4;
+ }
+ #endif
+ if ((ip < (MATCHLIMIT - 1)) && (A16(ref) == A16(ip))) {
+ ip += 2;
+ ref += 2;
+ }
+ if ((ip < MATCHLIMIT) && (*ref == *ip))
+ ip++;
+_endcount:
+
+ /* Encode MatchLength */
+ len = (int)(ip - anchor);
+ /* Check output limit */
+ if (unlikely(op + (1 + LASTLITERALS) + (len >> 8) > oend))
+ return 0;
+ if (len >= (int)ML_MASK) {
+ *token += ML_MASK;
+ len -= ML_MASK;
+ for (; len > 509 ; len -= 510) {
+ *op++ = 255;
+ *op++ = 255;
+ }
+ if (len > 254) {
+ len -= 255;
+ *op++ = 255;
+ }
+ *op++ = (u8)len;
+ } else
+ *token += len;
+
+ /* Test end of chunk */
+ if (ip > mflimit) {
+ anchor = ip;
+ break;
+ }
+
+ /* Fill table */
+ hashtable[LZ4_HASH64K_VALUE(ip-2)] = (u16)(ip - 2 - base);
+
+ /* Test next position */
+ ref = base + hashtable[LZ4_HASH64K_VALUE(ip)];
+ hashtable[LZ4_HASH64K_VALUE(ip)] = (u16)(ip - base);
+ if (A32(ref) == A32(ip)) {
+ token = op++;
+ *token = 0;
+ goto _next_match;
+ }
+
+ /* Prepare next loop */
+ anchor = ip++;
+ forwardh = LZ4_HASH64K_VALUE(ip);
+ }
+
+_last_literals:
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (op + lastrun + 1 + (lastrun - RUN_MASK + 255) / 255 > oend)
+ return 0;
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8)lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ /* End */
+ return (int)(((char *)op) - dest);
+}
+
+int lz4_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ if (src_len < LZ4_64KLIMIT)
+ out_len = lz4_compress64kctx(wrkmem, src, dst, src_len,
+ lz4_compressbound(src_len));
+ else
+ out_len = lz4_compressctx(wrkmem, src, dst, src_len,
+ lz4_compressbound(src_len));
+
+ if (out_len < 0)
+ goto exit;
+
+ *dst_len = out_len;
+
+ return 0;
+exit:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(lz4_compress);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 compressor");
--- /dev/null
+/*
+ * LZ4 Decompressor for Linux kernel
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * Based on LZ4 implementation by Yann Collet.
+ *
+ * LZ4 - Fast LZ compression algorithm
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ */
+
+#ifndef STATIC
+#include <linux/module.h>
+#include <linux/kernel.h>
+#endif
+#include <linux/lz4.h>
+
+#include <asm/unaligned.h>
+
+#include "lz4defs.h"
+
+static int lz4_uncompress(const char *source, char *dest, int osize)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *ref;
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + osize;
+ BYTE *cpy;
+ unsigned token;
+ size_t length;
+ size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
+#if LZ4_ARCH64
+ size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+#endif
+
+ while (1) {
+
+ /* get runlength */
+ token = *ip++;
+ length = (token >> ML_BITS);
+ if (length == RUN_MASK) {
+ size_t len;
+
+ len = *ip++;
+ for (; len == 255; length += 255)
+ len = *ip++;
+ length += len;
+ }
+
+ /* copy literals */
+ cpy = op + length;
+ if (unlikely(cpy > oend - COPYLENGTH)) {
+ /*
+ * Error: not enough place for another match
+ * (min 4) + 5 literals
+ */
+ if (cpy != oend)
+ goto _output_error;
+
+ memcpy(op, ip, length);
+ ip += length;
+ break; /* EOF */
+ }
+ LZ4_WILDCOPY(ip, op, cpy);
+ ip -= (op - cpy);
+ op = cpy;
+
+ /* get offset */
+ LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
+ ip += 2;
+
+ /* Error: offset create reference outside destination buffer */
+ if (unlikely(ref < (BYTE *const) dest))
+ goto _output_error;
+
+ /* get matchlength */
+ length = token & ML_MASK;
+ if (length == ML_MASK) {
+ for (; *ip == 255; length += 255)
+ ip++;
+ length += *ip++;
+ }
+
+ /* copy repeated sequence */
+ if (unlikely((op - ref) < STEPSIZE)) {
+#if LZ4_ARCH64
+ size_t dec64 = dec64table[op - ref];
+#else
+ const int dec64 = 0;
+#endif
+ op[0] = ref[0];
+ op[1] = ref[1];
+ op[2] = ref[2];
+ op[3] = ref[3];
+ op += 4;
+ ref += 4;
+ ref -= dec32table[op-ref];
+ PUT4(ref, op);
+ op += STEPSIZE - 4;
+ ref -= dec64;
+ } else {
+ LZ4_COPYSTEP(ref, op);
+ }
+ cpy = op + length - (STEPSIZE - 4);
+ if (cpy > (oend - COPYLENGTH)) {
+
+ /* Error: request to write beyond destination buffer */
+ if (cpy > oend)
+ goto _output_error;
+ LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ while (op < cpy)
+ *op++ = *ref++;
+ op = cpy;
+ /*
+ * Check EOF (should never happen, since last 5 bytes
+ * are supposed to be literals)
+ */
+ if (op == oend)
+ goto _output_error;
+ continue;
+ }
+ LZ4_SECURECOPY(ref, op, cpy);
+ op = cpy; /* correction */
+ }
+ /* end of decoding */
+ return (int) (((char *)ip) - source);
+
+ /* write overflow error detected */
+_output_error:
+ return (int) (-(((char *)ip) - source));
+}
+
+static int lz4_uncompress_unknownoutputsize(const char *source, char *dest,
+ int isize, size_t maxoutputsize)
+{
+ const BYTE *ip = (const BYTE *) source;
+ const BYTE *const iend = ip + isize;
+ const BYTE *ref;
+
+
+ BYTE *op = (BYTE *) dest;
+ BYTE * const oend = op + maxoutputsize;
+ BYTE *cpy;
+
+ size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};
+#if LZ4_ARCH64
+ size_t dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
+#endif
+
+ /* Main Loop */
+ while (ip < iend) {
+
+ unsigned token;
+ size_t length;
+
+ /* get runlength */
+ token = *ip++;
+ length = (token >> ML_BITS);
+ if (length == RUN_MASK) {
+ int s = 255;
+ while ((ip < iend) && (s == 255)) {
+ s = *ip++;
+ length += s;
+ }
+ }
+ /* copy literals */
+ cpy = op + length;
+ if ((cpy > oend - COPYLENGTH) ||
+ (ip + length > iend - COPYLENGTH)) {
+
+ if (cpy > oend)
+ goto _output_error;/* writes beyond buffer */
+
+ if (ip + length != iend)
+ goto _output_error;/*
+ * Error: LZ4 format requires
+ * to consume all input
+ * at this stage
+ */
+ memcpy(op, ip, length);
+ op += length;
+ break;/* Necessarily EOF, due to parsing restrictions */
+ }
+ LZ4_WILDCOPY(ip, op, cpy);
+ ip -= (op - cpy);
+ op = cpy;
+
+ /* get offset */
+ LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip);
+ ip += 2;
+ if (ref < (BYTE * const) dest)
+ goto _output_error;
+ /*
+ * Error : offset creates reference
+ * outside of destination buffer
+ */
+
+ /* get matchlength */
+ length = (token & ML_MASK);
+ if (length == ML_MASK) {
+ while (ip < iend) {
+ int s = *ip++;
+ length += s;
+ if (s == 255)
+ continue;
+ break;
+ }
+ }
+
+ /* copy repeated sequence */
+ if (unlikely((op - ref) < STEPSIZE)) {
+#if LZ4_ARCH64
+ size_t dec64 = dec64table[op - ref];
+#else
+ const int dec64 = 0;
+#endif
+ op[0] = ref[0];
+ op[1] = ref[1];
+ op[2] = ref[2];
+ op[3] = ref[3];
+ op += 4;
+ ref += 4;
+ ref -= dec32table[op - ref];
+ PUT4(ref, op);
+ op += STEPSIZE - 4;
+ ref -= dec64;
+ } else {
+ LZ4_COPYSTEP(ref, op);
+ }
+ cpy = op + length - (STEPSIZE-4);
+ if (cpy > oend - COPYLENGTH) {
+ if (cpy > oend)
+ goto _output_error; /* write outside of buf */
+
+ LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH));
+ while (op < cpy)
+ *op++ = *ref++;
+ op = cpy;
+ /*
+ * Check EOF (should never happen, since last 5 bytes
+ * are supposed to be literals)
+ */
+ if (op == oend)
+ goto _output_error;
+ continue;
+ }
+ LZ4_SECURECOPY(ref, op, cpy);
+ op = cpy; /* correction */
+ }
+ /* end of decoding */
+ return (int) (((char *) op) - dest);
+
+ /* write overflow error detected */
+_output_error:
+ return (int) (-(((char *) ip) - source));
+}
+
+int lz4_decompress(const char *src, size_t *src_len, char *dest,
+ size_t actual_dest_len)
+{
+ int ret = -1;
+ int input_len = 0;
+
+ input_len = lz4_uncompress(src, dest, actual_dest_len);
+ if (input_len < 0)
+ goto exit_0;
+ *src_len = input_len;
+
+ return 0;
+exit_0:
+ return ret;
+}
+#ifndef STATIC
+EXPORT_SYMBOL_GPL(lz4_decompress);
+#endif
+
+int lz4_decompress_unknownoutputsize(const char *src, size_t src_len,
+ char *dest, size_t *dest_len)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ out_len = lz4_uncompress_unknownoutputsize(src, dest, src_len,
+ *dest_len);
+ if (out_len < 0)
+ goto exit_0;
+ *dest_len = out_len;
+
+ return 0;
+exit_0:
+ return ret;
+}
+#ifndef STATIC
+EXPORT_SYMBOL_GPL(lz4_decompress_unknownoutputsize);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4 Decompressor");
+#endif
--- /dev/null
+/*
+ * lz4defs.h -- architecture specific defines
+ *
+ * Copyright (C) 2013, LG Electronics, Kyungsik Lee <kyungsik.lee@lge.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Detects 64 bits mode
+ */
+#if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) \
+ || defined(__ppc64__) || defined(__LP64__))
+#define LZ4_ARCH64 1
+#else
+#define LZ4_ARCH64 0
+#endif
+
+/*
+ * Architecture-specific macros
+ */
+#define BYTE u8
+typedef struct _U16_S { u16 v; } U16_S;
+typedef struct _U32_S { u32 v; } U32_S;
+typedef struct _U64_S { u64 v; } U64_S;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) \
+ || defined(CONFIG_ARM) && __LINUX_ARM_ARCH__ >= 6 \
+ && defined(ARM_EFFICIENT_UNALIGNED_ACCESS)
+
+#define A16(x) (((U16_S *)(x))->v)
+#define A32(x) (((U32_S *)(x))->v)
+#define A64(x) (((U64_S *)(x))->v)
+
+#define PUT4(s, d) (A32(d) = A32(s))
+#define PUT8(s, d) (A64(d) = A64(s))
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+ do { \
+ A16(p) = v; \
+ p += 2; \
+ } while (0)
+#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */
+
+#define A64(x) get_unaligned((u64 *)&(((U16_S *)(x))->v))
+#define A32(x) get_unaligned((u32 *)&(((U16_S *)(x))->v))
+#define A16(x) get_unaligned((u16 *)&(((U16_S *)(x))->v))
+
+#define PUT4(s, d) \
+ put_unaligned(get_unaligned((const u32 *) s), (u32 *) d)
+#define PUT8(s, d) \
+ put_unaligned(get_unaligned((const u64 *) s), (u64 *) d)
+
+#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \
+ do { \
+ put_unaligned(v, (u16 *)(p)); \
+ p += 2; \
+ } while (0)
+#endif
+
+#define COPYLENGTH 8
+#define ML_BITS 4
+#define ML_MASK ((1U << ML_BITS) - 1)
+#define RUN_BITS (8 - ML_BITS)
+#define RUN_MASK ((1U << RUN_BITS) - 1)
+#define MEMORY_USAGE 14
+#define MINMATCH 4
+#define SKIPSTRENGTH 6
+#define LASTLITERALS 5
+#define MFLIMIT (COPYLENGTH + MINMATCH)
+#define MINLENGTH (MFLIMIT + 1)
+#define MAXD_LOG 16
+#define MAXD (1 << MAXD_LOG)
+#define MAXD_MASK (u32)(MAXD - 1)
+#define MAX_DISTANCE (MAXD - 1)
+#define HASH_LOG (MAXD_LOG - 1)
+#define HASHTABLESIZE (1 << HASH_LOG)
+#define MAX_NB_ATTEMPTS 256
+#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH)
+#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT - 1))
+#define HASHLOG64K ((MEMORY_USAGE - 2) + 1)
+#define HASH64KTABLESIZE (1U << HASHLOG64K)
+#define LZ4_HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - (MEMORY_USAGE-2)))
+#define LZ4_HASH64K_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - HASHLOG64K))
+#define HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \
+ ((MINMATCH * 8) - HASH_LOG))
+
+#if LZ4_ARCH64/* 64-bit */
+#define STEPSIZE 8
+
+#define LZ4_COPYSTEP(s, d) \
+ do { \
+ PUT8(s, d); \
+ d += 8; \
+ s += 8; \
+ } while (0)
+
+#define LZ4_COPYPACKET(s, d) LZ4_COPYSTEP(s, d)
+
+#define LZ4_SECURECOPY(s, d, e) \
+ do { \
+ if (d < e) { \
+ LZ4_WILDCOPY(s, d, e); \
+ } \
+ } while (0)
+#define HTYPE u32
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctzll(val) >> 3)
+#endif
+
+#else /* 32-bit */
+#define STEPSIZE 4
+
+#define LZ4_COPYSTEP(s, d) \
+ do { \
+ PUT4(s, d); \
+ d += 4; \
+ s += 4; \
+ } while (0)
+
+#define LZ4_COPYPACKET(s, d) \
+ do { \
+ LZ4_COPYSTEP(s, d); \
+ LZ4_COPYSTEP(s, d); \
+ } while (0)
+
+#define LZ4_SECURECOPY LZ4_WILDCOPY
+#define HTYPE const u8*
+
+#ifdef __BIG_ENDIAN
+#define LZ4_NBCOMMONBYTES(val) (__builtin_clz(val) >> 3)
+#else
+#define LZ4_NBCOMMONBYTES(val) (__builtin_ctz(val) >> 3)
+#endif
+
+#endif
+
+#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \
+ (d = s - get_unaligned_le16(p))
+
+#define LZ4_WILDCOPY(s, d, e) \
+ do { \
+ LZ4_COPYPACKET(s, d); \
+ } while (d < e)
+
+#define LZ4_BLINDCOPY(s, d, l) \
+ do { \
+ u8 *e = (d) + l; \
+ LZ4_WILDCOPY(s, d, e); \
+ d = e; \
+ } while (0)
--- /dev/null
+/*
+ * LZ4 HC - High Compression Mode of LZ4
+ * Copyright (C) 2011-2012, Yann Collet.
+ * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are
+ * met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following disclaimer
+ * in the documentation and/or other materials provided with the
+ * distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * You can contact the author at :
+ * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html
+ * - LZ4 source repository : http://code.google.com/p/lz4/
+ *
+ * Changed for kernel use by:
+ * Chanho Min <chanho.min@lge.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lz4.h>
+#include <asm/unaligned.h>
+#include "lz4defs.h"
+
+struct lz4hc_data {
+ const u8 *base;
+ HTYPE hashtable[HASHTABLESIZE];
+ u16 chaintable[MAXD];
+ const u8 *nexttoupdate;
+} __attribute__((__packed__));
+
+static inline int lz4hc_init(struct lz4hc_data *hc4, const u8 *base)
+{
+ memset((void *)hc4->hashtable, 0, sizeof(hc4->hashtable));
+ memset(hc4->chaintable, 0xFF, sizeof(hc4->chaintable));
+
+#if LZ4_ARCH64
+ hc4->nexttoupdate = base + 1;
+#else
+ hc4->nexttoupdate = base;
+#endif
+ hc4->base = base;
+ return 1;
+}
+
+/* Update chains up to ip (excluded) */
+static inline void lz4hc_insert(struct lz4hc_data *hc4, const u8 *ip)
+{
+ u16 *chaintable = hc4->chaintable;
+ HTYPE *hashtable = hc4->hashtable;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+
+ while (hc4->nexttoupdate < ip) {
+ const u8 *p = hc4->nexttoupdate;
+ size_t delta = p - (hashtable[HASH_VALUE(p)] + base);
+ if (delta > MAX_DISTANCE)
+ delta = MAX_DISTANCE;
+ chaintable[(size_t)(p) & MAXD_MASK] = (u16)delta;
+ hashtable[HASH_VALUE(p)] = (p) - base;
+ hc4->nexttoupdate++;
+ }
+}
+
+static inline size_t lz4hc_commonlength(const u8 *p1, const u8 *p2,
+ const u8 *const matchlimit)
+{
+ const u8 *p1t = p1;
+
+ while (p1t < matchlimit - (STEPSIZE - 1)) {
+#if LZ4_ARCH64
+ u64 diff = A64(p2) ^ A64(p1t);
+#else
+ u32 diff = A32(p2) ^ A32(p1t);
+#endif
+ if (!diff) {
+ p1t += STEPSIZE;
+ p2 += STEPSIZE;
+ continue;
+ }
+ p1t += LZ4_NBCOMMONBYTES(diff);
+ return p1t - p1;
+ }
+#if LZ4_ARCH64
+ if ((p1t < (matchlimit-3)) && (A32(p2) == A32(p1t))) {
+ p1t += 4;
+ p2 += 4;
+ }
+#endif
+
+ if ((p1t < (matchlimit - 1)) && (A16(p2) == A16(p1t))) {
+ p1t += 2;
+ p2 += 2;
+ }
+ if ((p1t < matchlimit) && (*p2 == *p1t))
+ p1t++;
+ return p1t - p1;
+}
+
+static inline int lz4hc_insertandfindbestmatch(struct lz4hc_data *hc4,
+ const u8 *ip, const u8 *const matchlimit, const u8 **matchpos)
+{
+ u16 *const chaintable = hc4->chaintable;
+ HTYPE *const hashtable = hc4->hashtable;
+ const u8 *ref;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+ int nbattempts = MAX_NB_ATTEMPTS;
+ size_t repl = 0, ml = 0;
+ u16 delta;
+
+ /* HC4 match finder */
+ lz4hc_insert(hc4, ip);
+ ref = hashtable[HASH_VALUE(ip)] + base;
+
+ /* potential repetition */
+ if (ref >= ip-4) {
+ /* confirmed */
+ if (A32(ref) == A32(ip)) {
+ delta = (u16)(ip-ref);
+ repl = ml = lz4hc_commonlength(ip + MINMATCH,
+ ref + MINMATCH, matchlimit) + MINMATCH;
+ *matchpos = ref;
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+
+ while ((ref >= ip - MAX_DISTANCE) && nbattempts) {
+ nbattempts--;
+ if (*(ref + ml) == *(ip + ml)) {
+ if (A32(ref) == A32(ip)) {
+ size_t mlt =
+ lz4hc_commonlength(ip + MINMATCH,
+ ref + MINMATCH, matchlimit) + MINMATCH;
+ if (mlt > ml) {
+ ml = mlt;
+ *matchpos = ref;
+ }
+ }
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+
+ /* Complete table */
+ if (repl) {
+ const BYTE *ptr = ip;
+ const BYTE *end;
+ end = ip + repl - (MINMATCH-1);
+ /* Pre-Load */
+ while (ptr < end - delta) {
+ chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
+ ptr++;
+ }
+ do {
+ chaintable[(size_t)(ptr) & MAXD_MASK] = delta;
+ /* Head of chain */
+ hashtable[HASH_VALUE(ptr)] = (ptr) - base;
+ ptr++;
+ } while (ptr < end);
+ hc4->nexttoupdate = end;
+ }
+
+ return (int)ml;
+}
+
+static inline int lz4hc_insertandgetwidermatch(struct lz4hc_data *hc4,
+ const u8 *ip, const u8 *startlimit, const u8 *matchlimit, int longest,
+ const u8 **matchpos, const u8 **startpos)
+{
+ u16 *const chaintable = hc4->chaintable;
+ HTYPE *const hashtable = hc4->hashtable;
+#if LZ4_ARCH64
+ const BYTE * const base = hc4->base;
+#else
+ const int base = 0;
+#endif
+ const u8 *ref;
+ int nbattempts = MAX_NB_ATTEMPTS;
+ int delta = (int)(ip - startlimit);
+
+ /* First Match */
+ lz4hc_insert(hc4, ip);
+ ref = hashtable[HASH_VALUE(ip)] + base;
+
+ while ((ref >= ip - MAX_DISTANCE) && (ref >= hc4->base)
+ && (nbattempts)) {
+ nbattempts--;
+ if (*(startlimit + longest) == *(ref - delta + longest)) {
+ if (A32(ref) == A32(ip)) {
+ const u8 *reft = ref + MINMATCH;
+ const u8 *ipt = ip + MINMATCH;
+ const u8 *startt = ip;
+
+ while (ipt < matchlimit-(STEPSIZE - 1)) {
+ #if LZ4_ARCH64
+ u64 diff = A64(reft) ^ A64(ipt);
+ #else
+ u32 diff = A32(reft) ^ A32(ipt);
+ #endif
+
+ if (!diff) {
+ ipt += STEPSIZE;
+ reft += STEPSIZE;
+ continue;
+ }
+ ipt += LZ4_NBCOMMONBYTES(diff);
+ goto _endcount;
+ }
+ #if LZ4_ARCH64
+ if ((ipt < (matchlimit - 3))
+ && (A32(reft) == A32(ipt))) {
+ ipt += 4;
+ reft += 4;
+ }
+ ipt += 2;
+ #endif
+ if ((ipt < (matchlimit - 1))
+ && (A16(reft) == A16(ipt))) {
+ reft += 2;
+ }
+ if ((ipt < matchlimit) && (*reft == *ipt))
+ ipt++;
+_endcount:
+ reft = ref;
+
+ while ((startt > startlimit)
+ && (reft > hc4->base)
+ && (startt[-1] == reft[-1])) {
+ startt--;
+ reft--;
+ }
+
+ if ((ipt - startt) > longest) {
+ longest = (int)(ipt - startt);
+ *matchpos = reft;
+ *startpos = startt;
+ }
+ }
+ }
+ ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK];
+ }
+ return longest;
+}
+
+static inline int lz4_encodesequence(const u8 **ip, u8 **op, const u8 **anchor,
+ int ml, const u8 *ref)
+{
+ int length, len;
+ u8 *token;
+
+ /* Encode Literal length */
+ length = (int)(*ip - *anchor);
+ token = (*op)++;
+ if (length >= (int)RUN_MASK) {
+ *token = (RUN_MASK << ML_BITS);
+ len = length - RUN_MASK;
+ for (; len > 254 ; len -= 255)
+ *(*op)++ = 255;
+ *(*op)++ = (u8)len;
+ } else
+ *token = (length << ML_BITS);
+
+ /* Copy Literals */
+ LZ4_BLINDCOPY(*anchor, *op, length);
+
+ /* Encode Offset */
+ LZ4_WRITE_LITTLEENDIAN_16(*op, (u16)(*ip - ref));
+
+ /* Encode MatchLength */
+ len = (int)(ml - MINMATCH);
+ if (len >= (int)ML_MASK) {
+ *token += ML_MASK;
+ len -= ML_MASK;
+ for (; len > 509 ; len -= 510) {
+ *(*op)++ = 255;
+ *(*op)++ = 255;
+ }
+ if (len > 254) {
+ len -= 255;
+ *(*op)++ = 255;
+ }
+ *(*op)++ = (u8)len;
+ } else
+ *token += len;
+
+ /* Prepare next loop */
+ *ip += ml;
+ *anchor = *ip;
+
+ return 0;
+}
+
+static int lz4_compresshcctx(struct lz4hc_data *ctx,
+ const char *source,
+ char *dest,
+ int isize)
+{
+ const u8 *ip = (const u8 *)source;
+ const u8 *anchor = ip;
+ const u8 *const iend = ip + isize;
+ const u8 *const mflimit = iend - MFLIMIT;
+ const u8 *const matchlimit = (iend - LASTLITERALS);
+
+ u8 *op = (u8 *)dest;
+
+ int ml, ml2, ml3, ml0;
+ const u8 *ref = NULL;
+ const u8 *start2 = NULL;
+ const u8 *ref2 = NULL;
+ const u8 *start3 = NULL;
+ const u8 *ref3 = NULL;
+ const u8 *start0;
+ const u8 *ref0;
+ int lastrun;
+
+ ip++;
+
+ /* Main Loop */
+ while (ip < mflimit) {
+ ml = lz4hc_insertandfindbestmatch(ctx, ip, matchlimit, (&ref));
+ if (!ml) {
+ ip++;
+ continue;
+ }
+
+ /* saved, in case we would skip too much */
+ start0 = ip;
+ ref0 = ref;
+ ml0 = ml;
+_search2:
+ if (ip+ml < mflimit)
+ ml2 = lz4hc_insertandgetwidermatch(ctx, ip + ml - 2,
+ ip + 1, matchlimit, ml, &ref2, &start2);
+ else
+ ml2 = ml;
+ /* No better match */
+ if (ml2 == ml) {
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ continue;
+ }
+
+ if (start0 < ip) {
+ /* empirical */
+ if (start2 < ip + ml0) {
+ ip = start0;
+ ref = ref0;
+ ml = ml0;
+ }
+ }
+ /*
+ * Here, start0==ip
+ * First Match too small : removed
+ */
+ if ((start2 - ip) < 3) {
+ ml = ml2;
+ ip = start2;
+ ref = ref2;
+ goto _search2;
+ }
+
+_search3:
+ /*
+ * Currently we have :
+ * ml2 > ml1, and
+ * ip1+3 <= ip2 (usually < ip1+ml1)
+ */
+ if ((start2 - ip) < OPTIMAL_ML) {
+ int correction;
+ int new_ml = ml;
+ if (new_ml > OPTIMAL_ML)
+ new_ml = OPTIMAL_ML;
+ if (ip + new_ml > start2 + ml2 - MINMATCH)
+ new_ml = (int)(start2 - ip) + ml2 - MINMATCH;
+ correction = new_ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ }
+ /*
+ * Now, we have start2 = ip+new_ml,
+ * with new_ml=min(ml, OPTIMAL_ML=18)
+ */
+ if (start2 + ml2 < mflimit)
+ ml3 = lz4hc_insertandgetwidermatch(ctx,
+ start2 + ml2 - 3, start2, matchlimit,
+ ml2, &ref3, &start3);
+ else
+ ml3 = ml2;
+
+ /* No better match : 2 sequences to encode */
+ if (ml3 == ml2) {
+ /* ip & ref are known; Now for ml */
+ if (start2 < ip+ml)
+ ml = (int)(start2 - ip);
+
+ /* Now, encode 2 sequences */
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ ip = start2;
+ lz4_encodesequence(&ip, &op, &anchor, ml2, ref2);
+ continue;
+ }
+
+ /* Not enough space for match 2 : remove it */
+ if (start3 < ip + ml + 3) {
+ /*
+ * can write Seq1 immediately ==> Seq2 is removed,
+ * so Seq3 becomes Seq1
+ */
+ if (start3 >= (ip + ml)) {
+ if (start2 < ip + ml) {
+ int correction =
+ (int)(ip + ml - start2);
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ if (ml2 < MINMATCH) {
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ }
+ }
+
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+ ip = start3;
+ ref = ref3;
+ ml = ml3;
+
+ start0 = start2;
+ ref0 = ref2;
+ ml0 = ml2;
+ goto _search2;
+ }
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+ goto _search3;
+ }
+
+ /*
+ * OK, now we have 3 ascending matches; let's write at least
+ * the first one ip & ref are known; Now for ml
+ */
+ if (start2 < ip + ml) {
+ if ((start2 - ip) < (int)ML_MASK) {
+ int correction;
+ if (ml > OPTIMAL_ML)
+ ml = OPTIMAL_ML;
+ if (ip + ml > start2 + ml2 - MINMATCH)
+ ml = (int)(start2 - ip) + ml2
+ - MINMATCH;
+ correction = ml - (int)(start2 - ip);
+ if (correction > 0) {
+ start2 += correction;
+ ref2 += correction;
+ ml2 -= correction;
+ }
+ } else
+ ml = (int)(start2 - ip);
+ }
+ lz4_encodesequence(&ip, &op, &anchor, ml, ref);
+
+ ip = start2;
+ ref = ref2;
+ ml = ml2;
+
+ start2 = start3;
+ ref2 = ref3;
+ ml2 = ml3;
+
+ goto _search3;
+ }
+
+ /* Encode Last Literals */
+ lastrun = (int)(iend - anchor);
+ if (lastrun >= (int)RUN_MASK) {
+ *op++ = (RUN_MASK << ML_BITS);
+ lastrun -= RUN_MASK;
+ for (; lastrun > 254 ; lastrun -= 255)
+ *op++ = 255;
+ *op++ = (u8) lastrun;
+ } else
+ *op++ = (lastrun << ML_BITS);
+ memcpy(op, anchor, iend - anchor);
+ op += iend - anchor;
+ /* End */
+ return (int) (((char *)op) - dest);
+}
+
+int lz4hc_compress(const unsigned char *src, size_t src_len,
+ unsigned char *dst, size_t *dst_len, void *wrkmem)
+{
+ int ret = -1;
+ int out_len = 0;
+
+ struct lz4hc_data *hc4 = (struct lz4hc_data *)wrkmem;
+ lz4hc_init(hc4, (const u8 *)src);
+ out_len = lz4_compresshcctx((struct lz4hc_data *)hc4, (const u8 *)src,
+ (char *)dst, (int)src_len);
+
+ if (out_len < 0)
+ goto exit;
+
+ *dst_len = out_len;
+ return 0;
+
+exit:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(lz4hc_compress);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZ4HC compressor");
struct scatterlist *sg, *prv;
unsigned int left;
+ memset(table, 0, sizeof(*table));
+
+ if (nents == 0)
+ return -EINVAL;
#ifndef ARCH_HAS_SG_CHAIN
if (WARN_ON_ONCE(nents > max_ents))
return -EINVAL;
#endif
- memset(table, 0, sizeof(*table));
-
left = nents;
prv = NULL;
do {
}
EXPORT_SYMBOL(sg_miter_start);
+static bool sg_miter_get_next_page(struct sg_mapping_iter *miter)
+{
+ if (!miter->__remaining) {
+ struct scatterlist *sg;
+ unsigned long pgoffset;
+
+ if (!__sg_page_iter_next(&miter->piter))
+ return false;
+
+ sg = miter->piter.sg;
+ pgoffset = miter->piter.sg_pgoffset;
+
+ miter->__offset = pgoffset ? 0 : sg->offset;
+ miter->__remaining = sg->offset + sg->length -
+ (pgoffset << PAGE_SHIFT) - miter->__offset;
+ miter->__remaining = min_t(unsigned long, miter->__remaining,
+ PAGE_SIZE - miter->__offset);
+ }
+
+ return true;
+}
+
+/**
+ * sg_miter_skip - reposition mapping iterator
+ * @miter: sg mapping iter to be skipped
+ * @offset: number of bytes to plus the current location
+ *
+ * Description:
+ * Sets the offset of @miter to its current location plus @offset bytes.
+ * If mapping iterator @miter has been proceeded by sg_miter_next(), this
+ * stops @miter.
+ *
+ * Context:
+ * Don't care if @miter is stopped, or not proceeded yet.
+ * Otherwise, preemption disabled if the SG_MITER_ATOMIC is set.
+ *
+ * Returns:
+ * true if @miter contains the valid mapping. false if end of sg
+ * list is reached.
+ */
+static bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset)
+{
+ sg_miter_stop(miter);
+
+ while (offset) {
+ off_t consumed;
+
+ if (!sg_miter_get_next_page(miter))
+ return false;
+
+ consumed = min_t(off_t, offset, miter->__remaining);
+ miter->__offset += consumed;
+ miter->__remaining -= consumed;
+ offset -= consumed;
+ }
+
+ return true;
+}
+
/**
* sg_miter_next - proceed mapping iterator to the next mapping
* @miter: sg mapping iter to proceed
* Get to the next page if necessary.
* __remaining, __offset is adjusted by sg_miter_stop
*/
- if (!miter->__remaining) {
- struct scatterlist *sg;
- unsigned long pgoffset;
-
- if (!__sg_page_iter_next(&miter->piter))
- return false;
-
- sg = miter->piter.sg;
- pgoffset = miter->piter.sg_pgoffset;
+ if (!sg_miter_get_next_page(miter))
+ return false;
- miter->__offset = pgoffset ? 0 : sg->offset;
- miter->__remaining = sg->offset + sg->length -
- (pgoffset << PAGE_SHIFT) - miter->__offset;
- miter->__remaining = min_t(unsigned long, miter->__remaining,
- PAGE_SIZE - miter->__offset);
- }
miter->page = sg_page_iter_page(&miter->piter);
miter->consumed = miter->length = miter->__remaining;
* @nents: Number of SG entries
* @buf: Where to copy from
* @buflen: The number of bytes to copy
- * @to_buffer: transfer direction (non zero == from an sg list to a
- * buffer, 0 == from a buffer to an sg list
+ * @skip: Number of bytes to skip before copying
+ * @to_buffer: transfer direction (true == from an sg list to a
+ * buffer, false == from a buffer to an sg list
*
* Returns the number of copied bytes.
*
**/
static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
- void *buf, size_t buflen, int to_buffer)
+ void *buf, size_t buflen, off_t skip,
+ bool to_buffer)
{
unsigned int offset = 0;
struct sg_mapping_iter miter;
sg_miter_start(&miter, sgl, nents, sg_flags);
+ if (!sg_miter_skip(&miter, skip))
+ return false;
+
local_irq_save(flags);
while (sg_miter_next(&miter) && offset < buflen) {
size_t sg_copy_from_buffer(struct scatterlist *sgl, unsigned int nents,
void *buf, size_t buflen)
{
- return sg_copy_buffer(sgl, nents, buf, buflen, 0);
+ return sg_copy_buffer(sgl, nents, buf, buflen, 0, false);
}
EXPORT_SYMBOL(sg_copy_from_buffer);
size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
void *buf, size_t buflen)
{
- return sg_copy_buffer(sgl, nents, buf, buflen, 1);
+ return sg_copy_buffer(sgl, nents, buf, buflen, 0, true);
}
EXPORT_SYMBOL(sg_copy_to_buffer);
+
+/**
+ * sg_pcopy_from_buffer - Copy from a linear buffer to an SG list
+ * @sgl: The SG list
+ * @nents: Number of SG entries
+ * @buf: Where to copy from
+ * @skip: Number of bytes to skip before copying
+ * @buflen: The number of bytes to copy
+ *
+ * Returns the number of copied bytes.
+ *
+ **/
+size_t sg_pcopy_from_buffer(struct scatterlist *sgl, unsigned int nents,
+ void *buf, size_t buflen, off_t skip)
+{
+ return sg_copy_buffer(sgl, nents, buf, buflen, skip, false);
+}
+EXPORT_SYMBOL(sg_pcopy_from_buffer);
+
+/**
+ * sg_pcopy_to_buffer - Copy from an SG list to a linear buffer
+ * @sgl: The SG list
+ * @nents: Number of SG entries
+ * @buf: Where to copy to
+ * @skip: Number of bytes to skip before copying
+ * @buflen: The number of bytes to copy
+ *
+ * Returns the number of copied bytes.
+ *
+ **/
+size_t sg_pcopy_to_buffer(struct scatterlist *sgl, unsigned int nents,
+ void *buf, size_t buflen, off_t skip)
+{
+ return sg_copy_buffer(sgl, nents, buf, buflen, skip, true);
+}
+EXPORT_SYMBOL(sg_pcopy_to_buffer);
struct address_space *mapping = file->f_mapping;
/* If we don't want any read-ahead, don't bother */
- if (VM_RandomReadHint(vma))
+ if (vma->vm_flags & VM_RAND_READ)
return;
if (!ra->ra_pages)
return;
- if (VM_SequentialReadHint(vma)) {
+ if (vma->vm_flags & VM_SEQ_READ) {
page_cache_sync_readahead(mapping, ra, file, offset,
ra->ra_pages);
return;
struct address_space *mapping = file->f_mapping;
/* If we don't want any read-ahead, don't bother */
- if (VM_RandomReadHint(vma))
+ if (vma->vm_flags & VM_RAND_READ)
return;
if (ra->mmap_miss > 0)
ra->mmap_miss--;
set_page_count(page, 1);
}
-static inline void __put_page(struct page *page)
-{
- atomic_dec(&page->_count);
-}
-
static inline void __get_page_tail_foll(struct page *page,
bool get_page_head)
{
/**
* __next_free_mem_range - next function for for_each_free_mem_range()
* @idx: pointer to u64 loop variable
- * @nid: nid: node selector, %MAX_NUMNODES for all nodes
+ * @nid: node selector, %MAX_NUMNODES for all nodes
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};
-struct mem_cgroup_lru_info {
- struct mem_cgroup_per_node *nodeinfo[0];
-};
-
/*
* Cgroups above their limits are maintained in a RB-Tree, independent of
* their hierarchy representation
/* vmpressure notifications */
struct vmpressure vmpressure;
- union {
- /*
- * the counter to account for mem+swap usage.
- */
- struct res_counter memsw;
-
- /*
- * rcu_freeing is used only when freeing struct mem_cgroup,
- * so put it into a union to avoid wasting more memory.
- * It must be disjoint from the css field. It could be
- * in a union with the res field, but res plays a much
- * larger part in mem_cgroup life than memsw, and might
- * be of interest, even at time of free, when debugging.
- * So share rcu_head with the less interesting memsw.
- */
- struct rcu_head rcu_freeing;
- /*
- * We also need some space for a worker in deferred freeing.
- * By the time we call it, rcu_freeing is no longer in use.
- */
- struct work_struct work_freeing;
- };
+ /*
+ * the counter to account for mem+swap usage.
+ */
+ struct res_counter memsw;
/*
* the counter to account for kernel memory usage.
bool oom_lock;
atomic_t under_oom;
- atomic_t refcnt;
-
int swappiness;
/* OOM-Killer disable */
int oom_kill_disable;
atomic_t numainfo_updating;
#endif
- /*
- * Per cgroup active and inactive list, similar to the
- * per zone LRU lists.
- *
- * WARNING: This has to be the last element of the struct. Don't
- * add new fields after this point.
- */
- struct mem_cgroup_lru_info info;
+ struct mem_cgroup_per_node *nodeinfo[0];
+ /* WARNING: nodeinfo must be the last member here */
};
static size_t memcg_size(void)
static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
{
+ /*
+ * Our caller must use css_get() first, because memcg_uncharge_kmem()
+ * will call css_put() if it sees the memcg is dead.
+ */
+ smp_wmb();
if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
}
*/
static DEFINE_MUTEX(memcg_create_mutex);
-static void mem_cgroup_get(struct mem_cgroup *memcg);
-static void mem_cgroup_put(struct mem_cgroup *memcg);
-
static inline
struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
{
*/
if (sk->sk_cgrp) {
BUG_ON(mem_cgroup_is_root(sk->sk_cgrp->memcg));
- mem_cgroup_get(sk->sk_cgrp->memcg);
+ css_get(&sk->sk_cgrp->memcg->css);
return;
}
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
cg_proto = sk->sk_prot->proto_cgroup(memcg);
- if (!mem_cgroup_is_root(memcg) && memcg_proto_active(cg_proto)) {
- mem_cgroup_get(memcg);
+ if (!mem_cgroup_is_root(memcg) &&
+ memcg_proto_active(cg_proto) && css_tryget(&memcg->css)) {
sk->sk_cgrp = cg_proto;
}
rcu_read_unlock();
struct mem_cgroup *memcg;
WARN_ON(!sk->sk_cgrp->memcg);
memcg = sk->sk_cgrp->memcg;
- mem_cgroup_put(memcg);
+ css_put(&sk->sk_cgrp->memcg->css);
}
}
mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
{
VM_BUG_ON((unsigned)nid >= nr_node_ids);
- return &memcg->info.nodeinfo[nid]->zoneinfo[zid];
+ return &memcg->nodeinfo[nid]->zoneinfo[zid];
}
struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
if (res_counter_uncharge(&memcg->kmem, size))
return;
+ /*
+ * Releases a reference taken in kmem_cgroup_css_offline in case
+ * this last uncharge is racing with the offlining code or it is
+ * outliving the memcg existence.
+ *
+ * The memory barrier imposed by test&clear is paired with the
+ * explicit one in memcg_kmem_mark_dead().
+ */
if (memcg_kmem_test_and_clear_dead(memcg))
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
}
void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep)
list_del(&s->memcg_params->list);
mutex_unlock(&memcg->slab_caches_mutex);
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
out:
kfree(s->memcg_params);
}
mutex_lock(&memcg_cache_mutex);
new_cachep = cachep->memcg_params->memcg_caches[idx];
- if (new_cachep)
+ if (new_cachep) {
+ css_put(&memcg->css);
goto out;
+ }
new_cachep = kmem_cache_dup(memcg, cachep);
if (new_cachep == NULL) {
new_cachep = cachep;
+ css_put(&memcg->css);
goto out;
}
- mem_cgroup_get(memcg);
atomic_set(&new_cachep->memcg_params->nr_pages , 0);
cachep->memcg_params->memcg_caches[idx] = new_cachep;
cw = container_of(w, struct create_work, work);
memcg_create_kmem_cache(cw->memcg, cw->cachep);
- /* Drop the reference gotten when we enqueued. */
- css_put(&cw->memcg->css);
kfree(cw);
}
int ret;
*_memcg = NULL;
+
+ /*
+ * Disabling accounting is only relevant for some specific memcg
+ * internal allocations. Therefore we would initially not have such
+ * check here, since direct calls to the page allocator that are marked
+ * with GFP_KMEMCG only happen outside memcg core. We are mostly
+ * concerned with cache allocations, and by having this test at
+ * memcg_kmem_get_cache, we are already able to relay the allocation to
+ * the root cache and bypass the memcg cache altogether.
+ *
+ * There is one exception, though: the SLUB allocator does not create
+ * large order caches, but rather service large kmallocs directly from
+ * the page allocator. Therefore, the following sequence when backed by
+ * the SLUB allocator:
+ *
+ * memcg_stop_kmem_account();
+ * kmalloc(<large_number>)
+ * memcg_resume_kmem_account();
+ *
+ * would effectively ignore the fact that we should skip accounting,
+ * since it will drive us directly to this function without passing
+ * through the cache selector memcg_kmem_get_cache. Such large
+ * allocations are extremely rare but can happen, for instance, for the
+ * cache arrays. We bring this test here.
+ */
+ if (!current->mm || current->memcg_kmem_skip_account)
+ return true;
+
memcg = try_get_mem_cgroup_from_mm(current->mm);
/*
unlock_page_cgroup(pc);
/*
* even after unlock, we have memcg->res.usage here and this memcg
- * will never be freed.
+ * will never be freed, so it's safe to call css_get().
*/
memcg_check_events(memcg, page);
if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) {
mem_cgroup_swap_statistics(memcg, true);
- mem_cgroup_get(memcg);
+ css_get(&memcg->css);
}
/*
* Migration does not charge the res_counter for the
/*
* record memcg information, if swapout && memcg != NULL,
- * mem_cgroup_get() was called in uncharge().
+ * css_get() was called in uncharge().
*/
if (do_swap_account && swapout && memcg)
swap_cgroup_record(ent, css_id(&memcg->css));
if (!mem_cgroup_is_root(memcg))
res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
mem_cgroup_swap_statistics(memcg, false);
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
}
rcu_read_unlock();
}
* This function is only called from task migration context now.
* It postpones res_counter and refcount handling till the end
* of task migration(mem_cgroup_clear_mc()) for performance
- * improvement. But we cannot postpone mem_cgroup_get(to)
- * because if the process that has been moved to @to does
- * swap-in, the refcount of @to might be decreased to 0.
+ * improvement. But we cannot postpone css_get(to) because if
+ * the process that has been moved to @to does swap-in, the
+ * refcount of @to might be decreased to 0.
+ *
+ * We are in attach() phase, so the cgroup is guaranteed to be
+ * alive, so we can just call css_get().
*/
- mem_cgroup_get(to);
+ css_get(&to->css);
return 0;
}
return -EINVAL;
* starts accounting before all call sites are patched
*/
memcg_kmem_set_active(memcg);
-
- /*
- * kmem charges can outlive the cgroup. In the case of slab
- * pages, for instance, a page contain objects from various
- * processes, so it is unfeasible to migrate them away. We
- * need to reference count the memcg because of that.
- */
- mem_cgroup_get(memcg);
} else
ret = res_counter_set_limit(&memcg->kmem, val);
out:
goto out;
/*
- * destroy(), called if we fail, will issue static_key_slow_inc() and
- * mem_cgroup_put() if kmem is enabled. We have to either call them
- * unconditionally, or clear the KMEM_ACTIVE flag. I personally find
- * this more consistent, since it always leads to the same destroy path
+ * __mem_cgroup_free() will issue static_key_slow_dec() because this
+ * memcg is active already. If the later initialization fails then the
+ * cgroup core triggers the cleanup so we do not have to do it here.
*/
- mem_cgroup_get(memcg);
static_key_slow_inc(&memcg_kmem_enabled_key);
mutex_lock(&set_limit_mutex);
+ memcg_stop_kmem_account();
ret = memcg_update_cache_sizes(memcg);
+ memcg_resume_kmem_account();
mutex_unlock(&set_limit_mutex);
out:
return ret;
return mem_cgroup_sockets_init(memcg, ss);
}
-static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
+static void memcg_destroy_kmem(struct mem_cgroup *memcg)
{
mem_cgroup_sockets_destroy(memcg);
+}
+
+static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
+{
+ if (!memcg_kmem_is_active(memcg))
+ return;
+
+ /*
+ * kmem charges can outlive the cgroup. In the case of slab
+ * pages, for instance, a page contain objects from various
+ * processes. As we prevent from taking a reference for every
+ * such allocation we have to be careful when doing uncharge
+ * (see memcg_uncharge_kmem) and here during offlining.
+ *
+ * The idea is that that only the _last_ uncharge which sees
+ * the dead memcg will drop the last reference. An additional
+ * reference is taken here before the group is marked dead
+ * which is then paired with css_put during uncharge resp. here.
+ *
+ * Although this might sound strange as this path is called from
+ * css_offline() when the referencemight have dropped down to 0
+ * and shouldn't be incremented anymore (css_tryget would fail)
+ * we do not have other options because of the kmem allocations
+ * lifetime.
+ */
+ css_get(&memcg->css);
memcg_kmem_mark_dead(memcg);
if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
return;
- /*
- * Charges already down to 0, undo mem_cgroup_get() done in the charge
- * path here, being careful not to race with memcg_uncharge_kmem: it is
- * possible that the charges went down to 0 between mark_dead and the
- * res_counter read, so in that case, we don't need the put
- */
if (memcg_kmem_test_and_clear_dead(memcg))
- mem_cgroup_put(memcg);
+ css_put(&memcg->css);
}
#else
static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
return 0;
}
-static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
+static void memcg_destroy_kmem(struct mem_cgroup *memcg)
+{
+}
+
+static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
{
}
#endif
mz->on_tree = false;
mz->memcg = memcg;
}
- memcg->info.nodeinfo[node] = pn;
+ memcg->nodeinfo[node] = pn;
return 0;
}
static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
{
- kfree(memcg->info.nodeinfo[node]);
+ kfree(memcg->nodeinfo[node]);
}
static struct mem_cgroup *mem_cgroup_alloc(void)
vfree(memcg);
}
-
-/*
- * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
- * but in process context. The work_freeing structure is overlaid
- * on the rcu_freeing structure, which itself is overlaid on memsw.
- */
-static void free_work(struct work_struct *work)
-{
- struct mem_cgroup *memcg;
-
- memcg = container_of(work, struct mem_cgroup, work_freeing);
- __mem_cgroup_free(memcg);
-}
-
-static void free_rcu(struct rcu_head *rcu_head)
-{
- struct mem_cgroup *memcg;
-
- memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
- INIT_WORK(&memcg->work_freeing, free_work);
- schedule_work(&memcg->work_freeing);
-}
-
-static void mem_cgroup_get(struct mem_cgroup *memcg)
-{
- atomic_inc(&memcg->refcnt);
-}
-
-static void __mem_cgroup_put(struct mem_cgroup *memcg, int count)
-{
- if (atomic_sub_and_test(count, &memcg->refcnt)) {
- struct mem_cgroup *parent = parent_mem_cgroup(memcg);
- call_rcu(&memcg->rcu_freeing, free_rcu);
- if (parent)
- mem_cgroup_put(parent);
- }
-}
-
-static void mem_cgroup_put(struct mem_cgroup *memcg)
-{
- __mem_cgroup_put(memcg, 1);
-}
-
/*
* Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
*/
memcg->last_scanned_node = MAX_NUMNODES;
INIT_LIST_HEAD(&memcg->oom_notify);
- atomic_set(&memcg->refcnt, 1);
memcg->move_charge_at_immigrate = 0;
mutex_init(&memcg->thresholds_lock);
spin_lock_init(&memcg->move_lock);
res_counter_init(&memcg->kmem, &parent->kmem);
/*
- * We increment refcnt of the parent to ensure that we can
- * safely access it on res_counter_charge/uncharge.
- * This refcnt will be decremented when freeing this
- * mem_cgroup(see mem_cgroup_put).
+ * No need to take a reference to the parent because cgroup
+ * core guarantees its existence.
*/
- mem_cgroup_get(parent);
} else {
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
mutex_unlock(&memcg_create_mutex);
- if (error) {
- /*
- * We call put now because our (and parent's) refcnts
- * are already in place. mem_cgroup_put() will internally
- * call __mem_cgroup_free, so return directly
- */
- mem_cgroup_put(memcg);
- if (parent->use_hierarchy)
- mem_cgroup_put(parent);
- }
return error;
}
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ kmem_cgroup_css_offline(memcg);
+
mem_cgroup_invalidate_reclaim_iterators(memcg);
mem_cgroup_reparent_charges(memcg);
mem_cgroup_destroy_all_caches(memcg);
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
- kmem_cgroup_destroy(memcg);
-
- mem_cgroup_put(memcg);
+ memcg_destroy_kmem(memcg);
+ __mem_cgroup_free(memcg);
}
#ifdef CONFIG_MMU
{
struct mem_cgroup *from = mc.from;
struct mem_cgroup *to = mc.to;
+ int i;
/* we must uncharge all the leftover precharges from mc.to */
if (mc.precharge) {
if (!mem_cgroup_is_root(mc.from))
res_counter_uncharge(&mc.from->memsw,
PAGE_SIZE * mc.moved_swap);
- __mem_cgroup_put(mc.from, mc.moved_swap);
+
+ for (i = 0; i < mc.moved_swap; i++)
+ css_put(&mc.from->css);
if (!mem_cgroup_is_root(mc.to)) {
/*
res_counter_uncharge(&mc.to->res,
PAGE_SIZE * mc.moved_swap);
}
- /* we've already done mem_cgroup_get(mc.to) */
+ /* we've already done css_get(mc.to) */
mc.moved_swap = 0;
}
memcg_oom_recover(from);
if (pte_dirty(ptent))
set_page_dirty(page);
if (pte_young(ptent) &&
- likely(!VM_SequentialReadHint(vma)))
+ likely(!(vma->vm_flags & VM_SEQ_READ)))
mark_page_accessed(page);
rss[MM_FILEPAGES]--;
}
pfn = pgdat->node_start_pfn;
end_pfn = pgdat_end_pfn(pgdat);
- /* register_section info */
+ /* register section info */
for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
/*
* Some platforms can assign the same pfn to multiple nodes - on
* node0 as well as nodeN. To avoid registering a pfn against
* multiple nodes we check that this pfn does not already
- * reside in some other node.
+ * reside in some other nodes.
*/
if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
register_page_bootmem_info_section(pfn);
if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) &&
!can_online_high_movable(zone)) {
unlock_memory_hotplug();
- return -1;
+ return -EINVAL;
}
if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
unlock_memory_hotplug();
- return -1;
+ return -EINVAL;
}
}
if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) {
unlock_memory_hotplug();
- return -1;
+ return -EINVAL;
}
}
if (!(flags & MAP_ANONYMOUS)) {
audit_mmap_fd(fd, flags);
- if (unlikely(flags & MAP_HUGETLB))
- return -EINVAL;
file = fget(fd);
if (!file)
goto out;
if (is_file_hugepages(file))
len = ALIGN(len, huge_page_size(hstate_file(file)));
+ retval = -EINVAL;
+ if (unlikely(flags & MAP_HUGETLB && !is_file_hugepages(file)))
+ goto out_fput;
} else if (flags & MAP_HUGETLB) {
struct user_struct *user = NULL;
- struct hstate *hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) &
- SHM_HUGE_MASK);
+ struct hstate *hs;
+ hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & SHM_HUGE_MASK);
if (!hs)
return -EINVAL;
flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);
retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff);
+out_fput:
if (file)
fput(file);
out:
unsigned long charged = 0;
bool locked = false;
- down_write(¤t->mm->mmap_sem);
-
if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
- goto out;
+ return ret;
+
+ if (flags & MREMAP_FIXED && !(flags & MREMAP_MAYMOVE))
+ return ret;
if (addr & ~PAGE_MASK)
- goto out;
+ return ret;
old_len = PAGE_ALIGN(old_len);
new_len = PAGE_ALIGN(new_len);
* a zero new-len is nonsensical.
*/
if (!new_len)
- goto out;
+ return ret;
+
+ down_write(¤t->mm->mmap_sem);
if (flags & MREMAP_FIXED) {
- if (flags & MREMAP_MAYMOVE)
- ret = mremap_to(addr, old_len, new_addr, new_len,
- &locked);
+ ret = mremap_to(addr, old_len, new_addr, new_len,
+ &locked);
goto out;
}
};
int min_free_kbytes = 1024;
+int user_min_free_kbytes;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
* MIGRATE_CMA areas.
*/
if (!is_migrate_cma(migratetype) &&
- (unlikely(current_order >= pageblock_order / 2) ||
+ (current_order >= pageblock_order / 2 ||
start_migratetype == MIGRATE_RECLAIMABLE ||
page_group_by_mobility_disabled)) {
int pages;
* Add all populated zones of a node to the zonelist.
*/
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
- int nr_zones, enum zone_type zone_type)
+ int nr_zones)
{
struct zone *zone;
-
- BUG_ON(zone_type >= MAX_NR_ZONES);
- zone_type++;
+ enum zone_type zone_type = MAX_NR_ZONES;
do {
zone_type--;
&zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
-
} while (zone_type);
+
return nr_zones;
}
zonelist = &pgdat->node_zonelists[0];
for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j,
- MAX_NR_ZONES - 1);
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j);
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
struct zonelist *zonelist;
zonelist = &pgdat->node_zonelists[1];
- j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+ j = build_zonelists_node(pgdat, zonelist, 0);
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
local_node = pgdat->node_id;
zonelist = &pgdat->node_zonelists[0];
- j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+ j = build_zonelists_node(pgdat, zonelist, 0);
/*
* Now we build the zonelist so that it contains the zones
for (node = local_node + 1; node < MAX_NUMNODES; node++) {
if (!node_online(node))
continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j,
- MAX_NR_ZONES - 1);
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j);
}
for (node = 0; node < local_node; node++) {
if (!node_online(node))
continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j,
- MAX_NR_ZONES - 1);
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j);
}
zonelist->_zonerefs[j].zone = NULL;
*/
static unsigned long __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *ignored)
{
- unsigned long node_start_pfn, node_end_pfn;
unsigned long zone_start_pfn, zone_end_pfn;
- /* Get the start and end of the node and zone */
- get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
+ /* Get the start and end of the zone */
zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
adjust_zone_range_for_zone_movable(nid, zone_type,
/* Return the number of page frames in holes in a zone on a node */
static unsigned long __meminit zone_absent_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *ignored)
{
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
- unsigned long node_start_pfn, node_end_pfn;
unsigned long zone_start_pfn, zone_end_pfn;
- get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *zones_size)
{
return zones_size[zone_type];
static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *zholes_size)
{
if (!zholes_size)
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
- unsigned long *zones_size, unsigned long *zholes_size)
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
+ unsigned long *zones_size,
+ unsigned long *zholes_size)
{
unsigned long realtotalpages, totalpages = 0;
enum zone_type i;
for (i = 0; i < MAX_NR_ZONES; i++)
totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
- zones_size);
+ node_start_pfn,
+ node_end_pfn,
+ zones_size);
pgdat->node_spanned_pages = totalpages;
realtotalpages = totalpages;
for (i = 0; i < MAX_NR_ZONES; i++)
realtotalpages -=
zone_absent_pages_in_node(pgdat->node_id, i,
- zholes_size);
+ node_start_pfn, node_end_pfn,
+ zholes_size);
pgdat->node_present_pages = realtotalpages;
printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
realtotalpages);
* NOTE: pgdat should get zeroed by caller.
*/
static void __paginginit free_area_init_core(struct pglist_data *pgdat,
+ unsigned long node_start_pfn, unsigned long node_end_pfn,
unsigned long *zones_size, unsigned long *zholes_size)
{
enum zone_type j;
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
- size = zone_spanned_pages_in_node(nid, j, zones_size);
+ size = zone_spanned_pages_in_node(nid, j, node_start_pfn,
+ node_end_pfn, zones_size);
realsize = freesize = size - zone_absent_pages_in_node(nid, j,
+ node_start_pfn,
+ node_end_pfn,
zholes_size);
/*
unsigned long node_start_pfn, unsigned long *zholes_size)
{
pg_data_t *pgdat = NODE_DATA(nid);
+ unsigned long start_pfn = 0;
+ unsigned long end_pfn = 0;
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
init_zone_allows_reclaim(nid);
- calculate_node_totalpages(pgdat, zones_size, zholes_size);
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+#endif
+ calculate_node_totalpages(pgdat, start_pfn, end_pfn,
+ zones_size, zholes_size);
alloc_node_mem_map(pgdat);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
(unsigned long)pgdat->node_mem_map);
#endif
- free_area_init_core(pgdat, zones_size, zholes_size);
+ free_area_init_core(pgdat, start_pfn, end_pfn,
+ zones_size, zholes_size);
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int __meminit init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
+ int new_min_free_kbytes;
lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
-
- min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
- if (min_free_kbytes < 128)
- min_free_kbytes = 128;
- if (min_free_kbytes > 65536)
- min_free_kbytes = 65536;
+ new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
+
+ if (new_min_free_kbytes > user_min_free_kbytes) {
+ min_free_kbytes = new_min_free_kbytes;
+ if (min_free_kbytes < 128)
+ min_free_kbytes = 128;
+ if (min_free_kbytes > 65536)
+ min_free_kbytes = 65536;
+ } else {
+ pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
+ new_min_free_kbytes, user_min_free_kbytes);
+ }
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, buffer, length, ppos);
- if (write)
+ if (write) {
+ user_min_free_kbytes = min_free_kbytes;
setup_per_zone_wmarks();
+ }
return 0;
}
* mapping is already gone, the unmap path will have
* set PG_referenced or activated the page.
*/
- if (likely(!VM_SequentialReadHint(vma)))
+ if (likely(!(vma->vm_flags & VM_SEQ_READ)))
referenced++;
}
pte_unmap_unlock(pte, ptl);
return ret;
}
+#ifdef CONFIG_MEMORY_HOTREMOVE
#ifdef CONFIG_MEMORY_FAILURE
static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
{
}
#endif
-#ifdef CONFIG_MEMORY_HOTREMOVE
static void free_section_usemap(struct page *memmap, unsigned long *usemap)
{
struct page *usemap_page;
addr = ALIGN(first->va_end, align);
if (addr < vstart)
goto nocache;
- if (addr + size - 1 < addr)
+ if (addr + size < addr)
goto overflow;
} else {
addr = ALIGN(vstart, align);
- if (addr + size - 1 < addr)
+ if (addr + size < addr)
goto overflow;
n = vmap_area_root.rb_node;
if (addr + cached_hole_size < first->va_start)
cached_hole_size = first->va_start - addr;
addr = ALIGN(first->va_end, align);
- if (addr + size - 1 < addr)
+ if (addr + size < addr)
goto overflow;
if (list_is_last(&first->list, &vmap_area_list))
struct vmap_area *va;
struct vmap_block_queue *vbq;
unsigned long free, dirty;
- DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS);
DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
struct list_head free_list;
struct rcu_head rcu_head;
vb->va = va;
vb->free = VMAP_BBMAP_BITS;
vb->dirty = 0;
- bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS);
bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS);
INIT_LIST_HEAD(&vb->free_list);
if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) {
vb->free = 0; /* prevent further allocs after releasing lock */
vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */
- bitmap_fill(vb->alloc_map, VMAP_BBMAP_BITS);
bitmap_fill(vb->dirty_map, VMAP_BBMAP_BITS);
spin_lock(&vbq->lock);
list_del_rcu(&vb->free_list);
}
}
-static void purge_fragmented_blocks_thiscpu(void)
-{
- purge_fragmented_blocks(smp_processor_id());
-}
-
static void purge_fragmented_blocks_allcpus(void)
{
int cpu;
struct vmap_block *vb;
unsigned long addr = 0;
unsigned int order;
- int purge = 0;
BUG_ON(size & ~PAGE_MASK);
BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
if (vb->free < 1UL << order)
goto next;
- i = bitmap_find_free_region(vb->alloc_map,
- VMAP_BBMAP_BITS, order);
-
- if (i < 0) {
- if (vb->free + vb->dirty == VMAP_BBMAP_BITS) {
- /* fragmented and no outstanding allocations */
- BUG_ON(vb->dirty != VMAP_BBMAP_BITS);
- purge = 1;
- }
- goto next;
- }
+ i = VMAP_BBMAP_BITS - vb->free;
addr = vb->va->va_start + (i << PAGE_SHIFT);
BUG_ON(addr_to_vb_idx(addr) !=
addr_to_vb_idx(vb->va->va_start));
spin_unlock(&vb->lock);
}
- if (purge)
- purge_fragmented_blocks_thiscpu();
-
put_cpu_var(vmap_block_queue);
rcu_read_unlock();
spin_unlock(&vmap_area_lock);
}
-static void clear_vm_unlist(struct vm_struct *vm)
+static void clear_vm_uninitialized_flag(struct vm_struct *vm)
{
/*
- * Before removing VM_UNLIST,
+ * Before removing VM_UNINITIALIZED,
* we should make sure that vm has proper values.
* Pair with smp_rmb() in show_numa_info().
*/
smp_wmb();
- vm->flags &= ~VM_UNLIST;
+ vm->flags &= ~VM_UNINITIALIZED;
}
static struct vm_struct *__get_vm_area_node(unsigned long size,
return;
if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
- addr));
+ addr))
return;
area = remove_vm_area(addr);
* conventions for vfree() arch-depenedent would be a really bad idea)
*
* NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
- *
*/
void vfree(const void *addr)
{
return;
if (unlikely(in_interrupt())) {
struct vfree_deferred *p = &__get_cpu_var(vfree_deferred);
- llist_add((struct llist_node *)addr, &p->list);
- schedule_work(&p->wq);
+ if (llist_add((struct llist_node *)addr, &p->list))
+ schedule_work(&p->wq);
} else
__vunmap(addr, 1);
}
if (!size || (size >> PAGE_SHIFT) > totalram_pages)
goto fail;
- area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNLIST,
+ area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED,
start, end, node, gfp_mask, caller);
if (!area)
goto fail;
addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
if (!addr)
- return NULL;
+ goto fail;
/*
- * In this function, newly allocated vm_struct has VM_UNLIST flag.
- * It means that vm_struct is not fully initialized.
+ * In this function, newly allocated vm_struct has VM_UNINITIALIZED
+ * flag. It means that vm_struct is not fully initialized.
* Now, it is fully initialized, so remove this flag here.
*/
- clear_vm_unlist(area);
+ clear_vm_uninitialized_flag(area);
/*
* A ref_count = 3 is needed because the vm_struct and vmap_area
if (!counters)
return;
- /* Pair with smp_wmb() in clear_vm_unlist() */
- smp_rmb();
- if (v->flags & VM_UNLIST)
- return;
-
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
for (nr = 0; nr < v->nr_pages; nr++)
v = va->vm;
+ /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
+ smp_rmb();
+ if (v->flags & VM_UNINITIALIZED)
+ return 0;
+
seq_printf(m, "0x%pK-0x%pK %7ld",
v->addr, v->addr + v->size, v->size);
* as there is no guarantee the dirtying process is throttled in the
* same way balance_dirty_pages() manages.
*
- * This scales the number of dirty pages that must be under writeback
- * before a zone gets flagged ZONE_WRITEBACK. It is a simple backoff
- * function that has the most effect in the range DEF_PRIORITY to
- * DEF_PRIORITY-2 which is the priority reclaim is considered to be
- * in trouble and reclaim is considered to be in trouble.
- *
- * DEF_PRIORITY 100% isolated pages must be PageWriteback to throttle
- * DEF_PRIORITY-1 50% must be PageWriteback
- * DEF_PRIORITY-2 25% must be PageWriteback, kswapd in trouble
- * ...
- * DEF_PRIORITY-6 For SWAP_CLUSTER_MAX isolated pages, throttle if any
- * isolated page is PageWriteback
- *
* Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number
* of pages under pages flagged for immediate reclaim and stall if any
* are encountered in the nr_immediate check below.
*/
- if (nr_writeback && nr_writeback >=
- (nr_taken >> (DEF_PRIORITY - sc->priority)))
+ if (nr_writeback && nr_writeback == nr_taken)
zone_set_flag(zone, ZONE_WRITEBACK);
/*
aborted_reclaim = shrink_zones(zonelist, sc);
/*
- * Don't shrink slabs when reclaiming memory from
- * over limit cgroups
+ * Don't shrink slabs when reclaiming memory from over limit
+ * cgroups but do shrink slab at least once when aborting
+ * reclaim for compaction to avoid unevenly scanning file/anon
+ * LRU pages over slab pages.
*/
if (global_reclaim(sc)) {
unsigned long lru_pages = 0;
WB_REASON_TRY_TO_FREE_PAGES);
sc->may_writepage = 1;
}
- } while (--sc->priority >= 0);
+ } while (--sc->priority >= 0 && !aborted_reclaim);
out:
delayacct_freepages_end();
lzop -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
(rm -f $@ ; false)
+quiet_cmd_lz4 = LZ4 $@
+cmd_lz4 = (cat $(filter-out FORCE,$^) | \
+ lz4c -l -c1 stdin stdout && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
+ (rm -f $@ ; false)
+
# U-Boot mkimage
# ---------------------------------------------------------------------------
# Licensed under the terms of the GNU GPL License version 2
use strict;
+use POSIX;
my $P = $0;
$P =~ s@.*/@@g;
return if ($camelcase_seeded);
my $files;
- my $camelcase_git_file = "";
+ my $camelcase_cache = "";
+ my @include_files = ();
+
+ $camelcase_seeded = 1;
if (-d ".git") {
my $git_last_include_commit = `git log --no-merges --pretty=format:"%h%n" -1 -- include`;
chomp $git_last_include_commit;
- $camelcase_git_file = ".checkpatch-camelcase.$git_last_include_commit";
- if (-f $camelcase_git_file) {
- open(my $camelcase_file, '<', "$camelcase_git_file")
- or warn "$P: Can't read '$camelcase_git_file' $!\n";
- while (<$camelcase_file>) {
- chomp;
- $camelcase{$_} = 1;
- }
- close($camelcase_file);
-
- return;
- }
- $files = `git ls-files include`;
+ $camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit";
} else {
+ my $last_mod_date = 0;
$files = `find $root/include -name "*.h"`;
+ @include_files = split('\n', $files);
+ foreach my $file (@include_files) {
+ my $date = POSIX::strftime("%Y%m%d%H%M",
+ localtime((stat $file)[9]));
+ $last_mod_date = $date if ($last_mod_date < $date);
+ }
+ $camelcase_cache = ".checkpatch-camelcase.date.$last_mod_date";
+ }
+
+ if ($camelcase_cache ne "" && -f $camelcase_cache) {
+ open(my $camelcase_file, '<', "$camelcase_cache")
+ or warn "$P: Can't read '$camelcase_cache' $!\n";
+ while (<$camelcase_file>) {
+ chomp;
+ $camelcase{$_} = 1;
+ }
+ close($camelcase_file);
+
+ return;
+ }
+
+ if (-d ".git") {
+ $files = `git ls-files "include/*.h"`;
+ @include_files = split('\n', $files);
}
- my @include_files = split('\n', $files);
+
foreach my $file (@include_files) {
seed_camelcase_file($file);
}
- $camelcase_seeded = 1;
- if ($camelcase_git_file ne "") {
+ if ($camelcase_cache ne "") {
unlink glob ".checkpatch-camelcase.*";
- open(my $camelcase_file, '>', "$camelcase_git_file")
- or warn "$P: Can't write '$camelcase_git_file' $!\n";
+ open(my $camelcase_file, '>', "$camelcase_cache")
+ or warn "$P: Can't write '$camelcase_cache' $!\n";
foreach (sort { lc($a) cmp lc($b) } keys(%camelcase)) {
print $camelcase_file ("$_\n");
}
Support loading of a LZO encoded initial ramdisk or cpio buffer
If unsure, say N.
+config RD_LZ4
+ bool "Support initial ramdisks compressed using LZ4" if EXPERT
+ default !EXPERT
+ depends on BLK_DEV_INITRD
+ select DECOMPRESS_LZ4
+ help
+ Support loading of a LZ4 encoded initial ramdisk or cpio buffer
+ If unsure, say N.
+
choice
prompt "Built-in initramfs compression mode" if INITRAMFS_SOURCE!=""
help