diff options
163 files changed, 1559 insertions, 1413 deletions
diff --git a/Documentation/devicetree/bindings/rtc/rtc-opal.txt b/Documentation/devicetree/bindings/rtc/rtc-opal.txt new file mode 100644 index 000000000000..af87e5ecac54 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/rtc-opal.txt @@ -0,0 +1,16 @@ +IBM OPAL real-time clock +------------------------ + +Required properties: +- comapatible: Should be "ibm,opal-rtc" + +Optional properties: +- has-tpo: Decides if the wakeup is supported or not. + +Example: + rtc { + compatible = "ibm,opal-rtc"; + has-tpo; + phandle = <0x10000029>; + linux,phandle = <0x10000029>; + }; diff --git a/MAINTAINERS b/MAINTAINERS index 3c6427190be2..5d6136b8959e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1543,6 +1543,7 @@ F: arch/arm/mach-pxa/include/mach/z2.h ARM/ZYNQ ARCHITECTURE M: Michal Simek <michal.simek@xilinx.com> +R: Sören Brinkmann <soren.brinkmann@xilinx.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) W: http://wiki.xilinx.com T: git git://git.xilinx.com/linux-xlnx.git @@ -7179,6 +7180,7 @@ F: drivers/crypto/picoxcell* PIN CONTROL SUBSYSTEM M: Linus Walleij <linus.walleij@linaro.org> +L: linux-gpio@vger.kernel.org S: Maintained F: drivers/pinctrl/ F: include/linux/pinctrl/ @@ -8483,7 +8485,6 @@ F: arch/arm/mach-s3c24xx/bast-irq.c TI DAVINCI MACHINE SUPPORT M: Sekhar Nori <nsekhar@ti.com> M: Kevin Hilman <khilman@deeprootsystems.com> -L: davinci-linux-open-source@linux.davincidsp.com (moderated for non-subscribers) T: git git://gitorious.org/linux-davinci/linux-davinci.git Q: http://patchwork.kernel.org/project/linux-davinci/list/ S: Supported @@ -8493,7 +8494,6 @@ F: drivers/i2c/busses/i2c-davinci.c TI DAVINCI SERIES MEDIA DRIVER M: Lad, Prabhakar <prabhakar.csengg@gmail.com> L: linux-media@vger.kernel.org -L: davinci-linux-open-source@linux.davincidsp.com (moderated for non-subscribers) W: http://linuxtv.org/ Q: http://patchwork.linuxtv.org/project/linux-media/list/ T: git git://linuxtv.org/mhadli/v4l-dvb-davinci_devices.git diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 03dc4c1a8736..d8f6a2ec3d4e 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -1187,7 +1187,7 @@ config DEBUG_UART_VIRT default 0xf1c28000 if DEBUG_SUNXI_UART0 default 0xf1c28400 if DEBUG_SUNXI_UART1 default 0xf1f02800 if DEBUG_SUNXI_R_UART - default 0xf2100000 if DEBUG_PXA_UART1 + default 0xf6200000 if DEBUG_PXA_UART1 default 0xf4090000 if ARCH_LPC32XX default 0xf4200000 if ARCH_GEMINI default 0xf7000000 if DEBUG_S3C24XX_UART && (DEBUG_S3C_UART0 || \ diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index f1dc7fc668f3..3487046d8a78 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -235,6 +235,7 @@ CONFIG_SPI_TEGRA20_SLINK=y CONFIG_SPI_XILINX=y CONFIG_PINCTRL_AS3722=y CONFIG_PINCTRL_PALMAS=y +CONFIG_PINCTRL_APQ8084=y CONFIG_GPIO_SYSFS=y CONFIG_GPIO_GENERIC_PLATFORM=y CONFIG_GPIO_DWAPB=y @@ -411,6 +412,7 @@ CONFIG_NVEC_POWER=y CONFIG_NVEC_PAZ00=y CONFIG_QCOM_GSBI=y CONFIG_COMMON_CLK_QCOM=y +CONFIG_APQ_MMCC_8084=y CONFIG_MSM_GCC_8660=y CONFIG_MSM_MMCC_8960=y CONFIG_MSM_MMCC_8974=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 16e719c268dd..b3f86670d2eb 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -86,7 +86,6 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y # CONFIG_INET_LRO is not set -CONFIG_IPV6=y CONFIG_NETFILTER=y CONFIG_CAN=m CONFIG_CAN_C_CAN=m @@ -112,6 +111,7 @@ CONFIG_MTD_OOPS=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_ECC_BCH=y CONFIG_MTD_NAND_OMAP2=y CONFIG_MTD_ONENAND=y CONFIG_MTD_ONENAND_VERIFY_WRITE=y @@ -317,7 +317,7 @@ CONFIG_EXT4_FS=y CONFIG_FANOTIFY=y CONFIG_QUOTA=y CONFIG_QFMT_V2=y -CONFIG_AUTOFS4_FS=y +CONFIG_AUTOFS4_FS=m CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y diff --git a/arch/arm/configs/socfpga_defconfig b/arch/arm/configs/socfpga_defconfig index d7a5855a5db8..a2956c3112f1 100644 --- a/arch/arm/configs/socfpga_defconfig +++ b/arch/arm/configs/socfpga_defconfig @@ -1,5 +1,6 @@ -CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y +CONFIG_FHANDLE=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -11,23 +12,17 @@ CONFIG_PROFILING=y CONFIG_OPROFILE=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y -CONFIG_HOTPLUG=y # CONFIG_LBDAF is not set # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARCH_SOCFPGA=y -CONFIG_MACH_SOCFPGA_CYCLONE5=y CONFIG_ARM_THUMBEE=y -# CONFIG_ARCH_VEXPRESS_CORTEX_A5_A9_ERRATA is not set -# CONFIG_CACHE_L2X0 is not set -CONFIG_HIGH_RES_TIMERS=y CONFIG_SMP=y CONFIG_NR_CPUS=2 CONFIG_AEABI=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 -CONFIG_CMDLINE="" CONFIG_VFP=y CONFIG_NEON=y CONFIG_NET=y @@ -41,38 +36,30 @@ CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y +CONFIG_IPV6=y +CONFIG_NETWORK_PHY_TIMESTAMPING=y +CONFIG_VLAN_8021Q=y +CONFIG_VLAN_8021Q_GVRP=y CONFIG_CAN=y -CONFIG_CAN_RAW=y -CONFIG_CAN_BCM=y -CONFIG_CAN_GW=y -CONFIG_CAN_DEV=y -CONFIG_CAN_CALC_BITTIMING=y CONFIG_CAN_C_CAN=y CONFIG_CAN_C_CAN_PLATFORM=y CONFIG_CAN_DEBUG_DEVICES=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y -CONFIG_PROC_DEVICETREE=y +CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_SRAM=y CONFIG_SCSI=y # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y # CONFIG_SCSI_LOWLEVEL is not set CONFIG_NETDEVICES=y CONFIG_STMMAC_ETH=y +CONFIG_DWMAC_SOCFPGA=y CONFIG_MICREL_PHY=y -# CONFIG_STMMAC_PHY_ID_ZERO_WORKAROUND is not set CONFIG_INPUT_EVDEV=y -CONFIG_DWMAC_SOCFPGA=y -CONFIG_PPS=y -CONFIG_NETWORK_PHY_TIMESTAMPING=y -CONFIG_PTP_1588_CLOCK=y -CONFIG_VLAN_8021Q=y -CONFIG_VLAN_8021Q_GVRP=y -CONFIG_GARP=y -CONFIG_IPV6=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_AMBAKMI=y CONFIG_LEGACY_PTY_COUNT=16 @@ -81,45 +68,43 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 CONFIG_SERIAL_8250_RUNTIME_UARTS=2 CONFIG_SERIAL_8250_DW=y +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y CONFIG_GPIO_DWAPB=y -# CONFIG_RTC_HCTOSYS is not set +CONFIG_PMBUS=y +CONFIG_SENSORS_LTC2978=y +CONFIG_SENSORS_LTC2978_REGULATOR=y CONFIG_WATCHDOG=y CONFIG_DW_WATCHDOG=y +CONFIG_REGULATOR=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y +CONFIG_USB=y +CONFIG_USB_DWC2=y +CONFIG_USB_DWC2_HOST=y +CONFIG_MMC=y +CONFIG_MMC_DW=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT3_FS=y -CONFIG_NFS_FS=y -CONFIG_ROOT_NFS=y -# CONFIG_DNOTIFY is not set -# CONFIG_INOTIFY_USER is not set -CONFIG_FHANDLE=y +CONFIG_EXT4_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_NTFS_RW=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y +CONFIG_CONFIGFS_FS=y +CONFIG_NFS_FS=y +CONFIG_ROOT_NFS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set -CONFIG_DEBUG_INFO=y CONFIG_ENABLE_DEFAULT_TRACERS=y CONFIG_DEBUG_USER=y CONFIG_XZ_DEC=y -CONFIG_I2C=y -CONFIG_I2C_DESIGNWARE_CORE=y -CONFIG_I2C_DESIGNWARE_PLATFORM=y -CONFIG_I2C_CHARDEV=y -CONFIG_MMC=y -CONFIG_MMC_DW=y -CONFIG_PM=y -CONFIG_SUSPEND=y -CONFIG_MMC_UNSAFE_RESUME=y -CONFIG_USB=y -CONFIG_USB_DWC2=y -CONFIG_USB_DWC2_HOST=y -CONFIG_USB_DWC2_PLATFORM=y diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h index 559c69a47731..7d11979da030 100644 --- a/arch/arm/mach-ixp4xx/include/mach/io.h +++ b/arch/arm/mach-ixp4xx/include/mach/io.h @@ -76,7 +76,7 @@ static inline void __indirect_writeb(u8 value, volatile void __iomem *p) u32 n, byte_enables, data; if (!is_pci_memory(addr)) { - __raw_writeb(value, addr); + __raw_writeb(value, p); return; } @@ -141,7 +141,7 @@ static inline unsigned char __indirect_readb(const volatile void __iomem *p) u32 n, byte_enables, data; if (!is_pci_memory(addr)) - return __raw_readb(addr); + return __raw_readb(p); n = addr % 4; byte_enables = (0xf & ~BIT(n)) << IXP4XX_PCI_NP_CBE_BESL; diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index d22c30d3ccfa..8c58b71c2727 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -917,6 +917,10 @@ static int __init omap_device_late_idle(struct device *dev, void *data) static int __init omap_device_late_init(void) { bus_for_each_dev(&platform_bus_type, NULL, NULL, omap_device_late_idle); + + WARN(!of_have_populated_dt(), + "legacy booting deprecated, please update to boot with .dts\n"); + return 0; } omap_late_initcall_sync(omap_device_late_init); diff --git a/arch/arm/mach-pxa/include/mach/addr-map.h b/arch/arm/mach-pxa/include/mach/addr-map.h index bbf9df37ad4b..d28fe291233a 100644 --- a/arch/arm/mach-pxa/include/mach/addr-map.h +++ b/arch/arm/mach-pxa/include/mach/addr-map.h @@ -39,6 +39,11 @@ #define DMEMC_SIZE 0x00100000 /* + * Reserved space for low level debug virtual addresses within + * 0xf6200000..0xf6201000 + */ + +/* * Internal Memory Controller (PXA27x and later) */ #define IMEMC_PHYS 0x58000000 diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 4ef7a54813e6..75e75d7b1702 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -4,7 +4,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 354 +#define NR_syscalls 355 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index b419c6b7ac37..2c1bec9a14b6 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -359,5 +359,6 @@ #define __NR_renameat2 351 #define __NR_getrandom 352 #define __NR_memfd_create 353 +#define __NR_bpf 354 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 05b46c2b08b8..2ca219e184cd 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -374,4 +374,5 @@ ENTRY(sys_call_table) .long sys_renameat2 .long sys_getrandom .long sys_memfd_create + .long sys_bpf diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index abb8709d8b2a..af696874248b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -88,6 +88,7 @@ config PPC select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select BINFMT_ELF + select ARCH_BINFMT_ELF_RANDOMIZE_PIE select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM @@ -148,6 +149,8 @@ config PPC select HAVE_ARCH_AUDITSYSCALL select ARCH_SUPPORTS_ATOMIC_RMW select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN + select NO_BOOTMEM + select HAVE_GENERIC_RCU_GUP config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index d367a0aece2a..d80161b633f4 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -144,13 +144,24 @@ static char cmdline[BOOT_COMMAND_LINE_SIZE] static void prep_cmdline(void *chosen) { + unsigned int getline_timeout = 5000; + int v; + int n; + + /* Wait-for-input time */ + n = getprop(chosen, "linux,cmdline-timeout", &v, sizeof(v)); + if (n == sizeof(v)) + getline_timeout = v; + if (cmdline[0] == '\0') getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1); printf("\n\rLinux/PowerPC load: %s", cmdline); + /* If possible, edit the command line */ - if (console_ops.edit_cmdline) - console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE); + if (console_ops.edit_cmdline && getline_timeout) + console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE, getline_timeout); + printf("\n\r"); /* Put the command line back into the devtree for the kernel */ diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h index 8aad3c55aeda..5e75e1c5518e 100644 --- a/arch/powerpc/boot/ops.h +++ b/arch/powerpc/boot/ops.h @@ -58,7 +58,7 @@ extern struct dt_ops dt_ops; struct console_ops { int (*open)(void); void (*write)(const char *buf, int len); - void (*edit_cmdline)(char *buf, int len); + void (*edit_cmdline)(char *buf, int len, unsigned int getline_timeout); void (*close)(void); void *data; }; diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index f2156f07571f..167ee9433de6 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -33,7 +33,7 @@ static void serial_write(const char *buf, int len) scdp->putc(*buf++); } -static void serial_edit_cmdline(char *buf, int len) +static void serial_edit_cmdline(char *buf, int len, unsigned int timeout) { int timer = 0, count; char ch, *cp; @@ -44,7 +44,7 @@ static void serial_edit_cmdline(char *buf, int len) cp = &buf[count]; count++; - while (timer++ < 5*1000) { + do { if (scdp->tstc()) { while (((ch = scdp->getc()) != '\n') && (ch != '\r')) { /* Test for backspace/delete */ @@ -70,7 +70,7 @@ static void serial_edit_cmdline(char *buf, int len) break; /* Exit 'timer' loop */ } udelay(1000); /* 1 msec */ - } + } while (timer++ < timeout); *cp = 0; } diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index bd3bd573d0ae..59abc620f8e8 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -14,9 +14,9 @@ * * The bitop functions are defined to work on unsigned longs, so for a * ppc64 system the bits end up numbered: - * |63..............0|127............64|191...........128|255...........196| + * |63..............0|127............64|191...........128|255...........192| * and on ppc32: - * |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224| + * |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224| * * There are a few little-endian macros used mostly for filesystem * bitmaps, these work on similar bit arrays layouts, but @@ -213,7 +213,7 @@ static __inline__ unsigned long ffz(unsigned long x) return __ilog2(x & -x); } -static __inline__ int __ffs(unsigned long x) +static __inline__ unsigned long __ffs(unsigned long x) { return __ilog2(x & -x); } diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index daa5af91163c..22d5a7da9e68 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -448,13 +448,9 @@ extern const char *powerpc_base_platform; CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX) #define CPU_FTRS_COMPATIBLE (CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2) -#define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \ - CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \ - CPU_FTR_ICSWX | CPU_FTR_DABRX ) - #ifdef __powerpc64__ #ifdef CONFIG_PPC_BOOK3E -#define CPU_FTRS_POSSIBLE (CPU_FTRS_E6500 | CPU_FTRS_E5500 | CPU_FTRS_A2) +#define CPU_FTRS_POSSIBLE (CPU_FTRS_E6500 | CPU_FTRS_E5500) #else #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_POWER4 | CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \ @@ -505,13 +501,13 @@ enum { #ifdef __powerpc64__ #ifdef CONFIG_PPC_BOOK3E -#define CPU_FTRS_ALWAYS (CPU_FTRS_E6500 & CPU_FTRS_E5500 & CPU_FTRS_A2) +#define CPU_FTRS_ALWAYS (CPU_FTRS_E6500 & CPU_FTRS_E5500) #else #define CPU_FTRS_ALWAYS \ (CPU_FTRS_POWER4 & CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \ CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \ CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \ - CPU_FTRS_POWER8_DD1 & CPU_FTRS_POSSIBLE) + CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE) #endif #else enum { diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 888d8f3f2524..57d289acb803 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -28,8 +28,7 @@ the loader. We need to make sure that it is out of the way of the program that it will "exec", and that there is sufficient room for the brk. */ -extern unsigned long randomize_et_dyn(unsigned long base); -#define ELF_ET_DYN_BASE (randomize_et_dyn(0x20000000)) +#define ELF_ET_DYN_BASE 0x20000000 #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0) diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index a6774560afe3..493e72f64b35 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -70,39 +70,39 @@ #define CPU_UNKNOWN (~((u32)0)) /* Utility macros */ -#define SKIP_TO_NEXT_CPU(reg_entry) \ -({ \ - while (reg_entry->reg_id != REG_ID("CPUEND")) \ - reg_entry++; \ - reg_entry++; \ +#define SKIP_TO_NEXT_CPU(reg_entry) \ +({ \ + while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) \ + reg_entry++; \ + reg_entry++; \ }) /* Kernel Dump section info */ struct fadump_section { - u32 request_flag; - u16 source_data_type; - u16 error_flags; - u64 source_address; - u64 source_len; - u64 bytes_dumped; - u64 destination_address; + __be32 request_flag; + __be16 source_data_type; + __be16 error_flags; + __be64 source_address; + __be64 source_len; + __be64 bytes_dumped; + __be64 destination_address; }; /* ibm,configure-kernel-dump header. */ struct fadump_section_header { - u32 dump_format_version; - u16 dump_num_sections; - u16 dump_status_flag; - u32 offset_first_dump_section; + __be32 dump_format_version; + __be16 dump_num_sections; + __be16 dump_status_flag; + __be32 offset_first_dump_section; /* Fields for disk dump option. */ - u32 dd_block_size; - u64 dd_block_offset; - u64 dd_num_blocks; - u32 dd_offset_disk_path; + __be32 dd_block_size; + __be64 dd_block_offset; + __be64 dd_num_blocks; + __be32 dd_offset_disk_path; /* Maximum time allowed to prevent an automatic dump-reboot. */ - u32 max_time_auto; + __be32 max_time_auto; }; /* @@ -174,15 +174,15 @@ static inline u64 str_to_u64(const char *str) /* Register save area header. */ struct fadump_reg_save_area_header { - u64 magic_number; - u32 version; - u32 num_cpu_offset; + __be64 magic_number; + __be32 version; + __be32 num_cpu_offset; }; /* Register entry. */ struct fadump_reg_entry { - u64 reg_id; - u64 reg_value; + __be64 reg_id; + __be64 reg_value; }; /* fadump crash info structure */ diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 1bbb3013d6aa..8add8b861e8d 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -21,7 +21,12 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); #define __ARCH_IRQ_STAT -#define local_softirq_pending() __get_cpu_var(irq_stat).__softirq_pending +#define local_softirq_pending() __this_cpu_read(irq_stat.__softirq_pending) + +#define __ARCH_SET_SOFTIRQ_PENDING + +#define set_softirq_pending(x) __this_cpu_write(irq_stat.__softirq_pending, (x)) +#define or_softirq_pending(x) __this_cpu_or(irq_stat.__softirq_pending, (x)) static inline void ack_bad_irq(unsigned int irq) { diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 766b77d527ac..1d53a65b4ec1 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -48,7 +48,7 @@ static inline unsigned int hugepd_shift(hugepd_t hpd) #endif /* CONFIG_PPC_BOOK3S_64 */ -static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, +static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, unsigned pdshift) { /* @@ -58,9 +58,9 @@ static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, */ unsigned long idx = 0; - pte_t *dir = hugepd_page(*hpdp); + pte_t *dir = hugepd_page(hpd); #ifndef CONFIG_PPC_FSL_BOOK3E - idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp); + idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd); #endif return dir + idx; @@ -193,7 +193,7 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma, } #define hugepd_shift(x) 0 -static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, +static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, unsigned pdshift) { return 0; diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 97d3869991ca..5f0ad8904f65 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -851,9 +851,6 @@ static inline void * bus_to_virt(unsigned long address) #define clrsetbits_8(addr, clear, set) clrsetbits(8, addr, clear, set) -void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset, - size_t size, unsigned long flags); - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_IO_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 307347f8ddbd..15c9150a58cc 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -142,7 +142,6 @@ struct machdep_calls { #endif void (*restart)(char *cmd); - void (*power_off)(void); void (*halt)(void); void (*panic)(char *str); void (*cpu_die)(void); @@ -292,10 +291,6 @@ struct machdep_calls { #ifdef CONFIG_ARCH_RANDOM int (*get_random_long)(unsigned long *v); #endif - -#ifdef CONFIG_MEMORY_HOTREMOVE - int (*remove_memory)(u64, u64); -#endif }; extern void e500_idle(void); @@ -343,16 +338,6 @@ extern sys_ctrler_t sys_ctrler; #endif /* CONFIG_PPC_PMAC */ - -/* Functions to produce codes on the leds. - * The SRC code should be unique for the message category and should - * be limited to the lower 24 bits (the upper 8 are set by these funcs), - * and (for boot & dump) should be sorted numerically in the order - * the events occur. - */ -/* Print a boot progress message. */ -void ppc64_boot_msg(unsigned int src, const char *msg); - static inline void log_error(char *buf, unsigned int err_type, int fatal) { if (ppc_md.log_error) diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 9124b0ede1fc..60250e2d1f0d 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -154,6 +154,10 @@ struct opal_sg_list { #define OPAL_HANDLE_HMI 98 #define OPAL_REGISTER_DUMP_REGION 101 #define OPAL_UNREGISTER_DUMP_REGION 102 +#define OPAL_WRITE_TPO 103 +#define OPAL_READ_TPO 104 +#define OPAL_IPMI_SEND 107 +#define OPAL_IPMI_RECV 108 #ifndef __ASSEMBLY__ @@ -452,6 +456,17 @@ struct opal_msg { __be64 params[8]; }; +enum { + OPAL_IPMI_MSG_FORMAT_VERSION_1 = 1, +}; + +struct opal_ipmi_msg { + uint8_t version; + uint8_t netfn; + uint8_t cmd; + uint8_t data[]; +}; + struct opal_machine_check_event { enum OpalMCE_Version version:8; /* 0x00 */ uint8_t in_use; /* 0x01 */ @@ -819,6 +834,9 @@ int64_t opal_rtc_read(__be32 *year_month_day, __be64 *hour_minute_second_millisecond); int64_t opal_rtc_write(uint32_t year_month_day, uint64_t hour_minute_second_millisecond); +int64_t opal_tpo_read(uint64_t token, __be32 *year_mon_day, __be32 *hour_min); +int64_t opal_tpo_write(uint64_t token, uint32_t year_mon_day, + uint32_t hour_min); int64_t opal_cec_power_down(uint64_t request); int64_t opal_cec_reboot(void); int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset); @@ -963,6 +981,10 @@ int64_t opal_handle_hmi(void); int64_t opal_register_dump_region(uint32_t id, uint64_t start, uint64_t end); int64_t opal_unregister_dump_region(uint32_t id); int64_t opal_pci_set_phb_cxl_mode(uint64_t phb_id, uint64_t mode, uint64_t pe_number); +int64_t opal_ipmi_send(uint64_t interface, struct opal_ipmi_msg *msg, + uint64_t msg_len); +int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg, + uint64_t *msg_len); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, @@ -992,8 +1014,6 @@ extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg); extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data); struct rtc_time; -extern int opal_set_rtc_time(struct rtc_time *tm); -extern void opal_get_rtc_time(struct rtc_time *tm); extern unsigned long opal_get_boot_time(void); extern void opal_nvram_init(void); extern void opal_flash_init(void); diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 26fe1ae15212..69c059887a2c 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -379,12 +379,14 @@ static inline int hugepd_ok(hugepd_t hpd) } #endif -#define is_hugepd(pdep) (hugepd_ok(*((hugepd_t *)(pdep)))) +#define is_hugepd(hpd) (hugepd_ok(hpd)) +#define pgd_huge pgd_huge int pgd_huge(pgd_t pgd); #else /* CONFIG_HUGETLB_PAGE */ #define is_hugepd(pdep) 0 #define pgd_huge(pgd) 0 #endif /* CONFIG_HUGETLB_PAGE */ +#define __hugepd(x) ((hugepd_t) { (x) }) struct page; extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg); diff --git a/arch/powerpc/include/asm/pgtable-ppc64-4k.h b/arch/powerpc/include/asm/pgtable-ppc64-4k.h index 7b935683f268..132ee1d482c2 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-4k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-4k.h @@ -57,7 +57,21 @@ #define pgd_present(pgd) (pgd_val(pgd) != 0) #define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0) #define pgd_page_vaddr(pgd) (pgd_val(pgd) & ~PGD_MASKED_BITS) -#define pgd_page(pgd) virt_to_page(pgd_page_vaddr(pgd)) + +#ifndef __ASSEMBLY__ + +static inline pte_t pgd_pte(pgd_t pgd) +{ + return __pte(pgd_val(pgd)); +} + +static inline pgd_t pte_pgd(pte_t pte) +{ + return __pgd(pte_val(pte)); +} +extern struct page *pgd_page(pgd_t pgd); + +#endif /* !__ASSEMBLY__ */ #define pud_offset(pgdp, addr) \ (((pud_t *) pgd_page_vaddr(*(pgdp))) + \ diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h index a56b82fb0609..1de35bbd02a6 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h +++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h @@ -38,4 +38,7 @@ /* Bits to mask out from a PGD/PUD to get to the PMD page */ #define PUD_MASKED_BITS 0x1ff +#define pgd_pte(pgd) (pud_pte(((pud_t){ pgd }))) +#define pte_pgd(pte) ((pgd_t)pte_pud(pte)) + #endif /* _ASM_POWERPC_PGTABLE_PPC64_64K_H */ diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index ae153c40ab7c..5600e434332f 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -152,7 +152,7 @@ #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_bad(pmd) (!is_kernel_addr(pmd_val(pmd)) \ || (pmd_val(pmd) & PMD_BAD_BITS)) -#define pmd_present(pmd) (pmd_val(pmd) != 0) +#define pmd_present(pmd) (!pmd_none(pmd)) #define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0) #define pmd_page_vaddr(pmd) (pmd_val(pmd) & ~PMD_MASKED_BITS) extern struct page *pmd_page(pmd_t pmd); @@ -164,9 +164,21 @@ extern struct page *pmd_page(pmd_t pmd); #define pud_present(pud) (pud_val(pud) != 0) #define pud_clear(pudp) (pud_val(*(pudp)) = 0) #define pud_page_vaddr(pud) (pud_val(pud) & ~PUD_MASKED_BITS) -#define pud_page(pud) virt_to_page(pud_page_vaddr(pud)) +extern struct page *pud_page(pud_t pud); + +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} +#define pud_write(pud) pte_write(pud_pte(pud)) #define pgd_set(pgdp, pudp) ({pgd_val(*(pgdp)) = (unsigned long)(pudp);}) +#define pgd_write(pgd) pte_write(pgd_pte(pgd)) /* * Find an entry in a page-table-directory. We combine the address region @@ -422,7 +434,22 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd); - +/* + * + * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs + * page. The hugetlbfs page table walking and mangling paths are totally + * separated form the core VM paths and they're differentiated by + * VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run. + * + * pmd_trans_huge() is defined as false at build time if + * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build + * time in such case. + * + * For ppc64 we need to differntiate from explicit hugepages from THP, because + * for THP we also track the subpage details at the pmd level. We don't do + * that for explicit huge pages. + * + */ static inline int pmd_trans_huge(pmd_t pmd) { /* @@ -431,16 +458,6 @@ static inline int pmd_trans_huge(pmd_t pmd) return (pmd_val(pmd) & 0x3) && (pmd_val(pmd) & _PAGE_THP_HUGE); } -static inline int pmd_large(pmd_t pmd) -{ - /* - * leaf pte for huge page, bottom two bits != 00 - */ - if (pmd_trans_huge(pmd)) - return pmd_val(pmd) & _PAGE_PRESENT; - return 0; -} - static inline int pmd_trans_splitting(pmd_t pmd) { if (pmd_trans_huge(pmd)) @@ -451,6 +468,14 @@ static inline int pmd_trans_splitting(pmd_t pmd) extern int has_transparent_hugepage(void); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static inline int pmd_large(pmd_t pmd) +{ + /* + * leaf pte for huge page, bottom two bits != 00 + */ + return ((pmd_val(pmd) & 0x3) != 0x0); +} + static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); @@ -575,6 +600,5 @@ static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, */ return true; } - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_PPC64_H_ */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 316f9a5da173..a8805fee0df9 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -274,11 +274,9 @@ extern void paging_init(void); */ extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t *); -extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr); - extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr); + unsigned long end, int write, + struct page **pages, int *nr); #ifndef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_large(pmd) 0 #define has_transparent_hugepage() 0 diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 11ba86e17631..fbdf18cf954c 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -8,7 +8,6 @@ extern void ppc_printk_progress(char *s, unsigned short hex); extern unsigned int rtas_data; extern int mem_init_done; /* set on boot once kmalloc can be called */ -extern int init_bootmem_done; /* set once bootmem is available */ extern unsigned long long memory_limit; extern unsigned long klimit; extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask); @@ -24,7 +23,7 @@ extern void reloc_got2(unsigned long); #define PTRRELOC(x) ((typeof(x)) add_reloc_offset((unsigned long)(x))) void check_for_initrd(void); -void do_init_bootmem(void); +void initmem_init(void); void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index b034ecdb7c74..ebc4f165690a 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -71,13 +71,12 @@ struct thread_info { #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) /* how to get the thread information struct from C */ +register unsigned long __current_r1 asm("r1"); static inline struct thread_info *current_thread_info(void) { - register unsigned long sp asm("r1"); - /* gcc4, at least, is smart enough to turn this into a single * rlwinm for ppc32 and clrrdi for ppc64 */ - return (struct thread_info *)(sp & ~(THREAD_SIZE-1)); + return (struct thread_info *)(__current_r1 & ~(THREAD_SIZE-1)); } #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h index 2def01ed0cb2..cd7c2719d3ef 100644 --- a/arch/powerpc/include/asm/tlbflush.h +++ b/arch/powerpc/include/asm/tlbflush.h @@ -107,14 +107,14 @@ extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch); static inline void arch_enter_lazy_mmu_mode(void) { - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } static inline void arch_leave_lazy_mmu_mode(void) { - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->index) __flush_tlb_pending(batch); diff --git a/arch/powerpc/include/asm/vga.h b/arch/powerpc/include/asm/vga.h index a2eac409c1ec..e5f8dd366212 100644 --- a/arch/powerpc/include/asm/vga.h +++ b/arch/powerpc/include/asm/vga.h @@ -38,12 +38,10 @@ static inline u16 scr_readw(volatile const u16 *addr) #endif /* !CONFIG_VGA_CONSOLE && !CONFIG_MDA_CONSOLE */ -extern unsigned long vgacon_remap_base; - #ifdef __powerpc64__ #define VGA_MAP_MEM(x,s) ((unsigned long) ioremap((x), s)) #else -#define VGA_MAP_MEM(x,s) (x + vgacon_remap_base) +#define VGA_MAP_MEM(x,s) (x) #endif #define vga_readb(x) (*(x)) diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index 0d050ea37a04..6997f4a271df 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -98,7 +98,7 @@ DECLARE_PER_CPU(struct xics_cppr, xics_cppr); static inline void xics_push_cppr(unsigned int vec) { - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr); if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1)) return; @@ -111,7 +111,7 @@ static inline void xics_push_cppr(unsigned int vec) static inline unsigned char xics_pop_cppr(void) { - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr); if (WARN_ON(os_cppr->index < 1)) return LOWEST_PRIORITY; @@ -121,7 +121,7 @@ static inline unsigned char xics_pop_cppr(void) static inline void xics_set_base_cppr(unsigned char cppr) { - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr); /* we only really want to set the priority when there's * just one cppr value on the stack @@ -133,7 +133,7 @@ static inline void xics_set_base_cppr(unsigned char cppr) static inline unsigned char xics_cppr_top(void) { - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr); return os_cppr->stack[os_cppr->index]; } diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 34f55524d456..86150fbb42c3 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -908,7 +908,7 @@ int fix_alignment(struct pt_regs *regs) flush_fp_to_thread(current); } - if ((nb == 16)) { + if (nb == 16) { if (flags & F) { /* Special case for 16-byte FP loads and stores */ PPC_WARN_ALIGNMENT(fp_pair, regs); diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index c78e6dac4d7d..cfa0f81a5bb0 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -12,7 +12,6 @@ #undef DEBUG #include <linux/crash_dump.h> -#include <linux/bootmem.h> #include <linux/io.h> #include <linux/memblock.h> #include <asm/code-patching.h> diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index d55c76c571f3..f4217819cc31 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -41,7 +41,7 @@ void doorbell_exception(struct pt_regs *regs) may_hard_irq_enable(); - __get_cpu_var(irq_stat).doorbell_irqs++; + __this_cpu_inc(irq_stat.doorbell_irqs); smp_ipi_demux(); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 22b45a4955cd..10a093579191 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -1424,12 +1424,18 @@ _GLOBAL(ftrace_graph_caller) lwz r4, 44(r1) subi r4, r4, MCOUNT_INSN_SIZE - /* get the parent address */ - addi r3, r1, 52 + /* Grab the LR out of the caller stack frame */ + lwz r3,52(r1) bl prepare_ftrace_return nop + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR in the callers stack frame to this. + */ + stw r3,52(r1) + MCOUNT_RESTORE_FRAME /* old link register ends up in ctr reg */ bctr @@ -1457,4 +1463,4 @@ _GLOBAL(return_to_handler) blr #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#endif /* CONFIG_MCOUNT */ +#endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 5bbd1bc8c3b0..194e46dcf08d 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -659,7 +659,13 @@ _GLOBAL(ret_from_except_lite) 3: #endif bl save_nvgprs + /* + * Use a non volatile GPR to save and restore our thread_info flags + * across the call to restore_interrupts. + */ + mr r30,r4 bl restore_interrupts + mr r4,r30 addi r3,r1,STACK_FRAME_OVERHEAD bl do_notify_resume b ret_from_except @@ -1221,13 +1227,20 @@ _GLOBAL(ftrace_graph_caller) ld r4, 128(r1) subi r4, r4, MCOUNT_INSN_SIZE - /* get the parent address */ + /* Grab the LR out of the caller stack frame */ ld r11, 112(r1) - addi r3, r11, 16 + ld r3, 16(r11) bl prepare_ftrace_return nop + /* + * prepare_ftrace_return gives us the address we divert to. + * Change the LR in the callers stack frame to this. + */ + ld r11, 112(r1) + std r3, 16(r11) + ld r0, 128(r1) mtlr r0 addi r1, r1, 112 @@ -1235,28 +1248,6 @@ _GLOBAL(ftrace_graph_caller) _GLOBAL(return_to_handler) /* need to save return values */ - std r4, -24(r1) - std r3, -16(r1) - std r31, -8(r1) - mr r31, r1 - stdu r1, -112(r1) - - bl ftrace_return_to_handler - nop - - /* return value has real return address */ - mtlr r3 - - ld r1, 0(r1) - ld r4, -24(r1) - ld r3, -16(r1) - ld r31, -8(r1) - - /* Jump back to real return address */ - blr - -_GLOBAL(mod_return_to_handler) - /* need to save return values */ std r4, -32(r1) std r3, -24(r1) /* save TOC */ @@ -1266,7 +1257,7 @@ _GLOBAL(mod_return_to_handler) stdu r1, -112(r1) /* - * We are in a module using the module's TOC. + * We might be called from a module. * Switch to our TOC to run inside the core kernel. */ ld r2, PACATOC(r13) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 72e783ea0681..a1d45c161e24 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -292,15 +292,26 @@ decrementer_pSeries: . = 0xc00 .globl system_call_pSeries system_call_pSeries: - HMT_MEDIUM + /* + * If CONFIG_KVM_BOOK3S_64_HANDLER is set, save the PPR (on systems + * that support it) before changing to HMT_MEDIUM. That allows the KVM + * code to save that value into the guest state (it is the guest's PPR + * value). Otherwise just change to HMT_MEDIUM as userspace has + * already saved the PPR. + */ #ifdef CONFIG_KVM_BOOK3S_64_HANDLER SET_SCRATCH0(r13) GET_PACA(r13) std r9,PACA_EXGEN+EX_R9(r13) + OPT_GET_SPR(r9, SPRN_PPR, CPU_FTR_HAS_PPR); + HMT_MEDIUM; std r10,PACA_EXGEN+EX_R10(r13) + OPT_SAVE_REG_TO_PACA(PACA_EXGEN+EX_PPR, r9, CPU_FTR_HAS_PPR); mfcr r9 KVMTEST(0xc00) GET_SCRATCH0(r13) +#else + HMT_MEDIUM; #endif SYSCALL_PSERIES_1 SYSCALL_PSERIES_2_RFID diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 742694c1d852..26d091a1a54c 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -58,7 +58,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, const __be32 *sections; int i, num_sections; int size; - const int *token; + const __be32 *token; if (depth != 1 || strcmp(uname, "rtas") != 0) return 0; @@ -72,7 +72,7 @@ int __init early_init_dt_scan_fw_dump(unsigned long node, return 1; fw_dump.fadump_supported = 1; - fw_dump.ibm_configure_kernel_dump = *token; + fw_dump.ibm_configure_kernel_dump = be32_to_cpu(*token); /* * The 'ibm,kernel-dump' rtas node is present only if there is @@ -147,11 +147,11 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm, memset(fdm, 0, sizeof(struct fadump_mem_struct)); addr = addr & PAGE_MASK; - fdm->header.dump_format_version = 0x00000001; - fdm->header.dump_num_sections = 3; + fdm->header.dump_format_version = cpu_to_be32(0x00000001); + fdm->header.dump_num_sections = cpu_to_be16(3); fdm->header.dump_status_flag = 0; fdm->header.offset_first_dump_section = - (u32)offsetof(struct fadump_mem_struct, cpu_state_data); + cpu_to_be32((u32)offsetof(struct fadump_mem_struct, cpu_state_data)); /* * Fields for disk dump option. @@ -167,27 +167,27 @@ static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm, /* Kernel dump sections */ /* cpu state data section. */ - fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG; - fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA; + fdm->cpu_state_data.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); + fdm->cpu_state_data.source_data_type = cpu_to_be16(FADUMP_CPU_STATE_DATA); fdm->cpu_state_data.source_address = 0; - fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size; - fdm->cpu_state_data.destination_address = addr; + fdm->cpu_state_data.source_len = cpu_to_be64(fw_dump.cpu_state_data_size); + fdm->cpu_state_data.destination_address = cpu_to_be64(addr); addr += fw_dump.cpu_state_data_size; /* hpte region section */ - fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG; - fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION; + fdm->hpte_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); + fdm->hpte_region.source_data_type = cpu_to_be16(FADUMP_HPTE_REGION); fdm->hpte_region.source_address = 0; - fdm->hpte_region.source_len = fw_dump.hpte_region_size; - fdm->hpte_region.destination_address = addr; + fdm->hpte_region.source_len = cpu_to_be64(fw_dump.hpte_region_size); + fdm->hpte_region.destination_address = cpu_to_be64(addr); addr += fw_dump.hpte_region_size; /* RMA region section */ - fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG; - fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION; - fdm->rmr_region.source_address = RMA_START; - fdm->rmr_region.source_len = fw_dump.boot_memory_size; - fdm->rmr_region.destination_address = addr; + fdm->rmr_region.request_flag = cpu_to_be32(FADUMP_REQUEST_FLAG); + fdm->rmr_region.source_data_type = cpu_to_be16(FADUMP_REAL_MODE_REGION); + fdm->rmr_region.source_address = cpu_to_be64(RMA_START); + fdm->rmr_region.source_len = cpu_to_be64(fw_dump.boot_memory_size); + fdm->rmr_region.destination_address = cpu_to_be64(addr); addr += fw_dump.boot_memory_size; return addr; @@ -272,7 +272,7 @@ int __init fadump_reserve_mem(void) * first kernel. */ if (fdm_active) - fw_dump.boot_memory_size = fdm_active->rmr_region.source_len; + fw_dump.boot_memory_size = be64_to_cpu(fdm_active->rmr_region.source_len); else fw_dump.boot_memory_size = fadump_calculate_reserve_size(); @@ -314,8 +314,8 @@ int __init fadump_reserve_mem(void) (unsigned long)(base >> 20)); fw_dump.fadumphdr_addr = - fdm_active->rmr_region.destination_address + - fdm_active->rmr_region.source_len; + be64_to_cpu(fdm_active->rmr_region.destination_address) + + be64_to_cpu(fdm_active->rmr_region.source_len); pr_debug("fadumphdr_addr = %p\n", (void *) fw_dump.fadumphdr_addr); } else { @@ -472,9 +472,9 @@ fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs) { memset(regs, 0, sizeof(struct pt_regs)); - while (reg_entry->reg_id != REG_ID("CPUEND")) { - fadump_set_regval(regs, reg_entry->reg_id, - reg_entry->reg_value); + while (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUEND")) { + fadump_set_regval(regs, be64_to_cpu(reg_entry->reg_id), + be64_to_cpu(reg_entry->reg_value)); reg_entry++; } reg_entry++; @@ -603,20 +603,20 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) if (!fdm->cpu_state_data.bytes_dumped) return -EINVAL; - addr = fdm->cpu_state_data.destination_address; + addr = be64_to_cpu(fdm->cpu_state_data.destination_address); vaddr = __va(addr); reg_header = vaddr; - if (reg_header->magic_number != REGSAVE_AREA_MAGIC) { + if (be64_to_cpu(reg_header->magic_number) != REGSAVE_AREA_MAGIC) { printk(KERN_ERR "Unable to read register save area.\n"); return -ENOENT; } pr_debug("--------CPU State Data------------\n"); - pr_debug("Magic Number: %llx\n", reg_header->magic_number); - pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset); + pr_debug("Magic Number: %llx\n", be64_to_cpu(reg_header->magic_number)); + pr_debug("NumCpuOffset: %x\n", be32_to_cpu(reg_header->num_cpu_offset)); - vaddr += reg_header->num_cpu_offset; - num_cpus = *((u32 *)(vaddr)); + vaddr += be32_to_cpu(reg_header->num_cpu_offset); + num_cpus = be32_to_cpu(*((__be32 *)(vaddr))); pr_debug("NumCpus : %u\n", num_cpus); vaddr += sizeof(u32); reg_entry = (struct fadump_reg_entry *)vaddr; @@ -639,13 +639,13 @@ static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm) fdh = __va(fw_dump.fadumphdr_addr); for (i = 0; i < num_cpus; i++) { - if (reg_entry->reg_id != REG_ID("CPUSTRT")) { + if (be64_to_cpu(reg_entry->reg_id) != REG_ID("CPUSTRT")) { printk(KERN_ERR "Unable to read CPU state data\n"); rc = -ENOENT; goto error_out; } /* Lower 4 bytes of reg_value contains logical cpu id */ - cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK; + cpu = be64_to_cpu(reg_entry->reg_value) & FADUMP_CPU_ID_MASK; if (fdh && !cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) { SKIP_TO_NEXT_CPU(reg_entry); continue; @@ -692,7 +692,7 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active) return -EINVAL; /* Check if the dump data is valid. */ - if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) || + if ((be16_to_cpu(fdm_active->header.dump_status_flag) == FADUMP_ERROR_FLAG) || (fdm_active->cpu_state_data.error_flags != 0) || (fdm_active->rmr_region.error_flags != 0)) { printk(KERN_ERR "Dump taken by platform is not valid\n"); @@ -828,7 +828,7 @@ static void fadump_setup_crash_memory_ranges(void) static inline unsigned long fadump_relocate(unsigned long paddr) { if (paddr > RMA_START && paddr < fw_dump.boot_memory_size) - return fdm.rmr_region.destination_address + paddr; + return be64_to_cpu(fdm.rmr_region.destination_address) + paddr; else return paddr; } @@ -902,7 +902,7 @@ static int fadump_create_elfcore_headers(char *bufp) * to the specified destination_address. Hence set * the correct offset. */ - phdr->p_offset = fdm.rmr_region.destination_address; + phdr->p_offset = be64_to_cpu(fdm.rmr_region.destination_address); } phdr->p_paddr = mbase; @@ -951,7 +951,7 @@ static void register_fadump(void) fadump_setup_crash_memory_ranges(); - addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len; + addr = be64_to_cpu(fdm.rmr_region.destination_address) + be64_to_cpu(fdm.rmr_region.source_len); /* Initialize fadump crash info header. */ addr = init_fadump_header(addr); vaddr = __va(addr); @@ -1023,7 +1023,7 @@ void fadump_cleanup(void) /* Invalidate the registration only if dump is active. */ if (fw_dump.dump_active) { init_fadump_mem_struct(&fdm, - fdm_active->cpu_state_data.destination_address); + be64_to_cpu(fdm_active->cpu_state_data.destination_address)); fadump_invalidate_dump(&fdm); } } @@ -1063,7 +1063,7 @@ static void fadump_invalidate_release_mem(void) return; } - destination_address = fdm_active->cpu_state_data.destination_address; + destination_address = be64_to_cpu(fdm_active->cpu_state_data.destination_address); fadump_cleanup(); mutex_unlock(&fadump_mutex); @@ -1183,31 +1183,31 @@ static int fadump_region_show(struct seq_file *m, void *private) seq_printf(m, "CPU : [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", - fdm_ptr->cpu_state_data.destination_address, - fdm_ptr->cpu_state_data.destination_address + - fdm_ptr->cpu_state_data.source_len - 1, - fdm_ptr->cpu_state_data.source_len, - fdm_ptr->cpu_state_data.bytes_dumped); + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address), + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) + + be64_to_cpu(fdm_ptr->cpu_state_data.source_len) - 1, + be64_to_cpu(fdm_ptr->cpu_state_data.source_len), + be64_to_cpu(fdm_ptr->cpu_state_data.bytes_dumped)); seq_printf(m, "HPTE: [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", - fdm_ptr->hpte_region.destination_address, - fdm_ptr->hpte_region.destination_address + - fdm_ptr->hpte_region.source_len - 1, - fdm_ptr->hpte_region.source_len, - fdm_ptr->hpte_region.bytes_dumped); + be64_to_cpu(fdm_ptr->hpte_region.destination_address), + be64_to_cpu(fdm_ptr->hpte_region.destination_address) + + be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1, + be64_to_cpu(fdm_ptr->hpte_region.source_len), + be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped)); seq_printf(m, "DUMP: [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", - fdm_ptr->rmr_region.destination_address, - fdm_ptr->rmr_region.destination_address + - fdm_ptr->rmr_region.source_len - 1, - fdm_ptr->rmr_region.source_len, - fdm_ptr->rmr_region.bytes_dumped); + be64_to_cpu(fdm_ptr->rmr_region.destination_address), + be64_to_cpu(fdm_ptr->rmr_region.destination_address) + + be64_to_cpu(fdm_ptr->rmr_region.source_len) - 1, + be64_to_cpu(fdm_ptr->rmr_region.source_len), + be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped)); if (!fdm_active || (fw_dump.reserve_dump_area_start == - fdm_ptr->cpu_state_data.destination_address)) + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address))) goto out; /* Dump is active. Show reserved memory region. */ @@ -1215,10 +1215,10 @@ static int fadump_region_show(struct seq_file *m, void *private) " : [%#016llx-%#016llx] %#llx bytes, " "Dumped: %#llx\n", (unsigned long long)fw_dump.reserve_dump_area_start, - fdm_ptr->cpu_state_data.destination_address - 1, - fdm_ptr->cpu_state_data.destination_address - + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - 1, + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - fw_dump.reserve_dump_area_start, - fdm_ptr->cpu_state_data.destination_address - + be64_to_cpu(fdm_ptr->cpu_state_data.destination_address) - fw_dump.reserve_dump_area_start); out: if (fdm_active) diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 390311c0f03d..d7950317d3a1 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -510,79 +510,36 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifdef CONFIG_PPC64 -extern void mod_return_to_handler(void); -#endif - /* * Hook the return address and push it in the stack of return addrs - * in current thread info. + * in current thread info. Return the address we want to divert to. */ -void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) { - unsigned long old; - int faulted; struct ftrace_graph_ent trace; - unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long return_hooker; if (unlikely(ftrace_graph_is_dead())) - return; + goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) - return; - -#ifdef CONFIG_PPC64 - /* non core kernel code needs to save and restore the TOC */ - if (REGION_ID(self_addr) != KERNEL_REGION_ID) - return_hooker = (unsigned long)&mod_return_to_handler; -#endif - - return_hooker = ppc_function_entry((void *)return_hooker); + goto out; - /* - * Protect against fault, even if it shouldn't - * happen. This tool is too much intrusive to - * ignore such a protection. - */ - asm volatile( - "1: " PPC_LL "%[old], 0(%[parent])\n" - "2: " PPC_STL "%[return_hooker], 0(%[parent])\n" - " li %[faulted], 0\n" - "3:\n" - - ".section .fixup, \"ax\"\n" - "4: li %[faulted], 1\n" - " b 3b\n" - ".previous\n" - - ".section __ex_table,\"a\"\n" - PPC_LONG_ALIGN "\n" - PPC_LONG "1b,4b\n" - PPC_LONG "2b,4b\n" - ".previous" - - : [old] "=&r" (old), [faulted] "=r" (faulted) - : [parent] "r" (parent), [return_hooker] "r" (return_hooker) - : "memory" - ); - - if (unlikely(faulted)) { - ftrace_graph_stop(); - WARN_ON(1); - return; - } + return_hooker = ppc_function_entry(return_to_handler); - trace.func = self_addr; + trace.func = ip; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - *parent = old; - return; - } + if (!ftrace_graph_entry(&trace)) + goto out; + + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + goto out; - if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) - *parent = old; + parent = return_hooker; +out: + return parent; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 1f7d84e2e8b2..05e804cdecaa 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -63,7 +63,7 @@ int hw_breakpoint_slots(int type) int arch_install_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); - struct perf_event **slot = &__get_cpu_var(bp_per_reg); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg); *slot = bp; @@ -88,7 +88,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp) */ void arch_uninstall_hw_breakpoint(struct perf_event *bp) { - struct perf_event **slot = &__get_cpu_var(bp_per_reg); + struct perf_event **slot = this_cpu_ptr(&bp_per_reg); if (*slot != bp) { WARN_ONCE(1, "Can't find the breakpoint"); @@ -226,7 +226,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) */ rcu_read_lock(); - bp = __get_cpu_var(bp_per_reg); + bp = __this_cpu_read(bp_per_reg); if (!bp) goto out; info = counter_arch_bp(bp); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index a10642a0d861..71e60bfb89e2 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -208,7 +208,7 @@ static unsigned long iommu_range_alloc(struct device *dev, * We don't need to disable preemption here because any CPU can * safely use any IOMMU pool. */ - pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1); + pool_nr = __this_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1); if (largealloc) pool = &(tbl->large_pool); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c14383575fe8..45096033d37b 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -50,7 +50,6 @@ #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/mutex.h> -#include <linux/bootmem.h> #include <linux/pci.h> #include <linux/debugfs.h> #include <linux/of.h> @@ -114,7 +113,7 @@ static inline notrace void set_soft_enabled(unsigned long enable) static inline notrace int decrementer_check_overflow(void) { u64 now = get_tb_or_rtc(); - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); return now >= *next_tb; } @@ -499,7 +498,7 @@ void __do_irq(struct pt_regs *regs) /* And finally process it */ if (unlikely(irq == NO_IRQ)) - __get_cpu_var(irq_stat).spurious_irqs++; + __this_cpu_inc(irq_stat.spurious_irqs); else generic_handle_irq(irq); diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 8504657379f1..e77c3ccf8dcf 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -155,7 +155,7 @@ static int kgdb_singlestep(struct pt_regs *regs) { struct thread_info *thread_info, *exception_thread_info; struct thread_info *backup_current_thread_info = - &__get_cpu_var(kgdb_thread_info); + this_cpu_ptr(&kgdb_thread_info); if (user_mode(regs)) return 0; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 2f72af82513c..7c053f281406 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -119,7 +119,7 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp; + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr; } @@ -127,7 +127,7 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { - __get_cpu_var(current_kprobe) = p; + __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_msr = regs->msr; } @@ -192,7 +192,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) ret = 1; goto no_kprobe; } - p = __get_cpu_var(current_kprobe); + p = __this_cpu_read(current_kprobe); if (p->break_handler && p->break_handler(p, regs)) { goto ss_probe; } diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index a7fd4cb78b78..15c99b649b04 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -73,8 +73,8 @@ void save_mce_event(struct pt_regs *regs, long handled, uint64_t nip, uint64_t addr) { uint64_t srr1; - int index = __get_cpu_var(mce_nest_count)++; - struct machine_check_event *mce = &__get_cpu_var(mce_event[index]); + int index = __this_cpu_inc_return(mce_nest_count); + struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]); /* * Return if we don't have enough space to log mce event. @@ -143,7 +143,7 @@ void save_mce_event(struct pt_regs *regs, long handled, */ int get_mce_event(struct machine_check_event *mce, bool release) { - int index = __get_cpu_var(mce_nest_count) - 1; + int index = __this_cpu_read(mce_nest_count) - 1; struct machine_check_event *mc_evt; int ret = 0; @@ -153,7 +153,7 @@ int get_mce_event(struct machine_check_event *mce, bool release) /* Check if we have MCE info to process. */ if (index < MAX_MC_EVT) { - mc_evt = &__get_cpu_var(mce_event[index]); + mc_evt = this_cpu_ptr(&mce_event[index]); /* Copy the event structure and release the original */ if (mce) *mce = *mc_evt; @@ -163,7 +163,7 @@ int get_mce_event(struct machine_check_event *mce, bool release) } /* Decrement the count to free the slot. */ if (release) - __get_cpu_var(mce_nest_count)--; + __this_cpu_dec(mce_nest_count); return ret; } @@ -184,13 +184,13 @@ void machine_check_queue_event(void) if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; - index = __get_cpu_var(mce_queue_count)++; + index = __this_cpu_inc_return(mce_queue_count); /* If queue is full, just return for now. */ if (index >= MAX_MC_EVT) { - __get_cpu_var(mce_queue_count)--; + __this_cpu_dec(mce_queue_count); return; } - __get_cpu_var(mce_event_queue[index]) = evt; + memcpy(this_cpu_ptr(&mce_event_queue[index]), &evt, sizeof(evt)); /* Queue irq work to process this event later. */ irq_work_queue(&mce_event_process_work); @@ -208,11 +208,11 @@ static void machine_check_process_queued_event(struct irq_work *work) * For now just print it to console. * TODO: log this error event to FSP or nvram. */ - while (__get_cpu_var(mce_queue_count) > 0) { - index = __get_cpu_var(mce_queue_count) - 1; + while (__this_cpu_read(mce_queue_count) > 0) { + index = __this_cpu_read(mce_queue_count) - 1; machine_check_print_event_info( - &__get_cpu_var(mce_event_queue[index])); - __get_cpu_var(mce_queue_count)--; + this_cpu_ptr(&mce_event_queue[index])); + __this_cpu_dec(mce_queue_count); } } diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index e5dad9a9edc0..bc2dab52a991 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1464,7 +1464,7 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, res = &hose->io_resource; if (!res->flags) { - printk(KERN_WARNING "PCI: I/O resource not set for host" + pr_info("PCI: I/O resource not set for host" " bridge %s (domain %d)\n", hose->dn->full_name, hose->global_number); } else { diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 155013da27e0..ba0f2d6fc27f 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -17,7 +17,6 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/list.h> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 923cd2daba89..b4cc7bef6b16 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -37,9 +37,9 @@ #include <linux/personality.h> #include <linux/random.h> #include <linux/hw_breakpoint.h> +#include <linux/uaccess.h> #include <asm/pgtable.h> -#include <asm/uaccess.h> #include <asm/io.h> #include <asm/processor.h> #include <asm/mmu.h> @@ -499,7 +499,7 @@ static inline int set_dawr(struct arch_hw_breakpoint *brk) void __set_breakpoint(struct arch_hw_breakpoint *brk) { - __get_cpu_var(current_brk) = *brk; + memcpy(this_cpu_ptr(¤t_brk), brk, sizeof(*brk)); if (cpu_has_feature(CPU_FTR_DAWR)) set_dawr(brk); @@ -842,7 +842,7 @@ struct task_struct *__switch_to(struct task_struct *prev, * schedule DABR */ #ifndef CONFIG_HAVE_HW_BREAKPOINT - if (unlikely(!hw_brk_match(&__get_cpu_var(current_brk), &new->thread.hw_brk))) + if (unlikely(!hw_brk_match(this_cpu_ptr(¤t_brk), &new->thread.hw_brk))) __set_breakpoint(&new->thread.hw_brk); #endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif @@ -856,7 +856,7 @@ struct task_struct *__switch_to(struct task_struct *prev, * Collect processor utilization data per process */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); long unsigned start_tb, current_tb; start_tb = old_thread->start_tb; cu->current_tb = current_tb = mfspr(SPRN_PURR); @@ -866,7 +866,7 @@ struct task_struct *__switch_to(struct task_struct *prev, #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC_BOOK3S_64 - batch = &__get_cpu_var(ppc64_tlb_batch); + batch = this_cpu_ptr(&ppc64_tlb_batch); if (batch->active) { current_thread_info()->local_flags |= _TLF_LAZY_MMU; if (batch->index) @@ -889,7 +889,7 @@ struct task_struct *__switch_to(struct task_struct *prev, #ifdef CONFIG_PPC_BOOK3S_64 if (current_thread_info()->local_flags & _TLF_LAZY_MMU) { current_thread_info()->local_flags &= ~_TLF_LAZY_MMU; - batch = &__get_cpu_var(ppc64_tlb_batch); + batch = this_cpu_ptr(&ppc64_tlb_batch); batch->active = 1; } #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -921,12 +921,8 @@ static void show_instructions(struct pt_regs *regs) pc = (unsigned long)phys_to_virt(pc); #endif - /* We use __get_user here *only* to avoid an OOPS on a - * bad address because the pc *should* only be a - * kernel address. - */ if (!__kernel_text_address(pc) || - __get_user(instr, (unsigned int __user *)pc)) { + probe_kernel_address((unsigned int __user *)pc, instr)) { printk(KERN_CONT "XXXXXXXX "); } else { if (regs->nip == pc) @@ -1531,13 +1527,6 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) int curr_frame = current->curr_ret_stack; extern void return_to_handler(void); unsigned long rth = (unsigned long)return_to_handler; - unsigned long mrth = -1; -#ifdef CONFIG_PPC64 - extern void mod_return_to_handler(void); - rth = *(unsigned long *)rth; - mrth = (unsigned long)mod_return_to_handler; - mrth = *(unsigned long *)mrth; -#endif #endif sp = (unsigned long) stack; @@ -1562,7 +1551,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) if (!firstframe || ip != lr) { printk("["REG"] ["REG"] %pS", sp, ip, (void *)ip); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if ((ip == rth || ip == mrth) && curr_frame >= 0) { + if ((ip == rth) && curr_frame >= 0) { printk(" (%pS)", (void *)current->ret_stack[curr_frame].ret); curr_frame--; @@ -1665,12 +1654,3 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return ret; } -unsigned long randomize_et_dyn(unsigned long base) -{ - unsigned long ret = PAGE_ALIGN(base + brk_rnd()); - - if (ret < base) - return base; - - return ret; -} diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 099f27e6d1b0..6a799b3cc6b4 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -160,6 +160,12 @@ static struct ibm_pa_feature { {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + /* + * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), + * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP + * which is 0 if the kernel doesn't support TM. + */ + {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -696,10 +702,7 @@ void __init early_init_devtree(void *params) reserve_crashkernel(); early_reserve_mem(); - /* - * Ensure that total memory size is page-aligned, because otherwise - * mark_bootmem() gets upset. - */ + /* Ensure that total memory size is page-aligned. */ limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c index 8777fb02349f..fb2fb3ea85e5 100644 --- a/arch/powerpc/kernel/rtas-proc.c +++ b/arch/powerpc/kernel/rtas-proc.c @@ -113,17 +113,6 @@ #define SENSOR_PREFIX "ibm,sensor-" #define cel_to_fahr(x) ((x*9/5)+32) - -/* Globals */ -static struct rtas_sensors sensors; -static struct device_node *rtas_node = NULL; -static unsigned long power_on_time = 0; /* Save the time the user set */ -static char progress_led[MAX_LINELENGTH]; - -static unsigned long rtas_tone_frequency = 1000; -static unsigned long rtas_tone_volume = 0; - -/* ****************STRUCTS******************************************* */ struct individual_sensor { unsigned int token; unsigned int quant; @@ -134,6 +123,15 @@ struct rtas_sensors { unsigned int quant; }; +/* Globals */ +static struct rtas_sensors sensors; +static struct device_node *rtas_node = NULL; +static unsigned long power_on_time = 0; /* Save the time the user set */ +static char progress_led[MAX_LINELENGTH]; + +static unsigned long rtas_tone_frequency = 1000; +static unsigned long rtas_tone_volume = 0; + /* ****************************************************************** */ /* Declarations */ static int ppc_rtas_sensors_show(struct seq_file *m, void *v); diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 8b4c857c1421..4af905e81ab0 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1091,8 +1091,8 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) } /* - * Call early during boot, before mem init or bootmem, to retrieve the RTAS - * informations from the device-tree and allocate the RMO buffer for userland + * Call early during boot, before mem init, to retrieve the RTAS + * information from the device-tree and allocate the RMO buffer for userland * accesses. */ void __init rtas_initialize(void) diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 7c55b86206b3..ce230da2c015 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -26,7 +26,6 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <asm/io.h> #include <asm/pgtable.h> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 1362cd62b3fa..44c8d03558ac 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -139,8 +139,8 @@ void machine_restart(char *cmd) void machine_power_off(void) { machine_shutdown(); - if (ppc_md.power_off) - ppc_md.power_off(); + if (pm_power_off) + pm_power_off(); #ifdef CONFIG_SMP smp_send_stop(); #endif @@ -151,7 +151,7 @@ void machine_power_off(void) /* Used by the G5 thermal driver */ EXPORT_SYMBOL_GPL(machine_power_off); -void (*pm_power_off)(void) = machine_power_off; +void (*pm_power_off)(void); EXPORT_SYMBOL_GPL(pm_power_off); void machine_halt(void) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 07831ed0d9ef..bb02e9f6944e 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -11,7 +11,6 @@ #include <linux/delay.h> #include <linux/initrd.h> #include <linux/tty.h> -#include <linux/bootmem.h> #include <linux/seq_file.h> #include <linux/root_dev.h> #include <linux/cpu.h> @@ -53,11 +52,6 @@ unsigned long ISA_DMA_THRESHOLD; unsigned int DMA_MODE_READ; unsigned int DMA_MODE_WRITE; -#ifdef CONFIG_VGA_CONSOLE -unsigned long vgacon_remap_base; -EXPORT_SYMBOL(vgacon_remap_base); -#endif - /* * These are used in binfmt_elf.c to put aux entries on the stack * for each elf executable being started. @@ -311,9 +305,8 @@ void __init setup_arch(char **cmdline_p) irqstack_early_init(); - /* set up the bootmem stuff with available memory */ - do_init_bootmem(); - if ( ppc_md.progress ) ppc_md.progress("setup_arch: bootmem", 0x3eab); + initmem_init(); + if ( ppc_md.progress ) ppc_md.progress("setup_arch: initmem", 0x3eab); #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 4f3cfe1b6a33..6e5310ddf8c7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -665,8 +665,6 @@ static void __init emergency_stack_init(void) */ void __init setup_arch(char **cmdline_p) { - ppc64_boot_msg(0x12, "Setup Arch"); - *cmdline_p = boot_command_line; /* @@ -691,9 +689,7 @@ void __init setup_arch(char **cmdline_p) exc_lvl_early_init(); emergency_stack_init(); - /* set up the bootmem stuff with available memory */ - do_init_bootmem(); - sparse_init(); + initmem_init(); #ifdef CONFIG_DUMMY_CONSOLE conswitchp = &dummy_con; @@ -711,33 +707,6 @@ void __init setup_arch(char **cmdline_p) if ((unsigned long)_stext & 0xffff) panic("Kernelbase not 64K-aligned (0x%lx)!\n", (unsigned long)_stext); - - ppc64_boot_msg(0x15, "Setup Done"); -} - - -/* ToDo: do something useful if ppc_md is not yet setup. */ -#define PPC64_LINUX_FUNCTION 0x0f000000 -#define PPC64_IPL_MESSAGE 0xc0000000 -#define PPC64_TERM_MESSAGE 0xb0000000 - -static void ppc64_do_msg(unsigned int src, const char *msg) -{ - if (ppc_md.progress) { - char buf[128]; - - sprintf(buf, "%08X\n", src); - ppc_md.progress(buf, 0); - snprintf(buf, 128, "%s", msg); - ppc_md.progress(buf, 0); - } -} - -/* Print a boot progress message. */ -void ppc64_boot_msg(unsigned int src, const char *msg) -{ - ppc64_do_msg(PPC64_LINUX_FUNCTION|PPC64_IPL_MESSAGE|src, msg); - printk("[boot]%04x %s\n", src, msg); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 71e186d5f331..8b2d2dc8ef10 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -243,7 +243,7 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) irqreturn_t smp_ipi_demux(void) { - struct cpu_messages *info = &__get_cpu_var(ipi_message); + struct cpu_messages *info = this_cpu_ptr(&ipi_message); unsigned int all; mb(); /* order any irq clear */ @@ -442,9 +442,9 @@ void generic_mach_cpu_die(void) idle_task_exit(); cpu = smp_processor_id(); printk(KERN_DEBUG "CPU%d offline\n", cpu); - __get_cpu_var(cpu_state) = CPU_DEAD; + __this_cpu_write(cpu_state, CPU_DEAD); smp_wmb(); - while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) + while (__this_cpu_read(cpu_state) != CPU_UP_PREPARE) cpu_relax(); } diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 67fd2fd2620a..fa1fd8a0c867 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -394,10 +394,10 @@ void ppc_enable_pmcs(void) ppc_set_pmu_inuse(1); /* Only need to enable them once */ - if (__get_cpu_var(pmcs_enabled)) + if (__this_cpu_read(pmcs_enabled)) return; - __get_cpu_var(pmcs_enabled) = 1; + __this_cpu_write(pmcs_enabled, 1); if (ppc_md.enable_pmcs) ppc_md.enable_pmcs(); diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 7505599c2593..fa7c4f12104f 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -458,9 +458,9 @@ static inline void clear_irq_work_pending(void) DEFINE_PER_CPU(u8, irq_work_pending); -#define set_irq_work_pending_flag() __get_cpu_var(irq_work_pending) = 1 -#define test_irq_work_pending() __get_cpu_var(irq_work_pending) -#define clear_irq_work_pending() __get_cpu_var(irq_work_pending) = 0 +#define set_irq_work_pending_flag() __this_cpu_write(irq_work_pending, 1) +#define test_irq_work_pending() __this_cpu_read(irq_work_pending) +#define clear_irq_work_pending() __this_cpu_write(irq_work_pending, 0) #endif /* 32 vs 64 bit */ @@ -482,8 +482,8 @@ void arch_irq_work_raise(void) static void __timer_interrupt(void) { struct pt_regs *regs = get_irq_regs(); - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); - struct clock_event_device *evt = &__get_cpu_var(decrementers); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); + struct clock_event_device *evt = this_cpu_ptr(&decrementers); u64 now; trace_timer_interrupt_entry(regs); @@ -498,7 +498,7 @@ static void __timer_interrupt(void) *next_tb = ~(u64)0; if (evt->event_handler) evt->event_handler(evt); - __get_cpu_var(irq_stat).timer_irqs_event++; + __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; if (now <= DECREMENTER_MAX) @@ -506,13 +506,13 @@ static void __timer_interrupt(void) /* We may have raced with new irq work */ if (test_irq_work_pending()) set_dec(1); - __get_cpu_var(irq_stat).timer_irqs_others++; + __this_cpu_inc(irq_stat.timer_irqs_others); } #ifdef CONFIG_PPC64 /* collect purr register values often, for accurate calculations */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array); + struct cpu_usage *cu = this_cpu_ptr(&cpu_usage_array); cu->current_tb = mfspr(SPRN_PURR); } #endif @@ -527,7 +527,7 @@ static void __timer_interrupt(void) void timer_interrupt(struct pt_regs * regs) { struct pt_regs *old_regs; - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); /* Ensure a positive value is written to the decrementer, or else * some CPUs will continue to take decrementer exceptions. @@ -813,7 +813,7 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt; + __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt); set_dec(evt); /* We may have raced with new irq work */ @@ -833,7 +833,7 @@ static void decrementer_set_mode(enum clock_event_mode mode, /* Interrupt handler for the timer broadcast IPI */ void tick_broadcast_ipi_handler(void) { - u64 *next_tb = &__get_cpu_var(decrementers_next_tb); + u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); *next_tb = get_tb_or_rtc(); __timer_interrupt(); @@ -989,6 +989,7 @@ void GregorianDay(struct rtc_time * tm) tm->tm_wday = day % 7; } +EXPORT_SYMBOL_GPL(GregorianDay); void to_tm(int tim, struct rtc_time * tm) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 0dc43f9932cf..e6595b72269b 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -295,7 +295,7 @@ long machine_check_early(struct pt_regs *regs) { long handled = 0; - __get_cpu_var(irq_stat).mce_exceptions++; + __this_cpu_inc(irq_stat.mce_exceptions); if (cur_cpu_spec && cur_cpu_spec->machine_check_early) handled = cur_cpu_spec->machine_check_early(regs); @@ -304,7 +304,7 @@ long machine_check_early(struct pt_regs *regs) long hmi_exception_realmode(struct pt_regs *regs) { - __get_cpu_var(irq_stat).hmi_exceptions++; + __this_cpu_inc(irq_stat.hmi_exceptions); if (ppc_md.hmi_exception_early) ppc_md.hmi_exception_early(regs); @@ -700,7 +700,7 @@ void machine_check_exception(struct pt_regs *regs) enum ctx_state prev_state = exception_enter(); int recover = 0; - __get_cpu_var(irq_stat).mce_exceptions++; + __this_cpu_inc(irq_stat.mce_exceptions); /* See if any machine dependent calls. In theory, we would want * to call the CPU first, and call the ppc_md. one if the CPU @@ -1519,7 +1519,7 @@ void vsx_unavailable_tm(struct pt_regs *regs) void performance_monitor_exception(struct pt_regs *regs) { - __get_cpu_var(irq_stat).pmu_irqs++; + __this_cpu_inc(irq_stat.pmu_irqs); perf_irq(regs); } diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c index 6e7c4923b5ea..411116c38da4 100644 --- a/arch/powerpc/kernel/udbg_16550.c +++ b/arch/powerpc/kernel/udbg_16550.c @@ -69,8 +69,12 @@ static void udbg_uart_putc(char c) static int udbg_uart_getc_poll(void) { - if (!udbg_uart_in || !(udbg_uart_in(UART_LSR) & LSR_DR)) + if (!udbg_uart_in) + return -1; + + if (!(udbg_uart_in(UART_LSR) & LSR_DR)) return udbg_uart_in(UART_RBR); + return -1; } diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index f174351842cf..305eb0d9b768 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -20,7 +20,6 @@ #include <linux/user.h> #include <linux/elf.h> #include <linux/security.h> -#include <linux/bootmem.h> #include <linux/memblock.h> #include <asm/pgtable.h> diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 4fdc27c80f4c..3f1bb5a36c27 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -12,7 +12,6 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/spinlock.h> -#include <linux/bootmem.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/sizes.h> @@ -154,7 +153,7 @@ EXPORT_SYMBOL_GPL(kvm_release_hpt); * kvm_cma_reserve() - reserve area for kvm hash pagetable * * This function reserves memory from early allocator. It should be - * called by arch specific code once the early allocator (memblock or bootmem) + * called by arch specific code once the memblock allocator * has been activated and all other subsystems have already allocated/reserved * memory. */ diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 2e02ed849f36..16095841afe1 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -76,11 +76,11 @@ static inline int local_sid_setup_one(struct id *entry) unsigned long sid; int ret = -1; - sid = ++(__get_cpu_var(pcpu_last_used_sid)); + sid = __this_cpu_inc_return(pcpu_last_used_sid); if (sid < NUM_TIDS) { - __get_cpu_var(pcpu_sids).entry[sid] = entry; + __this_cpu_write(pcpu_sids)entry[sid], entry); entry->val = sid; - entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid]; + entry->pentry = this_cpu_ptr(&pcpu_sids.entry[sid]); ret = sid; } @@ -108,8 +108,8 @@ static inline int local_sid_setup_one(struct id *entry) static inline int local_sid_lookup(struct id *entry) { if (entry && entry->val != 0 && - __get_cpu_var(pcpu_sids).entry[entry->val] == entry && - entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val]) + __this_cpu_read(pcpu_sids.entry[entry->val]) == entry && + entry->pentry == this_cpu_ptr(&pcpu_sids.entry[entry->val])) return entry->val; return -1; } @@ -117,8 +117,8 @@ static inline int local_sid_lookup(struct id *entry) /* Invalidate all id mappings on local core -- call with preempt disabled */ static inline void local_sid_destroy_all(void) { - __get_cpu_var(pcpu_last_used_sid) = 0; - memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids))); + __this_cpu_write(pcpu_last_used_sid, 0); + memset(this_cpu_ptr(&pcpu_sids), 0, sizeof(pcpu_sids)); } static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500) diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 2fdc8722e324..cda695de8aa7 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -144,9 +144,9 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu) mtspr(SPRN_GESR, vcpu->arch.shared->esr); if (vcpu->arch.oldpir != mfspr(SPRN_PIR) || - __get_cpu_var(last_vcpu_of_lpid)[get_lpid(vcpu)] != vcpu) { + __this_cpu_read(last_vcpu_of_lpid[get_lpid(vcpu)]) != vcpu) { kvmppc_e500_tlbil_all(vcpu_e500); - __get_cpu_var(last_vcpu_of_lpid)[get_lpid(vcpu)] = vcpu; + __this_cpu_write(last_vcpu_of_lpid[get_lpid(vcpu)], vcpu); } } diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 9f342f134ae4..597562f69b2d 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -12,7 +12,6 @@ CFLAGS_REMOVE_feature-fixups.o = -pg obj-y := string.o alloc.o \ crtsavres.o ppc_ksyms.o obj-$(CONFIG_PPC32) += div64.o copy_32.o -obj-$(CONFIG_HAS_IOMEM) += devres.o obj-$(CONFIG_PPC64) += copypage_64.o copyuser_64.o \ usercopy_64.o mem_64.o string.o \ diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c deleted file mode 100644 index 8df55fc3aad6..000000000000 --- a/arch/powerpc/lib/devres.c +++ /dev/null @@ -1,43 +0,0 @@ -/* - * Copyright (C) 2008 Freescale Semiconductor, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include <linux/device.h> /* devres_*(), devm_ioremap_release() */ -#include <linux/gfp.h> -#include <linux/io.h> /* ioremap_prot() */ -#include <linux/export.h> /* EXPORT_SYMBOL() */ - -/** - * devm_ioremap_prot - Managed ioremap_prot() - * @dev: Generic device to remap IO address for - * @offset: BUS offset to map - * @size: Size of map - * @flags: Page flags - * - * Managed ioremap_prot(). Map is automatically unmapped on driver - * detach. - */ -void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset, - size_t size, unsigned long flags) -{ - void __iomem **ptr, *addr; - - ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return NULL; - - addr = ioremap_prot(offset, size, flags); - if (addr) { - *ptr = addr; - devres_add(dev, ptr); - } else - devres_free(ptr); - - return addr; -} -EXPORT_SYMBOL(devm_ioremap_prot); diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 54651fc2d412..dc885b30f7a6 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -1865,6 +1865,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) } goto ldst_done; +#ifdef CONFIG_PPC_FPU case LOAD_FP: if (regs->msr & MSR_LE) return 0; @@ -1873,7 +1874,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) else err = do_fp_load(op.reg, do_lfd, op.ea, size, regs); goto ldst_done; - +#endif #ifdef CONFIG_ALTIVEC case LOAD_VMX: if (regs->msr & MSR_LE) @@ -1919,6 +1920,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) err = write_mem(op.val, op.ea, size, regs); goto ldst_done; +#ifdef CONFIG_PPC_FPU case STORE_FP: if (regs->msr & MSR_LE) return 0; @@ -1927,7 +1929,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr) else err = do_fp_store(op.reg, do_stfd, op.ea, size, regs); goto ldst_done; - +#endif #ifdef CONFIG_ALTIVEC case STORE_VMX: if (regs->msr & MSR_LE) diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 325e861616a1..438dcd3fd0d1 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -6,7 +6,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) -obj-y := fault.o mem.o pgtable.o gup.o mmap.o \ +obj-y := fault.o mem.o pgtable.o mmap.o \ init_$(CONFIG_WORD_SIZE).o \ pgtable_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c deleted file mode 100644 index d8746684f606..000000000000 --- a/arch/powerpc/mm/gup.c +++ /dev/null @@ -1,235 +0,0 @@ -/* - * Lockless get_user_pages_fast for powerpc - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ -#undef DEBUG - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/hugetlb.h> -#include <linux/vmstat.h> -#include <linux/pagemap.h> -#include <linux/rwsem.h> -#include <asm/pgtable.h> - -#ifdef __HAVE_ARCH_PTE_SPECIAL - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - unsigned long mask, result; - pte_t *ptep; - - result = _PAGE_PRESENT|_PAGE_USER; - if (write) - result |= _PAGE_RW; - mask = result | _PAGE_SPECIAL; - - ptep = pte_offset_kernel(&pmd, addr); - do { - pte_t pte = ACCESS_ONCE(*ptep); - struct page *page; - /* - * Similar to the PMD case, NUMA hinting must take slow path - */ - if (pte_numa(pte)) - return 0; - - if ((pte_val(pte) & mask) != result) - return 0; - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - if (!page_cache_get_speculative(page)) - return 0; - if (unlikely(pte_val(pte) != pte_val(*ptep))) { - put_page(page); - return 0; - } - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = ACCESS_ONCE(*pmdp); - - next = pmd_addr_end(addr, end); - /* - * If we find a splitting transparent hugepage we - * return zero. That will result in taking the slow - * path which will call wait_split_huge_page() - * if the pmd is still in splitting state - */ - if (pmd_none(pmd) || pmd_trans_splitting(pmd)) - return 0; - if (pmd_huge(pmd) || pmd_large(pmd)) { - /* - * NUMA hinting faults need to be handled in the GUP - * slowpath for accounting purposes and so that they - * can be serialised against THP migration. - */ - if (pmd_numa(pmd)) - return 0; - - if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next, - write, pages, nr)) - return 0; - } else if (is_hugepd(pmdp)) { - if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT, - addr, next, write, pages, nr)) - return 0; - } else if (!gup_pte_range(pmd, addr, next, write, pages, nr)) - return 0; - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&pgd, addr); - do { - pud_t pud = ACCESS_ONCE(*pudp); - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (pud_huge(pud)) { - if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next, - write, pages, nr)) - return 0; - } else if (is_hugepd(pudp)) { - if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT, - addr, next, write, pages, nr)) - return 0; - } else if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } while (pudp++, addr = next, addr != end); - - return 1; -} - -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - pr_devel("%s(%lx,%x,%s)\n", __func__, start, nr_pages, write ? "write" : "read"); - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - - if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, - start, len))) - return 0; - - pr_devel(" aligned: %lx .. %lx\n", start, end); - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables from being freed on powerpc. - * - * So long as we atomically load page table pointers versus teardown, - * we can follow the address down to the the page and take a ref on it. - */ - local_irq_save(flags); - - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = ACCESS_ONCE(*pgdp); - - pr_devel(" %016lx: normal pgd %p\n", addr, - (void *)pgd_val(pgd)); - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (pgd_huge(pgd)) { - if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next, - write, pages, &nr)) - break; - } else if (is_hugepd(pgdp)) { - if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT, - addr, next, write, pages, &nr)) - break; - } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - - local_irq_restore(flags); - - return nr; -} - -int get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - int nr, ret; - - start &= PAGE_MASK; - nr = __get_user_pages_fast(start, nr_pages, write, pages); - ret = nr; - - if (nr < nr_pages) { - pr_devel(" slow path ! nr = %d\n", nr); - - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, start, - nr_pages - nr, write, 0, pages, NULL); - up_read(&mm->mmap_sem); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - } - - return ret; -} - -#endif /* __HAVE_ARCH_PTE_SPECIAL */ diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 057cbbb4c576..5094f32b706e 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -514,7 +514,7 @@ htab_insert_pte: andis. r0,r31,_PAGE_4K_PFN@h srdi r5,r31,PTE_RPN_SHIFT bne- htab_special_pfn - sldi r5,r5,PAGE_SHIFT-HW_PAGE_SHIFT + sldi r5,r5,PAGE_FACTOR add r5,r5,r25 htab_special_pfn: sldi r5,r5,HW_PAGE_SHIFT @@ -544,7 +544,7 @@ htab_call_hpte_insert1: andis. r0,r31,_PAGE_4K_PFN@h srdi r5,r31,PTE_RPN_SHIFT bne- 3f - sldi r5,r5,PAGE_SHIFT-HW_PAGE_SHIFT + sldi r5,r5,PAGE_FACTOR add r5,r5,r25 3: sldi r5,r5,HW_PAGE_SHIFT diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index ae4962a06476..d53288a08c37 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -629,7 +629,7 @@ static void native_flush_hash_range(unsigned long number, int local) unsigned long want_v; unsigned long flags; real_pte_t pte; - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); unsigned long psize = batch->psize; int ssize = batch->ssize; int i; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index d5339a3b9945..f01027731e23 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -1322,7 +1322,7 @@ void flush_hash_range(unsigned long number, int local) else { int i; struct ppc64_tlb_batch *batch = - &__get_cpu_var(ppc64_tlb_batch); + this_cpu_ptr(&ppc64_tlb_batch); for (i = 0; i < number; i++) flush_hash_page(batch->vpn[i], batch->pte[i], diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c index 5e4ee2573903..ba47aaf33a4b 100644 --- a/arch/powerpc/mm/hugetlbpage-book3e.c +++ b/arch/powerpc/mm/hugetlbpage-book3e.c @@ -33,13 +33,13 @@ static inline int tlb1_next(void) ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY; - index = __get_cpu_var(next_tlbcam_idx); + index = this_cpu_read(next_tlbcam_idx); /* Just round-robin the entries and wrap when we hit the end */ if (unlikely(index == ncams - 1)) - __get_cpu_var(next_tlbcam_idx) = tlbcam_index; + __this_cpu_write(next_tlbcam_idx, tlbcam_index); else - __get_cpu_var(next_tlbcam_idx)++; + __this_cpu_inc(next_tlbcam_idx); return index; } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 7e70ae968e5f..af56de82375d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -62,6 +62,9 @@ static unsigned nr_gpages; /* * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD; + * + * Defined in such a way that we can optimize away code block at build time + * if CONFIG_HUGETLB_PAGE=n. */ int pmd_huge(pmd_t pmd) { @@ -230,7 +233,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift)) return NULL; - return hugepte_offset(hpdp, addr, pdshift); + return hugepte_offset(*hpdp, addr, pdshift); } #else @@ -270,13 +273,13 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift)) return NULL; - return hugepte_offset(hpdp, addr, pdshift); + return hugepte_offset(*hpdp, addr, pdshift); } #endif #ifdef CONFIG_PPC_FSL_BOOK3E /* Build list of addresses of gigantic pages. This function is used in early - * boot before the buddy or bootmem allocator is setup. + * boot before the buddy allocator is setup. */ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) { @@ -399,7 +402,7 @@ void __init reserve_hugetlb_gpages(void) #else /* !PPC_FSL_BOOK3E */ /* Build list of addresses of gigantic pages. This function is used in early - * boot before the buddy or bootmem allocator is setup. + * boot before the buddy allocator is setup. */ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) { @@ -462,7 +465,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = &get_cpu_var(hugepd_freelist_cur); + batchp = this_cpu_ptr(&hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), @@ -538,7 +541,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, do { pmd = pmd_offset(pud, addr); next = pmd_addr_end(addr, end); - if (!is_hugepd(pmd)) { + if (!is_hugepd(__hugepd(pmd_val(*pmd)))) { /* * if it is not hugepd pointer, we should already find * it cleared. @@ -587,7 +590,7 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, do { pud = pud_offset(pgd, addr); next = pud_addr_end(addr, end); - if (!is_hugepd(pud)) { + if (!is_hugepd(__hugepd(pud_val(*pud)))) { if (pud_none_or_clear_bad(pud)) continue; hugetlb_free_pmd_range(tlb, pud, addr, next, floor, @@ -653,7 +656,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, do { next = pgd_addr_end(addr, end); pgd = pgd_offset(tlb->mm, addr); - if (!is_hugepd(pgd)) { + if (!is_hugepd(__hugepd(pgd_val(*pgd)))) { if (pgd_none_or_clear_bad(pgd)) continue; hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling); @@ -713,12 +716,11 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, return (__boundary - 1 < end - 1) ? __boundary : end; } -int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, - unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) +int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned pdshift, + unsigned long end, int write, struct page **pages, int *nr) { pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(*hugepd); + unsigned long sz = 1UL << hugepd_shift(hugepd); unsigned long next; ptep = hugepte_offset(hugepd, addr, pdshift); @@ -961,7 +963,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift else if (pgd_huge(pgd)) { ret_pte = (pte_t *) pgdp; goto out; - } else if (is_hugepd(&pgd)) + } else if (is_hugepd(__hugepd(pgd_val(pgd)))) hpdp = (hugepd_t *)&pgd; else { /* @@ -978,7 +980,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift else if (pud_huge(pud)) { ret_pte = (pte_t *) pudp; goto out; - } else if (is_hugepd(&pud)) + } else if (is_hugepd(__hugepd(pud_val(pud)))) hpdp = (hugepd_t *)&pud; else { pdshift = PMD_SHIFT; @@ -999,7 +1001,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift if (pmd_huge(pmd) || pmd_large(pmd)) { ret_pte = (pte_t *) pmdp; goto out; - } else if (is_hugepd(&pmd)) + } else if (is_hugepd(__hugepd(pmd_val(pmd)))) hpdp = (hugepd_t *)&pmd; else return pte_offset_kernel(&pmd, ea); @@ -1008,7 +1010,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift if (!hpdp) return NULL; - ret_pte = hugepte_offset(hpdp, ea, pdshift); + ret_pte = hugepte_offset(*hpdp, ea, pdshift); pdshift = hugepd_shift(*hpdp); out: if (shift) @@ -1038,14 +1040,6 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, if ((pte_val(pte) & mask) != mask) return 0; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - /* - * check for splitting here - */ - if (pmd_trans_splitting(pte_pmd(pte))) - return 0; -#endif - /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index cad68ff8eca5..a10be665b645 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -26,7 +26,6 @@ #include <linux/mm.h> #include <linux/stddef.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/highmem.h> #include <linux/initrd.h> #include <linux/pagemap.h> @@ -103,7 +102,7 @@ unsigned long __max_low_memory = MAX_LOW_MEM; /* * Check for command-line options that affect what MMU_init will do. */ -void MMU_setup(void) +void __init MMU_setup(void) { /* Check for nobats option (used in mapin_ram). */ if (strstr(boot_command_line, "nobats")) { @@ -195,15 +194,6 @@ void __init MMU_init(void) memblock_set_current_limit(lowmem_end_addr); } -/* This is only called until mem_init is done. */ -void __init *early_get_page(void) -{ - if (init_bootmem_done) - return alloc_bootmem_pages(PAGE_SIZE); - else - return __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); -} - #ifdef CONFIG_8xx /* No 8xx specific .c file to put that in ... */ void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 3481556a1880..10471f9bb63f 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -34,7 +34,6 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/delay.h> -#include <linux/bootmem.h> #include <linux/highmem.h> #include <linux/idr.h> #include <linux/nodemask.h> diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8ebaac75c940..b7285a5870f8 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -35,6 +35,7 @@ #include <linux/memblock.h> #include <linux/hugetlb.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/pgalloc.h> #include <asm/prom.h> @@ -60,7 +61,6 @@ #define CPU_FTR_NOEXECUTE 0 #endif -int init_bootmem_done; int mem_init_done; unsigned long long memory_limit; @@ -144,8 +144,17 @@ int arch_remove_memory(u64 start, u64 size) zone = page_zone(pfn_to_page(start_pfn)); ret = __remove_pages(zone, start_pfn, nr_pages); - if (!ret && (ppc_md.remove_memory)) - ret = ppc_md.remove_memory(start, size); + if (ret) + return ret; + + /* Remove htab bolted mappings for this section of memory */ + start = (unsigned long)__va(start); + ret = remove_section_mapping(start, start + size); + + /* Ensure all vmalloc mappings are flushed in case they also + * hit that section of memory + */ + vm_unmap_aliases(); return ret; } @@ -180,70 +189,23 @@ walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, } EXPORT_SYMBOL_GPL(walk_system_ram_range); -/* - * Initialize the bootmem system and give it all the memory we - * have available. If we are using highmem, we only put the - * lowmem into the bootmem system. - */ #ifndef CONFIG_NEED_MULTIPLE_NODES -void __init do_init_bootmem(void) +void __init initmem_init(void) { - unsigned long start, bootmap_pages; - unsigned long total_pages; - struct memblock_region *reg; - int boot_mapsize; - max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; - total_pages = (memblock_end_of_DRAM() - memstart_addr) >> PAGE_SHIFT; + min_low_pfn = MEMORY_START >> PAGE_SHIFT; #ifdef CONFIG_HIGHMEM - total_pages = total_lowmem >> PAGE_SHIFT; max_low_pfn = lowmem_end_addr >> PAGE_SHIFT; #endif - /* - * Find an area to use for the bootmem bitmap. Calculate the size of - * bitmap required as (Total Memory) / PAGE_SIZE / BITS_PER_BYTE. - * Add 1 additional page in case the address isn't page-aligned. - */ - bootmap_pages = bootmem_bootmap_pages(total_pages); - - start = memblock_alloc(bootmap_pages << PAGE_SHIFT, PAGE_SIZE); - - min_low_pfn = MEMORY_START >> PAGE_SHIFT; - boot_mapsize = init_bootmem_node(NODE_DATA(0), start >> PAGE_SHIFT, min_low_pfn, max_low_pfn); - /* Place all memblock_regions in the same node and merge contiguous * memblock_regions */ memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0); - /* Add all physical memory to the bootmem map, mark each area - * present. - */ -#ifdef CONFIG_HIGHMEM - free_bootmem_with_active_regions(0, lowmem_end_addr >> PAGE_SHIFT); - - /* reserve the sections we're already using */ - for_each_memblock(reserved, reg) { - unsigned long top = reg->base + reg->size - 1; - if (top < lowmem_end_addr) - reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); - else if (reg->base < lowmem_end_addr) { - unsigned long trunc_size = lowmem_end_addr - reg->base; - reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT); - } - } -#else - free_bootmem_with_active_regions(0, max_pfn); - - /* reserve the sections we're already using */ - for_each_memblock(reserved, reg) - reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); -#endif /* XXX need to clip this if using highmem? */ sparse_memory_present_with_active_regions(0); - - init_bootmem_done = 1; + sparse_init(); } /* mark pages that don't exist as nosave */ @@ -359,14 +321,6 @@ void __init paging_init(void) mark_nonram_nosave(); } -static void __init register_page_bootmem_info(void) -{ - int i; - - for_each_online_node(i) - register_page_bootmem_info_node(NODE_DATA(i)); -} - void __init mem_init(void) { /* @@ -379,7 +333,6 @@ void __init mem_init(void) swiotlb_init(0); #endif - register_page_bootmem_info(); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); set_max_mapnr(max_pfn); free_all_bootmem(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9d1dfdbe5bb..417b0a523a47 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -134,28 +134,6 @@ static int __init fake_numa_create_new_node(unsigned long end_pfn, return 0; } -/* - * get_node_active_region - Return active region containing pfn - * Active range returned is empty if none found. - * @pfn: The page to return the region for - * @node_ar: Returned set to the active region containing @pfn - */ -static void __init get_node_active_region(unsigned long pfn, - struct node_active_region *node_ar) -{ - unsigned long start_pfn, end_pfn; - int i, nid; - - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { - if (pfn >= start_pfn && pfn < end_pfn) { - node_ar->nid = nid; - node_ar->start_pfn = start_pfn; - node_ar->end_pfn = end_pfn; - break; - } - } -} - static void reset_numa_cpu_lookup_table(void) { unsigned int cpu; @@ -928,134 +906,48 @@ static void __init dump_numa_memory_topology(void) } } -/* - * Allocate some memory, satisfying the memblock or bootmem allocator where - * required. nid is the preferred node and end is the physical address of - * the highest address in the node. - * - * Returns the virtual address of the memory. - */ -static void __init *careful_zallocation(int nid, unsigned long size, - unsigned long align, - unsigned long end_pfn) -{ - void *ret; - int new_nid; - unsigned long ret_paddr; - - ret_paddr = __memblock_alloc_base(size, align, end_pfn << PAGE_SHIFT); - - /* retry over all memory */ - if (!ret_paddr) - ret_paddr = __memblock_alloc_base(size, align, memblock_end_of_DRAM()); - - if (!ret_paddr) - panic("numa.c: cannot allocate %lu bytes for node %d", - size, nid); - - ret = __va(ret_paddr); - - /* - * We initialize the nodes in numeric order: 0, 1, 2... - * and hand over control from the MEMBLOCK allocator to the - * bootmem allocator. If this function is called for - * node 5, then we know that all nodes <5 are using the - * bootmem allocator instead of the MEMBLOCK allocator. - * - * So, check the nid from which this allocation came - * and double check to see if we need to use bootmem - * instead of the MEMBLOCK. We don't free the MEMBLOCK memory - * since it would be useless. - */ - new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT); - if (new_nid < nid) { - ret = __alloc_bootmem_node(NODE_DATA(new_nid), - size, align, 0); - - dbg("alloc_bootmem %p %lx\n", ret, size); - } - - memset(ret, 0, size); - return ret; -} - static struct notifier_block ppc64_numa_nb = { .notifier_call = cpu_numa_callback, .priority = 1 /* Must run before sched domains notifier. */ }; -static void __init mark_reserved_regions_for_nid(int nid) +/* Initialize NODE_DATA for a node on the local memory */ +static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) { - struct pglist_data *node = NODE_DATA(nid); - struct memblock_region *reg; - - for_each_memblock(reserved, reg) { - unsigned long physbase = reg->base; - unsigned long size = reg->size; - unsigned long start_pfn = physbase >> PAGE_SHIFT; - unsigned long end_pfn = PFN_UP(physbase + size); - struct node_active_region node_ar; - unsigned long node_end_pfn = pgdat_end_pfn(node); - - /* - * Check to make sure that this memblock.reserved area is - * within the bounds of the node that we care about. - * Checking the nid of the start and end points is not - * sufficient because the reserved area could span the - * entire node. - */ - if (end_pfn <= node->node_start_pfn || - start_pfn >= node_end_pfn) - continue; - - get_node_active_region(start_pfn, &node_ar); - while (start_pfn < end_pfn && - node_ar.start_pfn < node_ar.end_pfn) { - unsigned long reserve_size = size; - /* - * if reserved region extends past active region - * then trim size to active region - */ - if (end_pfn > node_ar.end_pfn) - reserve_size = (node_ar.end_pfn << PAGE_SHIFT) - - physbase; - /* - * Only worry about *this* node, others may not - * yet have valid NODE_DATA(). - */ - if (node_ar.nid == nid) { - dbg("reserve_bootmem %lx %lx nid=%d\n", - physbase, reserve_size, node_ar.nid); - reserve_bootmem_node(NODE_DATA(node_ar.nid), - physbase, reserve_size, - BOOTMEM_DEFAULT); - } - /* - * if reserved region is contained in the active region - * then done. - */ - if (end_pfn <= node_ar.end_pfn) - break; - - /* - * reserved region extends past the active region - * get next active region that contains this - * reserved region - */ - start_pfn = node_ar.end_pfn; - physbase = start_pfn << PAGE_SHIFT; - size = size - reserve_size; - get_node_active_region(start_pfn, &node_ar); - } - } + u64 spanned_pages = end_pfn - start_pfn; + const size_t nd_size = roundup(sizeof(pg_data_t), SMP_CACHE_BYTES); + u64 nd_pa; + void *nd; + int tnid; + + if (spanned_pages) + pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n", + nid, start_pfn << PAGE_SHIFT, + (end_pfn << PAGE_SHIFT) - 1); + else + pr_info("Initmem setup node %d\n", nid); + + nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd = __va(nd_pa); + + /* report and initialize */ + pr_info(" NODE_DATA [mem %#010Lx-%#010Lx]\n", + nd_pa, nd_pa + nd_size - 1); + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); + if (tnid != nid) + pr_info(" NODE_DATA(%d) on node %d\n", nid, tnid); + + node_data[nid] = nd; + memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); + NODE_DATA(nid)->node_id = nid; + NODE_DATA(nid)->node_start_pfn = start_pfn; + NODE_DATA(nid)->node_spanned_pages = spanned_pages; } - -void __init do_init_bootmem(void) +void __init initmem_init(void) { int nid, cpu; - min_low_pfn = 0; max_low_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; max_pfn = max_low_pfn; @@ -1064,64 +956,18 @@ void __init do_init_bootmem(void) else dump_numa_memory_topology(); + memblock_dump_all(); + for_each_online_node(nid) { unsigned long start_pfn, end_pfn; - void *bootmem_vaddr; - unsigned long bootmap_pages; get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - - /* - * Allocate the node structure node local if possible - * - * Be careful moving this around, as it relies on all - * previous nodes' bootmem to be initialized and have - * all reserved areas marked. - */ - NODE_DATA(nid) = careful_zallocation(nid, - sizeof(struct pglist_data), - SMP_CACHE_BYTES, end_pfn); - - dbg("node %d\n", nid); - dbg("NODE_DATA() = %p\n", NODE_DATA(nid)); - - NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; - NODE_DATA(nid)->node_start_pfn = start_pfn; - NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; - - if (NODE_DATA(nid)->node_spanned_pages == 0) - continue; - - dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT); - dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT); - - bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); - bootmem_vaddr = careful_zallocation(nid, - bootmap_pages << PAGE_SHIFT, - PAGE_SIZE, end_pfn); - - dbg("bootmap_vaddr = %p\n", bootmem_vaddr); - - init_bootmem_node(NODE_DATA(nid), - __pa(bootmem_vaddr) >> PAGE_SHIFT, - start_pfn, end_pfn); - - free_bootmem_with_active_regions(nid, end_pfn); - /* - * Be very careful about moving this around. Future - * calls to careful_zallocation() depend on this getting - * done correctly. - */ - mark_reserved_regions_for_nid(nid); + setup_node_data(nid, start_pfn, end_pfn); sparse_memory_present_with_active_regions(nid); } - init_bootmem_done = 1; + sparse_init(); - /* - * Now bootmem is initialised we can create the node to cpumask - * lookup tables and setup the cpu callback to populate them. - */ setup_node_to_cpumask_map(); reset_numa_cpu_lookup_table(); diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index cf11342bf519..d545b1231594 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -100,12 +100,11 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add { pte_t *pte; extern int mem_init_done; - extern void *early_get_page(void); if (mem_init_done) { pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); } else { - pte = (pte_t *)early_get_page(); + pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); if (pte) clear_page(pte); } diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index c8d709ab489d..87ff0c1908a9 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -33,9 +33,9 @@ #include <linux/swap.h> #include <linux/stddef.h> #include <linux/vmalloc.h> -#include <linux/bootmem.h> #include <linux/memblock.h> #include <linux/slab.h> +#include <linux/hugetlb.h> #include <asm/pgalloc.h> #include <asm/page.h> @@ -51,6 +51,7 @@ #include <asm/cputable.h> #include <asm/sections.h> #include <asm/firmware.h> +#include <asm/dma.h> #include "mmu_decl.h" @@ -75,11 +76,7 @@ static __ref void *early_alloc_pgtable(unsigned long size) { void *pt; - if (init_bootmem_done) - pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS)); - else - pt = __va(memblock_alloc_base(size, size, - __pa(MAX_DMA_ADDRESS))); + pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); memset(pt, 0, size); return pt; @@ -113,10 +110,6 @@ int map_kernel_page(unsigned long ea, unsigned long pa, int flags) __pgprot(flags))); } else { #ifdef CONFIG_PPC_MMU_NOHASH - /* Warning ! This will blow up if bootmem is not initialized - * which our ppc64 code is keen to do that, we'll need to - * fix it and/or be more careful - */ pgdp = pgd_offset_k(ea); #ifdef PUD_TABLE_SIZE if (pgd_none(*pgdp)) { @@ -352,16 +345,31 @@ EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(__iounmap); EXPORT_SYMBOL(__iounmap_at); +#ifndef __PAGETABLE_PUD_FOLDED +/* 4 level page table */ +struct page *pgd_page(pgd_t pgd) +{ + if (pgd_huge(pgd)) + return pte_page(pgd_pte(pgd)); + return virt_to_page(pgd_page_vaddr(pgd)); +} +#endif + +struct page *pud_page(pud_t pud) +{ + if (pud_huge(pud)) + return pte_page(pud_pte(pud)); + return virt_to_page(pud_page_vaddr(pud)); +} + /* * For hugepage we have pfn in the pmd, we use PTE_RPN_SHIFT bits for flags * For PTE page, we have a PTE_FRAG_SIZE (4K) aligned virtual address. */ struct page *pmd_page(pmd_t pmd) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - if (pmd_trans_huge(pmd)) + if (pmd_trans_huge(pmd) || pmd_huge(pmd)) return pfn_to_page(pmd_pfn(pmd)); -#endif return virt_to_page(pmd_page_vaddr(pmd)); } diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index a6995d4e93d4..7c4f6690533a 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -339,7 +339,7 @@ static void power_pmu_bhrb_reset(void) static void power_pmu_bhrb_enable(struct perf_event *event) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); if (!ppmu->bhrb_nr) return; @@ -354,7 +354,7 @@ static void power_pmu_bhrb_enable(struct perf_event *event) static void power_pmu_bhrb_disable(struct perf_event *event) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); if (!ppmu->bhrb_nr) return; @@ -1144,7 +1144,7 @@ static void power_pmu_disable(struct pmu *pmu) if (!ppmu) return; local_irq_save(flags); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); if (!cpuhw->disabled) { /* @@ -1211,7 +1211,7 @@ static void power_pmu_enable(struct pmu *pmu) return; local_irq_save(flags); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); if (!cpuhw->disabled) goto out; @@ -1403,7 +1403,7 @@ static int power_pmu_add(struct perf_event *event, int ef_flags) * Add the event to the list (if there is room) * and check whether the total set is still feasible. */ - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); n0 = cpuhw->n_events; if (n0 >= ppmu->n_counter) goto out; @@ -1469,7 +1469,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) power_pmu_read(event); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); for (i = 0; i < cpuhw->n_events; ++i) { if (event == cpuhw->event[i]) { while (++i < cpuhw->n_events) { @@ -1575,7 +1575,7 @@ static void power_pmu_stop(struct perf_event *event, int ef_flags) */ static void power_pmu_start_txn(struct pmu *pmu) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); perf_pmu_disable(pmu); cpuhw->group_flag |= PERF_EVENT_TXN; @@ -1589,7 +1589,7 @@ static void power_pmu_start_txn(struct pmu *pmu) */ static void power_pmu_cancel_txn(struct pmu *pmu) { - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); cpuhw->group_flag &= ~PERF_EVENT_TXN; perf_pmu_enable(pmu); @@ -1607,7 +1607,7 @@ static int power_pmu_commit_txn(struct pmu *pmu) if (!ppmu) return -EAGAIN; - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); n = cpuhw->n_events; if (check_excludes(cpuhw->event, cpuhw->flags, 0, n)) return -EAGAIN; @@ -1964,7 +1964,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { struct cpu_hw_events *cpuhw; - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); power_pmu_bhrb_read(cpuhw); data.br_stack = &cpuhw->bhrb_stack; } @@ -2037,7 +2037,7 @@ static bool pmc_overflow(unsigned long val) static void perf_event_interrupt(struct pt_regs *regs) { int i, j; - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; unsigned long val[8]; int found, active; diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c index d35ae52c69dc..4acaea01fe03 100644 --- a/arch/powerpc/perf/core-fsl-emb.c +++ b/arch/powerpc/perf/core-fsl-emb.c @@ -210,7 +210,7 @@ static void fsl_emb_pmu_disable(struct pmu *pmu) unsigned long flags; local_irq_save(flags); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); if (!cpuhw->disabled) { cpuhw->disabled = 1; @@ -249,7 +249,7 @@ static void fsl_emb_pmu_enable(struct pmu *pmu) unsigned long flags; local_irq_save(flags); - cpuhw = &__get_cpu_var(cpu_hw_events); + cpuhw = this_cpu_ptr(&cpu_hw_events); if (!cpuhw->disabled) goto out; @@ -653,7 +653,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, static void perf_event_interrupt(struct pt_regs *regs) { int i; - struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events); + struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events); struct perf_event *event; unsigned long val; int found = 0; diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index 58db9d083969..c11ce6516c8f 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -94,7 +94,7 @@ static int avr_probe(struct i2c_client *client, { avr_i2c_client = client; ppc_md.restart = avr_reset_system; - ppc_md.power_off = avr_power_off_system; + pm_power_off = avr_power_off_system; return 0; } diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index e996e007bc44..711f3d352af7 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -18,7 +18,7 @@ #include <linux/irq.h> #include <linux/of_platform.h> #include <linux/fsl-diu-fb.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <sysdev/fsl_soc.h> #include <asm/cacheflush.h> @@ -297,14 +297,13 @@ static void __init mpc512x_setup_diu(void) * and so negatively affect boot time. Instead we reserve the * already configured frame buffer area so that it won't be * destroyed. The starting address of the area to reserve and - * also it's length is passed to reserve_bootmem(). It will be + * also it's length is passed to memblock_reserve(). It will be * freed later on first open of fbdev, when splash image is not * needed any more. */ if (diu_shared_fb.in_use) { - ret = reserve_bootmem(diu_shared_fb.fb_phys, - diu_shared_fb.fb_len, - BOOTMEM_EXCLUSIVE); + ret = memblock_reserve(diu_shared_fb.fb_phys, + diu_shared_fb.fb_len); if (ret) { pr_err("%s: reserve bootmem failed\n", __func__); diu_shared_fb.in_use = false; diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c index 3feffde9128d..6af651e69129 100644 --- a/arch/powerpc/platforms/52xx/efika.c +++ b/arch/powerpc/platforms/52xx/efika.c @@ -212,6 +212,8 @@ static int __init efika_probe(void) DMA_MODE_READ = 0x44; DMA_MODE_WRITE = 0x48; + pm_power_off = rtas_power_off; + return 1; } @@ -225,7 +227,6 @@ define_machine(efika) .init_IRQ = mpc52xx_init_irq, .get_irq = mpc52xx_get_irq, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .set_rtc_time = rtas_set_rtc_time, .get_rtc_time = rtas_get_rtc_time, diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 463fa91ee5b6..15e8021ddef9 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -167,10 +167,10 @@ static int mcu_probe(struct i2c_client *client, const struct i2c_device_id *id) if (ret) goto err; - /* XXX: this is potentially racy, but there is no lock for ppc_md */ - if (!ppc_md.power_off) { + /* XXX: this is potentially racy, but there is no lock for pm_power_off */ + if (!pm_power_off) { glob_mcu = mcu; - ppc_md.power_off = mcu_power_off; + pm_power_off = mcu_power_off; dev_info(&client->dev, "will provide power-off service\n"); } @@ -197,7 +197,7 @@ static int mcu_remove(struct i2c_client *client) device_remove_file(&client->dev, &dev_attr_status); if (glob_mcu == mcu) { - ppc_md.power_off = NULL; + pm_power_off = NULL; glob_mcu = NULL; } diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index e56b89a792ed..1f309ccb096e 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -170,7 +170,7 @@ static int __init corenet_generic_probe(void) ppc_md.get_irq = ehv_pic_get_irq; ppc_md.restart = fsl_hv_restart; - ppc_md.power_off = fsl_hv_halt; + pm_power_off = fsl_hv_halt; ppc_md.halt = fsl_hv_halt; #ifdef CONFIG_SMP /* diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c index 8162b0412117..e149c9ec26ae 100644 --- a/arch/powerpc/platforms/85xx/sgy_cts1000.c +++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c @@ -120,7 +120,7 @@ static int gpio_halt_probe(struct platform_device *pdev) /* Register our halt function */ ppc_md.halt = gpio_halt_cb; - ppc_md.power_off = gpio_halt_cb; + pm_power_off = gpio_halt_cb; printk(KERN_INFO "gpio-halt: registered GPIO %d (%d trigger, %d" " irq).\n", gpio, trigger, irq); @@ -137,7 +137,7 @@ static int gpio_halt_remove(struct platform_device *pdev) free_irq(irq, halt_node); ppc_md.halt = NULL; - ppc_md.power_off = NULL; + pm_power_off = NULL; gpio_free(gpio); diff --git a/arch/powerpc/platforms/cell/celleb_scc_epci.c b/arch/powerpc/platforms/cell/celleb_scc_epci.c index 844c0facb4f7..9438bbed402f 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_epci.c +++ b/arch/powerpc/platforms/cell/celleb_scc_epci.c @@ -25,7 +25,6 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/pci_regs.h> -#include <linux/bootmem.h> #include <asm/io.h> #include <asm/irq.h> diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c index 4278acfa2ede..f22387598040 100644 --- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c +++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c @@ -25,7 +25,6 @@ #include <linux/string.h> #include <linux/slab.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/delay.h> #include <linux/interrupt.h> diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c index 34e8ce2976aa..90be8ec51686 100644 --- a/arch/powerpc/platforms/cell/celleb_setup.c +++ b/arch/powerpc/platforms/cell/celleb_setup.c @@ -142,6 +142,7 @@ static int __init celleb_probe_beat(void) powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS | FW_FEATURE_BEAT | FW_FEATURE_LPAR; hpte_init_beat_v3(); + pm_power_off = beat_power_off; return 1; } @@ -190,6 +191,7 @@ static int __init celleb_probe_native(void) powerpc_firmware_features |= FW_FEATURE_CELLEB_ALWAYS; hpte_init_native(); + pm_power_off = rtas_power_off; return 1; } @@ -204,7 +206,6 @@ define_machine(celleb_beat) { .setup_arch = celleb_setup_arch_beat, .show_cpuinfo = celleb_show_cpuinfo, .restart = beat_restart, - .power_off = beat_power_off, .halt = beat_halt, .get_rtc_time = beat_get_rtc_time, .set_rtc_time = beat_set_rtc_time, @@ -230,7 +231,6 @@ define_machine(celleb_native) { .setup_arch = celleb_setup_arch_native, .show_cpuinfo = celleb_show_cpuinfo, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 8a106b4172e0..4c11421847be 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -82,7 +82,7 @@ static void iic_unmask(struct irq_data *d) static void iic_eoi(struct irq_data *d) { - struct iic *iic = &__get_cpu_var(cpu_iic); + struct iic *iic = this_cpu_ptr(&cpu_iic); out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]); BUG_ON(iic->eoi_ptr < 0); } @@ -148,7 +148,7 @@ static unsigned int iic_get_irq(void) struct iic *iic; unsigned int virq; - iic = &__get_cpu_var(cpu_iic); + iic = this_cpu_ptr(&cpu_iic); *(unsigned long *) &pending = in_be64((u64 __iomem *) &iic->regs->pending_destr); if (!(pending.flags & CBE_IIC_IRQ_VALID)) @@ -163,7 +163,7 @@ static unsigned int iic_get_irq(void) void iic_setup_cpu(void) { - out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff); + out_be64(this_cpu_ptr(&cpu_iic.regs->prio), 0xff); } u8 iic_get_target_id(int cpu) diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c index 6e3409d590ac..d328140dc6f5 100644 --- a/arch/powerpc/platforms/cell/qpace_setup.c +++ b/arch/powerpc/platforms/cell/qpace_setup.c @@ -127,6 +127,7 @@ static int __init qpace_probe(void) return 0; hpte_init_native(); + pm_power_off = rtas_power_off; return 1; } @@ -137,7 +138,6 @@ define_machine(qpace) { .setup_arch = qpace_setup_arch, .show_cpuinfo = qpace_show_cpuinfo, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 6ae25fb62015..d62aa982d530 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -259,6 +259,7 @@ static int __init cell_probe(void) return 0; hpte_init_native(); + pm_power_off = rtas_power_off; return 1; } @@ -269,7 +270,6 @@ define_machine(cell) { .setup_arch = cell_setup_arch, .show_cpuinfo = cell_show_cpuinfo, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index 5b77b1919fd2..860a59eb8ea2 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -585,6 +585,8 @@ static int __init chrp_probe(void) DMA_MODE_READ = 0x44; DMA_MODE_WRITE = 0x48; + pm_power_off = rtas_power_off; + return 1; } @@ -597,7 +599,6 @@ define_machine(chrp) { .show_cpuinfo = chrp_show_cpuinfo, .init_IRQ = chrp_init_IRQ, .restart = rtas_restart, - .power_off = rtas_power_off, .halt = rtas_halt, .time_init = chrp_time_init, .set_rtc_time = chrp_set_rtc_time, diff --git a/arch/powerpc/platforms/embedded6xx/gamecube.c b/arch/powerpc/platforms/embedded6xx/gamecube.c index bd4ba5d7d568..fe0ed6ee285e 100644 --- a/arch/powerpc/platforms/embedded6xx/gamecube.c +++ b/arch/powerpc/platforms/embedded6xx/gamecube.c @@ -67,6 +67,8 @@ static int __init gamecube_probe(void) if (!of_flat_dt_is_compatible(dt_root, "nintendo,gamecube")) return 0; + pm_power_off = gamecube_power_off; + return 1; } @@ -80,7 +82,6 @@ define_machine(gamecube) { .probe = gamecube_probe, .init_early = gamecube_init_early, .restart = gamecube_restart, - .power_off = gamecube_power_off, .halt = gamecube_halt, .init_IRQ = flipper_pic_probe, .get_irq = flipper_pic_get_irq, diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index 168e1d80b2e5..540eeb58d3f0 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -147,6 +147,9 @@ static int __init linkstation_probe(void) if (!of_flat_dt_is_compatible(root, "linkstation")) return 0; + + pm_power_off = linkstation_power_off; + return 1; } @@ -158,7 +161,6 @@ define_machine(linkstation){ .show_cpuinfo = linkstation_show_cpuinfo, .get_irq = mpic_get_irq, .restart = linkstation_restart, - .power_off = linkstation_power_off, .halt = linkstation_halt, .calibrate_decr = generic_calibrate_decr, }; diff --git a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c index 20a8ed91962e..7feb325b636b 100644 --- a/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c +++ b/arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c @@ -247,7 +247,7 @@ void __init ug_udbg_init(void) np = of_find_compatible_node(NULL, NULL, "nintendo,flipper-exi"); if (!np) { udbg_printf("%s: EXI node not found\n", __func__); - goto done; + goto out; } exi_io_base = ug_udbg_setup_exi_io_base(np); @@ -267,8 +267,8 @@ void __init ug_udbg_init(void) } done: - if (np) - of_node_put(np); + of_node_put(np); +out: return; } diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 388e29bab8f6..352592d3e44e 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -211,6 +211,8 @@ static int __init wii_probe(void) if (!of_flat_dt_is_compatible(dt_root, "nintendo,wii")) return 0; + pm_power_off = wii_power_off; + return 1; } @@ -226,7 +228,6 @@ define_machine(wii) { .init_early = wii_init_early, .setup_arch = wii_setup_arch, .restart = wii_restart, - .power_off = wii_power_off, .halt = wii_halt, .init_IRQ = wii_pic_probe, .get_irq = flipper_pic_get_irq, diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index f7136aae8bbf..d3a13067ec42 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -15,7 +15,6 @@ #include <linux/delay.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/irq.h> #include <asm/sections.h> diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c index cb1b0b35a0c6..56b85cd61aaf 100644 --- a/arch/powerpc/platforms/maple/setup.c +++ b/arch/powerpc/platforms/maple/setup.c @@ -169,7 +169,7 @@ static void __init maple_use_rtas_reboot_and_halt_if_present(void) if (rtas_service_present("system-reboot") && rtas_service_present("power-off")) { ppc_md.restart = rtas_restart; - ppc_md.power_off = rtas_power_off; + pm_power_off = rtas_power_off; ppc_md.halt = rtas_halt; } } @@ -312,6 +312,7 @@ static int __init maple_probe(void) alloc_dart_table(); hpte_init_native(); + pm_power_off = maple_power_off; return 1; } @@ -325,7 +326,6 @@ define_machine(maple) { .pci_irq_fixup = maple_pci_irq_fixup, .pci_get_legacy_ide_irq = maple_pci_get_legacy_ide_irq, .restart = maple_restart, - .power_off = maple_power_off, .halt = maple_halt, .get_boot_time = maple_get_boot_time, .set_rtc_time = maple_set_rtc_time, diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 7e868ccf3b0d..04702db35d45 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -15,7 +15,6 @@ #include <linux/delay.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/irq.h> #include <linux/of_pci.h> diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index b127a29ac526..713d36d45d1d 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -632,6 +632,8 @@ static int __init pmac_probe(void) smu_cmdbuf_abs = memblock_alloc_base(4096, 4096, 0x80000000UL); #endif /* CONFIG_PMAC_SMU */ + pm_power_off = pmac_power_off; + return 1; } @@ -663,7 +665,6 @@ define_machine(powermac) { .get_irq = NULL, /* changed later */ .pci_irq_fixup = pmac_pci_irq_fixup, .restart = pmac_restart, - .power_off = pmac_power_off, .halt = pmac_halt, .time_init = pmac_time_init, .get_boot_time = pmac_get_boot_time, diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index eba9cb10619c..db3803e21483 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/io.h> diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c index e462ab947d16..693b6cdac691 100644 --- a/arch/powerpc/platforms/powernv/opal-async.c +++ b/arch/powerpc/platforms/powernv/opal-async.c @@ -71,6 +71,7 @@ int opal_async_get_token_interruptible(void) return token; } +EXPORT_SYMBOL_GPL(opal_async_get_token_interruptible); int __opal_async_release_token(int token) { @@ -102,6 +103,7 @@ int opal_async_release_token(int token) return 0; } +EXPORT_SYMBOL_GPL(opal_async_release_token); int opal_async_wait_response(uint64_t token, struct opal_msg *msg) { @@ -120,6 +122,7 @@ int opal_async_wait_response(uint64_t token, struct opal_msg *msg) return 0; } +EXPORT_SYMBOL_GPL(opal_async_wait_response); static int opal_async_comp_event(struct notifier_block *nb, unsigned long msg_type, void *msg) diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c index ad4b31df779a..e4169d68cb32 100644 --- a/arch/powerpc/platforms/powernv/opal-lpc.c +++ b/arch/powerpc/platforms/powernv/opal-lpc.c @@ -216,14 +216,54 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf, &data, len); if (rc) return -ENXIO; + + /* + * Now there is some trickery with the data returned by OPAL + * as it's the desired data right justified in a 32-bit BE + * word. + * + * This is a very bad interface and I'm to blame for it :-( + * + * So we can't just apply a 32-bit swap to what comes from OPAL, + * because user space expects the *bytes* to be in their proper + * respective positions (ie, LPC position). + * + * So what we really want to do here is to shift data right + * appropriately on a LE kernel. + * + * IE. If the LPC transaction has bytes B0, B1, B2 and B3 in that + * order, we have in memory written to by OPAL at the "data" + * pointer: + * + * Bytes: OPAL "data" LE "data" + * 32-bit: B0 B1 B2 B3 B0B1B2B3 B3B2B1B0 + * 16-bit: B0 B1 0000B0B1 B1B00000 + * 8-bit: B0 000000B0 B0000000 + * + * So a BE kernel will have the leftmost of the above in the MSB + * and rightmost in the LSB and can just then "cast" the u32 "data" + * down to the appropriate quantity and write it. + * + * However, an LE kernel can't. It doesn't need to swap because a + * load from data followed by a store to user are going to preserve + * the byte ordering which is the wire byte order which is what the + * user wants, but in order to "crop" to the right size, we need to + * shift right first. + */ switch(len) { case 4: rc = __put_user((u32)data, (u32 __user *)ubuf); break; case 2: +#ifdef __LITTLE_ENDIAN__ + data >>= 16; +#endif rc = __put_user((u16)data, (u16 __user *)ubuf); break; default: +#ifdef __LITTLE_ENDIAN__ + data >>= 24; +#endif rc = __put_user((u8)data, (u8 __user *)ubuf); break; } @@ -263,12 +303,31 @@ static ssize_t lpc_debug_write(struct file *filp, const char __user *ubuf, else if (todo > 1 && (pos & 1) == 0) len = 2; } + + /* + * Similarly to the read case, we have some trickery here but + * it's different to handle. We need to pass the value to OPAL in + * a register whose layout depends on the access size. We want + * to reproduce the memory layout of the user, however we aren't + * doing a load from user and a store to another memory location + * which would achieve that. Here we pass the value to OPAL via + * a register which is expected to contain the "BE" interpretation + * of the byte sequence. IE: for a 32-bit access, byte 0 should be + * in the MSB. So here we *do* need to byteswap on LE. + * + * User bytes: LE "data" OPAL "data" + * 32-bit: B0 B1 B2 B3 B3B2B1B0 B0B1B2B3 + * 16-bit: B0 B1 0000B1B0 0000B0B1 + * 8-bit: B0 000000B0 000000B0 + */ switch(len) { case 4: rc = __get_user(data, (u32 __user *)ubuf); + data = cpu_to_be32(data); break; case 2: rc = __get_user(data, (u16 __user *)ubuf); + data = cpu_to_be16(data); break; default: rc = __get_user(data, (u8 __user *)ubuf); diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index 499707ddaa9c..37dbee15769f 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -15,6 +15,8 @@ #include <linux/bcd.h> #include <linux/rtc.h> #include <linux/delay.h> +#include <linux/platform_device.h> +#include <linux/of_platform.h> #include <asm/opal.h> #include <asm/firmware.h> @@ -43,7 +45,7 @@ unsigned long __init opal_get_boot_time(void) long rc = OPAL_BUSY; if (!opal_check_token(OPAL_RTC_READ)) - goto out; + return 0; while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); @@ -53,62 +55,33 @@ unsigned long __init opal_get_boot_time(void) mdelay(10); } if (rc != OPAL_SUCCESS) - goto out; + return 0; y_m_d = be32_to_cpu(__y_m_d); h_m_s_ms = be64_to_cpu(__h_m_s_ms); opal_to_tm(y_m_d, h_m_s_ms, &tm); return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec); -out: - ppc_md.get_rtc_time = NULL; - ppc_md.set_rtc_time = NULL; - return 0; } -void opal_get_rtc_time(struct rtc_time *tm) +static __init int opal_time_init(void) { - long rc = OPAL_BUSY; - u32 y_m_d; - u64 h_m_s_ms; - __be32 __y_m_d; - __be64 __h_m_s_ms; + struct platform_device *pdev; + struct device_node *rtc; - while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) - opal_poll_events(NULL); + rtc = of_find_node_by_path("/ibm,opal/rtc"); + if (rtc) { + pdev = of_platform_device_create(rtc, "opal-rtc", NULL); + of_node_put(rtc); + } else { + if (opal_check_token(OPAL_RTC_READ) || + opal_check_token(OPAL_READ_TPO)) + pdev = platform_device_register_simple("opal-rtc", -1, + NULL, 0); else - mdelay(10); + return -ENODEV; } - if (rc != OPAL_SUCCESS) - return; - y_m_d = be32_to_cpu(__y_m_d); - h_m_s_ms = be64_to_cpu(__h_m_s_ms); - opal_to_tm(y_m_d, h_m_s_ms, tm); -} - -int opal_set_rtc_time(struct rtc_time *tm) -{ - long rc = OPAL_BUSY; - u32 y_m_d = 0; - u64 h_m_s_ms = 0; - - y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24; - y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16; - y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8; - y_m_d |= ((u32)bin2bcd(tm->tm_mday)); - - h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56; - h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48; - h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40; - while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { - rc = opal_rtc_write(y_m_d, h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) - opal_poll_events(NULL); - else - mdelay(10); - } - return rc == OPAL_SUCCESS ? 0 : -EIO; + return PTR_ERR_OR_ZERO(pdev); } +machine_subsys_initcall(powernv, opal_time_init); diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c index ae14c40b4b1c..e11273b2386d 100644 --- a/arch/powerpc/platforms/powernv/opal-tracepoints.c +++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c @@ -48,7 +48,7 @@ void __trace_opal_entry(unsigned long opcode, unsigned long *args) local_irq_save(flags); - depth = &__get_cpu_var(opal_trace_depth); + depth = this_cpu_ptr(&opal_trace_depth); if (*depth) goto out; @@ -69,7 +69,7 @@ void __trace_opal_exit(long opcode, unsigned long retval) local_irq_save(flags); - depth = &__get_cpu_var(opal_trace_depth); + depth = this_cpu_ptr(&opal_trace_depth); if (*depth) goto out; diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index feb549aa3eea..0a299be588af 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -18,7 +18,7 @@ .section ".text" #ifdef CONFIG_TRACEPOINTS -#ifdef CONFIG_JUMP_LABEL +#ifdef HAVE_JUMP_LABEL #define OPAL_BRANCH(LABEL) \ ARCH_STATIC_BRANCH(LABEL, opal_tracepoint_key) #else @@ -250,3 +250,7 @@ OPAL_CALL(opal_handle_hmi, OPAL_HANDLE_HMI); OPAL_CALL(opal_register_dump_region, OPAL_REGISTER_DUMP_REGION); OPAL_CALL(opal_unregister_dump_region, OPAL_UNREGISTER_DUMP_REGION); OPAL_CALL(opal_pci_set_phb_cxl_mode, OPAL_PCI_SET_PHB_CXL_MODE); +OPAL_CALL(opal_tpo_write, OPAL_WRITE_TPO); +OPAL_CALL(opal_tpo_read, OPAL_READ_TPO); +OPAL_CALL(opal_ipmi_send, OPAL_IPMI_SEND); +OPAL_CALL(opal_ipmi_recv, OPAL_IPMI_RECV); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index d019b081df9d..a1c37f9d60d2 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -644,6 +644,16 @@ static void __init opal_dump_region_init(void) pr_warn("DUMP: Failed to register kernel log buffer. " "rc = %d\n", rc); } + +static void opal_ipmi_init(struct device_node *opal_node) +{ + struct device_node *np; + + for_each_child_of_node(opal_node, np) + if (of_device_is_compatible(np, "ibm,opal-ipmi")) + of_platform_device_create(np, NULL, NULL); +} + static int __init opal_init(void) { struct device_node *np, *consoles; @@ -707,6 +717,8 @@ static int __init opal_init(void) opal_msglog_init(); } + opal_ipmi_init(opal_node); + return 0; } machine_subsys_initcall(powernv, opal_init); @@ -742,6 +754,8 @@ void opal_shutdown(void) /* Export this so that test modules can use it */ EXPORT_SYMBOL_GPL(opal_invalid_call); +EXPORT_SYMBOL_GPL(opal_ipmi_send); +EXPORT_SYMBOL_GPL(opal_ipmi_recv); /* Convert a region of vmalloc memory to an opal sg list */ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, @@ -805,3 +819,9 @@ void opal_free_sg_list(struct opal_sg_list *sg) sg = NULL; } } + +EXPORT_SYMBOL_GPL(opal_poll_events); +EXPORT_SYMBOL_GPL(opal_rtc_read); +EXPORT_SYMBOL_GPL(opal_rtc_write); +EXPORT_SYMBOL_GPL(opal_tpo_read); +EXPORT_SYMBOL_GPL(opal_tpo_write); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 468a0f23c7f2..d03503515692 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -91,6 +91,24 @@ static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)); } +static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no) +{ + if (!(pe_no >= 0 && pe_no < phb->ioda.total_pe)) { + pr_warn("%s: Invalid PE %d on PHB#%x\n", + __func__, pe_no, phb->hose->global_number); + return; + } + + if (test_and_set_bit(pe_no, phb->ioda.pe_alloc)) { + pr_warn("%s: PE %d was assigned on PHB#%x\n", + __func__, pe_no, phb->hose->global_number); + return; + } + + phb->ioda.pe_array[pe_no].phb = phb; + phb->ioda.pe_array[pe_no].pe_number = pe_no; +} + static int pnv_ioda_alloc_pe(struct pnv_phb *phb) { unsigned long pe; @@ -172,7 +190,7 @@ fail: return -EIO; } -static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb) +static void pnv_ioda2_reserve_m64_pe(struct pnv_phb *phb) { resource_size_t sgsz = phb->ioda.m64_segsize; struct pci_dev *pdev; @@ -185,16 +203,15 @@ static void pnv_ioda2_alloc_m64_pe(struct pnv_phb *phb) * instead of root bus. */ list_for_each_entry(pdev, &phb->hose->bus->devices, bus_list) { - for (i = PCI_BRIDGE_RESOURCES; - i <= PCI_BRIDGE_RESOURCE_END; i++) { - r = &pdev->resource[i]; + for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) { + r = &pdev->resource[PCI_BRIDGE_RESOURCES + i]; if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags)) continue; base = (r->start - phb->ioda.m64_base) / sgsz; for (step = 0; step < resource_size(r) / sgsz; step++) - set_bit(base + step, phb->ioda.pe_alloc); + pnv_ioda_reserve_pe(phb, base + step); } } } @@ -287,8 +304,6 @@ done: while ((i = find_next_bit(pe_alloc, phb->ioda.total_pe, i + 1)) < phb->ioda.total_pe) { pe = &phb->ioda.pe_array[i]; - pe->phb = phb; - pe->pe_number = i; if (!master_pe) { pe->flags |= PNV_IODA_PE_MASTER; @@ -313,6 +328,12 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) const u32 *r; u64 pci_addr; + /* FIXME: Support M64 for P7IOC */ + if (phb->type != PNV_PHB_IODA2) { + pr_info(" Not support M64 window\n"); + return; + } + if (!firmware_has_feature(FW_FEATURE_OPALv3)) { pr_info(" Firmware too old to support M64 window\n"); return; @@ -325,12 +346,6 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) return; } - /* FIXME: Support M64 for P7IOC */ - if (phb->type != PNV_PHB_IODA2) { - pr_info(" Not support M64 window\n"); - return; - } - res = &hose->mem_resources[1]; res->start = of_translate_address(dn, r + 2); res->end = res->start + of_read_number(r + 4, 2) - 1; @@ -345,7 +360,7 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) /* Use last M64 BAR to cover M64 window */ phb->ioda.m64_bar_idx = 15; phb->init_m64 = pnv_ioda2_init_m64; - phb->alloc_m64_pe = pnv_ioda2_alloc_m64_pe; + phb->reserve_m64_pe = pnv_ioda2_reserve_m64_pe; phb->pick_m64_pe = pnv_ioda2_pick_m64_pe; } @@ -358,7 +373,9 @@ static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no) /* Fetch master PE */ if (pe->flags & PNV_IODA_PE_SLAVE) { pe = pe->master; - WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER)); + if (WARN_ON(!pe || !(pe->flags & PNV_IODA_PE_MASTER))) + return; + pe_no = pe->pe_number; } @@ -507,6 +524,106 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) } #endif /* CONFIG_PCI_MSI */ +static int pnv_ioda_set_one_peltv(struct pnv_phb *phb, + struct pnv_ioda_pe *parent, + struct pnv_ioda_pe *child, + bool is_add) +{ + const char *desc = is_add ? "adding" : "removing"; + uint8_t op = is_add ? OPAL_ADD_PE_TO_DOMAIN : + OPAL_REMOVE_PE_FROM_DOMAIN; + struct pnv_ioda_pe *slave; + long rc; + + /* Parent PE affects child PE */ + rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number, + child->pe_number, op); + if (rc != OPAL_SUCCESS) { + pe_warn(child, "OPAL error %ld %s to parent PELTV\n", + rc, desc); + return -ENXIO; + } + + if (!(child->flags & PNV_IODA_PE_MASTER)) + return 0; + + /* Compound case: parent PE affects slave PEs */ + list_for_each_entry(slave, &child->slaves, list) { + rc = opal_pci_set_peltv(phb->opal_id, parent->pe_number, + slave->pe_number, op); + if (rc != OPAL_SUCCESS) { + pe_warn(slave, "OPAL error %ld %s to parent PELTV\n", + rc, desc); + return -ENXIO; + } + } + + return 0; +} + +static int pnv_ioda_set_peltv(struct pnv_phb *phb, + struct pnv_ioda_pe *pe, + bool is_add) +{ + struct pnv_ioda_pe *slave; + struct pci_dev *pdev; + int ret; + + /* + * Clear PE frozen state. If it's master PE, we need + * clear slave PE frozen state as well. + */ + if (is_add) { + opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + if (pe->flags & PNV_IODA_PE_MASTER) { + list_for_each_entry(slave, &pe->slaves, list) + opal_pci_eeh_freeze_clear(phb->opal_id, + slave->pe_number, + OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + } + } + + /* + * Associate PE in PELT. We need add the PE into the + * corresponding PELT-V as well. Otherwise, the error + * originated from the PE might contribute to other + * PEs. + */ + ret = pnv_ioda_set_one_peltv(phb, pe, pe, is_add); + if (ret) + return ret; + + /* For compound PEs, any one affects all of them */ + if (pe->flags & PNV_IODA_PE_MASTER) { + list_for_each_entry(slave, &pe->slaves, list) { + ret = pnv_ioda_set_one_peltv(phb, slave, pe, is_add); + if (ret) + return ret; + } + } + + if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS)) + pdev = pe->pbus->self; + else + pdev = pe->pdev->bus->self; + while (pdev) { + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *parent; + + if (pdn && pdn->pe_number != IODA_INVALID_PE) { + parent = &phb->ioda.pe_array[pdn->pe_number]; + ret = pnv_ioda_set_one_peltv(phb, parent, pe, is_add); + if (ret) + return ret; + } + + pdev = pdev->bus->self; + } + + return 0; +} + static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { struct pci_dev *parent; @@ -561,48 +678,36 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) return -ENXIO; } - rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number, - pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); - if (rc) - pe_warn(pe, "OPAL error %d adding self to PELTV\n", rc); - opal_pci_eeh_freeze_clear(phb->opal_id, pe->pe_number, - OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); + /* Configure PELTV */ + pnv_ioda_set_peltv(phb, pe, true); - /* Add to all parents PELT-V */ - while (parent) { - struct pci_dn *pdn = pci_get_pdn(parent); - if (pdn && pdn->pe_number != IODA_INVALID_PE) { - rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number, - pe->pe_number, OPAL_ADD_PE_TO_DOMAIN); - /* XXX What to do in case of error ? */ - } - parent = parent->bus->self; - } /* Setup reverse map */ for (rid = pe->rid; rid < rid_end; rid++) phb->ioda.pe_rmap[rid] = pe->pe_number; /* Setup one MVTs on IODA1 */ - if (phb->type == PNV_PHB_IODA1) { - pe->mve_number = pe->pe_number; - rc = opal_pci_set_mve(phb->opal_id, pe->mve_number, - pe->pe_number); + if (phb->type != PNV_PHB_IODA1) { + pe->mve_number = 0; + goto out; + } + + pe->mve_number = pe->pe_number; + rc = opal_pci_set_mve(phb->opal_id, pe->mve_number, pe->pe_number); + if (rc != OPAL_SUCCESS) { + pe_err(pe, "OPAL error %ld setting up MVE %d\n", + rc, pe->mve_number); + pe->mve_number = -1; + } else { + rc = opal_pci_set_mve_enable(phb->opal_id, + pe->mve_number, OPAL_ENABLE_MVE); if (rc) { - pe_err(pe, "OPAL error %ld setting up MVE %d\n", + pe_err(pe, "OPAL error %ld enabling MVE %d\n", rc, pe->mve_number); pe->mve_number = -1; - } else { - rc = opal_pci_set_mve_enable(phb->opal_id, - pe->mve_number, OPAL_ENABLE_MVE); - if (rc) { - pe_err(pe, "OPAL error %ld enabling MVE %d\n", - rc, pe->mve_number); - pe->mve_number = -1; - } } - } else if (phb->type == PNV_PHB_IODA2) - pe->mve_number = 0; + } +out: return 0; } @@ -837,8 +942,8 @@ static void pnv_pci_ioda_setup_PEs(void) phb = hose->private_data; /* M64 layout might affect PE allocation */ - if (phb->alloc_m64_pe) - phb->alloc_m64_pe(phb); + if (phb->reserve_m64_pe) + phb->reserve_m64_pe(phb); pnv_ioda_setup_PEs(hose->bus); } @@ -2000,8 +2105,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, ioda_eeh_phb_reset(hose, OPAL_DEASSERT_RESET); } - /* Configure M64 window */ - if (phb->init_m64 && phb->init_m64(phb)) + /* Remove M64 resource if we can't configure it successfully */ + if (!phb->init_m64 || phb->init_m64(phb)) hose->mem_resources[1].flags = 0; } diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c index 94ce3481490b..3336fcbdd08a 100644 --- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c +++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c @@ -196,6 +196,22 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) hub_id = be64_to_cpup(prop64); pr_info(" HUB-ID : 0x%016llx\n", hub_id); + /* Count child PHBs and calculate TCE space per PHB */ + for_each_child_of_node(np, phbn) { + if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || + of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) + phb_count++; + } + + if (phb_count <= 0) { + pr_info(" No PHBs for Hub %s\n", np->full_name); + return; + } + + tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count); + pr_info(" Allocating %lld MB of TCE memory per PHB\n", + tce_per_phb >> 20); + /* Currently allocate 16M of TCE memory for every Hub * * XXX TODO: Make it chip local if possible @@ -215,18 +231,6 @@ void __init pnv_pci_init_p5ioc2_hub(struct device_node *np) return; } - /* Count child PHBs */ - for_each_child_of_node(np, phbn) { - if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || - of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) - phb_count++; - } - - /* Calculate how much TCE space we can give per PHB */ - tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count); - pr_info(" Allocating %lld MB of TCE memory per PHB\n", - tce_per_phb >> 20); - /* Initialize PHBs */ for_each_child_of_node(np, phbn) { if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") || diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b2187d0068b8..ba7452708db3 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -16,7 +16,6 @@ #include <linux/delay.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/bootmem.h> #include <linux/irq.h> #include <linux/io.h> #include <linux/msi.h> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 34d29eb2a4de..6c02ff8dd69f 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -130,7 +130,7 @@ struct pnv_phb { u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); void (*shutdown)(struct pnv_phb *phb); int (*init_m64)(struct pnv_phb *phb); - void (*alloc_m64_pe)(struct pnv_phb *phb); + void (*reserve_m64_pe)(struct pnv_phb *phb); int (*pick_m64_pe)(struct pnv_phb *phb, struct pci_bus *bus, int all); int (*get_pe_state)(struct pnv_phb *phb, int pe_no); void (*freeze_pe)(struct pnv_phb *phb, int pe_no); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 3f9546d8a51f..30b1c3e298a6 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -265,10 +265,8 @@ static unsigned long pnv_memory_block_size(void) static void __init pnv_setup_machdep_opal(void) { ppc_md.get_boot_time = opal_get_boot_time; - ppc_md.get_rtc_time = opal_get_rtc_time; - ppc_md.set_rtc_time = opal_set_rtc_time; ppc_md.restart = pnv_restart; - ppc_md.power_off = pnv_power_off; + pm_power_off = pnv_power_off; ppc_md.halt = pnv_halt; ppc_md.machine_check_exception = opal_machine_check; ppc_md.mce_check_early_recovery = opal_mce_check_early_recovery; @@ -285,7 +283,7 @@ static void __init pnv_setup_machdep_rtas(void) ppc_md.set_rtc_time = rtas_set_rtc_time; } ppc_md.restart = rtas_restart; - ppc_md.power_off = rtas_power_off; + pm_power_off = rtas_power_off; ppc_md.halt = rtas_halt; } #endif /* CONFIG_PPC_POWERNV_RTAS */ diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index 5f3b23220b8e..a6c42f34303a 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -711,7 +711,7 @@ void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq) static unsigned int ps3_get_irq(void) { - struct ps3_private *pd = &__get_cpu_var(ps3_private); + struct ps3_private *pd = this_cpu_ptr(&ps3_private); u64 x = (pd->bmp.status & pd->bmp.mask); unsigned int plug; diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 3f509f86432c..009a2004b876 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -248,6 +248,7 @@ static int __init ps3_probe(void) ps3_mm_init(); ps3_mm_vas_create(&htab_size); ps3_hpte_init(htab_size); + pm_power_off = ps3_power_off; DBG(" <- %s:%d\n", __func__, __LINE__); return 1; @@ -278,7 +279,6 @@ define_machine(ps3) { .calibrate_decr = ps3_calibrate_decr, .progress = ps3_progress, .restart = ps3_restart, - .power_off = ps3_power_off, .halt = ps3_halt, #if defined(CONFIG_KEXEC) .kexec_cpu_down = ps3_kexec_cpu_down, diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 6ad83bd11fe2..c22bb1b4beb8 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -382,7 +382,7 @@ static int dlpar_online_cpu(struct device_node *dn) BUG_ON(get_cpu_current_state(cpu) != CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_up(cpu); + rc = device_online(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); @@ -467,7 +467,7 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); cpu_maps_update_done(); - rc = cpu_down(cpu); + rc = device_offline(get_cpu_device(cpu)); if (rc) goto out; cpu_maps_update_begin(); diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c index 1062f71f5a85..39049e4884fb 100644 --- a/arch/powerpc/platforms/pseries/dtl.c +++ b/arch/powerpc/platforms/pseries/dtl.c @@ -75,7 +75,7 @@ static atomic_t dtl_count; */ static void consume_dtle(struct dtl_entry *dtle, u64 index) { - struct dtl_ring *dtlr = &__get_cpu_var(dtl_rings); + struct dtl_ring *dtlr = this_cpu_ptr(&dtl_rings); struct dtl_entry *wp = dtlr->write_ptr; struct lppaca *vpa = local_paca->lppaca_ptr; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 3c4c0dcd90d3..3cb256c2138e 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -12,7 +12,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/memblock.h> -#include <linux/vmalloc.h> #include <linux/memory.h> #include <linux/memory_hotplug.h> @@ -66,22 +65,6 @@ unsigned long pseries_memory_block_size(void) } #ifdef CONFIG_MEMORY_HOTREMOVE -static int pseries_remove_memory(u64 start, u64 size) -{ - int ret; - - /* Remove htab bolted mappings for this section of memory */ - start = (unsigned long)__va(start); - ret = remove_section_mapping(start, start + size); - - /* Ensure all vmalloc mappings are flushed in case they also - * hit that section of memory - */ - vm_unmap_aliases(); - - return ret; -} - static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { unsigned long block_sz, start_pfn; @@ -262,10 +245,6 @@ static int __init pseries_memory_hotplug_init(void) if (firmware_has_feature(FW_FEATURE_LPAR)) of_reconfig_notifier_register(&pseries_mem_nb); -#ifdef CONFIG_MEMORY_HOTREMOVE - ppc_md.remove_memory = pseries_remove_memory; -#endif - return 0; } machine_device_initcall(pseries, pseries_memory_hotplug_init); diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 3fda3f17b84e..ccd53f91e8aa 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -18,7 +18,7 @@ #ifdef CONFIG_TRACEPOINTS -#ifndef CONFIG_JUMP_LABEL +#ifndef HAVE_JUMP_LABEL .section ".toc","aw" .globl hcall_tracepoint_refcount @@ -78,7 +78,7 @@ hcall_tracepoint_refcount: mr r5,BUFREG; \ __HCALL_INST_POSTCALL -#ifdef CONFIG_JUMP_LABEL +#ifdef HAVE_JUMP_LABEL #define HCALL_BRANCH(LABEL) \ ARCH_STATIC_BRANCH(LABEL, hcall_tracepoint_key) #else diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index 4575f0c9e521..f02ec3ab428c 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -110,7 +110,7 @@ static void probe_hcall_entry(void *ignored, unsigned long opcode, unsigned long if (opcode > MAX_HCALL_OPCODE) return; - h = &__get_cpu_var(hcall_stats)[opcode / 4]; + h = this_cpu_ptr(&hcall_stats[opcode / 4]); h->tb_start = mftb(); h->purr_start = mfspr(SPRN_PURR); } @@ -123,7 +123,7 @@ static void probe_hcall_exit(void *ignored, unsigned long opcode, unsigned long if (opcode > MAX_HCALL_OPCODE) return; - h = &__get_cpu_var(hcall_stats)[opcode / 4]; + h = this_cpu_ptr(&hcall_stats[opcode / 4]); h->num_calls++; h->tb_total += mftb() - h->tb_start; h->purr_total += mfspr(SPRN_PURR) - h->purr_start; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index e32e00976a94..1cc3db95ee71 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -199,7 +199,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, local_irq_save(flags); /* to protect tcep and the page behind it */ - tcep = __get_cpu_var(tce_page); + tcep = __this_cpu_read(tce_page); /* This is safe to do since interrupts are off when we're called * from iommu_alloc{,_sg}() @@ -212,7 +212,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum, return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr, direction, attrs); } - __get_cpu_var(tce_page) = tcep; + __this_cpu_write(tce_page, tcep); } rpn = __pa(uaddr) >> TCE_SHIFT; @@ -398,7 +398,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, long l, limit; local_irq_disable(); /* to protect tcep and the page behind it */ - tcep = __get_cpu_var(tce_page); + tcep = __this_cpu_read(tce_page); if (!tcep) { tcep = (__be64 *)__get_free_page(GFP_ATOMIC); @@ -406,7 +406,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn, local_irq_enable(); return -ENOMEM; } - __get_cpu_var(tce_page) = tcep; + __this_cpu_write(tce_page, tcep); } proto_tce = TCE_PCI_READ | TCE_PCI_WRITE; @@ -574,8 +574,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) while (isa_dn && isa_dn != dn) isa_dn = isa_dn->parent; - if (isa_dn_orig) - of_node_put(isa_dn_orig); + of_node_put(isa_dn_orig); /* Count number of direct PCI children of the PHB. */ for (children = 0, tmp = dn->child; tmp; tmp = tmp->sibling) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 8c509d5397c6..d214a012b026 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -43,6 +43,7 @@ #include <asm/trace.h> #include <asm/firmware.h> #include <asm/plpar_wrappers.h> +#include <asm/fadump.h> #include "pseries.h" @@ -247,8 +248,17 @@ static void pSeries_lpar_hptab_clear(void) } #ifdef __LITTLE_ENDIAN__ - /* Reset exceptions to big endian */ - if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * Reset exceptions to big endian. + * + * FIXME this is a hack for kexec, we need to reset the exception + * endian before starting the new kernel and this is a convenient place + * to do it. + * + * This is also called on boot when a fadump happens. In that case we + * must not change the exception endian mode. + */ + if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active()) { long rc; rc = pseries_big_endian_exceptions(); @@ -505,7 +515,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) unsigned long vpn; unsigned long i, pix, rc; unsigned long flags = 0; - struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); + struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch); int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); unsigned long param[9]; unsigned long hash, index, shift, hidx, slot; @@ -695,7 +705,7 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args) local_irq_save(flags); - depth = &__get_cpu_var(hcall_trace_depth); + depth = this_cpu_ptr(&hcall_trace_depth); if (*depth) goto out; @@ -720,7 +730,7 @@ void __trace_hcall_exit(long opcode, unsigned long retval, local_irq_save(flags); - depth = &__get_cpu_var(hcall_trace_depth); + depth = this_cpu_ptr(&hcall_trace_depth); if (*depth) goto out; diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 67e48594040c..fe16a50700de 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -134,7 +134,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) of_node_put(pdn); if (rc) { - pr_err("no ibm,pcie-link-speed-stats property\n"); + pr_debug("no ibm,pcie-link-speed-stats property\n"); return 0; } diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 5a4d0fc03b03..c3b2a7e81ddb 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -302,8 +302,8 @@ static struct rtas_error_log *fwnmi_get_errinfo(struct pt_regs *regs) /* If it isn't an extended log we can use the per cpu 64bit buffer */ h = (struct rtas_error_log *)&savep[1]; if (!rtas_error_extended(h)) { - memcpy(&__get_cpu_var(mce_data_buf), h, sizeof(__u64)); - errhdr = (struct rtas_error_log *)&__get_cpu_var(mce_data_buf); + memcpy(this_cpu_ptr(&mce_data_buf), h, sizeof(__u64)); + errhdr = (struct rtas_error_log *)this_cpu_ptr(&mce_data_buf); } else { int len, error_log_length; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 125c589eeef5..8b8fb19a4097 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -499,7 +499,11 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_SET_MODE)) { long rc; - if ((rc = pSeries_enable_reloc_on_exc()) != H_SUCCESS) { + + rc = pSeries_enable_reloc_on_exc(); + if (rc == H_P2) { + pr_info("Relocation on exceptions not supported\n"); + } else if (rc != H_SUCCESS) { pr_warn("Unable to enable relocation on exceptions: " "%ld\n", rc); } @@ -659,6 +663,34 @@ static void __init pSeries_init_early(void) pr_debug(" <- pSeries_init_early()\n"); } +/** + * pseries_power_off - tell firmware about how to power off the system. + * + * This function calls either the power-off rtas token in normal cases + * or the ibm,power-off-ups token (if present & requested) in case of + * a power failure. If power-off token is used, power on will only be + * possible with power button press. If ibm,power-off-ups token is used + * it will allow auto poweron after power is restored. + */ +static void pseries_power_off(void) +{ + int rc; + int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups"); + + if (rtas_flash_term_hook) + rtas_flash_term_hook(SYS_POWER_OFF); + + if (rtas_poweron_auto == 0 || + rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) { + rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1); + printk(KERN_INFO "RTAS power-off returned %d\n", rc); + } else { + rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL); + printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc); + } + for (;;); +} + /* * Called very early, MMU is off, device-tree isn't unflattened */ @@ -741,6 +773,8 @@ static int __init pSeries_probe(void) else hpte_init_native(); + pm_power_off = pseries_power_off; + pr_debug("Machine is%s LPAR !\n", (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not"); @@ -754,34 +788,6 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus) return PCI_PROBE_NORMAL; } -/** - * pSeries_power_off - tell firmware about how to power off the system. - * - * This function calls either the power-off rtas token in normal cases - * or the ibm,power-off-ups token (if present & requested) in case of - * a power failure. If power-off token is used, power on will only be - * possible with power button press. If ibm,power-off-ups token is used - * it will allow auto poweron after power is restored. - */ -static void pSeries_power_off(void) -{ - int rc; - int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups"); - - if (rtas_flash_term_hook) - rtas_flash_term_hook(SYS_POWER_OFF); - - if (rtas_poweron_auto == 0 || - rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) { - rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1); - printk(KERN_INFO "RTAS power-off returned %d\n", rc); - } else { - rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL); - printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc); - } - for (;;); -} - #ifndef CONFIG_PCI void pSeries_final_fixup(void) { } #endif @@ -796,7 +802,6 @@ define_machine(pseries) { .pcibios_fixup = pSeries_final_fixup, .pci_probe_mode = pSeries_pci_probe_mode, .restart = rtas_restart, - .power_off = pSeries_power_off, .halt = rtas_halt, .panic = rtas_os_term, .get_boot_time = rtas_get_boot_time, diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index de40b48b460e..8f37204bf94f 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -13,7 +13,6 @@ * */ #include <linux/irq.h> -#include <linux/bootmem.h> #include <linux/msi.h> #include <linux/pci.h> #include <linux/slab.h> diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 65d2ed4549e6..d8484d7cffaa 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -152,7 +152,7 @@ static int setup_one_atmu(struct ccsr_pci __iomem *pci, flags |= 0x10000000; /* enable relaxed ordering */ for (i = 0; size > 0; i++) { - unsigned int bits = min(ilog2(size), + unsigned int bits = min_t(u32, ilog2(size), __ffs(pci_addr | phys_addr)); if (index + i >= 5) diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index ffd1169ebaab..99269c041615 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -197,8 +197,7 @@ static int __init setup_rstcr(void) if (!rstcr && ppc_md.restart == fsl_rstcr_restart) printk(KERN_ERR "No RSTCR register, warm reboot won't work\n"); - if (np) - of_node_put(np); + of_node_put(np); return 0; } @@ -238,7 +237,7 @@ void fsl_hv_restart(char *cmd) /* * Halt the current partition * - * This function should be assigned to the ppc_md.power_off and ppc_md.halt + * This function should be assigned to the pm_power_off and ppc_md.halt * function pointers, to shut down the partition when we're running under * the Freescale hypervisor. */ diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index b50f97811c25..b28733727ed3 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -20,7 +20,6 @@ #include <linux/signal.h> #include <linux/syscore_ops.h> #include <linux/device.h> -#include <linux/bootmem.h> #include <linux/spinlock.h> #include <linux/fsl_devices.h> #include <asm/irq.h> diff --git a/arch/powerpc/sysdev/mpc5xxx_clocks.c b/arch/powerpc/sysdev/mpc5xxx_clocks.c index 5492dc5f56f4..f4f0301b9a60 100644 --- a/arch/powerpc/sysdev/mpc5xxx_clocks.c +++ b/arch/powerpc/sysdev/mpc5xxx_clocks.c @@ -26,8 +26,7 @@ unsigned long mpc5xxx_get_bus_frequency(struct device_node *node) of_node_put(node); node = np; } - if (node) - of_node_put(node); + of_node_put(node); return p_bus_freq ? *p_bus_freq : 0; } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 89cec0ed6a58..c4648ad5c1f3 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -24,7 +24,6 @@ #include <linux/irq.h> #include <linux/smp.h> #include <linux/interrupt.h> -#include <linux/bootmem.h> #include <linux/spinlock.h> #include <linux/pci.h> #include <linux/slab.h> diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c index 15dccd35fa11..428de9d23120 100644 --- a/arch/powerpc/sysdev/mpic_pasemi_msi.c +++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c @@ -16,7 +16,6 @@ #undef DEBUG #include <linux/irq.h> -#include <linux/bootmem.h> #include <linux/msi.h> #include <asm/mpic.h> #include <asm/prom.h> diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c index 623d7fba15b4..4ce8f54f234c 100644 --- a/arch/powerpc/sysdev/mpic_u3msi.c +++ b/arch/powerpc/sysdev/mpic_u3msi.c @@ -10,7 +10,6 @@ */ #include <linux/irq.h> -#include <linux/bootmem.h> #include <linux/msi.h> #include <asm/mpic.h> #include <asm/prom.h> diff --git a/arch/powerpc/sysdev/ppc4xx_cpm.c b/arch/powerpc/sysdev/ppc4xx_cpm.c index 82e2cfe35c62..ba95adf81d8d 100644 --- a/arch/powerpc/sysdev/ppc4xx_cpm.c +++ b/arch/powerpc/sysdev/ppc4xx_cpm.c @@ -281,7 +281,7 @@ static int __init cpm_init(void) printk(KERN_ERR "cpm: could not parse dcr property for %s\n", np->full_name); ret = -EINVAL; - goto out; + goto node_put; } cpm.dcr_host = dcr_map(np, dcr_base, dcr_len); @@ -290,7 +290,7 @@ static int __init cpm_init(void) printk(KERN_ERR "cpm: failed to map dcr property for %s\n", np->full_name); ret = -EINVAL; - goto out; + goto node_put; } /* All 4xx SoCs with a CPM controller have one of two @@ -330,9 +330,9 @@ static int __init cpm_init(void) if (cpm.standby || cpm.suspend) suspend_set_ops(&cpm_suspend_ops); +node_put: + of_node_put(np); out: - if (np) - of_node_put(np); return ret; } diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c index 22b5200636e7..a59f2890897a 100644 --- a/arch/powerpc/sysdev/ppc4xx_msi.c +++ b/arch/powerpc/sysdev/ppc4xx_msi.c @@ -22,7 +22,6 @@ */ #include <linux/irq.h> -#include <linux/bootmem.h> #include <linux/pci.h> #include <linux/msi.h> #include <linux/of_platform.h> diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c index df6e2fc4ff92..086aca69ecae 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/sysdev/ppc4xx_pci.c @@ -22,7 +22,6 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/of.h> -#include <linux/bootmem.h> #include <linux/delay.h> #include <linux/slab.h> diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c index 238a07b97f2c..b584debbcd9c 100644 --- a/arch/powerpc/sysdev/qe_lib/qe.c +++ b/arch/powerpc/sysdev/qe_lib/qe.c @@ -22,7 +22,6 @@ #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/interrupt.h> -#include <linux/bootmem.h> #include <linux/module.h> #include <linux/delay.h> #include <linux/ioport.h> diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c index b2b87c30e266..543765e1ef14 100644 --- a/arch/powerpc/sysdev/qe_lib/qe_ic.c +++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c @@ -23,7 +23,6 @@ #include <linux/sched.h> #include <linux/signal.h> #include <linux/device.h> -#include <linux/bootmem.h> #include <linux/spinlock.h> #include <asm/irq.h> #include <asm/io.h> diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c index 92033936a8f7..7c37157d4c24 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/sysdev/uic.c @@ -19,7 +19,6 @@ #include <linux/sched.h> #include <linux/signal.h> #include <linux/device.h> -#include <linux/bootmem.h> #include <linux/spinlock.h> #include <linux/irq.h> #include <linux/interrupt.h> diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index fe0cca477164..365249cd346b 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -155,7 +155,7 @@ int __init xics_smp_probe(void) void xics_teardown_cpu(void) { - struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr); + struct xics_cppr *os_cppr = this_cpu_ptr(&xics_cppr); /* * we have to reset the cppr index to 0 because we're diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index b988b5addf86..ef18021d52e1 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -907,7 +907,7 @@ cmds(struct pt_regs *excp) case 'u': dump_segments(); break; -#elif defined(CONFIG_4xx) +#elif defined(CONFIG_44x) case 'u': dump_tlb_44x(); break; @@ -981,7 +981,8 @@ static void bootcmds(void) else if (cmd == 'h') ppc_md.halt(); else if (cmd == 'p') - ppc_md.power_off(); + if (pm_power_off) + pm_power_off(); } static int cpu_cmd(void) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 0a54c588e433..27b71a0b72d0 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -342,7 +342,6 @@ struct rbd_device { struct list_head rq_queue; /* incoming rq queue */ spinlock_t lock; /* queue, flags, open_count */ - struct workqueue_struct *rq_wq; struct work_struct rq_work; struct rbd_image_header header; @@ -402,6 +401,8 @@ static struct kmem_cache *rbd_segment_name_cache; static int rbd_major; static DEFINE_IDA(rbd_dev_id_ida); +static struct workqueue_struct *rbd_wq; + /* * Default to false for now, as single-major requires >= 0.75 version of * userspace rbd utility. @@ -3452,7 +3453,7 @@ static void rbd_request_fn(struct request_queue *q) } if (queued) - queue_work(rbd_dev->rq_wq, &rbd_dev->rq_work); + queue_work(rbd_wq, &rbd_dev->rq_work); } /* @@ -3532,7 +3533,7 @@ static int rbd_obj_read_sync(struct rbd_device *rbd_dev, page_count = (u32) calc_pages_for(offset, length); pages = ceph_alloc_page_vector(page_count, GFP_KERNEL); if (IS_ERR(pages)) - ret = PTR_ERR(pages); + return PTR_ERR(pages); ret = -ENOMEM; obj_request = rbd_obj_request_create(object_name, offset, length, @@ -5242,16 +5243,9 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE); set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only); - rbd_dev->rq_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, - rbd_dev->disk->disk_name); - if (!rbd_dev->rq_wq) { - ret = -ENOMEM; - goto err_out_mapping; - } - ret = rbd_bus_add_dev(rbd_dev); if (ret) - goto err_out_workqueue; + goto err_out_mapping; /* Everything's ready. Announce the disk to the world. */ @@ -5263,9 +5257,6 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) return ret; -err_out_workqueue: - destroy_workqueue(rbd_dev->rq_wq); - rbd_dev->rq_wq = NULL; err_out_mapping: rbd_dev_mapping_clear(rbd_dev); err_out_disk: @@ -5512,7 +5503,6 @@ static void rbd_dev_device_release(struct device *dev) { struct rbd_device *rbd_dev = dev_to_rbd_dev(dev); - destroy_workqueue(rbd_dev->rq_wq); rbd_free_disk(rbd_dev); clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags); rbd_dev_mapping_clear(rbd_dev); @@ -5716,11 +5706,21 @@ static int __init rbd_init(void) if (rc) return rc; + /* + * The number of active work items is limited by the number of + * rbd devices, so leave @max_active at default. + */ + rbd_wq = alloc_workqueue(RBD_DRV_NAME, WQ_MEM_RECLAIM, 0); + if (!rbd_wq) { + rc = -ENOMEM; + goto err_out_slab; + } + if (single_major) { rbd_major = register_blkdev(0, RBD_DRV_NAME); if (rbd_major < 0) { rc = rbd_major; - goto err_out_slab; + goto err_out_wq; } } @@ -5738,6 +5738,8 @@ static int __init rbd_init(void) err_out_blkdev: if (single_major) unregister_blkdev(rbd_major, RBD_DRV_NAME); +err_out_wq: + destroy_workqueue(rbd_wq); err_out_slab: rbd_slab_exit(); return rc; @@ -5749,6 +5751,7 @@ static void __exit rbd_exit(void) rbd_sysfs_cleanup(); if (single_major) unregister_blkdev(rbd_major, RBD_DRV_NAME); + destroy_workqueue(rbd_wq); rbd_slab_exit(); } diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index 3d2b8677ec8a..b5b6bda44a00 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -336,6 +336,8 @@ struct cxl_sste { struct cxl_afu { irq_hw_number_t psl_hwirq; irq_hw_number_t serr_hwirq; + char *err_irq_name; + char *psl_irq_name; unsigned int serr_virq; void __iomem *p1n_mmio; void __iomem *p2n_mmio; @@ -379,6 +381,12 @@ struct cxl_afu { bool enabled; }; + +struct cxl_irq_name { + struct list_head list; + char *name; +}; + /* * This is a cxl context. If the PSL is in dedicated mode, there will be one * of these per AFU. If in AFU directed there can be lots of these. @@ -403,6 +411,7 @@ struct cxl_context { unsigned long *irq_bitmap; /* Accessed from IRQ context */ struct cxl_irq_ranges irqs; + struct list_head irq_names; u64 fault_addr; u64 fault_dsisr; u64 afu_err; @@ -444,6 +453,7 @@ struct cxl { struct dentry *trace; struct dentry *psl_err_chk; struct dentry *debugfs; + char *irq_name; struct bin_attribute cxl_attr; int adapter_num; int user_irqs; @@ -563,9 +573,6 @@ int _cxl_afu_deactivate_mode(struct cxl_afu *afu, int mode); int cxl_afu_deactivate_mode(struct cxl_afu *afu); int cxl_afu_select_best_mode(struct cxl_afu *afu); -unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, - irq_handler_t handler, void *cookie); -void cxl_unmap_irq(unsigned int virq, void *cookie); int cxl_register_psl_irq(struct cxl_afu *afu); void cxl_release_psl_irq(struct cxl_afu *afu); int cxl_register_psl_err_irq(struct cxl *adapter); @@ -612,7 +619,7 @@ int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr); int cxl_detach_process(struct cxl_context *ctx); -int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info); +int cxl_get_irq(struct cxl_afu *afu, struct cxl_irq_info *info); int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask); int cxl_check_error(struct cxl_afu *afu); diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c index 336020c8e1af..c294925f73ee 100644 --- a/drivers/misc/cxl/irq.c +++ b/drivers/misc/cxl/irq.c @@ -92,20 +92,13 @@ static irqreturn_t schedule_cxl_fault(struct cxl_context *ctx, u64 dsisr, u64 da return IRQ_HANDLED; } -static irqreturn_t cxl_irq(int irq, void *data) +static irqreturn_t cxl_irq(int irq, void *data, struct cxl_irq_info *irq_info) { struct cxl_context *ctx = data; - struct cxl_irq_info irq_info; u64 dsisr, dar; - int result; - - if ((result = cxl_get_irq(ctx, &irq_info))) { - WARN(1, "Unable to get CXL IRQ Info: %i\n", result); - return IRQ_HANDLED; - } - dsisr = irq_info.dsisr; - dar = irq_info.dar; + dsisr = irq_info->dsisr; + dar = irq_info->dar; pr_devel("CXL interrupt %i for afu pe: %i DSISR: %#llx DAR: %#llx\n", irq, ctx->pe, dsisr, dar); @@ -149,9 +142,9 @@ static irqreturn_t cxl_irq(int irq, void *data) if (dsisr & CXL_PSL_DSISR_An_UR) pr_devel("CXL interrupt: AURP PTE not found\n"); if (dsisr & CXL_PSL_DSISR_An_PE) - return handle_psl_slice_error(ctx, dsisr, irq_info.errstat); + return handle_psl_slice_error(ctx, dsisr, irq_info->errstat); if (dsisr & CXL_PSL_DSISR_An_AE) { - pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info.afu_err); + pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info->afu_err); if (ctx->pending_afu_err) { /* @@ -163,10 +156,10 @@ static irqreturn_t cxl_irq(int irq, void *data) */ dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error " "undelivered to pe %i: %.llx\n", - ctx->pe, irq_info.afu_err); + ctx->pe, irq_info->afu_err); } else { spin_lock(&ctx->lock); - ctx->afu_err = irq_info.afu_err; + ctx->afu_err = irq_info->afu_err; ctx->pending_afu_err = 1; spin_unlock(&ctx->lock); @@ -182,24 +175,43 @@ static irqreturn_t cxl_irq(int irq, void *data) return IRQ_HANDLED; } +static irqreturn_t fail_psl_irq(struct cxl_afu *afu, struct cxl_irq_info *irq_info) +{ + if (irq_info->dsisr & CXL_PSL_DSISR_TRANS) + cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE); + else + cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A); + + return IRQ_HANDLED; +} + static irqreturn_t cxl_irq_multiplexed(int irq, void *data) { struct cxl_afu *afu = data; struct cxl_context *ctx; + struct cxl_irq_info irq_info; int ph = cxl_p2n_read(afu, CXL_PSL_PEHandle_An) & 0xffff; int ret; + if ((ret = cxl_get_irq(afu, &irq_info))) { + WARN(1, "Unable to get CXL IRQ Info: %i\n", ret); + return fail_psl_irq(afu, &irq_info); + } + rcu_read_lock(); ctx = idr_find(&afu->contexts_idr, ph); if (ctx) { - ret = cxl_irq(irq, ctx); + ret = cxl_irq(irq, ctx, &irq_info); rcu_read_unlock(); return ret; } rcu_read_unlock(); - WARN(1, "Unable to demultiplex CXL PSL IRQ\n"); - return IRQ_HANDLED; + WARN(1, "Unable to demultiplex CXL PSL IRQ for PE %i DSISR %.16llx DAR" + " %.16llx\n(Possible AFU HW issue - was a term/remove acked" + " with outstanding transactions?)\n", ph, irq_info.dsisr, + irq_info.dar); + return fail_psl_irq(afu, &irq_info); } static irqreturn_t cxl_irq_afu(int irq, void *data) @@ -243,7 +255,7 @@ static irqreturn_t cxl_irq_afu(int irq, void *data) } unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, - irq_handler_t handler, void *cookie) + irq_handler_t handler, void *cookie, const char *name) { unsigned int virq; int result; @@ -259,7 +271,7 @@ unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, pr_devel("hwirq %#lx mapped to virq %u\n", hwirq, virq); - result = request_irq(virq, handler, 0, "cxl", cookie); + result = request_irq(virq, handler, 0, name, cookie); if (result) { dev_warn(&adapter->dev, "cxl_map_irq: request_irq failed: %i\n", result); return 0; @@ -278,14 +290,15 @@ static int cxl_register_one_irq(struct cxl *adapter, irq_handler_t handler, void *cookie, irq_hw_number_t *dest_hwirq, - unsigned int *dest_virq) + unsigned int *dest_virq, + const char *name) { int hwirq, virq; if ((hwirq = cxl_alloc_one_irq(adapter)) < 0) return hwirq; - if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie))) + if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie, name))) goto err; *dest_hwirq = hwirq; @@ -302,10 +315,19 @@ int cxl_register_psl_err_irq(struct cxl *adapter) { int rc; + adapter->irq_name = kasprintf(GFP_KERNEL, "cxl-%s-err", + dev_name(&adapter->dev)); + if (!adapter->irq_name) + return -ENOMEM; + if ((rc = cxl_register_one_irq(adapter, cxl_irq_err, adapter, &adapter->err_hwirq, - &adapter->err_virq))) + &adapter->err_virq, + adapter->irq_name))) { + kfree(adapter->irq_name); + adapter->irq_name = NULL; return rc; + } cxl_p1_write(adapter, CXL_PSL_ErrIVTE, adapter->err_hwirq & 0xffff); @@ -317,6 +339,7 @@ void cxl_release_psl_err_irq(struct cxl *adapter) cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000); cxl_unmap_irq(adapter->err_virq, adapter); cxl_release_one_irq(adapter, adapter->err_hwirq); + kfree(adapter->irq_name); } int cxl_register_serr_irq(struct cxl_afu *afu) @@ -324,10 +347,18 @@ int cxl_register_serr_irq(struct cxl_afu *afu) u64 serr; int rc; + afu->err_irq_name = kasprintf(GFP_KERNEL, "cxl-%s-err", + dev_name(&afu->dev)); + if (!afu->err_irq_name) + return -ENOMEM; + if ((rc = cxl_register_one_irq(afu->adapter, cxl_slice_irq_err, afu, &afu->serr_hwirq, - &afu->serr_virq))) + &afu->serr_virq, afu->err_irq_name))) { + kfree(afu->err_irq_name); + afu->err_irq_name = NULL; return rc; + } serr = cxl_p1n_read(afu, CXL_PSL_SERR_An); serr = (serr & 0x00ffffffffff0000ULL) | (afu->serr_hwirq & 0xffff); @@ -341,24 +372,50 @@ void cxl_release_serr_irq(struct cxl_afu *afu) cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000); cxl_unmap_irq(afu->serr_virq, afu); cxl_release_one_irq(afu->adapter, afu->serr_hwirq); + kfree(afu->err_irq_name); } int cxl_register_psl_irq(struct cxl_afu *afu) { - return cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu, - &afu->psl_hwirq, &afu->psl_virq); + int rc; + + afu->psl_irq_name = kasprintf(GFP_KERNEL, "cxl-%s", + dev_name(&afu->dev)); + if (!afu->psl_irq_name) + return -ENOMEM; + + if ((rc = cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu, + &afu->psl_hwirq, &afu->psl_virq, + afu->psl_irq_name))) { + kfree(afu->psl_irq_name); + afu->psl_irq_name = NULL; + } + return rc; } void cxl_release_psl_irq(struct cxl_afu *afu) { cxl_unmap_irq(afu->psl_virq, afu); cxl_release_one_irq(afu->adapter, afu->psl_hwirq); + kfree(afu->psl_irq_name); +} + +void afu_irq_name_free(struct cxl_context *ctx) +{ + struct cxl_irq_name *irq_name, *tmp; + + list_for_each_entry_safe(irq_name, tmp, &ctx->irq_names, list) { + kfree(irq_name->name); + list_del(&irq_name->list); + kfree(irq_name); + } } int afu_register_irqs(struct cxl_context *ctx, u32 count) { irq_hw_number_t hwirq; - int rc, r, i; + int rc, r, i, j = 1; + struct cxl_irq_name *irq_name; if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count))) return rc; @@ -372,15 +429,47 @@ int afu_register_irqs(struct cxl_context *ctx, u32 count) sizeof(*ctx->irq_bitmap), GFP_KERNEL); if (!ctx->irq_bitmap) return -ENOMEM; + + /* + * Allocate names first. If any fail, bail out before allocating + * actual hardware IRQs. + */ + INIT_LIST_HEAD(&ctx->irq_names); + for (r = 1; r < CXL_IRQ_RANGES; r++) { + for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) { + irq_name = kmalloc(sizeof(struct cxl_irq_name), + GFP_KERNEL); + if (!irq_name) + goto out; + irq_name->name = kasprintf(GFP_KERNEL, "cxl-%s-pe%i-%i", + dev_name(&ctx->afu->dev), + ctx->pe, j); + if (!irq_name->name) { + kfree(irq_name); + goto out; + } + /* Add to tail so next look get the correct order */ + list_add_tail(&irq_name->list, &ctx->irq_names); + j++; + } + } + + /* We've allocated all memory now, so let's do the irq allocations */ + irq_name = list_first_entry(&ctx->irq_names, struct cxl_irq_name, list); for (r = 1; r < CXL_IRQ_RANGES; r++) { hwirq = ctx->irqs.offset[r]; for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) { cxl_map_irq(ctx->afu->adapter, hwirq, - cxl_irq_afu, ctx); + cxl_irq_afu, ctx, irq_name->name); + irq_name = list_next_entry(irq_name, list); } } return 0; + +out: + afu_irq_name_free(ctx); + return -ENOMEM; } void afu_release_irqs(struct cxl_context *ctx) @@ -398,5 +487,6 @@ void afu_release_irqs(struct cxl_context *ctx) } } + afu_irq_name_free(ctx); cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter); } diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index d47532e8f4f1..9a5a442269a8 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -637,18 +637,18 @@ int cxl_detach_process(struct cxl_context *ctx) return detach_process_native_afu_directed(ctx); } -int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info) +int cxl_get_irq(struct cxl_afu *afu, struct cxl_irq_info *info) { u64 pidtid; - info->dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An); - info->dar = cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An); - info->dsr = cxl_p2n_read(ctx->afu, CXL_PSL_DSR_An); - pidtid = cxl_p2n_read(ctx->afu, CXL_PSL_PID_TID_An); + info->dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An); + info->dar = cxl_p2n_read(afu, CXL_PSL_DAR_An); + info->dsr = cxl_p2n_read(afu, CXL_PSL_DSR_An); + pidtid = cxl_p2n_read(afu, CXL_PSL_PID_TID_An); info->pid = pidtid >> 32; info->tid = pidtid & 0xffffffff; - info->afu_err = cxl_p2n_read(ctx->afu, CXL_AFU_ERR_An); - info->errstat = cxl_p2n_read(ctx->afu, CXL_PSL_ErrStat_An); + info->afu_err = cxl_p2n_read(afu, CXL_AFU_ERR_An); + info->errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An); return 0; } diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c index e12e5b07f6d7..9dc38140194b 100644 --- a/drivers/pinctrl/pinctrl-baytrail.c +++ b/drivers/pinctrl/pinctrl-baytrail.c @@ -227,10 +227,14 @@ static int byt_irq_type(struct irq_data *d, unsigned type) spin_lock_irqsave(&vg->lock, flags); value = readl(reg); + WARN(value & BYT_DIRECT_IRQ_EN, + "Bad pad config for io mode, force direct_irq_en bit clearing"); + /* For level trigges the BYT_TRIG_POS and BYT_TRIG_NEG bits * are used to indicate high and low level triggering */ - value &= ~(BYT_TRIG_POS | BYT_TRIG_NEG | BYT_TRIG_LVL); + value &= ~(BYT_DIRECT_IRQ_EN | BYT_TRIG_POS | BYT_TRIG_NEG | + BYT_TRIG_LVL); switch (type) { case IRQ_TYPE_LEVEL_HIGH: @@ -318,7 +322,7 @@ static int byt_gpio_direction_output(struct gpio_chip *chip, "Potential Error: Setting GPIO with direct_irq_en to output"); reg_val = readl(reg) | BYT_DIR_MASK; - reg_val &= ~BYT_OUTPUT_EN; + reg_val &= ~(BYT_OUTPUT_EN | BYT_INPUT_EN); if (value) writel(reg_val | BYT_LEVEL, reg); diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 6dd12ddbabc6..c8f0ec7464ce 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -979,6 +979,17 @@ config RTC_DRV_NUC900 If you say yes here you get support for the RTC subsystem of the NUC910/NUC920 used in embedded systems. +config RTC_DRV_OPAL + tristate "IBM OPAL RTC driver" + depends on PPC_POWERNV + default y + help + If you say yes here you get support for the PowerNV platform RTC + driver based on OPAL interfaces. + + This driver can also be built as a module. If so, the module + will be called rtc-opal. + comment "on-CPU RTC drivers" config RTC_DRV_DAVINCI diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index b188323c096a..c8ef3e1e6ccd 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -92,6 +92,7 @@ obj-$(CONFIG_RTC_DRV_MSM6242) += rtc-msm6242.o obj-$(CONFIG_RTC_DRV_MPC5121) += rtc-mpc5121.o obj-$(CONFIG_RTC_DRV_MV) += rtc-mv.o obj-$(CONFIG_RTC_DRV_NUC900) += rtc-nuc900.o +obj-$(CONFIG_RTC_DRV_OPAL) += rtc-opal.o obj-$(CONFIG_RTC_DRV_OMAP) += rtc-omap.o obj-$(CONFIG_RTC_DRV_PALMAS) += rtc-palmas.o obj-$(CONFIG_RTC_DRV_PCAP) += rtc-pcap.o diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c new file mode 100644 index 000000000000..95f652165fe9 --- /dev/null +++ b/drivers/rtc/rtc-opal.c @@ -0,0 +1,261 @@ +/* + * IBM OPAL RTC driver + * Copyright (C) 2014 IBM + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. + */ + +#define DRVNAME "rtc-opal" +#define pr_fmt(fmt) DRVNAME ": " fmt + +#include <linux/module.h> +#include <linux/err.h> +#include <linux/rtc.h> +#include <linux/delay.h> +#include <linux/bcd.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <asm/opal.h> +#include <asm/firmware.h> + +static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm) +{ + tm->tm_year = ((bcd2bin(y_m_d >> 24) * 100) + + bcd2bin((y_m_d >> 16) & 0xff)) - 1900; + tm->tm_mon = bcd2bin((y_m_d >> 8) & 0xff) - 1; + tm->tm_mday = bcd2bin(y_m_d & 0xff); + tm->tm_hour = bcd2bin((h_m_s_ms >> 56) & 0xff); + tm->tm_min = bcd2bin((h_m_s_ms >> 48) & 0xff); + tm->tm_sec = bcd2bin((h_m_s_ms >> 40) & 0xff); + + GregorianDay(tm); +} + +static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms) +{ + *y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24; + *y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16; + *y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8; + *y_m_d |= ((u32)bin2bcd(tm->tm_mday)); + + *h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56; + *h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48; + *h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40; +} + +static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) +{ + long rc = OPAL_BUSY; + u32 y_m_d; + u64 h_m_s_ms; + __be32 __y_m_d; + __be64 __h_m_s_ms; + + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + msleep(10); + } + + if (rc != OPAL_SUCCESS) + return -EIO; + + y_m_d = be32_to_cpu(__y_m_d); + h_m_s_ms = be64_to_cpu(__h_m_s_ms); + opal_to_tm(y_m_d, h_m_s_ms, tm); + + return 0; +} + +static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm) +{ + long rc = OPAL_BUSY; + u32 y_m_d = 0; + u64 h_m_s_ms = 0; + + tm_to_opal(tm, &y_m_d, &h_m_s_ms); + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { + rc = opal_rtc_write(y_m_d, h_m_s_ms); + if (rc == OPAL_BUSY_EVENT) + opal_poll_events(NULL); + else + msleep(10); + } + + return rc == OPAL_SUCCESS ? 0 : -EIO; +} + +/* + * TPO Timed Power-On + * + * TPO get/set OPAL calls care about the hour and min and to make it consistent + * with the rtc utility time conversion functions, we use the 'u64' to store + * its value and perform bit shift by 32 before use.. + */ +static int opal_get_tpo_time(struct device *dev, struct rtc_wkalrm *alarm) +{ + __be32 __y_m_d, __h_m; + struct opal_msg msg; + int rc, token; + u64 h_m_s_ms; + u32 y_m_d; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + if (token != -ERESTARTSYS) + pr_err("Failed to get the async token\n"); + + return token; + } + + rc = opal_tpo_read(token, &__y_m_d, &__h_m); + if (rc != OPAL_ASYNC_COMPLETION) { + rc = -EIO; + goto exit; + } + + rc = opal_async_wait_response(token, &msg); + if (rc) { + rc = -EIO; + goto exit; + } + + rc = be64_to_cpu(msg.params[1]); + if (rc != OPAL_SUCCESS) { + rc = -EIO; + goto exit; + } + + y_m_d = be32_to_cpu(__y_m_d); + h_m_s_ms = ((u64)be32_to_cpu(__h_m) << 32); + opal_to_tm(y_m_d, h_m_s_ms, &alarm->time); + +exit: + opal_async_release_token(token); + return rc; +} + +/* Set Timed Power-On */ +static int opal_set_tpo_time(struct device *dev, struct rtc_wkalrm *alarm) +{ + u64 h_m_s_ms = 0, token; + struct opal_msg msg; + u32 y_m_d = 0; + int rc; + + tm_to_opal(&alarm->time, &y_m_d, &h_m_s_ms); + + token = opal_async_get_token_interruptible(); + if (token < 0) { + if (token != -ERESTARTSYS) + pr_err("Failed to get the async token\n"); + + return token; + } + + /* TPO, we care about hour and minute */ + rc = opal_tpo_write(token, y_m_d, + (u32)((h_m_s_ms >> 32) & 0xffff0000)); + if (rc != OPAL_ASYNC_COMPLETION) { + rc = -EIO; + goto exit; + } + + rc = opal_async_wait_response(token, &msg); + if (rc) { + rc = -EIO; + goto exit; + } + + rc = be64_to_cpu(msg.params[1]); + if (rc != OPAL_SUCCESS) + rc = -EIO; + +exit: + opal_async_release_token(token); + return rc; +} + +static const struct rtc_class_ops opal_rtc_ops = { + .read_time = opal_get_rtc_time, + .set_time = opal_set_rtc_time, + .read_alarm = opal_get_tpo_time, + .set_alarm = opal_set_tpo_time, +}; + +static int opal_rtc_probe(struct platform_device *pdev) +{ + struct rtc_device *rtc; + + if (pdev->dev.of_node && of_get_property(pdev->dev.of_node, "has-tpo", + NULL)) + device_set_wakeup_capable(&pdev->dev, true); + + rtc = devm_rtc_device_register(&pdev->dev, DRVNAME, &opal_rtc_ops, + THIS_MODULE); + if (IS_ERR(rtc)) + return PTR_ERR(rtc); + + rtc->uie_unsupported = 1; + + return 0; +} + +static const struct of_device_id opal_rtc_match[] = { + { + .compatible = "ibm,opal-rtc", + }, + { } +}; +MODULE_DEVICE_TABLE(of, opal_rtc_match); + +static const struct platform_device_id opal_rtc_driver_ids[] = { + { + .name = "opal-rtc", + }, + { } +}; +MODULE_DEVICE_TABLE(platform, opal_rtc_driver_ids); + +static struct platform_driver opal_rtc_driver = { + .probe = opal_rtc_probe, + .id_table = opal_rtc_driver_ids, + .driver = { + .name = DRVNAME, + .owner = THIS_MODULE, + .of_match_table = opal_rtc_match, + }, +}; + +static int __init opal_rtc_init(void) +{ + if (!firmware_has_feature(FW_FEATURE_OPAL)) + return -ENODEV; + + return platform_driver_register(&opal_rtc_driver); +} + +static void __exit opal_rtc_exit(void) +{ + platform_driver_unregister(&opal_rtc_driver); +} + +MODULE_AUTHOR("Neelesh Gupta <neelegup@linux.vnet.ibm.com>"); +MODULE_DESCRIPTION("IBM OPAL RTC driver"); +MODULE_LICENSE("GPL"); + +module_init(opal_rtc_init); +module_exit(opal_rtc_exit); diff --git a/drivers/soc/versatile/soc-realview.c b/drivers/soc/versatile/soc-realview.c index cea8ea3491d2..1a07bf540fec 100644 --- a/drivers/soc/versatile/soc-realview.c +++ b/drivers/soc/versatile/soc-realview.c @@ -26,6 +26,7 @@ static const struct of_device_id realview_soc_of_match[] = { { .compatible = "arm,realview-pb11mp-soc", }, { .compatible = "arm,realview-pba8-soc", }, { .compatible = "arm,realview-pbx-soc", }, + { } }; static u32 realview_coreid; diff --git a/include/linux/cma.h b/include/linux/cma.h index 0430ed05d3b9..a93438beb33c 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -18,12 +18,12 @@ struct cma; extern phys_addr_t cma_get_base(struct cma *cma); extern unsigned long cma_get_size(struct cma *cma); -extern int __init cma_declare_contiguous(phys_addr_t size, - phys_addr_t base, phys_addr_t limit, +extern int __init cma_declare_contiguous(phys_addr_t base, + phys_addr_t size, phys_addr_t limit, phys_addr_t alignment, unsigned int order_per_bit, bool fixed, struct cma **res_cma); -extern int cma_init_reserved_mem(phys_addr_t size, - phys_addr_t base, int order_per_bit, +extern int cma_init_reserved_mem(phys_addr_t base, + phys_addr_t size, int order_per_bit, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align); extern bool cma_release(struct cma *cma, struct page *pages, int count); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6e6d338641fe..e6b62f30ab21 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -175,6 +175,52 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb, } #endif /* !CONFIG_HUGETLB_PAGE */ +/* + * hugepages at page global directory. If arch support + * hugepages at pgd level, they need to define this. + */ +#ifndef pgd_huge +#define pgd_huge(x) 0 +#endif + +#ifndef pgd_write +static inline int pgd_write(pgd_t pgd) +{ + BUG(); + return 0; +} +#endif + +#ifndef pud_write +static inline int pud_write(pud_t pud) +{ + BUG(); + return 0; +} +#endif + +#ifndef is_hugepd +/* + * Some architectures requires a hugepage directory format that is + * required to support multiple hugepage sizes. For example + * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables" + * introduced the same on powerpc. This allows for a more flexible hugepage + * pagetable layout. + */ +typedef struct { unsigned long pd; } hugepd_t; +#define is_hugepd(hugepd) (0) +#define __hugepd(x) ((hugepd_t) { (x) }) +static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, + int write, struct page **pages, int *nr) +{ + return 0; +} +#else +extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr, + unsigned pdshift, unsigned long end, + int write, struct page **pages, int *nr); +#endif #define HUGETLB_ANON_FILE "anon_hugepage" @@ -124,6 +124,7 @@ static int __init cma_activate_area(struct cma *cma) err: kfree(cma->bitmap); + cma->count = 0; return -EINVAL; } @@ -217,9 +218,8 @@ int __init cma_declare_contiguous(phys_addr_t base, phys_addr_t highmem_start = __pa(high_memory); int ret = 0; - pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n", - __func__, (unsigned long)size, (unsigned long)base, - (unsigned long)limit, (unsigned long)alignment); + pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n", + __func__, &size, &base, &limit, &alignment); if (cma_area_count == ARRAY_SIZE(cma_areas)) { pr_err("Not enough slots for CMA reserved regions!\n"); @@ -244,52 +244,72 @@ int __init cma_declare_contiguous(phys_addr_t base, size = ALIGN(size, alignment); limit &= ~(alignment - 1); + if (!base) + fixed = false; + /* size should be aligned with order_per_bit */ if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit)) return -EINVAL; /* - * adjust limit to avoid crossing low/high memory boundary for - * automatically allocated regions + * If allocating at a fixed base the request region must not cross the + * low/high memory boundary. */ - if (((limit == 0 || limit > memblock_end) && - (memblock_end - size < highmem_start && - memblock_end > highmem_start)) || - (!fixed && limit > highmem_start && limit - size < highmem_start)) { - limit = highmem_start; - } - - if (fixed && base < highmem_start && base+size > highmem_start) { + if (fixed && base < highmem_start && base + size > highmem_start) { ret = -EINVAL; - pr_err("Region at %08lx defined on low/high memory boundary (%08lx)\n", - (unsigned long)base, (unsigned long)highmem_start); + pr_err("Region at %pa defined on low/high memory boundary (%pa)\n", + &base, &highmem_start); goto err; } + /* + * If the limit is unspecified or above the memblock end, its effective + * value will be the memblock end. Set it explicitly to simplify further + * checks. + */ + if (limit == 0 || limit > memblock_end) + limit = memblock_end; + /* Reserve memory */ - if (base && fixed) { + if (fixed) { if (memblock_is_region_reserved(base, size) || memblock_reserve(base, size) < 0) { ret = -EBUSY; goto err; } } else { - phys_addr_t addr = memblock_alloc_range(size, alignment, base, - limit); + phys_addr_t addr = 0; + + /* + * All pages in the reserved area must come from the same zone. + * If the requested region crosses the low/high memory boundary, + * try allocating from high memory first and fall back to low + * memory in case of failure. + */ + if (base < highmem_start && limit > highmem_start) { + addr = memblock_alloc_range(size, alignment, + highmem_start, limit); + limit = highmem_start; + } + if (!addr) { - ret = -ENOMEM; - goto err; - } else { - base = addr; + addr = memblock_alloc_range(size, alignment, base, + limit); + if (!addr) { + ret = -ENOMEM; + goto err; + } } + + base = addr; } ret = cma_init_reserved_mem(base, size, order_per_bit, res_cma); if (ret) goto err; - pr_info("Reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M, - (unsigned long)base); + pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M, + &base); return 0; err: @@ -3,7 +3,6 @@ #include <linux/err.h> #include <linux/spinlock.h> -#include <linux/hugetlb.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> @@ -12,6 +11,7 @@ #include <linux/sched.h> #include <linux/rwsem.h> +#include <linux/hugetlb.h> #include <asm/pgtable.h> #include "internal.h" @@ -875,6 +875,49 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr, return 1; } +static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, + unsigned long end, int write, + struct page **pages, int *nr) +{ + int refs; + struct page *head, *page, *tail; + + if (write && !pgd_write(orig)) + return 0; + + refs = 0; + head = pgd_page(orig); + page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT); + tail = page; + do { + VM_BUG_ON_PAGE(compound_head(page) != head, page); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + + if (!page_cache_add_speculative(head, refs)) { + *nr -= refs; + return 0; + } + + if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { + *nr -= refs; + while (refs--) + put_page(head); + return 0; + } + + while (refs--) { + if (PageTail(tail)) + get_huge_page_tail(tail); + tail++; + } + + return 1; +} + static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { @@ -902,6 +945,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pages, nr)) return 0; + } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) { + /* + * architecture have different format for hugetlbfs + * pmd format and THP pmd format + */ + if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr, + PMD_SHIFT, next, write, pages, nr)) + return 0; } else if (!gup_pte_range(pmd, addr, next, write, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); @@ -909,22 +960,26 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(pgdp, addr); + pudp = pud_offset(&pgd, addr); do { pud_t pud = ACCESS_ONCE(*pudp); next = pud_addr_end(addr, end); if (pud_none(pud)) return 0; - if (pud_huge(pud)) { + if (unlikely(pud_huge(pud))) { if (!gup_huge_pud(pud, pudp, addr, next, write, - pages, nr)) + pages, nr)) + return 0; + } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { + if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, + PUD_SHIFT, next, write, pages, nr)) return 0; } else if (!gup_pmd_range(pud, addr, next, write, pages, nr)) return 0; @@ -970,10 +1025,20 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, local_irq_save(flags); pgdp = pgd_offset(mm, addr); do { + pgd_t pgd = ACCESS_ONCE(*pgdp); + next = pgd_addr_end(addr, end); - if (pgd_none(*pgdp)) + if (pgd_none(pgd)) break; - else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr)) + if (unlikely(pgd_huge(pgd))) { + if (!gup_huge_pgd(pgd, pgdp, addr, next, write, + pages, &nr)) + break; + } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { + if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, + PGDIR_SHIFT, next, write, pages, &nr)) + break; + } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) break; } while (pgdp++, addr = next, addr != end); local_irq_restore(flags); diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index de6662b14e1f..7e38b729696a 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -149,6 +149,7 @@ static int process_one_ticket(struct ceph_auth_client *ac, struct ceph_crypto_key old_key; void *ticket_buf = NULL; void *tp, *tpend; + void **ptp; struct ceph_timespec new_validity; struct ceph_crypto_key new_session_key; struct ceph_buffer *new_ticket_blob; @@ -208,25 +209,19 @@ static int process_one_ticket(struct ceph_auth_client *ac, goto out; } tp = ticket_buf; - dlen = ceph_decode_32(&tp); + ptp = &tp; + tpend = *ptp + dlen; } else { /* unencrypted */ - ceph_decode_32_safe(p, end, dlen, bad); - ticket_buf = kmalloc(dlen, GFP_NOFS); - if (!ticket_buf) { - ret = -ENOMEM; - goto out; - } - tp = ticket_buf; - ceph_decode_need(p, end, dlen, bad); - ceph_decode_copy(p, ticket_buf, dlen); + ptp = p; + tpend = end; } - tpend = tp + dlen; + ceph_decode_32_safe(ptp, tpend, dlen, bad); dout(" ticket blob is %d bytes\n", dlen); - ceph_decode_need(&tp, tpend, 1 + sizeof(u64), bad); - blob_struct_v = ceph_decode_8(&tp); - new_secret_id = ceph_decode_64(&tp); - ret = ceph_decode_buffer(&new_ticket_blob, &tp, tpend); + ceph_decode_need(ptp, tpend, 1 + sizeof(u64), bad); + blob_struct_v = ceph_decode_8(ptp); + new_secret_id = ceph_decode_64(ptp); + ret = ceph_decode_buffer(&new_ticket_blob, ptp, tpend); if (ret) goto out; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 559c9f619c20..8d1653caffdb 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -484,7 +484,7 @@ static int ceph_tcp_connect(struct ceph_connection *con) IPPROTO_TCP, &sock); if (ret) return ret; - sock->sk->sk_allocation = GFP_NOFS; + sock->sk->sk_allocation = GFP_NOFS | __GFP_MEMALLOC; #ifdef CONFIG_LOCKDEP lockdep_set_class(&sock->sk->sk_lock, &socket_class); @@ -509,6 +509,9 @@ static int ceph_tcp_connect(struct ceph_connection *con) return ret; } + + sk_set_memalloc(sock->sk); + con->sock = sock; return 0; } @@ -2769,8 +2772,11 @@ static void con_work(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); + unsigned long pflags = current->flags; bool fault; + current->flags |= PF_MEMALLOC; + mutex_lock(&con->mutex); while (true) { int ret; @@ -2824,6 +2830,8 @@ static void con_work(struct work_struct *work) con_fault_finish(con); con->ops->put(con); + + tsk_restore_flags(current, pflags, PF_MEMALLOC); } /* diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index a8f81c782856..515247601df4 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -82,7 +82,7 @@ parse_opts() { # opts } # Parameters -DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' '` +DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1` TRACING_DIR=$DEBUGFS_DIR/tracing TOP_DIR=`absdir $0` TEST_DIR=$TOP_DIR/test.d |