diff options
Diffstat (limited to 'arch/powerpc')
77 files changed, 2561 insertions, 738 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 79f25cef32df..84b861316ce7 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -108,6 +108,8 @@ config ARCH_NO_VIRT_TO_BUS config PPC bool default y + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE select HAVE_FUNCTION_TRACER select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_IDE @@ -326,7 +328,8 @@ config KEXEC config CRASH_DUMP bool "Build a kdump crash kernel" - depends on (PPC64 && RELOCATABLE) || 6xx + depends on PPC64 || 6xx + select RELOCATABLE if PPC64 help Build a kernel suitable for use as a kdump capture kernel. The same kernel binary can be used as production kernel and dump diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index f32829937aad..e84df338ea29 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -208,7 +208,7 @@ image-$(CONFIG_DEFAULT_UIMAGE) += uImage # # Theses are default targets to build images which embed device tree blobs. # They are only required on boards which do not have FDT support in firmware. -# Boards with newish u-boot firmare can use the uImage target above +# Boards with newish u-boot firmware can use the uImage target above # # Board ports in arch/powerpc/platform/40x/Kconfig @@ -356,7 +356,7 @@ $(obj)/zImage.initrd: $(addprefix $(obj)/, $(initrd-y)) @rm -f $@; ln $< $@ install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y)) - sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)" $< + sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)" $^ # anything not in $(targets) clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \ diff --git a/arch/powerpc/boot/dts/mpc836x_mds.dts b/arch/powerpc/boot/dts/mpc836x_mds.dts index 14534d04e4db..6e34f170fa62 100644 --- a/arch/powerpc/boot/dts/mpc836x_mds.dts +++ b/arch/powerpc/boot/dts/mpc836x_mds.dts @@ -69,8 +69,18 @@ }; bcsr@1,0 { + #address-cells = <1>; + #size-cells = <1>; compatible = "fsl,mpc8360mds-bcsr"; reg = <1 0 0x8000>; + ranges = <0 1 0 0x8000>; + + bcsr13: gpio-controller@d { + #gpio-cells = <2>; + compatible = "fsl,mpc8360mds-bcsr-gpio"; + reg = <0xd 1>; + gpio-controller; + }; }; }; @@ -195,10 +205,21 @@ }; par_io@1400 { + #address-cells = <1>; + #size-cells = <1>; reg = <0x1400 0x100>; + ranges = <0 0x1400 0x100>; device_type = "par_io"; num-ports = <7>; + qe_pio_b: gpio-controller@18 { + #gpio-cells = <2>; + compatible = "fsl,mpc8360-qe-pario-bank", + "fsl,mpc8323-qe-pario-bank"; + reg = <0x18 0x18>; + gpio-controller; + }; + pio1: ucc_pin@01 { pio-map = < /* port pin dir open_drain assignment has_irq */ @@ -282,6 +303,15 @@ }; }; + timer@440 { + compatible = "fsl,mpc8360-qe-gtm", + "fsl,qe-gtm", "fsl,gtm"; + reg = <0x440 0x40>; + clock-frequency = <132000000>; + interrupts = <12 13 14 15>; + interrupt-parent = <&qeic>; + }; + spi@4c0 { cell-index = <0>; compatible = "fsl,spi"; @@ -301,11 +331,20 @@ }; usb@6c0 { - compatible = "qe_udc"; + compatible = "fsl,mpc8360-qe-usb", + "fsl,mpc8323-qe-usb"; reg = <0x6c0 0x40 0x8b00 0x100>; interrupts = <11>; interrupt-parent = <&qeic>; - mode = "slave"; + fsl,fullspeed-clock = "clk21"; + fsl,lowspeed-clock = "brg9"; + gpios = <&qe_pio_b 2 0 /* USBOE */ + &qe_pio_b 3 0 /* USBTP */ + &qe_pio_b 8 0 /* USBTN */ + &qe_pio_b 9 0 /* USBRP */ + &qe_pio_b 11 0 /* USBRN */ + &bcsr13 5 0 /* SPEED */ + &bcsr13 4 1>; /* POWER */ }; enet0: ucc@2000 { diff --git a/arch/powerpc/boot/dts/mpc836x_rdk.dts b/arch/powerpc/boot/dts/mpc836x_rdk.dts index decadf3d9e98..37b789510d68 100644 --- a/arch/powerpc/boot/dts/mpc836x_rdk.dts +++ b/arch/powerpc/boot/dts/mpc836x_rdk.dts @@ -218,8 +218,23 @@ reg = <0x440 0x40>; interrupts = <12 13 14 15>; interrupt-parent = <&qeic>; - /* filled by u-boot */ - clock-frequency = <0>; + clock-frequency = <166666666>; + }; + + usb@6c0 { + compatible = "fsl,mpc8360-qe-usb", + "fsl,mpc8323-qe-usb"; + reg = <0x6c0 0x40 0x8b00 0x100>; + interrupts = <11>; + interrupt-parent = <&qeic>; + fsl,fullspeed-clock = "clk21"; + gpios = <&qe_pio_b 2 0 /* USBOE */ + &qe_pio_b 3 0 /* USBTP */ + &qe_pio_b 8 0 /* USBTN */ + &qe_pio_b 9 0 /* USBRP */ + &qe_pio_b 11 0 /* USBRN */ + &qe_pio_e 20 0 /* SPEED */ + &qe_pio_e 21 1 /* POWER */>; }; spi@4c0 { diff --git a/arch/powerpc/boot/dts/mpc8641_hpcn.dts b/arch/powerpc/boot/dts/mpc8641_hpcn.dts index 35d5e248ccd7..4481532cbe77 100644 --- a/arch/powerpc/boot/dts/mpc8641_hpcn.dts +++ b/arch/powerpc/boot/dts/mpc8641_hpcn.dts @@ -26,7 +26,13 @@ serial1 = &serial1; pci0 = &pci0; pci1 = &pci1; - rapidio0 = &rapidio0; +/* + * Only one of Rapid IO or PCI can be present due to HW limitations and + * due to the fact that the 2 now share address space in the new memory + * map. The most likely case is that we have PCI, so comment out the + * rapidio node. Leave it here for reference. + */ + /* rapidio0 = &rapidio0; */ }; cpus { @@ -62,18 +68,17 @@ reg = <0x00000000 0x40000000>; // 1G at 0x0 }; - localbus@f8005000 { + localbus@ffe05000 { #address-cells = <2>; #size-cells = <1>; compatible = "fsl,mpc8641-localbus", "simple-bus"; - reg = <0xf8005000 0x1000>; + reg = <0xffe05000 0x1000>; interrupts = <19 2>; interrupt-parent = <&mpic>; - ranges = <0 0 0xff800000 0x00800000 - 1 0 0xfe000000 0x01000000 - 2 0 0xf8200000 0x00100000 - 3 0 0xf8100000 0x00100000>; + ranges = <0 0 0xef800000 0x00800000 + 2 0 0xffdf8000 0x00008000 + 3 0 0xffdf0000 0x00008000>; flash@0,0 { compatible = "cfi-flash"; @@ -103,13 +108,13 @@ }; }; - soc8641@f8000000 { + soc8641@ffe00000 { #address-cells = <1>; #size-cells = <1>; device_type = "soc"; compatible = "simple-bus"; - ranges = <0x00000000 0xf8000000 0x00100000>; - reg = <0xf8000000 0x00001000>; // CCSRBAR + ranges = <0x00000000 0xffe00000 0x00100000>; + reg = <0xffe00000 0x00001000>; // CCSRBAR bus-frequency = <0>; i2c@3000 { @@ -340,17 +345,17 @@ }; }; - pci0: pcie@f8008000 { + pci0: pcie@ffe08000 { cell-index = <0>; compatible = "fsl,mpc8641-pcie"; device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; - reg = <0xf8008000 0x1000>; + reg = <0xffe08000 0x1000>; bus-range = <0x0 0xff>; ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>; + 0x01000000 0x0 0x00000000 0xffc00000 0x0 0x00010000>; clock-frequency = <33333333>; interrupt-parent = <&mpic>; interrupts = <24 2>; @@ -481,7 +486,7 @@ 0x01000000 0x0 0x00000000 0x01000000 0x0 0x00000000 - 0x0 0x00100000>; + 0x0 0x00010000>; uli1575@0 { reg = <0 0 0 0 0>; #size-cells = <2>; @@ -491,7 +496,7 @@ 0x0 0x20000000 0x01000000 0x0 0x00000000 0x01000000 0x0 0x00000000 - 0x0 0x00100000>; + 0x0 0x00010000>; isa@1e { device_type = "isa"; #interrupt-cells = <2>; @@ -549,17 +554,17 @@ }; - pci1: pcie@f8009000 { + pci1: pcie@ffe09000 { cell-index = <1>; compatible = "fsl,mpc8641-pcie"; device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; #address-cells = <3>; - reg = <0xf8009000 0x1000>; + reg = <0xffe09000 0x1000>; bus-range = <0 0xff>; ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000 - 0x01000000 0x0 0x00000000 0xe3000000 0x0 0x00100000>; + 0x01000000 0x0 0x00000000 0xffc10000 0x0 0x00010000>; clock-frequency = <33333333>; interrupt-parent = <&mpic>; interrupts = <25 2>; @@ -582,18 +587,21 @@ 0x01000000 0x0 0x00000000 0x01000000 0x0 0x00000000 - 0x0 0x00100000>; + 0x0 0x00010000>; }; }; - rapidio0: rapidio@f80c0000 { +/* + rapidio0: rapidio@ffec0000 { #address-cells = <2>; #size-cells = <2>; compatible = "fsl,rapidio-delta"; - reg = <0xf80c0000 0x20000>; - ranges = <0 0 0xc0000000 0 0x20000000>; + reg = <0xffec0000 0x20000>; + ranges = <0 0 0x80000000 0 0x20000000>; interrupt-parent = <&mpic>; - /* err_irq bell_outb_irq bell_inb_irq - msg1_tx_irq msg1_rx_irq msg2_tx_irq msg2_rx_irq */ + // err_irq bell_outb_irq bell_inb_irq + // msg1_tx_irq msg1_rx_irq msg2_tx_irq msg2_rx_irq interrupts = <48 2 49 2 50 2 53 2 54 2 55 2 56 2>; }; +*/ + }; diff --git a/arch/powerpc/boot/dts/sequoia.dts b/arch/powerpc/boot/dts/sequoia.dts index 3b295e8df53f..43cc68bd3192 100644 --- a/arch/powerpc/boot/dts/sequoia.dts +++ b/arch/powerpc/boot/dts/sequoia.dts @@ -134,7 +134,7 @@ }; USB1: usb@e0000400 { - compatible = "ohci-be"; + compatible = "ibm,usb-ohci-440epx", "ohci-be"; reg = <0x00000000 0xe0000400 0x00000060>; interrupt-parent = <&UIC0>; interrupts = <0x15 0x8>; diff --git a/arch/powerpc/boot/install.sh b/arch/powerpc/boot/install.sh index b002bfd56786..51b2387bdba0 100644 --- a/arch/powerpc/boot/install.sh +++ b/arch/powerpc/boot/install.sh @@ -15,7 +15,7 @@ # $2 - kernel image file # $3 - kernel map file # $4 - default install path (blank if root directory) -# $5 - kernel boot file, the zImage +# $5 and more - kernel boot files; zImage*, uImage, cuImage.*, etc. # # User may have a custom install script @@ -38,3 +38,15 @@ fi cat $2 > $4/$image_name cp $3 $4/System.map + +# Copy all the bootable image files +path=$4 +shift 4 +while [ $# -ne 0 ]; do + image_name=`basename $1` + if [ -f $path/$image_name ]; then + mv $path/$image_name $path/$image_name.old + fi + cat $1 > $path/$image_name + shift +done; diff --git a/arch/powerpc/configs/85xx/mpc8572_ds_defconfig b/arch/powerpc/configs/85xx/mpc8572_ds_defconfig index 635588319e0d..32aeb79216f7 100644 --- a/arch/powerpc/configs/85xx/mpc8572_ds_defconfig +++ b/arch/powerpc/configs/85xx/mpc8572_ds_defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.28-rc3 -# Sat Nov 8 12:40:13 2008 +# Linux kernel version: 2.6.28-rc8 +# Tue Dec 30 11:17:46 2008 # # CONFIG_PPC64 is not set @@ -21,7 +21,10 @@ CONFIG_FSL_BOOKE=y CONFIG_FSL_EMB_PERFMON=y # CONFIG_PHYS_64BIT is not set CONFIG_SPE=y +CONFIG_PPC_MMU_NOHASH=y # CONFIG_PPC_MM_SLICES is not set +CONFIG_SMP=y +CONFIG_NR_CPUS=2 CONFIG_PPC32=y CONFIG_WORD_SIZE=32 # CONFIG_ARCH_PHYS_ADDR_T_64BIT is not set @@ -50,7 +53,7 @@ CONFIG_ARCH_MAY_HAVE_PC_FDC=y CONFIG_PPC_OF=y CONFIG_OF=y CONFIG_PPC_UDBG_16550=y -# CONFIG_GENERIC_TBSYNC is not set +CONFIG_GENERIC_TBSYNC=y CONFIG_AUDIT_ARCH=y CONFIG_GENERIC_BUG=y CONFIG_DEFAULT_UIMAGE=y @@ -62,7 +65,7 @@ CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config" # General setup # CONFIG_EXPERIMENTAL=y -CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y CONFIG_INIT_ENV_ARG_LIMIT=32 CONFIG_LOCALVERSION="" CONFIG_LOCALVERSION_AUTO=y @@ -126,6 +129,7 @@ CONFIG_HAVE_IOREMAP_PROT=y CONFIG_HAVE_KPROBES=y CONFIG_HAVE_KRETPROBES=y CONFIG_HAVE_ARCH_TRACEHOOK=y +CONFIG_USE_GENERIC_SMP_HELPERS=y # CONFIG_HAVE_GENERIC_DMA_COHERENT is not set CONFIG_SLABINFO=y CONFIG_RT_MUTEXES=y @@ -138,6 +142,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_MODULE_SRCVERSION_ALL is not set CONFIG_KMOD=y +CONFIG_STOP_MACHINE=y CONFIG_BLOCK=y CONFIG_LBD=y # CONFIG_BLK_DEV_IO_TRACE is not set @@ -197,6 +202,7 @@ CONFIG_PPC_I8259=y # CONFIG_CPM2 is not set CONFIG_FSL_ULI1575=y # CONFIG_MPC8xxx_GPIO is not set +# CONFIG_SIMPLE_GPIO is not set # # Kernel options @@ -224,6 +230,7 @@ CONFIG_MATH_EMULATION=y CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y CONFIG_ARCH_HAS_WALK_MEMORY=y CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y +# CONFIG_IRQ_ALL_CPUS is not set CONFIG_ARCH_FLATMEM_ENABLE=y CONFIG_ARCH_POPULATES_NODE_MAP=y CONFIG_SELECT_MEMORY_MODEL=y @@ -241,6 +248,9 @@ CONFIG_ZONE_DMA_FLAG=1 CONFIG_BOUNCE=y CONFIG_VIRT_TO_BUS=y CONFIG_UNEVICTABLE_LRU=y +CONFIG_PPC_4K_PAGES=y +# CONFIG_PPC_16K_PAGES is not set +# CONFIG_PPC_64K_PAGES is not set CONFIG_FORCE_MAX_ZONEORDER=11 CONFIG_PROC_DEVICETREE=y # CONFIG_CMDLINE_BOOL is not set @@ -443,8 +453,10 @@ CONFIG_MISC_DEVICES=y # CONFIG_EEPROM_93CX6 is not set # CONFIG_SGI_IOC4 is not set # CONFIG_TIFM_CORE is not set +# CONFIG_ICS932S401 is not set # CONFIG_ENCLOSURE_SERVICES is not set # CONFIG_HP_ILO is not set +# CONFIG_C2PORT is not set CONFIG_HAVE_IDE=y # CONFIG_IDE is not set @@ -784,6 +796,7 @@ CONFIG_SERIAL_CORE_CONSOLE=y CONFIG_UNIX98_PTYS=y CONFIG_LEGACY_PTYS=y CONFIG_LEGACY_PTY_COUNT=256 +# CONFIG_HVC_UDBG is not set # CONFIG_IPMI_HANDLER is not set CONFIG_HW_RANDOM=y CONFIG_NVRAM=y @@ -869,11 +882,11 @@ CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y # CONFIG_THERMAL is not set # CONFIG_THERMAL_HWMON is not set # CONFIG_WATCHDOG is not set +CONFIG_SSB_POSSIBLE=y # # Sonics Silicon Backplane # -CONFIG_SSB_POSSIBLE=y # CONFIG_SSB is not set # @@ -886,14 +899,7 @@ CONFIG_SSB_POSSIBLE=y # CONFIG_PMIC_DA903X is not set # CONFIG_MFD_WM8400 is not set # CONFIG_MFD_WM8350_I2C is not set - -# -# Voltage and Current regulators -# # CONFIG_REGULATOR is not set -# CONFIG_REGULATOR_FIXED_VOLTAGE is not set -# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set -# CONFIG_REGULATOR_BQ24022 is not set # # Multimedia devices @@ -1252,11 +1258,11 @@ CONFIG_USB_OHCI_LITTLE_ENDIAN=y # CONFIG_USB_TMC is not set # -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' +# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed; # # -# may also be needed; see USB_STORAGE Help for more information +# see USB_STORAGE Help for more information # CONFIG_USB_STORAGE=y # CONFIG_USB_STORAGE_DEBUG is not set @@ -1348,6 +1354,7 @@ CONFIG_RTC_INTF_DEV=y # CONFIG_RTC_DRV_M41T80 is not set # CONFIG_RTC_DRV_S35390A is not set # CONFIG_RTC_DRV_FM3130 is not set +# CONFIG_RTC_DRV_RX8581 is not set # # SPI RTC drivers @@ -1624,6 +1631,7 @@ CONFIG_HAVE_FUNCTION_TRACER=y # CONFIG_SAMPLES is not set CONFIG_HAVE_ARCH_KGDB=y # CONFIG_KGDB is not set +CONFIG_PRINT_STACK_DEPTH=64 # CONFIG_DEBUG_STACKOVERFLOW is not set # CONFIG_DEBUG_STACK_USAGE is not set # CONFIG_DEBUG_PAGEALLOC is not set @@ -1649,11 +1657,16 @@ CONFIG_CRYPTO=y # # CONFIG_CRYPTO_FIPS is not set CONFIG_CRYPTO_ALGAPI=y +CONFIG_CRYPTO_ALGAPI2=y CONFIG_CRYPTO_AEAD=y +CONFIG_CRYPTO_AEAD2=y CONFIG_CRYPTO_BLKCIPHER=y +CONFIG_CRYPTO_BLKCIPHER2=y CONFIG_CRYPTO_HASH=y -CONFIG_CRYPTO_RNG=y +CONFIG_CRYPTO_HASH2=y +CONFIG_CRYPTO_RNG2=y CONFIG_CRYPTO_MANAGER=y +CONFIG_CRYPTO_MANAGER2=y # CONFIG_CRYPTO_GF128MUL is not set # CONFIG_CRYPTO_NULL is not set # CONFIG_CRYPTO_CRYPTD is not set diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 5ab7d7fe198c..9268602de5d0 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -35,3 +35,4 @@ unifdef-y += spu_info.h unifdef-y += termios.h unifdef-y += types.h unifdef-y += unistd.h +unifdef-y += swab.h diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 499be5bdd6fa..b401950f5259 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -5,7 +5,7 @@ * PowerPC atomic operations */ -typedef struct { int counter; } atomic_t; +#include <linux/types.h> #ifdef __KERNEL__ #include <linux/compiler.h> @@ -251,8 +251,6 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v) #ifdef __powerpc64__ -typedef struct { long counter; } atomic64_t; - #define ATOMIC64_INIT(i) { (i) } static __inline__ long atomic64_read(const atomic64_t *v) diff --git a/arch/powerpc/include/asm/byteorder.h b/arch/powerpc/include/asm/byteorder.h index d5de325472e9..5cca27a41532 100644 --- a/arch/powerpc/include/asm/byteorder.h +++ b/arch/powerpc/include/asm/byteorder.h @@ -8,86 +8,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <asm/types.h> -#include <linux/compiler.h> - -#define __BIG_ENDIAN - -#ifdef __GNUC__ -#ifdef __KERNEL__ - -static __inline__ __u16 ld_le16(const volatile __u16 *addr) -{ - __u16 val; - - __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); - return val; -} -#define __arch_swab16p ld_le16 - -static __inline__ void st_le16(volatile __u16 *addr, const __u16 val) -{ - __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); -} - -static inline void __arch_swab16s(__u16 *addr) -{ - st_le16(addr, *addr); -} -#define __arch_swab16s __arch_swab16s - -static __inline__ __u32 ld_le32(const volatile __u32 *addr) -{ - __u32 val; - - __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); - return val; -} -#define __arch_swab32p ld_le32 - -static __inline__ void st_le32(volatile __u32 *addr, const __u32 val) -{ - __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); -} - -static inline void __arch_swab32s(__u32 *addr) -{ - st_le32(addr, *addr); -} -#define __arch_swab32s __arch_swab32s - -static inline __attribute_const__ __u16 __arch_swab16(__u16 value) -{ - __u16 result; - - __asm__("rlwimi %0,%1,8,16,23" - : "=r" (result) - : "r" (value), "0" (value >> 8)); - return result; -} -#define __arch_swab16 __arch_swab16 - -static inline __attribute_const__ __u32 __arch_swab32(__u32 value) -{ - __u32 result; - - __asm__("rlwimi %0,%1,24,16,23\n\t" - "rlwimi %0,%1,8,8,15\n\t" - "rlwimi %0,%1,24,0,7" - : "=r" (result) - : "r" (value), "0" (value >> 24)); - return result; -} -#define __arch_swab32 __arch_swab32 - -#endif /* __KERNEL__ */ - -#ifndef __powerpc64__ -#define __SWAB_64_THRU_32__ -#endif /* __powerpc64__ */ - -#endif /* __GNUC__ */ - -#include <linux/byteorder.h> +#include <asm/swab.h> +#include <linux/byteorder/big_endian.h> #endif /* _ASM_POWERPC_BYTEORDER_H */ diff --git a/arch/powerpc/include/asm/cell-pmu.h b/arch/powerpc/include/asm/cell-pmu.h index 8066eede3a0c..b4b7338ad79e 100644 --- a/arch/powerpc/include/asm/cell-pmu.h +++ b/arch/powerpc/include/asm/cell-pmu.h @@ -37,9 +37,11 @@ #define CBE_PM_STOP_AT_MAX 0x40000000 #define CBE_PM_TRACE_MODE_GET(pm_control) (((pm_control) >> 28) & 0x3) #define CBE_PM_TRACE_MODE_SET(mode) (((mode) & 0x3) << 28) +#define CBE_PM_TRACE_BUF_OVFLW(bit) (((bit) & 0x1) << 17) #define CBE_PM_COUNT_MODE_SET(count) (((count) & 0x3) << 18) #define CBE_PM_FREEZE_ALL_CTRS 0x00100000 #define CBE_PM_ENABLE_EXT_TRACE 0x00008000 +#define CBE_PM_SPU_ADDR_TRACE_SET(msk) (((msk) & 0x3) << 9) /* Macros for the trace_address register. */ #define CBE_PM_TRACE_BUF_FULL 0x00000800 diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 26f0d0ab27a5..b1dafb6a9743 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -18,6 +18,12 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); /* + * The version of vma_mmu_pagesize() in arch/powerpc/mm/hugetlbpage.c needs + * to override the version in mm/hugetlb.c + */ +#define vma_mmu_pagesize vma_mmu_pagesize + +/* * If the arch doesn't supply something else, assume that hugepage * size aligned regions are ok without further preparation. */ diff --git a/arch/powerpc/include/asm/ioctls.h b/arch/powerpc/include/asm/ioctls.h index 279a6229584b..1842186d872c 100644 --- a/arch/powerpc/include/asm/ioctls.h +++ b/arch/powerpc/include/asm/ioctls.h @@ -89,6 +89,8 @@ #define TIOCSBRK 0x5427 /* BSD compatibility */ #define TIOCCBRK 0x5428 /* BSD compatibility */ #define TIOCGSID 0x5429 /* Return the session ID of FD */ +#define TIOCGRS485 0x542e +#define TIOCSRS485 0x542f #define TIOCGPTN _IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ #define TIOCSPTLCK _IOW('T',0x31, int) /* Lock/unlock Pty */ diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 6dbffc981702..7e06b43720d3 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -48,63 +48,8 @@ static inline void crash_setup_regs(struct pt_regs *newregs, { if (oldregs) memcpy(newregs, oldregs, sizeof(*newregs)); -#ifdef __powerpc64__ - else { - /* FIXME Merge this with xmon_save_regs ?? */ - unsigned long tmp1, tmp2; - __asm__ __volatile__ ( - "std 0,0(%2)\n" - "std 1,8(%2)\n" - "std 2,16(%2)\n" - "std 3,24(%2)\n" - "std 4,32(%2)\n" - "std 5,40(%2)\n" - "std 6,48(%2)\n" - "std 7,56(%2)\n" - "std 8,64(%2)\n" - "std 9,72(%2)\n" - "std 10,80(%2)\n" - "std 11,88(%2)\n" - "std 12,96(%2)\n" - "std 13,104(%2)\n" - "std 14,112(%2)\n" - "std 15,120(%2)\n" - "std 16,128(%2)\n" - "std 17,136(%2)\n" - "std 18,144(%2)\n" - "std 19,152(%2)\n" - "std 20,160(%2)\n" - "std 21,168(%2)\n" - "std 22,176(%2)\n" - "std 23,184(%2)\n" - "std 24,192(%2)\n" - "std 25,200(%2)\n" - "std 26,208(%2)\n" - "std 27,216(%2)\n" - "std 28,224(%2)\n" - "std 29,232(%2)\n" - "std 30,240(%2)\n" - "std 31,248(%2)\n" - "mfmsr %0\n" - "std %0, 264(%2)\n" - "mfctr %0\n" - "std %0, 280(%2)\n" - "mflr %0\n" - "std %0, 288(%2)\n" - "bl 1f\n" - "1: mflr %1\n" - "std %1, 256(%2)\n" - "mtlr %0\n" - "mfxer %0\n" - "std %0, 296(%2)\n" - : "=&r" (tmp1), "=&r" (tmp2) - : "b" (newregs) - : "memory"); - } -#else else ppc_save_regs(newregs); -#endif /* __powerpc64__ */ } extern void kexec_smp_wait(void); /* get and clear naca physid, wait for diff --git a/arch/powerpc/include/asm/oprofile_impl.h b/arch/powerpc/include/asm/oprofile_impl.h index 95035c602ba6..639dc96077ab 100644 --- a/arch/powerpc/include/asm/oprofile_impl.h +++ b/arch/powerpc/include/asm/oprofile_impl.h @@ -32,6 +32,12 @@ struct op_system_config { unsigned long mmcr0; unsigned long mmcr1; unsigned long mmcra; +#ifdef CONFIG_OPROFILE_CELL + /* Register for oprofile user tool to check cell kernel profiling + * suport. + */ + unsigned long cell_support; +#endif #endif unsigned long enable_kernel; unsigned long enable_user; diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index cff30c0ef1ff..eead5c67197a 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -320,6 +320,7 @@ enum ps3_match_id { enum ps3_match_sub_id { PS3_MATCH_SUB_ID_GPU_FB = 1, + PS3_MATCH_SUB_ID_GPU_RAMDISK = 2, }; #define PS3_MODULE_ALIAS_EHCI "ps3:1:0" @@ -332,6 +333,7 @@ enum ps3_match_sub_id { #define PS3_MODULE_ALIAS_STOR_FLASH "ps3:8:0" #define PS3_MODULE_ALIAS_SOUND "ps3:9:0" #define PS3_MODULE_ALIAS_GPU_FB "ps3:10:1" +#define PS3_MODULE_ALIAS_GPU_RAMDISK "ps3:10:2" #define PS3_MODULE_ALIAS_LPM "ps3:11:0" enum ps3_system_bus_device_type { diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h index edee15d269ea..a0a15311d0d8 100644 --- a/arch/powerpc/include/asm/qe.h +++ b/arch/powerpc/include/asm/qe.h @@ -17,6 +17,8 @@ #ifdef __KERNEL__ #include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/err.h> #include <asm/cpm.h> #include <asm/immap_qe.h> @@ -84,7 +86,11 @@ static inline bool qe_clock_is_brg(enum qe_clock clk) extern spinlock_t cmxgcr_lock; /* Export QE common operations */ +#ifdef CONFIG_QUICC_ENGINE extern void __init qe_reset(void); +#else +static inline void qe_reset(void) {} +#endif /* QE PIO */ #define QE_PIO_PINS 32 @@ -101,16 +107,43 @@ struct qe_pio_regs { #endif }; -extern int par_io_init(struct device_node *np); -extern int par_io_of_config(struct device_node *np); #define QE_PIO_DIR_IN 2 #define QE_PIO_DIR_OUT 1 extern void __par_io_config_pin(struct qe_pio_regs __iomem *par_io, u8 pin, int dir, int open_drain, int assignment, int has_irq); +#ifdef CONFIG_QUICC_ENGINE +extern int par_io_init(struct device_node *np); +extern int par_io_of_config(struct device_node *np); extern int par_io_config_pin(u8 port, u8 pin, int dir, int open_drain, int assignment, int has_irq); extern int par_io_data_set(u8 port, u8 pin, u8 val); +#else +static inline int par_io_init(struct device_node *np) { return -ENOSYS; } +static inline int par_io_of_config(struct device_node *np) { return -ENOSYS; } +static inline int par_io_config_pin(u8 port, u8 pin, int dir, int open_drain, + int assignment, int has_irq) { return -ENOSYS; } +static inline int par_io_data_set(u8 port, u8 pin, u8 val) { return -ENOSYS; } +#endif /* CONFIG_QUICC_ENGINE */ + +/* + * Pin multiplexing functions. + */ +struct qe_pin; +#ifdef CONFIG_QE_GPIO +extern struct qe_pin *qe_pin_request(struct device_node *np, int index); +extern void qe_pin_free(struct qe_pin *qe_pin); +extern void qe_pin_set_gpio(struct qe_pin *qe_pin); +extern void qe_pin_set_dedicated(struct qe_pin *pin); +#else +static inline struct qe_pin *qe_pin_request(struct device_node *np, int index) +{ + return ERR_PTR(-ENOSYS); +} +static inline void qe_pin_free(struct qe_pin *qe_pin) {} +static inline void qe_pin_set_gpio(struct qe_pin *qe_pin) {} +static inline void qe_pin_set_dedicated(struct qe_pin *pin) {} +#endif /* CONFIG_QE_GPIO */ /* QE internal API */ int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input); diff --git a/arch/powerpc/include/asm/qe_ic.h b/arch/powerpc/include/asm/qe_ic.h index 56a7745ca343..cf519663a791 100644 --- a/arch/powerpc/include/asm/qe_ic.h +++ b/arch/powerpc/include/asm/qe_ic.h @@ -17,6 +17,9 @@ #include <linux/irq.h> +struct device_node; +struct qe_ic; + #define NUM_OF_QE_IC_GROUPS 6 /* Flags when we init the QE IC */ @@ -54,17 +57,27 @@ enum qe_ic_grp_id { QE_IC_GRP_RISCB /* QE interrupt controller RISC group B */ }; +#ifdef CONFIG_QUICC_ENGINE void qe_ic_init(struct device_node *node, unsigned int flags, void (*low_handler)(unsigned int irq, struct irq_desc *desc), void (*high_handler)(unsigned int irq, struct irq_desc *desc)); +unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic); +unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic); +#else +static inline void qe_ic_init(struct device_node *node, unsigned int flags, + void (*low_handler)(unsigned int irq, struct irq_desc *desc), + void (*high_handler)(unsigned int irq, struct irq_desc *desc)) +{} +static inline unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic) +{ return 0; } +static inline unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic) +{ return 0; } +#endif /* CONFIG_QUICC_ENGINE */ + void qe_ic_set_highest_priority(unsigned int virq, int high); int qe_ic_set_priority(unsigned int virq, unsigned int priority); int qe_ic_set_high_priority(unsigned int virq, unsigned int priority, int high); -struct qe_ic; -unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic); -unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic); - static inline void qe_ic_cascade_low_ipic(unsigned int irq, struct irq_desc *desc) { diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h index 8b2eb044270a..0ab8d869e3d6 100644 --- a/arch/powerpc/include/asm/spu.h +++ b/arch/powerpc/include/asm/spu.h @@ -128,7 +128,7 @@ struct spu { int number; unsigned int irqs[3]; u32 node; - u64 flags; + unsigned long flags; u64 class_0_pending; u64 class_0_dar; u64 class_1_dar; diff --git a/arch/powerpc/include/asm/swab.h b/arch/powerpc/include/asm/swab.h new file mode 100644 index 000000000000..ef824ae4b79c --- /dev/null +++ b/arch/powerpc/include/asm/swab.h @@ -0,0 +1,90 @@ +#ifndef _ASM_POWERPC_SWAB_H +#define _ASM_POWERPC_SWAB_H + +/* + * 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 <asm/types.h> +#include <linux/compiler.h> + +#ifdef __GNUC__ + +#ifndef __powerpc64__ +#define __SWAB_64_THRU_32__ +#endif /* __powerpc64__ */ + +#ifdef __KERNEL__ + +static __inline__ __u16 ld_le16(const volatile __u16 *addr) +{ + __u16 val; + + __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); + return val; +} +#define __arch_swab16p ld_le16 + +static __inline__ void st_le16(volatile __u16 *addr, const __u16 val) +{ + __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); +} + +static inline void __arch_swab16s(__u16 *addr) +{ + st_le16(addr, *addr); +} +#define __arch_swab16s __arch_swab16s + +static __inline__ __u32 ld_le32(const volatile __u32 *addr) +{ + __u32 val; + + __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr)); + return val; +} +#define __arch_swab32p ld_le32 + +static __inline__ void st_le32(volatile __u32 *addr, const __u32 val) +{ + __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr)); +} + +static inline void __arch_swab32s(__u32 *addr) +{ + st_le32(addr, *addr); +} +#define __arch_swab32s __arch_swab32s + +static inline __attribute_const__ __u16 __arch_swab16(__u16 value) +{ + __u16 result; + + __asm__("rlwimi %0,%1,8,16,23" + : "=r" (result) + : "r" (value), "0" (value >> 8)); + return result; +} +#define __arch_swab16 __arch_swab16 + +static inline __attribute_const__ __u32 __arch_swab32(__u32 value) +{ + __u32 result; + + __asm__("rlwimi %0,%1,24,16,23\n\t" + "rlwimi %0,%1,8,8,15\n\t" + "rlwimi %0,%1,24,0,7" + : "=r" (result) + : "r" (value), "0" (value >> 24)); + return result; +} +#define __arch_swab32 __arch_swab32 + +#endif /* __KERNEL__ */ + +#endif /* __GNUC__ */ + +#endif /* _ASM_POWERPC_SWAB_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 1308a86e9070..8d1a419df35d 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -29,7 +29,7 @@ endif obj-y := cputable.o ptrace.o syscalls.o \ irq.o align.o signal_32.o pmc.o vdso.o \ init_task.o process.o systbl.o idle.o \ - signal.o sysfs.o + signal.o sysfs.o cacheinfo.o obj-y += vdso32/ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c new file mode 100644 index 000000000000..b33f0417a4bf --- /dev/null +++ b/arch/powerpc/kernel/cacheinfo.c @@ -0,0 +1,837 @@ +/* + * Processor cache information made available to userspace via sysfs; + * intended to be compatible with x86 intel_cacheinfo implementation. + * + * Copyright 2008 IBM Corporation + * Author: Nathan Lynch + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + */ + +#include <linux/cpu.h> +#include <linux/cpumask.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/kobject.h> +#include <linux/list.h> +#include <linux/notifier.h> +#include <linux/of.h> +#include <linux/percpu.h> +#include <asm/prom.h> + +#include "cacheinfo.h" + +/* per-cpu object for tracking: + * - a "cache" kobject for the top-level directory + * - a list of "index" objects representing the cpu's local cache hierarchy + */ +struct cache_dir { + struct kobject *kobj; /* bare (not embedded) kobject for cache + * directory */ + struct cache_index_dir *index; /* list of index objects */ +}; + +/* "index" object: each cpu's cache directory has an index + * subdirectory corresponding to a cache object associated with the + * cpu. This object's lifetime is managed via the embedded kobject. + */ +struct cache_index_dir { + struct kobject kobj; + struct cache_index_dir *next; /* next index in parent directory */ + struct cache *cache; +}; + +/* Template for determining which OF properties to query for a given + * cache type */ +struct cache_type_info { + const char *name; + const char *size_prop; + + /* Allow for both [di]-cache-line-size and + * [di]-cache-block-size properties. According to the PowerPC + * Processor binding, -line-size should be provided if it + * differs from the cache block size (that which is operated + * on by cache instructions), so we look for -line-size first. + * See cache_get_line_size(). */ + + const char *line_size_props[2]; + const char *nr_sets_prop; +}; + +/* These are used to index the cache_type_info array. */ +#define CACHE_TYPE_UNIFIED 0 +#define CACHE_TYPE_INSTRUCTION 1 +#define CACHE_TYPE_DATA 2 + +static const struct cache_type_info cache_type_info[] = { + { + /* PowerPC Processor binding says the [di]-cache-* + * must be equal on unified caches, so just use + * d-cache properties. */ + .name = "Unified", + .size_prop = "d-cache-size", + .line_size_props = { "d-cache-line-size", + "d-cache-block-size", }, + .nr_sets_prop = "d-cache-sets", + }, + { + .name = "Instruction", + .size_prop = "i-cache-size", + .line_size_props = { "i-cache-line-size", + "i-cache-block-size", }, + .nr_sets_prop = "i-cache-sets", + }, + { + .name = "Data", + .size_prop = "d-cache-size", + .line_size_props = { "d-cache-line-size", + "d-cache-block-size", }, + .nr_sets_prop = "d-cache-sets", + }, +}; + +/* Cache object: each instance of this corresponds to a distinct cache + * in the system. There are separate objects for Harvard caches: one + * each for instruction and data, and each refers to the same OF node. + * The refcount of the OF node is elevated for the lifetime of the + * cache object. A cache object is released when its shared_cpu_map + * is cleared (see cache_cpu_clear). + * + * A cache object is on two lists: an unsorted global list + * (cache_list) of cache objects; and a singly-linked list + * representing the local cache hierarchy, which is ordered by level + * (e.g. L1d -> L1i -> L2 -> L3). + */ +struct cache { + struct device_node *ofnode; /* OF node for this cache, may be cpu */ + struct cpumask shared_cpu_map; /* online CPUs using this cache */ + int type; /* split cache disambiguation */ + int level; /* level not explicit in device tree */ + struct list_head list; /* global list of cache objects */ + struct cache *next_local; /* next cache of >= level */ +}; + +static DEFINE_PER_CPU(struct cache_dir *, cache_dir); + +/* traversal/modification of this list occurs only at cpu hotplug time; + * access is serialized by cpu hotplug locking + */ +static LIST_HEAD(cache_list); + +static struct cache_index_dir *kobj_to_cache_index_dir(struct kobject *k) +{ + return container_of(k, struct cache_index_dir, kobj); +} + +static const char *cache_type_string(const struct cache *cache) +{ + return cache_type_info[cache->type].name; +} + +static void __cpuinit cache_init(struct cache *cache, int type, int level, struct device_node *ofnode) +{ + cache->type = type; + cache->level = level; + cache->ofnode = of_node_get(ofnode); + INIT_LIST_HEAD(&cache->list); + list_add(&cache->list, &cache_list); +} + +static struct cache *__cpuinit new_cache(int type, int level, struct device_node *ofnode) +{ + struct cache *cache; + + cache = kzalloc(sizeof(*cache), GFP_KERNEL); + if (cache) + cache_init(cache, type, level, ofnode); + + return cache; +} + +static void release_cache_debugcheck(struct cache *cache) +{ + struct cache *iter; + + list_for_each_entry(iter, &cache_list, list) + WARN_ONCE(iter->next_local == cache, + "cache for %s(%s) refers to cache for %s(%s)\n", + iter->ofnode->full_name, + cache_type_string(iter), + cache->ofnode->full_name, + cache_type_string(cache)); +} + +static void release_cache(struct cache *cache) +{ + if (!cache) + return; + + pr_debug("freeing L%d %s cache for %s\n", cache->level, + cache_type_string(cache), cache->ofnode->full_name); + + release_cache_debugcheck(cache); + list_del(&cache->list); + of_node_put(cache->ofnode); + kfree(cache); +} + +static void cache_cpu_set(struct cache *cache, int cpu) +{ + struct cache *next = cache; + + while (next) { + WARN_ONCE(cpumask_test_cpu(cpu, &next->shared_cpu_map), + "CPU %i already accounted in %s(%s)\n", + cpu, next->ofnode->full_name, + cache_type_string(next)); + cpumask_set_cpu(cpu, &next->shared_cpu_map); + next = next->next_local; + } +} + +static int cache_size(const struct cache *cache, unsigned int *ret) +{ + const char *propname; + const u32 *cache_size; + + propname = cache_type_info[cache->type].size_prop; + + cache_size = of_get_property(cache->ofnode, propname, NULL); + if (!cache_size) + return -ENODEV; + + *ret = *cache_size; + return 0; +} + +static int cache_size_kb(const struct cache *cache, unsigned int *ret) +{ + unsigned int size; + + if (cache_size(cache, &size)) + return -ENODEV; + + *ret = size / 1024; + return 0; +} + +/* not cache_line_size() because that's a macro in include/linux/cache.h */ +static int cache_get_line_size(const struct cache *cache, unsigned int *ret) +{ + const u32 *line_size; + int i, lim; + + lim = ARRAY_SIZE(cache_type_info[cache->type].line_size_props); + + for (i = 0; i < lim; i++) { + const char *propname; + + propname = cache_type_info[cache->type].line_size_props[i]; + line_size = of_get_property(cache->ofnode, propname, NULL); + if (line_size) + break; + } + + if (!line_size) + return -ENODEV; + + *ret = *line_size; + return 0; +} + +static int cache_nr_sets(const struct cache *cache, unsigned int *ret) +{ + const char *propname; + const u32 *nr_sets; + + propname = cache_type_info[cache->type].nr_sets_prop; + + nr_sets = of_get_property(cache->ofnode, propname, NULL); + if (!nr_sets) + return -ENODEV; + + *ret = *nr_sets; + return 0; +} + +static int cache_associativity(const struct cache *cache, unsigned int *ret) +{ + unsigned int line_size; + unsigned int nr_sets; + unsigned int size; + + if (cache_nr_sets(cache, &nr_sets)) + goto err; + + /* If the cache is fully associative, there is no need to + * check the other properties. + */ + if (nr_sets == 1) { + *ret = 0; + return 0; + } + + if (cache_get_line_size(cache, &line_size)) + goto err; + if (cache_size(cache, &size)) + goto err; + + if (!(nr_sets > 0 && size > 0 && line_size > 0)) + goto err; + + *ret = (size / nr_sets) / line_size; + return 0; +err: + return -ENODEV; +} + +/* helper for dealing with split caches */ +static struct cache *cache_find_first_sibling(struct cache *cache) +{ + struct cache *iter; + + if (cache->type == CACHE_TYPE_UNIFIED) + return cache; + + list_for_each_entry(iter, &cache_list, list) + if (iter->ofnode == cache->ofnode && iter->next_local == cache) + return iter; + + return cache; +} + +/* return the first cache on a local list matching node */ +static struct cache *cache_lookup_by_node(const struct device_node *node) +{ + struct cache *cache = NULL; + struct cache *iter; + + list_for_each_entry(iter, &cache_list, list) { + if (iter->ofnode != node) + continue; + cache = cache_find_first_sibling(iter); + break; + } + + return cache; +} + +static bool cache_node_is_unified(const struct device_node *np) +{ + return of_get_property(np, "cache-unified", NULL); +} + +static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level) +{ + struct cache *cache; + + pr_debug("creating L%d ucache for %s\n", level, node->full_name); + + cache = new_cache(CACHE_TYPE_UNIFIED, level, node); + + return cache; +} + +static struct cache *__cpuinit cache_do_one_devnode_split(struct device_node *node, int level) +{ + struct cache *dcache, *icache; + + pr_debug("creating L%d dcache and icache for %s\n", level, + node->full_name); + + dcache = new_cache(CACHE_TYPE_DATA, level, node); + icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node); + + if (!dcache || !icache) + goto err; + + dcache->next_local = icache; + + return dcache; +err: + release_cache(dcache); + release_cache(icache); + return NULL; +} + +static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, int level) +{ + struct cache *cache; + + if (cache_node_is_unified(node)) + cache = cache_do_one_devnode_unified(node, level); + else + cache = cache_do_one_devnode_split(node, level); + + return cache; +} + +static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *node, int level) +{ + struct cache *cache; + + cache = cache_lookup_by_node(node); + + WARN_ONCE(cache && cache->level != level, + "cache level mismatch on lookup (got %d, expected %d)\n", + cache->level, level); + + if (!cache) + cache = cache_do_one_devnode(node, level); + + return cache; +} + +static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigger) +{ + while (smaller->next_local) { + if (smaller->next_local == bigger) + return; /* already linked */ + smaller = smaller->next_local; + } + + smaller->next_local = bigger; +} + +static void __cpuinit do_subsidiary_caches_debugcheck(struct cache *cache) +{ + WARN_ON_ONCE(cache->level != 1); + WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu")); +} + +static void __cpuinit do_subsidiary_caches(struct cache *cache) +{ + struct device_node *subcache_node; + int level = cache->level; + + do_subsidiary_caches_debugcheck(cache); + + while ((subcache_node = of_find_next_cache_node(cache->ofnode))) { + struct cache *subcache; + + level++; + subcache = cache_lookup_or_instantiate(subcache_node, level); + of_node_put(subcache_node); + if (!subcache) + break; + + link_cache_lists(cache, subcache); + cache = subcache; + } +} + +static struct cache *__cpuinit cache_chain_instantiate(unsigned int cpu_id) +{ + struct device_node *cpu_node; + struct cache *cpu_cache = NULL; + + pr_debug("creating cache object(s) for CPU %i\n", cpu_id); + + cpu_node = of_get_cpu_node(cpu_id, NULL); + WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id); + if (!cpu_node) + goto out; + + cpu_cache = cache_lookup_or_instantiate(cpu_node, 1); + if (!cpu_cache) + goto out; + + do_subsidiary_caches(cpu_cache); + + cache_cpu_set(cpu_cache, cpu_id); +out: + of_node_put(cpu_node); + + return cpu_cache; +} + +static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_id) +{ + struct cache_dir *cache_dir; + struct sys_device *sysdev; + struct kobject *kobj = NULL; + + sysdev = get_cpu_sysdev(cpu_id); + WARN_ONCE(!sysdev, "no sysdev for CPU %i\n", cpu_id); + if (!sysdev) + goto err; + + kobj = kobject_create_and_add("cache", &sysdev->kobj); + if (!kobj) + goto err; + + cache_dir = kzalloc(sizeof(*cache_dir), GFP_KERNEL); + if (!cache_dir) + goto err; + + cache_dir->kobj = kobj; + + WARN_ON_ONCE(per_cpu(cache_dir, cpu_id) != NULL); + + per_cpu(cache_dir, cpu_id) = cache_dir; + + return cache_dir; +err: + kobject_put(kobj); + return NULL; +} + +static void cache_index_release(struct kobject *kobj) +{ + struct cache_index_dir *index; + + index = kobj_to_cache_index_dir(kobj); + + pr_debug("freeing index directory for L%d %s cache\n", + index->cache->level, cache_type_string(index->cache)); + + kfree(index); +} + +static ssize_t cache_index_show(struct kobject *k, struct attribute *attr, char *buf) +{ + struct kobj_attribute *kobj_attr; + + kobj_attr = container_of(attr, struct kobj_attribute, attr); + + return kobj_attr->show(k, kobj_attr, buf); +} + +static struct cache *index_kobj_to_cache(struct kobject *k) +{ + struct cache_index_dir *index; + + index = kobj_to_cache_index_dir(k); + + return index->cache; +} + +static ssize_t size_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + unsigned int size_kb; + struct cache *cache; + + cache = index_kobj_to_cache(k); + + if (cache_size_kb(cache, &size_kb)) + return -ENODEV; + + return sprintf(buf, "%uK\n", size_kb); +} + +static struct kobj_attribute cache_size_attr = + __ATTR(size, 0444, size_show, NULL); + + +static ssize_t line_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + unsigned int line_size; + struct cache *cache; + + cache = index_kobj_to_cache(k); + + if (cache_get_line_size(cache, &line_size)) + return -ENODEV; + + return sprintf(buf, "%u\n", line_size); +} + +static struct kobj_attribute cache_line_size_attr = + __ATTR(coherency_line_size, 0444, line_size_show, NULL); + +static ssize_t nr_sets_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + unsigned int nr_sets; + struct cache *cache; + + cache = index_kobj_to_cache(k); + + if (cache_nr_sets(cache, &nr_sets)) + return -ENODEV; + + return sprintf(buf, "%u\n", nr_sets); +} + +static struct kobj_attribute cache_nr_sets_attr = + __ATTR(number_of_sets, 0444, nr_sets_show, NULL); + +static ssize_t associativity_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + unsigned int associativity; + struct cache *cache; + + cache = index_kobj_to_cache(k); + + if (cache_associativity(cache, &associativity)) + return -ENODEV; + + return sprintf(buf, "%u\n", associativity); +} + +static struct kobj_attribute cache_assoc_attr = + __ATTR(ways_of_associativity, 0444, associativity_show, NULL); + +static ssize_t type_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + struct cache *cache; + + cache = index_kobj_to_cache(k); + + return sprintf(buf, "%s\n", cache_type_string(cache)); +} + +static struct kobj_attribute cache_type_attr = + __ATTR(type, 0444, type_show, NULL); + +static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + struct cache_index_dir *index; + struct cache *cache; + + index = kobj_to_cache_index_dir(k); + cache = index->cache; + + return sprintf(buf, "%d\n", cache->level); +} + +static struct kobj_attribute cache_level_attr = + __ATTR(level, 0444, level_show, NULL); + +static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + struct cache_index_dir *index; + struct cache *cache; + int len; + int n = 0; + + index = kobj_to_cache_index_dir(k); + cache = index->cache; + len = PAGE_SIZE - 2; + + if (len > 1) { + n = cpumask_scnprintf(buf, len, &cache->shared_cpu_map); + buf[n++] = '\n'; + buf[n] = '\0'; + } + return n; +} + +static struct kobj_attribute cache_shared_cpu_map_attr = + __ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL); + +/* Attributes which should always be created -- the kobject/sysfs core + * does this automatically via kobj_type->default_attrs. This is the + * minimum data required to uniquely identify a cache. + */ +static struct attribute *cache_index_default_attrs[] = { + &cache_type_attr.attr, + &cache_level_attr.attr, + &cache_shared_cpu_map_attr.attr, + NULL, +}; + +/* Attributes which should be created if the cache device node has the + * right properties -- see cacheinfo_create_index_opt_attrs + */ +static struct kobj_attribute *cache_index_opt_attrs[] = { + &cache_size_attr, + &cache_line_size_attr, + &cache_nr_sets_attr, + &cache_assoc_attr, +}; + +static struct sysfs_ops cache_index_ops = { + .show = cache_index_show, +}; + +static struct kobj_type cache_index_type = { + .release = cache_index_release, + .sysfs_ops = &cache_index_ops, + .default_attrs = cache_index_default_attrs, +}; + +static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir) +{ + const char *cache_name; + const char *cache_type; + struct cache *cache; + char *buf; + int i; + + buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!buf) + return; + + cache = dir->cache; + cache_name = cache->ofnode->full_name; + cache_type = cache_type_string(cache); + + /* We don't want to create an attribute that can't provide a + * meaningful value. Check the return value of each optional + * attribute's ->show method before registering the + * attribute. + */ + for (i = 0; i < ARRAY_SIZE(cache_index_opt_attrs); i++) { + struct kobj_attribute *attr; + ssize_t rc; + + attr = cache_index_opt_attrs[i]; + + rc = attr->show(&dir->kobj, attr, buf); + if (rc <= 0) { + pr_debug("not creating %s attribute for " + "%s(%s) (rc = %zd)\n", + attr->attr.name, cache_name, + cache_type, rc); + continue; + } + if (sysfs_create_file(&dir->kobj, &attr->attr)) + pr_debug("could not create %s attribute for %s(%s)\n", + attr->attr.name, cache_name, cache_type); + } + + kfree(buf); +} + +static void __cpuinit cacheinfo_create_index_dir(struct cache *cache, int index, struct cache_dir *cache_dir) +{ + struct cache_index_dir *index_dir; + int rc; + + index_dir = kzalloc(sizeof(*index_dir), GFP_KERNEL); + if (!index_dir) + goto err; + + index_dir->cache = cache; + + rc = kobject_init_and_add(&index_dir->kobj, &cache_index_type, + cache_dir->kobj, "index%d", index); + if (rc) + goto err; + + index_dir->next = cache_dir->index; + cache_dir->index = index_dir; + + cacheinfo_create_index_opt_attrs(index_dir); + + return; +err: + kfree(index_dir); +} + +static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache *cache_list) +{ + struct cache_dir *cache_dir; + struct cache *cache; + int index = 0; + + cache_dir = cacheinfo_create_cache_dir(cpu_id); + if (!cache_dir) + return; + + cache = cache_list; + while (cache) { + cacheinfo_create_index_dir(cache, index, cache_dir); + index++; + cache = cache->next_local; + } +} + +void __cpuinit cacheinfo_cpu_online(unsigned int cpu_id) +{ + struct cache *cache; + + cache = cache_chain_instantiate(cpu_id); + if (!cache) + return; + + cacheinfo_sysfs_populate(cpu_id, cache); +} + +#ifdef CONFIG_HOTPLUG_CPU /* functions needed for cpu offline */ + +static struct cache *cache_lookup_by_cpu(unsigned int cpu_id) +{ + struct device_node *cpu_node; + struct cache *cache; + + cpu_node = of_get_cpu_node(cpu_id, NULL); + WARN_ONCE(!cpu_node, "no OF node found for CPU %i\n", cpu_id); + if (!cpu_node) + return NULL; + + cache = cache_lookup_by_node(cpu_node); + of_node_put(cpu_node); + + return cache; +} + +static void remove_index_dirs(struct cache_dir *cache_dir) +{ + struct cache_index_dir *index; + + index = cache_dir->index; + + while (index) { + struct cache_index_dir *next; + + next = index->next; + kobject_put(&index->kobj); + index = next; + } +} + +static void remove_cache_dir(struct cache_dir *cache_dir) +{ + remove_index_dirs(cache_dir); + + kobject_put(cache_dir->kobj); + + kfree(cache_dir); +} + +static void cache_cpu_clear(struct cache *cache, int cpu) +{ + while (cache) { + struct cache *next = cache->next_local; + + WARN_ONCE(!cpumask_test_cpu(cpu, &cache->shared_cpu_map), + "CPU %i not accounted in %s(%s)\n", + cpu, cache->ofnode->full_name, + cache_type_string(cache)); + + cpumask_clear_cpu(cpu, &cache->shared_cpu_map); + + /* Release the cache object if all the cpus using it + * are offline */ + if (cpumask_empty(&cache->shared_cpu_map)) + release_cache(cache); + + cache = next; + } +} + +void cacheinfo_cpu_offline(unsigned int cpu_id) +{ + struct cache_dir *cache_dir; + struct cache *cache; + + /* Prevent userspace from seeing inconsistent state - remove + * the sysfs hierarchy first */ + cache_dir = per_cpu(cache_dir, cpu_id); + + /* careful, sysfs population may have failed */ + if (cache_dir) + remove_cache_dir(cache_dir); + + per_cpu(cache_dir, cpu_id) = NULL; + + /* clear the CPU's bit in its cache chain, possibly freeing + * cache objects */ + cache = cache_lookup_by_cpu(cpu_id); + if (cache) + cache_cpu_clear(cache, cpu_id); +} +#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/kernel/cacheinfo.h b/arch/powerpc/kernel/cacheinfo.h new file mode 100644 index 000000000000..a7b74d36acd7 --- /dev/null +++ b/arch/powerpc/kernel/cacheinfo.h @@ -0,0 +1,8 @@ +#ifndef _PPC_CACHEINFO_H +#define _PPC_CACHEINFO_H + +/* These are just hooks for sysfs.c to use. */ +extern void cacheinfo_cpu_online(unsigned int cpu_id); +extern void cacheinfo_cpu_offline(unsigned int cpu_id); + +#endif /* _PPC_CACHEINFO_H */ diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index de79915452c8..c9329786073b 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -96,9 +96,10 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p) void __kprobes arch_remove_kprobe(struct kprobe *p) { - mutex_lock(&kprobe_mutex); - free_insn_slot(p->ainsn.insn, 0); - mutex_unlock(&kprobe_mutex); + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } } static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) @@ -316,7 +317,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, /* * It is possible to have multiple instances associated with a given * task either because an multiple functions in the call path - * have a return probe installed on them, and/or more then one return + * have a return probe installed on them, and/or more than one return * return probe was registered for a target function. * * We can handle this because: diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2538030954d8..da5a3855a0c4 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -16,7 +16,7 @@ * 2 of the License, or (at your option) any later version. */ -#undef DEBUG +#define DEBUG #include <linux/kernel.h> #include <linux/pci.h> @@ -1356,6 +1356,63 @@ static void __init pcibios_allocate_resources(int pass) } } +static void __init pcibios_reserve_legacy_regions(struct pci_bus *bus) +{ + struct pci_controller *hose = pci_bus_to_host(bus); + resource_size_t offset; + struct resource *res, *pres; + int i; + + pr_debug("Reserving legacy ranges for domain %04x\n", pci_domain_nr(bus)); + + /* Check for IO */ + if (!(hose->io_resource.flags & IORESOURCE_IO)) + goto no_io; + offset = (unsigned long)hose->io_base_virt - _IO_BASE; + res = kzalloc(sizeof(struct resource), GFP_KERNEL); + BUG_ON(res == NULL); + res->name = "Legacy IO"; + res->flags = IORESOURCE_IO; + res->start = offset; + res->end = (offset + 0xfff) & 0xfffffffful; + pr_debug("Candidate legacy IO: %pR\n", res); + if (request_resource(&hose->io_resource, res)) { + printk(KERN_DEBUG + "PCI %04x:%02x Cannot reserve Legacy IO %pR\n", + pci_domain_nr(bus), bus->number, res); + kfree(res); + } + + no_io: + /* Check for memory */ + offset = hose->pci_mem_offset; + pr_debug("hose mem offset: %016llx\n", (unsigned long long)offset); + for (i = 0; i < 3; i++) { + pres = &hose->mem_resources[i]; + if (!(pres->flags & IORESOURCE_MEM)) + continue; + pr_debug("hose mem res: %pR\n", pres); + if ((pres->start - offset) <= 0xa0000 && + (pres->end - offset) >= 0xbffff) + break; + } + if (i >= 3) + return; + res = kzalloc(sizeof(struct resource), GFP_KERNEL); + BUG_ON(res == NULL); + res->name = "Legacy VGA memory"; + res->flags = IORESOURCE_MEM; + res->start = 0xa0000 + offset; + res->end = 0xbffff + offset; + pr_debug("Candidate VGA memory: %pR\n", res); + if (request_resource(pres, res)) { + printk(KERN_DEBUG + "PCI %04x:%02x Cannot reserve VGA memory %pR\n", + pci_domain_nr(bus), bus->number, res); + kfree(res); + } +} + void __init pcibios_resource_survey(void) { struct pci_bus *b; @@ -1371,6 +1428,18 @@ void __init pcibios_resource_survey(void) pcibios_allocate_resources(1); } + /* Before we start assigning unassigned resource, we try to reserve + * the low IO area and the VGA memory area if they intersect the + * bus available resources to avoid allocating things on top of them + */ + if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { + list_for_each_entry(b, &pci_root_buses, node) + pcibios_reserve_legacy_regions(b); + } + + /* Now, if the platform didn't decide to blindly trust the firmware, + * we proceed to assigning things that were left unassigned + */ if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) { pr_debug("PCI: Assigning unassigned resouces...\n"); pci_assign_unassigned_resources(); diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 39fadc6e1492..586962f65c2a 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -560,9 +560,14 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus, * G5 machines... So when something asks for bus 0 io base * (bus 0 is HT root), we return the AGP one instead. */ - if (machine_is_compatible("MacRISC4")) - if (in_bus == 0) + if (in_bus == 0 && machine_is_compatible("MacRISC4")) { + struct device_node *agp; + + agp = of_find_compatible_node(NULL, NULL, "u3-agp"); + if (agp) in_bus = 0xf0; + of_node_put(agp); + } /* That syscall isn't quite compatible with PCI domains, but it's * used on pre-domains setup. We return the first match diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index dcec1325d340..c8b27bb4dbde 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -165,6 +165,7 @@ EXPORT_SYMBOL(timer_interrupt); EXPORT_SYMBOL(irq_desc); EXPORT_SYMBOL(tb_ticks_per_jiffy); EXPORT_SYMBOL(cacheable_memcpy); +EXPORT_SYMBOL(cacheable_memzero); #endif #ifdef CONFIG_PPC32 diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 6f73c739f1e2..c09cffafb6ee 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -824,11 +824,11 @@ static int __init early_init_dt_scan_chosen(unsigned long node, #endif #ifdef CONFIG_KEXEC - lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); + lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL); if (lprop) crashk_res.start = *lprop; - lprop = (u64*)of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL); + lprop = of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL); if (lprop) crashk_res.end = crashk_res.start + *lprop - 1; #endif @@ -893,12 +893,12 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) u64 base, size, lmb_size; unsigned int is_kexec_kdump = 0, rngs; - ls = (cell_t *)of_get_flat_dt_prop(node, "ibm,lmb-size", &l); + ls = of_get_flat_dt_prop(node, "ibm,lmb-size", &l); if (ls == NULL || l < dt_root_size_cells * sizeof(cell_t)) return 0; lmb_size = dt_mem_next_cell(dt_root_size_cells, &ls); - dm = (cell_t *)of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l); + dm = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &l); if (dm == NULL || l < sizeof(cell_t)) return 0; @@ -907,7 +907,7 @@ static int __init early_init_dt_scan_drconf_memory(unsigned long node) return 0; /* check if this is a kexec/kdump kernel. */ - usm = (cell_t *)of_get_flat_dt_prop(node, "linux,drconf-usable-memory", + usm = of_get_flat_dt_prop(node, "linux,drconf-usable-memory", &l); if (usm != NULL) is_kexec_kdump = 1; @@ -981,9 +981,9 @@ static int __init early_init_dt_scan_memory(unsigned long node, } else if (strcmp(type, "memory") != 0) return 0; - reg = (cell_t *)of_get_flat_dt_prop(node, "linux,usable-memory", &l); + reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l); if (reg == NULL) - reg = (cell_t *)of_get_flat_dt_prop(node, "reg", &l); + reg = of_get_flat_dt_prop(node, "reg", &l); if (reg == NULL) return 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 2445945d3761..7f1b33d5e30d 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -1210,7 +1210,7 @@ static void __init prom_initialize_tce_table(void) /* Initialize the table to have a one-to-one mapping * over the allocated size. */ - tce_entryp = (unsigned long *)base; + tce_entryp = (u64 *)base; for (i = 0; i < (minsize >> 3) ;tce_entryp++, i++) { tce_entry = (i << PAGE_SHIFT); tce_entry |= 0x3; diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 8c1335566089..8f0856f312da 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -232,11 +232,6 @@ int of_pci_address_to_resource(struct device_node *dev, int bar, } EXPORT_SYMBOL_GPL(of_pci_address_to_resource); -static u8 of_irq_pci_swizzle(u8 slot, u8 pin) -{ - return (((pin - 1) + slot) % 4) + 1; -} - int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) { struct device_node *dn, *ppnode; @@ -306,7 +301,7 @@ int of_irq_map_pci(struct pci_dev *pdev, struct of_irq *out_irq) /* We can only get here if we hit a P2P bridge with no node, * let's do standard swizzling and try again */ - lspec = of_irq_pci_swizzle(PCI_SLOT(pdev->devfn), lspec); + lspec = pci_swizzle_interrupt_pin(pdev, lspec); pdev = ppdev; } diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 0c64f10087b9..4a2ee08af6a7 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -18,6 +18,8 @@ #include <asm/machdep.h> #include <asm/smp.h> +#include "cacheinfo.h" + #ifdef CONFIG_PPC64 #include <asm/paca.h> #include <asm/lppaca.h> @@ -25,8 +27,6 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); -static DEFINE_PER_CPU(struct kobject *, cache_toplevel); - /* * SMT snooze delay stuff, 64-bit only for now */ @@ -343,283 +343,6 @@ static struct sysdev_attribute pa6t_attrs[] = { #endif /* HAS_PPC_PMC_PA6T */ #endif /* HAS_PPC_PMC_CLASSIC */ -struct cache_desc { - struct kobject kobj; - struct cache_desc *next; - const char *type; /* Instruction, Data, or Unified */ - u32 size; /* total cache size in KB */ - u32 line_size; /* in bytes */ - u32 nr_sets; /* number of sets */ - u32 level; /* e.g. 1, 2, 3... */ - u32 associativity; /* e.g. 8-way... 0 is fully associative */ -}; - -DEFINE_PER_CPU(struct cache_desc *, cache_desc); - -static struct cache_desc *kobj_to_cache_desc(struct kobject *k) -{ - return container_of(k, struct cache_desc, kobj); -} - -static void cache_desc_release(struct kobject *k) -{ - struct cache_desc *desc = kobj_to_cache_desc(k); - - pr_debug("%s: releasing %s\n", __func__, kobject_name(k)); - - if (desc->next) - kobject_put(&desc->next->kobj); - - kfree(kobj_to_cache_desc(k)); -} - -static ssize_t cache_desc_show(struct kobject *k, struct attribute *attr, char *buf) -{ - struct kobj_attribute *kobj_attr; - - kobj_attr = container_of(attr, struct kobj_attribute, attr); - - return kobj_attr->show(k, kobj_attr, buf); -} - -static struct sysfs_ops cache_desc_sysfs_ops = { - .show = cache_desc_show, -}; - -static struct kobj_type cache_desc_type = { - .release = cache_desc_release, - .sysfs_ops = &cache_desc_sysfs_ops, -}; - -static ssize_t cache_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf) -{ - struct cache_desc *cache = kobj_to_cache_desc(k); - - return sprintf(buf, "%uK\n", cache->size); -} - -static struct kobj_attribute cache_size_attr = - __ATTR(size, 0444, cache_size_show, NULL); - -static ssize_t cache_line_size_show(struct kobject *k, struct kobj_attribute *attr, char *buf) -{ - struct cache_desc *cache = kobj_to_cache_desc(k); - - return sprintf(buf, "%u\n", cache->line_size); -} - -static struct kobj_attribute cache_line_size_attr = - __ATTR(coherency_line_size, 0444, cache_line_size_show, NULL); - -static ssize_t cache_nr_sets_show(struct kobject *k, struct kobj_attribute *attr, char *buf) -{ - struct cache_desc *cache = kobj_to_cache_desc(k); - - return sprintf(buf, "%u\n", cache->nr_sets); -} - -static struct kobj_attribute cache_nr_sets_attr = - __ATTR(number_of_sets, 0444, cache_nr_sets_show, NULL); - -static ssize_t cache_type_show(struct kobject *k, struct kobj_attribute *attr, char *buf) -{ - struct cache_desc *cache = kobj_to_cache_desc(k); - - return sprintf(buf, "%s\n", cache->type); -} - -static struct kobj_attribute cache_type_attr = - __ATTR(type, 0444, cache_type_show, NULL); - -static ssize_t cache_level_show(struct kobject *k, struct kobj_attribute *attr, char *buf) -{ - struct cache_desc *cache = kobj_to_cache_desc(k); - - return sprintf(buf, "%u\n", cache->level); -} - -static struct kobj_attribute cache_level_attr = - __ATTR(level, 0444, cache_level_show, NULL); - -static ssize_t cache_assoc_show(struct kobject *k, struct kobj_attribute *attr, char *buf) -{ - struct cache_desc *cache = kobj_to_cache_desc(k); - - return sprintf(buf, "%u\n", cache->associativity); -} - -static struct kobj_attribute cache_assoc_attr = - __ATTR(ways_of_associativity, 0444, cache_assoc_show, NULL); - -struct cache_desc_info { - const char *type; - const char *size_prop; - const char *line_size_prop; - const char *nr_sets_prop; -}; - -/* PowerPC Processor binding says the [di]-cache-* must be equal on - * unified caches, so just use d-cache properties. */ -static struct cache_desc_info ucache_info = { - .type = "Unified", - .size_prop = "d-cache-size", - .line_size_prop = "d-cache-line-size", - .nr_sets_prop = "d-cache-sets", -}; - -static struct cache_desc_info dcache_info = { - .type = "Data", - .size_prop = "d-cache-size", - .line_size_prop = "d-cache-line-size", - .nr_sets_prop = "d-cache-sets", -}; - -static struct cache_desc_info icache_info = { - .type = "Instruction", - .size_prop = "i-cache-size", - .line_size_prop = "i-cache-line-size", - .nr_sets_prop = "i-cache-sets", -}; - -static struct cache_desc * __cpuinit create_cache_desc(struct device_node *np, struct kobject *parent, int index, int level, struct cache_desc_info *info) -{ - const u32 *cache_line_size; - struct cache_desc *new; - const u32 *cache_size; - const u32 *nr_sets; - int rc; - - new = kzalloc(sizeof(*new), GFP_KERNEL); - if (!new) - return NULL; - - rc = kobject_init_and_add(&new->kobj, &cache_desc_type, parent, - "index%d", index); - if (rc) - goto err; - - /* type */ - new->type = info->type; - rc = sysfs_create_file(&new->kobj, &cache_type_attr.attr); - WARN_ON(rc); - - /* level */ - new->level = level; - rc = sysfs_create_file(&new->kobj, &cache_level_attr.attr); - WARN_ON(rc); - - /* size */ - cache_size = of_get_property(np, info->size_prop, NULL); - if (cache_size) { - new->size = *cache_size / 1024; - rc = sysfs_create_file(&new->kobj, - &cache_size_attr.attr); - WARN_ON(rc); - } - - /* coherency_line_size */ - cache_line_size = of_get_property(np, info->line_size_prop, NULL); - if (cache_line_size) { - new->line_size = *cache_line_size; - rc = sysfs_create_file(&new->kobj, - &cache_line_size_attr.attr); - WARN_ON(rc); - } - - /* number_of_sets */ - nr_sets = of_get_property(np, info->nr_sets_prop, NULL); - if (nr_sets) { - new->nr_sets = *nr_sets; - rc = sysfs_create_file(&new->kobj, - &cache_nr_sets_attr.attr); - WARN_ON(rc); - } - - /* ways_of_associativity */ - if (new->nr_sets == 1) { - /* fully associative */ - new->associativity = 0; - goto create_assoc; - } - - if (new->nr_sets && new->size && new->line_size) { - /* If we have values for all of these we can derive - * the associativity. */ - new->associativity = - ((new->size * 1024) / new->nr_sets) / new->line_size; -create_assoc: - rc = sysfs_create_file(&new->kobj, - &cache_assoc_attr.attr); - WARN_ON(rc); - } - - return new; -err: - kfree(new); - return NULL; -} - -static bool cache_is_unified(struct device_node *np) -{ - return of_get_property(np, "cache-unified", NULL); -} - -static struct cache_desc * __cpuinit create_cache_index_info(struct device_node *np, struct kobject *parent, int index, int level) -{ - struct device_node *next_cache; - struct cache_desc *new, **end; - - pr_debug("%s(node = %s, index = %d)\n", __func__, np->full_name, index); - - if (cache_is_unified(np)) { - new = create_cache_desc(np, parent, index, level, - &ucache_info); - } else { - new = create_cache_desc(np, parent, index, level, - &dcache_info); - if (new) { - index++; - new->next = create_cache_desc(np, parent, index, level, - &icache_info); - } - } - if (!new) - return NULL; - - end = &new->next; - while (*end) - end = &(*end)->next; - - next_cache = of_find_next_cache_node(np); - if (!next_cache) - goto out; - - *end = create_cache_index_info(next_cache, parent, ++index, ++level); - - of_node_put(next_cache); -out: - return new; -} - -static void __cpuinit create_cache_info(struct sys_device *sysdev) -{ - struct kobject *cache_toplevel; - struct device_node *np = NULL; - int cpu = sysdev->id; - - cache_toplevel = kobject_create_and_add("cache", &sysdev->kobj); - if (!cache_toplevel) - return; - per_cpu(cache_toplevel, cpu) = cache_toplevel; - np = of_get_cpu_node(cpu, NULL); - if (np != NULL) { - per_cpu(cache_desc, cpu) = - create_cache_index_info(np, cache_toplevel, 0, 1); - of_node_put(np); - } - return; -} - static void __cpuinit register_cpu_online(unsigned int cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); @@ -684,25 +407,10 @@ static void __cpuinit register_cpu_online(unsigned int cpu) sysdev_create_file(s, &attr_dscr); #endif /* CONFIG_PPC64 */ - create_cache_info(s); + cacheinfo_cpu_online(cpu); } #ifdef CONFIG_HOTPLUG_CPU -static void remove_cache_info(struct sys_device *sysdev) -{ - struct kobject *cache_toplevel; - struct cache_desc *cache_desc; - int cpu = sysdev->id; - - cache_desc = per_cpu(cache_desc, cpu); - if (cache_desc != NULL) - kobject_put(&cache_desc->kobj); - - cache_toplevel = per_cpu(cache_toplevel, cpu); - if (cache_toplevel != NULL) - kobject_put(cache_toplevel); -} - static void unregister_cpu_online(unsigned int cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); @@ -769,7 +477,7 @@ static void unregister_cpu_online(unsigned int cpu) sysdev_remove_file(s, &attr_dscr); #endif /* CONFIG_PPC64 */ - remove_cache_info(s); + cacheinfo_cpu_offline(cpu); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 201c7a5486cb..9920d6a7cf29 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -512,6 +512,13 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0); } +unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) +{ + unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start); + + return 1UL << mmu_psize_to_shift(psize); +} + /* * Called by asm hashtable.S for doing lazy icache flush */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 53b06ebb3f2f..f00f09a77f12 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -132,7 +132,7 @@ int arch_add_memory(int nid, u64 start, u64 size) /* this should work for most non-highmem platforms */ zone = pgdata->node_zones; - return __add_pages(zone, start_pfn, nr_pages); + return __add_pages(nid, zone, start_pfn, nr_pages); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 4314b39b6faf..ad123bced404 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -30,11 +30,11 @@ #if defined(CONFIG_40x) || defined(CONFIG_8xx) static inline void _tlbil_all(void) { - asm volatile ("sync; tlbia; isync" : : : "memory") + asm volatile ("sync; tlbia; isync" : : : "memory"); } static inline void _tlbil_pid(unsigned int pid) { - asm volatile ("sync; tlbia; isync" : : : "memory") + asm volatile ("sync; tlbia; isync" : : : "memory"); } #else /* CONFIG_40x || CONFIG_8xx */ extern void _tlbil_all(void); @@ -47,7 +47,7 @@ extern void _tlbil_pid(unsigned int pid); #ifdef CONFIG_8xx static inline void _tlbil_va(unsigned long address, unsigned int pid) { - asm volatile ("tlbie %0; sync" : : "r" (address) : "memory") + asm volatile ("tlbie %0; sync" : : "r" (address) : "memory"); } #else /* CONFIG_8xx */ extern void _tlbil_va(unsigned long address, unsigned int pid); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index cf81049e1e51..7393bd76d698 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -822,42 +822,50 @@ static void __init dump_numa_memory_topology(void) * required. nid is the preferred node and end is the physical address of * the highest address in the node. * - * Returns the physical address of the memory. + * Returns the virtual address of the memory. */ -static void __init *careful_allocation(int nid, unsigned long size, +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 = __lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT); + unsigned long ret_paddr; + + ret_paddr = __lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT); /* retry over all memory */ - if (!ret) - ret = __lmb_alloc_base(size, align, lmb_end_of_DRAM()); + if (!ret_paddr) + ret_paddr = __lmb_alloc_base(size, align, lmb_end_of_DRAM()); - if (!ret) - panic("numa.c: cannot allocate %lu bytes on node %d", + if (!ret_paddr) + panic("numa.c: cannot allocate %lu bytes for node %d", size, nid); + ret = __va(ret_paddr); + /* - * If the memory came from a previously allocated node, we must - * retry with the bootmem allocator. + * We initialize the nodes in numeric order: 0, 1, 2... + * and hand over control from the LMB 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 LMB allocator. + * + * So, check the nid from which this allocation came + * and double check to see if we need to use bootmem + * instead of the LMB. We don't free the LMB memory + * since it would be useless. */ - new_nid = early_pfn_to_nid(ret >> PAGE_SHIFT); + new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT); if (new_nid < nid) { - ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(new_nid), + ret = __alloc_bootmem_node(NODE_DATA(new_nid), size, align, 0); - if (!ret) - panic("numa.c: cannot allocate %lu bytes on node %d", - size, new_nid); - - ret = __pa(ret); - - dbg("alloc_bootmem %lx %lx\n", ret, size); + dbg("alloc_bootmem %p %lx\n", ret, size); } - return (void *)ret; + memset(ret, 0, size); + return ret; } static struct notifier_block __cpuinitdata ppc64_numa_nb = { @@ -952,7 +960,7 @@ void __init do_init_bootmem(void) for_each_online_node(nid) { unsigned long start_pfn, end_pfn; - unsigned long bootmem_paddr; + void *bootmem_vaddr; unsigned long bootmap_pages; get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); @@ -964,11 +972,9 @@ void __init do_init_bootmem(void) * previous nodes' bootmem to be initialized and have * all reserved areas marked. */ - NODE_DATA(nid) = careful_allocation(nid, + NODE_DATA(nid) = careful_zallocation(nid, sizeof(struct pglist_data), SMP_CACHE_BYTES, end_pfn); - NODE_DATA(nid) = __va(NODE_DATA(nid)); - memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); dbg("node %d\n", nid); dbg("NODE_DATA() = %p\n", NODE_DATA(nid)); @@ -984,20 +990,20 @@ void __init do_init_bootmem(void) dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT); bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); - bootmem_paddr = (unsigned long)careful_allocation(nid, + bootmem_vaddr = careful_zallocation(nid, bootmap_pages << PAGE_SHIFT, PAGE_SIZE, end_pfn); - memset(__va(bootmem_paddr), 0, bootmap_pages << PAGE_SHIFT); - dbg("bootmap_paddr = %lx\n", bootmem_paddr); + dbg("bootmap_vaddr = %p\n", bootmem_vaddr); - init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT, + 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_allocation() depend on this getting + * calls to careful_zallocation() depend on this getting * done correctly. */ mark_reserved_regions_for_nid(nid); diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 38ff35f2142a..22972cd83cc9 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -266,7 +266,8 @@ int map_page(unsigned long va, phys_addr_t pa, int flags) /* The PTE should never be already set nor present in the * hash table */ - BUG_ON(pte_val(*pg) & (_PAGE_PRESENT | _PAGE_HASHPTE)); + BUG_ON((pte_val(*pg) & (_PAGE_PRESENT | _PAGE_HASHPTE)) && + flags); set_pte_at(&init_mm, va, pg, pfn_pte(pa >> PAGE_SHIFT, __pgprot(flags))); } diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 803a64c02b06..39ac22b13c73 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -189,8 +189,9 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) smp_call_function(do_flush_tlb_mm_ipi, NULL, 1); _tlbil_pid(0); preempt_enable(); -#endif +#else _tlbil_pid(0); +#endif } EXPORT_SYMBOL(flush_tlb_kernel_range); diff --git a/arch/powerpc/oprofile/cell/pr_util.h b/arch/powerpc/oprofile/cell/pr_util.h index 628009c01958..964b93974d89 100644 --- a/arch/powerpc/oprofile/cell/pr_util.h +++ b/arch/powerpc/oprofile/cell/pr_util.h @@ -30,6 +30,10 @@ extern struct delayed_work spu_work; extern int spu_prof_running; +#define TRACE_ARRAY_SIZE 1024 + +extern spinlock_t oprof_spu_smpl_arry_lck; + struct spu_overlay_info { /* map of sections within an SPU overlay */ unsigned int vma; /* SPU virtual memory address from elf */ unsigned int size; /* size of section from elf */ @@ -79,7 +83,7 @@ struct spu_buffer { * the vma-to-fileoffset map. */ struct vma_to_fileoffset_map *create_vma_map(const struct spu *spu, - u64 objectid); + unsigned long objectid); unsigned int vma_map_lookup(struct vma_to_fileoffset_map *map, unsigned int vma, const struct spu *aSpu, int *grd_val); @@ -89,10 +93,11 @@ void vma_map_free(struct vma_to_fileoffset_map *map); * Entry point for SPU profiling. * cycles_reset is the SPU_CYCLES count value specified by the user. */ -int start_spu_profiling(unsigned int cycles_reset); - -void stop_spu_profiling(void); +int start_spu_profiling_cycles(unsigned int cycles_reset); +void start_spu_profiling_events(void); +void stop_spu_profiling_cycles(void); +void stop_spu_profiling_events(void); /* add the necessary profiling hooks */ int spu_sync_start(void); diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c index dd499c3e9da7..9305ddaac512 100644 --- a/arch/powerpc/oprofile/cell/spu_profiler.c +++ b/arch/powerpc/oprofile/cell/spu_profiler.c @@ -18,11 +18,21 @@ #include <asm/cell-pmu.h> #include "pr_util.h" -#define TRACE_ARRAY_SIZE 1024 #define SCALE_SHIFT 14 static u32 *samples; +/* spu_prof_running is a flag used to indicate if spu profiling is enabled + * or not. It is set by the routines start_spu_profiling_cycles() and + * start_spu_profiling_events(). The flag is cleared by the routines + * stop_spu_profiling_cycles() and stop_spu_profiling_events(). These + * routines are called via global_start() and global_stop() which are called in + * op_powerpc_start() and op_powerpc_stop(). These routines are called once + * per system as a result of the user starting/stopping oprofile. Hence, only + * one CPU per user at a time will be changing the value of spu_prof_running. + * In general, OProfile does not protect against multiple users trying to run + * OProfile at a time. + */ int spu_prof_running; static unsigned int profiling_interval; @@ -31,8 +41,8 @@ static unsigned int profiling_interval; #define SPU_PC_MASK 0xFFFF -static DEFINE_SPINLOCK(sample_array_lock); -unsigned long sample_array_lock_flags; +DEFINE_SPINLOCK(oprof_spu_smpl_arry_lck); +unsigned long oprof_spu_smpl_arry_lck_flags; void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_reset) { @@ -49,7 +59,7 @@ void set_spu_profiling_frequency(unsigned int freq_khz, unsigned int cycles_rese * of precision. This is close enough for the purpose at hand. * * The value of the timeout should be small enough that the hw - * trace buffer will not get more then about 1/3 full for the + * trace buffer will not get more than about 1/3 full for the * maximum user specified (the LFSR value) hw sampling frequency. * This is to ensure the trace buffer will never fill even if the * kernel thread scheduling varies under a heavy system load. @@ -145,13 +155,13 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer) * sample array must be loaded and then processed for a given * cpu. The sample array is not per cpu. */ - spin_lock_irqsave(&sample_array_lock, - sample_array_lock_flags); + spin_lock_irqsave(&oprof_spu_smpl_arry_lck, + oprof_spu_smpl_arry_lck_flags); num_samples = cell_spu_pc_collection(cpu); if (num_samples == 0) { - spin_unlock_irqrestore(&sample_array_lock, - sample_array_lock_flags); + spin_unlock_irqrestore(&oprof_spu_smpl_arry_lck, + oprof_spu_smpl_arry_lck_flags); continue; } @@ -162,8 +172,8 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer) num_samples); } - spin_unlock_irqrestore(&sample_array_lock, - sample_array_lock_flags); + spin_unlock_irqrestore(&oprof_spu_smpl_arry_lck, + oprof_spu_smpl_arry_lck_flags); } smp_wmb(); /* insure spu event buffer updates are written */ @@ -182,13 +192,13 @@ static enum hrtimer_restart profile_spus(struct hrtimer *timer) static struct hrtimer timer; /* - * Entry point for SPU profiling. + * Entry point for SPU cycle profiling. * NOTE: SPU profiling is done system-wide, not per-CPU. * * cycles_reset is the count value specified by the user when * setting up OProfile to count SPU_CYCLES. */ -int start_spu_profiling(unsigned int cycles_reset) +int start_spu_profiling_cycles(unsigned int cycles_reset) { ktime_t kt; @@ -212,10 +222,30 @@ int start_spu_profiling(unsigned int cycles_reset) return 0; } -void stop_spu_profiling(void) +/* + * Entry point for SPU event profiling. + * NOTE: SPU profiling is done system-wide, not per-CPU. + * + * cycles_reset is the count value specified by the user when + * setting up OProfile to count SPU_CYCLES. + */ +void start_spu_profiling_events(void) +{ + spu_prof_running = 1; + schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE); + + return; +} + +void stop_spu_profiling_cycles(void) { spu_prof_running = 0; hrtimer_cancel(&timer); kfree(samples); - pr_debug("SPU_PROF: stop_spu_profiling issued\n"); + pr_debug("SPU_PROF: stop_spu_profiling_cycles issued\n"); +} + +void stop_spu_profiling_events(void) +{ + spu_prof_running = 0; } diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c index 17807acb05d9..21f16edf6c8d 100644 --- a/arch/powerpc/oprofile/common.c +++ b/arch/powerpc/oprofile/common.c @@ -132,6 +132,28 @@ static int op_powerpc_create_files(struct super_block *sb, struct dentry *root) oprofilefs_create_ulong(sb, root, "mmcr0", &sys.mmcr0); oprofilefs_create_ulong(sb, root, "mmcr1", &sys.mmcr1); oprofilefs_create_ulong(sb, root, "mmcra", &sys.mmcra); +#ifdef CONFIG_OPROFILE_CELL + /* create a file the user tool can check to see what level of profiling + * support exits with this kernel. Initialize bit mask to indicate + * what support the kernel has: + * bit 0 - Supports SPU event profiling in addition to PPU + * event and cycles; and SPU cycle profiling + * bits 1-31 - Currently unused. + * + * If the file does not exist, then the kernel only supports SPU + * cycle profiling, PPU event and cycle profiling. + */ + oprofilefs_create_ulong(sb, root, "cell_support", &sys.cell_support); + sys.cell_support = 0x1; /* Note, the user OProfile tool must check + * that this bit is set before attempting to + * user SPU event profiling. Older kernels + * will not have this file, hence the user + * tool is not allowed to do SPU event + * profiling on older kernels. Older kernels + * will accept SPU events but collected data + * is garbage. + */ +#endif #endif for (i = 0; i < model->num_counters; ++i) { diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c index 25a4ec2514a3..ae06c6236d9c 100644 --- a/arch/powerpc/oprofile/op_model_cell.c +++ b/arch/powerpc/oprofile/op_model_cell.c @@ -40,14 +40,15 @@ #include "../platforms/cell/interrupt.h" #include "cell/pr_util.h" -static void cell_global_stop_spu(void); +#define PPU_PROFILING 0 +#define SPU_PROFILING_CYCLES 1 +#define SPU_PROFILING_EVENTS 2 -/* - * spu_cycle_reset is the number of cycles between samples. - * This variable is used for SPU profiling and should ONLY be set - * at the beginning of cell_reg_setup; otherwise, it's read-only. - */ -static unsigned int spu_cycle_reset; +#define SPU_EVENT_NUM_START 4100 +#define SPU_EVENT_NUM_STOP 4399 +#define SPU_PROFILE_EVENT_ADDR 4363 /* spu, address trace, decimal */ +#define SPU_PROFILE_EVENT_ADDR_MASK_A 0x146 /* sub unit set to zero */ +#define SPU_PROFILE_EVENT_ADDR_MASK_B 0x186 /* sub unit set to zero */ #define NUM_SPUS_PER_NODE 8 #define SPU_CYCLES_EVENT_NUM 2 /* event number for SPU_CYCLES */ @@ -66,6 +67,21 @@ static unsigned int spu_cycle_reset; #define MAX_SPU_COUNT 0xFFFFFF /* maximum 24 bit LFSR value */ +/* Minumum HW interval timer setting to send value to trace buffer is 10 cycle. + * To configure counter to send value every N cycles set counter to + * 2^32 - 1 - N. + */ +#define NUM_INTERVAL_CYC 0xFFFFFFFF - 10 + +/* + * spu_cycle_reset is the number of cycles between samples. + * This variable is used for SPU profiling and should ONLY be set + * at the beginning of cell_reg_setup; otherwise, it's read-only. + */ +static unsigned int spu_cycle_reset; +static unsigned int profiling_mode; +static int spu_evnt_phys_spu_indx; + struct pmc_cntrl_data { unsigned long vcntr; unsigned long evnts; @@ -105,6 +121,8 @@ struct pm_cntrl { u16 trace_mode; u16 freeze; u16 count_mode; + u16 spu_addr_trace; + u8 trace_buf_ovflw; }; static struct { @@ -122,7 +140,7 @@ static struct { #define GET_INPUT_CONTROL(x) ((x & 0x00000004) >> 2) static DEFINE_PER_CPU(unsigned long[NR_PHYS_CTRS], pmc_values); - +static unsigned long spu_pm_cnt[MAX_NUMNODES * NUM_SPUS_PER_NODE]; static struct pmc_cntrl_data pmc_cntrl[NUM_THREADS][NR_PHYS_CTRS]; /* @@ -152,6 +170,7 @@ static u32 hdw_thread; static u32 virt_cntr_inter_mask; static struct timer_list timer_virt_cntr; +static struct timer_list timer_spu_event_swap; /* * pm_signal needs to be global since it is initialized in @@ -165,7 +184,7 @@ static int spu_rtas_token; /* token for SPU cycle profiling */ static u32 reset_value[NR_PHYS_CTRS]; static int num_counters; static int oprofile_running; -static DEFINE_SPINLOCK(virt_cntr_lock); +static DEFINE_SPINLOCK(cntr_lock); static u32 ctr_enabled; @@ -336,13 +355,13 @@ static void set_pm_event(u32 ctr, int event, u32 unit_mask) for (i = 0; i < NUM_DEBUG_BUS_WORDS; i++) { if (bus_word & (1 << i)) { pm_regs.debug_bus_control |= - (bus_type << (30 - (2 * i))); + (bus_type << (30 - (2 * i))); for (j = 0; j < NUM_INPUT_BUS_WORDS; j++) { if (input_bus[j] == 0xff) { input_bus[j] = i; pm_regs.group_control |= - (i << (30 - (2 * j))); + (i << (30 - (2 * j))); break; } @@ -367,12 +386,16 @@ static void write_pm_cntrl(int cpu) if (pm_regs.pm_cntrl.stop_at_max == 1) val |= CBE_PM_STOP_AT_MAX; - if (pm_regs.pm_cntrl.trace_mode == 1) + if (pm_regs.pm_cntrl.trace_mode != 0) val |= CBE_PM_TRACE_MODE_SET(pm_regs.pm_cntrl.trace_mode); + if (pm_regs.pm_cntrl.trace_buf_ovflw == 1) + val |= CBE_PM_TRACE_BUF_OVFLW(pm_regs.pm_cntrl.trace_buf_ovflw); if (pm_regs.pm_cntrl.freeze == 1) val |= CBE_PM_FREEZE_ALL_CTRS; + val |= CBE_PM_SPU_ADDR_TRACE_SET(pm_regs.pm_cntrl.spu_addr_trace); + /* * Routine set_count_mode must be called previously to set * the count mode based on the user selection of user and kernel. @@ -441,7 +464,7 @@ static void cell_virtual_cntr(unsigned long data) * not both playing with the counters on the same node. */ - spin_lock_irqsave(&virt_cntr_lock, flags); + spin_lock_irqsave(&cntr_lock, flags); prev_hdw_thread = hdw_thread; @@ -480,7 +503,7 @@ static void cell_virtual_cntr(unsigned long data) cbe_disable_pm_interrupts(cpu); for (i = 0; i < num_counters; i++) { per_cpu(pmc_values, cpu + prev_hdw_thread)[i] - = cbe_read_ctr(cpu, i); + = cbe_read_ctr(cpu, i); if (per_cpu(pmc_values, cpu + next_hdw_thread)[i] == 0xFFFFFFFF) @@ -527,7 +550,7 @@ static void cell_virtual_cntr(unsigned long data) cbe_enable_pm(cpu); } - spin_unlock_irqrestore(&virt_cntr_lock, flags); + spin_unlock_irqrestore(&cntr_lock, flags); mod_timer(&timer_virt_cntr, jiffies + HZ / 10); } @@ -541,38 +564,146 @@ static void start_virt_cntrs(void) add_timer(&timer_virt_cntr); } -/* This function is called once for all cpus combined */ -static int cell_reg_setup(struct op_counter_config *ctr, +static int cell_reg_setup_spu_cycles(struct op_counter_config *ctr, struct op_system_config *sys, int num_ctrs) { - int i, j, cpu; - spu_cycle_reset = 0; + spu_cycle_reset = ctr[0].count; - if (ctr[0].event == SPU_CYCLES_EVENT_NUM) { - spu_cycle_reset = ctr[0].count; + /* + * Each node will need to make the rtas call to start + * and stop SPU profiling. Get the token once and store it. + */ + spu_rtas_token = rtas_token("ibm,cbe-spu-perftools"); + + if (unlikely(spu_rtas_token == RTAS_UNKNOWN_SERVICE)) { + printk(KERN_ERR + "%s: rtas token ibm,cbe-spu-perftools unknown\n", + __func__); + return -EIO; + } + return 0; +} + +/* Unfortunately, the hardware will only support event profiling + * on one SPU per node at a time. Therefore, we must time slice + * the profiling across all SPUs in the node. Note, we do this + * in parallel for each node. The following routine is called + * periodically based on kernel timer to switch which SPU is + * being monitored in a round robbin fashion. + */ +static void spu_evnt_swap(unsigned long data) +{ + int node; + int cur_phys_spu, nxt_phys_spu, cur_spu_evnt_phys_spu_indx; + unsigned long flags; + int cpu; + int ret; + u32 interrupt_mask; + + + /* enable interrupts on cntr 0 */ + interrupt_mask = CBE_PM_CTR_OVERFLOW_INTR(0); + + hdw_thread = 0; + + /* Make sure spu event interrupt handler and spu event swap + * don't access the counters simultaneously. + */ + spin_lock_irqsave(&cntr_lock, flags); + + cur_spu_evnt_phys_spu_indx = spu_evnt_phys_spu_indx; + + if (++(spu_evnt_phys_spu_indx) == NUM_SPUS_PER_NODE) + spu_evnt_phys_spu_indx = 0; + + pm_signal[0].sub_unit = spu_evnt_phys_spu_indx; + pm_signal[1].sub_unit = spu_evnt_phys_spu_indx; + pm_signal[2].sub_unit = spu_evnt_phys_spu_indx; + + /* switch the SPU being profiled on each node */ + for_each_online_cpu(cpu) { + if (cbe_get_hw_thread_id(cpu)) + continue; + + node = cbe_cpu_to_node(cpu); + cur_phys_spu = (node * NUM_SPUS_PER_NODE) + + cur_spu_evnt_phys_spu_indx; + nxt_phys_spu = (node * NUM_SPUS_PER_NODE) + + spu_evnt_phys_spu_indx; /* - * Each node will need to make the rtas call to start - * and stop SPU profiling. Get the token once and store it. + * stop counters, save counter values, restore counts + * for previous physical SPU */ - spu_rtas_token = rtas_token("ibm,cbe-spu-perftools"); + cbe_disable_pm(cpu); + cbe_disable_pm_interrupts(cpu); - if (unlikely(spu_rtas_token == RTAS_UNKNOWN_SERVICE)) { - printk(KERN_ERR - "%s: rtas token ibm,cbe-spu-perftools unknown\n", - __func__); - return -EIO; - } + spu_pm_cnt[cur_phys_spu] + = cbe_read_ctr(cpu, 0); + + /* restore previous count for the next spu to sample */ + /* NOTE, hardware issue, counter will not start if the + * counter value is at max (0xFFFFFFFF). + */ + if (spu_pm_cnt[nxt_phys_spu] >= 0xFFFFFFFF) + cbe_write_ctr(cpu, 0, 0xFFFFFFF0); + else + cbe_write_ctr(cpu, 0, spu_pm_cnt[nxt_phys_spu]); + + pm_rtas_reset_signals(cbe_cpu_to_node(cpu)); + + /* setup the debug bus measure the one event and + * the two events to route the next SPU's PC on + * the debug bus + */ + ret = pm_rtas_activate_signals(cbe_cpu_to_node(cpu), 3); + if (ret) + printk(KERN_ERR "%s: pm_rtas_activate_signals failed, " + "SPU event swap\n", __func__); + + /* clear the trace buffer, don't want to take PC for + * previous SPU*/ + cbe_write_pm(cpu, trace_address, 0); + + enable_ctr(cpu, 0, pm_regs.pm07_cntrl); + + /* Enable interrupts on the CPU thread that is starting */ + cbe_enable_pm_interrupts(cpu, hdw_thread, + interrupt_mask); + cbe_enable_pm(cpu); } - pm_rtas_token = rtas_token("ibm,cbe-perftools"); + spin_unlock_irqrestore(&cntr_lock, flags); + /* swap approximately every 0.1 seconds */ + mod_timer(&timer_spu_event_swap, jiffies + HZ / 25); +} + +static void start_spu_event_swap(void) +{ + init_timer(&timer_spu_event_swap); + timer_spu_event_swap.function = spu_evnt_swap; + timer_spu_event_swap.data = 0UL; + timer_spu_event_swap.expires = jiffies + HZ / 25; + add_timer(&timer_spu_event_swap); +} + +static int cell_reg_setup_spu_events(struct op_counter_config *ctr, + struct op_system_config *sys, int num_ctrs) +{ + int i; + + /* routine is called once for all nodes */ + + spu_evnt_phys_spu_indx = 0; /* - * For all events excetp PPU CYCLEs, each node will need to make + * For all events except PPU CYCLEs, each node will need to make * the rtas cbe-perftools call to setup and reset the debug bus. * Make the token lookup call once and store it in the global * variable pm_rtas_token. */ + pm_rtas_token = rtas_token("ibm,cbe-perftools"); + if (unlikely(pm_rtas_token == RTAS_UNKNOWN_SERVICE)) { printk(KERN_ERR "%s: rtas token ibm,cbe-perftools unknown\n", @@ -580,6 +711,58 @@ static int cell_reg_setup(struct op_counter_config *ctr, return -EIO; } + /* setup the pm_control register settings, + * settings will be written per node by the + * cell_cpu_setup() function. + */ + pm_regs.pm_cntrl.trace_buf_ovflw = 1; + + /* Use the occurrence trace mode to have SPU PC saved + * to the trace buffer. Occurrence data in trace buffer + * is not used. Bit 2 must be set to store SPU addresses. + */ + pm_regs.pm_cntrl.trace_mode = 2; + + pm_regs.pm_cntrl.spu_addr_trace = 0x1; /* using debug bus + event 2 & 3 */ + + /* setup the debug bus event array with the SPU PC routing events. + * Note, pm_signal[0] will be filled in by set_pm_event() call below. + */ + pm_signal[1].signal_group = SPU_PROFILE_EVENT_ADDR / 100; + pm_signal[1].bus_word = GET_BUS_WORD(SPU_PROFILE_EVENT_ADDR_MASK_A); + pm_signal[1].bit = SPU_PROFILE_EVENT_ADDR % 100; + pm_signal[1].sub_unit = spu_evnt_phys_spu_indx; + + pm_signal[2].signal_group = SPU_PROFILE_EVENT_ADDR / 100; + pm_signal[2].bus_word = GET_BUS_WORD(SPU_PROFILE_EVENT_ADDR_MASK_B); + pm_signal[2].bit = SPU_PROFILE_EVENT_ADDR % 100; + pm_signal[2].sub_unit = spu_evnt_phys_spu_indx; + + /* Set the user selected spu event to profile on, + * note, only one SPU profiling event is supported + */ + num_counters = 1; /* Only support one SPU event at a time */ + set_pm_event(0, ctr[0].event, ctr[0].unit_mask); + + reset_value[0] = 0xFFFFFFFF - ctr[0].count; + + /* global, used by cell_cpu_setup */ + ctr_enabled |= 1; + + /* Initialize the count for each SPU to the reset value */ + for (i=0; i < MAX_NUMNODES * NUM_SPUS_PER_NODE; i++) + spu_pm_cnt[i] = reset_value[0]; + + return 0; +} + +static int cell_reg_setup_ppu(struct op_counter_config *ctr, + struct op_system_config *sys, int num_ctrs) +{ + /* routine is called once for all nodes */ + int i, j, cpu; + num_counters = num_ctrs; if (unlikely(num_ctrs > NR_PHYS_CTRS)) { @@ -589,14 +772,6 @@ static int cell_reg_setup(struct op_counter_config *ctr, __func__); return -EIO; } - pm_regs.group_control = 0; - pm_regs.debug_bus_control = 0; - - /* setup the pm_control register */ - memset(&pm_regs.pm_cntrl, 0, sizeof(struct pm_cntrl)); - pm_regs.pm_cntrl.stop_at_max = 1; - pm_regs.pm_cntrl.trace_mode = 0; - pm_regs.pm_cntrl.freeze = 1; set_count_mode(sys->enable_kernel, sys->enable_user); @@ -665,6 +840,63 @@ static int cell_reg_setup(struct op_counter_config *ctr, } +/* This function is called once for all cpus combined */ +static int cell_reg_setup(struct op_counter_config *ctr, + struct op_system_config *sys, int num_ctrs) +{ + int ret=0; + spu_cycle_reset = 0; + + /* initialize the spu_arr_trace value, will be reset if + * doing spu event profiling. + */ + pm_regs.group_control = 0; + pm_regs.debug_bus_control = 0; + pm_regs.pm_cntrl.stop_at_max = 1; + pm_regs.pm_cntrl.trace_mode = 0; + pm_regs.pm_cntrl.freeze = 1; + pm_regs.pm_cntrl.trace_buf_ovflw = 0; + pm_regs.pm_cntrl.spu_addr_trace = 0; + + /* + * For all events except PPU CYCLEs, each node will need to make + * the rtas cbe-perftools call to setup and reset the debug bus. + * Make the token lookup call once and store it in the global + * variable pm_rtas_token. + */ + pm_rtas_token = rtas_token("ibm,cbe-perftools"); + + if (unlikely(pm_rtas_token == RTAS_UNKNOWN_SERVICE)) { + printk(KERN_ERR + "%s: rtas token ibm,cbe-perftools unknown\n", + __func__); + return -EIO; + } + + if (ctr[0].event == SPU_CYCLES_EVENT_NUM) { + profiling_mode = SPU_PROFILING_CYCLES; + ret = cell_reg_setup_spu_cycles(ctr, sys, num_ctrs); + } else if ((ctr[0].event >= SPU_EVENT_NUM_START) && + (ctr[0].event <= SPU_EVENT_NUM_STOP)) { + profiling_mode = SPU_PROFILING_EVENTS; + spu_cycle_reset = ctr[0].count; + + /* for SPU event profiling, need to setup the + * pm_signal array with the events to route the + * SPU PC before making the FW call. Note, only + * one SPU event for profiling can be specified + * at a time. + */ + cell_reg_setup_spu_events(ctr, sys, num_ctrs); + } else { + profiling_mode = PPU_PROFILING; + ret = cell_reg_setup_ppu(ctr, sys, num_ctrs); + } + + return ret; +} + + /* This function is called once for each cpu */ static int cell_cpu_setup(struct op_counter_config *cntr) @@ -672,8 +904,13 @@ static int cell_cpu_setup(struct op_counter_config *cntr) u32 cpu = smp_processor_id(); u32 num_enabled = 0; int i; + int ret; - if (spu_cycle_reset) + /* Cycle based SPU profiling does not use the performance + * counters. The trace array is configured to collect + * the data. + */ + if (profiling_mode == SPU_PROFILING_CYCLES) return 0; /* There is one performance monitor per processor chip (i.e. node), @@ -686,7 +923,6 @@ static int cell_cpu_setup(struct op_counter_config *cntr) cbe_disable_pm(cpu); cbe_disable_pm_interrupts(cpu); - cbe_write_pm(cpu, pm_interval, 0); cbe_write_pm(cpu, pm_start_stop, 0); cbe_write_pm(cpu, group_control, pm_regs.group_control); cbe_write_pm(cpu, debug_bus_control, pm_regs.debug_bus_control); @@ -703,7 +939,20 @@ static int cell_cpu_setup(struct op_counter_config *cntr) * The pm_rtas_activate_signals will return -EIO if the FW * call failed. */ - return pm_rtas_activate_signals(cbe_cpu_to_node(cpu), num_enabled); + if (profiling_mode == SPU_PROFILING_EVENTS) { + /* For SPU event profiling also need to setup the + * pm interval timer + */ + ret = pm_rtas_activate_signals(cbe_cpu_to_node(cpu), + num_enabled+2); + /* store PC from debug bus to Trace buffer as often + * as possible (every 10 cycles) + */ + cbe_write_pm(cpu, pm_interval, NUM_INTERVAL_CYC); + return ret; + } else + return pm_rtas_activate_signals(cbe_cpu_to_node(cpu), + num_enabled); } #define ENTRIES 303 @@ -885,7 +1134,122 @@ static struct notifier_block cpu_freq_notifier_block = { }; #endif -static int cell_global_start_spu(struct op_counter_config *ctr) +/* + * Note the generic OProfile stop calls do not support returning + * an error on stop. Hence, will not return an error if the FW + * calls fail on stop. Failure to reset the debug bus is not an issue. + * Failure to disable the SPU profiling is not an issue. The FW calls + * to enable the performance counters and debug bus will work even if + * the hardware was not cleanly reset. + */ +static void cell_global_stop_spu_cycles(void) +{ + int subfunc, rtn_value; + unsigned int lfsr_value; + int cpu; + + oprofile_running = 0; + smp_wmb(); + +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&cpu_freq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); +#endif + + for_each_online_cpu(cpu) { + if (cbe_get_hw_thread_id(cpu)) + continue; + + subfunc = 3; /* + * 2 - activate SPU tracing, + * 3 - deactivate + */ + lfsr_value = 0x8f100000; + + rtn_value = rtas_call(spu_rtas_token, 3, 1, NULL, + subfunc, cbe_cpu_to_node(cpu), + lfsr_value); + + if (unlikely(rtn_value != 0)) { + printk(KERN_ERR + "%s: rtas call ibm,cbe-spu-perftools " \ + "failed, return = %d\n", + __func__, rtn_value); + } + + /* Deactivate the signals */ + pm_rtas_reset_signals(cbe_cpu_to_node(cpu)); + } + + stop_spu_profiling_cycles(); +} + +static void cell_global_stop_spu_events(void) +{ + int cpu; + oprofile_running = 0; + + stop_spu_profiling_events(); + smp_wmb(); + + for_each_online_cpu(cpu) { + if (cbe_get_hw_thread_id(cpu)) + continue; + + cbe_sync_irq(cbe_cpu_to_node(cpu)); + /* Stop the counters */ + cbe_disable_pm(cpu); + cbe_write_pm07_control(cpu, 0, 0); + + /* Deactivate the signals */ + pm_rtas_reset_signals(cbe_cpu_to_node(cpu)); + + /* Deactivate interrupts */ + cbe_disable_pm_interrupts(cpu); + } + del_timer_sync(&timer_spu_event_swap); +} + +static void cell_global_stop_ppu(void) +{ + int cpu; + + /* + * This routine will be called once for the system. + * There is one performance monitor per node, so we + * only need to perform this function once per node. + */ + del_timer_sync(&timer_virt_cntr); + oprofile_running = 0; + smp_wmb(); + + for_each_online_cpu(cpu) { + if (cbe_get_hw_thread_id(cpu)) + continue; + + cbe_sync_irq(cbe_cpu_to_node(cpu)); + /* Stop the counters */ + cbe_disable_pm(cpu); + + /* Deactivate the signals */ + pm_rtas_reset_signals(cbe_cpu_to_node(cpu)); + + /* Deactivate interrupts */ + cbe_disable_pm_interrupts(cpu); + } +} + +static void cell_global_stop(void) +{ + if (profiling_mode == PPU_PROFILING) + cell_global_stop_ppu(); + else if (profiling_mode == SPU_PROFILING_EVENTS) + cell_global_stop_spu_events(); + else + cell_global_stop_spu_cycles(); +} + +static int cell_global_start_spu_cycles(struct op_counter_config *ctr) { int subfunc; unsigned int lfsr_value; @@ -951,18 +1315,18 @@ static int cell_global_start_spu(struct op_counter_config *ctr) /* start profiling */ ret = rtas_call(spu_rtas_token, 3, 1, NULL, subfunc, - cbe_cpu_to_node(cpu), lfsr_value); + cbe_cpu_to_node(cpu), lfsr_value); if (unlikely(ret != 0)) { printk(KERN_ERR - "%s: rtas call ibm,cbe-spu-perftools failed, return = %d\n", - __func__, ret); + "%s: rtas call ibm,cbe-spu-perftools failed, " \ + "return = %d\n", __func__, ret); rtas_error = -EIO; goto out; } } - rtas_error = start_spu_profiling(spu_cycle_reset); + rtas_error = start_spu_profiling_cycles(spu_cycle_reset); if (rtas_error) goto out_stop; @@ -970,11 +1334,74 @@ static int cell_global_start_spu(struct op_counter_config *ctr) return 0; out_stop: - cell_global_stop_spu(); /* clean up the PMU/debug bus */ + cell_global_stop_spu_cycles(); /* clean up the PMU/debug bus */ out: return rtas_error; } +static int cell_global_start_spu_events(struct op_counter_config *ctr) +{ + int cpu; + u32 interrupt_mask = 0; + int rtn = 0; + + hdw_thread = 0; + + /* spu event profiling, uses the performance counters to generate + * an interrupt. The hardware is setup to store the SPU program + * counter into the trace array. The occurrence mode is used to + * enable storing data to the trace buffer. The bits are set + * to send/store the SPU address in the trace buffer. The debug + * bus must be setup to route the SPU program counter onto the + * debug bus. The occurrence data in the trace buffer is not used. + */ + + /* This routine gets called once for the system. + * There is one performance monitor per node, so we + * only need to perform this function once per node. + */ + + for_each_online_cpu(cpu) { + if (cbe_get_hw_thread_id(cpu)) + continue; + + /* + * Setup SPU event-based profiling. + * Set perf_mon_control bit 0 to a zero before + * enabling spu collection hardware. + * + * Only support one SPU event on one SPU per node. + */ + if (ctr_enabled & 1) { + cbe_write_ctr(cpu, 0, reset_value[0]); + enable_ctr(cpu, 0, pm_regs.pm07_cntrl); + interrupt_mask |= + CBE_PM_CTR_OVERFLOW_INTR(0); + } else { + /* Disable counter */ + cbe_write_pm07_control(cpu, 0, 0); + } + + cbe_get_and_clear_pm_interrupts(cpu); + cbe_enable_pm_interrupts(cpu, hdw_thread, interrupt_mask); + cbe_enable_pm(cpu); + + /* clear the trace buffer */ + cbe_write_pm(cpu, trace_address, 0); + } + + /* Start the timer to time slice collecting the event profile + * on each of the SPUs. Note, can collect profile on one SPU + * per node at a time. + */ + start_spu_event_swap(); + start_spu_profiling_events(); + oprofile_running = 1; + smp_wmb(); + + return rtn; +} + static int cell_global_start_ppu(struct op_counter_config *ctr) { u32 cpu, i; @@ -994,8 +1421,7 @@ static int cell_global_start_ppu(struct op_counter_config *ctr) if (ctr_enabled & (1 << i)) { cbe_write_ctr(cpu, i, reset_value[i]); enable_ctr(cpu, i, pm_regs.pm07_cntrl); - interrupt_mask |= - CBE_PM_CTR_OVERFLOW_INTR(i); + interrupt_mask |= CBE_PM_CTR_OVERFLOW_INTR(i); } else { /* Disable counter */ cbe_write_pm07_control(cpu, i, 0); @@ -1024,99 +1450,162 @@ static int cell_global_start_ppu(struct op_counter_config *ctr) static int cell_global_start(struct op_counter_config *ctr) { - if (spu_cycle_reset) - return cell_global_start_spu(ctr); + if (profiling_mode == SPU_PROFILING_CYCLES) + return cell_global_start_spu_cycles(ctr); + else if (profiling_mode == SPU_PROFILING_EVENTS) + return cell_global_start_spu_events(ctr); else return cell_global_start_ppu(ctr); } -/* - * Note the generic OProfile stop calls do not support returning - * an error on stop. Hence, will not return an error if the FW - * calls fail on stop. Failure to reset the debug bus is not an issue. - * Failure to disable the SPU profiling is not an issue. The FW calls - * to enable the performance counters and debug bus will work even if - * the hardware was not cleanly reset. + +/* The SPU interrupt handler + * + * SPU event profiling works as follows: + * The pm_signal[0] holds the one SPU event to be measured. It is routed on + * the debug bus using word 0 or 1. The value of pm_signal[1] and + * pm_signal[2] contain the necessary events to route the SPU program + * counter for the selected SPU onto the debug bus using words 2 and 3. + * The pm_interval register is setup to write the SPU PC value into the + * trace buffer at the maximum rate possible. The trace buffer is configured + * to store the PCs, wrapping when it is full. The performance counter is + * intialized to the max hardware count minus the number of events, N, between + * samples. Once the N events have occured, a HW counter overflow occurs + * causing the generation of a HW counter interrupt which also stops the + * writing of the SPU PC values to the trace buffer. Hence the last PC + * written to the trace buffer is the SPU PC that we want. Unfortunately, + * we have to read from the beginning of the trace buffer to get to the + * last value written. We just hope the PPU has nothing better to do then + * service this interrupt. The PC for the specific SPU being profiled is + * extracted from the trace buffer processed and stored. The trace buffer + * is cleared, interrupts are cleared, the counter is reset to max - N. + * A kernel timer is used to periodically call the routine spu_evnt_swap() + * to switch to the next physical SPU in the node to profile in round robbin + * order. This way data is collected for all SPUs on the node. It does mean + * that we need to use a relatively small value of N to ensure enough samples + * on each SPU are collected each SPU is being profiled 1/8 of the time. + * It may also be necessary to use a longer sample collection period. */ -static void cell_global_stop_spu(void) +static void cell_handle_interrupt_spu(struct pt_regs *regs, + struct op_counter_config *ctr) { - int subfunc, rtn_value; - unsigned int lfsr_value; - int cpu; + u32 cpu, cpu_tmp; + u64 trace_entry; + u32 interrupt_mask; + u64 trace_buffer[2]; + u64 last_trace_buffer; + u32 sample; + u32 trace_addr; + unsigned long sample_array_lock_flags; + int spu_num; + unsigned long flags; - oprofile_running = 0; + /* Make sure spu event interrupt handler and spu event swap + * don't access the counters simultaneously. + */ + cpu = smp_processor_id(); + spin_lock_irqsave(&cntr_lock, flags); -#ifdef CONFIG_CPU_FREQ - cpufreq_unregister_notifier(&cpu_freq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); -#endif + cpu_tmp = cpu; + cbe_disable_pm(cpu); - for_each_online_cpu(cpu) { - if (cbe_get_hw_thread_id(cpu)) - continue; + interrupt_mask = cbe_get_and_clear_pm_interrupts(cpu); - subfunc = 3; /* - * 2 - activate SPU tracing, - * 3 - deactivate - */ - lfsr_value = 0x8f100000; + sample = 0xABCDEF; + trace_entry = 0xfedcba; + last_trace_buffer = 0xdeadbeaf; - rtn_value = rtas_call(spu_rtas_token, 3, 1, NULL, - subfunc, cbe_cpu_to_node(cpu), - lfsr_value); + if ((oprofile_running == 1) && (interrupt_mask != 0)) { + /* disable writes to trace buff */ + cbe_write_pm(cpu, pm_interval, 0); - if (unlikely(rtn_value != 0)) { - printk(KERN_ERR - "%s: rtas call ibm,cbe-spu-perftools failed, return = %d\n", - __func__, rtn_value); + /* only have one perf cntr being used, cntr 0 */ + if ((interrupt_mask & CBE_PM_CTR_OVERFLOW_INTR(0)) + && ctr[0].enabled) + /* The SPU PC values will be read + * from the trace buffer, reset counter + */ + + cbe_write_ctr(cpu, 0, reset_value[0]); + + trace_addr = cbe_read_pm(cpu, trace_address); + + while (!(trace_addr & CBE_PM_TRACE_BUF_EMPTY)) { + /* There is data in the trace buffer to process + * Read the buffer until you get to the last + * entry. This is the value we want. + */ + + cbe_read_trace_buffer(cpu, trace_buffer); + trace_addr = cbe_read_pm(cpu, trace_address); } - /* Deactivate the signals */ - pm_rtas_reset_signals(cbe_cpu_to_node(cpu)); - } + /* SPU Address 16 bit count format for 128 bit + * HW trace buffer is used for the SPU PC storage + * HDR bits 0:15 + * SPU Addr 0 bits 16:31 + * SPU Addr 1 bits 32:47 + * unused bits 48:127 + * + * HDR: bit4 = 1 SPU Address 0 valid + * HDR: bit5 = 1 SPU Address 1 valid + * - unfortunately, the valid bits don't seem to work + * + * Note trace_buffer[0] holds bits 0:63 of the HW + * trace buffer, trace_buffer[1] holds bits 64:127 + */ - stop_spu_profiling(); -} + trace_entry = trace_buffer[0] + & 0x00000000FFFF0000; -static void cell_global_stop_ppu(void) -{ - int cpu; + /* only top 16 of the 18 bit SPU PC address + * is stored in trace buffer, hence shift right + * by 16 -2 bits */ + sample = trace_entry >> 14; + last_trace_buffer = trace_buffer[0]; - /* - * This routine will be called once for the system. - * There is one performance monitor per node, so we - * only need to perform this function once per node. - */ - del_timer_sync(&timer_virt_cntr); - oprofile_running = 0; - smp_wmb(); + spu_num = spu_evnt_phys_spu_indx + + (cbe_cpu_to_node(cpu) * NUM_SPUS_PER_NODE); - for_each_online_cpu(cpu) { - if (cbe_get_hw_thread_id(cpu)) - continue; + /* make sure only one process at a time is calling + * spu_sync_buffer() + */ + spin_lock_irqsave(&oprof_spu_smpl_arry_lck, + sample_array_lock_flags); + spu_sync_buffer(spu_num, &sample, 1); + spin_unlock_irqrestore(&oprof_spu_smpl_arry_lck, + sample_array_lock_flags); - cbe_sync_irq(cbe_cpu_to_node(cpu)); - /* Stop the counters */ - cbe_disable_pm(cpu); + smp_wmb(); /* insure spu event buffer updates are written + * don't want events intermingled... */ - /* Deactivate the signals */ - pm_rtas_reset_signals(cbe_cpu_to_node(cpu)); + /* The counters were frozen by the interrupt. + * Reenable the interrupt and restart the counters. + */ + cbe_write_pm(cpu, pm_interval, NUM_INTERVAL_CYC); + cbe_enable_pm_interrupts(cpu, hdw_thread, + virt_cntr_inter_mask); - /* Deactivate interrupts */ - cbe_disable_pm_interrupts(cpu); - } -} + /* clear the trace buffer, re-enable writes to trace buff */ + cbe_write_pm(cpu, trace_address, 0); + cbe_write_pm(cpu, pm_interval, NUM_INTERVAL_CYC); -static void cell_global_stop(void) -{ - if (spu_cycle_reset) - cell_global_stop_spu(); - else - cell_global_stop_ppu(); + /* The writes to the various performance counters only writes + * to a latch. The new values (interrupt setting bits, reset + * counter value etc.) are not copied to the actual registers + * until the performance monitor is enabled. In order to get + * this to work as desired, the permormance monitor needs to + * be disabled while writing to the latches. This is a + * HW design issue. + */ + write_pm_cntrl(cpu); + cbe_enable_pm(cpu); + } + spin_unlock_irqrestore(&cntr_lock, flags); } -static void cell_handle_interrupt(struct pt_regs *regs, - struct op_counter_config *ctr) +static void cell_handle_interrupt_ppu(struct pt_regs *regs, + struct op_counter_config *ctr) { u32 cpu; u64 pc; @@ -1132,7 +1621,7 @@ static void cell_handle_interrupt(struct pt_regs *regs, * routine are not running at the same time. See the * cell_virtual_cntr() routine for additional comments. */ - spin_lock_irqsave(&virt_cntr_lock, flags); + spin_lock_irqsave(&cntr_lock, flags); /* * Need to disable and reenable the performance counters @@ -1185,7 +1674,16 @@ static void cell_handle_interrupt(struct pt_regs *regs, */ cbe_enable_pm(cpu); } - spin_unlock_irqrestore(&virt_cntr_lock, flags); + spin_unlock_irqrestore(&cntr_lock, flags); +} + +static void cell_handle_interrupt(struct pt_regs *regs, + struct op_counter_config *ctr) +{ + if (profiling_mode == PPU_PROFILING) + cell_handle_interrupt_ppu(regs, ctr); + else + cell_handle_interrupt_spu(regs, ctr); } /* @@ -1195,7 +1693,8 @@ static void cell_handle_interrupt(struct pt_regs *regs, */ static int cell_sync_start(void) { - if (spu_cycle_reset) + if ((profiling_mode == SPU_PROFILING_CYCLES) || + (profiling_mode == SPU_PROFILING_EVENTS)) return spu_sync_start(); else return DO_GENERIC_SYNC; @@ -1203,7 +1702,8 @@ static int cell_sync_start(void) static int cell_sync_stop(void) { - if (spu_cycle_reset) + if ((profiling_mode == SPU_PROFILING_CYCLES) || + (profiling_mode == SPU_PROFILING_EVENTS)) return spu_sync_stop(); else return 1; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c index ae7c34f37e1c..98367a0255f3 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_common.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c @@ -42,7 +42,7 @@ static struct of_device_id mpc52xx_bus_ids[] __initdata = { * from interrupt context while node mapping (which calls ioremap()) * cannot be used at such point. */ -static spinlock_t mpc52xx_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(mpc52xx_lock); static struct mpc52xx_gpt __iomem *mpc52xx_wdt; static struct mpc52xx_cdm __iomem *mpc52xx_cdm; diff --git a/arch/powerpc/platforms/83xx/mpc831x_rdb.c b/arch/powerpc/platforms/83xx/mpc831x_rdb.c index a428f8d1ac80..5177bdd2c62a 100644 --- a/arch/powerpc/platforms/83xx/mpc831x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc831x_rdb.c @@ -42,7 +42,7 @@ static void __init mpc831x_rdb_setup_arch(void) mpc831x_usb_cfg(); } -void __init mpc831x_rdb_init_IRQ(void) +static void __init mpc831x_rdb_init_IRQ(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/83xx/mpc832x_mds.c b/arch/powerpc/platforms/83xx/mpc832x_mds.c index ec43477caa63..ec0b401bc9cf 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc832x_mds.c @@ -49,8 +49,6 @@ #define DBG(fmt...) #endif -static u8 *bcsr_regs = NULL; - /* ************************************************************************ * * Setup the architecture @@ -59,13 +57,14 @@ static u8 *bcsr_regs = NULL; static void __init mpc832x_sys_setup_arch(void) { struct device_node *np; + u8 __iomem *bcsr_regs = NULL; if (ppc_md.progress) ppc_md.progress("mpc832x_sys_setup_arch()", 0); /* Map BCSR area */ np = of_find_node_by_name(NULL, "bcsr"); - if (np != 0) { + if (np) { struct resource res; of_address_to_resource(np, 0, &res); @@ -93,9 +92,9 @@ static void __init mpc832x_sys_setup_arch(void) != NULL){ /* Reset the Ethernet PHYs */ #define BCSR8_FETH_RST 0x50 - bcsr_regs[8] &= ~BCSR8_FETH_RST; + clrbits8(&bcsr_regs[8], BCSR8_FETH_RST); udelay(1000); - bcsr_regs[8] |= BCSR8_FETH_RST; + setbits8(&bcsr_regs[8], BCSR8_FETH_RST); iounmap(bcsr_regs); of_node_put(np); } diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index 0300268ce5b8..2a1295f19832 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -38,6 +38,7 @@ #define DBG(fmt...) #endif +#ifdef CONFIG_QUICC_ENGINE static void mpc83xx_spi_activate_cs(u8 cs, u8 polarity) { pr_debug("%s %d %d\n", __func__, cs, polarity); @@ -77,8 +78,8 @@ static int __init mpc832x_spi_init(void) mpc83xx_spi_activate_cs, mpc83xx_spi_deactivate_cs); } - machine_device_initcall(mpc832x_rdb, mpc832x_spi_init); +#endif /* CONFIG_QUICC_ENGINE */ /* ************************************************************************ * @@ -130,7 +131,7 @@ static int __init mpc832x_declare_of_platform_devices(void) } machine_device_initcall(mpc832x_rdb, mpc832x_declare_of_platform_devices); -void __init mpc832x_rdb_init_IRQ(void) +static void __init mpc832x_rdb_init_IRQ(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/83xx/mpc836x_mds.c b/arch/powerpc/platforms/83xx/mpc836x_mds.c index 9d46e5bdd101..09e9d6fb7411 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc836x_mds.c @@ -18,6 +18,7 @@ #include <linux/stddef.h> #include <linux/kernel.h> +#include <linux/compiler.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/reboot.h> @@ -43,6 +44,7 @@ #include <asm/udbg.h> #include <sysdev/fsl_soc.h> #include <sysdev/fsl_pci.h> +#include <sysdev/simple_gpio.h> #include <asm/qe.h> #include <asm/qe_ic.h> @@ -55,8 +57,6 @@ #define DBG(fmt...) #endif -static u8 *bcsr_regs = NULL; - /* ************************************************************************ * * Setup the architecture @@ -65,13 +65,14 @@ static u8 *bcsr_regs = NULL; static void __init mpc836x_mds_setup_arch(void) { struct device_node *np; + u8 __iomem *bcsr_regs = NULL; if (ppc_md.progress) ppc_md.progress("mpc836x_mds_setup_arch()", 0); /* Map BCSR area */ np = of_find_node_by_name(NULL, "bcsr"); - if (np != 0) { + if (np) { struct resource res; of_address_to_resource(np, 0, &res); @@ -93,6 +94,16 @@ static void __init mpc836x_mds_setup_arch(void) for (np = NULL; (np = of_find_node_by_name(np, "ucc")) != NULL;) par_io_of_config(np); +#ifdef CONFIG_QE_USB + /* Must fixup Par IO before QE GPIO chips are registered. */ + par_io_config_pin(1, 2, 1, 0, 3, 0); /* USBOE */ + par_io_config_pin(1, 3, 1, 0, 3, 0); /* USBTP */ + par_io_config_pin(1, 8, 1, 0, 1, 0); /* USBTN */ + par_io_config_pin(1, 10, 2, 0, 3, 0); /* USBRXD */ + par_io_config_pin(1, 9, 2, 1, 3, 0); /* USBRP */ + par_io_config_pin(1, 11, 2, 1, 3, 0); /* USBRN */ + par_io_config_pin(2, 20, 2, 0, 1, 0); /* CLK21 */ +#endif /* CONFIG_QE_USB */ } if ((np = of_find_compatible_node(NULL, "network", "ucc_geth")) @@ -151,6 +162,70 @@ static int __init mpc836x_declare_of_platform_devices(void) } machine_device_initcall(mpc836x_mds, mpc836x_declare_of_platform_devices); +#ifdef CONFIG_QE_USB +static int __init mpc836x_usb_cfg(void) +{ + u8 __iomem *bcsr; + struct device_node *np; + const char *mode; + int ret = 0; + + np = of_find_compatible_node(NULL, NULL, "fsl,mpc8360mds-bcsr"); + if (!np) + return -ENODEV; + + bcsr = of_iomap(np, 0); + of_node_put(np); + if (!bcsr) + return -ENOMEM; + + np = of_find_compatible_node(NULL, NULL, "fsl,mpc8323-qe-usb"); + if (!np) { + ret = -ENODEV; + goto err; + } + +#define BCSR8_TSEC1M_MASK (0x3 << 6) +#define BCSR8_TSEC1M_RGMII (0x0 << 6) +#define BCSR8_TSEC2M_MASK (0x3 << 4) +#define BCSR8_TSEC2M_RGMII (0x0 << 4) + /* + * Default is GMII (2), but we should set it to RGMII (0) if we use + * USB (Eth PHY is in RGMII mode anyway). + */ + clrsetbits_8(&bcsr[8], BCSR8_TSEC1M_MASK | BCSR8_TSEC2M_MASK, + BCSR8_TSEC1M_RGMII | BCSR8_TSEC2M_RGMII); + +#define BCSR13_USBMASK 0x0f +#define BCSR13_nUSBEN 0x08 /* 1 - Disable, 0 - Enable */ +#define BCSR13_USBSPEED 0x04 /* 1 - Full, 0 - Low */ +#define BCSR13_USBMODE 0x02 /* 1 - Host, 0 - Function */ +#define BCSR13_nUSBVCC 0x01 /* 1 - gets VBUS, 0 - supplies VBUS */ + + clrsetbits_8(&bcsr[13], BCSR13_USBMASK, BCSR13_USBSPEED); + + mode = of_get_property(np, "mode", NULL); + if (mode && !strcmp(mode, "peripheral")) { + setbits8(&bcsr[13], BCSR13_nUSBVCC); + qe_usb_clock_set(QE_CLK21, 48000000); + } else { + setbits8(&bcsr[13], BCSR13_USBMODE); + /* + * The BCSR GPIOs are used to control power and + * speed of the USB transceiver. This is needed for + * the USB Host only. + */ + simple_gpiochip_init("fsl,mpc8360mds-bcsr-gpio"); + } + + of_node_put(np); +err: + iounmap(bcsr); + return ret; +} +machine_arch_initcall(mpc836x_mds, mpc836x_usb_cfg); +#endif /* CONFIG_QE_USB */ + static void __init mpc836x_mds_init_IRQ(void) { struct device_node *np; diff --git a/arch/powerpc/platforms/83xx/mpc836x_rdk.c b/arch/powerpc/platforms/83xx/mpc836x_rdk.c index a5273bb28e1b..b0090aac9642 100644 --- a/arch/powerpc/platforms/83xx/mpc836x_rdk.c +++ b/arch/powerpc/platforms/83xx/mpc836x_rdk.c @@ -51,8 +51,9 @@ static void __init mpc836x_rdk_setup_arch(void) for_each_compatible_node(np, "pci", "fsl,mpc8349-pci") mpc83xx_add_bridge(np); #endif - +#ifdef CONFIG_QUICC_ENGINE qe_reset(); +#endif } static void __init mpc836x_rdk_init_IRQ(void) @@ -71,13 +72,14 @@ static void __init mpc836x_rdk_init_IRQ(void) */ ipic_set_default_priority(); of_node_put(np); - +#ifdef CONFIG_QUICC_ENGINE np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic"); if (!np) return; qe_ic_init(np, 0, qe_ic_cascade_low_ipic, qe_ic_cascade_high_ipic); of_node_put(np); +#endif } /* diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c index 8bb13c807142..530ef990ca7c 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_mds.c +++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c @@ -26,7 +26,6 @@ #define BCSR12_USB_SER_MASK 0x8a #define BCSR12_USB_SER_PIN 0x80 #define BCSR12_USB_SER_DEVICE 0x02 -extern int mpc837x_usb_cfg(void); static int mpc837xmds_usb_cfg(void) { diff --git a/arch/powerpc/platforms/83xx/mpc837x_rdb.c b/arch/powerpc/platforms/83xx/mpc837x_rdb.c index da030afa2e2c..1d096545322b 100644 --- a/arch/powerpc/platforms/83xx/mpc837x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc837x_rdb.c @@ -21,8 +21,6 @@ #include "mpc83xx.h" -extern int mpc837x_usb_cfg(void); - /* ************************************************************************ * * Setup the architecture diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h index 2a7cbabb410a..83cfe51526ec 100644 --- a/arch/powerpc/platforms/83xx/mpc83xx.h +++ b/arch/powerpc/platforms/83xx/mpc83xx.h @@ -61,6 +61,7 @@ extern void mpc83xx_restart(char *cmd); extern long mpc83xx_time_init(void); +extern int mpc837x_usb_cfg(void); extern int mpc834x_usb_cfg(void); extern int mpc831x_usb_cfg(void); diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c index a8301c8ad537..7326d904202c 100644 --- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c +++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c @@ -148,6 +148,9 @@ static int mpc85xx_exclude_device(struct pci_controller *hose, /* * Setup the architecture */ +#ifdef CONFIG_SMP +extern void __init mpc85xx_smp_init(void); +#endif static void __init mpc85xx_ds_setup_arch(void) { #ifdef CONFIG_PCI @@ -173,6 +176,10 @@ static void __init mpc85xx_ds_setup_arch(void) ppc_md.pci_exclude_device = mpc85xx_exclude_device; #endif +#ifdef CONFIG_SMP + mpc85xx_smp_init(); +#endif + printk("MPC85xx DS board from Freescale Semiconductor\n"); } diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index d652c713f496..79a0df17078b 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -58,6 +58,7 @@ smp_85xx_kick_cpu(int nr) if (cpu_rel_addr == NULL) { printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr); + local_irq_restore(flags); return; } diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 47e956c871fe..47fe2bea9865 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -312,4 +312,15 @@ config MPC8xxx_GPIO Say Y here if you're going to use hardware that connects to the MPC831x/834x/837x/8572/8610 GPIOs. +config SIMPLE_GPIO + bool "Support for simple, memory-mapped GPIO controllers" + depends on PPC + select GENERIC_GPIO + select ARCH_REQUIRE_GPIOLIB + help + Say Y here to support simple, memory-mapped GPIO controllers. + These are usually BCSRs used to control board's switches, LEDs, + chip-selects, Ethernet/USB PHY's power and various other small + on-board peripherals. + endmenu diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 3d0c776f888d..e868b5c50723 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -231,7 +231,7 @@ config VIRT_CPU_ACCOUNTING If in doubt, say Y here. config SMP - depends on PPC_STD_MMU + depends on PPC_STD_MMU || FSL_BOOKE bool "Symmetric multi-processing support" ---help--- This enables support for systems with more than one CPU. If you have diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c index 2e67bd840e01..35b1ec492715 100644 --- a/arch/powerpc/platforms/cell/beat_htab.c +++ b/arch/powerpc/platforms/cell/beat_htab.c @@ -44,8 +44,8 @@ static DEFINE_SPINLOCK(beat_htab_lock); static inline unsigned int beat_read_mask(unsigned hpte_group) { - unsigned long hpte_v[5]; unsigned long rmask = 0; + u64 hpte_v[5]; beat_read_htab_entries(0, hpte_group + 0, hpte_v); if (!(hpte_v[0] & HPTE_V_BOLTED)) @@ -93,8 +93,7 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group, int psize, int ssize) { unsigned long lpar_rc; - unsigned long slot; - unsigned long hpte_v, hpte_r; + u64 hpte_v, hpte_r, slot; /* same as iseries */ if (vflags & HPTE_V_SECONDARY) @@ -153,8 +152,9 @@ static long beat_lpar_hpte_remove(unsigned long hpte_group) static unsigned long beat_lpar_hpte_getword0(unsigned long slot) { - unsigned long dword0, dword[5]; + unsigned long dword0; unsigned long lpar_rc; + u64 dword[5]; lpar_rc = beat_read_htab_entries(0, slot & ~3UL, dword); @@ -170,7 +170,7 @@ static void beat_lpar_hptab_clear(void) unsigned long size_bytes = 1UL << ppc64_pft_size; unsigned long hpte_count = size_bytes >> 4; int i; - unsigned long dummy0, dummy1; + u64 dummy0, dummy1; /* TODO: Use bulk call */ for (i = 0; i < hpte_count; i++) @@ -189,7 +189,8 @@ static long beat_lpar_hpte_updatepp(unsigned long slot, int psize, int ssize, int local) { unsigned long lpar_rc; - unsigned long dummy0, dummy1, want_v; + u64 dummy0, dummy1; + unsigned long want_v; want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); @@ -255,7 +256,8 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, int psize, int ssize) { - unsigned long lpar_rc, slot, vsid, va, dummy0, dummy1; + unsigned long lpar_rc, slot, vsid, va; + u64 dummy0, dummy1; vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M); va = (vsid << 28) | (ea & 0x0fffffff); @@ -276,7 +278,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long va, { unsigned long want_v; unsigned long lpar_rc; - unsigned long dummy1, dummy2; + u64 dummy1, dummy2; unsigned long flags; DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n", @@ -315,8 +317,7 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group, int psize, int ssize) { unsigned long lpar_rc; - unsigned long slot; - unsigned long hpte_v, hpte_r; + u64 hpte_v, hpte_r, slot; /* same as iseries */ if (vflags & HPTE_V_SECONDARY) diff --git a/arch/powerpc/platforms/cell/beat_udbg.c b/arch/powerpc/platforms/cell/beat_udbg.c index 6b418f6b6175..350735bc8888 100644 --- a/arch/powerpc/platforms/cell/beat_udbg.c +++ b/arch/powerpc/platforms/cell/beat_udbg.c @@ -40,8 +40,8 @@ static void udbg_putc_beat(char c) } /* Buffered chars getc */ -static long inbuflen; -static long inbuf[2]; /* must be 2 longs */ +static u64 inbuflen; +static u64 inbuf[2]; /* must be 2 u64s */ static int udbg_getc_poll_beat(void) { diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c index 70fa7aef5edd..20472e487b6f 100644 --- a/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c +++ b/arch/powerpc/platforms/cell/cbe_cpufreq_pervasive.c @@ -54,7 +54,7 @@ int cbe_cpufreq_set_pmode(int cpu, unsigned int pmode) { struct cbe_pmd_regs __iomem *pmd_regs; struct cbe_mic_tm_regs __iomem *mic_tm_regs; - u64 flags; + unsigned long flags; u64 value; #ifdef DEBUG long time; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 2d5bb22d6c09..28c04dab2633 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -148,7 +148,7 @@ static unsigned int iic_get_irq(void) iic = &__get_cpu_var(iic); *(unsigned long *) &pending = - in_be64((unsigned long __iomem *) &iic->regs->pending_destr); + in_be64((u64 __iomem *) &iic->regs->pending_destr); if (!(pending.flags & CBE_IIC_IRQ_VALID)) return NO_IRQ; virq = irq_linear_revmap(iic_host, iic_pending_to_hwnum(pending)); diff --git a/arch/powerpc/platforms/cell/io-workarounds.c b/arch/powerpc/platforms/cell/io-workarounds.c index b5f84e8f0899..059cad6c3f69 100644 --- a/arch/powerpc/platforms/cell/io-workarounds.c +++ b/arch/powerpc/platforms/cell/io-workarounds.c @@ -130,14 +130,14 @@ static const struct ppc_pci_io __devinitconst iowa_pci_io = { }; -static void __iomem *iowa_ioremap(unsigned long addr, unsigned long size, +static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size, unsigned long flags) { struct iowa_bus *bus; void __iomem *res = __ioremap(addr, size, flags); int busno; - bus = iowa_pci_find(0, addr); + bus = iowa_pci_find(0, (unsigned long)addr); if (bus != NULL) { busno = bus - iowa_busses; PCI_SET_ADDR_TOKEN(res, busno + 1); diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 86db4dd170a0..88d94b59a7cb 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -150,8 +150,8 @@ static int cbe_nr_iommus; static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte, long n_ptes) { - unsigned long __iomem *reg; - unsigned long val; + u64 __iomem *reg; + u64 val; long n; reg = iommu->xlate_regs + IOC_IOPT_CacheInvd; diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 6296bfd9cb0b..e309ef70a531 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -97,7 +97,6 @@ spufs_new_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; out: return inode; diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h index 15c62d3ca129..3bf908e2873a 100644 --- a/arch/powerpc/platforms/cell/spufs/spufs.h +++ b/arch/powerpc/platforms/cell/spufs/spufs.h @@ -314,7 +314,7 @@ extern char *isolated_loader; * we need to call spu_release(ctx) before sleeping, and * then spu_acquire(ctx) when awoken. * - * Returns with state_mutex re-acquired when successfull or + * Returns with state_mutex re-acquired when successful or * with -ERESTARTSYS and the state_mutex dropped when interrupted. */ diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig index ed3753d8c109..7ddd0a2c8027 100644 --- a/arch/powerpc/platforms/iseries/Kconfig +++ b/arch/powerpc/platforms/iseries/Kconfig @@ -10,18 +10,21 @@ menu "iSeries device drivers" config VIODASD tristate "iSeries Virtual I/O disk support" depends on BLOCK + select VIOPATH help If you are running on an iSeries system and you want to use virtual disks created and managed by OS/400, say Y. config VIOCD tristate "iSeries Virtual I/O CD support" + select VIOPATH help If you are running Linux on an IBM iSeries system and you want to read a CD drive owned by OS/400, say Y here. config VIOTAPE tristate "iSeries Virtual Tape Support" + select VIOPATH help If you are running Linux on an iSeries system and you want Linux to read and/or write a tape drive owned by OS/400, say Y here. @@ -30,5 +33,3 @@ endmenu config VIOPATH bool - depends on VIODASD || VIOCD || VIOTAPE || ISERIES_VETH - default y diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index 70b688c1aefb..24519b96d6ad 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -23,6 +23,7 @@ #include <linux/string.h> #include <linux/seq_file.h> #include <linux/kdev_t.h> +#include <linux/kexec.h> #include <linux/major.h> #include <linux/root_dev.h> #include <linux/kernel.h> @@ -638,6 +639,13 @@ static int __init iseries_probe(void) return 1; } +#ifdef CONFIG_KEXEC +static int iseries_kexec_prepare(struct kimage *image) +{ + return -ENOSYS; +} +#endif + define_machine(iseries) { .name = "iSeries", .setup_arch = iSeries_setup_arch, @@ -658,6 +666,9 @@ define_machine(iseries) { .probe = iseries_probe, .ioremap = iseries_ioremap, .iounmap = iseries_iounmap, +#ifdef CONFIG_KEXEC + .machine_kexec_prepare = iseries_kexec_prepare, +#endif /* XXX Implement enable_pmcs for iSeries */ }; diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c index 58556b028a4c..86db47c1b665 100644 --- a/arch/powerpc/platforms/pasemi/cpufreq.c +++ b/arch/powerpc/platforms/pasemi/cpufreq.c @@ -112,7 +112,7 @@ static int get_gizmo_latency(void) static void set_astate(int cpu, unsigned int astate) { - u64 flags; + unsigned long flags; /* Return if called before init has run */ if (unlikely(!sdcasr_mapbase)) diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c index 217af321b0ca..a6152d922243 100644 --- a/arch/powerpc/platforms/pasemi/dma_lib.c +++ b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -509,7 +509,7 @@ fallback: */ int pasemi_dma_init(void) { - static spinlock_t init_lock = SPIN_LOCK_UNLOCKED; + static DEFINE_SPINLOCK(init_lock); struct pci_dev *iob_pdev; struct pci_dev *pdev; struct resource res; diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 54b7b76ed4f0..04cdd32624d4 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -661,6 +661,7 @@ static void __init init_second_ohare(void) pci_find_hose_for_OF_device(np); if (!hose) { printk(KERN_ERR "Can't find PCI hose for OHare2 !\n"); + of_node_put(np); return; } early_read_config_word(hose, bus, devfn, PCI_COMMAND, &cmd); @@ -669,6 +670,7 @@ static void __init init_second_ohare(void) early_write_config_word(hose, bus, devfn, PCI_COMMAND, cmd); } has_second_ohare = 1; + of_node_put(np); } /* diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c index 59eb840d8ce2..1810e4226e56 100644 --- a/arch/powerpc/platforms/powermac/time.c +++ b/arch/powerpc/platforms/powermac/time.c @@ -265,12 +265,15 @@ int __init via_calibrate_decr(void) struct resource rsrc; vias = of_find_node_by_name(NULL, "via-cuda"); - if (vias == 0) + if (vias == NULL) vias = of_find_node_by_name(NULL, "via-pmu"); - if (vias == 0) + if (vias == NULL) vias = of_find_node_by_name(NULL, "via"); - if (vias == 0 || of_address_to_resource(vias, 0, &rsrc)) + if (vias == NULL || of_address_to_resource(vias, 0, &rsrc)) { + of_node_put(vias); return 0; + } + of_node_put(vias); via = ioremap(rsrc.start, rsrc.end - rsrc.start + 1); if (via == NULL) { printk(KERN_ERR "Failed to map VIA for timer calibration !\n"); @@ -297,7 +300,7 @@ int __init via_calibrate_decr(void) ppc_tb_freq = (dstart - dend) * 100 / 6; iounmap(via); - + return 1; } #endif diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index dbc124e05646..ca71a12b764c 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -518,6 +518,41 @@ fail_device_register: return result; } +static int __init ps3_register_ramdisk_device(void) +{ + int result; + struct layout { + struct ps3_system_bus_device dev; + } *p; + + pr_debug(" -> %s:%d\n", __func__, __LINE__); + + p = kzalloc(sizeof(struct layout), GFP_KERNEL); + + if (!p) + return -ENOMEM; + + p->dev.match_id = PS3_MATCH_ID_GPU; + p->dev.match_sub_id = PS3_MATCH_SUB_ID_GPU_RAMDISK; + p->dev.dev_type = PS3_DEVICE_TYPE_IOC0; + + result = ps3_system_bus_device_register(&p->dev); + + if (result) { + pr_debug("%s:%d ps3_system_bus_device_register failed\n", + __func__, __LINE__); + goto fail_device_register; + } + + pr_debug(" <- %s:%d\n", __func__, __LINE__); + return 0; + +fail_device_register: + kfree(p); + pr_debug(" <- %s:%d failed\n", __func__, __LINE__); + return result; +} + /** * ps3_setup_dynamic_device - Setup a dynamic device from the repository */ @@ -946,6 +981,8 @@ static int __init ps3_register_devices(void) ps3_register_lpm_devices(); + ps3_register_ramdisk_device(); + pr_debug(" <- %s:%d\n", __func__, __LINE__); return 0; } diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 5afce115ab1f..b33b28a6fe12 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_FSL_PCI) += fsl_pci.o $(fsl-msi-obj-y) obj-$(CONFIG_FSL_LBC) += fsl_lbc.o obj-$(CONFIG_FSL_GTM) += fsl_gtm.o obj-$(CONFIG_MPC8xxx_GPIO) += mpc8xxx_gpio.o +obj-$(CONFIG_SIMPLE_GPIO) += simple_gpio.o obj-$(CONFIG_RAPIDIO) += fsl_rio.o obj-$(CONFIG_TSI108_BRIDGE) += tsi108_pci.o tsi108_dev.o obj-$(CONFIG_QUICC_ENGINE) += qe_lib/ diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index d5f9ae0f1b75..f611d0369cc8 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -29,7 +29,8 @@ #if defined(CONFIG_PPC_85xx) || defined(CONFIG_PPC_86xx) /* atmu setup for fsl pci/pcie controller */ -void __init setup_pci_atmu(struct pci_controller *hose, struct resource *rsrc) +static void __init setup_pci_atmu(struct pci_controller *hose, + struct resource *rsrc) { struct ccsr_pci __iomem *pci; int i; @@ -86,7 +87,7 @@ void __init setup_pci_atmu(struct pci_controller *hose, struct resource *rsrc) out_be32(&pci->piw[2].piwar, PIWAR_2G); } -void __init setup_pci_cmd(struct pci_controller *hose) +static void __init setup_pci_cmd(struct pci_controller *hose) { u16 cmd; int cap_x; @@ -130,7 +131,7 @@ static void __init quirk_fsl_pcie_header(struct pci_dev *dev) return ; } -int __init fsl_pcie_check_link(struct pci_controller *hose) +static int __init fsl_pcie_check_link(struct pci_controller *hose) { u32 val; early_read_config_dword(hose, 0, 0, PCIE_LTSSM, &val); diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h index 60f7f227327c..9c744e4285a0 100644 --- a/arch/powerpc/sysdev/fsl_soc.h +++ b/arch/powerpc/sysdev/fsl_soc.h @@ -5,8 +5,13 @@ #include <asm/mmu.h> extern phys_addr_t get_immrbase(void); +#if defined(CONFIG_CPM2) || defined(CONFIG_QUICC_ENGINE) || defined(CONFIG_8xx) extern u32 get_brgfreq(void); extern u32 get_baudrate(void); +#else +static inline u32 get_brgfreq(void) { return -1; } +static inline u32 get_baudrate(void) { return -1; } +#endif extern u32 fsl_get_sys_freq(void); struct spi_board_info; diff --git a/arch/powerpc/sysdev/qe_lib/Kconfig b/arch/powerpc/sysdev/qe_lib/Kconfig index 76ffbc48d4b9..41ac3dfac98e 100644 --- a/arch/powerpc/sysdev/qe_lib/Kconfig +++ b/arch/powerpc/sysdev/qe_lib/Kconfig @@ -22,5 +22,6 @@ config UCC config QE_USB bool + default y if USB_GADGET_FSL_QE help - QE USB Host Controller support + QE USB Controller support diff --git a/arch/powerpc/sysdev/qe_lib/gpio.c b/arch/powerpc/sysdev/qe_lib/gpio.c index 8e5a0bc36d0b..3485288dce31 100644 --- a/arch/powerpc/sysdev/qe_lib/gpio.c +++ b/arch/powerpc/sysdev/qe_lib/gpio.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/spinlock.h> +#include <linux/err.h> #include <linux/io.h> #include <linux/of.h> #include <linux/of_gpio.h> @@ -24,8 +25,14 @@ struct qe_gpio_chip { struct of_mm_gpio_chip mm_gc; spinlock_t lock; + unsigned long pin_flags[QE_PIO_PINS]; +#define QE_PIN_REQUESTED 0 + /* shadowed data register to clear/set bits safely */ u32 cpdata; + + /* saved_regs used to restore dedicated functions */ + struct qe_pio_regs saved_regs; }; static inline struct qe_gpio_chip * @@ -40,6 +47,12 @@ static void qe_gpio_save_regs(struct of_mm_gpio_chip *mm_gc) struct qe_pio_regs __iomem *regs = mm_gc->regs; qe_gc->cpdata = in_be32(®s->cpdata); + qe_gc->saved_regs.cpdata = qe_gc->cpdata; + qe_gc->saved_regs.cpdir1 = in_be32(®s->cpdir1); + qe_gc->saved_regs.cpdir2 = in_be32(®s->cpdir2); + qe_gc->saved_regs.cppar1 = in_be32(®s->cppar1); + qe_gc->saved_regs.cppar2 = in_be32(®s->cppar2); + qe_gc->saved_regs.cpodr = in_be32(®s->cpodr); } static int qe_gpio_get(struct gpio_chip *gc, unsigned int gpio) @@ -103,6 +116,188 @@ static int qe_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) return 0; } +struct qe_pin { + /* + * The qe_gpio_chip name is unfortunate, we should change that to + * something like qe_pio_controller. Someday. + */ + struct qe_gpio_chip *controller; + int num; +}; + +/** + * qe_pin_request - Request a QE pin + * @np: device node to get a pin from + * @index: index of a pin in the device tree + * Context: non-atomic + * + * This function return qe_pin so that you could use it with the rest of + * the QE Pin Multiplexing API. + */ +struct qe_pin *qe_pin_request(struct device_node *np, int index) +{ + struct qe_pin *qe_pin; + struct device_node *gc; + struct of_gpio_chip *of_gc = NULL; + struct of_mm_gpio_chip *mm_gc; + struct qe_gpio_chip *qe_gc; + int err; + int size; + const void *gpio_spec; + const u32 *gpio_cells; + unsigned long flags; + + qe_pin = kzalloc(sizeof(*qe_pin), GFP_KERNEL); + if (!qe_pin) { + pr_debug("%s: can't allocate memory\n", __func__); + return ERR_PTR(-ENOMEM); + } + + err = of_parse_phandles_with_args(np, "gpios", "#gpio-cells", index, + &gc, &gpio_spec); + if (err) { + pr_debug("%s: can't parse gpios property\n", __func__); + goto err0; + } + + if (!of_device_is_compatible(gc, "fsl,mpc8323-qe-pario-bank")) { + pr_debug("%s: tried to get a non-qe pin\n", __func__); + err = -EINVAL; + goto err1; + } + + of_gc = gc->data; + if (!of_gc) { + pr_debug("%s: gpio controller %s isn't registered\n", + np->full_name, gc->full_name); + err = -ENODEV; + goto err1; + } + + gpio_cells = of_get_property(gc, "#gpio-cells", &size); + if (!gpio_cells || size != sizeof(*gpio_cells) || + *gpio_cells != of_gc->gpio_cells) { + pr_debug("%s: wrong #gpio-cells for %s\n", + np->full_name, gc->full_name); + err = -EINVAL; + goto err1; + } + + err = of_gc->xlate(of_gc, np, gpio_spec, NULL); + if (err < 0) + goto err1; + + mm_gc = to_of_mm_gpio_chip(&of_gc->gc); + qe_gc = to_qe_gpio_chip(mm_gc); + + spin_lock_irqsave(&qe_gc->lock, flags); + + if (test_and_set_bit(QE_PIN_REQUESTED, &qe_gc->pin_flags[err]) == 0) { + qe_pin->controller = qe_gc; + qe_pin->num = err; + err = 0; + } else { + err = -EBUSY; + } + + spin_unlock_irqrestore(&qe_gc->lock, flags); + + if (!err) + return qe_pin; +err1: + of_node_put(gc); +err0: + kfree(qe_pin); + pr_debug("%s failed with status %d\n", __func__, err); + return ERR_PTR(err); +} +EXPORT_SYMBOL(qe_pin_request); + +/** + * qe_pin_free - Free a pin + * @qe_pin: pointer to the qe_pin structure + * Context: any + * + * This function frees the qe_pin structure and makes a pin available + * for further qe_pin_request() calls. + */ +void qe_pin_free(struct qe_pin *qe_pin) +{ + struct qe_gpio_chip *qe_gc = qe_pin->controller; + unsigned long flags; + const int pin = qe_pin->num; + + spin_lock_irqsave(&qe_gc->lock, flags); + test_and_clear_bit(QE_PIN_REQUESTED, &qe_gc->pin_flags[pin]); + spin_unlock_irqrestore(&qe_gc->lock, flags); + + kfree(qe_pin); +} +EXPORT_SYMBOL(qe_pin_free); + +/** + * qe_pin_set_dedicated - Revert a pin to a dedicated peripheral function mode + * @qe_pin: pointer to the qe_pin structure + * Context: any + * + * This function resets a pin to a dedicated peripheral function that + * has been set up by the firmware. + */ +void qe_pin_set_dedicated(struct qe_pin *qe_pin) +{ + struct qe_gpio_chip *qe_gc = qe_pin->controller; + struct qe_pio_regs __iomem *regs = qe_gc->mm_gc.regs; + struct qe_pio_regs *sregs = &qe_gc->saved_regs; + int pin = qe_pin->num; + u32 mask1 = 1 << (QE_PIO_PINS - (pin + 1)); + u32 mask2 = 0x3 << (QE_PIO_PINS - (pin % (QE_PIO_PINS / 2) + 1) * 2); + bool second_reg = pin > (QE_PIO_PINS / 2) - 1; + unsigned long flags; + + spin_lock_irqsave(&qe_gc->lock, flags); + + if (second_reg) { + clrsetbits_be32(®s->cpdir2, mask2, sregs->cpdir2 & mask2); + clrsetbits_be32(®s->cppar2, mask2, sregs->cppar2 & mask2); + } else { + clrsetbits_be32(®s->cpdir1, mask2, sregs->cpdir1 & mask2); + clrsetbits_be32(®s->cppar1, mask2, sregs->cppar1 & mask2); + } + + if (sregs->cpdata & mask1) + qe_gc->cpdata |= mask1; + else + qe_gc->cpdata &= ~mask1; + + out_be32(®s->cpdata, qe_gc->cpdata); + clrsetbits_be32(®s->cpodr, mask1, sregs->cpodr & mask1); + + spin_unlock_irqrestore(&qe_gc->lock, flags); +} +EXPORT_SYMBOL(qe_pin_set_dedicated); + +/** + * qe_pin_set_gpio - Set a pin to the GPIO mode + * @qe_pin: pointer to the qe_pin structure + * Context: any + * + * This function sets a pin to the GPIO mode. + */ +void qe_pin_set_gpio(struct qe_pin *qe_pin) +{ + struct qe_gpio_chip *qe_gc = qe_pin->controller; + struct qe_pio_regs __iomem *regs = qe_gc->mm_gc.regs; + unsigned long flags; + + spin_lock_irqsave(&qe_gc->lock, flags); + + /* Let's make it input by default, GPIO API is able to change that. */ + __par_io_config_pin(regs, qe_pin->num, QE_PIO_DIR_IN, 0, 0, 0); + + spin_unlock_irqrestore(&qe_gc->lock, flags); +} +EXPORT_SYMBOL(qe_pin_set_gpio); + static int __init qe_add_gpiochips(void) { struct device_node *np; diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c new file mode 100644 index 000000000000..43c4569e24b7 --- /dev/null +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -0,0 +1,155 @@ +/* + * Simple Memory-Mapped GPIOs + * + * Copyright (c) MontaVista Software, Inc. 2008. + * + * Author: Anton Vorontsov <avorontsov@ru.mvista.com> + * + * 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/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/ioport.h> +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_gpio.h> +#include <linux/gpio.h> +#include <asm/prom.h> +#include "simple_gpio.h" + +struct u8_gpio_chip { + struct of_mm_gpio_chip mm_gc; + spinlock_t lock; + + /* shadowed data register to clear/set bits safely */ + u8 data; +}; + +static struct u8_gpio_chip *to_u8_gpio_chip(struct of_mm_gpio_chip *mm_gc) +{ + return container_of(mm_gc, struct u8_gpio_chip, mm_gc); +} + +static u8 u8_pin2mask(unsigned int pin) +{ + return 1 << (8 - 1 - pin); +} + +static int u8_gpio_get(struct gpio_chip *gc, unsigned int gpio) +{ + struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); + + return in_8(mm_gc->regs) & u8_pin2mask(gpio); +} + +static void u8_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val) +{ + struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); + struct u8_gpio_chip *u8_gc = to_u8_gpio_chip(mm_gc); + unsigned long flags; + + spin_lock_irqsave(&u8_gc->lock, flags); + + if (val) + u8_gc->data |= u8_pin2mask(gpio); + else + u8_gc->data &= ~u8_pin2mask(gpio); + + out_8(mm_gc->regs, u8_gc->data); + + spin_unlock_irqrestore(&u8_gc->lock, flags); +} + +static int u8_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio) +{ + return 0; +} + +static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) +{ + u8_gpio_set(gc, gpio, val); + return 0; +} + +static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc) +{ + struct u8_gpio_chip *u8_gc = to_u8_gpio_chip(mm_gc); + + u8_gc->data = in_8(mm_gc->regs); +} + +static int __init u8_simple_gpiochip_add(struct device_node *np) +{ + int ret; + struct u8_gpio_chip *u8_gc; + struct of_mm_gpio_chip *mm_gc; + struct of_gpio_chip *of_gc; + struct gpio_chip *gc; + + u8_gc = kzalloc(sizeof(*u8_gc), GFP_KERNEL); + if (!u8_gc) + return -ENOMEM; + + spin_lock_init(&u8_gc->lock); + + mm_gc = &u8_gc->mm_gc; + of_gc = &mm_gc->of_gc; + gc = &of_gc->gc; + + mm_gc->save_regs = u8_gpio_save_regs; + of_gc->gpio_cells = 2; + gc->ngpio = 8; + gc->direction_input = u8_gpio_dir_in; + gc->direction_output = u8_gpio_dir_out; + gc->get = u8_gpio_get; + gc->set = u8_gpio_set; + + ret = of_mm_gpiochip_add(np, mm_gc); + if (ret) + goto err; + return 0; +err: + kfree(u8_gc); + return ret; +} + +void __init simple_gpiochip_init(const char *compatible) +{ + struct device_node *np; + + for_each_compatible_node(np, NULL, compatible) { + int ret; + struct resource r; + + ret = of_address_to_resource(np, 0, &r); + if (ret) + goto err; + + switch (resource_size(&r)) { + case 1: + ret = u8_simple_gpiochip_add(np); + if (ret) + goto err; + break; + default: + /* + * Whenever you need support for GPIO bank width > 1, + * please just turn u8_ code into huge macros, and + * construct needed uX_ code with it. + */ + ret = -ENOSYS; + goto err; + } + continue; +err: + pr_err("%s: registration failed, status %d\n", + np->full_name, ret); + } +} diff --git a/arch/powerpc/sysdev/simple_gpio.h b/arch/powerpc/sysdev/simple_gpio.h new file mode 100644 index 000000000000..3a7b0c513c76 --- /dev/null +++ b/arch/powerpc/sysdev/simple_gpio.h @@ -0,0 +1,12 @@ +#ifndef __SYSDEV_SIMPLE_GPIO_H +#define __SYSDEV_SIMPLE_GPIO_H + +#include <linux/errno.h> + +#ifdef CONFIG_SIMPLE_GPIO +extern void simple_gpiochip_init(const char *compatible); +#else +static inline void simple_gpiochip_init(const char *compatible) {} +#endif /* CONFIG_SIMPLE_GPIO */ + +#endif /* __SYSDEV_SIMPLE_GPIO_H */ |