diff options
Diffstat (limited to 'arch/powerpc')
404 files changed, 10992 insertions, 5073 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 36f858c37ca7..809c468edab1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -85,6 +85,17 @@ config NMI_IPI depends on SMP && (DEBUGGER || KEXEC_CORE || HARDLOCKUP_DETECTOR) default y +config PPC_WATCHDOG + bool + depends on HARDLOCKUP_DETECTOR + depends on HAVE_HARDLOCKUP_DETECTOR_ARCH + default y + help + This is a placeholder when the powerpc hardlockup detector + watchdog is selected (arch/powerpc/kernel/watchdog.c). It is + seleted via the generic lockup detector menu which is why we + have no standalone config option for it here. + config STACKTRACE_SUPPORT bool default y @@ -165,7 +176,7 @@ config PPC select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S_64 && !RELOCATABLE && !HIBERNATION) + select ARCH_HAS_STRICT_KERNEL_RWX if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION) select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select HAVE_CBPF_JIT if !PPC64 select HAVE_CONTEXT_TRACKING if PPC64 @@ -199,7 +210,7 @@ config PPC select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI if PPC64 - select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP @@ -356,10 +367,6 @@ config PPC_ADV_DEBUG_DAC_RANGE depends on PPC_ADV_DEBUG_REGS && 44x default y -config PPC_EMULATE_SSTEP - bool - default y if KPROBES || UPROBES || XMON || HAVE_HW_BREAKPOINT - config ZONE_DMA32 bool default y if PPC64 @@ -394,7 +401,7 @@ config HUGETLB_PAGE_SIZE_VARIABLE config MATH_EMULATION bool "Math emulation" - depends on 4xx || 8xx || PPC_MPC832x || BOOKE + depends on 4xx || PPC_8xx || PPC_MPC832x || BOOKE ---help--- Some PowerPC chips designed for embedded applications do not have a floating-point unit and therefore do not implement the @@ -956,9 +963,9 @@ config PPC_PCI_CHOICE config PCI bool "PCI support" if PPC_PCI_CHOICE - default y if !40x && !CPM2 && !8xx && !PPC_83xx \ + default y if !40x && !CPM2 && !PPC_8xx && !PPC_83xx \ && !PPC_85xx && !PPC_86xx && !GAMECUBE_COMMON - default PCI_QSPAN if !4xx && !CPM2 && 8xx + default PCI_QSPAN if PPC_8xx select GENERIC_PCI_IOMAP help Find out whether your system includes a PCI bus. PCI is the name of @@ -974,7 +981,7 @@ config PCI_SYSCALL config PCI_QSPAN bool "QSpan PCI" - depends on !4xx && !CPM2 && 8xx + depends on PPC_8xx select PPC_I8259 help Say Y here if you have a system based on a Motorola 8xx-series @@ -1165,12 +1172,23 @@ config CONSISTENT_SIZE config PIN_TLB bool "Pinned Kernel TLBs (860 ONLY)" - depends on ADVANCED_OPTIONS && 8xx + depends on ADVANCED_OPTIONS && PPC_8xx && \ + !DEBUG_PAGEALLOC && !STRICT_KERNEL_RWX + +config PIN_TLB_DATA + bool "Pinned TLB for DATA" + depends on PIN_TLB + default y config PIN_TLB_IMMR bool "Pinned TLB for IMMR" depends on PIN_TLB default y + +config PIN_TLB_TEXT + bool "Pinned TLB for TEXT" + depends on PIN_TLB + default y endmenu if PPC64 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index e2b3e7a00c9e..1381693a4a51 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -250,7 +250,7 @@ KBUILD_AFLAGS += $(aflags-y) KBUILD_CFLAGS += $(cflags-y) head-y := arch/powerpc/kernel/head_$(BITS).o -head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o +head-$(CONFIG_PPC_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o head-$(CONFIG_FSL_BOOKE) := arch/powerpc/kernel/head_fsl_booke.o @@ -317,6 +317,10 @@ PHONY += ppc64le_defconfig ppc64le_defconfig: $(call merge_into_defconfig,ppc64_defconfig,le) +PHONY += powernv_be_defconfig +powernv_be_defconfig: + $(call merge_into_defconfig,powernv_defconfig,be) + PHONY += mpc85xx_defconfig mpc85xx_defconfig: $(call merge_into_defconfig,mpc85xx_basic_defconfig,\ diff --git a/arch/powerpc/boot/4xx.c b/arch/powerpc/boot/4xx.c index 9d3bd4c45a24..f7da65169124 100644 --- a/arch/powerpc/boot/4xx.c +++ b/arch/powerpc/boot/4xx.c @@ -564,7 +564,7 @@ void ibm405gp_fixup_clocks(unsigned int sys_clk, unsigned int ser_clk) fbdv = 16; cbdv = ((pllmr & 0x00060000) >> 17) + 1; /* CPU:PLB */ opdv = ((pllmr & 0x00018000) >> 15) + 1; /* PLB:OPB */ - ppdv = ((pllmr & 0x00001800) >> 13) + 1; /* PLB:PCI */ + ppdv = ((pllmr & 0x00006000) >> 13) + 1; /* PLB:PCI */ epdv = ((pllmr & 0x00001800) >> 11) + 2; /* PLB:EBC */ udiv = ((cpc0_cr0 & 0x3e) >> 1) + 1; diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index a7814a7b1523..c4e6fe35c075 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -25,12 +25,20 @@ compress-$(CONFIG_KERNEL_XZ) := CONFIG_KERNEL_XZ BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -Os -msoft-float -pipe \ -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ - -isystem $(shell $(CROSS32CC) -print-file-name=include) \ -D$(compress-y) +BOOTCC := $(CC) ifdef CONFIG_PPC64_BOOT_WRAPPER BOOTCFLAGS += -m64 +else +BOOTCFLAGS += -m32 +ifdef CROSS32_COMPILE + BOOTCC := $(CROSS32_COMPILE)gcc +endif endif + +BOOTCFLAGS += -isystem $(shell $(BOOTCC) -print-file-name=include) + ifdef CONFIG_CPU_BIG_ENDIAN BOOTCFLAGS += -mbig-endian else @@ -99,17 +107,18 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ $(libfdt) libfdt-wrapper.c \ ns16550.c serial.c simple_alloc.c div64.S util.S \ elf_util.c $(zlib-y) devtree.c stdlib.c \ - oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \ - uartlite.c mpc52xx-psc.c opal.c + oflib.c ofconsole.c cuboot.c cpm-serial.c \ + uartlite.c opal.c +src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S endif src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c -src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c fsl-soc.c +src-wlib-$(CONFIG_PPC_8xx) += mpc8xx.c planetcore.c fsl-soc.c src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c -src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c fsl-soc.c +src-wlib-$(CONFIG_EMBEDDED6xx) += mpsc.c mv64x60.c mv64x60_i2c.c ugecon.c fsl-soc.c src-plat-y := of.c epapr.c src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \ @@ -124,7 +133,7 @@ src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \ treeboot-iss4xx.c treeboot-currituck.c \ treeboot-akebono.c \ simpleboot.c fixed-head.S virtex.c -src-plat-$(CONFIG_8xx) += cuboot-8xx.c fixed-head.S ep88xc.c redboot-8xx.c +src-plat-$(CONFIG_PPC_8xx) += cuboot-8xx.c fixed-head.S ep88xc.c redboot-8xx.c src-plat-$(CONFIG_PPC_MPC52xx) += cuboot-52xx.c src-plat-$(CONFIG_PPC_82xx) += cuboot-pq2.c fixed-head.S ep8248e.c cuboot-824x.c src-plat-$(CONFIG_PPC_83xx) += cuboot-83xx.c fixed-head.S redboot-83xx.c @@ -183,10 +192,10 @@ clean-files := $(zlib-) $(zlibheader-) $(zliblinuxheader-) \ empty.c zImage.coff.lds zImage.ps3.lds zImage.lds quiet_cmd_bootcc = BOOTCC $@ - cmd_bootcc = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $< + cmd_bootcc = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTCFLAGS) -c -o $@ $< quiet_cmd_bootas = BOOTAS $@ - cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $< + cmd_bootas = $(BOOTCC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $< quiet_cmd_bootar = BOOTAR $@ cmd_bootar = $(CROSS32AR) -cr$(KBUILD_ARFLAGS) $@.$$$$ $(filter-out FORCE,$^); mv $@.$$$$ $@ diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index 12866ccb5694..dcf2f15e6797 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -26,17 +26,17 @@ _zimage_start_opd: #ifdef __powerpc64__ .balign 8 -p_start: .llong _start -p_etext: .llong _etext -p_bss_start: .llong __bss_start -p_end: .llong _end - -p_toc: .llong __toc_start + 0x8000 - p_base -p_dyn: .llong __dynamic_start - p_base -p_rela: .llong __rela_dyn_start - p_base -p_prom: .llong 0 +p_start: .8byte _start +p_etext: .8byte _etext +p_bss_start: .8byte __bss_start +p_end: .8byte _end + +p_toc: .8byte __toc_start + 0x8000 - p_base +p_dyn: .8byte __dynamic_start - p_base +p_rela: .8byte __rela_dyn_start - p_base +p_prom: .8byte 0 .weak _platform_stack_top -p_pstack: .llong _platform_stack_top +p_pstack: .8byte _platform_stack_top #else p_start: .long _start p_etext: .long _etext diff --git a/arch/powerpc/boot/dts/fsp2.dts b/arch/powerpc/boot/dts/fsp2.dts index 475953ada707..f10a64aeb83b 100644 --- a/arch/powerpc/boot/dts/fsp2.dts +++ b/arch/powerpc/boot/dts/fsp2.dts @@ -52,6 +52,7 @@ clocks { mmc_clk: mmc_clk { compatible = "fixed-clock"; + #clock-cells = <0>; clock-frequency = <50000000>; clock-output-names = "mmc_clk"; }; @@ -359,20 +360,6 @@ interrupts = <31 0x4 15 0x84>; }; - mmc0: sdhci@020c0000 { - compatible = "st,sdhci-stih407", "st,sdhci"; - status = "disabled"; - reg = <0x020c0000 0x20000>; - reg-names = "mmc"; - interrupt-parent = <&UIC1_3>; - interrupts = <21 0x4 22 0x4>; - interrupt-names = "mmcirq"; - pinctrl-names = "default"; - pinctrl-0 = <>; - clock-names = "mmc"; - clocks = <&mmc_clk>; - }; - plb6 { compatible = "ibm,plb6"; #address-cells = <2>; @@ -501,6 +488,24 @@ /*RXDE*/ 4 &UIC1_2 13 0x4>; }; + mmc0: mmc@20c0000 { + compatible = "st,sdhci-stih407", "st,sdhci"; + reg = <0x020c0000 0x20000>; + reg-names = "mmc"; + interrupts = <21 0x4>; + interrupt-parent = <&UIC1_3>; + interrupt-names = "mmcirq"; + pinctrl-names = "default"; + pinctrl-0 = <>; + clock-names = "mmc"; + clocks = <&mmc_clk>; + bus-width = <4>; + non-removable; + sd-uhs-sdr50; + sd-uhs-sdr104; + sd-uhs-ddr50; + }; + opb { compatible = "ibm,opb"; #address-cells = <1>; diff --git a/arch/powerpc/boot/ppc_asm.h b/arch/powerpc/boot/ppc_asm.h index 68e388ee94fe..c63299f9fdd9 100644 --- a/arch/powerpc/boot/ppc_asm.h +++ b/arch/powerpc/boot/ppc_asm.h @@ -80,4 +80,12 @@ .long 0xa6037b7d; /* mtsrr1 r11 */ \ .long 0x2400004c /* rfid */ +#ifdef CONFIG_PPC_8xx +#define MFTBL(dest) mftb dest +#define MFTBU(dest) mftbu dest +#else +#define MFTBL(dest) mfspr dest, SPRN_TBRL +#define MFTBU(dest) mfspr dest, SPRN_TBRU +#endif + #endif /* _PPC64_PPC_ASM_H */ diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index e04c1e4063ae..7b5c02b1afd0 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -120,15 +120,19 @@ int serial_console_init(void) if (dt_is_compatible(devp, "ns16550") || dt_is_compatible(devp, "pnpPNP,501")) rc = ns16550_console_init(devp, &serial_cd); +#ifdef CONFIG_EMBEDDED6xx else if (dt_is_compatible(devp, "marvell,mv64360-mpsc")) rc = mpsc_console_init(devp, &serial_cd); +#endif else if (dt_is_compatible(devp, "fsl,cpm1-scc-uart") || dt_is_compatible(devp, "fsl,cpm1-smc-uart") || dt_is_compatible(devp, "fsl,cpm2-scc-uart") || dt_is_compatible(devp, "fsl,cpm2-smc-uart")) rc = cpm_console_init(devp, &serial_cd); +#ifdef CONFIG_PPC_MPC52XX else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); +#endif else if (dt_is_compatible(devp, "xlnx,opb-uartlite-1.00.b") || dt_is_compatible(devp, "xlnx,xps-uartlite-1.00.a")) rc = uartlite_console_init(devp, &serial_cd); diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S index 243b8497d58b..ec069177d942 100644 --- a/arch/powerpc/boot/util.S +++ b/arch/powerpc/boot/util.S @@ -71,32 +71,18 @@ udelay: add r4,r4,r5 addi r4,r4,-1 divw r4,r4,r5 /* BUS ticks */ -#ifdef CONFIG_8xx -1: mftbu r5 - mftb r6 - mftbu r7 -#else -1: mfspr r5, SPRN_TBRU - mfspr r6, SPRN_TBRL - mfspr r7, SPRN_TBRU -#endif +1: MFTBU(r5) + MFTBL(r6) + MFTBU(r7) cmpw 0,r5,r7 bne 1b /* Get [synced] base time */ addc r9,r6,r4 /* Compute end time */ addze r8,r5 -#ifdef CONFIG_8xx -2: mftbu r5 -#else -2: mfspr r5, SPRN_TBRU -#endif +2: MFTBU(r5) cmpw 0,r5,r8 blt 2b bgt 3f -#ifdef CONFIG_8xx - mftb r6 -#else - mfspr r6, SPRN_TBRL -#endif + MFTBL(r6) cmpw 0,r6,r9 blt 2b 3: blr diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig index 3438ed99c088..e57344c3b0d7 100644 --- a/arch/powerpc/configs/40x/acadia_defconfig +++ b/arch/powerpc/configs/40x/acadia_defconfig @@ -64,4 +64,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig index 36c44c0b560c..0f66f8a87be8 100644 --- a/arch/powerpc/configs/40x/ep405_defconfig +++ b/arch/powerpc/configs/40x/ep405_defconfig @@ -64,4 +64,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig index ad2156c6e2fc..b5cc7426c21f 100644 --- a/arch/powerpc/configs/40x/kilauea_defconfig +++ b/arch/powerpc/configs/40x/kilauea_defconfig @@ -72,4 +72,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/40x/klondike_defconfig b/arch/powerpc/configs/40x/klondike_defconfig index 28adb782ec51..caab658d1da1 100644 --- a/arch/powerpc/configs/40x/klondike_defconfig +++ b/arch/powerpc/configs/40x/klondike_defconfig @@ -26,7 +26,6 @@ CONFIG_SCSI_SAS_ATTRS=y # CONFIG_VT is not set # CONFIG_UNIX98_PTYS is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set # CONFIG_USB_SUPPORT is not set diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig index a00f434c4d47..e0b1489b7c7b 100644 --- a/arch/powerpc/configs/40x/makalu_defconfig +++ b/arch/powerpc/configs/40x/makalu_defconfig @@ -62,4 +62,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/40x/obs600_defconfig b/arch/powerpc/configs/40x/obs600_defconfig index e500e6a12b3e..aac06d2ad01a 100644 --- a/arch/powerpc/configs/40x/obs600_defconfig +++ b/arch/powerpc/configs/40x/obs600_defconfig @@ -72,4 +72,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/40x/virtex_defconfig b/arch/powerpc/configs/40x/virtex_defconfig index 65dc084a154c..a2b2770eee8f 100644 --- a/arch/powerpc/configs/40x/virtex_defconfig +++ b/arch/powerpc/configs/40x/virtex_defconfig @@ -41,9 +41,9 @@ CONFIG_NETDEVICES=y CONFIG_SERIO_XILINX_XPS_PS2=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y CONFIG_XILINX_HWICAP=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y @@ -74,4 +74,3 @@ CONFIG_FONT_8x16=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_KERNEL=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig index 567f99bd64a3..6faa03cd661c 100644 --- a/arch/powerpc/configs/40x/walnut_defconfig +++ b/arch/powerpc/configs/40x/walnut_defconfig @@ -57,4 +57,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig index 143b2fbddb46..9fcd361607e2 100644 --- a/arch/powerpc/configs/44x/akebono_defconfig +++ b/arch/powerpc/configs/44x/akebono_defconfig @@ -123,7 +123,6 @@ CONFIG_NLS_DEFAULT="n" CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_XMON=y @@ -135,5 +134,4 @@ CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_SHA1_PPC=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig index 477d99fefd9a..6f3a6ecc81e7 100644 --- a/arch/powerpc/configs/44x/bamboo_defconfig +++ b/arch/powerpc/configs/44x/bamboo_defconfig @@ -55,4 +55,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig index 3799a26de6f4..5f1df5fe4453 100644 --- a/arch/powerpc/configs/44x/currituck_defconfig +++ b/arch/powerpc/configs/44x/currituck_defconfig @@ -81,7 +81,6 @@ CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_NLS_DEFAULT="n" CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_XMON=y @@ -94,5 +93,4 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig index c265f54ab9e5..e2b6578993d5 100644 --- a/arch/powerpc/configs/44x/ebony_defconfig +++ b/arch/powerpc/configs/44x/ebony_defconfig @@ -59,5 +59,4 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig index bb6bd6d90821..f6dc23fef683 100644 --- a/arch/powerpc/configs/44x/eiger_defconfig +++ b/arch/powerpc/configs/44x/eiger_defconfig @@ -84,18 +84,14 @@ CONFIG_CRYPTO_CCM=y CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CTS=y -CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_LRW=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_XTS=y -CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=y CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_SHA1=y -CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_ARC4=y CONFIG_CRYPTO_BLOWFISH=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig index e8e6a6999852..bae6b26bcfba 100644 --- a/arch/powerpc/configs/44x/fsp2_defconfig +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -92,8 +92,10 @@ CONFIG_MMC_DEBUG=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_OF_ARASAN=y +CONFIG_MMC_SDHCI_ST=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_M41T80=y +CONFIG_RESET_CONTROLLER=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y @@ -115,7 +117,6 @@ CONFIG_PRINTK_TIME=y CONFIG_MESSAGE_LOGLEVEL_DEFAULT=3 CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_CRYPTO_CBC=y diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig index 060f2edddb71..4453a4590b1a 100644 --- a/arch/powerpc/configs/44x/icon_defconfig +++ b/arch/powerpc/configs/44x/icon_defconfig @@ -47,8 +47,6 @@ CONFIG_FUSION_LOGGING=y CONFIG_NETDEVICES=y CONFIG_IBM_EMAC=y # CONFIG_WLAN is not set -CONFIG_INPUT_MOUSEDEV_SCREEN_X=640 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480 # CONFIG_MOUSE_PS2_ALPS is not set # CONFIG_MOUSE_PS2_LOGIPS2PP is not set # CONFIG_MOUSE_PS2_SYNAPTICS is not set @@ -94,4 +92,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig index 115a6b2be18b..d24bfa6ecd62 100644 --- a/arch/powerpc/configs/44x/iss476-smp_defconfig +++ b/arch/powerpc/configs/44x/iss476-smp_defconfig @@ -63,7 +63,6 @@ CONFIG_TMPFS=y CONFIG_CRAMFS=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_PPC_EARLY_DEBUG=y @@ -72,5 +71,4 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig index b999048c4ae6..5d3f685a7af8 100644 --- a/arch/powerpc/configs/44x/katmai_defconfig +++ b/arch/powerpc/configs/44x/katmai_defconfig @@ -60,4 +60,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig index b8c9ee45d0a2..7b8355a5698d 100644 --- a/arch/powerpc/configs/44x/rainier_defconfig +++ b/arch/powerpc/configs/44x/rainier_defconfig @@ -66,4 +66,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig index a4bb048448da..918cfb63f0c8 100644 --- a/arch/powerpc/configs/44x/redwood_defconfig +++ b/arch/powerpc/configs/44x/redwood_defconfig @@ -83,18 +83,14 @@ CONFIG_CRYPTO_CCM=y CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CTS=y -CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_LRW=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_XTS=y -CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_XCBC=y CONFIG_CRYPTO_MD4=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_SHA1=y -CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_ARC4=y CONFIG_CRYPTO_BLOWFISH=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig index b3792fd8111d..1e04122912f3 100644 --- a/arch/powerpc/configs/44x/sequoia_defconfig +++ b/arch/powerpc/configs/44x/sequoia_defconfig @@ -67,4 +67,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig index ff6f86241418..42cc7b4ed95f 100644 --- a/arch/powerpc/configs/44x/taishan_defconfig +++ b/arch/powerpc/configs/44x/taishan_defconfig @@ -61,4 +61,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/virtex5_defconfig b/arch/powerpc/configs/44x/virtex5_defconfig index ce052064bcbb..99cc3dc02df1 100644 --- a/arch/powerpc/configs/44x/virtex5_defconfig +++ b/arch/powerpc/configs/44x/virtex5_defconfig @@ -40,9 +40,9 @@ CONFIG_NETDEVICES=y CONFIG_SERIO_XILINX_XPS_PS2=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y CONFIG_XILINX_HWICAP=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y @@ -73,4 +73,3 @@ CONFIG_FONT_8x16=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_KERNEL=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig index ab932488e68b..b5c866073efd 100644 --- a/arch/powerpc/configs/44x/warp_defconfig +++ b/arch/powerpc/configs/44x/warp_defconfig @@ -97,4 +97,3 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/52xx/cm5200_defconfig b/arch/powerpc/configs/52xx/cm5200_defconfig index c1faac800806..73948e88ac82 100644 --- a/arch/powerpc/configs/52xx/cm5200_defconfig +++ b/arch/powerpc/configs/52xx/cm5200_defconfig @@ -77,4 +77,3 @@ CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/52xx/lite5200b_defconfig b/arch/powerpc/configs/52xx/lite5200b_defconfig index 9493b02ac660..6fc7f786c83c 100644 --- a/arch/powerpc/configs/52xx/lite5200b_defconfig +++ b/arch/powerpc/configs/52xx/lite5200b_defconfig @@ -14,6 +14,7 @@ CONFIG_PPC_MPC52xx=y CONFIG_PPC_MPC5200_SIMPLE=y CONFIG_PPC_LITE5200=y # CONFIG_PPC_PMAC is not set +CONFIG_GEN_RTC=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -44,7 +45,6 @@ CONFIG_SERIAL_MPC52xx=y CONFIG_SERIAL_MPC52xx_CONSOLE=y CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200 # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -62,4 +62,3 @@ CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/52xx/motionpro_defconfig b/arch/powerpc/configs/52xx/motionpro_defconfig index fe8126bc1655..ae2a1f74103b 100644 --- a/arch/powerpc/configs/52xx/motionpro_defconfig +++ b/arch/powerpc/configs/52xx/motionpro_defconfig @@ -41,16 +41,16 @@ CONFIG_ATA=y CONFIG_PATA_MPC52xx=y CONFIG_NETDEVICES=y CONFIG_FEC_MPC52xx=y -CONFIG_MARVELL_PHY=y +CONFIG_MDIO_BITBANG=y +CONFIG_BROADCOM_PHY=y +CONFIG_CICADA_PHY=y CONFIG_DAVICOM_PHY=y -CONFIG_QSEMI_PHY=y +CONFIG_ICPLUS_PHY=y CONFIG_LXT_PHY=y -CONFIG_CICADA_PHY=y -CONFIG_VITESSE_PHY=y +CONFIG_MARVELL_PHY=y +CONFIG_QSEMI_PHY=y CONFIG_SMSC_PHY=y -CONFIG_BROADCOM_PHY=y -CONFIG_ICPLUS_PHY=y -CONFIG_MDIO_BITBANG=y +CONFIG_VITESSE_PHY=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set @@ -90,4 +90,3 @@ CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig index b8b316b884aa..0777e6efd22d 100644 --- a/arch/powerpc/configs/52xx/tqm5200_defconfig +++ b/arch/powerpc/configs/52xx/tqm5200_defconfig @@ -48,7 +48,6 @@ CONFIG_PATA_PLATFORM=y CONFIG_NETDEVICES=y CONFIG_FEC_MPC52xx=y CONFIG_LXT_PHY=y -CONFIG_FIXED_PHY=y CONFIG_SERIAL_MPC52xx=y CONFIG_SERIAL_MPC52xx_CONSOLE=y CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200 @@ -92,4 +91,3 @@ CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/asp8347_defconfig b/arch/powerpc/configs/83xx/asp8347_defconfig index b60cac088a7b..dd884df32dfd 100644 --- a/arch/powerpc/configs/83xx/asp8347_defconfig +++ b/arch/powerpc/configs/83xx/asp8347_defconfig @@ -42,7 +42,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 CONFIG_NETDEVICES=y CONFIG_GIANFAR=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -71,4 +70,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig index 9547dcdd6489..d21b5cb365f2 100644 --- a/arch/powerpc/configs/83xx/kmeter1_defconfig +++ b/arch/powerpc/configs/83xx/kmeter1_defconfig @@ -55,7 +55,6 @@ CONFIG_HDLC=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y diff --git a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig index 80aa844c1428..1f69f4edf074 100644 --- a/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc8313_rdb_defconfig @@ -48,8 +48,6 @@ CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y CONFIG_CICADA_PHY=y -CONFIG_FIXED_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -87,4 +85,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig index d89d13bc6901..797fc3ffddee 100644 --- a/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc8315_rdb_defconfig @@ -47,7 +47,6 @@ CONFIG_MD_RAID1=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -85,4 +84,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig index e789518a2881..4f914906ee4b 100644 --- a/arch/powerpc/configs/83xx/mpc832x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc832x_mds_defconfig @@ -14,7 +14,6 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC832x_MDS=y -CONFIG_QUICC_ENGINE=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y CONFIG_NET=y @@ -36,7 +35,6 @@ CONFIG_SCSI=y CONFIG_NETDEVICES=y CONFIG_UCC_GETH=y CONFIG_DAVICOM_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -50,6 +48,7 @@ CONFIG_I2C_MPC=y CONFIG_WATCHDOG=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1374=y +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -59,4 +58,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig index 917a49ca2bd1..a484eb8401e8 100644 --- a/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc832x_rdb_defconfig @@ -14,7 +14,7 @@ CONFIG_LDM_PARTITION=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC832x_RDB=y -CONFIG_QUICC_ENGINE=y +CONFIG_GEN_RTC=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y CONFIG_NET=y @@ -38,7 +38,6 @@ CONFIG_NETDEVICES=y CONFIG_UCC_GETH=y CONFIG_E1000=y CONFIG_ICPLUS_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -46,7 +45,6 @@ CONFIG_ICPLUS_PHY=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HW_RANDOM=y -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -62,6 +60,7 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y CONFIG_USB_STORAGE=y CONFIG_MMC=y CONFIG_MMC_SPI=y +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y @@ -78,4 +77,3 @@ CONFIG_NLS_ISO8859_1=y CONFIG_CRC_T10DIF=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig index 00f636e95cc8..37f4d93b3f81 100644 --- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig +++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig @@ -49,7 +49,6 @@ CONFIG_MD_RAID1=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_CICADA_PHY=y -CONFIG_FIXED_PHY=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set @@ -84,4 +83,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRC_T10DIF=y CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig index a539d44d1dba..7adb6708a761 100644 --- a/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig +++ b/arch/powerpc/configs/83xx/mpc834x_itxgp_defconfig @@ -75,4 +75,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRC_T10DIF=y CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig index 9f0ddc830c82..d7ce3551529d 100644 --- a/arch/powerpc/configs/83xx/mpc834x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc834x_mds_defconfig @@ -35,7 +35,6 @@ CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -58,4 +57,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig index ceed4c1f0ab5..92134cee3f37 100644 --- a/arch/powerpc/configs/83xx/mpc836x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc836x_mds_defconfig @@ -14,7 +14,6 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC836x_MDS=y -CONFIG_QUICC_ENGINE=y CONFIG_PCI=y CONFIG_NET=y CONFIG_PACKET=y @@ -41,7 +40,6 @@ CONFIG_SCSI=y CONFIG_NETDEVICES=y CONFIG_UCC_GETH=y CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -55,6 +53,7 @@ CONFIG_I2C_MPC=y CONFIG_WATCHDOG=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1374=y +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -64,4 +63,3 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig index a6819bf3ef5e..97f7ea5f205f 100644 --- a/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig +++ b/arch/powerpc/configs/83xx/mpc836x_rdk_defconfig @@ -12,7 +12,6 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC836x_RDK=y -CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_PCI=y CONFIG_NET=y @@ -39,11 +38,9 @@ CONFIG_BLK_DEV_RAM_SIZE=32768 CONFIG_NETDEVICES=y CONFIG_UCC_GETH=y CONFIG_BROADCOM_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_QE=y @@ -63,6 +60,7 @@ CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_USB_SUPPORT is not set +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -72,4 +70,3 @@ CONFIG_NFS_FS=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_PPC_EARLY_DEBUG=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig index 4bd1992e4d98..ee7510a33d06 100644 --- a/arch/powerpc/configs/83xx/mpc837x_mds_defconfig +++ b/arch/powerpc/configs/83xx/mpc837x_mds_defconfig @@ -11,6 +11,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC837x_MDS=y +CONFIG_GEN_RTC=y CONFIG_PCI=y CONFIG_NET=y CONFIG_PACKET=y @@ -35,7 +36,6 @@ CONFIG_SATA_FSL=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -43,7 +43,6 @@ CONFIG_MARVELL_PHY=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -58,4 +57,3 @@ CONFIG_ROOT_NFS=y CONFIG_CRC_T10DIF=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig index 2d4bb63882b8..8966a9af4230 100644 --- a/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig +++ b/arch/powerpc/configs/83xx/mpc837x_rdb_defconfig @@ -11,6 +11,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_MPC837x_RDB=y +CONFIG_GEN_RTC=y CONFIG_PCI=y CONFIG_NET=y CONFIG_PACKET=y @@ -41,9 +42,7 @@ CONFIG_MD_RAID456=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_MARVELL_PHY=y -CONFIG_FIXED_PHY=y CONFIG_INPUT_FF_MEMLESS=m -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -51,7 +50,6 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -86,4 +84,3 @@ CONFIG_CRC_T10DIF=y # CONFIG_ENABLE_MUST_CHECK is not set CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/83xx/sbc834x_defconfig b/arch/powerpc/configs/83xx/sbc834x_defconfig index b3380dbd1925..7d74699334da 100644 --- a/arch/powerpc/configs/83xx/sbc834x_defconfig +++ b/arch/powerpc/configs/83xx/sbc834x_defconfig @@ -11,6 +11,7 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y CONFIG_SBC834x=y +CONFIG_GEN_RTC=y CONFIG_PCI=y CONFIG_NET=y CONFIG_PACKET=y @@ -41,7 +42,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_BROADCOM_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -52,7 +52,6 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 CONFIG_SERIAL_8250_RUNTIME_UARTS=2 # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -72,5 +71,4 @@ CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig index a917f7afb4f9..dd98f43b2fb8 100644 --- a/arch/powerpc/configs/85xx/ge_imp3a_defconfig +++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig @@ -22,7 +22,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_GE_IMP3A=y -CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_CPM2=y CONFIG_HIGHMEM=y @@ -161,6 +160,7 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_RX8581=y CONFIG_DMADEVICES=y CONFIG_FSL_DMA=y +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -233,5 +233,4 @@ CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_SHA512=m CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_TALITOS=y diff --git a/arch/powerpc/configs/85xx/ksi8560_defconfig b/arch/powerpc/configs/85xx/ksi8560_defconfig index bd814dfb0bbd..9ce6f48cfb61 100644 --- a/arch/powerpc/configs/85xx/ksi8560_defconfig +++ b/arch/powerpc/configs/85xx/ksi8560_defconfig @@ -8,6 +8,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_KSI8560=y CONFIG_CPM2=y +CONFIG_GEN_RTC=y CONFIG_HIGHMEM=y CONFIG_BINFMT_MISC=y CONFIG_MATH_EMULATION=y @@ -39,14 +40,12 @@ CONFIG_FS_ENET=y CONFIG_FS_ENET_MDIO_FCC=y CONFIG_GIANFAR=y CONFIG_MARVELL_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_VT is not set CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -57,4 +56,3 @@ CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_MUTEXES=y # CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig index 32af10def641..5fbc3f904046 100644 --- a/arch/powerpc/configs/85xx/mpc8540_ads_defconfig +++ b/arch/powerpc/configs/85xx/mpc8540_ads_defconfig @@ -9,6 +9,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_MPC8540_ADS=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y CONFIG_MATH_EMULATION=y # CONFIG_SECCOMP is not set @@ -30,7 +31,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 CONFIG_NETDEVICES=y CONFIG_GIANFAR=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -38,7 +38,6 @@ CONFIG_GIANFAR=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -47,4 +46,3 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_MUTEXES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig index a52b2170ee33..ff981d7905c7 100644 --- a/arch/powerpc/configs/85xx/mpc8560_ads_defconfig +++ b/arch/powerpc/configs/85xx/mpc8560_ads_defconfig @@ -7,6 +7,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_MPC8560_ADS=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y CONFIG_MATH_EMULATION=y # CONFIG_SECCOMP is not set @@ -32,16 +33,14 @@ CONFIG_FS_ENET=y # CONFIG_FS_ENET_HAS_SCC is not set CONFIG_GIANFAR=y CONFIG_E1000=y -CONFIG_MARVELL_PHY=y CONFIG_DAVICOM_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set +CONFIG_MARVELL_PHY=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_VT is not set CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -50,4 +49,3 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_MUTEXES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig index 002bb48abaa3..974f0706d777 100644 --- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig +++ b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig @@ -9,6 +9,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_MPC85xx_CDS=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y CONFIG_MATH_EMULATION=y # CONFIG_SECCOMP is not set @@ -35,7 +36,6 @@ CONFIG_BLK_DEV_VIA82CXXX=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E1000=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -43,7 +43,6 @@ CONFIG_E1000=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -52,4 +51,3 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_MUTEXES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/sbc8548_defconfig b/arch/powerpc/configs/85xx/sbc8548_defconfig index 97ae02377cf3..7e3e84a842e4 100644 --- a/arch/powerpc/configs/85xx/sbc8548_defconfig +++ b/arch/powerpc/configs/85xx/sbc8548_defconfig @@ -6,6 +6,7 @@ CONFIG_EXPERT=y CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set CONFIG_SBC8548=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y CONFIG_MATH_EMULATION=y # CONFIG_SECCOMP is not set @@ -36,7 +37,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_BROADCOM_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -44,10 +44,8 @@ CONFIG_BROADCOM_PHY=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y # CONFIG_USB_SUPPORT is not set CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/socrates_defconfig b/arch/powerpc/configs/85xx/socrates_defconfig index 13579cb30539..6106fadbbd8b 100644 --- a/arch/powerpc/configs/85xx/socrates_defconfig +++ b/arch/powerpc/configs/85xx/socrates_defconfig @@ -42,8 +42,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_MARVELL_PHY=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=800 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480 CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -86,4 +84,3 @@ CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_FONTS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/stx_gp3_defconfig b/arch/powerpc/configs/85xx/stx_gp3_defconfig index 384926f3ce1d..5b9cc01b9098 100644 --- a/arch/powerpc/configs/85xx/stx_gp3_defconfig +++ b/arch/powerpc/configs/85xx/stx_gp3_defconfig @@ -39,8 +39,6 @@ CONFIG_SCSI_CONSTANTS=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_MARVELL_PHY=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1280 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=1024 CONFIG_INPUT_JOYDEV=m CONFIG_INPUT_EVDEV=m # CONFIG_VT is not set @@ -68,4 +66,3 @@ CONFIG_CRC_T10DIF=m CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_BDI_SWITCH=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/tqm8540_defconfig b/arch/powerpc/configs/85xx/tqm8540_defconfig index 908f3885f4a5..98982a0e82d8 100644 --- a/arch/powerpc/configs/85xx/tqm8540_defconfig +++ b/arch/powerpc/configs/85xx/tqm8540_defconfig @@ -9,6 +9,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_TQM8540=y +CONFIG_GEN_RTC=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y CONFIG_NET=y @@ -35,14 +36,12 @@ CONFIG_BLK_DEV_VIA82CXXX=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_VT is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -56,4 +55,3 @@ CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/tqm8541_defconfig b/arch/powerpc/configs/85xx/tqm8541_defconfig index f47e57610b7c..a6e21db1dafe 100644 --- a/arch/powerpc/configs/85xx/tqm8541_defconfig +++ b/arch/powerpc/configs/85xx/tqm8541_defconfig @@ -9,6 +9,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_TQM8541=y +CONFIG_GEN_RTC=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y CONFIG_NET=y @@ -35,7 +36,6 @@ CONFIG_BLK_DEV_VIA82CXXX=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -44,7 +44,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -58,4 +57,3 @@ CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/tqm8548_defconfig b/arch/powerpc/configs/85xx/tqm8548_defconfig index 42f5d0a7698e..2697e4e8a761 100644 --- a/arch/powerpc/configs/85xx/tqm8548_defconfig +++ b/arch/powerpc/configs/85xx/tqm8548_defconfig @@ -43,7 +43,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 CONFIG_NETDEVICES=y CONFIG_GIANFAR=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -66,4 +65,3 @@ CONFIG_ROOT_NFS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_MUTEXES=y # CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/tqm8555_defconfig b/arch/powerpc/configs/85xx/tqm8555_defconfig index 71552b7929cd..ca1de3979474 100644 --- a/arch/powerpc/configs/85xx/tqm8555_defconfig +++ b/arch/powerpc/configs/85xx/tqm8555_defconfig @@ -9,6 +9,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_TQM8555=y +CONFIG_GEN_RTC=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y CONFIG_NET=y @@ -35,7 +36,6 @@ CONFIG_BLK_DEV_VIA82CXXX=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -44,7 +44,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -58,4 +57,3 @@ CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/tqm8560_defconfig b/arch/powerpc/configs/85xx/tqm8560_defconfig index 25aac973d6d7..ca3b8c8ef30f 100644 --- a/arch/powerpc/configs/85xx/tqm8560_defconfig +++ b/arch/powerpc/configs/85xx/tqm8560_defconfig @@ -9,6 +9,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_MSDOS_PARTITION is not set CONFIG_TQM8560=y +CONFIG_GEN_RTC=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y CONFIG_NET=y @@ -35,7 +36,6 @@ CONFIG_BLK_DEV_VIA82CXXX=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -44,7 +44,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_MPC=y @@ -58,4 +57,3 @@ CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig index 72900b84d3e0..6531139a8a8d 100644 --- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig +++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig @@ -54,7 +54,6 @@ CONFIG_IP_PIMSM_V2=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -CONFIG_IPV6=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_REDBOOT_PARTS=y @@ -86,7 +85,6 @@ CONFIG_DUMMY=y CONFIG_GIANFAR=y CONFIG_E1000=y CONFIG_BROADCOM_PHY=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set CONFIG_SERIO_LIBPS2=y @@ -107,8 +105,8 @@ CONFIG_SENSORS_LM90=y CONFIG_WATCHDOG=y CONFIG_USB=y CONFIG_USB_MON=y -CONFIG_USB_ISP1760=y CONFIG_USB_STORAGE=y +CONFIG_USB_ISP1760=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y CONFIG_LEDS_PCA955X=y @@ -143,4 +141,3 @@ CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MD5=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/adder875_defconfig b/arch/powerpc/configs/adder875_defconfig index 6a3f825452e9..935ea3ade7de 100644 --- a/arch/powerpc/configs/adder875_defconfig +++ b/arch/powerpc/configs/adder875_defconfig @@ -12,6 +12,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set CONFIG_PPC_ADDER875=y CONFIG_8xx_COPYBACK=y +CONFIG_GEN_RTC=y CONFIG_HZ_1000=y # CONFIG_SECCOMP is not set CONFIG_NET=y @@ -41,7 +42,6 @@ CONFIG_DAVICOM_PHY=y # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y # CONFIG_HWMON is not set CONFIG_THERMAL=y # CONFIG_USB_SUPPORT is not set diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index 8d3e3c41258d..12f397d403c6 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -45,7 +45,6 @@ CONFIG_PARPORT_PC_FIFO=y CONFIG_BLK_DEV_FD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -120,5 +119,4 @@ CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_CRYPTO_CBC=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/be.config b/arch/powerpc/configs/be.config new file mode 100644 index 000000000000..c5cdc99a6530 --- /dev/null +++ b/arch/powerpc/configs/be.config @@ -0,0 +1 @@ +CONFIG_CPU_BIG_ENDIAN=y diff --git a/arch/powerpc/configs/c2k_defconfig b/arch/powerpc/configs/c2k_defconfig index 7c9d95370150..f1552af9eecc 100644 --- a/arch/powerpc/configs/c2k_defconfig +++ b/arch/powerpc/configs/c2k_defconfig @@ -27,6 +27,7 @@ CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m CONFIG_CPU_FREQ_GOV_ONDEMAND=m +CONFIG_GEN_RTC=y CONFIG_HIGHMEM=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_BINFMT_MISC=y @@ -197,7 +198,6 @@ CONFIG_TUN=m # CONFIG_ATM_DRIVERS is not set CONFIG_MV643XX_ETH=y CONFIG_VITESSE_PHY=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -209,7 +209,6 @@ CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_MPSC=y CONFIG_SERIAL_MPSC_CONSOLE=y CONFIG_NVRAM=m -CONFIG_GEN_RTC=m CONFIG_RAW_DRIVER=y CONFIG_MAX_RAW_DEVS=8192 CONFIG_I2C=m @@ -390,7 +389,6 @@ CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA1=y @@ -402,4 +400,3 @@ CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index aa564599e368..560a93a84efe 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -4,7 +4,6 @@ CONFIG_ALTIVEC=y CONFIG_SMP=y CONFIG_NR_CPUS=4 CONFIG_SYSVIPC=y -CONFIG_FHANDLE=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -34,10 +33,10 @@ CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=m CONFIG_IRQ_ALL_CPUS=y CONFIG_NUMA=y -CONFIG_MEMORY_HOTREMOVE=y CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_PCIEPORTBUS=y @@ -53,7 +52,6 @@ CONFIG_IP_PNP_RARP=y CONFIG_NET_IPIP=y CONFIG_SYN_COOKIES=y # CONFIG_INET_XFRM_MODE_BEET is not set -CONFIG_IPV6=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m @@ -141,7 +139,6 @@ CONFIG_SKY2=m CONFIG_GELIC_NET=m CONFIG_GELIC_WIRELESS=y CONFIG_SPIDER_NET=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO_I8042 is not set @@ -149,8 +146,6 @@ CONFIG_SPIDER_NET=y CONFIG_SERIAL_NONSTANDARD=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_TXX9_NR_UARTS=2 -CONFIG_SERIAL_TXX9_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y CONFIG_HVC_RTAS=y CONFIG_IPMI_HANDLER=m @@ -159,7 +154,6 @@ CONFIG_IPMI_SI=m CONFIG_IPMI_WATCHDOG=m CONFIG_IPMI_POWEROFF=m # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_WATCHDOG=y # CONFIG_VGA_CONSOLE is not set @@ -207,7 +201,6 @@ CONFIG_NLS_ISO8859_13=m CONFIG_NLS_ISO8859_14=m CONFIG_NLS_ISO8859_15=m # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MUTEXES=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index 1f6f90cd8aff..a203b1cf67d3 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -16,6 +16,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_PARTITION_ADVANCED=y CONFIG_MAC_PARTITION=y # CONFIG_PPC_PMAC is not set +CONFIG_GEN_RTC=y CONFIG_HIGHMEM=y CONFIG_BINFMT_MISC=y CONFIG_IRQ_ALL_CPUS=y @@ -79,7 +80,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set CONFIG_NVRAM=y -CONFIG_GEN_RTC=y # CONFIG_HWMON is not set CONFIG_FB=y CONFIG_FIRMWARE_EDID=y @@ -124,5 +124,4 @@ CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_CRYPTO_CBC=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/ep8248e_defconfig b/arch/powerpc/configs/ep8248e_defconfig index 3403b85f9d81..2e6c8a45ae88 100644 --- a/arch/powerpc/configs/ep8248e_defconfig +++ b/arch/powerpc/configs/ep8248e_defconfig @@ -70,5 +70,4 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/ep88xc_defconfig b/arch/powerpc/configs/ep88xc_defconfig index 95411aeeeb8d..7cb590e8f8fd 100644 --- a/arch/powerpc/configs/ep88xc_defconfig +++ b/arch/powerpc/configs/ep88xc_defconfig @@ -14,6 +14,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set CONFIG_PPC_EP88XC=y CONFIG_8xx_COPYBACK=y +CONFIG_GEN_RTC=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set CONFIG_NET=y @@ -45,7 +46,6 @@ CONFIG_LXT_PHY=y # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y # CONFIG_HWMON is not set # CONFIG_USB_SUPPORT is not set # CONFIG_DNOTIFY is not set diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index e18f2e06553f..e084fa548d73 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -4,7 +4,6 @@ CONFIG_SMP=y CONFIG_NR_CPUS=4 CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -25,6 +24,7 @@ CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_PMAC64=y +CONFIG_GEN_RTC=y CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y CONFIG_PCI_MSI=y @@ -115,7 +115,6 @@ CONFIG_USB_USBNET=m # CONFIG_USB_NET_NET1080 is not set # CONFIG_USB_NET_CDC_SUBSET is not set # CONFIG_USB_NET_ZAURUS is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_JOYDEV=m CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set @@ -123,7 +122,6 @@ CONFIG_INPUT_EVDEV=y # CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y CONFIG_AGP=m @@ -213,20 +211,20 @@ CONFIG_USB_SERIAL_CYBERJACK=m CONFIG_USB_SERIAL_XIRCOM=m CONFIG_USB_SERIAL_OMNINET=m CONFIG_USB_APPLEDISPLAY=m -CONFIG_FS_DAX=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_FS=y CONFIG_REISERFS_FS=y CONFIG_REISERFS_FS_XATTR=y CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_POSIX_ACL=y +CONFIG_FS_DAX=y CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -254,14 +252,12 @@ CONFIG_NLS_ISO8859_1=y CONFIG_NLS_ISO8859_15=y CONFIG_NLS_UTF8=y CONFIG_CRC_T10DIF=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MUTEXES=y CONFIG_LATENCYTOP=y CONFIG_BOOTX_TEXT=y CONFIG_PPC_EARLY_DEBUG=y -CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y @@ -276,5 +272,4 @@ CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/gamecube_defconfig b/arch/powerpc/configs/gamecube_defconfig index c0eec4a5df4e..79bbc8238b32 100644 --- a/arch/powerpc/configs/gamecube_defconfig +++ b/arch/powerpc/configs/gamecube_defconfig @@ -45,7 +45,6 @@ CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_NETDEVICES=y # CONFIG_WLAN is not set CONFIG_INPUT_FF_MEMLESS=m -# CONFIG_INPUT_MOUSEDEV is not set CONFIG_INPUT_JOYDEV=y CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set @@ -54,7 +53,6 @@ CONFIG_INPUT_JOYSTICK=y # CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set CONFIG_LEGACY_PTY_COUNT=64 -# CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y diff --git a/arch/powerpc/configs/holly_defconfig b/arch/powerpc/configs/holly_defconfig index e56e80090529..71d8d2430b6c 100644 --- a/arch/powerpc/configs/holly_defconfig +++ b/arch/powerpc/configs/holly_defconfig @@ -11,6 +11,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_EMBEDDED6xx=y CONFIG_PPC_HOLLY=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=ttyS0,115200" @@ -37,7 +38,6 @@ CONFIG_NETDEVICES=y CONFIG_VORTEX=y CONFIG_TSI108_ETH=y CONFIG_PHYLIB=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -49,7 +49,6 @@ CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig index b413c19d7031..477794c41d50 100644 --- a/arch/powerpc/configs/linkstation_defconfig +++ b/arch/powerpc/configs/linkstation_defconfig @@ -26,7 +26,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_IPV6 is not set CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m -CONFIG_NF_CT_PROTO_SCTP=m CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m @@ -79,7 +78,6 @@ CONFIG_NET_TULIP=y CONFIG_TULIP=y CONFIG_TULIP_MMIO=y CONFIG_R8169=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -142,4 +140,3 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig index c4018179e219..078cdb427fc9 100644 --- a/arch/powerpc/configs/maple_defconfig +++ b/arch/powerpc/configs/maple_defconfig @@ -3,7 +3,6 @@ CONFIG_SMP=y CONFIG_NR_CPUS=4 CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -24,6 +23,7 @@ CONFIG_MAC_PARTITION=y # CONFIG_PPC_PMAC is not set CONFIG_PPC_MAPLE=y CONFIG_UDBG_RTAS_CONSOLE=y +CONFIG_GEN_RTC=y CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y CONFIG_PCI_MSI=y @@ -53,9 +53,6 @@ CONFIG_AMD8111_ETH=y CONFIG_TIGON3=y CONFIG_E1000=y CONFIG_USB_PEGASUS=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1600 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=1200 # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -63,7 +60,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_HVC_RTAS=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y @@ -100,8 +96,8 @@ CONFIG_USB_SERIAL_KEYSPAN_USA49W=y CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y CONFIG_USB_SERIAL_TI=m CONFIG_EXT2_FS=y -CONFIG_FS_DAX=y CONFIG_EXT4_FS=y +CONFIG_FS_DAX=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_PROC_KCORE=y @@ -127,5 +123,4 @@ CONFIG_BOOTX_TEXT=y CONFIG_PPC_EARLY_DEBUG=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig index 197acaa026eb..5d5f08e5b8d9 100644 --- a/arch/powerpc/configs/mgcoge_defconfig +++ b/arch/powerpc/configs/mgcoge_defconfig @@ -46,7 +46,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_NETDEVICES=y CONFIG_FS_ENET=y CONFIG_FS_ENET_MDIO_FCC=y -CONFIG_FIXED_PHY=y # CONFIG_WLAN is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set @@ -83,5 +82,4 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_BDI_SWITCH=y CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index 0b4854cf26cb..10be5773ad5d 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -12,6 +12,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set # CONFIG_PPC_CHRP is not set CONFIG_PPC_MPC512x=y +CONFIG_MPC512x_LPBFIFO=y CONFIG_MPC5121_ADS=y CONFIG_MPC512x_GENERIC=y CONFIG_PDM360NG=y @@ -61,25 +62,22 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_SG=y CONFIG_NETDEVICES=y CONFIG_FS_ENET=y -CONFIG_MARVELL_PHY=y -CONFIG_DAVICOM_PHY=y -CONFIG_QSEMI_PHY=y -CONFIG_LXT_PHY=y -CONFIG_CICADA_PHY=y -CONFIG_VITESSE_PHY=y -CONFIG_SMSC_PHY=y +CONFIG_MDIO_BITBANG=y CONFIG_BROADCOM_PHY=y +CONFIG_CICADA_PHY=y +CONFIG_DAVICOM_PHY=y CONFIG_ICPLUS_PHY=y -CONFIG_REALTEK_PHY=y +CONFIG_LSI_ET1011C_PHY=y +CONFIG_LXT_PHY=y +CONFIG_MARVELL_PHY=y CONFIG_NATIONAL_PHY=y +CONFIG_QSEMI_PHY=y +CONFIG_REALTEK_PHY=y +CONFIG_SMSC_PHY=y CONFIG_STE10XP=y -CONFIG_LSI_ET1011C_PHY=y -CONFIG_FIXED_PHY=y -CONFIG_MDIO_BITBANG=y +CONFIG_VITESSE_PHY=y # CONFIG_WLAN is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=y -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_MPC52xx=y CONFIG_SERIAL_MPC52xx_CONSOLE=y CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200 @@ -111,10 +109,9 @@ CONFIG_RTC_DRV_M41T80=y CONFIG_RTC_DRV_MPC5121=y CONFIG_DMADEVICES=y CONFIG_MPC512X_DMA=y -CONFIG_MPC512x_LPBFIFO=y -CONFIG_FS_DAX=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y +CONFIG_FS_DAX=y # CONFIG_DNOTIFY is not set CONFIG_VFAT_FS=y CONFIG_TMPFS=y @@ -126,5 +123,4 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig index 88336d0df0d6..7a2b2aa37def 100644 --- a/arch/powerpc/configs/mpc5200_defconfig +++ b/arch/powerpc/configs/mpc5200_defconfig @@ -50,7 +50,6 @@ CONFIG_NETDEVICES=y CONFIG_FEC_MPC52xx=y CONFIG_AMD_PHY=y CONFIG_LXT_PHY=y -CONFIG_FIXED_PHY=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -71,12 +70,10 @@ CONFIG_SENSORS_LM87=m CONFIG_WATCHDOG=y CONFIG_MFD_SM501=m CONFIG_DRM=y -CONFIG_FB=y CONFIG_FB_FOREIGN_ENDIAN=y CONFIG_FB_RADEON=y CONFIG_FB_SM501=m # CONFIG_VGA_CONSOLE is not set -CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y @@ -130,4 +127,3 @@ CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/mpc7448_hpc2_defconfig b/arch/powerpc/configs/mpc7448_hpc2_defconfig index d933326b4cf9..4b14c02b437c 100644 --- a/arch/powerpc/configs/mpc7448_hpc2_defconfig +++ b/arch/powerpc/configs/mpc7448_hpc2_defconfig @@ -11,6 +11,7 @@ CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_PMAC is not set CONFIG_EMBEDDED6xx=y CONFIG_MPC7448HPC2=y +CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y # CONFIG_SECCOMP is not set CONFIG_NET=y @@ -38,7 +39,6 @@ CONFIG_8139TOO=y # CONFIG_8139TOO_PIO is not set CONFIG_TSI108_ETH=y CONFIG_PHYLIB=y -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -46,7 +46,6 @@ CONFIG_PHYLIB=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -54,4 +53,3 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_CRC_T10DIF=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/mpc8272_ads_defconfig b/arch/powerpc/configs/mpc8272_ads_defconfig index 4cb0f617c0d6..b1e88b64536b 100644 --- a/arch/powerpc/configs/mpc8272_ads_defconfig +++ b/arch/powerpc/configs/mpc8272_ads_defconfig @@ -77,5 +77,4 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 6574477fd726..d1b82035d35f 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -21,7 +21,6 @@ CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y CONFIG_SBC834x=y CONFIG_ASP834x=y -CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_MATH_EMULATION=y CONFIG_PCI=y @@ -60,13 +59,11 @@ CONFIG_SATA_SIL=y CONFIG_NETDEVICES=y CONFIG_UCC_GETH=y CONFIG_GIANFAR=y -CONFIG_MARVELL_PHY=y CONFIG_DAVICOM_PHY=y -CONFIG_VITESSE_PHY=y CONFIG_ICPLUS_PHY=y -CONFIG_FIXED_PHY=y +CONFIG_MARVELL_PHY=y +CONFIG_VITESSE_PHY=y CONFIG_INPUT_FF_MEMLESS=m -# CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -99,6 +96,7 @@ CONFIG_USB_EHCI_FSL=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=y CONFIG_RTC_DRV_DS1374=y +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y CONFIG_PROC_KCORE=y @@ -109,7 +107,5 @@ CONFIG_ROOT_NFS=y CONFIG_CRC_T10DIF=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m -CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_TALITOS=y diff --git a/arch/powerpc/configs/mpc866_ads_defconfig b/arch/powerpc/configs/mpc866_ads_defconfig index 998454471a48..f1f176c29fa3 100644 --- a/arch/powerpc/configs/mpc866_ads_defconfig +++ b/arch/powerpc/configs/mpc866_ads_defconfig @@ -14,6 +14,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_MPC86XADS=y CONFIG_8xx_COPYBACK=y CONFIG_8xx_CPU6=y +CONFIG_GEN_RTC=y CONFIG_HZ_1000=y CONFIG_MATH_EMULATION=y # CONFIG_SECCOMP is not set @@ -28,12 +29,10 @@ CONFIG_SYN_COOKIES=y CONFIG_BLK_DEV_LOOP=y CONFIG_NETDEVICES=y CONFIG_FS_ENET=y -CONFIG_FIXED_PHY=y # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT4_FS=y @@ -43,4 +42,3 @@ CONFIG_NFS_FS=y CONFIG_ROOT_NFS=y CONFIG_CRC_CCITT=y CONFIG_CRC32_SLICEBY4=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/mpc86xx_basic_defconfig b/arch/powerpc/configs/mpc86xx_basic_defconfig index 3283f0586e11..67bd1fa036ee 100644 --- a/arch/powerpc/configs/mpc86xx_basic_defconfig +++ b/arch/powerpc/configs/mpc86xx_basic_defconfig @@ -1,11 +1,11 @@ -CONFIG_HIGHMEM=y -CONFIG_KEXEC=y CONFIG_PPC_86xx=y -CONFIG_PROC_KCORE=y +CONFIG_MPC8641_HPCN=y +CONFIG_SBC8641D=y +CONFIG_MPC8610_HPCD=y CONFIG_GEF_PPC9A=y CONFIG_GEF_SBC310=y CONFIG_GEF_SBC610=y -CONFIG_MPC8610_HPCD=y -CONFIG_MPC8641_HPCN=y -CONFIG_SBC8641D=y CONFIG_MVME7100=y +CONFIG_HIGHMEM=y +CONFIG_KEXEC=y +CONFIG_PROC_KCORE=y diff --git a/arch/powerpc/configs/mpc885_ads_defconfig b/arch/powerpc/configs/mpc885_ads_defconfig index 91f53f1bec5d..ec3fcc2bf737 100644 --- a/arch/powerpc/configs/mpc885_ads_defconfig +++ b/arch/powerpc/configs/mpc885_ads_defconfig @@ -13,6 +13,7 @@ CONFIG_EXPERT=y CONFIG_PARTITION_ADVANCED=y # CONFIG_IOSCHED_CFQ is not set CONFIG_8xx_COPYBACK=y +CONFIG_GEN_RTC=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set CONFIG_NET=y @@ -51,7 +52,6 @@ CONFIG_DAVICOM_PHY=y # CONFIG_LEGACY_PTYS is not set CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y -CONFIG_GEN_RTC=y # CONFIG_HWMON is not set # CONFIG_USB_SUPPORT is not set # CONFIG_DNOTIFY is not set diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig index 139add95a16a..63e38c7220f1 100644 --- a/arch/powerpc/configs/mvme5100_defconfig +++ b/arch/powerpc/configs/mvme5100_defconfig @@ -35,7 +35,6 @@ CONFIG_IP_PNP_BOOTP=y # CONFIG_IPV6 is not set CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m -CONFIG_NF_CT_PROTO_SCTP=m CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m @@ -70,7 +69,6 @@ CONFIG_TUN=m # CONFIG_NET_VENDOR_3COM is not set CONFIG_E100=y # CONFIG_WLAN is not set -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set @@ -130,4 +128,3 @@ CONFIG_CRYPTO_DES=y CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index fe43ff47bd2f..8cf4a46bef86 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -3,7 +3,6 @@ CONFIG_ALTIVEC=y CONFIG_SMP=y CONFIG_NR_CPUS=2 CONFIG_SYSVIPC=y -CONFIG_FHANDLE=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y @@ -145,6 +144,7 @@ CONFIG_EDAC=y CONFIG_EDAC_PASEMI=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=y +CONFIG_RAS=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -167,7 +167,6 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y CONFIG_CRC_CCITT=y CONFIG_PRINTK_TIME=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y @@ -175,7 +174,5 @@ CONFIG_DETECT_HUNG_TASK=y CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_CRYPTO_MD4=y -CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y CONFIG_CRYPTO_BLOWFISH=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index fc1e7a7388b8..8e798b1fbc99 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -21,6 +21,7 @@ CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_PMAC=y CONFIG_PPC601_SYNC_FIX=y +CONFIG_GEN_RTC=y CONFIG_HIGHMEM=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y @@ -179,10 +180,10 @@ CONFIG_PPP_ASYNC=y CONFIG_PPP_SYNC_TTY=m CONFIG_USB_USBNET=m # CONFIG_USB_NET_CDC_SUBSET is not set -CONFIG_PRISM54=m CONFIG_B43=m CONFIG_B43LEGACY=m CONFIG_P54_COMMON=m +CONFIG_PRISM54=m CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set # CONFIG_MOUSE_PS2 is not set @@ -193,7 +194,6 @@ CONFIG_SERIAL_8250=m CONFIG_SERIAL_PMACZILOG=m CONFIG_SERIAL_PMACZILOG_TTYS=y CONFIG_NVRAM=y -CONFIG_GEN_RTC=y CONFIG_I2C_CHARDEV=m CONFIG_APM_POWER=y CONFIG_BATTERY_PMU=y @@ -201,8 +201,9 @@ CONFIG_HWMON=m CONFIG_AGP=m CONFIG_AGP_UNINORTH=m CONFIG_DRM=m -CONFIG_DRM_R128=m CONFIG_DRM_RADEON=m +CONFIG_DRM_LEGACY=y +CONFIG_DRM_R128=m CONFIG_FB=y CONFIG_FB_OF=y CONFIG_FB_CONTROL=y @@ -300,8 +301,6 @@ CONFIG_NFSD_V4=y CONFIG_NLS_CODEPAGE_437=m CONFIG_NLS_ISO8859_1=m CONFIG_CRC_T10DIF=y -CONFIG_LIBCRC32C=m -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y @@ -310,7 +309,6 @@ CONFIG_XMON=y CONFIG_XMON_DEFAULT=y CONFIG_BOOTX_TEXT=y CONFIG_PPC_EARLY_DEBUG=y -CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_SHA512=m @@ -325,4 +323,3 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_DEFLATE=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 0695ce047d56..caee834760d2 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -1,10 +1,8 @@ CONFIG_PPC64=y -CONFIG_SMP=y CONFIG_NR_CPUS=2048 CONFIG_CPU_LITTLE_ENDIAN=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_NO_HZ=y @@ -26,8 +24,8 @@ CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_BPF=y CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_BPF_SYSCALL=y @@ -62,7 +60,6 @@ CONFIG_PPC_64K_PAGES=y CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y CONFIG_PM=y -CONFIG_PCI_MSI=y CONFIG_HOTPLUG_PCI=y CONFIG_NET=y CONFIG_PACKET=y @@ -158,7 +155,6 @@ CONFIG_NETCONSOLE=y CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m -CONFIG_VHOST_NET=m CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y @@ -184,16 +180,13 @@ CONFIG_PPP_DEFLATE=m CONFIG_PPPOE=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=m CONFIG_INPUT_MISC=y # CONFIG_SERIO_SERPORT is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_JSM=m CONFIG_VIRTIO_CONSOLE=m -CONFIG_POWERNV_OP_PANEL=m CONFIG_IPMI_HANDLER=y CONFIG_IPMI_DEVICE_INTERFACE=y CONFIG_IPMI_POWERNV=y @@ -293,11 +286,15 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y +CONFIG_FTRACE=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_GRAPH_TRACER=y CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y CONFIG_CODE_PATCHING_SELFTEST=y CONFIG_FTR_FIXUP_SELFTEST=y CONFIG_MSI_BITMAP_SELFTEST=y @@ -309,6 +306,7 @@ CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_CRC32C_VPMSUM=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m @@ -317,14 +315,13 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_VMX=y -CONFIG_CRYPTO_DEV_VMX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m +CONFIG_VHOST_NET=m diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig index 370c0bbcff71..10fb1df63b46 100644 --- a/arch/powerpc/configs/ppc40x_defconfig +++ b/arch/powerpc/configs/ppc40x_defconfig @@ -51,9 +51,9 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_XILINX_HWICAP=m CONFIG_I2C=m @@ -85,4 +85,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig index 2766e8f590bc..66dd6bf45cde 100644 --- a/arch/powerpc/configs/ppc44x_defconfig +++ b/arch/powerpc/configs/ppc44x_defconfig @@ -68,9 +68,9 @@ CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_SERIAL_8250_PCI is not set CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=y CONFIG_SERIAL_UARTLITE_CONSOLE=y -CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set CONFIG_XILINX_HWICAP=m CONFIG_I2C=m @@ -94,7 +94,6 @@ CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_JFFS2_FS=y CONFIG_UBIFS_FS=m -CONFIG_LOGFS=m CONFIG_CRAMFS=y CONFIG_SQUASHFS=m CONFIG_SQUASHFS_XATTR=y @@ -108,6 +107,5 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set CONFIG_VIRTUALIZATION=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 5175028c56ce..791db775a09c 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -1,8 +1,6 @@ CONFIG_PPC64=y -CONFIG_SMP=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y @@ -28,9 +26,10 @@ CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_PARTITION_ADVANCED=y CONFIG_PPC_SPLPAR=y +CONFIG_DTL=y CONFIG_SCANLOG=m CONFIG_PPC_SMLPAR=y -CONFIG_DTL=y +CONFIG_IBMEBUS=y CONFIG_PPC_MAPLE=y CONFIG_PPC_PASEMI=y CONFIG_PPC_PASEMI_IOMMU=y @@ -41,9 +40,8 @@ CONFIG_PS3_FLASH=m CONFIG_PS3_LPM=m CONFIG_PPC_IBM_CELL_BLADE=y CONFIG_RTAS_FLASH=m -CONFIG_IBMEBUS=y -CONFIG_CPU_FREQ_PMAC64=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_PMAC64=y CONFIG_HZ_100=y CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y @@ -51,14 +49,15 @@ CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_IRQ_ALL_CPUS=y -CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y +CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y -CONFIG_PCCARD=y -CONFIG_ELECTRA_CF=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_RPA=m CONFIG_HOTPLUG_PCI_RPA_DLPAR=m +CONFIG_PCCARD=y +CONFIG_ELECTRA_CF=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -154,7 +153,6 @@ CONFIG_DUMMY=m CONFIG_NETCONSOLE=y CONFIG_TUN=m CONFIG_VIRTIO_NET=m -CONFIG_VHOST_NET=m CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y @@ -181,15 +179,14 @@ CONFIG_SUNGEM=y CONFIG_GELIC_NET=m CONFIG_GELIC_WIRELESS=y CONFIG_SPIDER_NET=m -CONFIG_MARVELL_PHY=y CONFIG_BROADCOM_PHY=m +CONFIG_MARVELL_PHY=y CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m CONFIG_PPPOE=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=m CONFIG_INPUT_MISC=y CONFIG_INPUT_PCSPKR=m @@ -197,7 +194,6 @@ CONFIG_INPUT_PCSPKR=m CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_ICOM=m -CONFIG_SERIAL_TXX9_CONSOLE=y CONFIG_SERIAL_JSM=m CONFIG_HVC_CONSOLE=y CONFIG_HVC_RTAS=y @@ -250,6 +246,9 @@ CONFIG_USB_EHCI_HCD=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_STORAGE=m CONFIG_USB_APPLEDISPLAY=m +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=m +CONFIG_LEDS_POWERNV=m CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_MAD=m CONFIG_INFINIBAND_USER_ACCESS=m @@ -267,7 +266,7 @@ CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=y CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m -CONFIG_FS_DAX=y +CONFIG_RAS=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -287,6 +286,7 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m +CONFIG_FS_DAX=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m @@ -324,12 +324,15 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_DEBUG_MUTEXES=y CONFIG_LATENCYTOP=y +CONFIG_FTRACE=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_GRAPH_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y CONFIG_CODE_PATCHING_SELFTEST=y CONFIG_FTR_FIXUP_SELFTEST=y CONFIG_MSI_BITMAP_SELFTEST=y @@ -342,6 +345,7 @@ CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_CRC32C_VPMSUM=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m @@ -350,19 +354,14 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y -CONFIG_CRYPTO_DEV_VMX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=m -CONFIG_LEDS_POWERNV=m +CONFIG_VHOST_NET=m diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 6340e6c53c54..d0fe0f8f77c2 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -3,7 +3,6 @@ CONFIG_PPC_BOOK3E_64=y CONFIG_SMP=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_TASKSTATS=y @@ -30,8 +29,8 @@ CONFIG_BINFMT_MISC=m CONFIG_IRQ_ALL_CPUS=y CONFIG_SPARSEMEM_MANUAL=y CONFIG_PCI_MSI=y -CONFIG_PCCARD=y CONFIG_HOTPLUG_PCI=y +CONFIG_PCCARD=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -108,15 +107,14 @@ CONFIG_E100=y CONFIG_E1000=y CONFIG_IXGB=m CONFIG_SUNGEM=y -CONFIG_MARVELL_PHY=y CONFIG_BROADCOM_PHY=m +CONFIG_MARVELL_PHY=y CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m CONFIG_PPPOE=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=m CONFIG_INPUT_MISC=y # CONFIG_SERIO_SERPORT is not set @@ -172,10 +170,8 @@ CONFIG_INFINIBAND=m CONFIG_INFINIBAND_MTHCA=m CONFIG_INFINIBAND_IPOIB=m CONFIG_INFINIBAND_ISER=m -CONFIG_EDAC=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_DS1307=y -CONFIG_FS_DAX=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -192,6 +188,7 @@ CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_POSIX_ACL=y +CONFIG_FS_DAX=y CONFIG_AUTOFS4_FS=m CONFIG_ISO9660_FS=y CONFIG_UDF_FS=m @@ -251,5 +248,4 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 18d0d60dadbf..ae6eba482d75 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -11,10 +11,10 @@ CONFIG_TASK_DELAY_ACCT=y CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_CGROUPS=y -CONFIG_CGROUP_DEVICE=y -CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_SCHED=y CONFIG_RT_GROUP_SCHED=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set @@ -61,7 +61,7 @@ CONFIG_SBC8641D=y CONFIG_MPC8610_HPCD=y CONFIG_GEF_SBC610=y CONFIG_CPU_FREQ=y -CONFIG_CPU_FREQ_STAT=m +CONFIG_CPU_FREQ_STAT=y CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=m @@ -70,7 +70,6 @@ CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m CONFIG_CPU_FREQ_PMAC=y CONFIG_TAU=y CONFIG_TAU_AVERAGE=y -CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_MCU_MPC8349EMITX=y CONFIG_HIGHMEM=y @@ -141,7 +140,6 @@ CONFIG_NETFILTER=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_UDPLITE=m CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m @@ -187,7 +185,6 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m -CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -195,7 +192,6 @@ CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m CONFIG_NF_CONNTRACK_IPV4=m -# CONFIG_NF_CONNTRACK_PROC_COMPAT is not set CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -334,9 +330,7 @@ CONFIG_BT_BNEP_MC_FILTER=y CONFIG_BT_BNEP_PROTO_FILTER=y CONFIG_BT_HIDP=m CONFIG_BT_HCIUART=m -CONFIG_BT_HCIUART_H4=y CONFIG_BT_HCIUART_BCSP=y -CONFIG_BT_HCIUART_LL=y CONFIG_BT_HCIBCM203X=m CONFIG_BT_HCIBPA10X=m CONFIG_BT_HCIBFUSB=m @@ -370,7 +364,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_CDROM_PKTCDVD=m CONFIG_VIRTIO_BLK=m -CONFIG_BLK_DEV_HD=y CONFIG_ENCLOSURE_SERVICES=m CONFIG_SENSORS_TSL2550=m CONFIG_EEPROM_AT24=m @@ -548,16 +541,16 @@ CONFIG_PCMCIA_XIRC2PS=m CONFIG_FDDI=y CONFIG_SKFP=m CONFIG_NET_SB1000=m -CONFIG_MARVELL_PHY=m -CONFIG_DAVICOM_PHY=m -CONFIG_QSEMI_PHY=m -CONFIG_LXT_PHY=m -CONFIG_CICADA_PHY=m -CONFIG_VITESSE_PHY=m -CONFIG_SMSC_PHY=m CONFIG_BROADCOM_PHY=m +CONFIG_CICADA_PHY=m +CONFIG_DAVICOM_PHY=m CONFIG_ICPLUS_PHY=m +CONFIG_LXT_PHY=m +CONFIG_MARVELL_PHY=m +CONFIG_QSEMI_PHY=m CONFIG_REALTEK_PHY=m +CONFIG_SMSC_PHY=m +CONFIG_VITESSE_PHY=m CONFIG_PLIP=m CONFIG_PPP_DEFLATE=m CONFIG_PPP_FILTER=y @@ -585,7 +578,6 @@ CONFIG_USB_ALI_M5632=y CONFIG_USB_AN2720=y CONFIG_USB_EPSON2888=y CONFIG_USB_KC2190=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_JOYDEV=m CONFIG_INPUT_EVDEV=y CONFIG_MOUSE_SERIAL=m @@ -647,7 +639,6 @@ CONFIG_SYNCLINKMP=m CONFIG_SYNCLINK_GT=m CONFIG_NOZOMI=m CONFIG_N_HDLC=m -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_CS=m @@ -657,13 +648,13 @@ CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y +CONFIG_SERIAL_OF_PLATFORM=y CONFIG_SERIAL_UARTLITE=m CONFIG_SERIAL_PMACZILOG=m CONFIG_SERIAL_MPC52xx=y CONFIG_SERIAL_MPC52xx_CONSOLE=y CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200 CONFIG_SERIAL_JSM=m -CONFIG_SERIAL_OF_PLATFORM=y CONFIG_PRINTER=m CONFIG_LP_CONSOLE=y CONFIG_PPDEV=m @@ -748,9 +739,10 @@ CONFIG_MFD_SM501_GPIO=y CONFIG_AGP=y CONFIG_AGP_UNINORTH=y CONFIG_DRM=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_LEGACY=y CONFIG_DRM_TDFX=m CONFIG_DRM_R128=m -CONFIG_DRM_RADEON=m CONFIG_DRM_MGA=m CONFIG_DRM_SIS=m CONFIG_DRM_VIA=m @@ -899,7 +891,7 @@ CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=m -CONFIG_USB_EHCI_FSL=y +CONFIG_USB_EHCI_FSL=m CONFIG_USB_OHCI_HCD=m CONFIG_USB_OHCI_HCD_PPC_OF_BE=y CONFIG_USB_OHCI_HCD_PPC_OF_LE=y @@ -967,7 +959,6 @@ CONFIG_USB_ADUTUX=m CONFIG_USB_SEVSEG=m CONFIG_USB_LEGOTOWER=m CONFIG_USB_LCD=m -CONFIG_USB_LED=m CONFIG_USB_IDMOUSE=m CONFIG_USB_FTDI_ELAN=m CONFIG_USB_APPLEDISPLAY=m @@ -1020,15 +1011,14 @@ CONFIG_UIO_CIF=m CONFIG_UIO_PDRV_GENIRQ=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m -CONFIG_FS_DAX=y +CONFIG_QUICC_ENGINE=y CONFIG_EXT2_FS=m CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT4_FS=m +CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y -CONFIG_EXT4_FS=y CONFIG_JBD2_DEBUG=y CONFIG_REISERFS_FS=m CONFIG_REISERFS_PROC_INFO=y @@ -1042,6 +1032,7 @@ CONFIG_XFS_FS=m CONFIG_XFS_QUOTA=y CONFIG_XFS_POSIX_ACL=y CONFIG_GFS2_FS=m +CONFIG_FS_DAX=y CONFIG_QUOTA_NETLINK_INTERFACE=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m @@ -1146,7 +1137,6 @@ CONFIG_DEBUG_VM=y CONFIG_DEBUG_HIGHMEM=y CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_DEBUG_SHIRQ=y -CONFIG_TIMER_STATS=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y @@ -1173,7 +1163,6 @@ CONFIG_SECURITY_SELINUX=y CONFIG_SECURITY_SELINUX_BOOTPARAM=y CONFIG_SECURITY_SELINUX_DISABLE=y CONFIG_CRYPTO_TEST=m -CONFIG_CRYPTO_GCM=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -1201,7 +1190,6 @@ CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_HIFN_795X=m CONFIG_CRYPTO_DEV_HIFN_795X_RNG=y CONFIG_CRYPTO_DEV_TALITOS=m diff --git a/arch/powerpc/configs/pq2fads_defconfig b/arch/powerpc/configs/pq2fads_defconfig index 50b2bad51d0a..0ededa8c837d 100644 --- a/arch/powerpc/configs/pq2fads_defconfig +++ b/arch/powerpc/configs/pq2fads_defconfig @@ -79,4 +79,3 @@ CONFIG_CRYPTO_ECB=y CONFIG_CRYPTO_PCBC=y CONFIG_CRYPTO_MD5=y CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index ee0ec5a682fc..2efa025bf483 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -5,7 +5,6 @@ CONFIG_SMP=y CONFIG_NR_CPUS=2 CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y @@ -94,7 +93,6 @@ CONFIG_USB_USBNET=m # CONFIG_USB_NET_CDC_SUBSET is not set # CONFIG_USB_NET_ZAURUS is not set CONFIG_INPUT_FF_MEMLESS=m -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_JOYDEV=m CONFIG_INPUT_EVDEV=m # CONFIG_INPUT_KEYBOARD is not set @@ -161,7 +159,6 @@ CONFIG_NLS_ISO8859_1=y CONFIG_CRC_CCITT=m CONFIG_CRC_T10DIF=y CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_STACKOVERFLOW=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 1a61aa20dfba..3d935969e5a2 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -1,11 +1,8 @@ CONFIG_PPC64=y -CONFIG_SMP=y CONFIG_NR_CPUS=2048 CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_FHANDLE=y CONFIG_AUDIT=y -CONFIG_AUDITSYSCALL=y CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y @@ -18,17 +15,16 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 CONFIG_NUMA_BALANCING=y -CONFIG_NUMA_BALANCING_DEFAULT_ENABLED=y CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CGROUP_SCHED=y CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_DEVICE=y CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_BPF=y -CONFIG_MEMCG=y -CONFIG_MEMCG_SWAP=y CONFIG_CGROUP_PERF=y -CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_BPF=y CONFIG_USER_NS=y CONFIG_BLK_DEV_INITRD=y CONFIG_BPF_SYSCALL=y @@ -43,12 +39,12 @@ CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y CONFIG_PARTITION_ADVANCED=y CONFIG_PPC_SPLPAR=y +CONFIG_DTL=y CONFIG_SCANLOG=m CONFIG_PPC_SMLPAR=y -CONFIG_DTL=y +CONFIG_IBMEBUS=y # CONFIG_PPC_PMAC is not set CONFIG_RTAS_FLASH=m -CONFIG_IBMEBUS=y CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y CONFIG_HZ_100=y CONFIG_BINFMT_MISC=m @@ -155,7 +151,6 @@ CONFIG_NETCONSOLE=y CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m -CONFIG_VHOST_NET=m CONFIG_VORTEX=m CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y @@ -183,12 +178,10 @@ CONFIG_PPP_DEFLATE=m CONFIG_PPPOE=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_EVDEV=m CONFIG_INPUT_MISC=y CONFIG_INPUT_PCSPKR=m # CONFIG_SERIO_SERPORT is not set -CONFIG_DEVPTS_MULTIPLE_INSTANCES=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_ICOM=m @@ -198,8 +191,6 @@ CONFIG_HVC_RTAS=y CONFIG_HVCS=m CONFIG_VIRTIO_CONSOLE=m CONFIG_IBM_BSR=m -CONFIG_RTC_CLASS=y -CONFIG_RTC_DRV_GENERIC=y CONFIG_RAW_DRIVER=y CONFIG_MAX_RAW_DEVS=1024 CONFIG_FB=y @@ -227,6 +218,9 @@ CONFIG_USB_EHCI_HCD=y # CONFIG_USB_EHCI_HCD_PPC_OF is not set CONFIG_USB_OHCI_HCD=y CONFIG_USB_STORAGE=m +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=m +CONFIG_LEDS_POWERNV=m CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_MAD=m CONFIG_INFINIBAND_USER_ACCESS=m @@ -238,9 +232,10 @@ CONFIG_INFINIBAND_IPOIB=m CONFIG_INFINIBAND_IPOIB_CM=y CONFIG_INFINIBAND_SRP=m CONFIG_INFINIBAND_ISER=m +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_GENERIC=y CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m -CONFIG_FS_DAX=y CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_POSIX_ACL=y @@ -256,6 +251,7 @@ CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_NILFS2_FS=m +CONFIG_FS_DAX=y CONFIG_AUTOFS4_FS=m CONFIG_FUSE_FS=m CONFIG_OVERLAY_FS=m @@ -291,11 +287,14 @@ CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_STACK_USAGE=y CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_LOCKUP_DETECTOR=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y +CONFIG_FTRACE=y +CONFIG_FUNCTION_TRACER=y +CONFIG_FUNCTION_GRAPH_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_UPROBE_EVENT=y CONFIG_CODE_PATCHING_SELFTEST=y CONFIG_FTR_FIXUP_SELFTEST=y CONFIG_MSI_BITMAP_SELFTEST=y @@ -306,6 +305,7 @@ CONFIG_CRYPTO_HMAC=y CONFIG_CRYPTO_CRC32C_VPMSUM=m CONFIG_CRYPTO_MD5_PPC=m CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m @@ -314,19 +314,14 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST6=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m -CONFIG_CRYPTO_SHA1_PPC=m CONFIG_CRYPTO_SERPENT=m CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m -# CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y -CONFIG_CRYPTO_DEV_VMX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=m -CONFIG_NEW_LEDS=y -CONFIG_LEDS_CLASS=m -CONFIG_LEDS_POWERNV=m +CONFIG_VHOST_NET=m diff --git a/arch/powerpc/configs/tqm8xx_defconfig b/arch/powerpc/configs/tqm8xx_defconfig index 78fddf24b5d3..cd72193fac0a 100644 --- a/arch/powerpc/configs/tqm8xx_defconfig +++ b/arch/powerpc/configs/tqm8xx_defconfig @@ -18,6 +18,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_TQM8XX=y CONFIG_8xx_COPYBACK=y # CONFIG_8xx_CPU15 is not set +CONFIG_GEN_RTC=y CONFIG_HZ_100=y # CONFIG_SECCOMP is not set CONFIG_NET=y @@ -44,7 +45,6 @@ CONFIG_MTD_PHYSMAP_OF=y CONFIG_NETDEVICES=y CONFIG_FS_ENET=y CONFIG_DAVICOM_PHY=y -CONFIG_FIXED_PHY=y # CONFIG_WLAN is not set # CONFIG_INPUT is not set # CONFIG_SERIO is not set @@ -53,7 +53,6 @@ CONFIG_FIXED_PHY=y CONFIG_SERIAL_CPM=y CONFIG_SERIAL_CPM_CONSOLE=y CONFIG_HW_RANDOM=y -CONFIG_GEN_RTC=y # CONFIG_HWMON is not set # CONFIG_USB_SUPPORT is not set # CONFIG_DNOTIFY is not set diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig index dcdd51b57783..aef41b17a8bc 100644 --- a/arch/powerpc/configs/wii_defconfig +++ b/arch/powerpc/configs/wii_defconfig @@ -55,9 +55,6 @@ CONFIG_B43_SDIO=y # CONFIG_B43_PHY_LP is not set CONFIG_B43_DEBUG=y CONFIG_INPUT_FF_MEMLESS=m -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -CONFIG_INPUT_MOUSEDEV_SCREEN_X=640 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480 CONFIG_INPUT_JOYDEV=y CONFIG_INPUT_EVDEV=y # CONFIG_KEYBOARD_ATKBD is not set @@ -68,7 +65,6 @@ CONFIG_INPUT_UINPUT=y # CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set CONFIG_LEGACY_PTY_COUNT=64 -# CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set CONFIG_NVRAM=y CONFIG_I2C=y @@ -119,5 +115,4 @@ CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_DMA_API_DEBUG=y CONFIG_PPC_EARLY_DEBUG=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 5c4fbc80dc6c..2542ea15d338 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -8,3 +8,4 @@ generic-y += mcs_spinlock.h generic-y += preempt.h generic-y += rwsem.h generic-y += vtime.h +generic-y += msi.h diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index cee3aa087653..7f2a7702596c 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -25,7 +25,7 @@ #define PPC_LCMPI stringify_in_c(cmpdi) #define PPC_LCMPLI stringify_in_c(cmpldi) #define PPC_LCMP stringify_in_c(cmpd) -#define PPC_LONG stringify_in_c(.llong) +#define PPC_LONG stringify_in_c(.8byte) #define PPC_LONG_ALIGN stringify_in_c(.balign 8) #define PPC_TLNEI stringify_in_c(tdnei) #define PPC_LLARX(t, a, b, eh) PPC_LDARX(t, a, b, eh) diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index 25d42bd3f114..9c601adfc500 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -74,13 +74,6 @@ do { \ ___p1; \ }) -/* - * This must resolve to hwsync on SMP for the context switch path. - * See _switch, and core scheduler context switch memory ordering - * comments. - */ -#define smp_mb__before_spinlock() smp_mb() - #include <asm-generic/barrier.h> #endif /* _ASM_POWERPC_BARRIER_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 7fb755880409..4d453f979553 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -294,13 +294,11 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) -extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, - pmd_t **pmdp); - int map_kernel_page(unsigned long va, phys_addr_t pa, int flags); /* Generic accessors to PTE bits */ static inline int pte_write(pte_t pte) { return !!(pte_val(pte) & _PAGE_RW);} +static inline int pte_read(pte_t pte) { return 1; } static inline int pte_dirty(pte_t pte) { return !!(pte_val(pte) & _PAGE_DIRTY); } static inline int pte_young(pte_t pte) { return !!(pte_val(pte) & _PAGE_ACCESSED); } static inline int pte_special(pte_t pte) { return !!(pte_val(pte) & _PAGE_SPECIAL); } diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 36fc7bfe9e11..f88452019114 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -40,7 +40,7 @@ * Define the address range of the kernel non-linear virtual area */ #define H_KERN_VIRT_START ASM_CONST(0xD000000000000000) -#define H_KERN_VIRT_SIZE ASM_CONST(0x0000100000000000) +#define H_KERN_VIRT_SIZE ASM_CONST(0x0000400000000000) /* 64T */ /* * The vmalloc space starts at the beginning of that region, and @@ -48,9 +48,11 @@ * (we keep a quarter for the virtual memmap) */ #define H_VMALLOC_START H_KERN_VIRT_START -#define H_VMALLOC_SIZE (H_KERN_VIRT_SIZE >> 1) +#define H_VMALLOC_SIZE ASM_CONST(0x380000000000) /* 56T */ #define H_VMALLOC_END (H_VMALLOC_START + H_VMALLOC_SIZE) +#define H_KERN_IO_START H_VMALLOC_END + /* * Region IDs */ diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h index 5c28bd6f2ae1..2d1ca488ca44 100644 --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h @@ -54,9 +54,7 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE static inline bool gigantic_page_supported(void) { - if (radix_enabled()) - return true; - return false; + return true; } #endif diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 6981a52b3887..f28d21c69f79 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -468,7 +468,7 @@ extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend, int psize, int ssize); int htab_remove_mapping(unsigned long vstart, unsigned long vend, int psize, int ssize); -extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages); +extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages); extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr); #ifdef CONFIG_PPC_PSERIES diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 5b4023c616f7..c3b00e8ff791 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -83,6 +83,9 @@ typedef struct { mm_context_id_t id; u16 user_psize; /* page size index */ + /* Number of bits in the mm_cpumask */ + atomic_t active_cpus; + /* NPU NMMU context */ struct npu_context *npu_context; @@ -97,11 +100,6 @@ typedef struct { #ifdef CONFIG_PPC_SUBPAGE_PROT struct subpage_prot_table spt; #endif /* CONFIG_PPC_SUBPAGE_PROT */ -#ifdef CONFIG_PPC_ICSWX - struct spinlock *cop_lockp; /* guard acop and cop_pid */ - unsigned long acop; /* mask of enabled coprocessor types */ - unsigned int cop_pid; /* pid value used with coprocessors */ -#endif /* CONFIG_PPC_ICSWX */ #ifdef CONFIG_PPC_64K_PAGES /* for 4K PTE fragment support */ void *pte_frag; diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index e2329db9d6f4..1fcfa425cefa 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -41,8 +41,6 @@ extern struct kmem_cache *pgtable_cache[]; pgtable_cache[(shift) - 1]; \ }) -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO - extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int); extern void pte_fragment_free(unsigned long *, int); extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index d1da415e283c..b9aff515b4de 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -272,8 +272,10 @@ extern unsigned long __vmalloc_end; extern unsigned long __kernel_virt_start; extern unsigned long __kernel_virt_size; +extern unsigned long __kernel_io_start; #define KERN_VIRT_START __kernel_virt_start #define KERN_VIRT_SIZE __kernel_virt_size +#define KERN_IO_START __kernel_io_start extern struct page *vmemmap; extern unsigned long ioremap_bot; extern unsigned long pci_io_base; @@ -298,7 +300,6 @@ extern unsigned long pci_io_base; * PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces * IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE */ -#define KERN_IO_START (KERN_VIRT_START + (KERN_VIRT_SIZE >> 1)) #define FULL_IO_SIZE 0x80000000ul #define ISA_IO_BASE (KERN_IO_START) #define ISA_IO_END (KERN_IO_START + 0x10000ul) @@ -409,6 +410,11 @@ static inline int pte_write(pte_t pte) return __pte_write(pte) || pte_savedwrite(pte); } +static inline int pte_read(pte_t pte) +{ + return !!(pte_raw(pte) & cpu_to_be64(_PAGE_READ)); +} + #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -608,9 +614,17 @@ static inline pte_t pte_mkdevmap(pte_t pte) return __pte(pte_val(pte) | _PAGE_SPECIAL|_PAGE_DEVMAP); } +/* + * This is potentially called with a pmd as the argument, in which case it's not + * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set. + * That's because the bit we use for _PAGE_DEVMAP is not reserved for software + * use in page directory entries (ie. non-ptes). + */ static inline int pte_devmap(pte_t pte) { - return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DEVMAP)); + u64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE); + + return (pte_raw(pte) & mask) == mask; } static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) @@ -1159,6 +1173,7 @@ static inline bool arch_needs_pgtable_deposit(void) return false; return true; } +extern void serialize_against_pte_lookup(struct mm_struct *mm); static inline pmd_t pmd_mkdevmap(pmd_t pmd) diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 544440b5aff3..1e5ba94e62ef 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -110,6 +110,8 @@ */ #define RADIX_VMEMMAP_BASE (RADIX_VMALLOC_END) +#define RADIX_KERN_IO_START (RADIX_KERN_VIRT_START + (RADIX_KERN_VIRT_SIZE >> 1)) + #ifndef __ASSEMBLY__ #define RADIX_PTE_TABLE_SIZE (sizeof(pte_t) << RADIX_PTE_INDEX_SIZE) #define RADIX_PMD_TABLE_SIZE (sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index cc7fbde4f53c..9b433a624bf3 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -22,22 +22,21 @@ extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end extern void radix__local_flush_tlb_mm(struct mm_struct *mm); extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize); extern void radix__tlb_flush(struct mmu_gather *tlb); #ifdef CONFIG_SMP extern void radix__flush_tlb_mm(struct mm_struct *mm); extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); -extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize); #else #define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm) #define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr) #define radix__flush_tlb_page_psize(mm,addr,p) radix__local_flush_tlb_page_psize(mm,addr,p) -#define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr) #endif +extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); +extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr); extern void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa, unsigned long page_size); extern void radix__flush_tlb_lpid(unsigned long lpid); diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 87fcc1948817..7ee763d3bea9 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -133,6 +133,7 @@ extern int do_page_fault(struct pt_regs *, unsigned long, unsigned long); extern void bad_page_fault(struct pt_regs *, unsigned long, int); extern void _exception(int, struct pt_regs *, int, unsigned long); extern void die(const char *, struct pt_regs *, long); +extern bool die_will_crash(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 5a90292afbad..d122f7f957ce 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -5,7 +5,7 @@ /* bytes per L1 cache line */ -#if defined(CONFIG_8xx) || defined(CONFIG_403GCX) +#if defined(CONFIG_PPC_8xx) || defined(CONFIG_403GCX) #define L1_CACHE_SHIFT 4 #define MAX_COPY_PREFETCH 1 #elif defined(CONFIG_PPC_E500MC) diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 52586f9956bb..eb43b5c3a7b5 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -67,6 +67,17 @@ #define ERR_DEEP_STATE_ESL_MISMATCH -2 #ifndef __ASSEMBLY__ +/* Additional SPRs that need to be saved/restored during stop */ +struct stop_sprs { + u64 pid; + u64 ldbar; + u64 fscr; + u64 hfscr; + u64 mmcr1; + u64 mmcr2; + u64 mmcra; +}; + extern u32 pnv_fastsleep_workaround_at_entry[]; extern u32 pnv_fastsleep_workaround_at_exit[]; @@ -90,20 +101,4 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err) #endif -/* Idle state entry routines */ -#ifdef CONFIG_PPC_P7_NAP -#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ - /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ - std r0,0(r1); \ - ptesync; \ - ld r0,0(r1); \ -236: cmpd cr0,r0,r0; \ - bne 236b; \ - IDLE_INST; \ - -#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \ - IDLE_STATE_ENTER_SEQ(IDLE_INST) \ - b . -#endif /* CONFIG_PPC_P7_NAP */ - #endif diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index d02ad93bf708..a9bf921f4efc 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -513,7 +513,7 @@ enum { #else CPU_FTRS_GENERIC_32 | #endif -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx CPU_FTRS_8XX | #endif #ifdef CONFIG_40x @@ -565,7 +565,7 @@ enum { #else CPU_FTRS_GENERIC_32 & #endif -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx CPU_FTRS_8XX & #endif #ifdef CONFIG_40x diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 8e37b71674f4..9847ae3a12d1 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -131,7 +131,6 @@ static inline bool eeh_pe_passed(struct eeh_pe *pe) struct eeh_dev { int mode; /* EEH mode */ int class_code; /* Class code of the device */ - int config_addr; /* Config address */ int pe_config_addr; /* PE config address */ u32 config_space[16]; /* Saved PCI config space */ int pcix_cap; /* Saved PCIx capability */ @@ -141,7 +140,6 @@ struct eeh_dev { struct eeh_pe *pe; /* Associated PE */ struct list_head list; /* Form link list in the PE */ struct list_head rmv_list; /* Record the removed edevs */ - struct pci_controller *phb; /* Associated PHB */ struct pci_dn *pdn; /* Associated PCI device node */ struct pci_dev *pdev; /* Associated PCI device */ bool in_error; /* Error flag for edev */ @@ -262,7 +260,8 @@ typedef void *(*eeh_traverse_func)(void *data, void *flag); void eeh_set_pe_aux_size(int size); int eeh_phb_pe_create(struct pci_controller *phb); struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb); -struct eeh_pe *eeh_pe_get(struct eeh_dev *edev); +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, + int pe_no, int config_addr); int eeh_add_to_parent_pe(struct eeh_dev *edev); int eeh_rmv_from_parent_pe(struct eeh_dev *edev); void eeh_pe_update_time_stamp(struct eeh_pe *pe); diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index ce88bbe1d809..5a23010af600 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -209,11 +209,13 @@ extern int early_init_dt_scan_fw_dump(unsigned long node, extern int fadump_reserve_mem(void); extern int setup_fadump(void); extern int is_fadump_active(void); +extern int should_fadump_crash(void); extern void crash_fadump(struct pt_regs *, const char *); extern void fadump_cleanup(void); #else /* CONFIG_FA_DUMP */ static inline int is_fadump_active(void) { return 0; } +static inline int should_fadump_crash(void) { return 0; } static inline void crash_fadump(struct pt_regs *regs, const char *str) { } #endif #endif diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 2de2319b99e2..8f88f771cc55 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -19,11 +19,11 @@ */ #if defined(CONFIG_PPC64) && !defined(__powerpc64__) /* 64 bits kernel, 32 bits code (ie. vdso32) */ -#define FTR_ENTRY_LONG .llong +#define FTR_ENTRY_LONG .8byte #define FTR_ENTRY_OFFSET .long 0xffffffff; .long #elif defined(CONFIG_PPC64) -#define FTR_ENTRY_LONG .llong -#define FTR_ENTRY_OFFSET .llong +#define FTR_ENTRY_LONG .8byte +#define FTR_ENTRY_OFFSET .8byte #else #define FTR_ENTRY_LONG .long #define FTR_ENTRY_OFFSET .long diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 4508b322f2cd..6c40dfda5912 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -17,6 +17,7 @@ #ifndef __ASSEMBLY__ #include <linux/kernel.h> #include <asm/page.h> +#include <asm/pgtable.h> #ifdef CONFIG_HIGHMEM #include <linux/threads.h> #include <asm/kmap_types.h> @@ -62,9 +63,6 @@ enum fixed_addresses { __end_of_fixed_addresses }; -extern void __set_fixmap (enum fixed_addresses idx, - phys_addr_t phys, pgprot_t flags); - #define __FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) #define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) @@ -72,5 +70,11 @@ extern void __set_fixmap (enum fixed_addresses idx, #include <asm-generic/fixmap.h> +static inline void __set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags) +{ + map_kernel_page(fix_to_virt(idx), phys, pgprot_val(flags)); +} + #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/fs_pd.h b/arch/powerpc/include/asm/fs_pd.h index f79d6c74eb2a..8def56ec05c6 100644 --- a/arch/powerpc/include/asm/fs_pd.h +++ b/arch/powerpc/include/asm/fs_pd.h @@ -26,7 +26,7 @@ #define cpm2_unmap(addr) do {} while(0) #endif -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx #include <asm/8xx_immap.h> extern immap_t __iomem *mpc8xx_immr; diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h index eaada6c92344..719ed9b61ea7 100644 --- a/arch/powerpc/include/asm/futex.h +++ b/arch/powerpc/include/asm/futex.h @@ -29,18 +29,10 @@ : "b" (uaddr), "i" (-EFAULT), "r" (oparg) \ : "cr0", "memory") -static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) +static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) { - int op = (encoded_op >> 28) & 7; - int cmp = (encoded_op >> 24) & 15; - int oparg = (encoded_op << 8) >> 20; - int cmparg = (encoded_op << 20) >> 20; int oldval = 0, ret; - if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) - oparg = 1 << oparg; - - if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32))) - return -EFAULT; pagefault_disable(); @@ -66,17 +58,9 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) pagefault_enable(); - if (!ret) { - switch (cmp) { - case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break; - case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break; - case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break; - case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break; - case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break; - case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break; - default: ret = -ENOSYS; - } - } + if (!ret) + *oval = oldval; + return ret; } diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index 8add8b861e8d..c97603d617e3 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -12,6 +12,10 @@ typedef struct { unsigned int mce_exceptions; unsigned int spurious_irqs; unsigned int hmi_exceptions; + unsigned int sreset_irqs; +#ifdef CONFIG_PPC_WATCHDOG + unsigned int soft_nmi_irqs; +#endif #ifdef CONFIG_PPC_DOORBELL unsigned int doorbell_irqs; #endif diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 7f4025a6c69e..b8a0fb442c64 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -218,18 +218,4 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, } #endif /* CONFIG_HUGETLB_PAGE */ -/* - * FSL Book3E platforms require special gpage handling - the gpages - * are reserved early in the boot process by memblock instead of via - * the .dts as on IBM platforms. - */ -#if defined(CONFIG_HUGETLB_PAGE) && (defined(CONFIG_PPC_FSL_BOOK3E) || \ - defined(CONFIG_PPC_8xx)) -extern void __init reserve_hugetlb_gpages(void); -#else -static inline void reserve_hugetlb_gpages(void) -{ -} -#endif - #endif /* _ASM_POWERPC_HUGETLB_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 57d38b504ff7..3d34dc0869f6 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -280,7 +280,18 @@ #define H_RESIZE_HPT_COMMIT 0x370 #define H_REGISTER_PROC_TBL 0x37C #define H_SIGNAL_SYS_RESET 0x380 -#define MAX_HCALL_OPCODE H_SIGNAL_SYS_RESET +#define H_INT_GET_SOURCE_INFO 0x3A8 +#define H_INT_SET_SOURCE_CONFIG 0x3AC +#define H_INT_GET_SOURCE_CONFIG 0x3B0 +#define H_INT_GET_QUEUE_INFO 0x3B4 +#define H_INT_SET_QUEUE_CONFIG 0x3B8 +#define H_INT_GET_QUEUE_CONFIG 0x3BC +#define H_INT_SET_OS_REPORTING_LINE 0x3C0 +#define H_INT_GET_OS_REPORTING_LINE 0x3C4 +#define H_INT_ESB 0x3C8 +#define H_INT_SYNC 0x3CC +#define H_INT_RESET 0x3D0 +#define MAX_HCALL_OPCODE H_INT_RESET /* H_VIOCTL functions */ #define H_GET_VIOA_DUMP_SIZE 0x01 diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index 27e588f6c72e..6a2c87577541 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -69,7 +69,10 @@ struct coprocessor_completion_block { #define CSB_CC_WR_PROTECTION (16) #define CSB_CC_UNKNOWN_CODE (17) #define CSB_CC_ABORT (18) +#define CSB_CC_EXCEED_BYTE_COUNT (19) /* P9 or later */ #define CSB_CC_TRANSPORT (20) +#define CSB_CC_INVALID_CRB (21) /* P9 or later */ +#define CSB_CC_INVALID_DDE (30) /* P9 or later */ #define CSB_CC_SEGMENTED_DDL (31) #define CSB_CC_PROGRESS_POINT (32) #define CSB_CC_DDE_OVERFLOW (33) diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h new file mode 100644 index 000000000000..7f74c282710f --- /dev/null +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -0,0 +1,128 @@ +#ifndef __ASM_POWERPC_IMC_PMU_H +#define __ASM_POWERPC_IMC_PMU_H + +/* + * IMC Nest Performance Monitor counter support. + * + * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation. + * (C) 2017 Anju T Sudhakar, IBM Corporation. + * (C) 2017 Hemant K Shaw, IBM Corporation. + * + * 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 later version. + */ + +#include <linux/perf_event.h> +#include <linux/slab.h> +#include <linux/of.h> +#include <linux/io.h> +#include <asm/opal.h> + +/* + * For static allocation of some of the structures. + */ +#define IMC_MAX_PMUS 32 + +/* + * Compatibility macros for IMC devices + */ +#define IMC_DTB_COMPAT "ibm,opal-in-memory-counters" +#define IMC_DTB_UNIT_COMPAT "ibm,imc-counters" + + +/* + * LDBAR: Counter address and Enable/Disable macro. + * perf/imc-pmu.c has the LDBAR layout information. + */ +#define THREAD_IMC_LDBAR_MASK 0x0003ffffffffe000ULL +#define THREAD_IMC_ENABLE 0x8000000000000000ULL + +/* + * Structure to hold memory address information for imc units. + */ +struct imc_mem_info { + u64 *vbase; + u32 id; +}; + +/* + * Place holder for nest pmu events and values. + */ +struct imc_events { + u32 value; + char *name; + char *unit; + char *scale; +}; + +/* Event attribute array index */ +#define IMC_FORMAT_ATTR 0 +#define IMC_EVENT_ATTR 1 +#define IMC_CPUMASK_ATTR 2 +#define IMC_NULL_ATTR 3 + +/* PMU Format attribute macros */ +#define IMC_EVENT_OFFSET_MASK 0xffffffffULL + +/* + * Device tree parser code detects IMC pmu support and + * registers new IMC pmus. This structure will hold the + * pmu functions, events, counter memory information + * and attrs for each imc pmu and will be referenced at + * the time of pmu registration. + */ +struct imc_pmu { + struct pmu pmu; + struct imc_mem_info *mem_info; + struct imc_events **events; + /* + * Attribute groups for the PMU. Slot 0 used for + * format attribute, slot 1 used for cpusmask attribute, + * slot 2 used for event attribute. Slot 3 keep as + * NULL. + */ + const struct attribute_group *attr_groups[4]; + u32 counter_mem_size; + int domain; + /* + * flag to notify whether the memory is mmaped + * or allocated by kernel. + */ + bool imc_counter_mmaped; +}; + +/* + * Structure to hold id, lock and reference count for the imc events which + * are inited. + */ +struct imc_pmu_ref { + struct mutex lock; + unsigned int id; + int refc; +}; + +/* + * In-Memory Collection Counters type. + * Data comes from Device tree. + * Three device type are supported. + */ + +enum { + IMC_TYPE_THREAD = 0x1, + IMC_TYPE_CORE = 0x4, + IMC_TYPE_CHIP = 0x10, +}; + +/* + * Domains for IMC PMUs + */ +#define IMC_DOMAIN_NEST 1 +#define IMC_DOMAIN_CORE 2 +#define IMC_DOMAIN_THREAD 3 + +extern int init_imc_pmu(struct device_node *parent, + struct imc_pmu *pmu_ptr, int pmu_id); +extern void thread_imc_disable(void); +#endif /* __ASM_POWERPC_IMC_PMU_H */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 7cea76f11c26..83596f32f50b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -104,6 +104,10 @@ struct kvmppc_host_state { u8 napping; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + /* + * hwthread_req/hwthread_state pair is used to pull sibling threads + * out of guest on pre-ISAv3.0B CPUs where threads share MMU. + */ u8 hwthread_req; u8 hwthread_state; u8 host_ipi; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 8b3f1238d07f..e372ed871c51 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -67,11 +67,6 @@ extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); -static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ -} - #define HPTEG_CACHE_NUM (1 << 15) #define HPTEG_HASH_BITS_PTE 13 #define HPTEG_HASH_BITS_PTE_LONG 12 diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index cd2fc1cc1cc7..73b92017b6d7 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -76,7 +76,6 @@ struct machdep_calls { void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); - void (*panic)(char *str); void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 0c76675394c5..309592589e30 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -77,58 +77,8 @@ extern void switch_cop(struct mm_struct *next); extern int use_cop(unsigned long acop, struct mm_struct *mm); extern void drop_cop(unsigned long acop, struct mm_struct *mm); -/* - * switch_mm is the entry point called from the architecture independent - * code in kernel/sched/core.c - */ -static inline void switch_mm_irqs_off(struct mm_struct *prev, - struct mm_struct *next, - struct task_struct *tsk) -{ - bool new_on_cpu = false; - - /* Mark this context has been used on the new CPU */ - if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) { - cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); - new_on_cpu = true; - } - - /* 32-bit keeps track of the current PGDIR in the thread struct */ -#ifdef CONFIG_PPC32 - tsk->thread.pgdir = next->pgd; -#endif /* CONFIG_PPC32 */ - - /* 64-bit Book3E keeps track of current PGD in the PACA */ -#ifdef CONFIG_PPC_BOOK3E_64 - get_paca()->pgd = next->pgd; -#endif - /* Nothing else to do if we aren't actually switching */ - if (prev == next) - return; - -#ifdef CONFIG_PPC_ICSWX - /* Switch coprocessor context only if prev or next uses a coprocessor */ - if (prev->context.acop || next->context.acop) - switch_cop(next); -#endif /* CONFIG_PPC_ICSWX */ - - /* We must stop all altivec streams before changing the HW - * context - */ -#ifdef CONFIG_ALTIVEC - if (cpu_has_feature(CPU_FTR_ALTIVEC)) - asm volatile ("dssall"); -#endif /* CONFIG_ALTIVEC */ - - if (new_on_cpu) - radix_kvm_prefetch_workaround(next); - - /* - * The actual HW switching method differs between the various - * sub architectures. Out of line for now - */ - switch_mmu_context(prev, next, tsk); -} +extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk); static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) @@ -150,11 +100,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - unsigned long flags; - - local_irq_save(flags); switch_mm(prev, next, current); - local_irq_restore(flags); } /* We don't currently use enter_lazy_tlb() for anything */ diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 6f8e79cd35d8..3760150a0ff0 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -1,9 +1,8 @@ #ifndef _ASM_NMI_H #define _ASM_NMI_H -#ifdef CONFIG_HARDLOCKUP_DETECTOR +#ifdef CONFIG_PPC_WATCHDOG extern void arch_touch_nmi_watchdog(void); - extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 91314268f04f..185c6a47f9ba 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -121,7 +121,7 @@ extern int icache_44x_need_flush; #include <asm/nohash/pte-book3e.h> #elif defined(CONFIG_FSL_BOOKE) #include <asm/nohash/32/pte-fsl-booke.h> -#elif defined(CONFIG_8xx) +#elif defined(CONFIG_PPC_8xx) #include <asm/nohash/32/pte-8xx.h> #endif @@ -337,9 +337,6 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm, #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 }) -extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, - pmd_t **pmdp); - int map_kernel_page(unsigned long va, phys_addr_t pa, int flags); #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index e5805ad78e12..17989c3d9a24 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -14,6 +14,7 @@ static inline int pte_write(pte_t pte) { return (pte_val(pte) & (_PAGE_RW | _PAGE_RO)) != _PAGE_RO; } +static inline int pte_read(pte_t pte) { return 1; } static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 3130a73652c7..450a60b81d2a 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -42,6 +42,7 @@ #define OPAL_I2C_STOP_ERR -24 #define OPAL_XIVE_PROVISIONING -31 #define OPAL_XIVE_FREE_ACTIVE -32 +#define OPAL_TIMEOUT -33 /* API Tokens (in r0) */ #define OPAL_INVALID_CALL -1 @@ -190,7 +191,16 @@ #define OPAL_NPU_INIT_CONTEXT 146 #define OPAL_NPU_DESTROY_CONTEXT 147 #define OPAL_NPU_MAP_LPAR 148 -#define OPAL_LAST 148 +#define OPAL_IMC_COUNTERS_INIT 149 +#define OPAL_IMC_COUNTERS_START 150 +#define OPAL_IMC_COUNTERS_STOP 151 +#define OPAL_GET_POWERCAP 152 +#define OPAL_SET_POWERCAP 153 +#define OPAL_GET_POWER_SHIFT_RATIO 154 +#define OPAL_SET_POWER_SHIFT_RATIO 155 +#define OPAL_SENSOR_GROUP_CLEAR 156 +#define OPAL_PCI_SET_P2P 157 +#define OPAL_LAST 157 /* Device tree flags */ @@ -1084,6 +1094,18 @@ enum { XIVE_DUMP_EMU_STATE = 5, }; +/* "type" argument options for OPAL_IMC_COUNTERS_* calls */ +enum { + OPAL_IMC_COUNTERS_NEST = 1, + OPAL_IMC_COUNTERS_CORE = 2, +}; + + +/* PCI p2p descriptor */ +#define OPAL_PCI_P2P_ENABLE 0x1 +#define OPAL_PCI_P2P_LOAD 0x2 +#define OPAL_PCI_P2P_STORE 0x4 + #endif /* __ASSEMBLY__ */ #endif /* __OPAL_API_H */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 588fb1c23af9..726c23304a57 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -50,7 +50,7 @@ int64_t opal_tpo_write(uint64_t token, uint32_t year_mon_day, uint32_t hour_min); int64_t opal_cec_power_down(uint64_t request); int64_t opal_cec_reboot(void); -int64_t opal_cec_reboot2(uint32_t reboot_type, char *diag); +int64_t opal_cec_reboot2(uint32_t reboot_type, const char *diag); int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_write_nvram(uint64_t buffer, uint64_t size, uint64_t offset); int64_t opal_handle_interrupt(uint64_t isn, __be64 *outstanding_event_mask); @@ -267,6 +267,19 @@ int64_t opal_xive_allocate_irq(uint32_t chip_id); int64_t opal_xive_free_irq(uint32_t girq); int64_t opal_xive_sync(uint32_t type, uint32_t id); int64_t opal_xive_dump(uint32_t type, uint32_t id); +int64_t opal_pci_set_p2p(uint64_t phb_init, uint64_t phb_target, + uint64_t desc, uint16_t pe_number); + +int64_t opal_imc_counters_init(uint32_t type, uint64_t address, + uint64_t cpu_pir); +int64_t opal_imc_counters_start(uint32_t type, uint64_t cpu_pir); +int64_t opal_imc_counters_stop(uint32_t type, uint64_t cpu_pir); + +int opal_get_powercap(u32 handle, int token, u32 *pcap); +int opal_set_powercap(u32 handle, int token, u32 pcap); +int opal_get_power_shift_ratio(u32 handle, int token, u32 *psr); +int opal_set_power_shift_ratio(u32 handle, int token, u32 psr); +int opal_sensor_group_clear(u32 group_hndl, int token); /* Internal functions */ extern int early_init_dt_scan_opal(unsigned long node, const char *uname, @@ -345,6 +358,10 @@ static inline int opal_get_async_rc(struct opal_msg msg) void opal_wake_poller(void); +void opal_powercap_init(void); +void opal_psr_init(void); +void opal_sensor_groups_init(void); + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_OPAL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index dc88a31cc79a..04b60af027ae 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -31,6 +31,7 @@ #endif #include <asm/accounting.h> #include <asm/hmi.h> +#include <asm/cpuidle.h> register struct paca_struct *local_paca asm("r13"); @@ -183,6 +184,12 @@ struct paca_struct { struct paca_struct **thread_sibling_pacas; /* The PSSCR value that the kernel requested before going to stop */ u64 requested_psscr; + + /* + * Save area for additional SPRs that need to be + * saved/restored during cpuidle stop. + */ + struct stop_sprs stop_sprs; #endif #ifdef CONFIG_PPC_STD_MMU_64 diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index 56c67d3f0108..0b8aa1fe2d5f 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -195,7 +195,6 @@ struct pci_dn { struct pci_dn *parent; struct pci_controller *phb; /* for pci devices */ struct iommu_table_group *table_group; /* for phb's or bridges */ - struct device_node *node; /* back-pointer to the device_node */ int pci_ext_config_space; /* for pci devices */ diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index d795c5d5789c..45ae1212ab8a 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -17,6 +17,8 @@ static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp) } #endif /* MODULE */ +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) + #ifdef CONFIG_PPC_BOOK3S #include <asm/book3s/pgalloc.h> #else diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h index 9c0f5db5cf46..67e7e3d990f4 100644 --- a/arch/powerpc/include/asm/pgtable-be-types.h +++ b/arch/powerpc/include/asm/pgtable-be-types.h @@ -87,6 +87,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) unsigned long *p = (unsigned long *)ptep; __be64 prev; + /* See comment in switch_mm_irqs_off() */ prev = (__force __be64)__cmpxchg_u64(p, (__force unsigned long)pte_raw(old), (__force unsigned long)pte_raw(new)); diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index 8bd3b13fe2fb..369a164b545c 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -62,6 +62,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) { unsigned long *p = (unsigned long *)ptep; + /* See comment in switch_mm_irqs_off() */ return pte_val(old) == __cmpxchg_u64(p, pte_val(old), pte_val(new)); } #endif diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index afae9a336136..7d0d38f58243 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -66,22 +66,14 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, #ifndef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_large(pmd) 0 #endif -pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, - bool *is_thp, unsigned *shift); -static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, - bool *is_thp, unsigned *shift) -{ - VM_WARN(!arch_irqs_disabled(), - "%s called with irq enabled\n", __func__); - return __find_linux_pte_or_hugepte(pgdir, ea, is_thp, shift); -} +/* can we use this in kvm */ unsigned long vmalloc_to_phys(void *vmalloc_addr); void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); void pgtable_cache_init(void); -#ifdef CONFIG_STRICT_KERNEL_RWX +#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32) void mark_initmem_nx(void); #else static inline void mark_initmem_nx(void) { } diff --git a/arch/powerpc/include/asm/pnv-pci.h b/arch/powerpc/include/asm/pnv-pci.h index de9681034353..3e5cf251ad9a 100644 --- a/arch/powerpc/include/asm/pnv-pci.h +++ b/arch/powerpc/include/asm/pnv-pci.h @@ -26,6 +26,8 @@ extern int pnv_pci_get_presence_state(uint64_t id, uint8_t *state); extern int pnv_pci_get_power_state(uint64_t id, uint8_t *state); extern int pnv_pci_set_power_state(uint64_t id, uint8_t state, struct opal_msg *msg); +extern int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target, + u64 desc); int pnv_phb_to_cxl_mode(struct pci_dev *dev, uint64_t mode); int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq, diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index fa9ebaead91e..ce0930d68857 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -193,6 +193,7 @@ #define PPC_INST_CLRBHRB 0x7c00035c #define PPC_INST_COPY 0x7c20060c #define PPC_INST_CP_ABORT 0x7c00068c +#define PPC_INST_DARN 0x7c0005e6 #define PPC_INST_DCBA 0x7c0005ec #define PPC_INST_DCBA_MASK 0xfc0007fe #define PPC_INST_DCBAL 0x7c2005ec @@ -204,6 +205,8 @@ #define PPC_INST_ISEL_MASK 0xfc00003e #define PPC_INST_LDARX 0x7c0000a8 #define PPC_INST_STDCX 0x7c0001ad +#define PPC_INST_LQARX 0x7c000228 +#define PPC_INST_STQCX 0x7c00016d #define PPC_INST_LSWI 0x7c0004aa #define PPC_INST_LSWX 0x7c00042a #define PPC_INST_LWARX 0x7c000028 @@ -261,7 +264,7 @@ #define PPC_INST_TLBSRX_DOT 0x7c0006a5 #define PPC_INST_VPMSUMW 0x10000488 #define PPC_INST_VPMSUMD 0x100004c8 -#define PPC_INST_XXLOR 0xf0000510 +#define PPC_INST_XXLOR 0xf0000490 #define PPC_INST_XXSWAPD 0xf0000250 #define PPC_INST_XVCPSGNDP 0xf0000780 #define PPC_INST_TRECHKPT 0x7c0007dd @@ -395,16 +398,25 @@ #define PPC_CP_ABORT stringify_in_c(.long PPC_INST_CP_ABORT) #define PPC_COPY(a, b) stringify_in_c(.long PPC_INST_COPY | \ ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_DARN(t, l) stringify_in_c(.long PPC_INST_DARN | \ + ___PPC_RT(t) | \ + (((l) & 0x3) << 16)) #define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \ __PPC_RA(a) | __PPC_RB(b)) #define PPC_DCBZL(a, b) stringify_in_c(.long PPC_INST_DCBZL | \ __PPC_RA(a) | __PPC_RB(b)) +#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LQARX | \ + ___PPC_RT(t) | ___PPC_RA(a) | \ + ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \ ___PPC_RT(t) | ___PPC_RA(a) | \ ___PPC_RB(b) | __PPC_EH(eh)) #define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \ ___PPC_RT(t) | ___PPC_RA(a) | \ ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_INST_STQCX | \ + ___PPC_RT(t) | ___PPC_RA(a) | \ + ___PPC_RB(b)) #define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ ___PPC_RB(b)) #define PPC_MSGSYNC stringify_in_c(.long PPC_INST_MSGSYNC) @@ -414,6 +426,8 @@ ___PPC_RB(b)) #define PPC_MSGCLRP(b) stringify_in_c(.long PPC_INST_MSGCLRP | \ ___PPC_RB(b)) +#define PPC_PASTE(a, b) stringify_in_c(.long PPC_INST_PASTE | \ + ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ __PPC_RA(a) | __PPC_RS(s)) #define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_INST_POPCNTD | \ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 6baeeb9acd0d..36f3e41c9fbe 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -378,10 +378,16 @@ BEGIN_FTR_SECTION_NESTED(96); \ cmpwi dest,0; \ beq- 90b; \ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) -#elif defined(CONFIG_8xx) -#define MFTB(dest) mftb dest #else -#define MFTB(dest) mfspr dest, SPRN_TBRL +#define MFTB(dest) MFTBL(dest) +#endif + +#ifdef CONFIG_PPC_8xx +#define MFTBL(dest) mftb dest +#define MFTBU(dest) mftbu dest +#else +#define MFTBL(dest) mfspr dest, SPRN_TBRL +#define MFTBU(dest) mfspr dest, SPRN_TBRU #endif #ifndef CONFIG_SMP @@ -411,7 +417,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) * and they must be used. */ -#if !defined(CONFIG_4xx) && !defined(CONFIG_8xx) +#if !defined(CONFIG_4xx) && !defined(CONFIG_PPC_8xx) #define tlbia \ li r4,1024; \ mtctr r4; \ @@ -439,7 +445,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601) .machine push ; \ .machine "power4" ; \ lis scratch,0x60000000@h; \ - dcbt r0,scratch,0b01010; \ + dcbt 0,scratch,0b01010; \ .machine pop /* diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index 35c00d7a0cf8..825bd5998701 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -159,7 +159,10 @@ struct of_drconf_cell { #define OV5_PFO_HW_842 0x1140 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x1120 /* PFO Encryption Accelerator */ #define OV5_SUB_PROCESSORS 0x1501 /* 1,2,or 4 Sub-Processors supported */ -#define OV5_XIVE_EXPLOIT 0x1701 /* XIVE exploitation supported */ +#define OV5_XIVE_SUPPORT 0x17C0 /* XIVE Exploitation Support Mask */ +#define OV5_XIVE_LEGACY 0x1700 /* XIVE legacy mode Only */ +#define OV5_XIVE_EXPLOIT 0x1740 /* XIVE exploitation mode Only */ +#define OV5_XIVE_EITHER 0x1780 /* XIVE legacy or exploitation mode */ /* MMU Base Architecture */ #define OV5_MMU_SUPPORT 0x18C0 /* MMU Mode Support Mask */ #define OV5_MMU_HASH 0x1800 /* Hash MMU Only */ diff --git a/arch/powerpc/include/asm/pte-walk.h b/arch/powerpc/include/asm/pte-walk.h new file mode 100644 index 000000000000..2d633e9d686c --- /dev/null +++ b/arch/powerpc/include/asm/pte-walk.h @@ -0,0 +1,35 @@ +#ifndef _ASM_POWERPC_PTE_WALK_H +#define _ASM_POWERPC_PTE_WALK_H + +#include <linux/sched.h> + +/* Don't use this directly */ +extern pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, + bool *is_thp, unsigned *hshift); + +static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea, + bool *is_thp, unsigned *hshift) +{ + VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__); + return __find_linux_pte(pgdir, ea, is_thp, hshift); +} + +static inline pte_t *find_init_mm_pte(unsigned long ea, unsigned *hshift) +{ + pgd_t *pgdir = init_mm.pgd; + return __find_linux_pte(pgdir, ea, NULL, hshift); +} +/* + * This is what we should always use. Any other lockless page table lookup needs + * careful audit against THP split. + */ +static inline pte_t *find_current_mm_pte(pgd_t *pgdir, unsigned long ea, + bool *is_thp, unsigned *hshift) +{ + VM_WARN(!arch_irqs_disabled(), "%s called with irq enabled\n", __func__); + VM_WARN(pgdir != current->mm->pgd, + "%s lock less page table lookup called on wrong mm\n", __func__); + return __find_linux_pte(pgdir, ea, is_thp, hshift); +} + +#endif /* _ASM_POWERPC_PTE_WALK_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index a3b6575c7842..f92eaf7a4c0d 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -22,9 +22,9 @@ #include <asm/reg_fsl_emb.h> #endif -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx #include <asm/reg_8xx.h> -#endif /* CONFIG_8xx */ +#endif /* CONFIG_PPC_8xx */ #define MSR_SF_LG 63 /* Enable 64 bit mode */ #define MSR_ISF_LG 61 /* Interrupt 64b mode valid on 630 */ @@ -135,7 +135,7 @@ #define MSR_KERNEL (MSR_ | MSR_64BIT) #define MSR_USER32 (MSR_ | MSR_PR | MSR_EE) #define MSR_USER64 (MSR_USER32 | MSR_64BIT) -#elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_8xx) +#elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx) /* Default MSR for kernel mode. */ #define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR) #define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE) @@ -272,16 +272,65 @@ #define SPRN_DAR 0x013 /* Data Address Register */ #define SPRN_DBCR 0x136 /* e300 Data Breakpoint Control Reg */ #define SPRN_DSISR 0x012 /* Data Storage Interrupt Status Register */ -#define DSISR_NOHPTE 0x40000000 /* no translation found */ -#define DSISR_PROTFAULT 0x08000000 /* protection fault */ -#define DSISR_BADACCESS 0x04000000 /* bad access to CI or G */ -#define DSISR_ISSTORE 0x02000000 /* access was a store */ -#define DSISR_DABRMATCH 0x00400000 /* hit data breakpoint */ -#define DSISR_NOSEGMENT 0x00200000 /* SLB miss */ -#define DSISR_KEYFAULT 0x00200000 /* Key fault */ -#define DSISR_UNSUPP_MMU 0x00080000 /* Unsupported MMU config */ -#define DSISR_SET_RC 0x00040000 /* Failed setting of R/C bits */ -#define DSISR_PGDIRFAULT 0x00020000 /* Fault on page directory */ +#define DSISR_BAD_DIRECT_ST 0x80000000 /* Obsolete: Direct store error */ +#define DSISR_NOHPTE 0x40000000 /* no translation found */ +#define DSISR_ATTR_CONFLICT 0x20000000 /* P9: Process vs. Partition attr */ +#define DSISR_NOEXEC_OR_G 0x10000000 /* Alias of SRR1 bit, see below */ +#define DSISR_PROTFAULT 0x08000000 /* protection fault */ +#define DSISR_BADACCESS 0x04000000 /* bad access to CI or G */ +#define DSISR_ISSTORE 0x02000000 /* access was a store */ +#define DSISR_DABRMATCH 0x00400000 /* hit data breakpoint */ +#define DSISR_NOSEGMENT 0x00200000 /* STAB miss (unsupported) */ +#define DSISR_KEYFAULT 0x00200000 /* Storage Key fault */ +#define DSISR_BAD_EXT_CTRL 0x00100000 /* Obsolete: External ctrl error */ +#define DSISR_UNSUPP_MMU 0x00080000 /* P9: Unsupported MMU config */ +#define DSISR_SET_RC 0x00040000 /* P9: Failed setting of R/C bits */ +#define DSISR_PRTABLE_FAULT 0x00020000 /* P9: Fault on process table */ +#define DSISR_ICSWX_NO_CT 0x00004000 /* P7: icswx unavailable cp type */ +#define DSISR_BAD_COPYPASTE 0x00000008 /* P9: Copy/Paste on wrong memtype */ +#define DSISR_BAD_AMO 0x00000004 /* P9: Incorrect AMO opcode */ +#define DSISR_BAD_CI_LDST 0x00000002 /* P8: Bad HV CI load/store */ + +/* + * DSISR_NOEXEC_OR_G doesn't actually exist. This bit is always + * 0 on DSIs. However, on ISIs, the corresponding bit in SRR1 + * indicates an attempt at executing from a no-execute PTE + * or segment or from a guarded page. + * + * We add a definition here for completeness as we alias + * DSISR and SRR1 in do_page_fault. + */ + +/* + * DSISR bits that are treated as a fault. Any bit set + * here will skip hash_page, and cause do_page_fault to + * trigger a SIGBUS or SIGSEGV: + */ +#define DSISR_BAD_FAULT_32S (DSISR_BAD_DIRECT_ST | \ + DSISR_BADACCESS | \ + DSISR_BAD_EXT_CTRL) +#define DSISR_BAD_FAULT_64S (DSISR_BAD_FAULT_32S | \ + DSISR_ATTR_CONFLICT | \ + DSISR_KEYFAULT | \ + DSISR_UNSUPP_MMU | \ + DSISR_PRTABLE_FAULT | \ + DSISR_ICSWX_NO_CT | \ + DSISR_BAD_COPYPASTE | \ + DSISR_BAD_AMO | \ + DSISR_BAD_CI_LDST) +/* + * These bits are equivalent in SRR1 and DSISR for 0x400 + * instruction access interrupts on Book3S + */ +#define DSISR_SRR1_MATCH_32S (DSISR_NOHPTE | \ + DSISR_NOEXEC_OR_G | \ + DSISR_PROTFAULT) +#define DSISR_SRR1_MATCH_64S (DSISR_SRR1_MATCH_32S | \ + DSISR_KEYFAULT | \ + DSISR_UNSUPP_MMU | \ + DSISR_SET_RC | \ + DSISR_PRTABLE_FAULT) + #define SPRN_TBRL 0x10C /* Time Base Read Lower Register (user, R/O) */ #define SPRN_TBRU 0x10D /* Time Base Read Upper Register (user, R/O) */ #define SPRN_CIR 0x11B /* Chip Information Register (hyper, R/0) */ @@ -307,6 +356,7 @@ #define SPRN_PMSR 0x355 /* Power Management Status Reg */ #define SPRN_PMMAR 0x356 /* Power Management Memory Activity Register */ #define SPRN_PSSCR 0x357 /* Processor Stop Status and Control Register (ISA 3.0) */ +#define SPRN_PSSCR_PR 0x337 /* PSSCR ISA 3.0, privileged mode access */ #define SPRN_PMCR 0x374 /* Power Management Control Register */ /* HFSCR and FSCR bit numbers are the same */ @@ -675,6 +725,7 @@ * may not be recoverable */ #define SRR1_WS_DEEPER 0x00020000 /* Some resources not maintained */ #define SRR1_WS_DEEP 0x00010000 /* All resources maintained */ +#define SRR1_PROGTM 0x00200000 /* TM Bad Thing */ #define SRR1_PROGFPE 0x00100000 /* Floating Point Enabled */ #define SRR1_PROGILL 0x00080000 /* Illegal instruction */ #define SRR1_PROGPRIV 0x00040000 /* Privileged instruction */ @@ -1114,7 +1165,7 @@ #endif #endif -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx #define SPRN_SPRG_SCRATCH0 SPRN_SPRG0 #define SPRN_SPRG_SCRATCH1 SPRN_SPRG1 #define SPRN_SPRG_SCRATCH2 SPRN_SPRG2 @@ -1197,10 +1248,8 @@ * differentiated by the version number in the Communication Processor * Module (CPM). */ -#define PVR_821 0x00500000 -#define PVR_823 PVR_821 -#define PVR_850 PVR_821 -#define PVR_860 PVR_821 +#define PVR_8xx 0x00500000 + #define PVR_8240 0x00810100 #define PVR_8245 0x80811014 #define PVR_8260 PVR_8240 @@ -1295,12 +1344,12 @@ static inline void msr_check_and_clear(unsigned long bits) ".section __ftr_fixup,\"a\"\n" \ ".align 3\n" \ "98:\n" \ - " .llong %1\n" \ - " .llong %1\n" \ - " .llong 97b-98b\n" \ - " .llong 99b-98b\n" \ - " .llong 0\n" \ - " .llong 0\n" \ + " .8byte %1\n" \ + " .8byte %1\n" \ + " .8byte 97b-98b\n" \ + " .8byte 99b-98b\n" \ + " .8byte 0\n" \ + " .8byte 0\n" \ ".previous" \ : "=r" (rval) \ : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ @@ -1313,7 +1362,7 @@ static inline void msr_check_and_clear(unsigned long bits) #else /* __powerpc64__ */ -#if defined(CONFIG_8xx) +#if defined(CONFIG_PPC_8xx) #define mftbl() ({unsigned long rval; \ asm volatile("mftbl %0" : "=r" (rval)); rval;}) #define mftbu() ({unsigned long rval; \ diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index 737e012ef56e..eb2a33d5df26 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -221,10 +221,7 @@ #define SPRN_CSRR0 SPRN_SRR2 /* Critical Save and Restore Register 0 */ #define SPRN_CSRR1 SPRN_SRR3 /* Critical Save and Restore Register 1 */ #endif - -#ifdef CONFIG_PPC_ICSWX #define SPRN_HACOP 0x15F /* Hypervisor Available Coprocessor Register */ -#endif /* Bit definitions for CCR1. */ #define CCR1_DPC 0x00000100 /* Disable L1 I-Cache/D-Cache parity checking */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 654d64c9f3ac..3a3fb0ca68f5 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -23,7 +23,6 @@ extern void reloc_got2(unsigned long); void check_for_initrd(void); void initmem_init(void); -void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 8ea98504f900..fac963e10d39 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -97,6 +97,7 @@ static inline void set_hard_smp_processor_id(int cpu, int phys) #endif DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_l2_cache_map); DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); static inline struct cpumask *cpu_sibling_mask(int cpu) @@ -109,6 +110,11 @@ static inline struct cpumask *cpu_core_mask(int cpu) return per_cpu(cpu_core_map, cpu); } +static inline struct cpumask *cpu_l2_cache_mask(int cpu) +{ + return per_cpu(cpu_l2_cache_map, cpu); +} + extern int cpu_to_core_id(int cpu); /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 8c1b913de6d7..edbe571bcc54 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -170,39 +170,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) lock->slock = 0; } -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - arch_spinlock_t lock_val; - - smp_mb(); - - /* - * Atomically load and store back the lock value (unchanged). This - * ensures that our observation of the lock value is ordered with - * respect to other lock operations. - */ - __asm__ __volatile__( -"1: " PPC_LWARX(%0, 0, %2, 0) "\n" -" stwcx. %0, 0, %2\n" -" bne- 1b\n" - : "=&r" (lock_val), "+m" (*lock) - : "r" (lock) - : "cr0", "xer"); - - if (arch_spin_value_unlocked(lock_val)) - goto out; - - while (lock->slock) { - HMT_low(); - if (SHARED_PROCESSOR) - __spin_yield(lock); - } - HMT_medium(); - -out: - smp_mb(); -} - /* * Read-write spinlocks, allowing multiple readers * but only one writer. @@ -342,5 +309,8 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) #define arch_read_relax(lock) __rw_yield(lock) #define arch_write_relax(lock) __rw_yield(lock) +/* See include/linux/spinlock.h */ +#define smp_mb__after_spinlock() smp_mb() + #endif /* __KERNEL__ */ #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h index d3a42cc45a82..ab9d849644d0 100644 --- a/arch/powerpc/include/asm/sstep.h +++ b/arch/powerpc/include/asm/sstep.h @@ -23,12 +23,9 @@ struct pt_regs; #define IS_RFID(instr) (((instr) & 0xfc0007fe) == 0x4c000024) #define IS_RFI(instr) (((instr) & 0xfc0007fe) == 0x4c000064) -/* Emulate instructions that cause a transfer of control. */ -extern int emulate_step(struct pt_regs *regs, unsigned int instr); - enum instruction_type { COMPUTE, /* arith/logical/CR op, etc. */ - LOAD, + LOAD, /* load and store types need to be contiguous */ LOAD_MULTI, LOAD_FP, LOAD_VMX, @@ -55,10 +52,31 @@ enum instruction_type { #define INSTR_TYPE_MASK 0x1f +#define OP_IS_LOAD_STORE(type) (LOAD <= (type) && (type) <= STCX) + +/* Compute flags, ORed in with type */ +#define SETREG 0x20 +#define SETCC 0x40 +#define SETXER 0x80 + +/* Branch flags, ORed in with type */ +#define SETLK 0x20 +#define BRTAKEN 0x40 +#define DECCTR 0x80 + /* Load/store flags, ORed in with type */ #define SIGNEXT 0x20 #define UPDATE 0x40 /* matches bit in opcode 31 instructions */ #define BYTEREV 0x80 +#define FPCONV 0x100 + +/* Barrier type field, ORed in with type */ +#define BARRIER_MASK 0xe0 +#define BARRIER_SYNC 0x00 +#define BARRIER_ISYNC 0x20 +#define BARRIER_EIEIO 0x40 +#define BARRIER_LWSYNC 0x60 +#define BARRIER_PTESYNC 0x80 /* Cacheop values, ORed in with type */ #define CACHEOP_MASK 0x700 @@ -67,10 +85,17 @@ enum instruction_type { #define DCBTST 0x200 #define DCBT 0x300 #define ICBI 0x400 +#define DCBZ 0x500 + +/* VSX flags values */ +#define VSX_FPCONV 1 /* do floating point SP/DP conversion */ +#define VSX_SPLAT 2 /* store loaded value into all elements */ +#define VSX_LDLEFT 4 /* load VSX register from left */ +#define VSX_CHECK_VEC 8 /* check MSR_VEC not MSR_VSX for reg >= 32 */ /* Size field in type word */ -#define SIZE(n) ((n) << 8) -#define GETSIZE(w) ((w) >> 8) +#define SIZE(n) ((n) << 12) +#define GETSIZE(w) ((w) >> 12) #define MKOP(t, f, s) ((t) | (f) | SIZE(s)) @@ -83,7 +108,63 @@ struct instruction_op { int update_reg; /* For MFSPR */ int spr; + u32 ccval; + u32 xerval; + u8 element_size; /* for VSX/VMX loads/stores */ + u8 vsx_flags; +}; + +union vsx_reg { + u8 b[16]; + u16 h[8]; + u32 w[4]; + unsigned long d[2]; + float fp[4]; + double dp[2]; + __vector128 v; }; -extern int analyse_instr(struct instruction_op *op, struct pt_regs *regs, +/* + * Decode an instruction, and return information about it in *op + * without changing *regs. + * + * Return value is 1 if the instruction can be emulated just by + * updating *regs with the information in *op, -1 if we need the + * GPRs but *regs doesn't contain the full register set, or 0 + * otherwise. + */ +extern int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, unsigned int instr); + +/* + * Emulate an instruction that can be executed just by updating + * fields in *regs. + */ +void emulate_update_regs(struct pt_regs *reg, struct instruction_op *op); + +/* + * Emulate instructions that cause a transfer of control, + * arithmetic/logical instructions, loads and stores, + * cache operations and barriers. + * + * Returns 1 if the instruction was emulated successfully, + * 0 if it could not be emulated, or -1 for an instruction that + * should not be emulated (rfid, mtmsrd clearing MSR_RI, etc.). + */ +extern int emulate_step(struct pt_regs *regs, unsigned int instr); + +/* + * Emulate a load or store instruction by reading/writing the + * memory of the current process. FP/VMX/VSX registers are assumed + * to hold live values if the appropriate enable bit in regs->msr is + * set; otherwise this will use the saved values in the thread struct + * for user-mode accesses. + */ +extern int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op); + +extern void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg, + const void *mem, bool cross_endian); +extern void emulate_vsx_store(struct instruction_op *op, + const union vsx_reg *reg, void *mem, + bool cross_endian); +extern int emulate_dcbz(unsigned long ea, struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index da3cdffca440..cc9addefb51c 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -10,6 +10,7 @@ #define __HAVE_ARCH_MEMMOVE #define __HAVE_ARCH_MEMCMP #define __HAVE_ARCH_MEMCHR +#define __HAVE_ARCH_MEMSET16 extern char * strcpy(char *,const char *); extern char * strncpy(char *,const char *, __kernel_size_t); @@ -23,6 +24,31 @@ extern void * memmove(void *,const void *,__kernel_size_t); extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); +#ifdef CONFIG_PPC64 +#define __HAVE_ARCH_MEMSET32 +#define __HAVE_ARCH_MEMSET64 + +extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t); +extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t); +extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t); + +static inline void *memset16(uint16_t *p, uint16_t v, __kernel_size_t n) +{ + return __memset16(p, v, n * 2); +} + +static inline void *memset32(uint32_t *p, uint32_t v, __kernel_size_t n) +{ + return __memset32(p, v, n * 4); +} + +static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n) +{ + return __memset64(p, v, n * 8); +} +#else +extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); +#endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_STRING_H */ diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index 2cf846edb3fc..cb61eae5b7ed 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -29,7 +29,7 @@ static inline cycles_t get_cycles(void) ret = 0; __asm__ __volatile__( -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx "97: mftb %0\n" #else "97: mfspr %0, %2\n" @@ -45,11 +45,7 @@ static inline cycles_t get_cycles(void) " .long 0\n" " .long 0\n" ".previous" -#ifdef CONFIG_8xx - : "=r" (ret) : "i" (CPU_FTR_601)); -#else : "=r" (ret) : "i" (CPU_FTR_601), "i" (SPRN_TBRL)); -#endif return ret; #endif } diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 609557569f65..a7eabff27a0f 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -69,13 +69,22 @@ static inline int mm_is_core_local(struct mm_struct *mm) topology_sibling_cpumask(smp_processor_id())); } +#ifdef CONFIG_PPC_BOOK3S_64 +static inline int mm_is_thread_local(struct mm_struct *mm) +{ + if (atomic_read(&mm->context.active_cpus) > 1) + return false; + return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); +} +#else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { return cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())); } +#endif /* !CONFIG_PPC_BOOK3S_64 */ -#else +#else /* CONFIG_SMP */ static inline int mm_is_core_local(struct mm_struct *mm) { return 1; diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index dc4e15937ccf..2d84bca8d053 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -16,8 +16,6 @@ struct device_node; #include <asm/mmzone.h> -#define parent_node(node) (node) - #define cpumask_of_node(node) ((node) == -1 ? \ cpu_all_mask : \ node_to_cpumask_map[node]) diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h new file mode 100644 index 000000000000..fd5963acd658 --- /dev/null +++ b/arch/powerpc/include/asm/vas.h @@ -0,0 +1,159 @@ +/* + * Copyright 2016-17 IBM Corp. + * + * 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. + */ + +#ifndef _ASM_POWERPC_VAS_H +#define _ASM_POWERPC_VAS_H + +/* + * Min and max FIFO sizes are based on Version 1.05 Section 3.1.4.25 + * (Local FIFO Size Register) of the VAS workbook. + */ +#define VAS_RX_FIFO_SIZE_MIN (1 << 10) /* 1KB */ +#define VAS_RX_FIFO_SIZE_MAX (8 << 20) /* 8MB */ + +/* + * Threshold Control Mode: Have paste operation fail if the number of + * requests in receive FIFO exceeds a threshold. + * + * NOTE: No special error code yet if paste is rejected because of these + * limits. So users can't distinguish between this and other errors. + */ +#define VAS_THRESH_DISABLED 0 +#define VAS_THRESH_FIFO_GT_HALF_FULL 1 +#define VAS_THRESH_FIFO_GT_QTR_FULL 2 +#define VAS_THRESH_FIFO_GT_EIGHTH_FULL 3 + +/* + * Get/Set bit fields + */ +#define GET_FIELD(m, v) (((v) & (m)) >> MASK_LSH(m)) +#define MASK_LSH(m) (__builtin_ffsl(m) - 1) +#define SET_FIELD(m, v, val) \ + (((v) & ~(m)) | ((((typeof(v))(val)) << MASK_LSH(m)) & (m))) + +/* + * Co-processor Engine type. + */ +enum vas_cop_type { + VAS_COP_TYPE_FAULT, + VAS_COP_TYPE_842, + VAS_COP_TYPE_842_HIPRI, + VAS_COP_TYPE_GZIP, + VAS_COP_TYPE_GZIP_HIPRI, + VAS_COP_TYPE_FTW, + VAS_COP_TYPE_MAX, +}; + +/* + * Receive window attributes specified by the (in-kernel) owner of window. + */ +struct vas_rx_win_attr { + void *rx_fifo; + int rx_fifo_size; + int wcreds_max; + + bool pin_win; + bool rej_no_credit; + bool tx_wcred_mode; + bool rx_wcred_mode; + bool tx_win_ord_mode; + bool rx_win_ord_mode; + bool data_stamp; + bool nx_win; + bool fault_win; + bool user_win; + bool notify_disable; + bool intr_disable; + bool notify_early; + + int lnotify_lpid; + int lnotify_pid; + int lnotify_tid; + u32 pswid; + + int tc_mode; +}; + +/* + * Window attributes specified by the in-kernel owner of a send window. + */ +struct vas_tx_win_attr { + enum vas_cop_type cop; + int wcreds_max; + int lpid; + int pidr; /* hardware PID (from SPRN_PID) */ + int pid; /* linux process id */ + int pswid; + int rsvd_txbuf_count; + int tc_mode; + + bool user_win; + bool pin_win; + bool rej_no_credit; + bool rsvd_txbuf_enable; + bool tx_wcred_mode; + bool rx_wcred_mode; + bool tx_win_ord_mode; + bool rx_win_ord_mode; +}; + +/* + * Helper to initialize receive window attributes to defaults for an + * NX window. + */ +void vas_init_rx_win_attr(struct vas_rx_win_attr *rxattr, enum vas_cop_type cop); + +/* + * Open a VAS receive window for the instance of VAS identified by @vasid + * Use @attr to initialize the attributes of the window. + * + * Return a handle to the window or ERR_PTR() on error. + */ +struct vas_window *vas_rx_win_open(int vasid, enum vas_cop_type cop, + struct vas_rx_win_attr *attr); + +/* + * Helper to initialize send window attributes to defaults for an NX window. + */ +extern void vas_init_tx_win_attr(struct vas_tx_win_attr *txattr, + enum vas_cop_type cop); + +/* + * Open a VAS send window for the instance of VAS identified by @vasid + * and the co-processor type @cop. Use @attr to initialize attributes + * of the window. + * + * Note: The instance of VAS must already have an open receive window for + * the coprocessor type @cop. + * + * Return a handle to the send window or ERR_PTR() on error. + */ +struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, + struct vas_tx_win_attr *attr); + +/* + * Close the send or receive window identified by @win. For receive windows + * return -EAGAIN if there are active send windows attached to this receive + * window. + */ +int vas_win_close(struct vas_window *win); + +/* + * Copy the co-processor request block (CRB) @crb into the local L2 cache. + */ +int vas_copy_crb(void *crb, int offset); + +/* + * Paste a previously copied CRB (see vas_copy_crb()) from the L2 cache to + * the hardware address associated with the window @win. @re is expected/ + * assumed to be true for NX windows. + */ +int vas_paste_crb(struct vas_window *win, int offset, bool re); + +#endif /* __ASM_POWERPC_VAS_H */ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index c23ff4389ca2..371fbebf1ec9 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -45,6 +45,7 @@ struct xive_irq_data { void __iomem *trig_mmio; u32 esb_shift; int src_chip; + u32 hw_irq; /* Setup/used by frontend */ int target; @@ -55,6 +56,7 @@ struct xive_irq_data { #define XIVE_IRQ_FLAG_SHIFT_BUG 0x04 #define XIVE_IRQ_FLAG_MASK_FW 0x08 #define XIVE_IRQ_FLAG_EOI_FW 0x10 +#define XIVE_IRQ_FLAG_H_INT_ESB 0x20 #define XIVE_INVALID_CHIP_ID -1 @@ -110,11 +112,13 @@ extern bool __xive_enabled; static inline bool xive_enabled(void) { return __xive_enabled; } +extern bool xive_spapr_init(void); extern bool xive_native_init(void); extern void xive_smp_probe(void); extern int xive_smp_prepare_cpu(unsigned int cpu); extern void xive_smp_setup_cpu(void); extern void xive_smp_disable_cpu(void); +extern void xive_teardown_cpu(void); extern void xive_kexec_teardown_cpu(int secondary); extern void xive_shutdown(void); extern void xive_flush_interrupt(void); @@ -147,6 +151,7 @@ extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id) static inline bool xive_enabled(void) { return false; } +static inline bool xive_spapr_init(void) { return false; } static inline bool xive_native_init(void) { return false; } static inline void xive_smp_probe(void) { } extern inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; } diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index ab45cc2f3101..03c06ba7464f 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -29,20 +29,4 @@ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ -/* - * When MAP_HUGETLB is set, bits [26:31] of the flags argument to mmap(2), - * encode the log2 of the huge page size. A value of zero indicates that the - * default huge page size should be used. To use a non-default huge page size, - * one of these defines can be used, or the size can be encoded by hand. Note - * that on most systems only a subset, or possibly none, of these sizes will be - * available. - */ -#define MAP_HUGE_512KB (19 << MAP_HUGE_SHIFT) /* 512KB HugeTLB Page */ -#define MAP_HUGE_1MB (20 << MAP_HUGE_SHIFT) /* 1MB HugeTLB Page */ -#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) /* 2MB HugeTLB Page */ -#define MAP_HUGE_8MB (23 << MAP_HUGE_SHIFT) /* 8MB HugeTLB Page */ -#define MAP_HUGE_16MB (24 << MAP_HUGE_SHIFT) /* 16MB HugeTLB Page */ -#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) /* 1GB HugeTLB Page */ -#define MAP_HUGE_16GB (34 << MAP_HUGE_SHIFT) /* 16GB HugeTLB Page */ - #endif /* _UAPI_ASM_POWERPC_MMAN_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 4aa7c147e447..91960f83039c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -38,7 +38,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \ signal_64.o ptrace32.o \ paca.o nvram_64.o firmware.o obj-$(CONFIG_VDSO32) += vdso32/ -obj-$(CONFIG_HARDLOCKUP_DETECTOR) += watchdog.o +obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o @@ -83,7 +83,7 @@ extra-y := head_$(BITS).o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o -extra-$(CONFIG_8xx) := head_8xx.o +extra-$(CONFIG_PPC_8xx) := head_8xx.o extra-y += vmlinux.lds obj-$(CONFIG_RELOCATABLE) += reloc_$(BITS).o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index ec7a8b099dd9..26b9994d27ee 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -27,6 +27,7 @@ #include <asm/switch_to.h> #include <asm/disassemble.h> #include <asm/cpu_has_feature.h> +#include <asm/sstep.h> struct aligninfo { unsigned char len; @@ -40,364 +41,9 @@ struct aligninfo { #define LD 0 /* load */ #define ST 1 /* store */ #define SE 2 /* sign-extend value, or FP ld/st as word */ -#define F 4 /* to/from fp regs */ -#define U 8 /* update index register */ -#define M 0x10 /* multiple load/store */ #define SW 0x20 /* byte swap */ -#define S 0x40 /* single-precision fp or... */ -#define SX 0x40 /* ... byte count in XER */ -#define HARD 0x80 /* string, stwcx. */ #define E4 0x40 /* SPE endianness is word */ #define E8 0x80 /* SPE endianness is double word */ -#define SPLT 0x80 /* VSX SPLAT load */ - -/* DSISR bits reported for a DCBZ instruction: */ -#define DCBZ 0x5f /* 8xx/82xx dcbz faults when cache not enabled */ - -/* - * The PowerPC stores certain bits of the instruction that caused the - * alignment exception in the DSISR register. This array maps those - * bits to information about the operand length and what the - * instruction would do. - */ -static struct aligninfo aligninfo[128] = { - { 4, LD }, /* 00 0 0000: lwz / lwarx */ - INVALID, /* 00 0 0001 */ - { 4, ST }, /* 00 0 0010: stw */ - INVALID, /* 00 0 0011 */ - { 2, LD }, /* 00 0 0100: lhz */ - { 2, LD+SE }, /* 00 0 0101: lha */ - { 2, ST }, /* 00 0 0110: sth */ - { 4, LD+M }, /* 00 0 0111: lmw */ - { 4, LD+F+S }, /* 00 0 1000: lfs */ - { 8, LD+F }, /* 00 0 1001: lfd */ - { 4, ST+F+S }, /* 00 0 1010: stfs */ - { 8, ST+F }, /* 00 0 1011: stfd */ - { 16, LD }, /* 00 0 1100: lq */ - { 8, LD }, /* 00 0 1101: ld/ldu/lwa */ - INVALID, /* 00 0 1110 */ - { 8, ST }, /* 00 0 1111: std/stdu */ - { 4, LD+U }, /* 00 1 0000: lwzu */ - INVALID, /* 00 1 0001 */ - { 4, ST+U }, /* 00 1 0010: stwu */ - INVALID, /* 00 1 0011 */ - { 2, LD+U }, /* 00 1 0100: lhzu */ - { 2, LD+SE+U }, /* 00 1 0101: lhau */ - { 2, ST+U }, /* 00 1 0110: sthu */ - { 4, ST+M }, /* 00 1 0111: stmw */ - { 4, LD+F+S+U }, /* 00 1 1000: lfsu */ - { 8, LD+F+U }, /* 00 1 1001: lfdu */ - { 4, ST+F+S+U }, /* 00 1 1010: stfsu */ - { 8, ST+F+U }, /* 00 1 1011: stfdu */ - { 16, LD+F }, /* 00 1 1100: lfdp */ - INVALID, /* 00 1 1101 */ - { 16, ST+F }, /* 00 1 1110: stfdp */ - INVALID, /* 00 1 1111 */ - { 8, LD }, /* 01 0 0000: ldx */ - INVALID, /* 01 0 0001 */ - { 8, ST }, /* 01 0 0010: stdx */ - INVALID, /* 01 0 0011 */ - INVALID, /* 01 0 0100 */ - { 4, LD+SE }, /* 01 0 0101: lwax */ - INVALID, /* 01 0 0110 */ - INVALID, /* 01 0 0111 */ - { 4, LD+M+HARD+SX }, /* 01 0 1000: lswx */ - { 4, LD+M+HARD }, /* 01 0 1001: lswi */ - { 4, ST+M+HARD+SX }, /* 01 0 1010: stswx */ - { 4, ST+M+HARD }, /* 01 0 1011: stswi */ - INVALID, /* 01 0 1100 */ - { 8, LD+U }, /* 01 0 1101: ldu */ - INVALID, /* 01 0 1110 */ - { 8, ST+U }, /* 01 0 1111: stdu */ - { 8, LD+U }, /* 01 1 0000: ldux */ - INVALID, /* 01 1 0001 */ - { 8, ST+U }, /* 01 1 0010: stdux */ - INVALID, /* 01 1 0011 */ - INVALID, /* 01 1 0100 */ - { 4, LD+SE+U }, /* 01 1 0101: lwaux */ - INVALID, /* 01 1 0110 */ - INVALID, /* 01 1 0111 */ - INVALID, /* 01 1 1000 */ - INVALID, /* 01 1 1001 */ - INVALID, /* 01 1 1010 */ - INVALID, /* 01 1 1011 */ - INVALID, /* 01 1 1100 */ - INVALID, /* 01 1 1101 */ - INVALID, /* 01 1 1110 */ - INVALID, /* 01 1 1111 */ - INVALID, /* 10 0 0000 */ - INVALID, /* 10 0 0001 */ - INVALID, /* 10 0 0010: stwcx. */ - INVALID, /* 10 0 0011 */ - INVALID, /* 10 0 0100 */ - INVALID, /* 10 0 0101 */ - INVALID, /* 10 0 0110 */ - INVALID, /* 10 0 0111 */ - { 4, LD+SW }, /* 10 0 1000: lwbrx */ - INVALID, /* 10 0 1001 */ - { 4, ST+SW }, /* 10 0 1010: stwbrx */ - INVALID, /* 10 0 1011 */ - { 2, LD+SW }, /* 10 0 1100: lhbrx */ - { 4, LD+SE }, /* 10 0 1101 lwa */ - { 2, ST+SW }, /* 10 0 1110: sthbrx */ - { 16, ST }, /* 10 0 1111: stq */ - INVALID, /* 10 1 0000 */ - INVALID, /* 10 1 0001 */ - INVALID, /* 10 1 0010 */ - INVALID, /* 10 1 0011 */ - INVALID, /* 10 1 0100 */ - INVALID, /* 10 1 0101 */ - INVALID, /* 10 1 0110 */ - INVALID, /* 10 1 0111 */ - INVALID, /* 10 1 1000 */ - INVALID, /* 10 1 1001 */ - INVALID, /* 10 1 1010 */ - INVALID, /* 10 1 1011 */ - INVALID, /* 10 1 1100 */ - INVALID, /* 10 1 1101 */ - INVALID, /* 10 1 1110 */ - { 0, ST+HARD }, /* 10 1 1111: dcbz */ - { 4, LD }, /* 11 0 0000: lwzx */ - INVALID, /* 11 0 0001 */ - { 4, ST }, /* 11 0 0010: stwx */ - INVALID, /* 11 0 0011 */ - { 2, LD }, /* 11 0 0100: lhzx */ - { 2, LD+SE }, /* 11 0 0101: lhax */ - { 2, ST }, /* 11 0 0110: sthx */ - INVALID, /* 11 0 0111 */ - { 4, LD+F+S }, /* 11 0 1000: lfsx */ - { 8, LD+F }, /* 11 0 1001: lfdx */ - { 4, ST+F+S }, /* 11 0 1010: stfsx */ - { 8, ST+F }, /* 11 0 1011: stfdx */ - { 16, LD+F }, /* 11 0 1100: lfdpx */ - { 4, LD+F+SE }, /* 11 0 1101: lfiwax */ - { 16, ST+F }, /* 11 0 1110: stfdpx */ - { 4, ST+F }, /* 11 0 1111: stfiwx */ - { 4, LD+U }, /* 11 1 0000: lwzux */ - INVALID, /* 11 1 0001 */ - { 4, ST+U }, /* 11 1 0010: stwux */ - INVALID, /* 11 1 0011 */ - { 2, LD+U }, /* 11 1 0100: lhzux */ - { 2, LD+SE+U }, /* 11 1 0101: lhaux */ - { 2, ST+U }, /* 11 1 0110: sthux */ - INVALID, /* 11 1 0111 */ - { 4, LD+F+S+U }, /* 11 1 1000: lfsux */ - { 8, LD+F+U }, /* 11 1 1001: lfdux */ - { 4, ST+F+S+U }, /* 11 1 1010: stfsux */ - { 8, ST+F+U }, /* 11 1 1011: stfdux */ - INVALID, /* 11 1 1100 */ - { 4, LD+F }, /* 11 1 1101: lfiwzx */ - INVALID, /* 11 1 1110 */ - INVALID, /* 11 1 1111 */ -}; - -/* - * The dcbz (data cache block zero) instruction - * gives an alignment fault if used on non-cacheable - * memory. We handle the fault mainly for the - * case when we are running with the cache disabled - * for debugging. - */ -static int emulate_dcbz(struct pt_regs *regs, unsigned char __user *addr) -{ - long __user *p; - int i, size; - -#ifdef __powerpc64__ - size = ppc64_caches.l1d.block_size; -#else - size = L1_CACHE_BYTES; -#endif - p = (long __user *) (regs->dar & -size); - if (user_mode(regs) && !access_ok(VERIFY_WRITE, p, size)) - return -EFAULT; - for (i = 0; i < size / sizeof(long); ++i) - if (__put_user_inatomic(0, p+i)) - return -EFAULT; - return 1; -} - -/* - * Emulate load & store multiple instructions - * On 64-bit machines, these instructions only affect/use the - * bottom 4 bytes of each register, and the loads clear the - * top 4 bytes of the affected register. - */ -#ifdef __BIG_ENDIAN__ -#ifdef CONFIG_PPC64 -#define REG_BYTE(rp, i) *((u8 *)((rp) + ((i) >> 2)) + ((i) & 3) + 4) -#else -#define REG_BYTE(rp, i) *((u8 *)(rp) + (i)) -#endif -#else -#define REG_BYTE(rp, i) (*(((u8 *)((rp) + ((i)>>2)) + ((i)&3)))) -#endif - -#define SWIZ_PTR(p) ((unsigned char __user *)((p) ^ swiz)) - -static int emulate_multiple(struct pt_regs *regs, unsigned char __user *addr, - unsigned int reg, unsigned int nb, - unsigned int flags, unsigned int instr, - unsigned long swiz) -{ - unsigned long *rptr; - unsigned int nb0, i, bswiz; - unsigned long p; - - /* - * We do not try to emulate 8 bytes multiple as they aren't really - * available in our operating environments and we don't try to - * emulate multiples operations in kernel land as they should never - * be used/generated there at least not on unaligned boundaries - */ - if (unlikely((nb > 4) || !user_mode(regs))) - return 0; - - /* lmw, stmw, lswi/x, stswi/x */ - nb0 = 0; - if (flags & HARD) { - if (flags & SX) { - nb = regs->xer & 127; - if (nb == 0) - return 1; - } else { - unsigned long pc = regs->nip ^ (swiz & 4); - - if (__get_user_inatomic(instr, - (unsigned int __user *)pc)) - return -EFAULT; - if (swiz == 0 && (flags & SW)) - instr = cpu_to_le32(instr); - nb = (instr >> 11) & 0x1f; - if (nb == 0) - nb = 32; - } - if (nb + reg * 4 > 128) { - nb0 = nb + reg * 4 - 128; - nb = 128 - reg * 4; - } -#ifdef __LITTLE_ENDIAN__ - /* - * String instructions are endian neutral but the code - * below is not. Force byte swapping on so that the - * effects of swizzling are undone in the load/store - * loops below. - */ - flags ^= SW; -#endif - } else { - /* lwm, stmw */ - nb = (32 - reg) * 4; - } - - if (!access_ok((flags & ST ? VERIFY_WRITE: VERIFY_READ), addr, nb+nb0)) - return -EFAULT; /* bad address */ - - rptr = ®s->gpr[reg]; - p = (unsigned long) addr; - bswiz = (flags & SW)? 3: 0; - - if (!(flags & ST)) { - /* - * This zeroes the top 4 bytes of the affected registers - * in 64-bit mode, and also zeroes out any remaining - * bytes of the last register for lsw*. - */ - memset(rptr, 0, ((nb + 3) / 4) * sizeof(unsigned long)); - if (nb0 > 0) - memset(®s->gpr[0], 0, - ((nb0 + 3) / 4) * sizeof(unsigned long)); - - for (i = 0; i < nb; ++i, ++p) - if (__get_user_inatomic(REG_BYTE(rptr, i ^ bswiz), - SWIZ_PTR(p))) - return -EFAULT; - if (nb0 > 0) { - rptr = ®s->gpr[0]; - addr += nb; - for (i = 0; i < nb0; ++i, ++p) - if (__get_user_inatomic(REG_BYTE(rptr, - i ^ bswiz), - SWIZ_PTR(p))) - return -EFAULT; - } - - } else { - for (i = 0; i < nb; ++i, ++p) - if (__put_user_inatomic(REG_BYTE(rptr, i ^ bswiz), - SWIZ_PTR(p))) - return -EFAULT; - if (nb0 > 0) { - rptr = ®s->gpr[0]; - addr += nb; - for (i = 0; i < nb0; ++i, ++p) - if (__put_user_inatomic(REG_BYTE(rptr, - i ^ bswiz), - SWIZ_PTR(p))) - return -EFAULT; - } - } - return 1; -} - -/* - * Emulate floating-point pair loads and stores. - * Only POWER6 has these instructions, and it does true little-endian, - * so we don't need the address swizzling. - */ -static int emulate_fp_pair(unsigned char __user *addr, unsigned int reg, - unsigned int flags) -{ - char *ptr0 = (char *) ¤t->thread.TS_FPR(reg); - char *ptr1 = (char *) ¤t->thread.TS_FPR(reg+1); - int i, ret, sw = 0; - - if (reg & 1) - return 0; /* invalid form: FRS/FRT must be even */ - if (flags & SW) - sw = 7; - ret = 0; - for (i = 0; i < 8; ++i) { - if (!(flags & ST)) { - ret |= __get_user(ptr0[i^sw], addr + i); - ret |= __get_user(ptr1[i^sw], addr + i + 8); - } else { - ret |= __put_user(ptr0[i^sw], addr + i); - ret |= __put_user(ptr1[i^sw], addr + i + 8); - } - } - if (ret) - return -EFAULT; - return 1; /* exception handled and fixed up */ -} - -#ifdef CONFIG_PPC64 -static int emulate_lq_stq(struct pt_regs *regs, unsigned char __user *addr, - unsigned int reg, unsigned int flags) -{ - char *ptr0 = (char *)®s->gpr[reg]; - char *ptr1 = (char *)®s->gpr[reg+1]; - int i, ret, sw = 0; - - if (reg & 1) - return 0; /* invalid form: GPR must be even */ - if (flags & SW) - sw = 7; - ret = 0; - for (i = 0; i < 8; ++i) { - if (!(flags & ST)) { - ret |= __get_user(ptr0[i^sw], addr + i); - ret |= __get_user(ptr1[i^sw], addr + i + 8); - } else { - ret |= __put_user(ptr0[i^sw], addr + i); - ret |= __put_user(ptr1[i^sw], addr + i + 8); - } - } - if (ret) - return -EFAULT; - return 1; /* exception handled and fixed up */ -} -#endif /* CONFIG_PPC64 */ #ifdef CONFIG_SPE @@ -636,133 +282,21 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, } #endif /* CONFIG_SPE */ -#ifdef CONFIG_VSX -/* - * Emulate VSX instructions... - */ -static int emulate_vsx(unsigned char __user *addr, unsigned int reg, - unsigned int areg, struct pt_regs *regs, - unsigned int flags, unsigned int length, - unsigned int elsize) -{ - char *ptr; - unsigned long *lptr; - int ret = 0; - int sw = 0; - int i, j; - - /* userland only */ - if (unlikely(!user_mode(regs))) - return 0; - - flush_vsx_to_thread(current); - - if (reg < 32) - ptr = (char *) ¤t->thread.fp_state.fpr[reg][0]; - else - ptr = (char *) ¤t->thread.vr_state.vr[reg - 32]; - - lptr = (unsigned long *) ptr; - -#ifdef __LITTLE_ENDIAN__ - if (flags & SW) { - elsize = length; - sw = length-1; - } else { - /* - * The elements are BE ordered, even in LE mode, so process - * them in reverse order. - */ - addr += length - elsize; - - /* 8 byte memory accesses go in the top 8 bytes of the VR */ - if (length == 8) - ptr += 8; - } -#else - if (flags & SW) - sw = elsize-1; -#endif - - for (j = 0; j < length; j += elsize) { - for (i = 0; i < elsize; ++i) { - if (flags & ST) - ret |= __put_user(ptr[i^sw], addr + i); - else - ret |= __get_user(ptr[i^sw], addr + i); - } - ptr += elsize; -#ifdef __LITTLE_ENDIAN__ - addr -= elsize; -#else - addr += elsize; -#endif - } - -#ifdef __BIG_ENDIAN__ -#define VSX_HI 0 -#define VSX_LO 1 -#else -#define VSX_HI 1 -#define VSX_LO 0 -#endif - - if (!ret) { - if (flags & U) - regs->gpr[areg] = regs->dar; - - /* Splat load copies the same data to top and bottom 8 bytes */ - if (flags & SPLT) - lptr[VSX_LO] = lptr[VSX_HI]; - /* For 8 byte loads, zero the low 8 bytes */ - else if (!(flags & ST) && (8 == length)) - lptr[VSX_LO] = 0; - } else - return -EFAULT; - - return 1; -} -#endif - /* * Called on alignment exception. Attempts to fixup * * Return 1 on success * Return 0 if unable to handle the interrupt * Return -EFAULT if data address is bad + * Other negative return values indicate that the instruction can't + * be emulated, and the process should be given a SIGBUS. */ int fix_alignment(struct pt_regs *regs) { - unsigned int instr, nb, flags, instruction = 0; - unsigned int reg, areg; - unsigned int dsisr; - unsigned char __user *addr; - unsigned long p, swiz; - int ret, i; - union data { - u64 ll; - double dd; - unsigned char v[8]; - struct { -#ifdef __LITTLE_ENDIAN__ - int low32; - unsigned hi32; -#else - unsigned hi32; - int low32; -#endif - } x32; - struct { -#ifdef __LITTLE_ENDIAN__ - short low16; - unsigned char hi48[6]; -#else - unsigned char hi48[6]; - short low16; -#endif - } x16; - } data; + unsigned int instr; + struct instruction_op op; + int r, type; /* * We require a complete register set, if not, then our assembly @@ -770,121 +304,23 @@ int fix_alignment(struct pt_regs *regs) */ CHECK_FULL_REGS(regs); - dsisr = regs->dsisr; - - /* Some processors don't provide us with a DSISR we can use here, - * let's make one up from the instruction - */ - if (cpu_has_feature(CPU_FTR_NODSISRALIGN)) { - unsigned long pc = regs->nip; - - if (cpu_has_feature(CPU_FTR_PPC_LE) && (regs->msr & MSR_LE)) - pc ^= 4; - if (unlikely(__get_user_inatomic(instr, - (unsigned int __user *)pc))) - return -EFAULT; - if (cpu_has_feature(CPU_FTR_REAL_LE) && (regs->msr & MSR_LE)) - instr = cpu_to_le32(instr); - dsisr = make_dsisr(instr); - instruction = instr; + if (unlikely(__get_user(instr, (unsigned int __user *)regs->nip))) + return -EFAULT; + if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) { + /* We don't handle PPC little-endian any more... */ + if (cpu_has_feature(CPU_FTR_PPC_LE)) + return -EIO; + instr = swab32(instr); } - /* extract the operation and registers from the dsisr */ - reg = (dsisr >> 5) & 0x1f; /* source/dest register */ - areg = dsisr & 0x1f; /* register to update */ - #ifdef CONFIG_SPE if ((instr >> 26) == 0x4) { + int reg = (instr >> 21) & 0x1f; PPC_WARN_ALIGNMENT(spe, regs); return emulate_spe(regs, reg, instr); } #endif - instr = (dsisr >> 10) & 0x7f; - instr |= (dsisr >> 13) & 0x60; - - /* Lookup the operation in our table */ - nb = aligninfo[instr].len; - flags = aligninfo[instr].flags; - - /* - * Handle some cases which give overlaps in the DSISR values. - */ - if (IS_XFORM(instruction)) { - switch (get_xop(instruction)) { - case 532: /* ldbrx */ - nb = 8; - flags = LD+SW; - break; - case 660: /* stdbrx */ - nb = 8; - flags = ST+SW; - break; - case 20: /* lwarx */ - case 84: /* ldarx */ - case 116: /* lharx */ - case 276: /* lqarx */ - return 0; /* not emulated ever */ - } - } - - /* Byteswap little endian loads and stores */ - swiz = 0; - if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) { - flags ^= SW; -#ifdef __BIG_ENDIAN__ - /* - * So-called "PowerPC little endian" mode works by - * swizzling addresses rather than by actually doing - * any byte-swapping. To emulate this, we XOR each - * byte address with 7. We also byte-swap, because - * the processor's address swizzling depends on the - * operand size (it xors the address with 7 for bytes, - * 6 for halfwords, 4 for words, 0 for doublewords) but - * we will xor with 7 and load/store each byte separately. - */ - if (cpu_has_feature(CPU_FTR_PPC_LE)) - swiz = 7; -#endif - } - - /* DAR has the operand effective address */ - addr = (unsigned char __user *)regs->dar; - -#ifdef CONFIG_VSX - if ((instruction & 0xfc00003e) == 0x7c000018) { - unsigned int elsize; - - /* Additional register addressing bit (64 VSX vs 32 FPR/GPR) */ - reg |= (instruction & 0x1) << 5; - /* Simple inline decoder instead of a table */ - /* VSX has only 8 and 16 byte memory accesses */ - nb = 8; - if (instruction & 0x200) - nb = 16; - - /* Vector stores in little-endian mode swap individual - elements, so process them separately */ - elsize = 4; - if (instruction & 0x80) - elsize = 8; - - flags = 0; - if ((regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE)) - flags |= SW; - if (instruction & 0x100) - flags |= ST; - if (instruction & 0x040) - flags |= U; - /* splat load needs a special decoder */ - if ((instruction & 0x400) == 0){ - flags |= SPLT; - nb = 8; - } - PPC_WARN_ALIGNMENT(vsx, regs); - return emulate_vsx(addr, reg, areg, regs, flags, nb, elsize); - } -#endif /* * ISA 3.0 (such as P9) copy, copy_first, paste and paste_last alignment @@ -896,173 +332,27 @@ int fix_alignment(struct pt_regs *regs) * when pasting to a co-processor. Furthermore, paste_last is the * synchronisation point for preceding copy/paste sequences. */ - if ((instruction & 0xfc0006fe) == PPC_INST_COPY) + if ((instr & 0xfc0006fe) == PPC_INST_COPY) return -EIO; - /* A size of 0 indicates an instruction we don't support, with - * the exception of DCBZ which is handled as a special case here - */ - if (instr == DCBZ) { - PPC_WARN_ALIGNMENT(dcbz, regs); - return emulate_dcbz(regs, addr); - } - if (unlikely(nb == 0)) - return 0; - - /* Load/Store Multiple instructions are handled in their own - * function - */ - if (flags & M) { - PPC_WARN_ALIGNMENT(multiple, regs); - return emulate_multiple(regs, addr, reg, nb, - flags, instr, swiz); - } - - /* Verify the address of the operand */ - if (unlikely(user_mode(regs) && - !access_ok((flags & ST ? VERIFY_WRITE : VERIFY_READ), - addr, nb))) - return -EFAULT; - - /* Force the fprs into the save area so we can reference them */ - if (flags & F) { - /* userland only */ - if (unlikely(!user_mode(regs))) - return 0; - flush_fp_to_thread(current); - } + r = analyse_instr(&op, regs, instr); + if (r < 0) + return -EINVAL; - if (nb == 16) { - if (flags & F) { - /* Special case for 16-byte FP loads and stores */ - PPC_WARN_ALIGNMENT(fp_pair, regs); - return emulate_fp_pair(addr, reg, flags); - } else { -#ifdef CONFIG_PPC64 - /* Special case for 16-byte loads and stores */ - PPC_WARN_ALIGNMENT(lq_stq, regs); - return emulate_lq_stq(regs, addr, reg, flags); -#else - return 0; -#endif - } - } - - PPC_WARN_ALIGNMENT(unaligned, regs); - - /* If we are loading, get the data from user space, else - * get it from register values - */ - if (!(flags & ST)) { - unsigned int start = 0; - - switch (nb) { - case 4: - start = offsetof(union data, x32.low32); - break; - case 2: - start = offsetof(union data, x16.low16); - break; - } - - data.ll = 0; - ret = 0; - p = (unsigned long)addr; - - for (i = 0; i < nb; i++) - ret |= __get_user_inatomic(data.v[start + i], - SWIZ_PTR(p++)); - - if (unlikely(ret)) - return -EFAULT; - - } else if (flags & F) { - data.ll = current->thread.TS_FPR(reg); - if (flags & S) { - /* Single-precision FP store requires conversion... */ -#ifdef CONFIG_PPC_FPU - preempt_disable(); - enable_kernel_fp(); - cvt_df(&data.dd, (float *)&data.x32.low32); - disable_kernel_fp(); - preempt_enable(); -#else - return 0; -#endif - } - } else - data.ll = regs->gpr[reg]; - - if (flags & SW) { - switch (nb) { - case 8: - data.ll = swab64(data.ll); - break; - case 4: - data.x32.low32 = swab32(data.x32.low32); - break; - case 2: - data.x16.low16 = swab16(data.x16.low16); - break; - } - } - - /* Perform other misc operations like sign extension - * or floating point single precision conversion - */ - switch (flags & ~(U|SW)) { - case LD+SE: /* sign extending integer loads */ - case LD+F+SE: /* sign extend for lfiwax */ - if ( nb == 2 ) - data.ll = data.x16.low16; - else /* nb must be 4 */ - data.ll = data.x32.low32; - break; - - /* Single-precision FP load requires conversion... */ - case LD+F+S: -#ifdef CONFIG_PPC_FPU - preempt_disable(); - enable_kernel_fp(); - cvt_fd((float *)&data.x32.low32, &data.dd); - disable_kernel_fp(); - preempt_enable(); -#else - return 0; -#endif - break; + type = op.type & INSTR_TYPE_MASK; + if (!OP_IS_LOAD_STORE(type)) { + if (type != CACHEOP + DCBZ) + return -EINVAL; + PPC_WARN_ALIGNMENT(dcbz, regs); + r = emulate_dcbz(op.ea, regs); + } else { + if (type == LARX || type == STCX) + return -EIO; + PPC_WARN_ALIGNMENT(unaligned, regs); + r = emulate_loadstore(regs, &op); } - /* Store result to memory or update registers */ - if (flags & ST) { - unsigned int start = 0; - - switch (nb) { - case 4: - start = offsetof(union data, x32.low32); - break; - case 2: - start = offsetof(union data, x16.low16); - break; - } - - ret = 0; - p = (unsigned long)addr; - - for (i = 0; i < nb; i++) - ret |= __put_user_inatomic(data.v[start + i], - SWIZ_PTR(p++)); - - if (unlikely(ret)) - return -EFAULT; - } else if (flags & F) - current->thread.TS_FPR(reg) = data.ll; - else - regs->gpr[reg] = data.ll; - - /* Update RA as needed */ - if (flags & U) - regs->gpr[areg] = regs->dar; - - return 1; + if (!r) + return 1; + return r; } diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6e95c2c19a7e..8cfb20e38cfe 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -746,6 +746,14 @@ int main(void) OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask); OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas); OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr); +#define STOP_SPR(x, f) OFFSET(x, paca_struct, stop_sprs.f) + STOP_SPR(STOP_PID, pid); + STOP_SPR(STOP_LDBAR, ldbar); + STOP_SPR(STOP_FSCR, fscr); + STOP_SPR(STOP_HFSCR, hfscr); + STOP_SPR(STOP_MMCR1, mmcr1); + STOP_SPR(STOP_MMCR2, mmcr2); + STOP_SPR(STOP_MMCRA, mmcra); #endif DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER); diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 8275858a434d..3f46ca1c59f9 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -253,7 +253,7 @@ int __init btext_find_display(int allow_nonstdout) for_each_node_by_type(np, "display") { if (of_get_property(np, "linux,opened", NULL)) { - printk("trying %s ...\n", np->full_name); + printk("trying %pOF ...\n", np); rc = btext_initialize(np); printk("result: %d\n", rc); } diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index c641983bbdd6..a8f20e5928e1 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -167,10 +167,10 @@ static void release_cache_debugcheck(struct cache *cache) 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 for %pOF(%s) refers to cache for %pOF(%s)\n", + iter->ofnode, cache_type_string(iter), - cache->ofnode->full_name, + cache->ofnode, cache_type_string(cache)); } @@ -179,8 +179,8 @@ 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); + pr_debug("freeing L%d %s cache for %pOF\n", cache->level, + cache_type_string(cache), cache->ofnode); release_cache_debugcheck(cache); list_del(&cache->list); @@ -194,8 +194,8 @@ static void cache_cpu_set(struct cache *cache, int cpu) 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, + "CPU %i already accounted in %pOF(%s)\n", + cpu, next->ofnode, cache_type_string(next)); cpumask_set_cpu(cpu, &next->shared_cpu_map); next = next->next_local; @@ -355,7 +355,7 @@ static int cache_is_unified_d(const struct device_node *np) */ static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level) { - pr_debug("creating L%d ucache for %s\n", level, node->full_name); + pr_debug("creating L%d ucache for %pOF\n", level, node); return new_cache(cache_is_unified_d(node), level, node); } @@ -365,8 +365,8 @@ static struct cache *cache_do_one_devnode_split(struct device_node *node, { struct cache *dcache, *icache; - pr_debug("creating L%d dcache and icache for %s\n", level, - node->full_name); + pr_debug("creating L%d dcache and icache for %pOF\n", level, + node); dcache = new_cache(CACHE_TYPE_DATA, level, node); icache = new_cache(CACHE_TYPE_INSTRUCTION, level, node); @@ -679,7 +679,6 @@ static struct kobj_type cache_index_type = { static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir) { - const char *cache_name; const char *cache_type; struct cache *cache; char *buf; @@ -690,7 +689,6 @@ static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir) 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 @@ -707,14 +705,14 @@ static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir) 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, + "%pOF(%s) (rc = %zd)\n", + attr->attr.name, cache->ofnode, 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); + pr_debug("could not create %s attribute for %pOF(%s)\n", + attr->attr.name, cache->ofnode, cache_type); } kfree(buf); @@ -831,8 +829,8 @@ static void cache_cpu_clear(struct cache *cache, int cpu) 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, + "CPU %i not accounted in %pOF(%s)\n", + cpu, cache->ofnode, cache_type_string(cache)); cpumask_clear_cpu(cpu, &cache->shared_cpu_map); diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 6f849832a669..760872916013 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -1259,10 +1259,10 @@ static struct cpu_spec __initdata cpu_specs[] = { .platform = "ppc603", }, #endif /* CONFIG_PPC_BOOK3S_32 */ -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx { /* 8xx */ .pvr_mask = 0xffff0000, - .pvr_value = 0x00500000, + .pvr_value = PVR_8xx, .cpu_name = "8xx", /* CPU_FTR_MAYBE_CAN_DOZE is possible, * if the 8xx code is there.... */ @@ -1274,7 +1274,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_8xx, .platform = "ppc823", }, -#endif /* CONFIG_8xx */ +#endif /* CONFIG_PPC_8xx */ #ifdef CONFIG_40x { /* 403GC */ .pvr_mask = 0xffffff00, @@ -1936,6 +1936,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_440A, .platform = "ppc440", }, +#ifdef CONFIG_PPC_47x { /* 476 DD2 core */ .pvr_mask = 0xffffffff, .pvr_value = 0x11a52080, @@ -1992,6 +1993,7 @@ static struct cpu_spec __initdata cpu_specs[] = { .machine_check = machine_check_47x, .platform = "ppc470", }, +#endif /* CONFIG_PPC_47x */ { /* default match */ .pvr_mask = 0x00000000, .pvr_value = 0x00000000, diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 63992b2d8e15..9e816787c0d4 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -44,6 +44,7 @@ #include <asm/machdep.h> #include <asm/ppc-pci.h> #include <asm/rtas.h> +#include <asm/pte-walk.h> /** Overview: @@ -169,10 +170,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) char buffer[128]; n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", - edev->phb->global_number, pdn->busno, + pdn->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", - edev->phb->global_number, pdn->busno, + pdn->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg); @@ -352,8 +353,7 @@ static inline unsigned long eeh_token_to_phys(unsigned long token) * worried about _PAGE_SPLITTING/collapse. Also we will not hit * page table free, because of init_mm. */ - ptep = __find_linux_pte_or_hugepte(init_mm.pgd, token, - NULL, &hugepage_shift); + ptep = find_init_mm_pte(token, &hugepage_shift); if (!ptep) return token; WARN_ON(hugepage_shift); @@ -435,7 +435,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) int ret; int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE); unsigned long flags; - struct pci_dn *pdn; + struct device_node *dn; struct pci_dev *dev; struct eeh_pe *pe, *parent_pe, *phb_pe; int rc = 0; @@ -493,9 +493,10 @@ int eeh_dev_check_failure(struct eeh_dev *edev) if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; if (pe->check_count % EEH_MAX_FAILS == 0) { - pdn = eeh_dev_to_pdn(edev); - if (pdn->node) - location = of_get_property(pdn->node, "ibm,loc-code", NULL); + dn = pci_device_to_OF_node(dev); + if (dn) + location = of_get_property(dn, "ibm,loc-code", + NULL); printk(KERN_ERR "EEH: %d reads ignored for recovering device at " "location=%s driver=%s pci addr=%s\n", pe->check_count, @@ -1064,7 +1065,7 @@ core_initcall_sync(eeh_init); */ void eeh_add_device_early(struct pci_dn *pdn) { - struct pci_controller *phb; + struct pci_controller *phb = pdn ? pdn->phb : NULL; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); if (!edev) @@ -1074,7 +1075,6 @@ void eeh_add_device_early(struct pci_dn *pdn) return; /* USB Bus children of PCI devices will not have BUID's */ - phb = edev->phb; if (NULL == phb || (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid)) return; diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c index d6b2ca70d14d..ad04ecd63c20 100644 --- a/arch/powerpc/kernel/eeh_dev.c +++ b/arch/powerpc/kernel/eeh_dev.c @@ -50,21 +50,16 @@ */ struct eeh_dev *eeh_dev_init(struct pci_dn *pdn) { - struct pci_controller *phb = pdn->phb; struct eeh_dev *edev; /* Allocate EEH device */ edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) { - pr_warn("%s: out of memory\n", - __func__); + if (!edev) return NULL; - } /* Associate EEH device with OF node */ pdn->edev = edev; edev->pdn = pdn; - edev->phb = phb; INIT_LIST_HEAD(&edev->list); INIT_LIST_HEAD(&edev->rmv_list); diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index c405c79e50cd..8b840191df59 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -428,7 +428,7 @@ static void *eeh_add_virt_device(void *data, void *userdata) if (!(edev->physfn)) { pr_warn("%s: EEH dev %04x:%02x:%02x.%01x not for VF\n", - __func__, edev->phb->global_number, pdn->busno, + __func__, pdn->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); return NULL; } diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index cc4b206f77e4..2e8d1b2b5af4 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -230,10 +230,15 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root, * Bus/Device/Function number. The extra data referred by flag * indicates which type of address should be used. */ +struct eeh_pe_get_flag { + int pe_no; + int config_addr; +}; + static void *__eeh_pe_get(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - struct eeh_dev *edev = (struct eeh_dev *)flag; + struct eeh_pe_get_flag *tmp = (struct eeh_pe_get_flag *) flag; /* Unexpected PHB PE */ if (pe->type & EEH_PE_PHB) @@ -244,17 +249,17 @@ static void *__eeh_pe_get(void *data, void *flag) * have non-zero PE address */ if (eeh_has_flag(EEH_VALID_PE_ZERO)) { - if (edev->pe_config_addr == pe->addr) + if (tmp->pe_no == pe->addr) return pe; } else { - if (edev->pe_config_addr && - (edev->pe_config_addr == pe->addr)) + if (tmp->pe_no && + (tmp->pe_no == pe->addr)) return pe; } /* Try BDF address */ - if (edev->config_addr && - (edev->config_addr == pe->config_addr)) + if (tmp->config_addr && + (tmp->config_addr == pe->config_addr)) return pe; return NULL; @@ -262,7 +267,9 @@ static void *__eeh_pe_get(void *data, void *flag) /** * eeh_pe_get - Search PE based on the given address - * @edev: EEH device + * @phb: PCI controller + * @pe_no: PE number + * @config_addr: Config address * * Search the corresponding PE based on the specified address which * is included in the eeh device. The function is used to check if @@ -271,12 +278,14 @@ static void *__eeh_pe_get(void *data, void *flag) * which is composed of PCI bus/device/function number, or unified * PE address. */ -struct eeh_pe *eeh_pe_get(struct eeh_dev *edev) +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, + int pe_no, int config_addr) { - struct eeh_pe *root = eeh_phb_pe_get(edev->phb); + struct eeh_pe *root = eeh_phb_pe_get(phb); + struct eeh_pe_get_flag tmp = { pe_no, config_addr }; struct eeh_pe *pe; - pe = eeh_pe_traverse(root, __eeh_pe_get, edev); + pe = eeh_pe_traverse(root, __eeh_pe_get, &tmp); return pe; } @@ -330,11 +339,13 @@ static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) int eeh_add_to_parent_pe(struct eeh_dev *edev) { struct eeh_pe *pe, *parent; + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + int config_addr = (pdn->busno << 8) | (pdn->devfn); /* Check if the PE number is valid */ if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%x\n", - __func__, edev->config_addr, edev->phb->global_number); + __func__, config_addr, pdn->phb->global_number); return -EINVAL; } @@ -344,7 +355,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) * PE should be composed of PCI bus and its subordinate * components. */ - pe = eeh_pe_get(edev); + pe = eeh_pe_get(pdn->phb, edev->pe_config_addr, config_addr); if (pe && !(pe->type & EEH_PE_INVALID)) { /* Mark the PE as type of PCI bus */ pe->type = EEH_PE_BUS; @@ -353,11 +364,11 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) /* Put the edev to PE */ list_add_tail(&edev->list, &pe->edevs); pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n", - edev->phb->global_number, - edev->config_addr >> 8, - PCI_SLOT(edev->config_addr & 0xFF), - PCI_FUNC(edev->config_addr & 0xFF), - pe->addr); + pdn->phb->global_number, + pdn->busno, + PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn), + pe->addr); return 0; } else if (pe && (pe->type & EEH_PE_INVALID)) { list_add_tail(&edev->list, &pe->edevs); @@ -376,25 +387,25 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device " "PE#%x, Parent PE#%x\n", - edev->phb->global_number, - edev->config_addr >> 8, - PCI_SLOT(edev->config_addr & 0xFF), - PCI_FUNC(edev->config_addr & 0xFF), - pe->addr, pe->parent->addr); + pdn->phb->global_number, + pdn->busno, + PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn), + pe->addr, pe->parent->addr); return 0; } /* Create a new EEH PE */ if (edev->physfn) - pe = eeh_pe_alloc(edev->phb, EEH_PE_VF); + pe = eeh_pe_alloc(pdn->phb, EEH_PE_VF); else - pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE); + pe = eeh_pe_alloc(pdn->phb, EEH_PE_DEVICE); if (!pe) { pr_err("%s: out of memory!\n", __func__); return -ENOMEM; } pe->addr = edev->pe_config_addr; - pe->config_addr = edev->config_addr; + pe->config_addr = config_addr; /* * Put the new EEH PE into hierarchy tree. If the parent @@ -404,10 +415,10 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) */ parent = eeh_pe_get_parent(edev); if (!parent) { - parent = eeh_phb_pe_get(edev->phb); + parent = eeh_phb_pe_get(pdn->phb); if (!parent) { pr_err("%s: No PHB PE is found (PHB Domain=%d)\n", - __func__, edev->phb->global_number); + __func__, pdn->phb->global_number); edev->pe = NULL; kfree(pe); return -EEXIST; @@ -424,10 +435,10 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) edev->pe = pe; pr_debug("EEH: Add %04x:%02x:%02x.%01x to " "Device PE#%x, Parent PE#%x\n", - edev->phb->global_number, - edev->config_addr >> 8, - PCI_SLOT(edev->config_addr & 0xFF), - PCI_FUNC(edev->config_addr & 0xFF), + pdn->phb->global_number, + pdn->busno, + PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn), pe->addr, pe->parent->addr); return 0; @@ -446,13 +457,14 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev) { struct eeh_pe *pe, *parent, *child; int cnt; + struct pci_dn *pdn = eeh_dev_to_pdn(edev); if (!edev->pe) { pr_debug("%s: No PE found for device %04x:%02x:%02x.%01x\n", - __func__, edev->phb->global_number, - edev->config_addr >> 8, - PCI_SLOT(edev->config_addr & 0xFF), - PCI_FUNC(edev->config_addr & 0xFF)); + __func__, pdn->phb->global_number, + pdn->busno, + PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn)); return -EEXIST; } @@ -712,10 +724,10 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) return; pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n", - __func__, edev->phb->global_number, - edev->config_addr >> 8, - PCI_SLOT(edev->config_addr & 0xFF), - PCI_FUNC(edev->config_addr & 0xFF)); + __func__, pdn->phb->global_number, + pdn->busno, + PCI_SLOT(pdn->devfn), + PCI_FUNC(pdn->devfn)); /* Check slot status */ cap = edev->pcie_cap; diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 1ceecdda810b..797549289798 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -51,7 +51,6 @@ static ssize_t eeh_show_##_name(struct device *dev, \ static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL); EEH_SHOW_ATTR(eeh_mode, mode, "0x%x"); -EEH_SHOW_ATTR(eeh_config_addr, config_addr, "0x%x"); EEH_SHOW_ATTR(eeh_pe_config_addr, pe_config_addr, "0x%x"); static ssize_t eeh_pe_state_show(struct device *dev, @@ -103,7 +102,6 @@ void eeh_sysfs_add_device(struct pci_dev *pdev) return; rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode); - rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr); rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_state); @@ -128,7 +126,6 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev) } device_remove_file(&pdev->dev, &dev_attr_eeh_mode); - device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr); device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state); diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 8587059ad848..e780e1fbf6c2 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -43,6 +43,13 @@ #define LOAD_MSR_KERNEL(r, x) li r,(x) #endif +/* + * Align to 4k in order to ensure that all functions modyfing srr0/srr1 + * fit into one page in order to not encounter a TLB miss between the + * modification of srr0/srr1 and the associated rfi. + */ + .align 12 + #ifdef CONFIG_BOOKE .globl mcheck_transfer_to_handler mcheck_transfer_to_handler: @@ -586,6 +593,10 @@ ppc_swapcontext: handle_page_fault: stw r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_6xx + andis. r0,r5,DSISR_DABRMATCH@h + bne- handle_dabr_fault +#endif bl do_page_fault cmpwi r3,0 beq+ ret_from_except @@ -599,6 +610,17 @@ handle_page_fault: bl bad_page_fault b ret_from_except_full +#ifdef CONFIG_6xx + /* We have a data breakpoint exception - handle it */ +handle_dabr_fault: + SAVE_NVGPRS(r1) + lwz r0,_TRAP(r1) + clrrwi r0,r0,1 + stw r0,_TRAP(r1) + bl do_break + b ret_from_except_full +#endif + /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 49d8422767b4..4a0fd4f40245 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -223,17 +223,27 @@ system_call_exit: andi. r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK) bne- .Lsyscall_exit_work - /* If MSR_FP and MSR_VEC are set in user msr, then no need to restore */ - li r7,MSR_FP + andi. r0,r8,MSR_FP + beq 2f #ifdef CONFIG_ALTIVEC - oris r7,r7,MSR_VEC@h + andis. r0,r8,MSR_VEC@h + bne 3f #endif - and r0,r8,r7 - cmpd r0,r7 - bne .Lsyscall_restore_math -.Lsyscall_restore_math_cont: +2: addi r3,r1,STACK_FRAME_OVERHEAD +#ifdef CONFIG_PPC_BOOK3S + li r10,MSR_RI + mtmsrd r10,1 /* Restore RI */ +#endif + bl restore_math +#ifdef CONFIG_PPC_BOOK3S + li r11,0 + mtmsrd r11,1 +#endif + ld r8,_MSR(r1) + ld r3,RESULT(r1) + li r11,-MAX_ERRNO - cmpld r3,r11 +3: cmpld r3,r11 ld r5,_CCR(r1) bge- .Lsyscall_error .Lsyscall_error_cont: @@ -267,40 +277,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) std r5,_CCR(r1) b .Lsyscall_error_cont -.Lsyscall_restore_math: - /* - * Some initial tests from restore_math to avoid the heavyweight - * C code entry and MSR manipulations. - */ - LOAD_REG_IMMEDIATE(r0, MSR_TS_MASK) - and. r0,r0,r8 - bne 1f - - ld r7,PACACURRENT(r13) - lbz r0,THREAD+THREAD_LOAD_FP(r7) -#ifdef CONFIG_ALTIVEC - lbz r6,THREAD+THREAD_LOAD_VEC(r7) - add r0,r0,r6 -#endif - cmpdi r0,0 - beq .Lsyscall_restore_math_cont - -1: addi r3,r1,STACK_FRAME_OVERHEAD -#ifdef CONFIG_PPC_BOOK3S - li r10,MSR_RI - mtmsrd r10,1 /* Restore RI */ -#endif - bl restore_math -#ifdef CONFIG_PPC_BOOK3S - li r11,0 - mtmsrd r11,1 -#endif - /* Restore volatiles, reload MSR from updated one */ - ld r8,_MSR(r1) - ld r3,RESULT(r1) - li r11,-MAX_ERRNO - b .Lsyscall_restore_math_cont - /* Traced system call support */ .Lsyscall_dotrace: bl save_nvgprs @@ -990,16 +966,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) #ifdef CONFIG_PPC_BOOK3E cmpwi cr0,r3,0x280 #else - BEGIN_FTR_SECTION - cmpwi cr0,r3,0xe80 - FTR_SECTION_ELSE - cmpwi cr0,r3,0xa00 - ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) + cmpwi cr0,r3,0xa00 #endif /* CONFIG_PPC_BOOK3E */ bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; bl doorbell_exception - b ret_from_except #endif /* CONFIG_PPC_DOORBELL */ 1: b ret_from_except /* What else to do here ? */ @@ -1133,7 +1104,7 @@ _ASM_NOKPROBE_SYMBOL(__enter_rtas) _ASM_NOKPROBE_SYMBOL(rtas_return_loc) .align 3 -1: .llong rtas_restore_regs +1: .8byte rtas_restore_regs rtas_restore_regs: /* relocation is on at this point */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 9029afd1fa2a..48da0f5d2f7f 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -541,7 +541,7 @@ EXC_COMMON_BEGIN(instruction_access_common) RECONCILE_IRQ_STATE(r10, r11) ld r12,_MSR(r1) ld r3,_NIP(r1) - andis. r4,r12,0x5820 + andis. r4,r12,DSISR_BAD_FAULT_64S@h li r5,0x400 std r3,_DAR(r1) std r4,_DSISR(r1) @@ -1314,7 +1314,7 @@ EXC_REAL_NONE(0x1800, 0x100) EXC_VIRT_NONE(0x5800, 0x100) #endif -#if defined(CONFIG_HARDLOCKUP_DETECTOR) && defined(CONFIG_HAVE_HARDLOCKUP_DETECTOR_ARCH) +#ifdef CONFIG_PPC_WATCHDOG #define MASKED_DEC_HANDLER_LABEL 3f @@ -1325,20 +1325,28 @@ EXC_VIRT_NONE(0x5800, 0x100) std r10,PACA_EXGEN+EX_R13(r13); \ EXCEPTION_PROLOG_PSERIES_1(soft_nmi_common, _H) +/* + * Branch to soft_nmi_interrupt using the emergency stack. The emergency + * stack is one that is usable by maskable interrupts so long as MSR_EE + * remains off. It is used for recovery when something has corrupted the + * normal kernel stack, for example. The "soft NMI" must not use the process + * stack because we want irq disabled sections to avoid touching the stack + * at all (other than PMU interrupts), so use the emergency stack for this, + * and run it entirely with interrupts hard disabled. + */ EXC_COMMON_BEGIN(soft_nmi_common) mr r10,r1 ld r1,PACAEMERGSP(r13) - ld r1,PACA_NMI_EMERG_SP(r13) subi r1,r1,INT_FRAME_SIZE EXCEPTION_COMMON_NORET_STACK(PACA_EXGEN, 0x900, system_reset, soft_nmi_interrupt, ADD_NVGPRS;ADD_RECONCILE) b ret_from_except -#else +#else /* CONFIG_PPC_WATCHDOG */ #define MASKED_DEC_HANDLER_LABEL 2f /* normal return */ #define MASKED_DEC_HANDLER(_H) -#endif +#endif /* CONFIG_PPC_WATCHDOG */ /* * An interrupt came in while soft-disabled. We set paca->irq_happened, then: @@ -1362,19 +1370,16 @@ masked_##_H##interrupt: \ ori r10,r10,0xffff; \ mtspr SPRN_DEC,r10; \ b MASKED_DEC_HANDLER_LABEL; \ -1: cmpwi r10,PACA_IRQ_DBELL; \ - beq 2f; \ - cmpwi r10,PACA_IRQ_HMI; \ - beq 2f; \ +1: andi. r10,r10,(PACA_IRQ_DBELL|PACA_IRQ_HMI); \ + bne 2f; \ mfspr r10,SPRN_##_H##SRR1; \ - rldicl r10,r10,48,1; /* clear MSR_EE */ \ - rotldi r10,r10,16; \ + xori r10,r10,MSR_EE; /* clear MSR_EE */ \ mtspr SPRN_##_H##SRR1,r10; \ 2: mtcrf 0x80,r9; \ ld r9,PACA_EXGEN+EX_R9(r13); \ ld r10,PACA_EXGEN+EX_R10(r13); \ ld r11,PACA_EXGEN+EX_R11(r13); \ - GET_SCRATCH0(r13); \ + /* returns to kernel where r13 must be set up, so don't restore it */ \ ##_H##rfid; \ b .; \ MASKED_DEC_HANDLER(_H) @@ -1477,8 +1482,10 @@ USE_TEXT_SECTION() */ .balign IFETCH_ALIGN_BYTES do_hash_page: -#ifdef CONFIG_PPC_STD_MMU_64 - andis. r0,r4,0xa450 /* weird error? */ + #ifdef CONFIG_PPC_STD_MMU_64 + lis r0,DSISR_BAD_FAULT_64S@h + ori r0,r0,DSISR_BAD_FAULT_64S@l + and. r0,r4,r0 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ CURRENT_THREAD_INFO(r11, r1) lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */ @@ -1661,25 +1668,27 @@ _GLOBAL(__replay_interrupt) * we don't give a damn about, so we don't bother storing them. */ mfmsr r12 - LOAD_REG_ADDR(r11, 1f) + LOAD_REG_ADDR(r11, replay_interrupt_return) mfcr r9 ori r12,r12,MSR_EE cmpwi r3,0x900 beq decrementer_common cmpwi r3,0x500 +BEGIN_FTR_SECTION + beq h_virt_irq_common +FTR_SECTION_ELSE beq hardware_interrupt_common +ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300) BEGIN_FTR_SECTION - cmpwi r3,0xe80 + cmpwi r3,0xa00 beq h_doorbell_common_msgclr - cmpwi r3,0xea0 - beq h_virt_irq_common cmpwi r3,0xe60 beq hmi_exception_common FTR_SECTION_ELSE cmpwi r3,0xa00 beq doorbell_super_common_msgclr ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE) -1: +replay_interrupt_return: blr _ASM_NOKPROBE_SYMBOL(__replay_interrupt) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index dc0c49cfd90a..e1431800bfb9 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -125,6 +125,13 @@ int is_fadump_boot_memory_area(u64 addr, ulong size) return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size; } +int should_fadump_crash(void) +{ + if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr) + return 0; + return 1; +} + int is_fadump_active(void) { return fw_dump.dump_active; @@ -518,7 +525,7 @@ void crash_fadump(struct pt_regs *regs, const char *str) struct fadump_crash_info_header *fdh = NULL; int old_cpu, this_cpu; - if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr) + if (!should_fadump_crash()) return; /* @@ -1446,6 +1453,25 @@ static void fadump_init_files(void) return; } +static int fadump_panic_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + /* + * If firmware-assisted dump has been registered then trigger + * firmware-assisted dump and let firmware handle everything + * else. If this returns, then fadump was not registered, so + * go through the rest of the panic path. + */ + crash_fadump(NULL, ptr); + + return NOTIFY_DONE; +} + +static struct notifier_block fadump_panic_block = { + .notifier_call = fadump_panic_event, + .priority = INT_MIN /* may not return; must be done last */ +}; + /* * Prepare for firmware-assisted dump. */ @@ -1478,6 +1504,9 @@ int __init setup_fadump(void) init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start); fadump_init_files(); + atomic_notifier_chain_register(&panic_notifier_list, + &fadump_panic_block); + return 1; } subsys_initcall(setup_fadump); diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index e22734278458..8c54166491e7 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -388,7 +388,7 @@ DataAccess: EXCEPTION_PROLOG mfspr r10,SPRN_DSISR stw r10,_DSISR(r11) - andis. r0,r10,0xa470 /* weird error? */ + andis. r0,r10,DSISR_BAD_FAULT_32S@h bne 1f /* if not, try to put a PTE */ mfspr r4,SPRN_DAR /* into the hash table */ rlwinm r3,r10,32-15,21,21 /* DSISR_STORE -> _PAGE_RW */ @@ -403,13 +403,13 @@ DataAccess: DO_KVM 0x400 InstructionAccess: EXCEPTION_PROLOG - andis. r0,r9,0x4000 /* no pte found? */ + andis. r0,r9,SRR1_ISI_NOPT@h /* no pte found? */ beq 1f /* if so, try to put a PTE */ li r3,0 /* into the hash table */ mr r4,r12 /* SRR0 is fault address */ bl hash_page 1: mr r4,r12 - mr r5,r9 + andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ EXC_XFER_LITE(0x400, handle_page_fault) /* External interrupt */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 0ddc602b33a4..ff8511d6d8ea 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -92,13 +92,13 @@ END_FTR_SECTION(0, 1) .balign 8 .globl __secondary_hold_spinloop __secondary_hold_spinloop: - .llong 0x0 + .8byte 0x0 /* Secondary processors write this value with their cpu # */ /* after they enter the spin loop immediately below. */ .globl __secondary_hold_acknowledge __secondary_hold_acknowledge: - .llong 0x0 + .8byte 0x0 #ifdef CONFIG_RELOCATABLE /* This flag is set to 1 by a loader if the kernel should run @@ -650,7 +650,7 @@ __after_prom_start: bctr .balign 8 -p_end: .llong _end - copy_to_here +p_end: .8byte _end - copy_to_here 4: /* @@ -892,7 +892,7 @@ _GLOBAL(relative_toc) blr .balign 8 -p_toc: .llong __toc_start + 0x8000 - 0b +p_toc: .8byte __toc_start + 0x8000 - 0b /* * This is where the main kernel code starts. diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index c032fe8c2d26..4fee00d414e8 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -50,18 +50,20 @@ mtspr spr, reg #endif -/* Macro to test if an address is a kernel address */ #if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 -#define IS_KERNEL(tmp, addr) \ - andis. tmp, addr, 0x8000 /* Address >= 0x80000000 */ -#define BRANCH_UNLESS_KERNEL(label) beq label -#else -#define IS_KERNEL(tmp, addr) \ - rlwinm tmp, addr, 16, 16, 31; \ - cmpli cr0, tmp, PAGE_OFFSET >> 16 -#define BRANCH_UNLESS_KERNEL(label) blt label +/* By simply checking Address >= 0x80000000, we know if its a kernel address */ +#define SIMPLE_KERNEL_ADDRESS 1 #endif +/* + * We need an ITLB miss handler for kernel addresses if: + * - Either we have modules + * - Or we have not pinned the first 8M + */ +#if defined(CONFIG_MODULES) || !defined(CONFIG_PIN_TLB_TEXT) || \ + defined(CONFIG_DEBUG_PAGEALLOC) +#define ITLB_MISS_KERNEL 1 +#endif /* * Value for the bits that have fixed value in RPN entries. @@ -123,7 +125,6 @@ turn_on_mmu: lis r0,start_here@h ori r0,r0,start_here@l mtspr SPRN_SRR0,r0 - SYNC rfi /* enables MMU */ /* @@ -170,7 +171,7 @@ turn_on_mmu: stw r1,0(r11); \ tovirt(r1,r11); /* set new kernel sp */ \ li r10,MSR_KERNEL & ~(MSR_IR|MSR_DR); /* can take exceptions */ \ - MTMSRD(r10); /* (except for mach check in rtas) */ \ + mtmsr r10; \ stw r0,GPR0(r11); \ SAVE_4GPRS(3, r11); \ SAVE_2GPRS(7, r11) @@ -300,7 +301,7 @@ SystemCall: /* On the MPC8xx, this is a software emulation interrupt. It occurs * for all unimplemented and illegal instructions. */ - EXCEPTION(0x1000, SoftEmu, SoftwareEmulation, EXC_XFER_STD) + EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD) . = 0x1100 /* @@ -325,7 +326,7 @@ SystemCall: #endif InstructionTLBMiss: -#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) +#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) mtspr SPRN_SPRG_SCRATCH2, r3 #endif EXCEPTION_PROLOG_0 @@ -343,15 +344,32 @@ InstructionTLBMiss: INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10) /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ -#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) mfcr r3 #endif -#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) - IS_KERNEL(r11, r10) +#ifdef ITLB_MISS_KERNEL +#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) + andis. r11, r10, 0x8000 /* Address >= 0x80000000 */ +#else + rlwinm r11, r10, 16, 0xfff8 + cmpli cr0, r11, PAGE_OFFSET@h +#ifndef CONFIG_PIN_TLB_TEXT + /* It is assumed that kernel code fits into the first 8M page */ +_ENTRY(ITLBMiss_cmp) + cmpli cr7, r11, (PAGE_OFFSET + 0x0800000)@h +#endif +#endif #endif mfspr r11, SPRN_M_TW /* Get level 1 table */ -#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) - BRANCH_UNLESS_KERNEL(3f) +#ifdef ITLB_MISS_KERNEL +#if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) + beq+ 3f +#else + blt+ 3f +#endif +#ifndef CONFIG_PIN_TLB_TEXT + blt cr7, ITLBMissLinear +#endif lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha 3: #endif @@ -369,7 +387,7 @@ InstructionTLBMiss: rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ lwz r10, 0(r10) /* Get the pte */ 4: -#if defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) mtcr r3 #endif /* Insert the APG into the TWC from the Linux PTE. */ @@ -400,7 +418,7 @@ InstructionTLBMiss: MTSPR_CPU6(SPRN_MI_RPN, r10, r3) /* Update TLB entry */ /* Restore registers */ -#if defined(CONFIG_8xx_CPU6) || defined(CONFIG_MODULES) || defined (CONFIG_DEBUG_PAGEALLOC) || defined (CONFIG_HUGETLB_PAGE) +#if defined(CONFIG_8xx_CPU6) || defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) mfspr r3, SPRN_SPRG_SCRATCH2 #endif EXCEPTION_EPILOG_0 @@ -447,23 +465,23 @@ DataStoreTLBMiss: * kernel page tables. */ mfspr r10, SPRN_MD_EPN - rlwinm r10, r10, 16, 0xfff8 - cmpli cr0, r10, PAGE_OFFSET@h + rlwinm r11, r10, 16, 0xfff8 + cmpli cr0, r11, PAGE_OFFSET@h mfspr r11, SPRN_M_TW /* Get level 1 table */ blt+ 3f + rlwinm r11, r10, 16, 0xfff8 #ifndef CONFIG_PIN_TLB_IMMR - cmpli cr0, r10, VIRT_IMMR_BASE@h + cmpli cr0, r11, VIRT_IMMR_BASE@h #endif _ENTRY(DTLBMiss_cmp) - cmpli cr7, r10, (PAGE_OFFSET + 0x1800000)@h - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha + cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h #ifndef CONFIG_PIN_TLB_IMMR _ENTRY(DTLBMiss_jmp) beq- DTLBMissIMMR #endif blt cr7, DTLBMissLinear + lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha 3: - mfspr r10, SPRN_MD_EPN /* Insert level 1 index */ rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 @@ -569,8 +587,8 @@ _ENTRY(DTLBMiss_jmp) InstructionTLBError: EXCEPTION_PROLOG mr r4,r12 - mr r5,r9 - andis. r10,r5,0x4000 + andis. r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */ + andis. r10,r9,SRR1_ISI_NOPT@h beq+ 1f tlbie r4 itlbie: @@ -595,7 +613,7 @@ DARFixed:/* Return from dcbx instruction bug workaround */ mfspr r5,SPRN_DSISR stw r5,_DSISR(r11) mfspr r4,SPRN_DAR - andis. r10,r5,0x4000 + andis. r10,r5,DSISR_NOHPTE@h beq+ 1f tlbie r4 dtlbie: @@ -684,7 +702,7 @@ DTLBMissLinear: /* Set 8M byte page and mark it valid */ li r11, MD_PS8MEG | MD_SVALID MTSPR_CPU6(SPRN_MD_TWC, r11, r3) - rlwinm r10, r10, 16, 0x0f800000 /* 8xx supports max 256Mb RAM */ + rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ _PAGE_PRESENT MTSPR_CPU6(SPRN_MD_RPN, r10, r11) /* Update TLB entry */ @@ -695,6 +713,22 @@ DTLBMissLinear: EXCEPTION_EPILOG_0 rfi +#ifndef CONFIG_PIN_TLB_TEXT +ITLBMissLinear: + mtcr r3 + /* Set 8M byte page and mark it valid */ + li r11, MI_PS8MEG | MI_SVALID | _PAGE_EXEC + MTSPR_CPU6(SPRN_MI_TWC, r11, r3) + rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ + ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SHARED | _PAGE_DIRTY | \ + _PAGE_PRESENT + MTSPR_CPU6(SPRN_MI_RPN, r10, r11) /* Update TLB entry */ + + mfspr r3, SPRN_SPRG_SCRATCH2 + EXCEPTION_EPILOG_0 + rfi +#endif + /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions * by decoding the registers used by the dcbx instruction and adding them. * DAR is set to the calculated address. @@ -705,9 +739,10 @@ FixupDAR:/* Entry point for dcbx workaround. */ mtspr SPRN_SPRG_SCRATCH2, r10 /* fetch instruction from memory. */ mfspr r10, SPRN_SRR0 - IS_KERNEL(r11, r10) + rlwinm r11, r10, 16, 0xfff8 + cmpli cr0, r11, PAGE_OFFSET@h mfspr r11, SPRN_M_TW /* Get level 1 table */ - BRANCH_UNLESS_KERNEL(3f) + blt+ 3f rlwinm r11, r10, 16, 0xfff8 _ENTRY(FixupDAR_cmp) cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h @@ -915,10 +950,8 @@ start_here: rfi /* Load up the kernel context */ 2: - SYNC /* Force all PTE updates to finish */ tlbia /* Clear all TLB entries */ sync /* wait for tlbia/tlbie to finish */ - TLBSYNC /* ... on all CPUs */ /* set up the PTE pointers for the Abatron bdiGDB. */ @@ -955,15 +988,14 @@ initial_mmu: mtspr SPRN_MD_CTR, r10 /* remove PINNED DTLB entries */ tlbia /* Invalidate all TLB entries */ -/* Always pin the first 8 MB ITLB to prevent ITLB - misses while mucking around with SRR0/SRR1 in asm -*/ +#ifdef CONFIG_PIN_TLB_TEXT lis r8, MI_RSV4I@h ori r8, r8, 0x1c00 mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */ +#endif -#ifdef CONFIG_PIN_TLB +#ifdef CONFIG_PIN_TLB_DATA oris r10, r10, MD_RSV4I@h mtspr SPRN_MD_CTR, r10 /* Set data TLB control */ #endif @@ -989,6 +1021,7 @@ initial_mmu: * internal registers (among other things). */ #ifdef CONFIG_PIN_TLB_IMMR + oris r10, r10, MD_RSV4I@h ori r10, r10, 0x1c00 mtspr SPRN_MD_CTR, r10 diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index 516ebef905c0..1125c9be9e06 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -85,7 +85,61 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) std r3,_WORT(r1) mfspr r3,SPRN_WORC std r3,_WORC(r1) +/* + * On POWER9, there are idle states such as stop4, invoked via cpuidle, + * that lose hypervisor resources. In such cases, we need to save + * additional SPRs before entering those idle states so that they can + * be restored to their older values on wakeup from the idle state. + * + * On POWER8, the only such deep idle state is winkle which is used + * only in the context of CPU-Hotplug, where these additional SPRs are + * reinitiazed to a sane value. Hence there is no need to save/restore + * these SPRs. + */ +BEGIN_FTR_SECTION + blr +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) + +power9_save_additional_sprs: + mfspr r3, SPRN_PID + mfspr r4, SPRN_LDBAR + std r3, STOP_PID(r13) + std r4, STOP_LDBAR(r13) + mfspr r3, SPRN_FSCR + mfspr r4, SPRN_HFSCR + std r3, STOP_FSCR(r13) + std r4, STOP_HFSCR(r13) + + mfspr r3, SPRN_MMCRA + mfspr r4, SPRN_MMCR1 + std r3, STOP_MMCRA(r13) + std r4, STOP_MMCR1(r13) + + mfspr r3, SPRN_MMCR2 + std r3, STOP_MMCR2(r13) + blr + +power9_restore_additional_sprs: + ld r3,_LPCR(r1) + ld r4, STOP_PID(r13) + mtspr SPRN_LPCR,r3 + mtspr SPRN_PID, r4 + + ld r3, STOP_LDBAR(r13) + ld r4, STOP_FSCR(r13) + mtspr SPRN_LDBAR, r3 + mtspr SPRN_FSCR, r4 + + ld r3, STOP_HFSCR(r13) + ld r4, STOP_MMCRA(r13) + mtspr SPRN_HFSCR, r3 + mtspr SPRN_MMCRA, r4 + /* We have already restored PACA_MMCR0 */ + ld r3, STOP_MMCR1(r13) + ld r4, STOP_MMCR2(r13) + mtspr SPRN_MMCR1, r3 + mtspr SPRN_MMCR2, r4 blr /* @@ -141,7 +195,16 @@ pnv_powersave_common: std r5,_CCR(r1) std r1,PACAR1(r13) +BEGIN_FTR_SECTION + /* + * POWER9 does not require real mode to stop, and presently does not + * set hwthread_state for KVM (threads don't share MMU context), so + * we can remain in virtual mode for this. + */ + bctr +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) /* + * POWER8 * Go to real mode to do the nap, as required by the architecture. * Also, we need to be in real mode before setting hwthread_state, * because as soon as we do that, another thread can switch @@ -151,6 +214,20 @@ pnv_powersave_common: mtmsrd r7,0 bctr +/* + * This is the sequence required to execute idle instructions, as + * specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0. + */ +#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \ + /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ + std r0,0(r1); \ + ptesync; \ + ld r0,0(r1); \ +236: cmpd cr0,r0,r0; \ + bne 236b; \ + IDLE_INST; + + .globl pnv_enter_arch207_idle_mode pnv_enter_arch207_idle_mode: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE @@ -242,20 +319,27 @@ enter_winkle: /* * r3 - PSSCR value corresponding to the requested stop state. */ -power_enter_stop: #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - /* Tell KVM we're entering idle */ +power_enter_stop_kvm_rm: + /* + * This is currently unused because POWER9 KVM does not have to + * gather secondary threads into sibling mode, but the code is + * here in case that function is required. + * + * Tell KVM we're entering idle. + */ li r4,KVM_HWTHREAD_IN_IDLE /* DO THIS IN REAL MODE! See comment above. */ stb r4,HSTATE_HWTHREAD_STATE(r13) #endif +power_enter_stop: /* * Check if we are executing the lite variant with ESL=EC=0 */ andis. r4,r3,PSSCR_EC_ESL_MASK_SHIFTED clrldi r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */ bne .Lhandle_esl_ec_set - IDLE_STATE_ENTER_SEQ(PPC_STOP) + PPC_STOP li r3,0 /* Since we didn't lose state, return 0 */ /* @@ -288,7 +372,8 @@ power_enter_stop: ld r4,ADDROFF(pnv_first_deep_stop_state)(r5) cmpd r3,r4 bge .Lhandle_deep_stop - IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP) + PPC_STOP /* Does not return (system reset interrupt) */ + .Lhandle_deep_stop: /* * Entering deep idle state. @@ -310,7 +395,7 @@ lwarx_loop_stop: bl save_sprs_to_stack - IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP) + PPC_STOP /* Does not return (system reset interrupt) */ /* * Entered with MSR[EE]=0 and no soft-masked interrupts pending. @@ -411,6 +496,18 @@ pnv_powersave_wakeup_mce: b pnv_powersave_wakeup +#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE +kvm_start_guest_check: + li r0,KVM_HWTHREAD_IN_KERNEL + stb r0,HSTATE_HWTHREAD_STATE(r13) + /* Order setting hwthread_state vs. testing hwthread_req */ + sync + lbz r0,HSTATE_HWTHREAD_REQ(r13) + cmpwi r0,0 + beqlr + b kvm_start_guest +#endif + /* * Called from reset vector for powersave wakeups. * cr3 - set to gt if waking up with partial/complete hypervisor state loss @@ -435,15 +532,9 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_ARCH_300) mr r3,r12 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - li r0,KVM_HWTHREAD_IN_KERNEL - stb r0,HSTATE_HWTHREAD_STATE(r13) - /* Order setting hwthread_state vs. testing hwthread_req */ - sync - lbz r0,HSTATE_HWTHREAD_REQ(r13) - cmpwi r0,0 - beq 1f - b kvm_start_guest -1: +BEGIN_FTR_SECTION + bl kvm_start_guest_check +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) #endif /* Return SRR1 from power7_nap() */ @@ -460,11 +551,17 @@ pnv_restore_hyp_resource_arch300: /* * Workaround for POWER9, if we lost resources, the ERAT * might have been mixed up and needs flushing. We also need - * to reload MMCR0 (see comment above). + * to reload MMCR0 (see comment above). We also need to set + * then clear bit 60 in MMCRA to ensure the PMU starts running. */ blt cr3,1f PPC_INVALIDATE_ERAT ld r1,PACAR1(r13) + mfspr r4,SPRN_MMCRA + ori r4,r4,(1 << (63-60)) + mtspr SPRN_MMCRA,r4 + xori r4,r4,(1 << (63-60)) + mtspr SPRN_MMCRA,r4 ld r4,_MMCR0(r1) mtspr SPRN_MMCR0,r4 1: @@ -803,9 +900,16 @@ no_segments: mtctr r12 bctrl +/* + * On POWER9, we can come here on wakeup from a cpuidle stop state. + * Hence restore the additional SPRs to the saved value. + * + * On POWER8, we come here only on winkle. Since winkle is used + * only in the case of CPU-Hotplug, we don't need to restore + * the additional SPRs. + */ BEGIN_FTR_SECTION - ld r4,_LPCR(r1) - mtspr SPRN_LPCR,r4 + bl power9_restore_additional_sprs END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) hypervisor_state_restored: diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c index a582e0d42525..aa9f1b8261db 100644 --- a/arch/powerpc/kernel/io-workarounds.c +++ b/arch/powerpc/kernel/io-workarounds.c @@ -19,6 +19,8 @@ #include <asm/pgtable.h> #include <asm/ppc-pci.h> #include <asm/io-workarounds.h> +#include <asm/pte-walk.h> + #define IOWA_MAX_BUS 8 @@ -75,8 +77,7 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr) * We won't find huge pages here (iomem). Also can't hit * a page table free due to init_mm */ - ptep = __find_linux_pte_or_hugepte(init_mm.pgd, vaddr, - NULL, &hugepage_shift); + ptep = find_init_mm_pte(vaddr, &hugepage_shift); if (ptep == NULL) paddr = 0; else { @@ -192,7 +193,7 @@ void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops, if (iowa_bus_count >= IOWA_MAX_BUS) { pr_err("IOWA:Too many pci bridges, " - "workarounds disabled for %s\n", np->full_name); + "workarounds disabled for %pOF\n", np); return; } @@ -207,6 +208,6 @@ void iowa_register_bus(struct pci_controller *phb, struct ppc_pci_io *ops, iowa_bus_count++; - pr_debug("IOWA:[%d]Add bus, %s.\n", iowa_bus_count-1, np->full_name); + pr_debug("IOWA:[%d]Add bus, %pOF.\n", iowa_bus_count-1, np); } diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 233ca3fe4754..af7a20dc6e09 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -127,8 +127,7 @@ static ssize_t fail_iommu_store(struct device *dev, return count; } -static DEVICE_ATTR(fail_iommu, S_IRUGO|S_IWUSR, fail_iommu_show, - fail_iommu_store); +static DEVICE_ATTR_RW(fail_iommu); static int fail_iommu_bus_notify(struct notifier_block *nb, unsigned long action, void *data) @@ -190,7 +189,7 @@ static unsigned long iommu_range_alloc(struct device *dev, unsigned int pool_nr; struct iommu_pool *pool; - align_mask = 0xffffffffffffffffl >> (64 - align_order); + align_mask = (1ull << align_order) - 1; /* This allocator was derived from x86_64's bit string search */ @@ -208,7 +207,7 @@ static unsigned long iommu_range_alloc(struct device *dev, * We don't need to disable preemption here because any CPU can * safely use any IOMMU pool. */ - pool_nr = __this_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1); + pool_nr = raw_cpu_read(iommu_pool_hash) & (tbl->nr_pools - 1); if (largealloc) pool = &(tbl->large_pool); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 0bcec745a672..4e65bf82f5e0 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -24,7 +24,7 @@ * mask register (of which only 16 are defined), hence the weird shifting * and complement of the cached_irq_mask. I want to be able to stuff * this right into the SIU SMASK register. - * Many of the prep/chrp functions are conditional compiled on CONFIG_8xx + * Many of the prep/chrp functions are conditional compiled on CONFIG_PPC_8xx * to reduce code space and undefined function references. */ @@ -143,8 +143,22 @@ notrace unsigned int __check_irq_replay(void) */ unsigned char happened = local_paca->irq_happened; - /* Clear bit 0 which we wouldn't clear otherwise */ - local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + if (happened & PACA_IRQ_HARD_DIS) { + /* Clear bit 0 which we wouldn't clear otherwise */ + local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS; + + /* + * We may have missed a decrementer interrupt if hard disabled. + * Check the decrementer register in case we had a rollover + * while hard disabled. + */ + if (!(happened & PACA_IRQ_DEC)) { + if (decrementer_check_overflow()) { + local_paca->irq_happened |= PACA_IRQ_DEC; + happened |= PACA_IRQ_DEC; + } + } + } /* * Force the delivery of pending soft-disabled interrupts on PS3. @@ -160,41 +174,39 @@ notrace unsigned int __check_irq_replay(void) * This is a higher priority interrupt than the others, so * replay it first. */ - local_paca->irq_happened &= ~PACA_IRQ_HMI; - if (happened & PACA_IRQ_HMI) + if (happened & PACA_IRQ_HMI) { + local_paca->irq_happened &= ~PACA_IRQ_HMI; return 0xe60; + } - /* - * We may have missed a decrementer interrupt. We check the - * decrementer itself rather than the paca irq_happened field - * in case we also had a rollover while hard disabled - */ - local_paca->irq_happened &= ~PACA_IRQ_DEC; - if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow()) + if (happened & PACA_IRQ_DEC) { + local_paca->irq_happened &= ~PACA_IRQ_DEC; return 0x900; + } - /* Finally check if an external interrupt happened */ - local_paca->irq_happened &= ~PACA_IRQ_EE; - if (happened & PACA_IRQ_EE) + if (happened & PACA_IRQ_EE) { + local_paca->irq_happened &= ~PACA_IRQ_EE; return 0x500; + } #ifdef CONFIG_PPC_BOOK3E - /* Finally check if an EPR external interrupt happened - * this bit is typically set if we need to handle another - * "edge" interrupt from within the MPIC "EPR" handler + /* + * Check if an EPR external interrupt happened this bit is typically + * set if we need to handle another "edge" interrupt from within the + * MPIC "EPR" handler. */ - local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE; - if (happened & PACA_IRQ_EE_EDGE) + if (happened & PACA_IRQ_EE_EDGE) { + local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE; return 0x500; + } - local_paca->irq_happened &= ~PACA_IRQ_DBELL; - if (happened & PACA_IRQ_DBELL) + if (happened & PACA_IRQ_DBELL) { + local_paca->irq_happened &= ~PACA_IRQ_DBELL; return 0x280; + } #else - local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (happened & PACA_IRQ_DBELL) { - if (cpu_has_feature(CPU_FTR_HVMODE)) - return 0xe80; + local_paca->irq_happened &= ~PACA_IRQ_DBELL; return 0xa00; } #endif /* CONFIG_PPC_BOOK3E */ @@ -470,6 +482,18 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, " Hypervisor Maintenance Interrupts\n"); } + seq_printf(p, "%*s: ", prec, "NMI"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).sreset_irqs); + seq_printf(p, " System Reset interrupts\n"); + +#ifdef CONFIG_PPC_WATCHDOG + seq_printf(p, "%*s: ", prec, "WDG"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat, j).soft_nmi_irqs); + seq_printf(p, " Watchdog soft-NMI interrupts\n"); +#endif + #ifdef CONFIG_PPC_DOORBELL if (cpu_has_feature(CPU_FTR_DBELL)) { seq_printf(p, "%*s: ", prec, "DBL"); @@ -494,6 +518,10 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += per_cpu(irq_stat, cpu).spurious_irqs; sum += per_cpu(irq_stat, cpu).timer_irqs_others; sum += per_cpu(irq_stat, cpu).hmi_exceptions; + sum += per_cpu(irq_stat, cpu).sreset_irqs; +#ifdef CONFIG_PPC_WATCHDOG + sum += per_cpu(irq_stat, cpu).soft_nmi_irqs; +#endif #ifdef CONFIG_PPC_DOORBELL sum += per_cpu(irq_stat, cpu).doorbell_irqs; #endif diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index bb6f8993412e..1df6c74aa731 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -164,7 +164,7 @@ void __init isa_bridge_find_early(struct pci_controller *hose) /* Set the global ISA io base to indicate we have an ISA bridge */ isa_io_base = ISA_IO_BASE; - pr_debug("ISA bridge (early) is %s\n", np->full_name); + pr_debug("ISA bridge (early) is %pOF\n", np); } /** @@ -187,15 +187,15 @@ void __init isa_bridge_init_non_pci(struct device_node *np) pna = of_n_addr_cells(np); if (of_property_read_u32(np, "#address-cells", &na) || of_property_read_u32(np, "#size-cells", &ns)) { - pr_warn("ISA: Non-PCI bridge %s is missing address format\n", - np->full_name); + pr_warn("ISA: Non-PCI bridge %pOF is missing address format\n", + np); return; } /* Check it's a supported address format */ if (na != 2 || ns != 1) { - pr_warn("ISA: Non-PCI bridge %s has unsupported address format\n", - np->full_name); + pr_warn("ISA: Non-PCI bridge %pOF has unsupported address format\n", + np); return; } rs = na + ns + pna; @@ -203,8 +203,8 @@ void __init isa_bridge_init_non_pci(struct device_node *np) /* Grab the ranges property */ ranges = of_get_property(np, "ranges", &rlen); if (ranges == NULL || rlen < rs) { - pr_warn("ISA: Non-PCI bridge %s has absent or invalid ranges\n", - np->full_name); + pr_warn("ISA: Non-PCI bridge %pOF has absent or invalid ranges\n", + np); return; } @@ -220,8 +220,8 @@ void __init isa_bridge_init_non_pci(struct device_node *np) /* Got something ? */ if (!size || !pbasep) { - pr_warn("ISA: Non-PCI bridge %s has no usable IO range\n", - np->full_name); + pr_warn("ISA: Non-PCI bridge %pOF has no usable IO range\n", + np); return; } @@ -233,15 +233,15 @@ void __init isa_bridge_init_non_pci(struct device_node *np) /* Map pbase */ pbase = of_translate_address(np, pbasep); if (pbase == OF_BAD_ADDR) { - pr_warn("ISA: Non-PCI bridge %s failed to translate IO base\n", - np->full_name); + pr_warn("ISA: Non-PCI bridge %pOF failed to translate IO base\n", + np); return; } /* We need page alignment */ if ((cbase & ~PAGE_MASK) || (pbase & ~PAGE_MASK)) { - pr_warn("ISA: Non-PCI bridge %s has non aligned IO range\n", - np->full_name); + pr_warn("ISA: Non-PCI bridge %pOF has non aligned IO range\n", + np); return; } @@ -255,7 +255,7 @@ void __init isa_bridge_init_non_pci(struct device_node *np) __ioremap_at(pbase, (void *)ISA_IO_BASE, size, pgprot_val(pgprot_noncached(__pgprot(0)))); - pr_debug("ISA: Non-PCI bridge is %s\n", np->full_name); + pr_debug("ISA: Non-PCI bridge is %pOF\n", np); } /** @@ -277,8 +277,8 @@ static void isa_bridge_find_late(struct pci_dev *pdev, /* Set the global ISA io base to indicate we have an ISA bridge */ isa_io_base = ISA_IO_BASE; - pr_debug("ISA bridge (late) is %s on %s\n", - devnode->full_name, pci_name(pdev)); + pr_debug("ISA bridge (late) is %pOF on %s\n", + devnode, pci_name(pdev)); } /** diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index dbf098121ce6..35e240a0a408 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -67,9 +67,9 @@ static struct hard_trap_info #endif #else /* ! (defined(CONFIG_40x) || defined(CONFIG_BOOKE)) */ { 0x0d00, 0x05 /* SIGTRAP */ }, /* single-step */ -#if defined(CONFIG_8xx) +#if defined(CONFIG_PPC_8xx) { 0x1000, 0x04 /* SIGILL */ }, /* software emulation */ -#else /* ! CONFIG_8xx */ +#else /* ! CONFIG_PPC_8xx */ { 0x0f00, 0x04 /* SIGILL */ }, /* performance monitor */ { 0x0f20, 0x08 /* SIGFPE */ }, /* altivec unavailable */ { 0x1300, 0x05 /* SIGTRAP */ }, /* instruction address break */ diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 1086ea37c832..9ad37f827a97 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -25,7 +25,6 @@ #include <linux/kvm_para.h> #include <linux/slab.h> #include <linux/of.h> -#include <linux/nmi.h> /* hardlockup_detector_disable() */ #include <asm/reg.h> #include <asm/sections.h> @@ -719,12 +718,6 @@ static __init void kvm_free_tmp(void) static int __init kvm_guest_init(void) { - /* - * The hardlockup detector is likely to get false positives in - * KVM guests, so disable it by default. - */ - hardlockup_detector_disable(); - if (!kvm_para_available()) goto free_tmp; diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S index 97ec8557f974..6408f09dbbd9 100644 --- a/arch/powerpc/kernel/l2cr_6xx.S +++ b/arch/powerpc/kernel/l2cr_6xx.S @@ -181,7 +181,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450) mtctr r4 li r4,0 1: - lwzx r0,r0,r4 + lwzx r0,0,r4 addi r4,r4,32 /* Go to start of next cache line */ bdnz 1b isync @@ -328,7 +328,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_L3CR) mtctr r4 li r4,0 1: - lwzx r0,r0,r4 + lwzx r0,0,r4 dcbf 0,r4 addi r4,r4,32 /* Go to start of next cache line */ bdnz 1b diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 0694d20f85b6..5e5a64a8b4e4 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -147,8 +147,8 @@ static int __init add_legacy_port(struct device_node *np, int want_index, legacy_serial_ports[index].serial_out = tsi_serial_out; } - printk(KERN_DEBUG "Found legacy serial port %d for %s\n", - index, np->full_name); + printk(KERN_DEBUG "Found legacy serial port %d for %pOF\n", + index, np); printk(KERN_DEBUG " %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n", (iotype == UPIO_PORT) ? "port" : "mem", (unsigned long long)base, (unsigned long long)taddr, irq, @@ -207,7 +207,7 @@ static int __init add_legacy_isa_port(struct device_node *np, int index = -1; u64 taddr; - DBG(" -> add_legacy_isa_port(%s)\n", np->full_name); + DBG(" -> add_legacy_isa_port(%pOF)\n", np); /* Get the ISA port number */ reg = of_get_property(np, "reg", NULL); @@ -256,7 +256,7 @@ static int __init add_legacy_pci_port(struct device_node *np, unsigned int flags; int iotype, index = -1, lindex = 0; - DBG(" -> add_legacy_pci_port(%s)\n", np->full_name); + DBG(" -> add_legacy_pci_port(%pOF)\n", np); /* We only support ports that have a clock frequency properly * encoded in the device-tree (that is have an fcode). Anything @@ -374,7 +374,7 @@ void __init find_legacy_serial_ports(void) if (path != NULL) { stdout = of_find_node_by_path(path); if (stdout) - DBG("stdout is %s\n", stdout->full_name); + DBG("stdout is %pOF\n", stdout); } else { DBG(" no linux,stdout-path !\n"); } @@ -603,7 +603,7 @@ static int __init check_legacy_serial_console(void) DBG(" can't find stdout package %s !\n", name); return -ENODEV; } - DBG("stdout is %s\n", prom_stdout->full_name); + DBG("stdout is %pOF\n", prom_stdout); name = of_get_property(prom_stdout, "name", NULL); if (!name) { diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index e0e131e662ed..9b2ea7e71c06 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -22,11 +22,14 @@ #undef DEBUG #define pr_fmt(fmt) "mce: " fmt +#include <linux/hardirq.h> #include <linux/types.h> #include <linux/ptrace.h> #include <linux/percpu.h> #include <linux/export.h> #include <linux/irq_work.h> + +#include <asm/machdep.h> #include <asm/mce.h> static DEFINE_PER_CPU(int, mce_nest_count); @@ -446,3 +449,33 @@ uint64_t get_mce_fault_addr(struct machine_check_event *evt) return 0; } EXPORT_SYMBOL(get_mce_fault_addr); + +/* + * This function is called in real mode. Strictly no printk's please. + * + * regs->nip and regs->msr contains srr0 and ssr1. + */ +long machine_check_early(struct pt_regs *regs) +{ + long handled = 0; + + __this_cpu_inc(irq_stat.mce_exceptions); + + if (cur_cpu_spec && cur_cpu_spec->machine_check_early) + handled = cur_cpu_spec->machine_check_early(regs); + return handled; +} + +long hmi_exception_realmode(struct pt_regs *regs) +{ + __this_cpu_inc(irq_stat.hmi_exceptions); + + wait_for_subcore_guest_exit(); + + if (ppc_md.hmi_exception_early) + ppc_md.hmi_exception_early(regs); + + wait_for_tb_resync(); + + return 0; +} diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 34aeac54f120..becaec990140 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -45,7 +45,7 @@ static int of_pci_phb_probe(struct platform_device *dev) if (ppc_md.pci_setup_phb == NULL) return -ENODEV; - pr_info("Setting up PCI bus %s\n", dev->dev.of_node->full_name); + pr_info("Setting up PCI bus %pOF\n", dev->dev.of_node); /* Alloc and setup PHB data structure */ phb = pcibios_alloc_controller(dev->dev.of_node); diff --git a/arch/powerpc/kernel/optprobes_head.S b/arch/powerpc/kernel/optprobes_head.S index 4937bef7652f..52fc864cdec4 100644 --- a/arch/powerpc/kernel/optprobes_head.S +++ b/arch/powerpc/kernel/optprobes_head.S @@ -60,10 +60,6 @@ optprobe_template_entry: std r5,_CCR(r1) lbz r5,PACASOFTIRQEN(r13) std r5,SOFTE(r1) - mfdar r5 - std r5,_DAR(r1) - mfdsisr r5 - std r5,_DSISR(r1) /* * We may get here from a module, so load the kernel TOC in r2. @@ -122,10 +118,6 @@ optprobe_template_call_emulate: mtxer r5 ld r5,_CCR(r1) mtcr r5 - ld r5,_DAR(r1) - mtdar r5 - ld r5,_DSISR(r1) - mtdsisr r5 REST_GPR(0,r1) REST_10GPRS(2,r1) REST_10GPRS(12,r1) diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 8d63627e067f..70f073d6c3b2 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -99,18 +99,27 @@ static inline void free_lppacas(void) { } * If you make the number of persistent SLB entries dynamic, please also * update PR KVM to flush and restore them accordingly. */ -static struct slb_shadow *slb_shadow; +static struct slb_shadow * __initdata slb_shadow; static void __init allocate_slb_shadows(int nr_cpus, int limit) { int size = PAGE_ALIGN(sizeof(struct slb_shadow) * nr_cpus); + + if (early_radix_enabled()) + return; + slb_shadow = __va(memblock_alloc_base(size, PAGE_SIZE, limit)); memset(slb_shadow, 0, size); } static struct slb_shadow * __init init_slb_shadow(int cpu) { - struct slb_shadow *s = &slb_shadow[cpu]; + struct slb_shadow *s; + + if (early_radix_enabled()) + return NULL; + + s = &slb_shadow[cpu]; /* * When we come through here to initialise boot_paca, the slb_shadow diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 341a7469cab8..02831a396419 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -373,9 +373,8 @@ static int pci_read_irq_line(struct pci_dev *pci_dev) if (virq) irq_set_irq_type(virq, IRQ_TYPE_LEVEL_LOW); } else { - pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n", - oirq.args_count, oirq.args[0], oirq.args[1], - of_node_full_name(oirq.np)); + pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %pOF\n", + oirq.args_count, oirq.args[0], oirq.args[1], oirq.np); virq = irq_create_of_mapping(&oirq); } @@ -741,8 +740,8 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose, struct of_pci_range range; struct of_pci_range_parser parser; - printk(KERN_INFO "PCI host bridge %s %s ranges:\n", - dev->full_name, primary ? "(primary)" : ""); + printk(KERN_INFO "PCI host bridge %pOF %s ranges:\n", + dev, primary ? "(primary)" : ""); /* Check for ranges property */ if (of_pci_range_parser_init(&parser, dev)) @@ -1556,8 +1555,8 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose, if (!res->flags) { pr_debug("PCI: I/O resource not set for host" - " bridge %s (domain %d)\n", - hose->dn->full_name, hose->global_number); + " bridge %pOF (domain %d)\n", + hose->dn, hose->global_number); } else { offset = pcibios_io_space_offset(hose); @@ -1668,7 +1667,7 @@ void pcibios_scan_phb(struct pci_controller *hose) struct device_node *node = hose->dn; int mode; - pr_debug("PCI: Scanning PHB %s\n", of_node_full_name(node)); + pr_debug("PCI: Scanning PHB %pOF\n", node); /* Get some IO space for the new PHB */ pcibios_setup_phb_io_space(hose); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 41c86c6b6e4d..1d817f4d97d9 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -79,8 +79,8 @@ make_one_node_map(struct device_node* node, u8 pci_bus) return; bus_range = of_get_property(node, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s, " - "assuming it starts at 0\n", node->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, " + "assuming it starts at 0\n", node); pci_to_OF_bus_map[pci_bus] = 0; } else pci_to_OF_bus_map[pci_bus] = bus_range[0]; diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index ed5e9ff61a68..932b9741aa8f 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -111,7 +111,7 @@ int pcibios_unmap_io_space(struct pci_bus *bus) if (hose->io_base_alloc == NULL) return 0; - pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name); + pr_debug("IO unmapping for PHB %pOF\n", hose->dn); pr_debug(" alloc=0x%p\n", hose->io_base_alloc); /* This is a PHB, we fully unmap the IO area */ @@ -151,7 +151,7 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose) hose->io_base_virt = (void __iomem *)(area->addr + hose->io_base_phys - phys_page); - pr_debug("IO mapping for PHB %s\n", hose->dn->full_name); + pr_debug("IO mapping for PHB %pOF\n", hose->dn); pr_debug(" phys=0x%016llx, virt=0x%p (alloc=0x%p)\n", hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc); pr_debug(" size=0x%016llx (alloc=0x%016lx)\n", diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 592693437070..0e395afbf0f4 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -139,7 +139,6 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev) #ifdef CONFIG_PCI_IOV static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, - struct pci_dev *pdev, int vf_index, int busno, int devfn) { @@ -150,10 +149,8 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, return NULL; pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); - if (!pdn) { - dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__); + if (!pdn) return NULL; - } pdn->phb = parent->phb; pdn->parent = parent; @@ -167,13 +164,6 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent, INIT_LIST_HEAD(&pdn->list); list_add_tail(&pdn->list, &parent->child_list); - /* - * If we already have PCI device instance, lets - * bind them. - */ - if (pdev) - pdev->dev.archdata.pci_data = pdn; - return pdn; } #endif @@ -201,7 +191,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev) for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { struct eeh_dev *edev __maybe_unused; - pdn = add_one_dev_pci_data(parent, NULL, i, + pdn = add_one_dev_pci_data(parent, i, pci_iov_virtfn_bus(pdev, i), pci_iov_virtfn_devfn(pdev, i)); if (!pdn) { @@ -303,7 +293,6 @@ struct pci_dn *pci_add_device_node_info(struct pci_controller *hose, if (pdn == NULL) return NULL; dn->data = pdn; - pdn->node = dn; pdn->phb = hose; #ifdef CONFIG_PPC_POWERNV pdn->pe_number = IODA_INVALID_PE; @@ -352,6 +341,7 @@ EXPORT_SYMBOL_GPL(pci_add_device_node_info); void pci_remove_device_node_info(struct device_node *dn) { struct pci_dn *pdn = dn ? PCI_DN(dn) : NULL; + struct device_node *parent; #ifdef CONFIG_EEH struct eeh_dev *edev = pdn_to_eeh_dev(pdn); @@ -364,8 +354,10 @@ void pci_remove_device_node_info(struct device_node *dn) WARN_ON(!list_empty(&pdn->child_list)); list_del(&pdn->list); - if (pdn->parent) - of_node_put(pdn->parent->node); + + parent = of_get_parent(dn); + if (parent) + of_node_put(parent); dn->data = NULL; kfree(pdn); diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index ea3d98115b88..0d790f8432d2 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -211,19 +211,19 @@ void of_scan_pci_bridge(struct pci_dev *dev) unsigned int flags; u64 size; - pr_debug("of_scan_pci_bridge(%s)\n", node->full_name); + pr_debug("of_scan_pci_bridge(%pOF)\n", node); /* parse bus-range property */ busrange = of_get_property(node, "bus-range", &len); if (busrange == NULL || len != 8) { - printk(KERN_DEBUG "Can't get bus-range for PCI-PCI bridge %s\n", - node->full_name); + printk(KERN_DEBUG "Can't get bus-range for PCI-PCI bridge %pOF\n", + node); return; } ranges = of_get_property(node, "ranges", &len); if (ranges == NULL) { - printk(KERN_DEBUG "Can't get ranges for PCI-PCI bridge %s\n", - node->full_name); + printk(KERN_DEBUG "Can't get ranges for PCI-PCI bridge %pOF\n", + node); return; } @@ -233,8 +233,8 @@ void of_scan_pci_bridge(struct pci_dev *dev) bus = pci_add_new_bus(dev->bus, dev, of_read_number(busrange, 1)); if (!bus) { - printk(KERN_ERR "Failed to create pci bus for %s\n", - node->full_name); + printk(KERN_ERR "Failed to create pci bus for %pOF\n", + node); return; } } @@ -262,13 +262,13 @@ void of_scan_pci_bridge(struct pci_dev *dev) res = bus->resource[0]; if (res->flags) { printk(KERN_ERR "PCI: ignoring extra I/O range" - " for bridge %s\n", node->full_name); + " for bridge %pOF\n", node); continue; } } else { if (i >= PCI_NUM_RESOURCES - PCI_BRIDGE_RESOURCES) { printk(KERN_ERR "PCI: too many memory ranges" - " for bridge %s\n", node->full_name); + " for bridge %pOF\n", node); continue; } res = bus->resource[i]; @@ -307,7 +307,7 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus, struct eeh_dev *edev = pdn_to_eeh_dev(PCI_DN(dn)); #endif - pr_debug(" * %s\n", dn->full_name); + pr_debug(" * %pOF\n", dn); if (!of_device_is_available(dn)) return NULL; @@ -350,8 +350,8 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus, struct device_node *child; struct pci_dev *dev; - pr_debug("of_scan_bus(%s) bus no %d...\n", - node->full_name, bus->number); + pr_debug("of_scan_bus(%pOF) bus no %d...\n", + node, bus->number); /* Scan direct children */ for_each_child_of_node(node, child) { diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9f3e2c932dcc..a0c74bbf3454 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -230,7 +230,8 @@ void enable_kernel_fp(void) } EXPORT_SYMBOL(enable_kernel_fp); -static int restore_fp(struct task_struct *tsk) { +static int restore_fp(struct task_struct *tsk) +{ if (tsk->thread.load_fp || msr_tm_active(tsk->thread.regs->msr)) { load_fp_state(¤t->thread.fp_state); current->thread.load_fp++; @@ -330,11 +331,19 @@ static inline int restore_altivec(struct task_struct *tsk) { return 0; } #ifdef CONFIG_VSX static void __giveup_vsx(struct task_struct *tsk) { - if (tsk->thread.regs->msr & MSR_FP) + unsigned long msr = tsk->thread.regs->msr; + + /* + * We should never be ssetting MSR_VSX without also setting + * MSR_FP and MSR_VEC + */ + WARN_ON((msr & MSR_VSX) && !((msr & MSR_FP) && (msr & MSR_VEC))); + + /* __giveup_fpu will clear MSR_VSX */ + if (msr & MSR_FP) __giveup_fpu(tsk); - if (tsk->thread.regs->msr & MSR_VEC) + if (msr & MSR_VEC) __giveup_altivec(tsk); - tsk->thread.regs->msr &= ~MSR_VSX; } static void giveup_vsx(struct task_struct *tsk) @@ -346,14 +355,6 @@ static void giveup_vsx(struct task_struct *tsk) msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX); } -static void save_vsx(struct task_struct *tsk) -{ - if (tsk->thread.regs->msr & MSR_FP) - save_fpu(tsk); - if (tsk->thread.regs->msr & MSR_VEC) - save_altivec(tsk); -} - void enable_kernel_vsx(void) { unsigned long cpumsr; @@ -362,7 +363,8 @@ void enable_kernel_vsx(void) cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); - if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) { + if (current->thread.regs && + (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) { check_if_tm_restore_required(current); /* * If a thread has already been reclaimed then the @@ -373,10 +375,6 @@ void enable_kernel_vsx(void) */ if(!msr_tm_active(cpumsr) && msr_tm_active(current->thread.regs->msr)) return; - if (current->thread.regs->msr & MSR_FP) - __giveup_fpu(current); - if (current->thread.regs->msr & MSR_VEC) - __giveup_altivec(current); __giveup_vsx(current); } } @@ -386,7 +384,7 @@ void flush_vsx_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) { preempt_disable(); - if (tsk->thread.regs->msr & MSR_VSX) { + if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) { BUG_ON(tsk != current); giveup_vsx(tsk); } @@ -406,7 +404,6 @@ static int restore_vsx(struct task_struct *tsk) } #else static inline int restore_vsx(struct task_struct *tsk) { return 0; } -static inline void save_vsx(struct task_struct *tsk) { } #endif /* CONFIG_VSX */ #ifdef CONFIG_SPE @@ -486,6 +483,8 @@ void giveup_all(struct task_struct *tsk) msr_check_and_set(msr_all_available); check_if_tm_restore_required(tsk); + WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); + #ifdef CONFIG_PPC_FPU if (usermsr & MSR_FP) __giveup_fpu(tsk); @@ -494,10 +493,6 @@ void giveup_all(struct task_struct *tsk) if (usermsr & MSR_VEC) __giveup_altivec(tsk); #endif -#ifdef CONFIG_VSX - if (usermsr & MSR_VSX) - __giveup_vsx(tsk); -#endif #ifdef CONFIG_SPE if (usermsr & MSR_SPE) __giveup_spe(tsk); @@ -511,10 +506,6 @@ void restore_math(struct pt_regs *regs) { unsigned long msr; - /* - * Syscall exit makes a similar initial check before branching - * to restore_math. Keep them in synch. - */ if (!msr_tm_active(regs->msr) && !current->thread.load_fp && !loadvec(current->thread)) return; @@ -556,19 +547,13 @@ void save_all(struct task_struct *tsk) msr_check_and_set(msr_all_available); - /* - * Saving the way the register space is in hardware, save_vsx boils - * down to a save_fpu() and save_altivec() - */ - if (usermsr & MSR_VSX) { - save_vsx(tsk); - } else { - if (usermsr & MSR_FP) - save_fpu(tsk); + WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); - if (usermsr & MSR_VEC) - save_altivec(tsk); - } + if (usermsr & MSR_FP) + save_fpu(tsk); + + if (usermsr & MSR_VEC) + save_altivec(tsk); if (usermsr & MSR_SPE) __giveup_spe(tsk); @@ -1395,13 +1380,13 @@ void show_regs(struct pt_regs * regs) show_regs_print_info(KERN_DEFAULT); - printk("NIP: "REG" LR: "REG" CTR: "REG"\n", + printk("NIP: "REG" LR: "REG" CTR: "REG"\n", regs->nip, regs->link, regs->ctr); printk("REGS: %p TRAP: %04lx %s (%s)\n", regs, regs->trap, print_tainted(), init_utsname()->release); - printk("MSR: "REG" ", regs->msr); + printk("MSR: "REG" ", regs->msr); print_msr_bits(regs->msr); - printk(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); + pr_cont(" CR: %08lx XER: %08lx\n", regs->ccr, regs->xer); trap = TRAP(regs); if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR)) pr_cont("CFAR: "REG" ", regs->orig_gpr3); @@ -1994,11 +1979,25 @@ void show_stack(struct task_struct *tsk, unsigned long *stack) void notrace __ppc64_runlatch_on(void) { struct thread_info *ti = current_thread_info(); - unsigned long ctrl; - ctrl = mfspr(SPRN_CTRLF); - ctrl |= CTRL_RUNLATCH; - mtspr(SPRN_CTRLT, ctrl); + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + /* + * Least significant bit (RUN) is the only writable bit of + * the CTRL register, so we can avoid mfspr. 2.06 is not the + * earliest ISA where this is the case, but it's convenient. + */ + mtspr(SPRN_CTRLT, CTRL_RUNLATCH); + } else { + unsigned long ctrl; + + /* + * Some architectures (e.g., Cell) have writable fields other + * than RUN, so do the read-modify-write. + */ + ctrl = mfspr(SPRN_CTRLF); + ctrl |= CTRL_RUNLATCH; + mtspr(SPRN_CTRLT, ctrl); + } ti->local_flags |= _TLF_RUNLATCH; } @@ -2007,13 +2006,18 @@ void notrace __ppc64_runlatch_on(void) void notrace __ppc64_runlatch_off(void) { struct thread_info *ti = current_thread_info(); - unsigned long ctrl; ti->local_flags &= ~_TLF_RUNLATCH; - ctrl = mfspr(SPRN_CTRLF); - ctrl &= ~CTRL_RUNLATCH; - mtspr(SPRN_CTRLT, ctrl); + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + mtspr(SPRN_CTRLT, 0); + } else { + unsigned long ctrl; + + ctrl = mfspr(SPRN_CTRLF); + ctrl &= ~CTRL_RUNLATCH; + mtspr(SPRN_CTRLT, ctrl); + } } #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 613f79f03877..02190e90c7ae 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -177,6 +177,7 @@ struct platform_support { bool hash_mmu; bool radix_mmu; bool radix_gtse; + bool xive; }; /* Platforms codes are now obsolete in the kernel. Now only used within this @@ -1041,6 +1042,27 @@ static void __init prom_parse_mmu_model(u8 val, } } +static void __init prom_parse_xive_model(u8 val, + struct platform_support *support) +{ + switch (val) { + case OV5_FEAT(OV5_XIVE_EITHER): /* Either Available */ + prom_debug("XIVE - either mode supported\n"); + support->xive = true; + break; + case OV5_FEAT(OV5_XIVE_EXPLOIT): /* Only Exploitation mode */ + prom_debug("XIVE - exploitation mode supported\n"); + support->xive = true; + break; + case OV5_FEAT(OV5_XIVE_LEGACY): /* Only Legacy mode */ + prom_debug("XIVE - legacy mode supported\n"); + break; + default: + prom_debug("Unknown xive support option: 0x%x\n", val); + break; + } +} + static void __init prom_parse_platform_support(u8 index, u8 val, struct platform_support *support) { @@ -1054,6 +1076,10 @@ static void __init prom_parse_platform_support(u8 index, u8 val, support->radix_gtse = true; } break; + case OV5_INDX(OV5_XIVE_SUPPORT): /* Interrupt mode */ + prom_parse_xive_model(val & OV5_FEAT(OV5_XIVE_SUPPORT), + support); + break; } } @@ -1062,7 +1088,8 @@ static void __init prom_check_platform_support(void) struct platform_support supported = { .hash_mmu = false, .radix_mmu = false, - .radix_gtse = false + .radix_gtse = false, + .xive = false }; int prop_len = prom_getproplen(prom.chosen, "ibm,arch-vec-5-platform-support"); @@ -1095,6 +1122,11 @@ static void __init prom_check_platform_support(void) /* We're probably on a legacy hypervisor */ prom_debug("Assuming legacy hash support\n"); } + + if (supported.xive) { + prom_debug("Asking for XIVE\n"); + ibm_architecture_vec.vec5.intarch = OV5_FEAT(OV5_XIVE_EXPLOIT); + } } static void __init prom_send_capabilities(void) diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 925a4ef90559..07cd22e35405 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -127,12 +127,19 @@ static void flush_tmregs_to_thread(struct task_struct *tsk) * If task is not current, it will have been flushed already to * it's thread_struct during __switch_to(). * - * A reclaim flushes ALL the state. + * A reclaim flushes ALL the state or if not in TM save TM SPRs + * in the appropriate thread structures from live. */ - if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) - tm_reclaim_current(TM_CAUSE_SIGNAL); + if (tsk != current) + return; + if (MSR_TM_SUSPENDED(mfmsr())) { + tm_reclaim_current(TM_CAUSE_SIGNAL); + } else { + tm_enable(); + tm_save_sprs(&(tsk->thread)); + } } #else static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } @@ -1587,11 +1594,8 @@ static int ppr_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - int ret; - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.ppr, 0, sizeof(u64)); - return ret; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); } static int ppr_set(struct task_struct *target, @@ -1599,11 +1603,8 @@ static int ppr_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - int ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.ppr, 0, sizeof(u64)); - return ret; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.ppr, 0, sizeof(u64)); } static int dscr_get(struct task_struct *target, @@ -1611,22 +1612,16 @@ static int dscr_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - int ret; - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.dscr, 0, sizeof(u64)); - return ret; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); } static int dscr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - int ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.dscr, 0, sizeof(u64)); - return ret; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.dscr, 0, sizeof(u64)); } #endif #ifdef CONFIG_PPC_BOOK3S_64 @@ -1635,22 +1630,16 @@ static int tar_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - int ret; - - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.tar, 0, sizeof(u64)); - return ret; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); } static int tar_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - int ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.tar, 0, sizeof(u64)); - return ret; + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.tar, 0, sizeof(u64)); } static int ebb_active(struct task_struct *target, diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index d88736fbece6..e8cfc69f59ae 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -82,7 +82,7 @@ _GLOBAL(relocate) 6: blr .balign 8 -p_dyn: .llong __dynamic_start - 0b -p_rela: .llong __rela_dyn_start - 0b -p_st: .llong _stext - 0b +p_dyn: .8byte __dynamic_start - 0b +p_rela: .8byte __rela_dyn_start - 0b +p_st: .8byte _stext - 0b diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c index 73f1934582c2..c2b148b1634a 100644 --- a/arch/powerpc/kernel/rtas_pci.c +++ b/arch/powerpc/kernel/rtas_pci.c @@ -91,26 +91,14 @@ static int rtas_pci_read_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct device_node *busdn, *dn; struct pci_dn *pdn; - bool found = false; int ret; - /* Search only direct children of the bus */ *val = 0xFFFFFFFF; - busdn = pci_bus_to_OF_node(bus); - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) { - found = true; - break; - } - } - if (!found) - return PCIBIOS_DEVICE_NOT_FOUND; + pdn = pci_get_pdn_by_devfn(bus, devfn); + /* Validity of pdn is checked in here */ ret = rtas_read_config(pdn, where, size, val); if (*val == EEH_IO_ERROR_VALUE(size) && eeh_dev_check_failure(pdn_to_eeh_dev(pdn))) @@ -153,24 +141,11 @@ static int rtas_pci_write_config(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct device_node *busdn, *dn; struct pci_dn *pdn; - bool found = false; - - /* Search only direct children of the bus */ - busdn = pci_bus_to_OF_node(bus); - for (dn = busdn->child; dn; dn = dn->sibling) { - pdn = PCI_DN(dn); - if (pdn && pdn->devfn == devfn - && of_device_is_available(dn)) { - found = true; - break; - } - } - if (!found) - return PCIBIOS_DEVICE_NOT_FOUND; + pdn = pci_get_pdn_by_devfn(bus, devfn); + /* Validity of pdn is checked in here. */ return rtas_write_config(pdn, where, size, val); } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 94a948207cd2..7de73589d8e2 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -481,7 +481,7 @@ void __init smp_setup_cpu_maps(void) __be32 cpu_be; int j, len; - DBG(" * %s...\n", dn->full_name); + DBG(" * %pOF...\n", dn); intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); @@ -704,30 +704,6 @@ int check_legacy_ioport(unsigned long base_port) } EXPORT_SYMBOL(check_legacy_ioport); -static int ppc_panic_event(struct notifier_block *this, - unsigned long event, void *ptr) -{ - /* - * If firmware-assisted dump has been registered then trigger - * firmware-assisted dump and let firmware handle everything else. - */ - crash_fadump(NULL, ptr); - ppc_md.panic(ptr); /* May not return */ - return NOTIFY_DONE; -} - -static struct notifier_block ppc_panic_block = { - .notifier_call = ppc_panic_event, - .priority = INT_MIN /* may not return; must be done last */ -}; - -void __init setup_panic(void) -{ - if (!ppc_md.panic) - return; - atomic_notifier_chain_register(&panic_notifier_list, &ppc_panic_block); -} - #ifdef CONFIG_CHECK_CACHE_COHERENCY /* * For platforms that have configurable cache-coherency. This function @@ -872,9 +848,6 @@ void __init setup_arch(char **cmdline_p) /* Probe the machine type, establish ppc_md. */ probe_machine(); - /* Setup panic notifier if requested by the platform. */ - setup_panic(); - /* * Configure ppc_md.power_save (ppc32 only, 64-bit machines do * it from their respective probe() function. @@ -916,13 +889,6 @@ void __init setup_arch(char **cmdline_p) /* Reserve large chunks of memory for use by CMA for KVM. */ kvm_cma_reserve(); - /* - * Reserve any gigantic pages requested on the command line. - * memblock needs to have been initialized by the time this is - * called since this will reserve memory. - */ - reserve_hugetlb_gpages(); - klp_init_thread_info(&init_thread_info); init_mm.start_code = (unsigned long)_stext; diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 2f88f6cf1a42..51ebc01fff52 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -98,6 +98,9 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { + unsigned int *addr = &memset_nocache_branch; + unsigned long insn; + /* Configure static keys first, now that we're relocated. */ setup_feature_keys(); @@ -105,7 +108,9 @@ notrace void __init machine_init(u64 dt_ptr) udbg_early_init(); patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP); - patch_instruction(&memset_nocache_branch, PPC_INST_NOP); + + insn = create_cond_branch(addr, branch_target(addr), 0x820000); + patch_instruction(addr, insn); /* replace b by bne cr0 */ /* Do some early initialization based on the flat device tree */ early_init_devtree(__va(dt_ptr)); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index af23d4b576ec..b89c6aac48c9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -564,6 +564,9 @@ static __init u64 safe_stack_limit(void) /* Other BookE, we assume the first GB is bolted */ return 1ul << 30; #else + if (early_radix_enabled()) + return ULONG_MAX; + /* BookS, the first segment is bolted */ if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) return 1UL << SID_SHIFT_1T; @@ -578,7 +581,8 @@ void __init irqstack_early_init(void) /* * Interrupt stacks must be in the first segment since we - * cannot afford to take SLB misses on them. + * cannot afford to take SLB misses on them. They are not + * accessed in realmode. */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) @@ -649,8 +653,9 @@ void __init emergency_stack_init(void) * aligned. * * Since we use these as temporary stacks during secondary CPU - * bringup, we need to get at them in real mode. This means they - * must also be within the RMO region. + * bringup, machine check, system reset, and HMI, we need to get + * at them in real mode. This means they must also be within the RMO + * region. * * The IRQ stacks allocated elsewhere in this file are zeroed and * initialized in kernel/irq.c. These are initialized here in order @@ -751,3 +756,31 @@ unsigned long memory_block_size_bytes(void) struct ppc_pci_io ppc_pci_io; EXPORT_SYMBOL(ppc_pci_io); #endif + +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF +u64 hw_nmi_get_sample_period(int watchdog_thresh) +{ + return ppc_proc_freq * watchdog_thresh; +} +#endif + +/* + * The perf based hardlockup detector breaks PMU event based branches, so + * disable it by default. Book3S has a soft-nmi hardlockup detector based + * on the decrementer interrupt, so it does not suffer from this problem. + * + * It is likely to get false positives in VM guests, so disable it there + * by default too. + */ +static int __init disable_hardlockup_detector(void) +{ +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF + hardlockup_detector_disable(); +#else + if (firmware_has_feature(FW_FEATURE_LPAR)) + hardlockup_detector_disable(); +#endif + + return 0; +} +early_initcall(disable_hardlockup_detector); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 997c88d54acf..e0a4c1f82e25 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -75,9 +75,11 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 }; struct thread_info *secondary_ti; DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map); DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); +EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* SMP operations for this machine */ @@ -351,7 +353,7 @@ static void nmi_ipi_lock_start(unsigned long *flags) hard_irq_disable(); while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) { raw_local_irq_restore(*flags); - cpu_relax(); + spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0); raw_local_irq_save(*flags); hard_irq_disable(); } @@ -360,7 +362,7 @@ static void nmi_ipi_lock_start(unsigned long *flags) static void nmi_ipi_lock(void) { while (atomic_cmpxchg(&__nmi_ipi_lock, 0, 1) == 1) - cpu_relax(); + spin_until_cond(atomic_read(&__nmi_ipi_lock) == 0); } static void nmi_ipi_unlock(void) @@ -475,7 +477,7 @@ int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us) nmi_ipi_lock_start(&flags); while (nmi_ipi_busy_count) { nmi_ipi_unlock_end(&flags); - cpu_relax(); + spin_until_cond(nmi_ipi_busy_count == 0); nmi_ipi_lock_start(&flags); } @@ -571,6 +573,26 @@ static void smp_store_cpu_info(int id) #endif } +/* + * Relationships between CPUs are maintained in a set of per-cpu cpumasks so + * rather than just passing around the cpumask we pass around a function that + * returns the that cpumask for the given CPU. + */ +static void set_cpus_related(int i, int j, struct cpumask *(*get_cpumask)(int)) +{ + cpumask_set_cpu(i, get_cpumask(j)); + cpumask_set_cpu(j, get_cpumask(i)); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void set_cpus_unrelated(int i, int j, + struct cpumask *(*get_cpumask)(int)) +{ + cpumask_clear_cpu(i, get_cpumask(j)); + cpumask_clear_cpu(j, get_cpumask(i)); +} +#endif + void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned int cpu; @@ -590,6 +612,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu), GFP_KERNEL, cpu_to_node(cpu)); + zalloc_cpumask_var_node(&per_cpu(cpu_l2_cache_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, cpu_to_node(cpu)); /* @@ -602,7 +626,9 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } } + /* Init the cpumasks so the boot CPU is related to itself */ cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); + cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); if (smp_ops && smp_ops->probe) @@ -828,33 +854,6 @@ int cpu_first_thread_of_core(int core) } EXPORT_SYMBOL_GPL(cpu_first_thread_of_core); -static void traverse_siblings_chip_id(int cpu, bool add, int chipid) -{ - const struct cpumask *mask; - struct device_node *np; - int i, plen; - const __be32 *prop; - - mask = add ? cpu_online_mask : cpu_present_mask; - for_each_cpu(i, mask) { - np = of_get_cpu_node(i, NULL); - if (!np) - continue; - prop = of_get_property(np, "ibm,chip-id", &plen); - if (prop && plen == sizeof(int) && - of_read_number(prop, 1) == chipid) { - if (add) { - cpumask_set_cpu(cpu, cpu_core_mask(i)); - cpumask_set_cpu(i, cpu_core_mask(cpu)); - } else { - cpumask_clear_cpu(cpu, cpu_core_mask(i)); - cpumask_clear_cpu(i, cpu_core_mask(cpu)); - } - } - of_node_put(np); - } -} - /* Must be called when no change can occur to cpu_present_mask, * i.e. during cpu online or offline. */ @@ -877,52 +876,93 @@ static struct device_node *cpu_to_l2cache(int cpu) return cache; } -static void traverse_core_siblings(int cpu, bool add) +static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) { struct device_node *l2_cache, *np; - const struct cpumask *mask; - int i, chip, plen; - const __be32 *prop; - - /* First see if we have ibm,chip-id properties in cpu nodes */ - np = of_get_cpu_node(cpu, NULL); - if (np) { - chip = -1; - prop = of_get_property(np, "ibm,chip-id", &plen); - if (prop && plen == sizeof(int)) - chip = of_read_number(prop, 1); - of_node_put(np); - if (chip >= 0) { - traverse_siblings_chip_id(cpu, add, chip); - return; - } - } + int i; l2_cache = cpu_to_l2cache(cpu); - mask = add ? cpu_online_mask : cpu_present_mask; - for_each_cpu(i, mask) { + if (!l2_cache) + return false; + + for_each_cpu(i, cpu_online_mask) { + /* + * when updating the marks the current CPU has not been marked + * online, but we need to update the cache masks + */ np = cpu_to_l2cache(i); if (!np) continue; - if (np == l2_cache) { - if (add) { - cpumask_set_cpu(cpu, cpu_core_mask(i)); - cpumask_set_cpu(i, cpu_core_mask(cpu)); - } else { - cpumask_clear_cpu(cpu, cpu_core_mask(i)); - cpumask_clear_cpu(i, cpu_core_mask(cpu)); - } - } + + if (np == l2_cache) + set_cpus_related(cpu, i, mask_fn); + of_node_put(np); } of_node_put(l2_cache); + + return true; } +#ifdef CONFIG_HOTPLUG_CPU +static void remove_cpu_from_masks(int cpu) +{ + int i; + + /* NB: cpu_core_mask is a superset of the others */ + for_each_cpu(i, cpu_core_mask(cpu)) { + set_cpus_unrelated(cpu, i, cpu_core_mask); + set_cpus_unrelated(cpu, i, cpu_l2_cache_mask); + set_cpus_unrelated(cpu, i, cpu_sibling_mask); + } +} +#endif + +static void add_cpu_to_masks(int cpu) +{ + int first_thread = cpu_first_thread_sibling(cpu); + int chipid = cpu_to_chip_id(cpu); + int i; + + /* + * This CPU will not be in the online mask yet so we need to manually + * add it to it's own thread sibling mask. + */ + cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + + for (i = first_thread; i < first_thread + threads_per_core; i++) + if (cpu_online(i)) + set_cpus_related(i, cpu, cpu_sibling_mask); + + /* + * Copy the thread sibling mask into the cache sibling mask + * and mark any CPUs that share an L2 with this CPU. + */ + for_each_cpu(i, cpu_sibling_mask(cpu)) + set_cpus_related(cpu, i, cpu_l2_cache_mask); + update_mask_by_l2(cpu, cpu_l2_cache_mask); + + /* + * Copy the cache sibling mask into core sibling mask and mark + * any CPUs on the same chip as this CPU. + */ + for_each_cpu(i, cpu_l2_cache_mask(cpu)) + set_cpus_related(cpu, i, cpu_core_mask); + + if (chipid == -1) + return; + + for_each_cpu(i, cpu_online_mask) + if (cpu_to_chip_id(i) == chipid) + set_cpus_related(cpu, i, cpu_core_mask); +} + +static bool shared_caches; + /* Activate a secondary processor. */ void start_secondary(void *unused) { unsigned int cpu = smp_processor_id(); - int i, base; mmgrab(&init_mm); current->active_mm = &init_mm; @@ -945,22 +985,15 @@ void start_secondary(void *unused) vdso_getcpu_init(); #endif - /* Update sibling maps */ - base = cpu_first_thread_sibling(cpu); - for (i = 0; i < threads_per_core; i++) { - if (cpu_is_offline(base + i) && (cpu != base + i)) - continue; - cpumask_set_cpu(cpu, cpu_sibling_mask(base + i)); - cpumask_set_cpu(base + i, cpu_sibling_mask(cpu)); + /* Update topology CPU masks */ + add_cpu_to_masks(cpu); - /* cpu_core_map should be a superset of - * cpu_sibling_map even if we don't have cache - * information, so update the former here, too. - */ - cpumask_set_cpu(cpu, cpu_core_mask(base + i)); - cpumask_set_cpu(base + i, cpu_core_mask(cpu)); - } - traverse_core_siblings(cpu, true); + /* + * Check for any shared caches. Note that this must be done on a + * per-core basis because one core in the pair might be disabled. + */ + if (!cpumask_equal(cpu_l2_cache_mask(cpu), cpu_sibling_mask(cpu))) + shared_caches = true; set_numa_node(numa_cpu_lookup_table[cpu]); set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); @@ -1003,35 +1036,65 @@ static struct sched_domain_topology_level powerpc_topology[] = { { NULL, }, }; -static __init long smp_setup_cpu_workfn(void *data __always_unused) +/* + * P9 has a slightly odd architecture where pairs of cores share an L2 cache. + * This topology makes it *much* cheaper to migrate tasks between adjacent cores + * since the migrated task remains cache hot. We want to take advantage of this + * at the scheduler level so an extra topology level is required. + */ +static int powerpc_shared_cache_flags(void) { - smp_ops->setup_cpu(boot_cpuid); - return 0; + return SD_SHARE_PKG_RESOURCES; } +/* + * We can't just pass cpu_l2_cache_mask() directly because + * returns a non-const pointer and the compiler barfs on that. + */ +static const struct cpumask *shared_cache_mask(int cpu) +{ + return cpu_l2_cache_mask(cpu); +} + +static struct sched_domain_topology_level power9_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, +#endif + { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + void __init smp_cpus_done(unsigned int max_cpus) { /* - * We want the setup_cpu() here to be called on the boot CPU, but - * init might run on any CPU, so make sure it's invoked on the boot - * CPU. + * We are running pinned to the boot CPU, see rest_init(). */ if (smp_ops && smp_ops->setup_cpu) - work_on_cpu_safe(boot_cpuid, smp_setup_cpu_workfn, NULL); + smp_ops->setup_cpu(boot_cpuid); if (smp_ops && smp_ops->bringup_done) smp_ops->bringup_done(); dump_numa_cpu_topology(); - set_sched_topology(powerpc_topology); + /* + * If any CPU detects that it's sharing a cache with another CPU then + * use the deeper topology that is aware of this sharing. + */ + if (shared_caches) { + pr_info("Using shared cache scheduler topology\n"); + set_sched_topology(power9_topology); + } else { + pr_info("Using standard scheduler topology\n"); + set_sched_topology(powerpc_topology); + } } #ifdef CONFIG_HOTPLUG_CPU int __cpu_disable(void) { int cpu = smp_processor_id(); - int base, i; int err; if (!smp_ops->cpu_disable) @@ -1042,14 +1105,7 @@ int __cpu_disable(void) return err; /* Update sibling maps */ - base = cpu_first_thread_sibling(cpu); - for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) { - cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i)); - cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu)); - cpumask_clear_cpu(cpu, cpu_core_mask(base + i)); - cpumask_clear_cpu(base + i, cpu_core_mask(cpu)); - } - traverse_core_siblings(cpu, false); + remove_cpu_from_masks(cpu); return 0; } diff --git a/arch/powerpc/kernel/swsusp_asm64.S b/arch/powerpc/kernel/swsusp_asm64.S index 988f38dced0f..82d8aae81c6a 100644 --- a/arch/powerpc/kernel/swsusp_asm64.S +++ b/arch/powerpc/kernel/swsusp_asm64.S @@ -179,7 +179,7 @@ nothing_to_copy: sld r3, r3, r0 li r0, 0 1: - dcbf r0,r3 + dcbf 0,r3 addi r3,r3,0x20 bdnz 1b diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S index 4d6b1d3a747f..7ccb7f81f8db 100644 --- a/arch/powerpc/kernel/systbl.S +++ b/arch/powerpc/kernel/systbl.S @@ -17,13 +17,13 @@ #include <asm/ppc_asm.h> #ifdef CONFIG_PPC64 -#define SYSCALL(func) .llong DOTSYM(sys_##func),DOTSYM(sys_##func) -#define COMPAT_SYS(func) .llong DOTSYM(sys_##func),DOTSYM(compat_sys_##func) -#define PPC_SYS(func) .llong DOTSYM(ppc_##func),DOTSYM(ppc_##func) -#define OLDSYS(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) -#define SYS32ONLY(func) .llong DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) -#define PPC64ONLY(func) .llong DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall) -#define SYSX(f, f3264, f32) .llong DOTSYM(f),DOTSYM(f3264) +#define SYSCALL(func) .8byte DOTSYM(sys_##func),DOTSYM(sys_##func) +#define COMPAT_SYS(func) .8byte DOTSYM(sys_##func),DOTSYM(compat_sys_##func) +#define PPC_SYS(func) .8byte DOTSYM(ppc_##func),DOTSYM(ppc_##func) +#define OLDSYS(func) .8byte DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall) +#define SYS32ONLY(func) .8byte DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func) +#define PPC64ONLY(func) .8byte DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall) +#define SYSX(f, f3264, f32) .8byte DOTSYM(f),DOTSYM(f3264) #else #define SYSCALL(func) .long sys_##func #define COMPAT_SYS(func) .long sys_##func diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index bfcfd9ef09f2..ec74e203ee04 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -114,6 +114,28 @@ static void pmac_backlight_unblank(void) static inline void pmac_backlight_unblank(void) { } #endif +/* + * If oops/die is expected to crash the machine, return true here. + * + * This should not be expected to be 100% accurate, there may be + * notifiers registered or other unexpected conditions that may bring + * down the kernel. Or if the current process in the kernel is holding + * locks or has other critical state, the kernel may become effectively + * unusable anyway. + */ +bool die_will_crash(void) +{ + if (should_fadump_crash()) + return true; + if (kexec_should_crash(current)) + return true; + if (in_interrupt() || panic_on_oops || + !current->pid || is_global_init(current)) + return true; + + return false; +} + static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; static int die_owner = -1; static unsigned int die_nest_count; @@ -162,21 +184,9 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, crash_fadump(regs, "die oops"); - /* - * A system reset (0x100) is a request to dump, so we always send - * it through the crashdump code. - */ - if (kexec_should_crash(current) || (TRAP(regs) == 0x100)) { + if (kexec_should_crash(current)) crash_kexec(regs); - /* - * We aren't the primary crash CPU. We need to send it - * to a holding pattern to avoid it ending up in the panic - * code. - */ - crash_kexec_secondary(regs); - } - if (!signr) return; @@ -202,18 +212,25 @@ NOKPROBE_SYMBOL(oops_end); static int __die(const char *str, struct pt_regs *regs, long err) { printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP NR_CPUS=%d ", NR_CPUS); -#endif + + if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) + printk("LE "); + else + printk("BE "); + + if (IS_ENABLED(CONFIG_PREEMPT)) + pr_cont("PREEMPT "); + + if (IS_ENABLED(CONFIG_SMP)) + pr_cont("SMP NR_CPUS=%d ", NR_CPUS); + if (debug_pagealloc_enabled()) - printk("DEBUG_PAGEALLOC "); -#ifdef CONFIG_NUMA - printk("NUMA "); -#endif - printk("%s\n", ppc_md.name ? ppc_md.name : ""); + pr_cont("DEBUG_PAGEALLOC "); + + if (IS_ENABLED(CONFIG_NUMA)) + pr_cont("NUMA "); + + pr_cont("%s\n", ppc_md.name ? ppc_md.name : ""); if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP) return 1; @@ -288,23 +305,52 @@ void system_reset_exception(struct pt_regs *regs) if (!nested) nmi_enter(); + __this_cpu_inc(irq_stat.sreset_irqs); + /* See if any machine dependent calls */ if (ppc_md.system_reset_exception) { if (ppc_md.system_reset_exception(regs)) goto out; } - die("System Reset", regs, SIGABRT); + if (debugger(regs)) + goto out; + + /* + * A system reset is a request to dump, so we always send + * it through the crashdump code (if fadump or kdump are + * registered). + */ + crash_fadump(regs, "System Reset"); + + crash_kexec(regs); + + /* + * We aren't the primary crash CPU. We need to send it + * to a holding pattern to avoid it ending up in the panic + * code. + */ + crash_kexec_secondary(regs); + + /* + * No debugger or crash dump registered, print logs then + * panic. + */ + __die("System Reset", regs, SIGABRT); + + mdelay(2*MSEC_PER_SEC); /* Wait a little while for others to print */ + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + nmi_panic(regs, "System Reset"); out: #ifdef CONFIG_PPC_BOOK3S_64 BUG_ON(get_paca()->in_nmi == 0); if (get_paca()->in_nmi > 1) - panic("Unrecoverable nested System Reset"); + nmi_panic(regs, "Unrecoverable nested System Reset"); #endif /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - panic("Unrecoverable System Reset"); + nmi_panic(regs, "Unrecoverable System Reset"); if (!nested) nmi_exit(); @@ -312,39 +358,6 @@ out: /* What should we do here? We could issue a shutdown or hard reset. */ } -#ifdef CONFIG_PPC64 -/* - * This function is called in real mode. Strictly no printk's please. - * - * regs->nip and regs->msr contains srr0 and ssr1. - */ -long machine_check_early(struct pt_regs *regs) -{ - long handled = 0; - - __this_cpu_inc(irq_stat.mce_exceptions); - - if (cur_cpu_spec && cur_cpu_spec->machine_check_early) - handled = cur_cpu_spec->machine_check_early(regs); - return handled; -} - -long hmi_exception_realmode(struct pt_regs *regs) -{ - __this_cpu_inc(irq_stat.hmi_exceptions); - - wait_for_subcore_guest_exit(); - - if (ppc_md.hmi_exception_early) - ppc_md.hmi_exception_early(regs); - - wait_for_tb_resync(); - - return 0; -} - -#endif - /* * I/O accesses can cause machine checks on powermacs. * Check if the NIP corresponds to the address of a sync @@ -397,11 +410,6 @@ static inline int check_io_access(struct pt_regs *regs) /* On 4xx, the reason for the machine check or program exception is in the ESR. */ #define get_reason(regs) ((regs)->dsisr) -#ifndef CONFIG_FSL_BOOKE -#define get_mc_reason(regs) ((regs)->dsisr) -#else -#define get_mc_reason(regs) (mfspr(SPRN_MCSR)) -#endif #define REASON_FP ESR_FP #define REASON_ILLEGAL (ESR_PIL | ESR_PUO) #define REASON_PRIVILEGED ESR_PPR @@ -415,108 +423,17 @@ static inline int check_io_access(struct pt_regs *regs) /* On non-4xx, the reason for the machine check or program exception is in the MSR. */ #define get_reason(regs) ((regs)->msr) -#define get_mc_reason(regs) ((regs)->msr) -#define REASON_TM 0x200000 -#define REASON_FP 0x100000 -#define REASON_ILLEGAL 0x80000 -#define REASON_PRIVILEGED 0x40000 -#define REASON_TRAP 0x20000 +#define REASON_TM SRR1_PROGTM +#define REASON_FP SRR1_PROGFPE +#define REASON_ILLEGAL SRR1_PROGILL +#define REASON_PRIVILEGED SRR1_PROGPRIV +#define REASON_TRAP SRR1_PROGTRAP #define single_stepping(regs) ((regs)->msr & MSR_SE) #define clear_single_step(regs) ((regs)->msr &= ~MSR_SE) #endif -#if defined(CONFIG_4xx) -int machine_check_4xx(struct pt_regs *regs) -{ - unsigned long reason = get_mc_reason(regs); - - if (reason & ESR_IMCP) { - printk("Instruction"); - mtspr(SPRN_ESR, reason & ~ESR_IMCP); - } else - printk("Data"); - printk(" machine check in kernel mode.\n"); - - return 0; -} - -int machine_check_440A(struct pt_regs *regs) -{ - unsigned long reason = get_mc_reason(regs); - - printk("Machine check in kernel mode.\n"); - if (reason & ESR_IMCP){ - printk("Instruction Synchronous Machine Check exception\n"); - mtspr(SPRN_ESR, reason & ~ESR_IMCP); - } - else { - u32 mcsr = mfspr(SPRN_MCSR); - if (mcsr & MCSR_IB) - printk("Instruction Read PLB Error\n"); - if (mcsr & MCSR_DRB) - printk("Data Read PLB Error\n"); - if (mcsr & MCSR_DWB) - printk("Data Write PLB Error\n"); - if (mcsr & MCSR_TLBP) - printk("TLB Parity Error\n"); - if (mcsr & MCSR_ICP){ - flush_instruction_cache(); - printk("I-Cache Parity Error\n"); - } - if (mcsr & MCSR_DCSP) - printk("D-Cache Search Parity Error\n"); - if (mcsr & MCSR_DCFP) - printk("D-Cache Flush Parity Error\n"); - if (mcsr & MCSR_IMPE) - printk("Machine Check exception is imprecise\n"); - - /* Clear MCSR */ - mtspr(SPRN_MCSR, mcsr); - } - return 0; -} - -int machine_check_47x(struct pt_regs *regs) -{ - unsigned long reason = get_mc_reason(regs); - u32 mcsr; - - printk(KERN_ERR "Machine check in kernel mode.\n"); - if (reason & ESR_IMCP) { - printk(KERN_ERR - "Instruction Synchronous Machine Check exception\n"); - mtspr(SPRN_ESR, reason & ~ESR_IMCP); - return 0; - } - mcsr = mfspr(SPRN_MCSR); - if (mcsr & MCSR_IB) - printk(KERN_ERR "Instruction Read PLB Error\n"); - if (mcsr & MCSR_DRB) - printk(KERN_ERR "Data Read PLB Error\n"); - if (mcsr & MCSR_DWB) - printk(KERN_ERR "Data Write PLB Error\n"); - if (mcsr & MCSR_TLBP) - printk(KERN_ERR "TLB Parity Error\n"); - if (mcsr & MCSR_ICP) { - flush_instruction_cache(); - printk(KERN_ERR "I-Cache Parity Error\n"); - } - if (mcsr & MCSR_DCSP) - printk(KERN_ERR "D-Cache Search Parity Error\n"); - if (mcsr & PPC47x_MCSR_GPR) - printk(KERN_ERR "GPR Parity Error\n"); - if (mcsr & PPC47x_MCSR_FPR) - printk(KERN_ERR "FPR Parity Error\n"); - if (mcsr & PPC47x_MCSR_IPR) - printk(KERN_ERR "Machine Check exception is imprecise\n"); - - /* Clear MCSR */ - mtspr(SPRN_MCSR, mcsr); - - return 0; -} -#elif defined(CONFIG_E500) +#if defined(CONFIG_E500) int machine_check_e500mc(struct pt_regs *regs) { unsigned long mcsr = mfspr(SPRN_MCSR); @@ -618,7 +535,7 @@ silent_out: int machine_check_e500(struct pt_regs *regs) { - unsigned long reason = get_mc_reason(regs); + unsigned long reason = mfspr(SPRN_MCSR); if (reason & MCSR_BUS_RBERR) { if (fsl_rio_mcheck_exception(regs)) @@ -665,7 +582,7 @@ int machine_check_generic(struct pt_regs *regs) #elif defined(CONFIG_E200) int machine_check_e200(struct pt_regs *regs) { - unsigned long reason = get_mc_reason(regs); + unsigned long reason = mfspr(SPRN_MCSR); printk("Machine check in kernel mode.\n"); printk("Caused by (from MCSR=%lx): ", reason); @@ -687,35 +604,10 @@ int machine_check_e200(struct pt_regs *regs) return 0; } -#elif defined(CONFIG_PPC_8xx) -int machine_check_8xx(struct pt_regs *regs) -{ - unsigned long reason = get_mc_reason(regs); - - pr_err("Machine check in kernel mode.\n"); - pr_err("Caused by (from SRR1=%lx): ", reason); - if (reason & 0x40000000) - pr_err("Fetch error at address %lx\n", regs->nip); - else - pr_err("Data access error at address %lx\n", regs->dar); - -#ifdef CONFIG_PCI - /* the qspan pci read routines can cause machine checks -- Cort - * - * yuck !!! that totally needs to go away ! There are better ways - * to deal with that than having a wart in the mcheck handler. - * -- BenH - */ - bad_page_fault(regs, regs->dar, SIGBUS); - return 1; -#else - return 0; -#endif -} -#else +#elif defined(CONFIG_PPC32) int machine_check_generic(struct pt_regs *regs) { - unsigned long reason = get_mc_reason(regs); + unsigned long reason = regs->msr; printk("Machine check in kernel mode.\n"); printk("Caused by (from SRR1=%lx): ", reason); @@ -752,10 +644,14 @@ int machine_check_generic(struct pt_regs *regs) void machine_check_exception(struct pt_regs *regs) { - enum ctx_state prev_state = exception_enter(); int recover = 0; + bool nested = in_nmi(); + if (!nested) + nmi_enter(); - __this_cpu_inc(irq_stat.mce_exceptions); + /* 64s accounts the mce in machine_check_early when in HVMODE */ + if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64) || !cpu_has_feature(CPU_FTR_HVMODE)) + __this_cpu_inc(irq_stat.mce_exceptions); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); @@ -783,10 +679,11 @@ void machine_check_exception(struct pt_regs *regs) /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - panic("Unrecoverable Machine check"); + nmi_panic(regs, "Unrecoverable Machine check"); bail: - exception_exit(prev_state); + if (!nested) + nmi_exit(); } void SMIException(struct pt_regs *regs) @@ -1672,24 +1569,6 @@ void performance_monitor_exception(struct pt_regs *regs) perf_irq(regs); } -#ifdef CONFIG_8xx -void SoftwareEmulation(struct pt_regs *regs) -{ - CHECK_FULL_REGS(regs); - - if (!user_mode(regs)) { - debugger(regs); - die("Kernel Mode Unimplemented Instruction or SW FPU Emulation", - regs, SIGFPE); - } - - if (!emulate_math(regs)) - return; - - _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); -} -#endif /* CONFIG_8xx */ - #ifdef CONFIG_PPC_ADV_DEBUG_REGS static void handle_debug(struct pt_regs *regs, unsigned long debug_status) { diff --git a/arch/powerpc/kernel/uprobes.c b/arch/powerpc/kernel/uprobes.c index 003b20964ea0..5d105b8eeece 100644 --- a/arch/powerpc/kernel/uprobes.c +++ b/arch/powerpc/kernel/uprobes.c @@ -205,3 +205,12 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs return orig_ret_vaddr; } + +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CHAIN_CALL) + return regs->gpr[1] <= ret->stack; + else + return regs->gpr[1] < ret->stack; +} diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index 6b2b69616e77..769c2624e0a6 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -232,15 +232,9 @@ __do_get_tspec: lwz r6,(CFG_TB_ORIG_STAMP+4)(r9) /* Get a stable TB value */ -#ifdef CONFIG_8xx -2: mftbu r3 - mftbl r4 - mftbu r0 -#else -2: mfspr r3, SPRN_TBRU - mfspr r4, SPRN_TBRL - mfspr r0, SPRN_TBRU -#endif +2: MFTBU(r3) + MFTBL(r4) + MFTBU(r0) cmplw cr0,r3,r0 bne- 2b diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index b1a250560198..882628fa6987 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -8,7 +8,7 @@ #include <asm/cache.h> #include <asm/thread_info.h> -#ifdef CONFIG_STRICT_KERNEL_RWX +#if defined(CONFIG_STRICT_KERNEL_RWX) && !defined(CONFIG_PPC32) #define STRICT_ALIGN_SIZE (1 << 24) #else #define STRICT_ALIGN_SIZE PAGE_SIZE diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index b67f8b03a32d..2f6eadd9408d 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -71,15 +71,20 @@ static inline void wd_smp_lock(unsigned long *flags) * This may be called from low level interrupt handlers at some * point in future. */ - local_irq_save(*flags); - while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) - cpu_relax(); + raw_local_irq_save(*flags); + hard_irq_disable(); /* Make it soft-NMI safe */ + while (unlikely(test_and_set_bit_lock(0, &__wd_smp_lock))) { + raw_local_irq_restore(*flags); + spin_until_cond(!test_bit(0, &__wd_smp_lock)); + raw_local_irq_save(*flags); + hard_irq_disable(); + } } static inline void wd_smp_unlock(unsigned long *flags) { clear_bit_unlock(0, &__wd_smp_lock); - local_irq_restore(*flags); + raw_local_irq_restore(*flags); } static void wd_lockup_ipi(struct pt_regs *regs) @@ -96,10 +101,10 @@ static void wd_lockup_ipi(struct pt_regs *regs) nmi_panic(regs, "Hard LOCKUP"); } -static void set_cpu_stuck(int cpu, u64 tb) +static void set_cpumask_stuck(const struct cpumask *cpumask, u64 tb) { - cpumask_set_cpu(cpu, &wd_smp_cpus_stuck); - cpumask_clear_cpu(cpu, &wd_smp_cpus_pending); + cpumask_or(&wd_smp_cpus_stuck, &wd_smp_cpus_stuck, cpumask); + cpumask_andnot(&wd_smp_cpus_pending, &wd_smp_cpus_pending, cpumask); if (cpumask_empty(&wd_smp_cpus_pending)) { wd_smp_last_reset_tb = tb; cpumask_andnot(&wd_smp_cpus_pending, @@ -107,6 +112,10 @@ static void set_cpu_stuck(int cpu, u64 tb) &wd_smp_cpus_stuck); } } +static void set_cpu_stuck(int cpu, u64 tb) +{ + set_cpumask_stuck(cpumask_of(cpu), tb); +} static void watchdog_smp_panic(int cpu, u64 tb) { @@ -135,11 +144,9 @@ static void watchdog_smp_panic(int cpu, u64 tb) } smp_flush_nmi_ipi(1000000); - /* Take the stuck CPU out of the watch group */ - for_each_cpu(c, &wd_smp_cpus_pending) - set_cpu_stuck(c, tb); + /* Take the stuck CPUs out of the watch group */ + set_cpumask_stuck(&wd_smp_cpus_pending, tb); -out: wd_smp_unlock(&flags); printk_safe_flush(); @@ -152,6 +159,11 @@ out: if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); + + return; + +out: + wd_smp_unlock(&flags); } static void wd_smp_clear_cpu_pending(int cpu, u64 tb) @@ -204,6 +216,9 @@ void soft_nmi_interrupt(struct pt_regs *regs) return; nmi_enter(); + + __this_cpu_inc(irq_stat.soft_nmi_irqs); + tb = get_tb(); if (tb - per_cpu(wd_timer_tb, cpu) >= wd_panic_timeout_tb) { per_cpu(wd_timer_tb, cpu) = tb; @@ -258,9 +273,11 @@ static void wd_timer_fn(unsigned long data) void arch_touch_nmi_watchdog(void) { + unsigned long ticks = tb_ticks_per_usec * wd_timer_period_ms * 1000; int cpu = smp_processor_id(); - watchdog_timer_interrupt(cpu); + if (get_tb() - per_cpu(wd_timer_tb, cpu) >= ticks) + watchdog_timer_interrupt(cpu); } EXPORT_SYMBOL(arch_touch_nmi_watchdog); @@ -283,6 +300,8 @@ static void stop_watchdog_timer_on(unsigned int cpu) static int start_wd_on_cpu(unsigned int cpu) { + unsigned long flags; + if (cpumask_test_cpu(cpu, &wd_cpus_enabled)) { WARN_ON(1); return 0; @@ -297,12 +316,14 @@ static int start_wd_on_cpu(unsigned int cpu) if (!cpumask_test_cpu(cpu, &watchdog_cpumask)) return 0; + wd_smp_lock(&flags); cpumask_set_cpu(cpu, &wd_cpus_enabled); if (cpumask_weight(&wd_cpus_enabled) == 1) { cpumask_set_cpu(cpu, &wd_smp_cpus_pending); wd_smp_last_reset_tb = get_tb(); } - smp_wmb(); + wd_smp_unlock(&flags); + start_watchdog_timer_on(cpu); return 0; @@ -310,12 +331,17 @@ static int start_wd_on_cpu(unsigned int cpu) static int stop_wd_on_cpu(unsigned int cpu) { + unsigned long flags; + if (!cpumask_test_cpu(cpu, &wd_cpus_enabled)) return 0; /* Can happen in CPU unplug case */ stop_watchdog_timer_on(cpu); + wd_smp_lock(&flags); cpumask_clear_cpu(cpu, &wd_cpus_enabled); + wd_smp_unlock(&flags); + wd_smp_clear_cpu_pending(cpu, get_tb()); return 0; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index b42812e014c0..67075e065ef2 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -37,6 +37,7 @@ #include <asm/synch.h> #include <asm/ppc-opcode.h> #include <asm/cputable.h> +#include <asm/pte-walk.h> #include "trace_hv.h" @@ -599,8 +600,8 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, * hugepage split and collapse. */ local_irq_save(flags); - ptep = find_linux_pte_or_hugepte(current->mm->pgd, - hva, NULL, NULL); + ptep = find_current_mm_pte(current->mm->pgd, + hva, NULL, NULL); if (ptep) { pte = kvmppc_read_update_linux_pte(ptep, 1); if (__pte_write(pte)) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index f6b3e67c5762..c5d7435455f1 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -17,6 +17,7 @@ #include <asm/mmu.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> +#include <asm/pte-walk.h> /* * Supported radix tree geometry. @@ -322,13 +323,13 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, gpa = vcpu->arch.fault_gpa & ~0xfffUL; gpa &= ~0xF000000000000000ul; gfn = gpa >> PAGE_SHIFT; - if (!(dsisr & DSISR_PGDIRFAULT)) + if (!(dsisr & DSISR_PRTABLE_FAULT)) gpa |= ea & 0xfff; memslot = gfn_to_memslot(kvm, gfn); /* No memslot means it's an emulated MMIO region */ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) { - if (dsisr & (DSISR_PGDIRFAULT | DSISR_BADACCESS | + if (dsisr & (DSISR_PRTABLE_FAULT | DSISR_BADACCESS | DSISR_SET_RC)) { /* * Bad address in guest page table tree, or other @@ -359,8 +360,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, if (writing) pgflags |= _PAGE_DIRTY; local_irq_save(flags); - ptep = __find_linux_pte_or_hugepte(current->mm->pgd, hva, - NULL, NULL); + ptep = find_current_mm_pte(current->mm->pgd, hva, NULL, NULL); if (ptep) { pte = READ_ONCE(*ptep); if (pte_present(pte) && @@ -374,8 +374,12 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, spin_unlock(&kvm->mmu_lock); return RESUME_GUEST; } - ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, - gpa, NULL, &shift); + /* + * We are walking the secondary page table here. We can do this + * without disabling irq. + */ + ptep = __find_linux_pte(kvm->arch.pgtable, + gpa, NULL, &shift); if (ptep && pte_present(*ptep)) { kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift); @@ -427,8 +431,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu, pgflags |= _PAGE_WRITE; } else { local_irq_save(flags); - ptep = __find_linux_pte_or_hugepte(current->mm->pgd, - hva, NULL, NULL); + ptep = find_current_mm_pte(current->mm->pgd, + hva, NULL, NULL); if (ptep && pte_write(*ptep) && pte_dirty(*ptep)) pgflags |= _PAGE_WRITE; local_irq_restore(flags); @@ -499,8 +503,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned int shift; unsigned long old; - ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, - NULL, &shift); + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep)) { old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0, gpa, shift); @@ -525,8 +528,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned int shift; int ref = 0; - ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, - NULL, &shift); + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_young(*ptep)) { kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0, gpa, shift); @@ -545,8 +547,7 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, unsigned int shift; int ref = 0; - ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, - NULL, &shift); + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_young(*ptep)) ref = 1; return ref; @@ -562,8 +563,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm, unsigned int shift; int ret = 0; - ptep = __find_linux_pte_or_hugepte(kvm->arch.pgtable, gpa, - NULL, &shift); + ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift); if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) { ret = 1; if (shift) diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index a160c14304eb..53766e2bc029 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -294,32 +294,26 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args) { struct kvmppc_spapr_tce_table *stt = NULL; + struct kvmppc_spapr_tce_table *siter; unsigned long npages, size; int ret = -ENOMEM; int i; + int fd = -1; if (!args->size) return -EINVAL; - /* Check this LIOBN hasn't been previously allocated */ - list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { - if (stt->liobn == args->liobn) - return -EBUSY; - } - size = _ALIGN_UP(args->size, PAGE_SIZE >> 3); npages = kvmppc_tce_pages(size); ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true); - if (ret) { - stt = NULL; - goto fail; - } + if (ret) + return ret; ret = -ENOMEM; stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), GFP_KERNEL); if (!stt) - goto fail; + goto fail_acct; stt->liobn = args->liobn; stt->page_shift = args->page_shift; @@ -334,24 +328,42 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, goto fail; } - kvm_get_kvm(kvm); + ret = fd = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, + stt, O_RDWR | O_CLOEXEC); + if (ret < 0) + goto fail; mutex_lock(&kvm->lock); - list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); + + /* Check this LIOBN hasn't been previously allocated */ + ret = 0; + list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) { + if (siter->liobn == args->liobn) { + ret = -EBUSY; + break; + } + } + + if (!ret) { + list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); + kvm_get_kvm(kvm); + } mutex_unlock(&kvm->lock); - return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, - stt, O_RDWR | O_CLOEXEC); + if (!ret) + return fd; -fail: - if (stt) { - for (i = 0; i < npages; i++) - if (stt->pages[i]) - __free_page(stt->pages[i]); + put_unused_fd(fd); - kfree(stt); - } + fail: + for (i = 0; i < npages; i++) + if (stt->pages[i]) + __free_page(stt->pages[i]); + + kfree(stt); + fail_acct: + kvmppc_account_memlimit(kvmppc_stt_pages(npages), false); return ret; } diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c index 3adfd2f5301c..c32e9bfe75b1 100644 --- a/arch/powerpc/kvm/book3s_64_vio_hv.c +++ b/arch/powerpc/kvm/book3s_64_vio_hv.c @@ -39,6 +39,7 @@ #include <asm/udbg.h> #include <asm/iommu.h> #include <asm/tce.h> +#include <asm/pte-walk.h> #ifdef CONFIG_BUG @@ -353,7 +354,16 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu, pte_t *ptep, pte; unsigned shift = 0; - ptep = __find_linux_pte_or_hugepte(vcpu->arch.pgdir, ua, NULL, &shift); + /* + * Called in real mode with MSR_EE = 0. We are safe here. + * It is ok to do the lookup with arch.pgdir here, because + * we are doing this on secondary cpus and current task there + * is not the hypervisor. Also this is safe against THP in the + * host, because an IPI to primary thread will wait for the secondary + * to exit which will agains result in the below page table walk + * to finish. + */ + ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift); if (!ptep || !pte_present(*ptep)) return -ENXIO; pte = *ptep; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 359c79cdf0cc..ebcf97cb5c98 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2111,6 +2111,15 @@ static int kvmppc_grab_hwthread(int cpu) struct paca_struct *tpaca; long timeout = 10000; + /* + * ISA v3.0 idle routines do not set hwthread_state or test + * hwthread_req, so they can not grab idle threads. + */ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + WARN(1, "KVM: can not control sibling threads\n"); + return -EBUSY; + } + tpaca = &paca[cpu]; /* Ensure the thread won't go into the kernel if it wakes */ @@ -2145,10 +2154,12 @@ static void kvmppc_release_hwthread(int cpu) struct paca_struct *tpaca; tpaca = &paca[cpu]; - tpaca->kvm_hstate.hwthread_req = 0; tpaca->kvm_hstate.kvm_vcpu = NULL; tpaca->kvm_hstate.kvm_vcore = NULL; tpaca->kvm_hstate.kvm_split_mode = NULL; + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + tpaca->kvm_hstate.hwthread_req = 0; + } static void radix_flush_cpu(struct kvm *kvm, int cpu, struct kvm_vcpu *vcpu) diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index 584c74c8119f..fedb0139524c 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -22,6 +22,7 @@ #include <asm/hvcall.h> #include <asm/synch.h> #include <asm/ppc-opcode.h> +#include <asm/pte-walk.h> /* Translate address of a vmalloc'd thing to a linear map address */ static void *real_vmalloc_addr(void *x) @@ -31,9 +32,9 @@ static void *real_vmalloc_addr(void *x) /* * assume we don't have huge pages in vmalloc space... * So don't worry about THP collapse/split. Called - * Only in realmode, hence won't need irq_save/restore. + * Only in realmode with MSR_EE = 0, hence won't need irq_save/restore. */ - p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL, NULL); + p = find_init_mm_pte(addr, NULL); if (!p || !pte_present(*p)) return NULL; addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK); @@ -230,14 +231,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags, * If we had a page table table change after lookup, we would * retry via mmu_notifier_retry. */ - if (realmode) - ptep = __find_linux_pte_or_hugepte(pgdir, hva, NULL, - &hpage_shift); - else { + if (!realmode) local_irq_save(irq_flags); - ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, - &hpage_shift); - } + /* + * If called in real mode we have MSR_EE = 0. Otherwise + * we disable irq above. + */ + ptep = __find_linux_pte(pgdir, hva, NULL, &hpage_shift); if (ptep) { pte_t pte; unsigned int host_pte_size; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index c52184a8efdf..2259b6cde119 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -149,9 +149,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) subf r4, r4, r3 mtspr SPRN_DEC, r4 +BEGIN_FTR_SECTION /* hwthread_req may have got set by cede or no vcpu, so clear it */ li r0, 0 stb r0, HSTATE_HWTHREAD_REQ(r13) +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) /* * For external interrupts we need to call the Linux @@ -314,6 +316,7 @@ kvm_novcpu_exit: * Relocation is off and most register values are lost. * r13 points to the PACA. * r3 contains the SRR1 wakeup value, SRR1 is trashed. + * This is not used by ISAv3.0B processors. */ .globl kvm_start_guest kvm_start_guest: @@ -432,6 +435,9 @@ kvm_secondary_got_guest: * While waiting we also need to check if we get given a vcpu to run. */ kvm_no_guest: +BEGIN_FTR_SECTION + twi 31,0,0 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r3, HSTATE_HWTHREAD_REQ(r13) cmpwi r3, 0 bne 53f @@ -1291,6 +1297,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Hypervisor doorbell - exit only if host IPI flag set */ cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL bne 3f +BEGIN_FTR_SECTION + PPC_MSGSYNC +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 beq 4f @@ -2509,8 +2518,10 @@ kvm_do_nap: clrrdi r0, r0, 1 mtspr SPRN_CTRLT, r0 +BEGIN_FTR_SECTION li r0,1 stb r0,HSTATE_HWTHREAD_REQ(r13) +END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300) mfspr r5,SPRN_LPCR ori r5,r5,LPCR_PECE0 | LPCR_PECE1 BEGIN_FTR_SECTION diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c index 4636ca6e7d38..d1ed2c41b5d2 100644 --- a/arch/powerpc/kvm/book3s_xive_template.c +++ b/arch/powerpc/kvm/book3s_xive_template.c @@ -16,7 +16,22 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc) u8 cppr; u16 ack; - /* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */ + /* + * Ensure any previous store to CPPR is ordered vs. + * the subsequent loads from PIPR or ACK. + */ + eieio(); + + /* + * DD1 bug workaround: If PIPR is less favored than CPPR + * ignore the interrupt or we might incorrectly lose an IPB + * bit. + */ + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { + u8 pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR); + if (pipr >= xc->hw_cppr) + return; + } /* Perform the acknowledge OS to register cycle. */ ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG)); @@ -235,6 +250,11 @@ skip_ipi: /* * If we found an interrupt, adjust what the guest CPPR should * be as if we had just fetched that interrupt from HW. + * + * Note: This can only make xc->cppr smaller as the previous + * loop will only exit with hirq != 0 if prio is lower than + * the current xc->cppr. Thus we don't need to re-check xc->mfrr + * for pending IPIs. */ if (hirq) xc->cppr = prio; @@ -381,6 +401,12 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr) xc->cppr = cppr; /* + * Order the above update of xc->cppr with the subsequent + * read of xc->mfrr inside push_pending_to_hw() + */ + smp_mb(); + + /* * We are masking less, we need to look for pending things * to deliver and set VP pending bits accordingly to trigger * a new interrupt otherwise we might miss MFRR changes for @@ -420,21 +446,37 @@ X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr) * used to signal MFRR changes is EOId when fetched from * the queue. */ - if (irq == XICS_IPI || irq == 0) + if (irq == XICS_IPI || irq == 0) { + /* + * This barrier orders the setting of xc->cppr vs. + * subsquent test of xc->mfrr done inside + * scan_interrupts and push_pending_to_hw + */ + smp_mb(); goto bail; + } /* Find interrupt source */ sb = kvmppc_xive_find_source(xive, irq, &src); if (!sb) { pr_devel(" source not found !\n"); rc = H_PARAMETER; + /* Same as above */ + smp_mb(); goto bail; } state = &sb->irq_state[src]; kvmppc_xive_select_irq(state, &hw_num, &xd); state->in_eoi = true; - mb(); + + /* + * This barrier orders both setting of in_eoi above vs, + * subsequent test of guest_priority, and the setting + * of xc->cppr vs. subsquent test of xc->mfrr done inside + * scan_interrupts and push_pending_to_hw + */ + smp_mb(); again: if (state->guest_priority == MASKED) { @@ -461,6 +503,14 @@ again: } + /* + * This barrier orders the above guest_priority check + * and spin_lock/unlock with clearing in_eoi below. + * + * It also has to be a full mb() as it must ensure + * the MMIOs done in source_eoi() are completed before + * state->in_eoi is visible. + */ mb(); state->in_eoi = false; bail: @@ -495,6 +545,18 @@ X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server, /* Locklessly write over MFRR */ xc->mfrr = mfrr; + /* + * The load of xc->cppr below and the subsequent MMIO store + * to the IPI must happen after the above mfrr update is + * globally visible so that: + * + * - Synchronize with another CPU doing an H_EOI or a H_CPPR + * updating xc->cppr then reading xc->mfrr. + * + * - The target of the IPI sees the xc->mfrr update + */ + mb(); + /* Shoot the IPI if most favored than target cppr */ if (mfrr < xc->cppr) __x_writeq(0, __x_trig_page(&xc->vp_ipi_data)); diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 77fd043b3ecc..c6c734424c70 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -30,6 +30,7 @@ #include <linux/vmalloc.h> #include <linux/hugetlb.h> #include <asm/kvm_ppc.h> +#include <asm/pte-walk.h> #include "e500.h" #include "timing.h" @@ -476,7 +477,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, * can't run hence pfn won't change. */ local_irq_save(flags); - ptep = find_linux_pte_or_hugepte(pgdir, hva, NULL, NULL); + ptep = find_linux_pte(pgdir, hva, NULL, NULL); if (ptep) { pte_t pte = READ_ONCE(*ptep); diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 3c3146ba62da..50d5bf954cff 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -31,7 +31,8 @@ obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o obj-y += checksum_$(BITS).o checksum_wrappers.o -obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o +obj-y += sstep.o ldstfp.o quad.o +obj64-y += quad.o obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index 8aedbb5f4b86..da425bb6b369 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -67,6 +67,20 @@ CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT CACHELINE_MASK = (L1_CACHE_BYTES-1) +_GLOBAL(memset16) + rlwinm. r0 ,r5, 31, 1, 31 + addi r6, r3, -4 + beq- 2f + rlwimi r4 ,r4 ,16 ,0 ,15 + mtctr r0 +1: stwu r4, 4(r6) + bdnz 1b +2: andi. r0, r5, 1 + beqlr + sth r4, 4(r6) + blr +EXPORT_SYMBOL(memset16) + /* * Use dcbz on the complete cache lines in the destination * to set them to zero. This requires that the destination @@ -77,22 +91,24 @@ CACHELINE_MASK = (L1_CACHE_BYTES-1) * replaced by a nop once cache is active. This is done in machine_init() */ _GLOBAL(memset) + cmplwi 0,r5,4 + blt 7f + rlwimi r4,r4,8,16,23 rlwimi r4,r4,16,0,15 - addi r6,r3,-4 - cmplwi 0,r5,4 - blt 7f - stwu r4,4(r6) + stw r4,0(r3) beqlr - andi. r0,r6,3 + andi. r0,r3,3 add r5,r0,r5 - subf r6,r0,r6 + subf r6,r0,r3 cmplwi 0,r4,0 - bne 2f /* Use normal procedure if r4 is not zero */ -EXPORT_SYMBOL(memset) + /* + * Skip optimised bloc until cache is enabled. Will be replaced + * by 'bne' during boot to use normal procedure if r4 is not zero + */ _GLOBAL(memset_nocache_branch) - b 2f /* Skip optimised bloc until cache is enabled */ + b 2f clrlwi r7,r6,32-LG_CACHELINE_BYTES add r8,r7,r5 @@ -119,7 +135,6 @@ _GLOBAL(memset_nocache_branch) 1: stwu r4,4(r6) bdnz 1b 6: andi. r5,r5,3 -7: cmpwi 0,r5,0 beqlr mtctr r5 addi r6,r6,3 @@ -127,6 +142,15 @@ _GLOBAL(memset_nocache_branch) bdnz 8b blr +7: cmpwi 0,r5,0 + beqlr + mtctr r5 + addi r6,r3,-1 +9: stbu r4,1(r6) + bdnz 9b + blr +EXPORT_SYMBOL(memset) + /* * This version uses dcbz on the complete cache lines in the * destination area to reduce memory traffic. This requires that diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S index a84d333ecb09..ca5fc8fa7efc 100644 --- a/arch/powerpc/lib/copypage_power7.S +++ b/arch/powerpc/lib/copypage_power7.S @@ -45,13 +45,13 @@ _GLOBAL(copypage_power7) .machine push .machine "power4" /* setup read stream 0 */ - dcbt r0,r4,0b01000 /* addr from */ - dcbt r0,r7,0b01010 /* length and depth from */ + dcbt 0,r4,0b01000 /* addr from */ + dcbt 0,r7,0b01010 /* length and depth from */ /* setup write stream 1 */ - dcbtst r0,r9,0b01000 /* addr to */ - dcbtst r0,r10,0b01010 /* length and depth to */ + dcbtst 0,r9,0b01000 /* addr to */ + dcbtst 0,r10,0b01010 /* length and depth to */ eieio - dcbt r0,r8,0b01010 /* all streams GO */ + dcbt 0,r8,0b01010 /* all streams GO */ .machine pop #ifdef CONFIG_ALTIVEC @@ -83,7 +83,7 @@ _GLOBAL(copypage_power7) li r12,112 .align 5 -1: lvx v7,r0,r4 +1: lvx v7,0,r4 lvx v6,r4,r6 lvx v5,r4,r7 lvx v4,r4,r8 @@ -92,7 +92,7 @@ _GLOBAL(copypage_power7) lvx v1,r4,r11 lvx v0,r4,r12 addi r4,r4,128 - stvx v7,r0,r3 + stvx v7,0,r3 stvx v6,r3,r6 stvx v5,r3,r7 stvx v4,r3,r8 diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 706b7cc19846..d416a4a66578 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -315,13 +315,13 @@ err1; stb r0,0(r3) .machine push .machine "power4" /* setup read stream 0 */ - dcbt r0,r6,0b01000 /* addr from */ - dcbt r0,r7,0b01010 /* length and depth from */ + dcbt 0,r6,0b01000 /* addr from */ + dcbt 0,r7,0b01010 /* length and depth from */ /* setup write stream 1 */ - dcbtst r0,r9,0b01000 /* addr to */ - dcbtst r0,r10,0b01010 /* length and depth to */ + dcbtst 0,r9,0b01000 /* addr to */ + dcbtst 0,r10,0b01010 /* length and depth to */ eieio - dcbt r0,r8,0b01010 /* all streams GO */ + dcbt 0,r8,0b01010 /* all streams GO */ .machine pop beq cr1,.Lunwind_stack_nonvmx_copy @@ -376,26 +376,26 @@ err3; std r0,0(r3) li r11,48 bf cr7*4+3,5f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 addi r4,r4,16 -err3; stvx v1,r0,r3 +err3; stvx v1,0,r3 addi r3,r3,16 5: bf cr7*4+2,6f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 err3; lvx v0,r4,r9 addi r4,r4,32 -err3; stvx v1,r0,r3 +err3; stvx v1,0,r3 err3; stvx v0,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f -err3; lvx v3,r0,r4 +err3; lvx v3,0,r4 err3; lvx v2,r4,r9 err3; lvx v1,r4,r10 err3; lvx v0,r4,r11 addi r4,r4,64 -err3; stvx v3,r0,r3 +err3; stvx v3,0,r3 err3; stvx v2,r3,r9 err3; stvx v1,r3,r10 err3; stvx v0,r3,r11 @@ -421,7 +421,7 @@ err3; stvx v0,r3,r11 */ .align 5 8: -err4; lvx v7,r0,r4 +err4; lvx v7,0,r4 err4; lvx v6,r4,r9 err4; lvx v5,r4,r10 err4; lvx v4,r4,r11 @@ -430,7 +430,7 @@ err4; lvx v2,r4,r14 err4; lvx v1,r4,r15 err4; lvx v0,r4,r16 addi r4,r4,128 -err4; stvx v7,r0,r3 +err4; stvx v7,0,r3 err4; stvx v6,r3,r9 err4; stvx v5,r3,r10 err4; stvx v4,r3,r11 @@ -451,29 +451,29 @@ err4; stvx v0,r3,r16 mtocrf 0x01,r6 bf cr7*4+1,9f -err3; lvx v3,r0,r4 +err3; lvx v3,0,r4 err3; lvx v2,r4,r9 err3; lvx v1,r4,r10 err3; lvx v0,r4,r11 addi r4,r4,64 -err3; stvx v3,r0,r3 +err3; stvx v3,0,r3 err3; stvx v2,r3,r9 err3; stvx v1,r3,r10 err3; stvx v0,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 err3; lvx v0,r4,r9 addi r4,r4,32 -err3; stvx v1,r0,r3 +err3; stvx v1,0,r3 err3; stvx v0,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 addi r4,r4,16 -err3; stvx v1,r0,r3 +err3; stvx v1,0,r3 addi r3,r3,16 /* Up to 15B to go */ @@ -553,25 +553,25 @@ err3; lvx v0,0,r4 addi r4,r4,16 bf cr7*4+3,5f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 VPERM(v8,v0,v1,v16) addi r4,r4,16 -err3; stvx v8,r0,r3 +err3; stvx v8,0,r3 addi r3,r3,16 vor v0,v1,v1 5: bf cr7*4+2,6f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 VPERM(v8,v0,v1,v16) err3; lvx v0,r4,r9 VPERM(v9,v1,v0,v16) addi r4,r4,32 -err3; stvx v8,r0,r3 +err3; stvx v8,0,r3 err3; stvx v9,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f -err3; lvx v3,r0,r4 +err3; lvx v3,0,r4 VPERM(v8,v0,v3,v16) err3; lvx v2,r4,r9 VPERM(v9,v3,v2,v16) @@ -580,7 +580,7 @@ err3; lvx v1,r4,r10 err3; lvx v0,r4,r11 VPERM(v11,v1,v0,v16) addi r4,r4,64 -err3; stvx v8,r0,r3 +err3; stvx v8,0,r3 err3; stvx v9,r3,r9 err3; stvx v10,r3,r10 err3; stvx v11,r3,r11 @@ -606,7 +606,7 @@ err3; stvx v11,r3,r11 */ .align 5 8: -err4; lvx v7,r0,r4 +err4; lvx v7,0,r4 VPERM(v8,v0,v7,v16) err4; lvx v6,r4,r9 VPERM(v9,v7,v6,v16) @@ -623,7 +623,7 @@ err4; lvx v1,r4,r15 err4; lvx v0,r4,r16 VPERM(v15,v1,v0,v16) addi r4,r4,128 -err4; stvx v8,r0,r3 +err4; stvx v8,0,r3 err4; stvx v9,r3,r9 err4; stvx v10,r3,r10 err4; stvx v11,r3,r11 @@ -644,7 +644,7 @@ err4; stvx v15,r3,r16 mtocrf 0x01,r6 bf cr7*4+1,9f -err3; lvx v3,r0,r4 +err3; lvx v3,0,r4 VPERM(v8,v0,v3,v16) err3; lvx v2,r4,r9 VPERM(v9,v3,v2,v16) @@ -653,27 +653,27 @@ err3; lvx v1,r4,r10 err3; lvx v0,r4,r11 VPERM(v11,v1,v0,v16) addi r4,r4,64 -err3; stvx v8,r0,r3 +err3; stvx v8,0,r3 err3; stvx v9,r3,r9 err3; stvx v10,r3,r10 err3; stvx v11,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 VPERM(v8,v0,v1,v16) err3; lvx v0,r4,r9 VPERM(v9,v1,v0,v16) addi r4,r4,32 -err3; stvx v8,r0,r3 +err3; stvx v8,0,r3 err3; stvx v9,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f -err3; lvx v1,r0,r4 +err3; lvx v1,0,r4 VPERM(v8,v0,v1,v16) addi r4,r4,16 -err3; stvx v8,r0,r3 +err3; stvx v8,0,r3 addi r3,r3,16 /* Up to 15B to go */ diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index a58777c1b2cb..ae15eba49c1f 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -21,27 +21,19 @@ #define STKFRM (PPC_MIN_STKFRM + 16) - .macro inst32 op -reg = 0 - .rept 32 -20: \op reg,0,r4 - b 3f - EX_TABLE(20b,99f) -reg = reg + 1 - .endr - .endm - -/* Get the contents of frN into fr0; N is in r3. */ +/* Get the contents of frN into *p; N is in r3 and p is in r4. */ _GLOBAL(get_fpr) mflr r0 + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* fr0 is already in fr0 */ - nop -reg = 1 - .rept 31 - fmr fr0,reg - blr +reg = 0 + .rept 32 + stfd reg, 0(r4) + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -49,18 +41,23 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr +2: MTMSRD(r6) + isync + blr -/* Put the contents of fr0 into frN; N is in r3. */ +/* Put the contents of *p into frN; N is in r3 and p is in r4. */ _GLOBAL(put_fpr) mflr r0 + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* fr0 is already in fr0 */ - nop -reg = 1 - .rept 31 - fmr reg,fr0 - blr +reg = 0 + .rept 32 + lfd reg, 0(r4) + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -68,127 +65,24 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr - -/* Load FP reg N from float at *p. N is in r3, p in r4. */ -_GLOBAL(do_lfs) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 - MTMSRD(r7) - isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) -1: li r9,-EFAULT -2: lfs fr0,0(r4) - li r9,0 -3: bl put_fpr - beq cr7,4f - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -/* Load FP reg N from double at *p. N is in r3, p in r4. */ -_GLOBAL(do_lfd) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 - MTMSRD(r7) - isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) -1: li r9,-EFAULT -2: lfd fr0,0(r4) - li r9,0 -3: beq cr7,4f - bl put_fpr - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) +2: MTMSRD(r6) isync - mr r3,r9 - addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) -/* Store FP reg N to float at *p. N is in r3, p in r4. */ -_GLOBAL(do_stfs) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 - MTMSRD(r7) - isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) - bl get_fpr -1: li r9,-EFAULT -2: stfs fr0,0(r4) - li r9,0 -3: beq cr7,4f - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -/* Store FP reg N to double at *p. N is in r3, p in r4. */ -_GLOBAL(do_stfd) - PPC_STLU r1,-STKFRM(r1) +#ifdef CONFIG_ALTIVEC +/* Get the contents of vrN into *p; N is in r3 and p is in r4. */ +_GLOBAL(get_vr) mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) mfmsr r6 - ori r7,r6,MSR_FP - cmpwi cr7,r3,0 + oris r7, r6, MSR_VEC@h MTMSRD(r7) isync - beq cr7,1f - stfd fr0,STKFRM-16(r1) - bl get_fpr -1: li r9,-EFAULT -2: stfd fr0,0(r4) - li r9,0 -3: beq cr7,4f - lfd fr0,STKFRM-16(r1) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -#ifdef CONFIG_ALTIVEC -/* Get the contents of vrN into v0; N is in r3. */ -_GLOBAL(get_vr) - mflr r0 rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* v0 is already in v0 */ - nop -reg = 1 - .rept 31 - vor v0,reg,reg /* assembler doesn't know vmr? */ - blr +reg = 0 + .rept 32 + stvx reg, 0, r4 + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -196,18 +90,23 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr +2: MTMSRD(r6) + isync + blr -/* Put the contents of v0 into vrN; N is in r3. */ +/* Put the contents of *p into vrN; N is in r3 and p is in r4. */ _GLOBAL(put_vr) mflr r0 + mfmsr r6 + oris r7, r6, MSR_VEC@h + MTMSRD(r7) + isync rlwinm r3,r3,3,0xf8 bcl 20,31,1f - blr /* v0 is already in v0 */ - nop -reg = 1 - .rept 31 - vor reg,v0,v0 - blr +reg = 0 + .rept 32 + lvx reg, 0, r4 + b 2f reg = reg + 1 .endr 1: mflr r5 @@ -215,62 +114,9 @@ reg = reg + 1 mtctr r5 mtlr r0 bctr - -/* Load vector reg N from *p. N is in r3, p in r4. */ -_GLOBAL(do_lvx) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - oris r7,r6,MSR_VEC@h - cmpwi cr7,r3,0 - li r8,STKFRM-16 - MTMSRD(r7) - isync - beq cr7,1f - stvx v0,r1,r8 -1: li r9,-EFAULT -2: lvx v0,0,r4 - li r9,0 -3: beq cr7,4f - bl put_vr - lvx v0,r1,r8 -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) +2: MTMSRD(r6) isync - mr r3,r9 - addi r1,r1,STKFRM - blr - EX_TABLE(2b,3b) - -/* Store vector reg N to *p. N is in r3, p in r4. */ -_GLOBAL(do_stvx) - PPC_STLU r1,-STKFRM(r1) - mflr r0 - PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) - mfmsr r6 - oris r7,r6,MSR_VEC@h - cmpwi cr7,r3,0 - li r8,STKFRM-16 - MTMSRD(r7) - isync - beq cr7,1f - stvx v0,r1,r8 - bl get_vr -1: li r9,-EFAULT -2: stvx v0,0,r4 - li r9,0 -3: beq cr7,4f - lvx v0,r1,r8 -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) - mtlr r0 - MTMSRD(r6) - isync - mr r3,r9 - addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX @@ -313,7 +159,7 @@ reg = reg + 1 bctr /* Load VSX reg N from vector doubleword *p. N is in r3, p in r4. */ -_GLOBAL(do_lxvd2x) +_GLOBAL(load_vsrn) PPC_STLU r1,-STKFRM(r1) mflr r0 PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) @@ -325,49 +171,74 @@ _GLOBAL(do_lxvd2x) isync beq cr7,1f STXVD2X(0,R1,R8) -1: li r9,-EFAULT -2: LXVD2X(0,R0,R4) - li r9,0 -3: beq cr7,4f +1: LXVD2X(0,R0,R4) +#ifdef __LITTLE_ENDIAN__ + XXSWAPD(0,0) +#endif + beq cr7,4f bl put_vsr LXVD2X(0,R1,R8) 4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) isync - mr r3,r9 addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) /* Store VSX reg N to vector doubleword *p. N is in r3, p in r4. */ -_GLOBAL(do_stxvd2x) +_GLOBAL(store_vsrn) PPC_STLU r1,-STKFRM(r1) mflr r0 PPC_STL r0,STKFRM+PPC_LR_STKOFF(r1) mfmsr r6 oris r7,r6,MSR_VSX@h - cmpwi cr7,r3,0 li r8,STKFRM-16 MTMSRD(r7) isync - beq cr7,1f STXVD2X(0,R1,R8) bl get_vsr -1: li r9,-EFAULT -2: STXVD2X(0,R0,R4) - li r9,0 -3: beq cr7,4f +#ifdef __LITTLE_ENDIAN__ + XXSWAPD(0,0) +#endif + STXVD2X(0,R0,R4) LXVD2X(0,R1,R8) -4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) + PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1) mtlr r0 MTMSRD(r6) isync mr r3,r9 addi r1,r1,STKFRM blr - EX_TABLE(2b,3b) - #endif /* CONFIG_VSX */ +/* Convert single-precision to double, without disturbing FPRs. */ +/* conv_sp_to_dp(float *sp, double *dp) */ +_GLOBAL(conv_sp_to_dp) + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync + stfd fr0, -16(r1) + lfs fr0, 0(r3) + stfd fr0, 0(r4) + lfd fr0, -16(r1) + MTMSRD(r6) + isync + blr + +/* Convert single-precision to double, without disturbing FPRs. */ +/* conv_sp_to_dp(double *dp, float *sp) */ +_GLOBAL(conv_dp_to_sp) + mfmsr r6 + ori r7, r6, MSR_FP + MTMSRD(r7) + isync + stfd fr0, -16(r1) + lfd fr0, 0(r3) + stfs fr0, 0(r4) + lfd fr0, -16(r1) + MTMSRD(r6) + isync + blr + #endif /* CONFIG_PPC_FPU */ diff --git a/arch/powerpc/lib/mem_64.S b/arch/powerpc/lib/mem_64.S index 85fa9869aec5..ec531de99996 100644 --- a/arch/powerpc/lib/mem_64.S +++ b/arch/powerpc/lib/mem_64.S @@ -13,6 +13,23 @@ #include <asm/ppc_asm.h> #include <asm/export.h> +_GLOBAL(__memset16) + rlwimi r4,r4,16,0,15 + /* fall through */ + +_GLOBAL(__memset32) + rldimi r4,r4,32,0 + /* fall through */ + +_GLOBAL(__memset64) + neg r0,r3 + andi. r0,r0,7 + cmplw cr1,r5,r0 + b .Lms +EXPORT_SYMBOL(__memset16) +EXPORT_SYMBOL(__memset32) +EXPORT_SYMBOL(__memset64) + _GLOBAL(memset) neg r0,r3 rlwimi r4,r4,8,16,23 @@ -20,7 +37,7 @@ _GLOBAL(memset) rlwimi r4,r4,16,0,15 cmplw cr1,r5,r0 /* do we get that far? */ rldimi r4,r4,32,0 - PPC_MTOCRF(1,r0) +.Lms: PPC_MTOCRF(1,r0) mr r6,r3 blt cr1,8f beq+ 3f /* if already 8-byte aligned */ diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index 786234fd4e91..193909abd18b 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -261,12 +261,12 @@ _GLOBAL(memcpy_power7) .machine push .machine "power4" - dcbt r0,r6,0b01000 - dcbt r0,r7,0b01010 - dcbtst r0,r9,0b01000 - dcbtst r0,r10,0b01010 + dcbt 0,r6,0b01000 + dcbt 0,r7,0b01010 + dcbtst 0,r9,0b01000 + dcbtst 0,r10,0b01010 eieio - dcbt r0,r8,0b01010 /* GO */ + dcbt 0,r8,0b01010 /* GO */ .machine pop beq cr1,.Lunwind_stack_nonvmx_copy @@ -321,26 +321,26 @@ _GLOBAL(memcpy_power7) li r11,48 bf cr7*4+3,5f - lvx v1,r0,r4 + lvx v1,0,r4 addi r4,r4,16 - stvx v1,r0,r3 + stvx v1,0,r3 addi r3,r3,16 5: bf cr7*4+2,6f - lvx v1,r0,r4 + lvx v1,0,r4 lvx v0,r4,r9 addi r4,r4,32 - stvx v1,r0,r3 + stvx v1,0,r3 stvx v0,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f - lvx v3,r0,r4 + lvx v3,0,r4 lvx v2,r4,r9 lvx v1,r4,r10 lvx v0,r4,r11 addi r4,r4,64 - stvx v3,r0,r3 + stvx v3,0,r3 stvx v2,r3,r9 stvx v1,r3,r10 stvx v0,r3,r11 @@ -366,7 +366,7 @@ _GLOBAL(memcpy_power7) */ .align 5 8: - lvx v7,r0,r4 + lvx v7,0,r4 lvx v6,r4,r9 lvx v5,r4,r10 lvx v4,r4,r11 @@ -375,7 +375,7 @@ _GLOBAL(memcpy_power7) lvx v1,r4,r15 lvx v0,r4,r16 addi r4,r4,128 - stvx v7,r0,r3 + stvx v7,0,r3 stvx v6,r3,r9 stvx v5,r3,r10 stvx v4,r3,r11 @@ -396,29 +396,29 @@ _GLOBAL(memcpy_power7) mtocrf 0x01,r6 bf cr7*4+1,9f - lvx v3,r0,r4 + lvx v3,0,r4 lvx v2,r4,r9 lvx v1,r4,r10 lvx v0,r4,r11 addi r4,r4,64 - stvx v3,r0,r3 + stvx v3,0,r3 stvx v2,r3,r9 stvx v1,r3,r10 stvx v0,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f - lvx v1,r0,r4 + lvx v1,0,r4 lvx v0,r4,r9 addi r4,r4,32 - stvx v1,r0,r3 + stvx v1,0,r3 stvx v0,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f - lvx v1,r0,r4 + lvx v1,0,r4 addi r4,r4,16 - stvx v1,r0,r3 + stvx v1,0,r3 addi r3,r3,16 /* Up to 15B to go */ @@ -499,25 +499,25 @@ _GLOBAL(memcpy_power7) addi r4,r4,16 bf cr7*4+3,5f - lvx v1,r0,r4 + lvx v1,0,r4 VPERM(v8,v0,v1,v16) addi r4,r4,16 - stvx v8,r0,r3 + stvx v8,0,r3 addi r3,r3,16 vor v0,v1,v1 5: bf cr7*4+2,6f - lvx v1,r0,r4 + lvx v1,0,r4 VPERM(v8,v0,v1,v16) lvx v0,r4,r9 VPERM(v9,v1,v0,v16) addi r4,r4,32 - stvx v8,r0,r3 + stvx v8,0,r3 stvx v9,r3,r9 addi r3,r3,32 6: bf cr7*4+1,7f - lvx v3,r0,r4 + lvx v3,0,r4 VPERM(v8,v0,v3,v16) lvx v2,r4,r9 VPERM(v9,v3,v2,v16) @@ -526,7 +526,7 @@ _GLOBAL(memcpy_power7) lvx v0,r4,r11 VPERM(v11,v1,v0,v16) addi r4,r4,64 - stvx v8,r0,r3 + stvx v8,0,r3 stvx v9,r3,r9 stvx v10,r3,r10 stvx v11,r3,r11 @@ -552,7 +552,7 @@ _GLOBAL(memcpy_power7) */ .align 5 8: - lvx v7,r0,r4 + lvx v7,0,r4 VPERM(v8,v0,v7,v16) lvx v6,r4,r9 VPERM(v9,v7,v6,v16) @@ -569,7 +569,7 @@ _GLOBAL(memcpy_power7) lvx v0,r4,r16 VPERM(v15,v1,v0,v16) addi r4,r4,128 - stvx v8,r0,r3 + stvx v8,0,r3 stvx v9,r3,r9 stvx v10,r3,r10 stvx v11,r3,r11 @@ -590,7 +590,7 @@ _GLOBAL(memcpy_power7) mtocrf 0x01,r6 bf cr7*4+1,9f - lvx v3,r0,r4 + lvx v3,0,r4 VPERM(v8,v0,v3,v16) lvx v2,r4,r9 VPERM(v9,v3,v2,v16) @@ -599,27 +599,27 @@ _GLOBAL(memcpy_power7) lvx v0,r4,r11 VPERM(v11,v1,v0,v16) addi r4,r4,64 - stvx v8,r0,r3 + stvx v8,0,r3 stvx v9,r3,r9 stvx v10,r3,r10 stvx v11,r3,r11 addi r3,r3,64 9: bf cr7*4+2,10f - lvx v1,r0,r4 + lvx v1,0,r4 VPERM(v8,v0,v1,v16) lvx v0,r4,r9 VPERM(v9,v1,v0,v16) addi r4,r4,32 - stvx v8,r0,r3 + stvx v8,0,r3 stvx v9,r3,r9 addi r3,r3,32 10: bf cr7*4+3,11f - lvx v1,r0,r4 + lvx v1,0,r4 VPERM(v8,v0,v1,v16) addi r4,r4,16 - stvx v8,r0,r3 + stvx v8,0,r3 addi r3,r3,16 /* Up to 15B to go */ diff --git a/arch/powerpc/lib/quad.S b/arch/powerpc/lib/quad.S new file mode 100644 index 000000000000..c4d12fae8724 --- /dev/null +++ b/arch/powerpc/lib/quad.S @@ -0,0 +1,62 @@ +/* + * Quadword loads and stores + * for use in instruction emulation. + * + * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.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 <asm/processor.h> +#include <asm/ppc_asm.h> +#include <asm/ppc-opcode.h> +#include <asm/reg.h> +#include <asm/asm-offsets.h> +#include <linux/errno.h> + +/* do_lq(unsigned long ea, unsigned long *regs) */ +_GLOBAL(do_lq) +1: lq r6, 0(r3) + std r6, 0(r4) + std r7, 8(r4) + li r3, 0 + blr +2: li r3, -EFAULT + blr + EX_TABLE(1b, 2b) + +/* do_stq(unsigned long ea, unsigned long val0, unsigned long val1) */ +_GLOBAL(do_stq) +1: stq r4, 0(r3) + li r3, 0 + blr +2: li r3, -EFAULT + blr + EX_TABLE(1b, 2b) + +/* do_lqarx(unsigned long ea, unsigned long *regs) */ +_GLOBAL(do_lqarx) +1: PPC_LQARX(6, 0, 3, 0) + std r6, 0(r4) + std r7, 8(r4) + li r3, 0 + blr +2: li r3, -EFAULT + blr + EX_TABLE(1b, 2b) + +/* do_stqcx(unsigned long ea, unsigned long val0, unsigned long val1, + unsigned int *crp) */ + +_GLOBAL(do_stqcx) +1: PPC_STQCX(4, 0, 3) + mfcr r5 + stw r5, 0(r6) + li r3, 0 + blr +2: li r3, -EFAULT + blr + EX_TABLE(1b, 2b) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index ee33327686ae..fb9f58b868e7 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -36,14 +36,33 @@ extern char system_call_common[]; /* * Functions in ldstfp.S */ -extern int do_lfs(int rn, unsigned long ea); -extern int do_lfd(int rn, unsigned long ea); -extern int do_stfs(int rn, unsigned long ea); -extern int do_stfd(int rn, unsigned long ea); -extern int do_lvx(int rn, unsigned long ea); -extern int do_stvx(int rn, unsigned long ea); -extern int do_lxvd2x(int rn, unsigned long ea); -extern int do_stxvd2x(int rn, unsigned long ea); +extern void get_fpr(int rn, double *p); +extern void put_fpr(int rn, const double *p); +extern void get_vr(int rn, __vector128 *p); +extern void put_vr(int rn, __vector128 *p); +extern void load_vsrn(int vsr, const void *p); +extern void store_vsrn(int vsr, void *p); +extern void conv_sp_to_dp(const float *sp, double *dp); +extern void conv_dp_to_sp(const double *dp, float *sp); +#endif + +#ifdef __powerpc64__ +/* + * Functions in quad.S + */ +extern int do_lq(unsigned long ea, unsigned long *regs); +extern int do_stq(unsigned long ea, unsigned long val0, unsigned long val1); +extern int do_lqarx(unsigned long ea, unsigned long *regs); +extern int do_stqcx(unsigned long ea, unsigned long val0, unsigned long val1, + unsigned int *crp); +#endif + +#ifdef __LITTLE_ENDIAN__ +#define IS_LE 1 +#define IS_BE 0 +#else +#define IS_LE 0 +#define IS_BE 1 #endif /* @@ -62,15 +81,17 @@ static nokprobe_inline unsigned long truncate_if_32bit(unsigned long msr, /* * Determine whether a conditional branch instruction would branch. */ -static nokprobe_inline int branch_taken(unsigned int instr, struct pt_regs *regs) +static nokprobe_inline int branch_taken(unsigned int instr, + const struct pt_regs *regs, + struct instruction_op *op) { unsigned int bo = (instr >> 21) & 0x1f; unsigned int bi; if ((bo & 4) == 0) { /* decrement counter */ - --regs->ctr; - if (((bo >> 1) & 1) ^ (regs->ctr == 0)) + op->type |= DECCTR; + if (((bo >> 1) & 1) ^ (regs->ctr == 1)) return 0; } if ((bo & 0x10) == 0) { @@ -82,17 +103,26 @@ static nokprobe_inline int branch_taken(unsigned int instr, struct pt_regs *regs return 1; } -static nokprobe_inline long address_ok(struct pt_regs *regs, unsigned long ea, int nb) +static nokprobe_inline long address_ok(struct pt_regs *regs, + unsigned long ea, int nb) { if (!user_mode(regs)) return 1; - return __access_ok(ea, nb, USER_DS); + if (__access_ok(ea, nb, USER_DS)) + return 1; + if (__access_ok(ea, 1, USER_DS)) + /* Access overlaps the end of the user region */ + regs->dar = USER_DS.seg; + else + regs->dar = ea; + return 0; } /* * Calculate effective address for a D-form instruction */ -static nokprobe_inline unsigned long dform_ea(unsigned int instr, struct pt_regs *regs) +static nokprobe_inline unsigned long dform_ea(unsigned int instr, + const struct pt_regs *regs) { int ra; unsigned long ea; @@ -102,14 +132,15 @@ static nokprobe_inline unsigned long dform_ea(unsigned int instr, struct pt_regs if (ra) ea += regs->gpr[ra]; - return truncate_if_32bit(regs->msr, ea); + return ea; } #ifdef __powerpc64__ /* * Calculate effective address for a DS-form instruction */ -static nokprobe_inline unsigned long dsform_ea(unsigned int instr, struct pt_regs *regs) +static nokprobe_inline unsigned long dsform_ea(unsigned int instr, + const struct pt_regs *regs) { int ra; unsigned long ea; @@ -119,7 +150,24 @@ static nokprobe_inline unsigned long dsform_ea(unsigned int instr, struct pt_reg if (ra) ea += regs->gpr[ra]; - return truncate_if_32bit(regs->msr, ea); + return ea; +} + +/* + * Calculate effective address for a DQ-form instruction + */ +static nokprobe_inline unsigned long dqform_ea(unsigned int instr, + const struct pt_regs *regs) +{ + int ra; + unsigned long ea; + + ra = (instr >> 16) & 0x1f; + ea = (signed short) (instr & ~0xf); /* sign-extend */ + if (ra) + ea += regs->gpr[ra]; + + return ea; } #endif /* __powerpc64 */ @@ -127,7 +175,7 @@ static nokprobe_inline unsigned long dsform_ea(unsigned int instr, struct pt_reg * Calculate effective address for an X-form instruction */ static nokprobe_inline unsigned long xform_ea(unsigned int instr, - struct pt_regs *regs) + const struct pt_regs *regs) { int ra, rb; unsigned long ea; @@ -138,7 +186,7 @@ static nokprobe_inline unsigned long xform_ea(unsigned int instr, if (ra) ea += regs->gpr[ra]; - return truncate_if_32bit(regs->msr, ea); + return ea; } /* @@ -151,7 +199,6 @@ static nokprobe_inline unsigned long max_align(unsigned long x) return x & -x; /* isolates rightmost bit */ } - static nokprobe_inline unsigned long byterev_2(unsigned long x) { return ((x >> 8) & 0xff) | ((x & 0xff) << 8); @@ -170,8 +217,36 @@ static nokprobe_inline unsigned long byterev_8(unsigned long x) } #endif +static nokprobe_inline void do_byte_reverse(void *ptr, int nb) +{ + switch (nb) { + case 2: + *(u16 *)ptr = byterev_2(*(u16 *)ptr); + break; + case 4: + *(u32 *)ptr = byterev_4(*(u32 *)ptr); + break; +#ifdef __powerpc64__ + case 8: + *(unsigned long *)ptr = byterev_8(*(unsigned long *)ptr); + break; + case 16: { + unsigned long *up = (unsigned long *)ptr; + unsigned long tmp; + tmp = byterev_8(up[0]); + up[0] = byterev_8(up[1]); + up[1] = tmp; + break; + } +#endif + default: + WARN_ON_ONCE(1); + } +} + static nokprobe_inline int read_mem_aligned(unsigned long *dest, - unsigned long ea, int nb) + unsigned long ea, int nb, + struct pt_regs *regs) { int err = 0; unsigned long x = 0; @@ -194,59 +269,77 @@ static nokprobe_inline int read_mem_aligned(unsigned long *dest, } if (!err) *dest = x; + else + regs->dar = ea; return err; } -static nokprobe_inline int read_mem_unaligned(unsigned long *dest, - unsigned long ea, int nb, struct pt_regs *regs) +/* + * Copy from userspace to a buffer, using the largest possible + * aligned accesses, up to sizeof(long). + */ +static int nokprobe_inline copy_mem_in(u8 *dest, unsigned long ea, int nb, + struct pt_regs *regs) { - int err; - unsigned long x, b, c; -#ifdef __LITTLE_ENDIAN__ - int len = nb; /* save a copy of the length for byte reversal */ -#endif + int err = 0; + int c; - /* unaligned, do this in pieces */ - x = 0; for (; nb > 0; nb -= c) { -#ifdef __LITTLE_ENDIAN__ - c = 1; -#endif -#ifdef __BIG_ENDIAN__ c = max_align(ea); -#endif if (c > nb) c = max_align(nb); - err = read_mem_aligned(&b, ea, c); - if (err) - return err; - x = (x << (8 * c)) + b; - ea += c; - } -#ifdef __LITTLE_ENDIAN__ - switch (len) { - case 2: - *dest = byterev_2(x); - break; - case 4: - *dest = byterev_4(x); - break; + switch (c) { + case 1: + err = __get_user(*dest, (unsigned char __user *) ea); + break; + case 2: + err = __get_user(*(u16 *)dest, + (unsigned short __user *) ea); + break; + case 4: + err = __get_user(*(u32 *)dest, + (unsigned int __user *) ea); + break; #ifdef __powerpc64__ - case 8: - *dest = byterev_8(x); - break; + case 8: + err = __get_user(*(unsigned long *)dest, + (unsigned long __user *) ea); + break; #endif + } + if (err) { + regs->dar = ea; + return err; + } + dest += c; + ea += c; } -#endif -#ifdef __BIG_ENDIAN__ - *dest = x; -#endif return 0; } +static nokprobe_inline int read_mem_unaligned(unsigned long *dest, + unsigned long ea, int nb, + struct pt_regs *regs) +{ + union { + unsigned long ul; + u8 b[sizeof(unsigned long)]; + } u; + int i; + int err; + + u.ul = 0; + i = IS_BE ? sizeof(unsigned long) - nb : 0; + err = copy_mem_in(&u.b[i], ea, nb, regs); + if (!err) + *dest = u.ul; + return err; +} + /* * Read memory at address ea for nb bytes, return 0 for success - * or -EFAULT if an error occurred. + * or -EFAULT if an error occurred. N.B. nb must be 1, 2, 4 or 8. + * If nb < sizeof(long), the result is right-justified on BE systems. */ static int read_mem(unsigned long *dest, unsigned long ea, int nb, struct pt_regs *regs) @@ -254,13 +347,14 @@ static int read_mem(unsigned long *dest, unsigned long ea, int nb, if (!address_ok(regs, ea, nb)) return -EFAULT; if ((ea & (nb - 1)) == 0) - return read_mem_aligned(dest, ea, nb); + return read_mem_aligned(dest, ea, nb, regs); return read_mem_unaligned(dest, ea, nb, regs); } NOKPROBE_SYMBOL(read_mem); static nokprobe_inline int write_mem_aligned(unsigned long val, - unsigned long ea, int nb) + unsigned long ea, int nb, + struct pt_regs *regs) { int err = 0; @@ -280,51 +374,72 @@ static nokprobe_inline int write_mem_aligned(unsigned long val, break; #endif } + if (err) + regs->dar = ea; return err; } -static nokprobe_inline int write_mem_unaligned(unsigned long val, - unsigned long ea, int nb, struct pt_regs *regs) +/* + * Copy from a buffer to userspace, using the largest possible + * aligned accesses, up to sizeof(long). + */ +static int nokprobe_inline copy_mem_out(u8 *dest, unsigned long ea, int nb, + struct pt_regs *regs) { - int err; - unsigned long c; + int err = 0; + int c; -#ifdef __LITTLE_ENDIAN__ - switch (nb) { - case 2: - val = byterev_2(val); - break; - case 4: - val = byterev_4(val); - break; -#ifdef __powerpc64__ - case 8: - val = byterev_8(val); - break; -#endif - } -#endif - /* unaligned or little-endian, do this in pieces */ for (; nb > 0; nb -= c) { -#ifdef __LITTLE_ENDIAN__ - c = 1; -#endif -#ifdef __BIG_ENDIAN__ c = max_align(ea); -#endif if (c > nb) c = max_align(nb); - err = write_mem_aligned(val >> (nb - c) * 8, ea, c); - if (err) + switch (c) { + case 1: + err = __put_user(*dest, (unsigned char __user *) ea); + break; + case 2: + err = __put_user(*(u16 *)dest, + (unsigned short __user *) ea); + break; + case 4: + err = __put_user(*(u32 *)dest, + (unsigned int __user *) ea); + break; +#ifdef __powerpc64__ + case 8: + err = __put_user(*(unsigned long *)dest, + (unsigned long __user *) ea); + break; +#endif + } + if (err) { + regs->dar = ea; return err; + } + dest += c; ea += c; } return 0; } +static nokprobe_inline int write_mem_unaligned(unsigned long val, + unsigned long ea, int nb, + struct pt_regs *regs) +{ + union { + unsigned long ul; + u8 b[sizeof(unsigned long)]; + } u; + int i; + + u.ul = val; + i = IS_BE ? sizeof(unsigned long) - nb : 0; + return copy_mem_out(&u.b[i], ea, nb, regs); +} + /* * Write memory at address ea for nb bytes, return 0 for success - * or -EFAULT if an error occurred. + * or -EFAULT if an error occurred. N.B. nb must be 1, 2, 4 or 8. */ static int write_mem(unsigned long val, unsigned long ea, int nb, struct pt_regs *regs) @@ -332,163 +447,465 @@ static int write_mem(unsigned long val, unsigned long ea, int nb, if (!address_ok(regs, ea, nb)) return -EFAULT; if ((ea & (nb - 1)) == 0) - return write_mem_aligned(val, ea, nb); + return write_mem_aligned(val, ea, nb, regs); return write_mem_unaligned(val, ea, nb, regs); } NOKPROBE_SYMBOL(write_mem); #ifdef CONFIG_PPC_FPU /* - * Check the address and alignment, and call func to do the actual - * load or store. + * These access either the real FP register or the image in the + * thread_struct, depending on regs->msr & MSR_FP. */ -static int do_fp_load(int rn, int (*func)(int, unsigned long), - unsigned long ea, int nb, - struct pt_regs *regs) +static int do_fp_load(struct instruction_op *op, unsigned long ea, + struct pt_regs *regs, bool cross_endian) { - int err; + int err, rn, nb; union { - double dbl; - unsigned long ul[2]; - struct { -#ifdef __BIG_ENDIAN__ - unsigned _pad_; - unsigned word; -#endif -#ifdef __LITTLE_ENDIAN__ - unsigned word; - unsigned _pad_; -#endif - } single; - } data; - unsigned long ptr; - + int i; + unsigned int u; + float f; + double d[2]; + unsigned long l[2]; + u8 b[2 * sizeof(double)]; + } u; + + nb = GETSIZE(op->type); if (!address_ok(regs, ea, nb)) return -EFAULT; - if ((ea & 3) == 0) - return (*func)(rn, ea); - ptr = (unsigned long) &data.ul; - if (sizeof(unsigned long) == 8 || nb == 4) { - err = read_mem_unaligned(&data.ul[0], ea, nb, regs); - if (nb == 4) - ptr = (unsigned long)&(data.single.word); - } else { - /* reading a double on 32-bit */ - err = read_mem_unaligned(&data.ul[0], ea, 4, regs); - if (!err) - err = read_mem_unaligned(&data.ul[1], ea + 4, 4, regs); - } + rn = op->reg; + err = copy_mem_in(u.b, ea, nb, regs); if (err) return err; - return (*func)(rn, ptr); + if (unlikely(cross_endian)) { + do_byte_reverse(u.b, min(nb, 8)); + if (nb == 16) + do_byte_reverse(&u.b[8], 8); + } + preempt_disable(); + if (nb == 4) { + if (op->type & FPCONV) + conv_sp_to_dp(&u.f, &u.d[0]); + else if (op->type & SIGNEXT) + u.l[0] = u.i; + else + u.l[0] = u.u; + } + if (regs->msr & MSR_FP) + put_fpr(rn, &u.d[0]); + else + current->thread.TS_FPR(rn) = u.l[0]; + if (nb == 16) { + /* lfdp */ + rn |= 1; + if (regs->msr & MSR_FP) + put_fpr(rn, &u.d[1]); + else + current->thread.TS_FPR(rn) = u.l[1]; + } + preempt_enable(); + return 0; } NOKPROBE_SYMBOL(do_fp_load); -static int do_fp_store(int rn, int (*func)(int, unsigned long), - unsigned long ea, int nb, - struct pt_regs *regs) +static int do_fp_store(struct instruction_op *op, unsigned long ea, + struct pt_regs *regs, bool cross_endian) { - int err; + int rn, nb; union { - double dbl; - unsigned long ul[2]; - struct { -#ifdef __BIG_ENDIAN__ - unsigned _pad_; - unsigned word; -#endif -#ifdef __LITTLE_ENDIAN__ - unsigned word; - unsigned _pad_; -#endif - } single; - } data; - unsigned long ptr; - + unsigned int u; + float f; + double d[2]; + unsigned long l[2]; + u8 b[2 * sizeof(double)]; + } u; + + nb = GETSIZE(op->type); if (!address_ok(regs, ea, nb)) return -EFAULT; - if ((ea & 3) == 0) - return (*func)(rn, ea); - ptr = (unsigned long) &data.ul[0]; - if (sizeof(unsigned long) == 8 || nb == 4) { - if (nb == 4) - ptr = (unsigned long)&(data.single.word); - err = (*func)(rn, ptr); - if (err) - return err; - err = write_mem_unaligned(data.ul[0], ea, nb, regs); - } else { - /* writing a double on 32-bit */ - err = (*func)(rn, ptr); - if (err) - return err; - err = write_mem_unaligned(data.ul[0], ea, 4, regs); - if (!err) - err = write_mem_unaligned(data.ul[1], ea + 4, 4, regs); + rn = op->reg; + preempt_disable(); + if (regs->msr & MSR_FP) + get_fpr(rn, &u.d[0]); + else + u.l[0] = current->thread.TS_FPR(rn); + if (nb == 4) { + if (op->type & FPCONV) + conv_dp_to_sp(&u.d[0], &u.f); + else + u.u = u.l[0]; } - return err; + if (nb == 16) { + rn |= 1; + if (regs->msr & MSR_FP) + get_fpr(rn, &u.d[1]); + else + u.l[1] = current->thread.TS_FPR(rn); + } + preempt_enable(); + if (unlikely(cross_endian)) { + do_byte_reverse(u.b, min(nb, 8)); + if (nb == 16) + do_byte_reverse(&u.b[8], 8); + } + return copy_mem_out(u.b, ea, nb, regs); } NOKPROBE_SYMBOL(do_fp_store); #endif #ifdef CONFIG_ALTIVEC /* For Altivec/VMX, no need to worry about alignment */ -static nokprobe_inline int do_vec_load(int rn, int (*func)(int, unsigned long), - unsigned long ea, struct pt_regs *regs) +static nokprobe_inline int do_vec_load(int rn, unsigned long ea, + int size, struct pt_regs *regs, + bool cross_endian) { + int err; + union { + __vector128 v; + u8 b[sizeof(__vector128)]; + } u = {}; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; - return (*func)(rn, ea); + /* align to multiple of size */ + ea &= ~(size - 1); + err = copy_mem_in(&u.b[ea & 0xf], ea, size, regs); + if (err) + return err; + if (unlikely(cross_endian)) + do_byte_reverse(&u.b[ea & 0xf], size); + preempt_disable(); + if (regs->msr & MSR_VEC) + put_vr(rn, &u.v); + else + current->thread.vr_state.vr[rn] = u.v; + preempt_enable(); + return 0; } -static nokprobe_inline int do_vec_store(int rn, int (*func)(int, unsigned long), - unsigned long ea, struct pt_regs *regs) +static nokprobe_inline int do_vec_store(int rn, unsigned long ea, + int size, struct pt_regs *regs, + bool cross_endian) { + union { + __vector128 v; + u8 b[sizeof(__vector128)]; + } u; + if (!address_ok(regs, ea & ~0xfUL, 16)) return -EFAULT; - return (*func)(rn, ea); + /* align to multiple of size */ + ea &= ~(size - 1); + + preempt_disable(); + if (regs->msr & MSR_VEC) + get_vr(rn, &u.v); + else + u.v = current->thread.vr_state.vr[rn]; + preempt_enable(); + if (unlikely(cross_endian)) + do_byte_reverse(&u.b[ea & 0xf], size); + return copy_mem_out(&u.b[ea & 0xf], ea, size, regs); } #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_VSX -static nokprobe_inline int do_vsx_load(int rn, int (*func)(int, unsigned long), - unsigned long ea, struct pt_regs *regs) +#ifdef __powerpc64__ +static nokprobe_inline int emulate_lq(struct pt_regs *regs, unsigned long ea, + int reg, bool cross_endian) { int err; - unsigned long val[2]; if (!address_ok(regs, ea, 16)) return -EFAULT; - if ((ea & 3) == 0) - return (*func)(rn, ea); - err = read_mem_unaligned(&val[0], ea, 8, regs); - if (!err) - err = read_mem_unaligned(&val[1], ea + 8, 8, regs); - if (!err) - err = (*func)(rn, (unsigned long) &val[0]); + /* if aligned, should be atomic */ + if ((ea & 0xf) == 0) { + err = do_lq(ea, ®s->gpr[reg]); + } else { + err = read_mem(®s->gpr[reg + IS_LE], ea, 8, regs); + if (!err) + err = read_mem(®s->gpr[reg + IS_BE], ea + 8, 8, regs); + } + if (!err && unlikely(cross_endian)) + do_byte_reverse(®s->gpr[reg], 16); return err; } -static nokprobe_inline int do_vsx_store(int rn, int (*func)(int, unsigned long), - unsigned long ea, struct pt_regs *regs) +static nokprobe_inline int emulate_stq(struct pt_regs *regs, unsigned long ea, + int reg, bool cross_endian) { int err; - unsigned long val[2]; + unsigned long vals[2]; if (!address_ok(regs, ea, 16)) return -EFAULT; - if ((ea & 3) == 0) - return (*func)(rn, ea); - err = (*func)(rn, (unsigned long) &val[0]); - if (err) - return err; - err = write_mem_unaligned(val[0], ea, 8, regs); + vals[0] = regs->gpr[reg]; + vals[1] = regs->gpr[reg + 1]; + if (unlikely(cross_endian)) + do_byte_reverse(vals, 16); + + /* if aligned, should be atomic */ + if ((ea & 0xf) == 0) + return do_stq(ea, vals[0], vals[1]); + + err = write_mem(vals[IS_LE], ea, 8, regs); if (!err) - err = write_mem_unaligned(val[1], ea + 8, 8, regs); + err = write_mem(vals[IS_BE], ea + 8, 8, regs); return err; } +#endif /* __powerpc64 */ + +#ifdef CONFIG_VSX +void emulate_vsx_load(struct instruction_op *op, union vsx_reg *reg, + const void *mem, bool rev) +{ + int size, read_size; + int i, j; + const unsigned int *wp; + const unsigned short *hp; + const unsigned char *bp; + + size = GETSIZE(op->type); + reg->d[0] = reg->d[1] = 0; + + switch (op->element_size) { + case 16: + /* whole vector; lxv[x] or lxvl[l] */ + if (size == 0) + break; + memcpy(reg, mem, size); + if (IS_LE && (op->vsx_flags & VSX_LDLEFT)) + rev = !rev; + if (rev) + do_byte_reverse(reg, 16); + break; + case 8: + /* scalar loads, lxvd2x, lxvdsx */ + read_size = (size >= 8) ? 8 : size; + i = IS_LE ? 8 : 8 - read_size; + memcpy(®->b[i], mem, read_size); + if (rev) + do_byte_reverse(®->b[i], 8); + if (size < 8) { + if (op->type & SIGNEXT) { + /* size == 4 is the only case here */ + reg->d[IS_LE] = (signed int) reg->d[IS_LE]; + } else if (op->vsx_flags & VSX_FPCONV) { + preempt_disable(); + conv_sp_to_dp(®->fp[1 + IS_LE], + ®->dp[IS_LE]); + preempt_enable(); + } + } else { + if (size == 16) { + unsigned long v = *(unsigned long *)(mem + 8); + reg->d[IS_BE] = !rev ? v : byterev_8(v); + } else if (op->vsx_flags & VSX_SPLAT) + reg->d[IS_BE] = reg->d[IS_LE]; + } + break; + case 4: + /* lxvw4x, lxvwsx */ + wp = mem; + for (j = 0; j < size / 4; ++j) { + i = IS_LE ? 3 - j : j; + reg->w[i] = !rev ? *wp++ : byterev_4(*wp++); + } + if (op->vsx_flags & VSX_SPLAT) { + u32 val = reg->w[IS_LE ? 3 : 0]; + for (; j < 4; ++j) { + i = IS_LE ? 3 - j : j; + reg->w[i] = val; + } + } + break; + case 2: + /* lxvh8x */ + hp = mem; + for (j = 0; j < size / 2; ++j) { + i = IS_LE ? 7 - j : j; + reg->h[i] = !rev ? *hp++ : byterev_2(*hp++); + } + break; + case 1: + /* lxvb16x */ + bp = mem; + for (j = 0; j < size; ++j) { + i = IS_LE ? 15 - j : j; + reg->b[i] = *bp++; + } + break; + } +} +EXPORT_SYMBOL_GPL(emulate_vsx_load); +NOKPROBE_SYMBOL(emulate_vsx_load); + +void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg, + void *mem, bool rev) +{ + int size, write_size; + int i, j; + union vsx_reg buf; + unsigned int *wp; + unsigned short *hp; + unsigned char *bp; + + size = GETSIZE(op->type); + + switch (op->element_size) { + case 16: + /* stxv, stxvx, stxvl, stxvll */ + if (size == 0) + break; + if (IS_LE && (op->vsx_flags & VSX_LDLEFT)) + rev = !rev; + if (rev) { + /* reverse 16 bytes */ + buf.d[0] = byterev_8(reg->d[1]); + buf.d[1] = byterev_8(reg->d[0]); + reg = &buf; + } + memcpy(mem, reg, size); + break; + case 8: + /* scalar stores, stxvd2x */ + write_size = (size >= 8) ? 8 : size; + i = IS_LE ? 8 : 8 - write_size; + if (size < 8 && op->vsx_flags & VSX_FPCONV) { + buf.d[0] = buf.d[1] = 0; + preempt_disable(); + conv_dp_to_sp(®->dp[IS_LE], &buf.fp[1 + IS_LE]); + preempt_enable(); + reg = &buf; + } + memcpy(mem, ®->b[i], write_size); + if (size == 16) + memcpy(mem + 8, ®->d[IS_BE], 8); + if (unlikely(rev)) { + do_byte_reverse(mem, write_size); + if (size == 16) + do_byte_reverse(mem + 8, 8); + } + break; + case 4: + /* stxvw4x */ + wp = mem; + for (j = 0; j < size / 4; ++j) { + i = IS_LE ? 3 - j : j; + *wp++ = !rev ? reg->w[i] : byterev_4(reg->w[i]); + } + break; + case 2: + /* stxvh8x */ + hp = mem; + for (j = 0; j < size / 2; ++j) { + i = IS_LE ? 7 - j : j; + *hp++ = !rev ? reg->h[i] : byterev_2(reg->h[i]); + } + break; + case 1: + /* stvxb16x */ + bp = mem; + for (j = 0; j < size; ++j) { + i = IS_LE ? 15 - j : j; + *bp++ = reg->b[i]; + } + break; + } +} +EXPORT_SYMBOL_GPL(emulate_vsx_store); +NOKPROBE_SYMBOL(emulate_vsx_store); + +static nokprobe_inline int do_vsx_load(struct instruction_op *op, + unsigned long ea, struct pt_regs *regs, + bool cross_endian) +{ + int reg = op->reg; + u8 mem[16]; + union vsx_reg buf; + int size = GETSIZE(op->type); + + if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs)) + return -EFAULT; + + emulate_vsx_load(op, &buf, mem, cross_endian); + preempt_disable(); + if (reg < 32) { + /* FP regs + extensions */ + if (regs->msr & MSR_FP) { + load_vsrn(reg, &buf); + } else { + current->thread.fp_state.fpr[reg][0] = buf.d[0]; + current->thread.fp_state.fpr[reg][1] = buf.d[1]; + } + } else { + if (regs->msr & MSR_VEC) + load_vsrn(reg, &buf); + else + current->thread.vr_state.vr[reg - 32] = buf.v; + } + preempt_enable(); + return 0; +} + +static nokprobe_inline int do_vsx_store(struct instruction_op *op, + unsigned long ea, struct pt_regs *regs, + bool cross_endian) +{ + int reg = op->reg; + u8 mem[16]; + union vsx_reg buf; + int size = GETSIZE(op->type); + + if (!address_ok(regs, ea, size)) + return -EFAULT; + + preempt_disable(); + if (reg < 32) { + /* FP regs + extensions */ + if (regs->msr & MSR_FP) { + store_vsrn(reg, &buf); + } else { + buf.d[0] = current->thread.fp_state.fpr[reg][0]; + buf.d[1] = current->thread.fp_state.fpr[reg][1]; + } + } else { + if (regs->msr & MSR_VEC) + store_vsrn(reg, &buf); + else + buf.v = current->thread.vr_state.vr[reg - 32]; + } + preempt_enable(); + emulate_vsx_store(op, &buf, mem, cross_endian); + return copy_mem_out(mem, ea, size, regs); +} #endif /* CONFIG_VSX */ +int emulate_dcbz(unsigned long ea, struct pt_regs *regs) +{ + int err; + unsigned long i, size; + +#ifdef __powerpc64__ + size = ppc64_caches.l1d.block_size; + if (!(regs->msr & MSR_64BIT)) + ea &= 0xffffffffUL; +#else + size = L1_CACHE_BYTES; +#endif + ea &= ~(size - 1); + if (!address_ok(regs, ea, size)) + return -EFAULT; + for (i = 0; i < size; i += sizeof(long)) { + err = __put_user(0, (unsigned long __user *) (ea + i)); + if (err) { + regs->dar = ea; + return err; + } + } + return 0; +} +NOKPROBE_SYMBOL(emulate_dcbz); + #define __put_user_asmx(x, addr, err, op, cr) \ __asm__ __volatile__( \ "1: " op " %2,0,%3\n" \ @@ -526,24 +943,27 @@ static nokprobe_inline int do_vsx_store(int rn, int (*func)(int, unsigned long), : "=r" (err) \ : "r" (addr), "i" (-EFAULT), "0" (err)) -static nokprobe_inline void set_cr0(struct pt_regs *regs, int rd) +static nokprobe_inline void set_cr0(const struct pt_regs *regs, + struct instruction_op *op, int rd) { long val = regs->gpr[rd]; - regs->ccr = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000); + op->type |= SETCC; + op->ccval = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000); #ifdef __powerpc64__ if (!(regs->msr & MSR_64BIT)) val = (int) val; #endif if (val < 0) - regs->ccr |= 0x80000000; + op->ccval |= 0x80000000; else if (val > 0) - regs->ccr |= 0x40000000; + op->ccval |= 0x40000000; else - regs->ccr |= 0x20000000; + op->ccval |= 0x20000000; } -static nokprobe_inline void add_with_carry(struct pt_regs *regs, int rd, +static nokprobe_inline void add_with_carry(const struct pt_regs *regs, + struct instruction_op *op, int rd, unsigned long val1, unsigned long val2, unsigned long carry_in) { @@ -551,24 +971,29 @@ static nokprobe_inline void add_with_carry(struct pt_regs *regs, int rd, if (carry_in) ++val; - regs->gpr[rd] = val; + op->type = COMPUTE + SETREG + SETXER; + op->reg = rd; + op->val = val; #ifdef __powerpc64__ if (!(regs->msr & MSR_64BIT)) { val = (unsigned int) val; val1 = (unsigned int) val1; } #endif + op->xerval = regs->xer; if (val < val1 || (carry_in && val == val1)) - regs->xer |= XER_CA; + op->xerval |= XER_CA; else - regs->xer &= ~XER_CA; + op->xerval &= ~XER_CA; } -static nokprobe_inline void do_cmp_signed(struct pt_regs *regs, long v1, long v2, - int crfld) +static nokprobe_inline void do_cmp_signed(const struct pt_regs *regs, + struct instruction_op *op, + long v1, long v2, int crfld) { unsigned int crval, shift; + op->type = COMPUTE + SETCC; crval = (regs->xer >> 31) & 1; /* get SO bit */ if (v1 < v2) crval |= 8; @@ -577,14 +1002,17 @@ static nokprobe_inline void do_cmp_signed(struct pt_regs *regs, long v1, long v2 else crval |= 2; shift = (7 - crfld) * 4; - regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift); + op->ccval = (regs->ccr & ~(0xf << shift)) | (crval << shift); } -static nokprobe_inline void do_cmp_unsigned(struct pt_regs *regs, unsigned long v1, - unsigned long v2, int crfld) +static nokprobe_inline void do_cmp_unsigned(const struct pt_regs *regs, + struct instruction_op *op, + unsigned long v1, + unsigned long v2, int crfld) { unsigned int crval, shift; + op->type = COMPUTE + SETCC; crval = (regs->xer >> 31) & 1; /* get SO bit */ if (v1 < v2) crval |= 8; @@ -593,7 +1021,90 @@ static nokprobe_inline void do_cmp_unsigned(struct pt_regs *regs, unsigned long else crval |= 2; shift = (7 - crfld) * 4; - regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift); + op->ccval = (regs->ccr & ~(0xf << shift)) | (crval << shift); +} + +static nokprobe_inline void do_cmpb(const struct pt_regs *regs, + struct instruction_op *op, + unsigned long v1, unsigned long v2) +{ + unsigned long long out_val, mask; + int i; + + out_val = 0; + for (i = 0; i < 8; i++) { + mask = 0xffUL << (i * 8); + if ((v1 & mask) == (v2 & mask)) + out_val |= mask; + } + op->val = out_val; +} + +/* + * The size parameter is used to adjust the equivalent popcnt instruction. + * popcntb = 8, popcntw = 32, popcntd = 64 + */ +static nokprobe_inline void do_popcnt(const struct pt_regs *regs, + struct instruction_op *op, + unsigned long v1, int size) +{ + unsigned long long out = v1; + + out -= (out >> 1) & 0x5555555555555555; + out = (0x3333333333333333 & out) + (0x3333333333333333 & (out >> 2)); + out = (out + (out >> 4)) & 0x0f0f0f0f0f0f0f0f; + + if (size == 8) { /* popcntb */ + op->val = out; + return; + } + out += out >> 8; + out += out >> 16; + if (size == 32) { /* popcntw */ + op->val = out & 0x0000003f0000003f; + return; + } + + out = (out + (out >> 32)) & 0x7f; + op->val = out; /* popcntd */ +} + +#ifdef CONFIG_PPC64 +static nokprobe_inline void do_bpermd(const struct pt_regs *regs, + struct instruction_op *op, + unsigned long v1, unsigned long v2) +{ + unsigned char perm, idx; + unsigned int i; + + perm = 0; + for (i = 0; i < 8; i++) { + idx = (v1 >> (i * 8)) & 0xff; + if (idx < 64) + if (v2 & PPC_BIT(idx)) + perm |= 1 << i; + } + op->val = perm; +} +#endif /* CONFIG_PPC64 */ +/* + * The size parameter adjusts the equivalent prty instruction. + * prtyw = 32, prtyd = 64 + */ +static nokprobe_inline void do_prty(const struct pt_regs *regs, + struct instruction_op *op, + unsigned long v, int size) +{ + unsigned long long res = v ^ (v >> 8); + + res ^= res >> 16; + if (size == 32) { /* prtyw */ + op->val = res & 0x0000000100000001; + return; + } + + res ^= res >> 32; + op->val = res & 1; /*prtyd */ } static nokprobe_inline int trap_compare(long v1, long v2) @@ -629,14 +1140,18 @@ static nokprobe_inline int trap_compare(long v1, long v2) #define ROTATE(x, n) ((n) ? (((x) << (n)) | ((x) >> (8 * sizeof(long) - (n)))) : (x)) /* - * Decode an instruction, and execute it if that can be done just by - * modifying *regs (i.e. integer arithmetic and logical instructions, - * branches, and barrier instructions). - * Returns 1 if the instruction has been executed, or 0 if not. - * Sets *op to indicate what the instruction does. + * Decode an instruction, and return information about it in *op + * without changing *regs. + * Integer arithmetic and logical instructions, branches, and barrier + * instructions can be emulated just using the information in *op. + * + * Return value is 1 if the instruction can be emulated just by + * updating *regs with the information in *op, -1 if we need the + * GPRs but *regs doesn't contain the full register set, or 0 + * otherwise. */ -int analyse_instr(struct instruction_op *op, struct pt_regs *regs, - unsigned int instr) +int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, + unsigned int instr) { unsigned int opcode, ra, rb, rd, spr, u; unsigned long int imm; @@ -653,12 +1168,11 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, imm = (signed short)(instr & 0xfffc); if ((instr & 2) == 0) imm += regs->nip; - regs->nip += 4; - regs->nip = truncate_if_32bit(regs->msr, regs->nip); + op->val = truncate_if_32bit(regs->msr, imm); if (instr & 1) - regs->link = regs->nip; - if (branch_taken(instr, regs)) - regs->nip = truncate_if_32bit(regs->msr, imm); + op->type |= SETLK; + if (branch_taken(instr, regs, op)) + op->type |= BRTAKEN; return 1; #ifdef CONFIG_PPC64 case 17: /* sc */ @@ -669,38 +1183,37 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, return 0; #endif case 18: /* b */ - op->type = BRANCH; + op->type = BRANCH | BRTAKEN; imm = instr & 0x03fffffc; if (imm & 0x02000000) imm -= 0x04000000; if ((instr & 2) == 0) imm += regs->nip; + op->val = truncate_if_32bit(regs->msr, imm); if (instr & 1) - regs->link = truncate_if_32bit(regs->msr, regs->nip + 4); - imm = truncate_if_32bit(regs->msr, imm); - regs->nip = imm; + op->type |= SETLK; return 1; case 19: switch ((instr >> 1) & 0x3ff) { case 0: /* mcrf */ + op->type = COMPUTE + SETCC; rd = 7 - ((instr >> 23) & 0x7); ra = 7 - ((instr >> 18) & 0x7); rd *= 4; ra *= 4; val = (regs->ccr >> ra) & 0xf; - regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd); - goto instr_done; + op->ccval = (regs->ccr & ~(0xfUL << rd)) | (val << rd); + return 1; case 16: /* bclr */ case 528: /* bcctr */ op->type = BRANCH; imm = (instr & 0x400)? regs->ctr: regs->link; - regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4); - imm = truncate_if_32bit(regs->msr, imm); + op->val = truncate_if_32bit(regs->msr, imm); if (instr & 1) - regs->link = regs->nip; - if (branch_taken(instr, regs)) - regs->nip = imm; + op->type |= SETLK; + if (branch_taken(instr, regs, op)) + op->type |= BRTAKEN; return 1; case 18: /* rfid, scary */ @@ -710,9 +1223,8 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, return 0; case 150: /* isync */ - op->type = BARRIER; - isync(); - goto instr_done; + op->type = BARRIER | BARRIER_ISYNC; + return 1; case 33: /* crnor */ case 129: /* crandc */ @@ -722,45 +1234,44 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 289: /* creqv */ case 417: /* crorc */ case 449: /* cror */ + op->type = COMPUTE + SETCC; ra = (instr >> 16) & 0x1f; rb = (instr >> 11) & 0x1f; rd = (instr >> 21) & 0x1f; ra = (regs->ccr >> (31 - ra)) & 1; rb = (regs->ccr >> (31 - rb)) & 1; val = (instr >> (6 + ra * 2 + rb)) & 1; - regs->ccr = (regs->ccr & ~(1UL << (31 - rd))) | + op->ccval = (regs->ccr & ~(1UL << (31 - rd))) | (val << (31 - rd)); - goto instr_done; + return 1; } break; case 31: switch ((instr >> 1) & 0x3ff) { case 598: /* sync */ - op->type = BARRIER; + op->type = BARRIER + BARRIER_SYNC; #ifdef __powerpc64__ switch ((instr >> 21) & 3) { case 1: /* lwsync */ - asm volatile("lwsync" : : : "memory"); - goto instr_done; + op->type = BARRIER + BARRIER_LWSYNC; + break; case 2: /* ptesync */ - asm volatile("ptesync" : : : "memory"); - goto instr_done; + op->type = BARRIER + BARRIER_PTESYNC; + break; } #endif - mb(); - goto instr_done; + return 1; case 854: /* eieio */ - op->type = BARRIER; - eieio(); - goto instr_done; + op->type = BARRIER + BARRIER_EIEIO; + return 1; } break; } /* Following cases refer to regs->gpr[], so we need all regs */ if (!FULL_REGS(regs)) - return 0; + return -1; rd = (instr >> 21) & 0x1f; ra = (instr >> 16) & 0x1f; @@ -771,21 +1282,21 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 2: /* tdi */ if (rd & trap_compare(regs->gpr[ra], (short) instr)) goto trap; - goto instr_done; + return 1; #endif case 3: /* twi */ if (rd & trap_compare((int)regs->gpr[ra], (short) instr)) goto trap; - goto instr_done; + return 1; case 7: /* mulli */ - regs->gpr[rd] = regs->gpr[ra] * (short) instr; - goto instr_done; + op->val = regs->gpr[ra] * (short) instr; + goto compute_done; case 8: /* subfic */ imm = (short) instr; - add_with_carry(regs, rd, ~regs->gpr[ra], imm, 1); - goto instr_done; + add_with_carry(regs, op, rd, ~regs->gpr[ra], imm, 1); + return 1; case 10: /* cmpli */ imm = (unsigned short) instr; @@ -794,8 +1305,8 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, if ((rd & 1) == 0) val = (unsigned int) val; #endif - do_cmp_unsigned(regs, val, imm, rd >> 2); - goto instr_done; + do_cmp_unsigned(regs, op, val, imm, rd >> 2); + return 1; case 11: /* cmpi */ imm = (short) instr; @@ -804,47 +1315,58 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, if ((rd & 1) == 0) val = (int) val; #endif - do_cmp_signed(regs, val, imm, rd >> 2); - goto instr_done; + do_cmp_signed(regs, op, val, imm, rd >> 2); + return 1; case 12: /* addic */ imm = (short) instr; - add_with_carry(regs, rd, regs->gpr[ra], imm, 0); - goto instr_done; + add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0); + return 1; case 13: /* addic. */ imm = (short) instr; - add_with_carry(regs, rd, regs->gpr[ra], imm, 0); - set_cr0(regs, rd); - goto instr_done; + add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0); + set_cr0(regs, op, rd); + return 1; case 14: /* addi */ imm = (short) instr; if (ra) imm += regs->gpr[ra]; - regs->gpr[rd] = imm; - goto instr_done; + op->val = imm; + goto compute_done; case 15: /* addis */ imm = ((short) instr) << 16; if (ra) imm += regs->gpr[ra]; - regs->gpr[rd] = imm; - goto instr_done; + op->val = imm; + goto compute_done; + + case 19: + if (((instr >> 1) & 0x1f) == 2) { + /* addpcis */ + imm = (short) (instr & 0xffc1); /* d0 + d2 fields */ + imm |= (instr >> 15) & 0x3e; /* d1 field */ + op->val = regs->nip + (imm << 16) + 4; + goto compute_done; + } + op->type = UNKNOWN; + return 0; case 20: /* rlwimi */ mb = (instr >> 6) & 0x1f; me = (instr >> 1) & 0x1f; val = DATA32(regs->gpr[rd]); imm = MASK32(mb, me); - regs->gpr[ra] = (regs->gpr[ra] & ~imm) | (ROTATE(val, rb) & imm); + op->val = (regs->gpr[ra] & ~imm) | (ROTATE(val, rb) & imm); goto logical_done; case 21: /* rlwinm */ mb = (instr >> 6) & 0x1f; me = (instr >> 1) & 0x1f; val = DATA32(regs->gpr[rd]); - regs->gpr[ra] = ROTATE(val, rb) & MASK32(mb, me); + op->val = ROTATE(val, rb) & MASK32(mb, me); goto logical_done; case 23: /* rlwnm */ @@ -852,40 +1374,37 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, me = (instr >> 1) & 0x1f; rb = regs->gpr[rb] & 0x1f; val = DATA32(regs->gpr[rd]); - regs->gpr[ra] = ROTATE(val, rb) & MASK32(mb, me); + op->val = ROTATE(val, rb) & MASK32(mb, me); goto logical_done; case 24: /* ori */ - imm = (unsigned short) instr; - regs->gpr[ra] = regs->gpr[rd] | imm; - goto instr_done; + op->val = regs->gpr[rd] | (unsigned short) instr; + goto logical_done_nocc; case 25: /* oris */ imm = (unsigned short) instr; - regs->gpr[ra] = regs->gpr[rd] | (imm << 16); - goto instr_done; + op->val = regs->gpr[rd] | (imm << 16); + goto logical_done_nocc; case 26: /* xori */ - imm = (unsigned short) instr; - regs->gpr[ra] = regs->gpr[rd] ^ imm; - goto instr_done; + op->val = regs->gpr[rd] ^ (unsigned short) instr; + goto logical_done_nocc; case 27: /* xoris */ imm = (unsigned short) instr; - regs->gpr[ra] = regs->gpr[rd] ^ (imm << 16); - goto instr_done; + op->val = regs->gpr[rd] ^ (imm << 16); + goto logical_done_nocc; case 28: /* andi. */ - imm = (unsigned short) instr; - regs->gpr[ra] = regs->gpr[rd] & imm; - set_cr0(regs, ra); - goto instr_done; + op->val = regs->gpr[rd] & (unsigned short) instr; + set_cr0(regs, op, ra); + goto logical_done_nocc; case 29: /* andis. */ imm = (unsigned short) instr; - regs->gpr[ra] = regs->gpr[rd] & (imm << 16); - set_cr0(regs, ra); - goto instr_done; + op->val = regs->gpr[rd] & (imm << 16); + set_cr0(regs, op, ra); + goto logical_done_nocc; #ifdef __powerpc64__ case 30: /* rld* */ @@ -896,48 +1415,60 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, val = ROTATE(val, sh); switch ((instr >> 2) & 3) { case 0: /* rldicl */ - regs->gpr[ra] = val & MASK64_L(mb); - goto logical_done; + val &= MASK64_L(mb); + break; case 1: /* rldicr */ - regs->gpr[ra] = val & MASK64_R(mb); - goto logical_done; + val &= MASK64_R(mb); + break; case 2: /* rldic */ - regs->gpr[ra] = val & MASK64(mb, 63 - sh); - goto logical_done; + val &= MASK64(mb, 63 - sh); + break; case 3: /* rldimi */ imm = MASK64(mb, 63 - sh); - regs->gpr[ra] = (regs->gpr[ra] & ~imm) | + val = (regs->gpr[ra] & ~imm) | (val & imm); - goto logical_done; } + op->val = val; + goto logical_done; } else { sh = regs->gpr[rb] & 0x3f; val = ROTATE(val, sh); switch ((instr >> 1) & 7) { case 0: /* rldcl */ - regs->gpr[ra] = val & MASK64_L(mb); + op->val = val & MASK64_L(mb); goto logical_done; case 1: /* rldcr */ - regs->gpr[ra] = val & MASK64_R(mb); + op->val = val & MASK64_R(mb); goto logical_done; } } #endif - break; /* illegal instruction */ + op->type = UNKNOWN; /* illegal instruction */ + return 0; case 31: + /* isel occupies 32 minor opcodes */ + if (((instr >> 1) & 0x1f) == 15) { + mb = (instr >> 6) & 0x1f; /* bc field */ + val = (regs->ccr >> (31 - mb)) & 1; + val2 = (ra) ? regs->gpr[ra] : 0; + + op->val = (val) ? val2 : regs->gpr[rb]; + goto compute_done; + } + switch ((instr >> 1) & 0x3ff) { case 4: /* tw */ if (rd == 0x1f || (rd & trap_compare((int)regs->gpr[ra], (int)regs->gpr[rb]))) goto trap; - goto instr_done; + return 1; #ifdef __powerpc64__ case 68: /* td */ if (rd & trap_compare(regs->gpr[ra], regs->gpr[rb])) goto trap; - goto instr_done; + return 1; #endif case 83: /* mfmsr */ if (regs->msr & MSR_PR) @@ -966,74 +1497,50 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, #endif case 19: /* mfcr */ + imm = 0xffffffffUL; if ((instr >> 20) & 1) { imm = 0xf0000000UL; for (sh = 0; sh < 8; ++sh) { - if (instr & (0x80000 >> sh)) { - regs->gpr[rd] = regs->ccr & imm; + if (instr & (0x80000 >> sh)) break; - } imm >>= 4; } - - goto instr_done; } - - regs->gpr[rd] = regs->ccr; - regs->gpr[rd] &= 0xffffffffUL; - goto instr_done; + op->val = regs->ccr & imm; + goto compute_done; case 144: /* mtcrf */ + op->type = COMPUTE + SETCC; imm = 0xf0000000UL; val = regs->gpr[rd]; + op->val = regs->ccr; for (sh = 0; sh < 8; ++sh) { if (instr & (0x80000 >> sh)) - regs->ccr = (regs->ccr & ~imm) | + op->val = (op->val & ~imm) | (val & imm); imm >>= 4; } - goto instr_done; + return 1; case 339: /* mfspr */ spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0); - switch (spr) { - case SPRN_XER: /* mfxer */ - regs->gpr[rd] = regs->xer; - regs->gpr[rd] &= 0xffffffffUL; - goto instr_done; - case SPRN_LR: /* mflr */ - regs->gpr[rd] = regs->link; - goto instr_done; - case SPRN_CTR: /* mfctr */ - regs->gpr[rd] = regs->ctr; - goto instr_done; - default: - op->type = MFSPR; - op->reg = rd; - op->spr = spr; - return 0; - } - break; + op->type = MFSPR; + op->reg = rd; + op->spr = spr; + if (spr == SPRN_XER || spr == SPRN_LR || + spr == SPRN_CTR) + return 1; + return 0; case 467: /* mtspr */ spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0); - switch (spr) { - case SPRN_XER: /* mtxer */ - regs->xer = (regs->gpr[rd] & 0xffffffffUL); - goto instr_done; - case SPRN_LR: /* mtlr */ - regs->link = regs->gpr[rd]; - goto instr_done; - case SPRN_CTR: /* mtctr */ - regs->ctr = regs->gpr[rd]; - goto instr_done; - default: - op->type = MTSPR; - op->val = regs->gpr[rd]; - op->spr = spr; - return 0; - } - break; + op->type = MTSPR; + op->val = regs->gpr[rd]; + op->spr = spr; + if (spr == SPRN_XER || spr == SPRN_LR || + spr == SPRN_CTR) + return 1; + return 0; /* * Compare instructions @@ -1048,8 +1555,8 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, val2 = (int) val2; } #endif - do_cmp_signed(regs, val, val2, rd >> 2); - goto instr_done; + do_cmp_signed(regs, op, val, val2, rd >> 2); + return 1; case 32: /* cmpl */ val = regs->gpr[ra]; @@ -1061,109 +1568,113 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, val2 = (unsigned int) val2; } #endif - do_cmp_unsigned(regs, val, val2, rd >> 2); - goto instr_done; + do_cmp_unsigned(regs, op, val, val2, rd >> 2); + return 1; + + case 508: /* cmpb */ + do_cmpb(regs, op, regs->gpr[rd], regs->gpr[rb]); + goto logical_done_nocc; /* * Arithmetic instructions */ case 8: /* subfc */ - add_with_carry(regs, rd, ~regs->gpr[ra], + add_with_carry(regs, op, rd, ~regs->gpr[ra], regs->gpr[rb], 1); goto arith_done; #ifdef __powerpc64__ case 9: /* mulhdu */ - asm("mulhdu %0,%1,%2" : "=r" (regs->gpr[rd]) : + asm("mulhdu %0,%1,%2" : "=r" (op->val) : "r" (regs->gpr[ra]), "r" (regs->gpr[rb])); goto arith_done; #endif case 10: /* addc */ - add_with_carry(regs, rd, regs->gpr[ra], + add_with_carry(regs, op, rd, regs->gpr[ra], regs->gpr[rb], 0); goto arith_done; case 11: /* mulhwu */ - asm("mulhwu %0,%1,%2" : "=r" (regs->gpr[rd]) : + asm("mulhwu %0,%1,%2" : "=r" (op->val) : "r" (regs->gpr[ra]), "r" (regs->gpr[rb])); goto arith_done; case 40: /* subf */ - regs->gpr[rd] = regs->gpr[rb] - regs->gpr[ra]; + op->val = regs->gpr[rb] - regs->gpr[ra]; goto arith_done; #ifdef __powerpc64__ case 73: /* mulhd */ - asm("mulhd %0,%1,%2" : "=r" (regs->gpr[rd]) : + asm("mulhd %0,%1,%2" : "=r" (op->val) : "r" (regs->gpr[ra]), "r" (regs->gpr[rb])); goto arith_done; #endif case 75: /* mulhw */ - asm("mulhw %0,%1,%2" : "=r" (regs->gpr[rd]) : + asm("mulhw %0,%1,%2" : "=r" (op->val) : "r" (regs->gpr[ra]), "r" (regs->gpr[rb])); goto arith_done; case 104: /* neg */ - regs->gpr[rd] = -regs->gpr[ra]; + op->val = -regs->gpr[ra]; goto arith_done; case 136: /* subfe */ - add_with_carry(regs, rd, ~regs->gpr[ra], regs->gpr[rb], - regs->xer & XER_CA); + add_with_carry(regs, op, rd, ~regs->gpr[ra], + regs->gpr[rb], regs->xer & XER_CA); goto arith_done; case 138: /* adde */ - add_with_carry(regs, rd, regs->gpr[ra], regs->gpr[rb], - regs->xer & XER_CA); + add_with_carry(regs, op, rd, regs->gpr[ra], + regs->gpr[rb], regs->xer & XER_CA); goto arith_done; case 200: /* subfze */ - add_with_carry(regs, rd, ~regs->gpr[ra], 0L, + add_with_carry(regs, op, rd, ~regs->gpr[ra], 0L, regs->xer & XER_CA); goto arith_done; case 202: /* addze */ - add_with_carry(regs, rd, regs->gpr[ra], 0L, + add_with_carry(regs, op, rd, regs->gpr[ra], 0L, regs->xer & XER_CA); goto arith_done; case 232: /* subfme */ - add_with_carry(regs, rd, ~regs->gpr[ra], -1L, + add_with_carry(regs, op, rd, ~regs->gpr[ra], -1L, regs->xer & XER_CA); goto arith_done; #ifdef __powerpc64__ case 233: /* mulld */ - regs->gpr[rd] = regs->gpr[ra] * regs->gpr[rb]; + op->val = regs->gpr[ra] * regs->gpr[rb]; goto arith_done; #endif case 234: /* addme */ - add_with_carry(regs, rd, regs->gpr[ra], -1L, + add_with_carry(regs, op, rd, regs->gpr[ra], -1L, regs->xer & XER_CA); goto arith_done; case 235: /* mullw */ - regs->gpr[rd] = (unsigned int) regs->gpr[ra] * + op->val = (unsigned int) regs->gpr[ra] * (unsigned int) regs->gpr[rb]; goto arith_done; case 266: /* add */ - regs->gpr[rd] = regs->gpr[ra] + regs->gpr[rb]; + op->val = regs->gpr[ra] + regs->gpr[rb]; goto arith_done; #ifdef __powerpc64__ case 457: /* divdu */ - regs->gpr[rd] = regs->gpr[ra] / regs->gpr[rb]; + op->val = regs->gpr[ra] / regs->gpr[rb]; goto arith_done; #endif case 459: /* divwu */ - regs->gpr[rd] = (unsigned int) regs->gpr[ra] / + op->val = (unsigned int) regs->gpr[ra] / (unsigned int) regs->gpr[rb]; goto arith_done; #ifdef __powerpc64__ case 489: /* divd */ - regs->gpr[rd] = (long int) regs->gpr[ra] / + op->val = (long int) regs->gpr[ra] / (long int) regs->gpr[rb]; goto arith_done; #endif case 491: /* divw */ - regs->gpr[rd] = (int) regs->gpr[ra] / + op->val = (int) regs->gpr[ra] / (int) regs->gpr[rb]; goto arith_done; @@ -1172,57 +1683,79 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, * Logical instructions */ case 26: /* cntlzw */ - asm("cntlzw %0,%1" : "=r" (regs->gpr[ra]) : - "r" (regs->gpr[rd])); + op->val = __builtin_clz((unsigned int) regs->gpr[rd]); goto logical_done; #ifdef __powerpc64__ case 58: /* cntlzd */ - asm("cntlzd %0,%1" : "=r" (regs->gpr[ra]) : - "r" (regs->gpr[rd])); + op->val = __builtin_clzl(regs->gpr[rd]); goto logical_done; #endif case 28: /* and */ - regs->gpr[ra] = regs->gpr[rd] & regs->gpr[rb]; + op->val = regs->gpr[rd] & regs->gpr[rb]; goto logical_done; case 60: /* andc */ - regs->gpr[ra] = regs->gpr[rd] & ~regs->gpr[rb]; + op->val = regs->gpr[rd] & ~regs->gpr[rb]; goto logical_done; + case 122: /* popcntb */ + do_popcnt(regs, op, regs->gpr[rd], 8); + goto logical_done_nocc; + case 124: /* nor */ - regs->gpr[ra] = ~(regs->gpr[rd] | regs->gpr[rb]); + op->val = ~(regs->gpr[rd] | regs->gpr[rb]); goto logical_done; + case 154: /* prtyw */ + do_prty(regs, op, regs->gpr[rd], 32); + goto logical_done_nocc; + + case 186: /* prtyd */ + do_prty(regs, op, regs->gpr[rd], 64); + goto logical_done_nocc; +#ifdef CONFIG_PPC64 + case 252: /* bpermd */ + do_bpermd(regs, op, regs->gpr[rd], regs->gpr[rb]); + goto logical_done_nocc; +#endif case 284: /* xor */ - regs->gpr[ra] = ~(regs->gpr[rd] ^ regs->gpr[rb]); + op->val = ~(regs->gpr[rd] ^ regs->gpr[rb]); goto logical_done; case 316: /* xor */ - regs->gpr[ra] = regs->gpr[rd] ^ regs->gpr[rb]; + op->val = regs->gpr[rd] ^ regs->gpr[rb]; goto logical_done; + case 378: /* popcntw */ + do_popcnt(regs, op, regs->gpr[rd], 32); + goto logical_done_nocc; + case 412: /* orc */ - regs->gpr[ra] = regs->gpr[rd] | ~regs->gpr[rb]; + op->val = regs->gpr[rd] | ~regs->gpr[rb]; goto logical_done; case 444: /* or */ - regs->gpr[ra] = regs->gpr[rd] | regs->gpr[rb]; + op->val = regs->gpr[rd] | regs->gpr[rb]; goto logical_done; case 476: /* nand */ - regs->gpr[ra] = ~(regs->gpr[rd] & regs->gpr[rb]); + op->val = ~(regs->gpr[rd] & regs->gpr[rb]); goto logical_done; - +#ifdef CONFIG_PPC64 + case 506: /* popcntd */ + do_popcnt(regs, op, regs->gpr[rd], 64); + goto logical_done_nocc; +#endif case 922: /* extsh */ - regs->gpr[ra] = (signed short) regs->gpr[rd]; + op->val = (signed short) regs->gpr[rd]; goto logical_done; case 954: /* extsb */ - regs->gpr[ra] = (signed char) regs->gpr[rd]; + op->val = (signed char) regs->gpr[rd]; goto logical_done; #ifdef __powerpc64__ case 986: /* extsw */ - regs->gpr[ra] = (signed int) regs->gpr[rd]; + op->val = (signed int) regs->gpr[rd]; goto logical_done; #endif @@ -1232,75 +1765,83 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 24: /* slw */ sh = regs->gpr[rb] & 0x3f; if (sh < 32) - regs->gpr[ra] = (regs->gpr[rd] << sh) & 0xffffffffUL; + op->val = (regs->gpr[rd] << sh) & 0xffffffffUL; else - regs->gpr[ra] = 0; + op->val = 0; goto logical_done; case 536: /* srw */ sh = regs->gpr[rb] & 0x3f; if (sh < 32) - regs->gpr[ra] = (regs->gpr[rd] & 0xffffffffUL) >> sh; + op->val = (regs->gpr[rd] & 0xffffffffUL) >> sh; else - regs->gpr[ra] = 0; + op->val = 0; goto logical_done; case 792: /* sraw */ + op->type = COMPUTE + SETREG + SETXER; sh = regs->gpr[rb] & 0x3f; ival = (signed int) regs->gpr[rd]; - regs->gpr[ra] = ival >> (sh < 32 ? sh : 31); + op->val = ival >> (sh < 32 ? sh : 31); + op->xerval = regs->xer; if (ival < 0 && (sh >= 32 || (ival & ((1ul << sh) - 1)) != 0)) - regs->xer |= XER_CA; + op->xerval |= XER_CA; else - regs->xer &= ~XER_CA; + op->xerval &= ~XER_CA; goto logical_done; case 824: /* srawi */ + op->type = COMPUTE + SETREG + SETXER; sh = rb; ival = (signed int) regs->gpr[rd]; - regs->gpr[ra] = ival >> sh; + op->val = ival >> sh; + op->xerval = regs->xer; if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0) - regs->xer |= XER_CA; + op->xerval |= XER_CA; else - regs->xer &= ~XER_CA; + op->xerval &= ~XER_CA; goto logical_done; #ifdef __powerpc64__ case 27: /* sld */ sh = regs->gpr[rb] & 0x7f; if (sh < 64) - regs->gpr[ra] = regs->gpr[rd] << sh; + op->val = regs->gpr[rd] << sh; else - regs->gpr[ra] = 0; + op->val = 0; goto logical_done; case 539: /* srd */ sh = regs->gpr[rb] & 0x7f; if (sh < 64) - regs->gpr[ra] = regs->gpr[rd] >> sh; + op->val = regs->gpr[rd] >> sh; else - regs->gpr[ra] = 0; + op->val = 0; goto logical_done; case 794: /* srad */ + op->type = COMPUTE + SETREG + SETXER; sh = regs->gpr[rb] & 0x7f; ival = (signed long int) regs->gpr[rd]; - regs->gpr[ra] = ival >> (sh < 64 ? sh : 63); + op->val = ival >> (sh < 64 ? sh : 63); + op->xerval = regs->xer; if (ival < 0 && (sh >= 64 || (ival & ((1ul << sh) - 1)) != 0)) - regs->xer |= XER_CA; + op->xerval |= XER_CA; else - regs->xer &= ~XER_CA; + op->xerval &= ~XER_CA; goto logical_done; case 826: /* sradi with sh_5 = 0 */ case 827: /* sradi with sh_5 = 1 */ + op->type = COMPUTE + SETREG + SETXER; sh = rb | ((instr & 2) << 4); ival = (signed long int) regs->gpr[rd]; - regs->gpr[ra] = ival >> sh; + op->val = ival >> sh; + op->xerval = regs->xer; if (ival < 0 && (ival & ((1ul << sh) - 1)) != 0) - regs->xer |= XER_CA; + op->xerval |= XER_CA; else - regs->xer &= ~XER_CA; + op->xerval &= ~XER_CA; goto logical_done; #endif /* __powerpc64__ */ @@ -1333,18 +1874,24 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, op->type = MKOP(CACHEOP, ICBI, 0); op->ea = xform_ea(instr, regs); return 0; + + case 1014: /* dcbz */ + op->type = MKOP(CACHEOP, DCBZ, 0); + op->ea = xform_ea(instr, regs); + return 0; } break; } - /* - * Loads and stores. - */ +/* + * Loads and stores. + */ op->type = UNKNOWN; op->update_reg = ra; op->reg = rd; op->val = regs->gpr[rd]; u = (instr >> 20) & UPDATE; + op->vsx_flags = 0; switch (opcode) { case 31: @@ -1368,9 +1915,30 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, op->type = MKOP(STCX, 0, 8); break; - case 21: /* ldx */ - case 53: /* ldux */ - op->type = MKOP(LOAD, u, 8); + case 52: /* lbarx */ + op->type = MKOP(LARX, 0, 1); + break; + + case 694: /* stbcx. */ + op->type = MKOP(STCX, 0, 1); + break; + + case 116: /* lharx */ + op->type = MKOP(LARX, 0, 2); + break; + + case 726: /* sthcx. */ + op->type = MKOP(STCX, 0, 2); + break; + + case 276: /* lqarx */ + if (!((rd & 1) || rd == ra || rd == rb)) + op->type = MKOP(LARX, 0, 16); + break; + + case 182: /* stqcx. */ + if (!(rd & 1)) + op->type = MKOP(STCX, 0, 16); break; #endif @@ -1385,22 +1953,58 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, break; #ifdef CONFIG_ALTIVEC + /* + * Note: for the load/store vector element instructions, + * bits of the EA say which field of the VMX register to use. + */ + case 7: /* lvebx */ + op->type = MKOP(LOAD_VMX, 0, 1); + op->element_size = 1; + break; + + case 39: /* lvehx */ + op->type = MKOP(LOAD_VMX, 0, 2); + op->element_size = 2; + break; + + case 71: /* lvewx */ + op->type = MKOP(LOAD_VMX, 0, 4); + op->element_size = 4; + break; + case 103: /* lvx */ case 359: /* lvxl */ - if (!(regs->msr & MSR_VEC)) - goto vecunavail; op->type = MKOP(LOAD_VMX, 0, 16); + op->element_size = 16; + break; + + case 135: /* stvebx */ + op->type = MKOP(STORE_VMX, 0, 1); + op->element_size = 1; + break; + + case 167: /* stvehx */ + op->type = MKOP(STORE_VMX, 0, 2); + op->element_size = 2; + break; + + case 199: /* stvewx */ + op->type = MKOP(STORE_VMX, 0, 4); + op->element_size = 4; break; case 231: /* stvx */ case 487: /* stvxl */ - if (!(regs->msr & MSR_VEC)) - goto vecunavail; op->type = MKOP(STORE_VMX, 0, 16); break; #endif /* CONFIG_ALTIVEC */ #ifdef __powerpc64__ + case 21: /* ldx */ + case 53: /* ldux */ + op->type = MKOP(LOAD, u, 8); + break; + case 149: /* stdx */ case 181: /* stdux */ op->type = MKOP(STORE, u, 8); @@ -1457,41 +2061,52 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, if (rb == 0) rb = 32; /* # bytes to load */ op->type = MKOP(LOAD_MULTI, 0, rb); - op->ea = 0; - if (ra) - op->ea = truncate_if_32bit(regs->msr, - regs->gpr[ra]); + op->ea = ra ? regs->gpr[ra] : 0; break; #ifdef CONFIG_PPC_FPU case 535: /* lfsx */ case 567: /* lfsux */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; - op->type = MKOP(LOAD_FP, u, 4); + op->type = MKOP(LOAD_FP, u | FPCONV, 4); break; case 599: /* lfdx */ case 631: /* lfdux */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; op->type = MKOP(LOAD_FP, u, 8); break; case 663: /* stfsx */ case 695: /* stfsux */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; - op->type = MKOP(STORE_FP, u, 4); + op->type = MKOP(STORE_FP, u | FPCONV, 4); break; case 727: /* stfdx */ case 759: /* stfdux */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; op->type = MKOP(STORE_FP, u, 8); break; -#endif + +#ifdef __powerpc64__ + case 791: /* lfdpx */ + op->type = MKOP(LOAD_FP, 0, 16); + break; + + case 855: /* lfiwax */ + op->type = MKOP(LOAD_FP, SIGNEXT, 4); + break; + + case 887: /* lfiwzx */ + op->type = MKOP(LOAD_FP, 0, 4); + break; + + case 919: /* stfdpx */ + op->type = MKOP(STORE_FP, 0, 16); + break; + + case 983: /* stfiwx */ + op->type = MKOP(STORE_FP, 0, 4); + break; +#endif /* __powerpc64 */ +#endif /* CONFIG_PPC_FPU */ #ifdef __powerpc64__ case 660: /* stdbrx */ @@ -1509,14 +2124,11 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, op->val = byterev_4(regs->gpr[rd]); break; - case 725: + case 725: /* stswi */ if (rb == 0) rb = 32; /* # bytes to store */ op->type = MKOP(STORE_MULTI, 0, rb); - op->ea = 0; - if (ra) - op->ea = truncate_if_32bit(regs->msr, - regs->gpr[ra]); + op->ea = ra ? regs->gpr[ra] : 0; break; case 790: /* lhbrx */ @@ -1529,20 +2141,184 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, break; #ifdef CONFIG_VSX + case 12: /* lxsiwzx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 4); + op->element_size = 8; + break; + + case 76: /* lxsiwax */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, SIGNEXT, 4); + op->element_size = 8; + break; + + case 140: /* stxsiwx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 4); + op->element_size = 8; + break; + + case 268: /* lxvx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 16); + op->element_size = 16; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 269: /* lxvl */ + case 301: { /* lxvll */ + int nb; + op->reg = rd | ((instr & 1) << 5); + op->ea = ra ? regs->gpr[ra] : 0; + nb = regs->gpr[rb] & 0xff; + if (nb > 16) + nb = 16; + op->type = MKOP(LOAD_VSX, 0, nb); + op->element_size = 16; + op->vsx_flags = ((instr & 0x20) ? VSX_LDLEFT : 0) | + VSX_CHECK_VEC; + break; + } + case 332: /* lxvdsx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 8); + op->element_size = 8; + op->vsx_flags = VSX_SPLAT; + break; + + case 364: /* lxvwsx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 4); + op->element_size = 4; + op->vsx_flags = VSX_SPLAT | VSX_CHECK_VEC; + break; + + case 396: /* stxvx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 16); + op->element_size = 16; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 397: /* stxvl */ + case 429: { /* stxvll */ + int nb; + op->reg = rd | ((instr & 1) << 5); + op->ea = ra ? regs->gpr[ra] : 0; + nb = regs->gpr[rb] & 0xff; + if (nb > 16) + nb = 16; + op->type = MKOP(STORE_VSX, 0, nb); + op->element_size = 16; + op->vsx_flags = ((instr & 0x20) ? VSX_LDLEFT : 0) | + VSX_CHECK_VEC; + break; + } + case 524: /* lxsspx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 4); + op->element_size = 8; + op->vsx_flags = VSX_FPCONV; + break; + + case 588: /* lxsdx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 8); + op->element_size = 8; + break; + + case 652: /* stxsspx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 4); + op->element_size = 8; + op->vsx_flags = VSX_FPCONV; + break; + + case 716: /* stxsdx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 8); + op->element_size = 8; + break; + + case 780: /* lxvw4x */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 16); + op->element_size = 4; + break; + + case 781: /* lxsibzx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 1); + op->element_size = 8; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 812: /* lxvh8x */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 16); + op->element_size = 2; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 813: /* lxsihzx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 2); + op->element_size = 8; + op->vsx_flags = VSX_CHECK_VEC; + break; + case 844: /* lxvd2x */ - case 876: /* lxvd2ux */ - if (!(regs->msr & MSR_VSX)) - goto vsxunavail; op->reg = rd | ((instr & 1) << 5); - op->type = MKOP(LOAD_VSX, u, 16); + op->type = MKOP(LOAD_VSX, 0, 16); + op->element_size = 8; + break; + + case 876: /* lxvb16x */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(LOAD_VSX, 0, 16); + op->element_size = 1; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 908: /* stxvw4x */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 16); + op->element_size = 4; + break; + + case 909: /* stxsibx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 1); + op->element_size = 8; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 940: /* stxvh8x */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 16); + op->element_size = 2; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 941: /* stxsihx */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 2); + op->element_size = 8; + op->vsx_flags = VSX_CHECK_VEC; break; case 972: /* stxvd2x */ - case 1004: /* stxvd2ux */ - if (!(regs->msr & MSR_VSX)) - goto vsxunavail; op->reg = rd | ((instr & 1) << 5); - op->type = MKOP(STORE_VSX, u, 16); + op->type = MKOP(STORE_VSX, 0, 16); + op->element_size = 8; + break; + + case 1004: /* stxvb16x */ + op->reg = rd | ((instr & 1) << 5); + op->type = MKOP(STORE_VSX, 0, 16); + op->element_size = 1; + op->vsx_flags = VSX_CHECK_VEC; break; #endif /* CONFIG_VSX */ @@ -1606,38 +2382,63 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, #ifdef CONFIG_PPC_FPU case 48: /* lfs */ case 49: /* lfsu */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; - op->type = MKOP(LOAD_FP, u, 4); + op->type = MKOP(LOAD_FP, u | FPCONV, 4); op->ea = dform_ea(instr, regs); break; case 50: /* lfd */ case 51: /* lfdu */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; op->type = MKOP(LOAD_FP, u, 8); op->ea = dform_ea(instr, regs); break; case 52: /* stfs */ case 53: /* stfsu */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; - op->type = MKOP(STORE_FP, u, 4); + op->type = MKOP(STORE_FP, u | FPCONV, 4); op->ea = dform_ea(instr, regs); break; case 54: /* stfd */ case 55: /* stfdu */ - if (!(regs->msr & MSR_FP)) - goto fpunavail; op->type = MKOP(STORE_FP, u, 8); op->ea = dform_ea(instr, regs); break; #endif #ifdef __powerpc64__ + case 56: /* lq */ + if (!((rd & 1) || (rd == ra))) + op->type = MKOP(LOAD, 0, 16); + op->ea = dqform_ea(instr, regs); + break; +#endif + +#ifdef CONFIG_VSX + case 57: /* lfdp, lxsd, lxssp */ + op->ea = dsform_ea(instr, regs); + switch (instr & 3) { + case 0: /* lfdp */ + if (rd & 1) + break; /* reg must be even */ + op->type = MKOP(LOAD_FP, 0, 16); + break; + case 2: /* lxsd */ + op->reg = rd + 32; + op->type = MKOP(LOAD_VSX, 0, 8); + op->element_size = 8; + op->vsx_flags = VSX_CHECK_VEC; + break; + case 3: /* lxssp */ + op->reg = rd + 32; + op->type = MKOP(LOAD_VSX, 0, 4); + op->element_size = 8; + op->vsx_flags = VSX_FPCONV | VSX_CHECK_VEC; + break; + } + break; +#endif /* CONFIG_VSX */ + +#ifdef __powerpc64__ case 58: /* ld[u], lwa */ op->ea = dsform_ea(instr, regs); switch (instr & 3) { @@ -1652,7 +2453,57 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, break; } break; +#endif +#ifdef CONFIG_VSX + case 61: /* stfdp, lxv, stxsd, stxssp, stxv */ + switch (instr & 7) { + case 0: /* stfdp with LSB of DS field = 0 */ + case 4: /* stfdp with LSB of DS field = 1 */ + op->ea = dsform_ea(instr, regs); + op->type = MKOP(STORE_FP, 0, 16); + break; + + case 1: /* lxv */ + op->ea = dqform_ea(instr, regs); + if (instr & 8) + op->reg = rd + 32; + op->type = MKOP(LOAD_VSX, 0, 16); + op->element_size = 16; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 2: /* stxsd with LSB of DS field = 0 */ + case 6: /* stxsd with LSB of DS field = 1 */ + op->ea = dsform_ea(instr, regs); + op->reg = rd + 32; + op->type = MKOP(STORE_VSX, 0, 8); + op->element_size = 8; + op->vsx_flags = VSX_CHECK_VEC; + break; + + case 3: /* stxssp with LSB of DS field = 0 */ + case 7: /* stxssp with LSB of DS field = 1 */ + op->ea = dsform_ea(instr, regs); + op->reg = rd + 32; + op->type = MKOP(STORE_VSX, 0, 4); + op->element_size = 8; + op->vsx_flags = VSX_FPCONV | VSX_CHECK_VEC; + break; + + case 5: /* stxv */ + op->ea = dqform_ea(instr, regs); + if (instr & 8) + op->reg = rd + 32; + op->type = MKOP(STORE_VSX, 0, 16); + op->element_size = 16; + op->vsx_flags = VSX_CHECK_VEC; + break; + } + break; +#endif /* CONFIG_VSX */ + +#ifdef __powerpc64__ case 62: /* std[u] */ op->ea = dsform_ea(instr, regs); switch (instr & 3) { @@ -1662,6 +2513,10 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, case 1: /* stdu */ op->type = MKOP(STORE, UPDATE, 8); break; + case 2: /* stq */ + if (!(rd & 1)) + op->type = MKOP(STORE, 0, 16); + break; } break; #endif /* __powerpc64__ */ @@ -1671,15 +2526,18 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, logical_done: if (instr & 1) - set_cr0(regs, ra); - goto instr_done; + set_cr0(regs, op, ra); + logical_done_nocc: + op->reg = ra; + op->type |= SETREG; + return 1; arith_done: if (instr & 1) - set_cr0(regs, rd); - - instr_done: - regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4); + set_cr0(regs, op, rd); + compute_done: + op->reg = rd; + op->type |= SETREG; return 1; priv: @@ -1691,24 +2549,6 @@ int analyse_instr(struct instruction_op *op, struct pt_regs *regs, op->type = INTERRUPT | 0x700; op->val = SRR1_PROGTRAP; return 0; - -#ifdef CONFIG_PPC_FPU - fpunavail: - op->type = INTERRUPT | 0x800; - return 0; -#endif - -#ifdef CONFIG_ALTIVEC - vecunavail: - op->type = INTERRUPT | 0xf20; - return 0; -#endif - -#ifdef CONFIG_VSX - vsxunavail: - op->type = INTERRUPT | 0xf40; - return 0; -#endif } EXPORT_SYMBOL_GPL(analyse_instr); NOKPROBE_SYMBOL(analyse_instr); @@ -1771,190 +2611,412 @@ static nokprobe_inline void do_byterev(unsigned long *valp, int size) } /* - * Emulate instructions that cause a transfer of control, - * loads and stores, and a few other instructions. - * Returns 1 if the step was emulated, 0 if not, - * or -1 if the instruction is one that should not be stepped, - * such as an rfid, or a mtmsrd that would clear MSR_RI. + * Emulate an instruction that can be executed just by updating + * fields in *regs. */ -int emulate_step(struct pt_regs *regs, unsigned int instr) +void emulate_update_regs(struct pt_regs *regs, struct instruction_op *op) { - struct instruction_op op; - int r, err, size; - unsigned long val; - unsigned int cr; - int i, rd, nb; + unsigned long next_pc; + + next_pc = truncate_if_32bit(regs->msr, regs->nip + 4); + switch (op->type & INSTR_TYPE_MASK) { + case COMPUTE: + if (op->type & SETREG) + regs->gpr[op->reg] = op->val; + if (op->type & SETCC) + regs->ccr = op->ccval; + if (op->type & SETXER) + regs->xer = op->xerval; + break; - r = analyse_instr(&op, regs, instr); - if (r != 0) - return r; + case BRANCH: + if (op->type & SETLK) + regs->link = next_pc; + if (op->type & BRTAKEN) + next_pc = op->val; + if (op->type & DECCTR) + --regs->ctr; + break; - err = 0; - size = GETSIZE(op.type); - switch (op.type & INSTR_TYPE_MASK) { - case CACHEOP: - if (!address_ok(regs, op.ea, 8)) - return 0; - switch (op.type & CACHEOP_MASK) { - case DCBST: - __cacheop_user_asmx(op.ea, err, "dcbst"); + case BARRIER: + switch (op->type & BARRIER_MASK) { + case BARRIER_SYNC: + mb(); break; - case DCBF: - __cacheop_user_asmx(op.ea, err, "dcbf"); + case BARRIER_ISYNC: + isync(); break; - case DCBTST: - if (op.reg == 0) - prefetchw((void *) op.ea); + case BARRIER_EIEIO: + eieio(); break; - case DCBT: - if (op.reg == 0) - prefetch((void *) op.ea); + case BARRIER_LWSYNC: + asm volatile("lwsync" : : : "memory"); break; - case ICBI: - __cacheop_user_asmx(op.ea, err, "icbi"); + case BARRIER_PTESYNC: + asm volatile("ptesync" : : : "memory"); break; } - if (err) - return 0; - goto instr_done; + break; + + case MFSPR: + switch (op->spr) { + case SPRN_XER: + regs->gpr[op->reg] = regs->xer & 0xffffffffUL; + break; + case SPRN_LR: + regs->gpr[op->reg] = regs->link; + break; + case SPRN_CTR: + regs->gpr[op->reg] = regs->ctr; + break; + default: + WARN_ON_ONCE(1); + } + break; + + case MTSPR: + switch (op->spr) { + case SPRN_XER: + regs->xer = op->val & 0xffffffffUL; + break; + case SPRN_LR: + regs->link = op->val; + break; + case SPRN_CTR: + regs->ctr = op->val; + break; + default: + WARN_ON_ONCE(1); + } + break; + + default: + WARN_ON_ONCE(1); + } + regs->nip = next_pc; +} + +/* + * Emulate a previously-analysed load or store instruction. + * Return values are: + * 0 = instruction emulated successfully + * -EFAULT = address out of range or access faulted (regs->dar + * contains the faulting address) + * -EACCES = misaligned access, instruction requires alignment + * -EINVAL = unknown operation in *op + */ +int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) +{ + int err, size, type; + int i, rd, nb; + unsigned int cr; + unsigned long val; + unsigned long ea; + bool cross_endian; + + err = 0; + size = GETSIZE(op->type); + type = op->type & INSTR_TYPE_MASK; + cross_endian = (regs->msr & MSR_LE) != (MSR_KERNEL & MSR_LE); + ea = truncate_if_32bit(regs->msr, op->ea); + switch (type) { case LARX: - if (op.ea & (size - 1)) - break; /* can't handle misaligned */ - if (!address_ok(regs, op.ea, size)) - return 0; + if (ea & (size - 1)) + return -EACCES; /* can't handle misaligned */ + if (!address_ok(regs, ea, size)) + return -EFAULT; err = 0; + val = 0; switch (size) { +#ifdef __powerpc64__ + case 1: + __get_user_asmx(val, ea, err, "lbarx"); + break; + case 2: + __get_user_asmx(val, ea, err, "lharx"); + break; +#endif case 4: - __get_user_asmx(val, op.ea, err, "lwarx"); + __get_user_asmx(val, ea, err, "lwarx"); break; #ifdef __powerpc64__ case 8: - __get_user_asmx(val, op.ea, err, "ldarx"); + __get_user_asmx(val, ea, err, "ldarx"); + break; + case 16: + err = do_lqarx(ea, ®s->gpr[op->reg]); break; #endif default: - return 0; + return -EINVAL; } - if (!err) - regs->gpr[op.reg] = val; - goto ldst_done; + if (err) { + regs->dar = ea; + break; + } + if (size < 16) + regs->gpr[op->reg] = val; + break; case STCX: - if (op.ea & (size - 1)) - break; /* can't handle misaligned */ - if (!address_ok(regs, op.ea, size)) - return 0; + if (ea & (size - 1)) + return -EACCES; /* can't handle misaligned */ + if (!address_ok(regs, ea, size)) + return -EFAULT; err = 0; switch (size) { +#ifdef __powerpc64__ + case 1: + __put_user_asmx(op->val, ea, err, "stbcx.", cr); + break; + case 2: + __put_user_asmx(op->val, ea, err, "stbcx.", cr); + break; +#endif case 4: - __put_user_asmx(op.val, op.ea, err, "stwcx.", cr); + __put_user_asmx(op->val, ea, err, "stwcx.", cr); break; #ifdef __powerpc64__ case 8: - __put_user_asmx(op.val, op.ea, err, "stdcx.", cr); + __put_user_asmx(op->val, ea, err, "stdcx.", cr); + break; + case 16: + err = do_stqcx(ea, regs->gpr[op->reg], + regs->gpr[op->reg + 1], &cr); break; #endif default: - return 0; + return -EINVAL; } if (!err) regs->ccr = (regs->ccr & 0x0fffffff) | (cr & 0xe0000000) | ((regs->xer >> 3) & 0x10000000); - goto ldst_done; + else + regs->dar = ea; + break; case LOAD: - err = read_mem(®s->gpr[op.reg], op.ea, size, regs); +#ifdef __powerpc64__ + if (size == 16) { + err = emulate_lq(regs, ea, op->reg, cross_endian); + break; + } +#endif + err = read_mem(®s->gpr[op->reg], ea, size, regs); if (!err) { - if (op.type & SIGNEXT) - do_signext(®s->gpr[op.reg], size); - if (op.type & BYTEREV) - do_byterev(®s->gpr[op.reg], size); + if (op->type & SIGNEXT) + do_signext(®s->gpr[op->reg], size); + if ((op->type & BYTEREV) == (cross_endian ? 0 : BYTEREV)) + do_byterev(®s->gpr[op->reg], size); } - goto ldst_done; + break; #ifdef CONFIG_PPC_FPU case LOAD_FP: - if (size == 4) - err = do_fp_load(op.reg, do_lfs, op.ea, size, regs); - else - err = do_fp_load(op.reg, do_lfd, op.ea, size, regs); - goto ldst_done; + /* + * If the instruction is in userspace, we can emulate it even + * if the VMX state is not live, because we have the state + * stored in the thread_struct. If the instruction is in + * the kernel, we must not touch the state in the thread_struct. + */ + if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP)) + return 0; + err = do_fp_load(op, ea, regs, cross_endian); + break; #endif #ifdef CONFIG_ALTIVEC case LOAD_VMX: - err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs); - goto ldst_done; + if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC)) + return 0; + err = do_vec_load(op->reg, ea, size, regs, cross_endian); + break; #endif #ifdef CONFIG_VSX - case LOAD_VSX: - err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs); - goto ldst_done; + case LOAD_VSX: { + unsigned long msrbit = MSR_VSX; + + /* + * Some VSX instructions check the MSR_VEC bit rather than MSR_VSX + * when the target of the instruction is a vector register. + */ + if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC)) + msrbit = MSR_VEC; + if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit)) + return 0; + err = do_vsx_load(op, ea, regs, cross_endian); + break; + } #endif case LOAD_MULTI: - if (regs->msr & MSR_LE) - return 0; - rd = op.reg; + if (!address_ok(regs, ea, size)) + return -EFAULT; + rd = op->reg; for (i = 0; i < size; i += 4) { + unsigned int v32 = 0; + nb = size - i; if (nb > 4) nb = 4; - err = read_mem(®s->gpr[rd], op.ea, nb, regs); + err = copy_mem_in((u8 *) &v32, ea, nb, regs); if (err) - return 0; - if (nb < 4) /* left-justify last bytes */ - regs->gpr[rd] <<= 32 - 8 * nb; - op.ea += 4; - ++rd; + break; + if (unlikely(cross_endian)) + v32 = byterev_4(v32); + regs->gpr[rd] = v32; + ea += 4; + /* reg number wraps from 31 to 0 for lsw[ix] */ + rd = (rd + 1) & 0x1f; } - goto instr_done; + break; case STORE: - if ((op.type & UPDATE) && size == sizeof(long) && - op.reg == 1 && op.update_reg == 1 && +#ifdef __powerpc64__ + if (size == 16) { + err = emulate_stq(regs, ea, op->reg, cross_endian); + break; + } +#endif + if ((op->type & UPDATE) && size == sizeof(long) && + op->reg == 1 && op->update_reg == 1 && !(regs->msr & MSR_PR) && - op.ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) { - err = handle_stack_update(op.ea, regs); - goto ldst_done; + ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) { + err = handle_stack_update(ea, regs); + break; } - err = write_mem(op.val, op.ea, size, regs); - goto ldst_done; + if (unlikely(cross_endian)) + do_byterev(&op->val, size); + err = write_mem(op->val, ea, size, regs); + break; #ifdef CONFIG_PPC_FPU case STORE_FP: - if (size == 4) - err = do_fp_store(op.reg, do_stfs, op.ea, size, regs); - else - err = do_fp_store(op.reg, do_stfd, op.ea, size, regs); - goto ldst_done; + if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_FP)) + return 0; + err = do_fp_store(op, ea, regs, cross_endian); + break; #endif #ifdef CONFIG_ALTIVEC case STORE_VMX: - err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs); - goto ldst_done; + if (!(regs->msr & MSR_PR) && !(regs->msr & MSR_VEC)) + return 0; + err = do_vec_store(op->reg, ea, size, regs, cross_endian); + break; #endif #ifdef CONFIG_VSX - case STORE_VSX: - err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs); - goto ldst_done; + case STORE_VSX: { + unsigned long msrbit = MSR_VSX; + + /* + * Some VSX instructions check the MSR_VEC bit rather than MSR_VSX + * when the target of the instruction is a vector register. + */ + if (op->reg >= 32 && (op->vsx_flags & VSX_CHECK_VEC)) + msrbit = MSR_VEC; + if (!(regs->msr & MSR_PR) && !(regs->msr & msrbit)) + return 0; + err = do_vsx_store(op, ea, regs, cross_endian); + break; + } #endif case STORE_MULTI: - if (regs->msr & MSR_LE) - return 0; - rd = op.reg; + if (!address_ok(regs, ea, size)) + return -EFAULT; + rd = op->reg; for (i = 0; i < size; i += 4) { - val = regs->gpr[rd]; + unsigned int v32 = regs->gpr[rd]; + nb = size - i; if (nb > 4) nb = 4; - else - val >>= 32 - 8 * nb; - err = write_mem(val, op.ea, nb, regs); + if (unlikely(cross_endian)) + v32 = byterev_4(v32); + err = copy_mem_out((u8 *) &v32, ea, nb, regs); if (err) - return 0; - op.ea += 4; - ++rd; + break; + ea += 4; + /* reg number wraps from 31 to 0 for stsw[ix] */ + rd = (rd + 1) & 0x1f; + } + break; + + default: + return -EINVAL; + } + + if (err) + return err; + + if (op->type & UPDATE) + regs->gpr[op->update_reg] = op->ea; + + return 0; +} +NOKPROBE_SYMBOL(emulate_loadstore); + +/* + * Emulate instructions that cause a transfer of control, + * loads and stores, and a few other instructions. + * Returns 1 if the step was emulated, 0 if not, + * or -1 if the instruction is one that should not be stepped, + * such as an rfid, or a mtmsrd that would clear MSR_RI. + */ +int emulate_step(struct pt_regs *regs, unsigned int instr) +{ + struct instruction_op op; + int r, err, type; + unsigned long val; + unsigned long ea; + + r = analyse_instr(&op, regs, instr); + if (r < 0) + return r; + if (r > 0) { + emulate_update_regs(regs, &op); + return 1; + } + + err = 0; + type = op.type & INSTR_TYPE_MASK; + + if (OP_IS_LOAD_STORE(type)) { + err = emulate_loadstore(regs, &op); + if (err) + return 0; + goto instr_done; + } + + switch (type) { + case CACHEOP: + ea = truncate_if_32bit(regs->msr, op.ea); + if (!address_ok(regs, ea, 8)) + return 0; + switch (op.type & CACHEOP_MASK) { + case DCBST: + __cacheop_user_asmx(ea, err, "dcbst"); + break; + case DCBF: + __cacheop_user_asmx(ea, err, "dcbf"); + break; + case DCBTST: + if (op.reg == 0) + prefetchw((void *) ea); + break; + case DCBT: + if (op.reg == 0) + prefetch((void *) ea); + break; + case ICBI: + __cacheop_user_asmx(ea, err, "icbi"); + break; + case DCBZ: + err = emulate_dcbz(ea, regs); + break; + } + if (err) { + regs->dar = ea; + return 0; } goto instr_done; @@ -1998,12 +3060,6 @@ int emulate_step(struct pt_regs *regs, unsigned int instr) } return 0; - ldst_done: - if (err) - return 0; - if (op.type & UPDATE) - regs->gpr[op.update_reg] = op.ea; - instr_done: regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4); return 1; diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S index d5b4d9498c54..56aac4c22025 100644 --- a/arch/powerpc/lib/string_64.S +++ b/arch/powerpc/lib/string_64.S @@ -184,7 +184,7 @@ err1; std r0,8(r3) mtctr r6 mr r8,r3 14: -err1; dcbz r0,r3 +err1; dcbz 0,r3 add r3,r3,r9 bdnz 14b diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c index f4c6472f2fc4..f29212e40f40 100644 --- a/arch/powerpc/mm/8xx_mmu.c +++ b/arch/powerpc/mm/8xx_mmu.c @@ -22,8 +22,11 @@ extern int __map_without_ltlbs; +static unsigned long block_mapped_ram; + /* - * Return PA for this VA if it is in IMMR area, or 0 + * Return PA for this VA if it is in an area mapped with LTLBs. + * Otherwise, returns 0 */ phys_addr_t v_block_mapped(unsigned long va) { @@ -33,11 +36,13 @@ phys_addr_t v_block_mapped(unsigned long va) return 0; if (va >= VIRT_IMMR_BASE && va < VIRT_IMMR_BASE + IMMR_SIZE) return p + va - VIRT_IMMR_BASE; + if (va >= PAGE_OFFSET && va < PAGE_OFFSET + block_mapped_ram) + return __pa(va); return 0; } /* - * Return VA for a given PA or 0 if not mapped + * Return VA for a given PA mapped with LTLBs or 0 if not mapped */ unsigned long p_block_mapped(phys_addr_t pa) { @@ -47,6 +52,8 @@ unsigned long p_block_mapped(phys_addr_t pa) return 0; if (pa >= p && pa < p + IMMR_SIZE) return VIRT_IMMR_BASE + pa - p; + if (pa < block_mapped_ram) + return (unsigned long)__va(pa); return 0; } @@ -58,7 +65,7 @@ unsigned long p_block_mapped(phys_addr_t pa) void __init MMU_init_hw(void) { /* PIN up to the 3 first 8Mb after IMMR in DTLB table */ -#ifdef CONFIG_PIN_TLB +#ifdef CONFIG_PIN_TLB_DATA unsigned long ctr = mfspr(SPRN_MD_CTR) & 0xfe000000; unsigned long flags = 0xf0 | MD_SPS16K | _PAGE_SHARED | _PAGE_DIRTY; #ifdef CONFIG_PIN_TLB_IMMR @@ -80,7 +87,7 @@ void __init MMU_init_hw(void) #endif } -static void mmu_mapin_immr(void) +static void __init mmu_mapin_immr(void) { unsigned long p = PHYS_IMMR_BASE; unsigned long v = VIRT_IMMR_BASE; @@ -96,8 +103,11 @@ static void mmu_mapin_immr(void) extern unsigned int DTLBMiss_jmp; #endif extern unsigned int DTLBMiss_cmp, FixupDAR_cmp; +#ifndef CONFIG_PIN_TLB_TEXT +extern unsigned int ITLBMiss_cmp; +#endif -void mmu_patch_cmp_limit(unsigned int *addr, unsigned long mapped) +static void __init mmu_patch_cmp_limit(unsigned int *addr, unsigned long mapped) { unsigned int instr = *addr; @@ -116,6 +126,9 @@ unsigned long __init mmu_mapin_ram(unsigned long top) #ifndef CONFIG_PIN_TLB_IMMR patch_instruction(&DTLBMiss_jmp, PPC_INST_NOP); #endif +#ifndef CONFIG_PIN_TLB_TEXT + mmu_patch_cmp_limit(&ITLBMiss_cmp, 0); +#endif } else { mapped = top & ~(LARGE_PAGE_SIZE_8M - 1); } @@ -133,11 +146,13 @@ unsigned long __init mmu_mapin_ram(unsigned long top) if (mapped) memblock_set_current_limit(mapped); + block_mapped_ram = mapped; + return mapped; } -void setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size) +void __init setup_initial_memory_limit(phys_addr_t first_memblock_base, + phys_addr_t first_memblock_size) { /* We don't currently support the first MEMBLOCK not mapping 0 * physical on those processors diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 7414034df1c3..fb844d2f266e 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -8,7 +8,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y := fault.o mem.o pgtable.o mmap.o \ init_$(BITS).o pgtable_$(BITS).o \ - init-common.o + init-common.o mmu_context.o obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ tlb_nohash_low.o obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o @@ -22,8 +22,6 @@ ifeq ($(CONFIG_PPC_STD_MMU_64),y) obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o endif -obj-$(CONFIG_PPC_ICSWX) += icswx.o -obj-$(CONFIG_PPC_ICSWX_PID) += icswx_pid.o obj-$(CONFIG_40x) += 40x_mmu.o obj-$(CONFIG_44x) += 44x_mmu.o obj-$(CONFIG_PPC_8xx) += 8xx_mmu.o diff --git a/arch/powerpc/mm/dump_hashpagetable.c b/arch/powerpc/mm/dump_hashpagetable.c index b1c144b03fcf..5c4c93dcff19 100644 --- a/arch/powerpc/mm/dump_hashpagetable.c +++ b/arch/powerpc/mm/dump_hashpagetable.c @@ -205,7 +205,7 @@ static void dump_hpte_info(struct pg_state *st, unsigned long ea, u64 v, u64 r, aps_index = calculate_pagesize(st, aps, "actual"); if (aps_index != 2) seq_printf(st->seq, "LP enc: %lx", lp); - seq_puts(st->seq, "\n"); + seq_putc(st->seq, '\n'); } diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c index 44fe4833910f..c9282d27b203 100644 --- a/arch/powerpc/mm/dump_linuxpagetables.c +++ b/arch/powerpc/mm/dump_linuxpagetables.c @@ -350,7 +350,7 @@ static void note_page(struct pg_state *st, unsigned long addr, st->current_flags, pg_level[st->level].num); - seq_puts(st->seq, "\n"); + seq_putc(st->seq, '\n'); } /* diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 4c422632047b..4797d08581ce 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -45,43 +45,39 @@ #include <asm/siginfo.h> #include <asm/debug.h> -#include "icswx.h" - -#ifdef CONFIG_KPROBES -static inline int notify_page_fault(struct pt_regs *regs) +static inline bool notify_page_fault(struct pt_regs *regs) { - int ret = 0; + bool ret = false; +#ifdef CONFIG_KPROBES /* kprobe_running() needs smp_processor_id() */ if (!user_mode(regs)) { preempt_disable(); if (kprobe_running() && kprobe_fault_handler(regs, 11)) - ret = 1; + ret = true; preempt_enable(); } +#endif /* CONFIG_KPROBES */ + + if (unlikely(debugger_fault_handler(regs))) + ret = true; return ret; } -#else -static inline int notify_page_fault(struct pt_regs *regs) -{ - return 0; -} -#endif /* * Check whether the instruction at regs->nip is a store using * an update addressing form which will update r1. */ -static int store_updates_sp(struct pt_regs *regs) +static bool store_updates_sp(struct pt_regs *regs) { unsigned int inst; if (get_user(inst, (unsigned int __user *)regs->nip)) - return 0; + return false; /* check for 1 in the rA field */ if (((inst >> 16) & 0x1f) != 1) - return 0; + return false; /* check major opcode */ switch (inst >> 26) { case 37: /* stwu */ @@ -89,7 +85,7 @@ static int store_updates_sp(struct pt_regs *regs) case 45: /* sthu */ case 53: /* stfsu */ case 55: /* stfdu */ - return 1; + return true; case 62: /* std or stdu */ return (inst & 3) == 1; case 31: @@ -101,18 +97,53 @@ static int store_updates_sp(struct pt_regs *regs) case 439: /* sthux */ case 695: /* stfsux */ case 759: /* stfdux */ - return 1; + return true; } } - return 0; + return false; } /* * do_page_fault error handling helpers */ -#define MM_FAULT_RETURN 0 -#define MM_FAULT_CONTINUE -1 -#define MM_FAULT_ERR(sig) (sig) +static int +__bad_area_nosemaphore(struct pt_regs *regs, unsigned long address, int si_code) +{ + /* + * If we are in kernel mode, bail out with a SEGV, this will + * be caught by the assembly which will restore the non-volatile + * registers before calling bad_page_fault() + */ + if (!user_mode(regs)) + return SIGSEGV; + + _exception(SIGSEGV, regs, si_code, address); + + return 0; +} + +static noinline int bad_area_nosemaphore(struct pt_regs *regs, unsigned long address) +{ + return __bad_area_nosemaphore(regs, address, SEGV_MAPERR); +} + +static int __bad_area(struct pt_regs *regs, unsigned long address, int si_code) +{ + struct mm_struct *mm = current->mm; + + /* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ + up_read(&mm->mmap_sem); + + return __bad_area_nosemaphore(regs, address, si_code); +} + +static noinline int bad_area(struct pt_regs *regs, unsigned long address) +{ + return __bad_area(regs, address, SEGV_MAPERR); +} static int do_sigbus(struct pt_regs *regs, unsigned long address, unsigned int fault) @@ -121,7 +152,7 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address, unsigned int lsb = 0; if (!user_mode(regs)) - return MM_FAULT_ERR(SIGBUS); + return SIGBUS; current->thread.trap_nr = BUS_ADRERR; info.si_signo = SIGBUS; @@ -142,25 +173,17 @@ static int do_sigbus(struct pt_regs *regs, unsigned long address, #endif info.si_addr_lsb = lsb; force_sig_info(SIGBUS, &info, current); - return MM_FAULT_RETURN; + return 0; } static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) { /* - * Pagefault was interrupted by SIGKILL. We have no reason to - * continue the pagefault. + * Kernel page fault interrupted by SIGKILL. We have no reason to + * continue processing. */ - if (fatal_signal_pending(current)) { - /* Coming from kernel, we need to deal with uaccess fixups */ - if (user_mode(regs)) - return MM_FAULT_RETURN; - return MM_FAULT_ERR(SIGKILL); - } - - /* No fault: be happy */ - if (!(fault & VM_FAULT_ERROR)) - return MM_FAULT_CONTINUE; + if (fatal_signal_pending(current) && !user_mode(regs)) + return SIGKILL; /* Out of memory */ if (fault & VM_FAULT_OOM) { @@ -169,19 +192,176 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) * made us unable to handle the page fault gracefully. */ if (!user_mode(regs)) - return MM_FAULT_ERR(SIGKILL); + return SIGSEGV; pagefault_out_of_memory(); - return MM_FAULT_RETURN; + } else { + if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| + VM_FAULT_HWPOISON_LARGE)) + return do_sigbus(regs, addr, fault); + else if (fault & VM_FAULT_SIGSEGV) + return bad_area_nosemaphore(regs, addr); + else + BUG(); + } + return 0; +} + +/* Is this a bad kernel fault ? */ +static bool bad_kernel_fault(bool is_exec, unsigned long error_code, + unsigned long address) +{ + if (is_exec && (error_code & (DSISR_NOEXEC_OR_G | DSISR_KEYFAULT))) { + printk_ratelimited(KERN_CRIT "kernel tried to execute" + " exec-protected page (%lx) -" + "exploit attempt? (uid: %d)\n", + address, from_kuid(&init_user_ns, + current_uid())); } + return is_exec || (address >= TASK_SIZE); +} - if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) - return do_sigbus(regs, addr, fault); +static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, + struct vm_area_struct *vma, + bool store_update_sp) +{ + /* + * N.B. The POWER/Open ABI allows programs to access up to + * 288 bytes below the stack pointer. + * The kernel signal delivery code writes up to about 1.5kB + * below the stack pointer (r1) before decrementing it. + * The exec code can write slightly over 640kB to the stack + * before setting the user r1. Thus we allow the stack to + * expand to 1MB without further checks. + */ + if (address + 0x100000 < vma->vm_end) { + /* get user regs even if this fault is in kernel mode */ + struct pt_regs *uregs = current->thread.regs; + if (uregs == NULL) + return true; - /* We don't understand the fault code, this is fatal */ - BUG(); - return MM_FAULT_CONTINUE; + /* + * A user-mode access to an address a long way below + * the stack pointer is only valid if the instruction + * is one which would update the stack pointer to the + * address accessed if the instruction completed, + * i.e. either stwu rs,n(r1) or stwux rs,r1,rb + * (or the byte, halfword, float or double forms). + * + * If we don't check this then any write to the area + * between the last mapped region and the stack will + * expand the stack rather than segfaulting. + */ + if (address + 2048 < uregs->gpr[1] && !store_update_sp) + return true; + } + return false; +} + +static bool access_error(bool is_write, bool is_exec, + struct vm_area_struct *vma) +{ + /* + * Allow execution from readable areas if the MMU does not + * provide separate controls over reading and executing. + * + * Note: That code used to not be enabled for 4xx/BookE. + * It is now as I/D cache coherency for these is done at + * set_pte_at() time and I see no reason why the test + * below wouldn't be valid on those processors. This -may- + * break programs compiled with a really old ABI though. + */ + if (is_exec) { + return !(vma->vm_flags & VM_EXEC) && + (cpu_has_feature(CPU_FTR_NOEXECUTE) || + !(vma->vm_flags & (VM_READ | VM_WRITE))); + } + + if (is_write) { + if (unlikely(!(vma->vm_flags & VM_WRITE))) + return true; + return false; + } + + if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))) + return true; + + return false; } +#ifdef CONFIG_PPC_SMLPAR +static inline void cmo_account_page_fault(void) +{ + if (firmware_has_feature(FW_FEATURE_CMO)) { + u32 page_ins; + + preempt_disable(); + page_ins = be32_to_cpu(get_lppaca()->page_ins); + page_ins += 1 << PAGE_FACTOR; + get_lppaca()->page_ins = cpu_to_be32(page_ins); + preempt_enable(); + } +} +#else +static inline void cmo_account_page_fault(void) { } +#endif /* CONFIG_PPC_SMLPAR */ + +#ifdef CONFIG_PPC_STD_MMU +static void sanity_check_fault(bool is_write, unsigned long error_code) +{ + /* + * For hash translation mode, we should never get a + * PROTFAULT. Any update to pte to reduce access will result in us + * removing the hash page table entry, thus resulting in a DSISR_NOHPTE + * fault instead of DSISR_PROTFAULT. + * + * A pte update to relax the access will not result in a hash page table + * entry invalidate and hence can result in DSISR_PROTFAULT. + * ptep_set_access_flags() doesn't do a hpte flush. This is why we have + * the special !is_write in the below conditional. + * + * For platforms that doesn't supports coherent icache and do support + * per page noexec bit, we do setup things such that we do the + * sync between D/I cache via fault. But that is handled via low level + * hash fault code (hash_page_do_lazy_icache()) and we should not reach + * here in such case. + * + * For wrong access that can result in PROTFAULT, the above vma->vm_flags + * check should handle those and hence we should fall to the bad_area + * handling correctly. + * + * For embedded with per page exec support that doesn't support coherent + * icache we do get PROTFAULT and we handle that D/I cache sync in + * set_pte_at while taking the noexec/prot fault. Hence this is WARN_ON + * is conditional for server MMU. + * + * For radix, we can get prot fault for autonuma case, because radix + * page table will have them marked noaccess for user. + */ + if (!radix_enabled() && !is_write) + WARN_ON_ONCE(error_code & DSISR_PROTFAULT); +} +#else +static void sanity_check_fault(bool is_write, unsigned long error_code) { } +#endif /* CONFIG_PPC_STD_MMU */ + +/* + * Define the correct "is_write" bit in error_code based + * on the processor family + */ +#if (defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) +#define page_fault_is_write(__err) ((__err) & ESR_DST) +#define page_fault_is_bad(__err) (0) +#else +#define page_fault_is_write(__err) ((__err) & DSISR_ISSTORE) +#if defined(CONFIG_PPC_8xx) +#define page_fault_is_bad(__err) ((__err) & DSISR_NOEXEC_OR_G) +#elif defined(CONFIG_PPC64) +#define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_64S) +#else +#define page_fault_is_bad(__err) ((__err) & DSISR_BAD_FAULT_32S) +#endif +#endif + /* * For 600- and 800-family processors, the error_code parameter is DSISR * for a data fault, SRR1 for an instruction fault. For 400-family processors @@ -195,92 +375,56 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) * The return value is 0 if the fault was handled, or the signal * number if this is a kernel fault that can't be handled here. */ -int do_page_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code) +static int __do_page_fault(struct pt_regs *regs, unsigned long address, + unsigned long error_code) { - enum ctx_state prev_state = exception_enter(); struct vm_area_struct * vma; struct mm_struct *mm = current->mm; unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; - int code = SEGV_MAPERR; - int is_write = 0; - int trap = TRAP(regs); - int is_exec = trap == 0x400; + int is_exec = TRAP(regs) == 0x400; int is_user = user_mode(regs); - int fault; - int rc = 0, store_update_sp = 0; + int is_write = page_fault_is_write(error_code); + int fault, major = 0; + bool store_update_sp = false; -#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) - /* - * Fortunately the bit assignments in SRR1 for an instruction - * fault and DSISR for a data fault are mostly the same for the - * bits we are interested in. But there are some bits which - * indicate errors in DSISR but can validly be set in SRR1. - */ - if (is_exec) - error_code &= 0x48200000; - else - is_write = error_code & DSISR_ISSTORE; -#else - is_write = error_code & ESR_DST; -#endif /* CONFIG_4xx || CONFIG_BOOKE */ + if (notify_page_fault(regs)) + return 0; -#ifdef CONFIG_PPC_ICSWX - /* - * we need to do this early because this "data storage - * interrupt" does not update the DAR/DEAR so we don't want to - * look at it - */ - if (error_code & ICSWX_DSI_UCT) { - rc = acop_handle_fault(regs, address, error_code); - if (rc) - goto bail; + if (unlikely(page_fault_is_bad(error_code))) { + if (is_user) { + _exception(SIGBUS, regs, BUS_OBJERR, address); + return 0; + } + return SIGBUS; } -#endif /* CONFIG_PPC_ICSWX */ - - if (notify_page_fault(regs)) - goto bail; - if (unlikely(debugger_fault_handler(regs))) - goto bail; + /* Additional sanity check(s) */ + sanity_check_fault(is_write, error_code); /* * The kernel should never take an execute fault nor should it * take a page fault to a kernel address. */ - if (!is_user && (is_exec || (address >= TASK_SIZE))) { - rc = SIGSEGV; - goto bail; - } + if (unlikely(!is_user && bad_kernel_fault(is_exec, error_code, address))) + return SIGSEGV; -#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \ - defined(CONFIG_PPC_BOOK3S_64) || defined(CONFIG_PPC_8xx)) - if (error_code & DSISR_DABRMATCH) { - /* breakpoint match */ - do_break(regs, address, error_code); - goto bail; + /* + * If we're in an interrupt, have no user context or are running + * in a region with pagefaults disabled then we must not take the fault + */ + if (unlikely(faulthandler_disabled() || !mm)) { + if (is_user) + printk_ratelimited(KERN_ERR "Page fault in user mode" + " with faulthandler_disabled()=%d" + " mm=%p\n", + faulthandler_disabled(), mm); + return bad_area_nosemaphore(regs, address); } -#endif /* We restore the interrupt state now */ if (!arch_irq_disabled_regs(regs)) local_irq_enable(); - if (faulthandler_disabled() || mm == NULL) { - if (!is_user) { - rc = SIGSEGV; - goto bail; - } - /* faulthandler_disabled() in user mode is really bad, - as is current->mm == NULL. */ - printk(KERN_EMERG "Page fault in user mode with " - "faulthandler_disabled() = %d mm = %p\n", - faulthandler_disabled(), mm); - printk(KERN_EMERG "NIP = %lx MSR = %lx\n", - regs->nip, regs->msr); - die("Weird page fault", regs, SIGSEGV); - } - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* @@ -293,6 +437,10 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (is_user) flags |= FAULT_FLAG_USER; + if (is_write) + flags |= FAULT_FLAG_WRITE; + if (is_exec) + flags |= FAULT_FLAG_INSTRUCTION; /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the @@ -309,9 +457,9 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, * source. If this is invalid we can skip the address space check, * thus avoiding the deadlock. */ - if (!down_read_trylock(&mm->mmap_sem)) { + if (unlikely(!down_read_trylock(&mm->mmap_sem))) { if (!is_user && !search_exception_tables(regs->nip)) - goto bad_area_nosemaphore; + return bad_area_nosemaphore(regs, address); retry: down_read(&mm->mmap_sem); @@ -325,122 +473,24 @@ retry: } vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (vma->vm_start <= address) + if (unlikely(!vma)) + return bad_area(regs, address); + if (likely(vma->vm_start <= address)) goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) + return bad_area(regs, address); - /* - * N.B. The POWER/Open ABI allows programs to access up to - * 288 bytes below the stack pointer. - * The kernel signal delivery code writes up to about 1.5kB - * below the stack pointer (r1) before decrementing it. - * The exec code can write slightly over 640kB to the stack - * before setting the user r1. Thus we allow the stack to - * expand to 1MB without further checks. - */ - if (address + 0x100000 < vma->vm_end) { - /* get user regs even if this fault is in kernel mode */ - struct pt_regs *uregs = current->thread.regs; - if (uregs == NULL) - goto bad_area; + /* The stack is being expanded, check if it's valid */ + if (unlikely(bad_stack_expansion(regs, address, vma, store_update_sp))) + return bad_area(regs, address); - /* - * A user-mode access to an address a long way below - * the stack pointer is only valid if the instruction - * is one which would update the stack pointer to the - * address accessed if the instruction completed, - * i.e. either stwu rs,n(r1) or stwux rs,r1,rb - * (or the byte, halfword, float or double forms). - * - * If we don't check this then any write to the area - * between the last mapped region and the stack will - * expand the stack rather than segfaulting. - */ - if (address + 2048 < uregs->gpr[1] && !store_update_sp) - goto bad_area; - } - if (expand_stack(vma, address)) - goto bad_area; + /* Try to expand it */ + if (unlikely(expand_stack(vma, address))) + return bad_area(regs, address); good_area: - code = SEGV_ACCERR; -#if defined(CONFIG_6xx) - if (error_code & 0x95700000) - /* an error such as lwarx to I/O controller space, - address matching DABR, eciwx, etc. */ - goto bad_area; -#endif /* CONFIG_6xx */ -#if defined(CONFIG_8xx) - /* The MPC8xx seems to always set 0x80000000, which is - * "undefined". Of those that can be set, this is the only - * one which seems bad. - */ - if (error_code & 0x10000000) - /* Guarded storage error. */ - goto bad_area; -#endif /* CONFIG_8xx */ - - if (is_exec) { - /* - * Allow execution from readable areas if the MMU does not - * provide separate controls over reading and executing. - * - * Note: That code used to not be enabled for 4xx/BookE. - * It is now as I/D cache coherency for these is done at - * set_pte_at() time and I see no reason why the test - * below wouldn't be valid on those processors. This -may- - * break programs compiled with a really old ABI though. - */ - if (!(vma->vm_flags & VM_EXEC) && - (cpu_has_feature(CPU_FTR_NOEXECUTE) || - !(vma->vm_flags & (VM_READ | VM_WRITE)))) - goto bad_area; - /* a write */ - } else if (is_write) { - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - flags |= FAULT_FLAG_WRITE; - /* a read */ - } else { - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) - goto bad_area; - } -#ifdef CONFIG_PPC_STD_MMU - /* - * For hash translation mode, we should never get a - * PROTFAULT. Any update to pte to reduce access will result in us - * removing the hash page table entry, thus resulting in a DSISR_NOHPTE - * fault instead of DSISR_PROTFAULT. - * - * A pte update to relax the access will not result in a hash page table - * entry invalidate and hence can result in DSISR_PROTFAULT. - * ptep_set_access_flags() doesn't do a hpte flush. This is why we have - * the special !is_write in the below conditional. - * - * For platforms that doesn't supports coherent icache and do support - * per page noexec bit, we do setup things such that we do the - * sync between D/I cache via fault. But that is handled via low level - * hash fault code (hash_page_do_lazy_icache()) and we should not reach - * here in such case. - * - * For wrong access that can result in PROTFAULT, the above vma->vm_flags - * check should handle those and hence we should fall to the bad_area - * handling correctly. - * - * For embedded with per page exec support that doesn't support coherent - * icache we do get PROTFAULT and we handle that D/I cache sync in - * set_pte_at while taking the noexec/prot fault. Hence this is WARN_ON - * is conditional for server MMU. - * - * For radix, we can get prot fault for autonuma case, because radix - * page table will have them marked noaccess for user. - */ - if (!radix_enabled() && !is_write) - WARN_ON_ONCE(error_code & DSISR_PROTFAULT); -#endif /* CONFIG_PPC_STD_MMU */ + if (unlikely(access_error(is_write, is_exec, vma))) + return bad_area(regs, address); /* * If for any reason at all we couldn't handle the fault, @@ -448,6 +498,7 @@ good_area: * the fault. */ fault = handle_mm_fault(vma, address, flags); + major |= fault & VM_FAULT_MAJOR; /* * Handle the retry right now, the mmap_sem has been released in that @@ -465,64 +516,39 @@ good_area: if (!fatal_signal_pending(current)) goto retry; } - /* We will enter mm_fault_error() below */ - } else - up_read(¤t->mm->mmap_sem); - - if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { - if (fault & VM_FAULT_SIGSEGV) - goto bad_area_nosemaphore; - rc = mm_fault_error(regs, address, fault); - if (rc >= MM_FAULT_RETURN) - goto bail; - else - rc = 0; + + /* + * User mode? Just return to handle the fatal exception otherwise + * return to bad_page_fault + */ + return is_user ? 0 : SIGBUS; } + up_read(¤t->mm->mmap_sem); + + if (unlikely(fault & VM_FAULT_ERROR)) + return mm_fault_error(regs, address, fault); + /* * Major/minor page fault accounting. */ - if (fault & VM_FAULT_MAJOR) { + if (major) { current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); -#ifdef CONFIG_PPC_SMLPAR - if (firmware_has_feature(FW_FEATURE_CMO)) { - u32 page_ins; - - preempt_disable(); - page_ins = be32_to_cpu(get_lppaca()->page_ins); - page_ins += 1 << PAGE_FACTOR; - get_lppaca()->page_ins = cpu_to_be32(page_ins); - preempt_enable(); - } -#endif /* CONFIG_PPC_SMLPAR */ + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + cmo_account_page_fault(); } else { current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } - - goto bail; - -bad_area: - up_read(&mm->mmap_sem); - -bad_area_nosemaphore: - /* User mode accesses cause a SIGSEGV */ - if (is_user) { - _exception(SIGSEGV, regs, code, address); - goto bail; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } + return 0; +} +NOKPROBE_SYMBOL(__do_page_fault); - if (is_exec && (error_code & DSISR_PROTFAULT)) - printk_ratelimited(KERN_CRIT "kernel tried to execute NX-protected" - " page (%lx) - exploit attempt? (uid: %d)\n", - address, from_kuid(&init_user_ns, current_uid())); - - rc = SIGSEGV; - -bail: +int do_page_fault(struct pt_regs *regs, unsigned long address, + unsigned long error_code) +{ + enum ctx_state prev_state = exception_enter(); + int rc = __do_page_fault(regs, address, error_code); exception_exit(prev_state); return rc; } diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S index 6f962e5cb5e1..ffbd7c0bda96 100644 --- a/arch/powerpc/mm/hash_low_32.S +++ b/arch/powerpc/mm/hash_low_32.S @@ -575,7 +575,6 @@ _GLOBAL(flush_hash_pages) rlwinm r8,r8,0,31,29 /* clear HASHPTE bit */ stwcx. r8,0,r5 /* update the pte */ bne- 33b -EXPORT_SYMBOL(flush_hash_pages) /* Get the address of the primary PTE group in the hash table (r3) */ _GLOBAL(flush_hash_patch_A) @@ -634,6 +633,7 @@ _GLOBAL(flush_hash_patch_B) SYNC_601 isync blr +EXPORT_SYMBOL(flush_hash_pages) /* * Flush an entry from the TLB diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 7a20669c19e7..67ec2e927253 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -61,6 +61,7 @@ #include <asm/tm.h> #include <asm/trace.h> #include <asm/ps3.h> +#include <asm/pte-walk.h> #ifdef DEBUG #define DBG(fmt...) udbg_printf(fmt) @@ -507,9 +508,9 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node, printk(KERN_INFO "Huge page(16GB) memory: " "addr = 0x%lX size = 0x%lX pages = %d\n", phys_addr, block_size, expected_pages); - if (phys_addr + (16 * GB) <= memblock_end_of_DRAM()) { + if (phys_addr + block_size * expected_pages <= memblock_end_of_DRAM()) { memblock_reserve(phys_addr, block_size * expected_pages); - add_gpage(phys_addr, block_size, expected_pages); + pseries_add_gpage(phys_addr, block_size, expected_pages); } return 0; } @@ -1019,6 +1020,7 @@ void __init hash__early_init_mmu(void) __kernel_virt_size = H_KERN_VIRT_SIZE; __vmalloc_start = H_VMALLOC_START; __vmalloc_end = H_VMALLOC_END; + __kernel_io_start = H_KERN_IO_START; vmemmap = (struct page *)H_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; @@ -1228,7 +1230,6 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, unsigned long vsid; pte_t *ptep; unsigned hugeshift; - const struct cpumask *tmp; int rc, user_region = 0; int psize, ssize; @@ -1280,8 +1281,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, } /* Check CPU locality */ - tmp = cpumask_of(smp_processor_id()); - if (user_region && cpumask_equal(mm_cpumask(mm), tmp)) + if (user_region && mm_is_thread_local(mm)) flags |= HPTE_LOCAL_UPDATE; #ifndef CONFIG_PPC_64K_PAGES @@ -1297,7 +1297,7 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea, #endif /* CONFIG_PPC_64K_PAGES */ /* Get PTE and page size from page tables */ - ptep = __find_linux_pte_or_hugepte(pgdir, ea, &is_thp, &hugeshift); + ptep = find_linux_pte(pgdir, ea, &is_thp, &hugeshift); if (ptep == NULL || !pte_present(*ptep)) { DBG_LOW(" no PTE !\n"); rc = 1; @@ -1526,7 +1526,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, * THP pages use update_mmu_cache_pmd. We don't do * hash preload there. Hence can ignore THP here */ - ptep = find_linux_pte_or_hugepte(pgdir, ea, NULL, &hugepage_shift); + ptep = find_current_mm_pte(pgdir, ea, NULL, &hugepage_shift); if (!ptep) goto out_exit; @@ -1543,7 +1543,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, #endif /* CONFIG_PPC_64K_PAGES */ /* Is that local to this CPU ? */ - if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) + if (mm_is_thread_local(mm)) update_flags |= HPTE_LOCAL_UPDATE; /* Hash it in */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index e1bf5ca397fe..1571a498a33f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -24,6 +24,8 @@ #include <asm/tlb.h> #include <asm/setup.h> #include <asm/hugetlb.h> +#include <asm/pte-walk.h> + #ifdef CONFIG_HUGETLB_PAGE @@ -36,32 +38,15 @@ unsigned int HPAGE_SHIFT; EXPORT_SYMBOL(HPAGE_SHIFT); -/* - * Tracks gpages after the device tree is scanned and before the - * huge_boot_pages list is ready. On non-Freescale implementations, this is - * just used to track 16G pages and so is a single array. FSL-based - * implementations may have more than one gpage size, so we need multiple - * arrays - */ -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) -#define MAX_NUMBER_GPAGES 128 -struct psize_gpages { - u64 gpage_list[MAX_NUMBER_GPAGES]; - unsigned int nr_gpages; -}; -static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT]; -#else -#define MAX_NUMBER_GPAGES 1024 -static u64 gpage_freearray[MAX_NUMBER_GPAGES]; -static unsigned nr_gpages; -#endif - #define hugepd_none(hpd) (hpd_val(hpd) == 0) pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { - /* Only called for hugetlbfs pages, hence can ignore THP */ - return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL); + /* + * Only called for hugetlbfs pages, hence can ignore THP and the + * irq disabled walk. + */ + return __find_linux_pte(mm->pgd, addr, NULL, NULL); } static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, @@ -210,145 +195,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz return hugepte_offset(*hpdp, addr, pdshift); } -#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) -/* Build list of addresses of gigantic pages. This function is used in early - * boot before the buddy allocator is setup. - */ -void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) -{ - unsigned int idx = shift_to_mmu_psize(__ffs(page_size)); - int i; - - if (addr == 0) - return; - - gpage_freearray[idx].nr_gpages = number_of_pages; - - for (i = 0; i < number_of_pages; i++) { - gpage_freearray[idx].gpage_list[i] = addr; - addr += page_size; - } -} - -/* - * Moves the gigantic page addresses from the temporary list to the - * huge_boot_pages list. - */ -int alloc_bootmem_huge_page(struct hstate *hstate) -{ - struct huge_bootmem_page *m; - int idx = shift_to_mmu_psize(huge_page_shift(hstate)); - int nr_gpages = gpage_freearray[idx].nr_gpages; - - if (nr_gpages == 0) - return 0; - -#ifdef CONFIG_HIGHMEM - /* - * If gpages can be in highmem we can't use the trick of storing the - * data structure in the page; allocate space for this - */ - m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0); - m->phys = gpage_freearray[idx].gpage_list[--nr_gpages]; -#else - m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]); -#endif - - list_add(&m->list, &huge_boot_pages); - gpage_freearray[idx].nr_gpages = nr_gpages; - gpage_freearray[idx].gpage_list[nr_gpages] = 0; - m->hstate = hstate; - - return 1; -} +#ifdef CONFIG_PPC_BOOK3S_64 /* - * Scan the command line hugepagesz= options for gigantic pages; store those in - * a list that we use to allocate the memory once all options are parsed. + * Tracks gpages after the device tree is scanned and before the + * huge_boot_pages list is ready on pseries. */ - -unsigned long gpage_npages[MMU_PAGE_COUNT]; - -static int __init do_gpage_early_setup(char *param, char *val, - const char *unused, void *arg) -{ - static phys_addr_t size; - unsigned long npages; - - /* - * The hugepagesz and hugepages cmdline options are interleaved. We - * use the size variable to keep track of whether or not this was done - * properly and skip over instances where it is incorrect. Other - * command-line parsing code will issue warnings, so we don't need to. - * - */ - if ((strcmp(param, "default_hugepagesz") == 0) || - (strcmp(param, "hugepagesz") == 0)) { - size = memparse(val, NULL); - } else if (strcmp(param, "hugepages") == 0) { - if (size != 0) { - if (sscanf(val, "%lu", &npages) <= 0) - npages = 0; - if (npages > MAX_NUMBER_GPAGES) { - pr_warn("MMU: %lu pages requested for page " -#ifdef CONFIG_PHYS_ADDR_T_64BIT - "size %llu KB, limiting to " -#else - "size %u KB, limiting to " -#endif - __stringify(MAX_NUMBER_GPAGES) "\n", - npages, size / 1024); - npages = MAX_NUMBER_GPAGES; - } - gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages; - size = 0; - } - } - return 0; -} - +#define MAX_NUMBER_GPAGES 1024 +__initdata static u64 gpage_freearray[MAX_NUMBER_GPAGES]; +__initdata static unsigned nr_gpages; /* - * This function allocates physical space for pages that are larger than the - * buddy allocator can handle. We want to allocate these in highmem because - * the amount of lowmem is limited. This means that this function MUST be - * called before lowmem_end_addr is set up in MMU_init() in order for the lmb - * allocate to grab highmem. - */ -void __init reserve_hugetlb_gpages(void) -{ - static __initdata char cmdline[COMMAND_LINE_SIZE]; - phys_addr_t size, base; - int i; - - strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE); - parse_args("hugetlb gpages", cmdline, NULL, 0, 0, 0, - NULL, &do_gpage_early_setup); - - /* - * Walk gpage list in reverse, allocating larger page sizes first. - * Skip over unsupported sizes, or sizes that have 0 gpages allocated. - * When we reach the point in the list where pages are no longer - * considered gpages, we're done. - */ - for (i = MMU_PAGE_COUNT-1; i >= 0; i--) { - if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0) - continue; - else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT)) - break; - - size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i)); - base = memblock_alloc_base(size * gpage_npages[i], size, - MEMBLOCK_ALLOC_ANYWHERE); - add_gpage(base, size, gpage_npages[i]); - } -} - -#else /* !PPC_FSL_BOOK3E */ - -/* Build list of addresses of gigantic pages. This function is used in early + * Build list of addresses of gigantic pages. This function is used in early * boot before the buddy allocator is setup. */ -void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) +void __init pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) { if (!addr) return; @@ -360,10 +220,7 @@ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages) } } -/* Moves the gigantic page addresses from the temporary list to the - * huge_boot_pages list. - */ -int alloc_bootmem_huge_page(struct hstate *hstate) +int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) { struct huge_bootmem_page *m; if (nr_gpages == 0) @@ -376,6 +233,17 @@ int alloc_bootmem_huge_page(struct hstate *hstate) } #endif + +int __init alloc_bootmem_huge_page(struct hstate *h) +{ + +#ifdef CONFIG_PPC_BOOK3S_64 + if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) + return pseries_alloc_bootmem_huge_page(h); +#endif + return __alloc_bootmem_huge_page(h); +} + #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) #define HUGEPD_FREELIST_SIZE \ ((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t)) @@ -407,8 +275,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || - cpumask_equal(mm_cpumask(tlb->mm), - cpumask_of(smp_processor_id()))) { + mm_is_thread_local(tlb->mm)) { kmem_cache_free(hugepte_cache, hugepte); put_cpu_var(hugepd_freelist_cur); return; @@ -886,9 +753,8 @@ void flush_dcache_icache_hugepage(struct page *page) * This function need to be called with interrupts disabled. We use this variant * when we have MSR[EE] = 0 but the paca->soft_enabled = 1 */ - -pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, - bool *is_thp, unsigned *shift) +pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea, + bool *is_thp, unsigned *hpage_shift) { pgd_t pgd, *pgdp; pud_t pud, *pudp; @@ -897,8 +763,8 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, hugepd_t *hpdp = NULL; unsigned pdshift = PGDIR_SHIFT; - if (shift) - *shift = 0; + if (hpage_shift) + *hpage_shift = 0; if (is_thp) *is_thp = false; @@ -968,16 +834,15 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, ret_pte = hugepte_offset(*hpdp, ea, pdshift); pdshift = hugepd_shift(*hpdp); out: - if (shift) - *shift = pdshift; + if (hpage_shift) + *hpage_shift = pdshift; return ret_pte; } -EXPORT_SYMBOL_GPL(__find_linux_pte_or_hugepte); +EXPORT_SYMBOL_GPL(__find_linux_pte); int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { - unsigned long mask; unsigned long pte_end; struct page *head, *page; pte_t pte; @@ -988,18 +853,10 @@ int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, end = pte_end; pte = READ_ONCE(*ptep); - mask = _PAGE_PRESENT | _PAGE_READ; - /* - * On some CPUs like the 8xx, _PAGE_RW hence _PAGE_WRITE is defined - * as 0 and _PAGE_RO has to be set when a page is not writable - */ - if (write) - mask |= _PAGE_WRITE; - else - mask |= _PAGE_RO; - - if ((pte_val(pte) & mask) != mask) + if (!pte_present(pte) || !pte_read(pte)) + return 0; + if (write && !pte_write(pte)) return 0; /* hugepages are never "special" */ diff --git a/arch/powerpc/mm/icswx.c b/arch/powerpc/mm/icswx.c deleted file mode 100644 index 1fa794d7d59f..000000000000 --- a/arch/powerpc/mm/icswx.c +++ /dev/null @@ -1,292 +0,0 @@ -/* - * ICSWX and ACOP Management - * - * Copyright (C) 2011 Anton Blanchard, IBM Corp. <anton@samba.org> - * - * 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/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/spinlock.h> -#include <linux/module.h> -#include <linux/uaccess.h> - -#include "icswx.h" - -/* - * The processor and its L2 cache cause the icswx instruction to - * generate a COP_REQ transaction on PowerBus. The transaction has no - * address, and the processor does not perform an MMU access to - * authenticate the transaction. The command portion of the PowerBus - * COP_REQ transaction includes the LPAR_ID (LPID) and the coprocessor - * Process ID (PID), which the coprocessor compares to the authorized - * LPID and PID held in the coprocessor, to determine if the process - * is authorized to generate the transaction. The data of the COP_REQ - * transaction is 128-byte or less in size and is placed in cacheable - * memory on a 128-byte cache line boundary. - * - * The task to use a coprocessor should use use_cop() to mark the use - * of the Coprocessor Type (CT) and context switching. On a server - * class processor, the PID register is used only for coprocessor - * management + * and so a coprocessor PID is allocated before - * executing icswx + * instruction. Drop_cop() is used to free the - * coprocessor PID. - * - * Example: - * Host Fabric Interface (HFI) is a PowerPC network coprocessor. - * Each HFI have multiple windows. Each HFI window serves as a - * network device sending to and receiving from HFI network. - * HFI immediate send function uses icswx instruction. The immediate - * send function allows small (single cache-line) packets be sent - * without using the regular HFI send FIFO and doorbell, which are - * much slower than immediate send. - * - * For each task intending to use HFI immediate send, the HFI driver - * calls use_cop() to obtain a coprocessor PID for the task. - * The HFI driver then allocate a free HFI window and save the - * coprocessor PID to the HFI window to allow the task to use the - * HFI window. - * - * The HFI driver repeatedly creates immediate send packets and - * issues icswx instruction to send data through the HFI window. - * The HFI compares the coprocessor PID in the CPU PID register - * to the PID held in the HFI window to determine if the transaction - * is allowed. - * - * When the task to release the HFI window, the HFI driver calls - * drop_cop() to release the coprocessor PID. - */ - -void switch_cop(struct mm_struct *next) -{ -#ifdef CONFIG_PPC_ICSWX_PID - mtspr(SPRN_PID, next->context.cop_pid); -#endif - mtspr(SPRN_ACOP, next->context.acop); -} - -/** - * Start using a coprocessor. - * @acop: mask of coprocessor to be used. - * @mm: The mm the coprocessor to associate with. Most likely current mm. - * - * Return a positive PID if successful. Negative errno otherwise. - * The returned PID will be fed to the coprocessor to determine if an - * icswx transaction is authenticated. - */ -int use_cop(unsigned long acop, struct mm_struct *mm) -{ - int ret; - - if (!cpu_has_feature(CPU_FTR_ICSWX)) - return -ENODEV; - - if (!mm || !acop) - return -EINVAL; - - /* The page_table_lock ensures mm_users won't change under us */ - spin_lock(&mm->page_table_lock); - spin_lock(mm->context.cop_lockp); - - ret = get_cop_pid(mm); - if (ret < 0) - goto out; - - /* update acop */ - mm->context.acop |= acop; - - sync_cop(mm); - - /* - * If this is a threaded process then there might be other threads - * running. We need to send an IPI to force them to pick up any - * change in PID and ACOP. - */ - if (atomic_read(&mm->mm_users) > 1) - smp_call_function(sync_cop, mm, 1); - -out: - spin_unlock(mm->context.cop_lockp); - spin_unlock(&mm->page_table_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(use_cop); - -/** - * Stop using a coprocessor. - * @acop: mask of coprocessor to be stopped. - * @mm: The mm the coprocessor associated with. - */ -void drop_cop(unsigned long acop, struct mm_struct *mm) -{ - int free_pid; - - if (!cpu_has_feature(CPU_FTR_ICSWX)) - return; - - if (WARN_ON_ONCE(!mm)) - return; - - /* The page_table_lock ensures mm_users won't change under us */ - spin_lock(&mm->page_table_lock); - spin_lock(mm->context.cop_lockp); - - mm->context.acop &= ~acop; - - free_pid = disable_cop_pid(mm); - sync_cop(mm); - - /* - * If this is a threaded process then there might be other threads - * running. We need to send an IPI to force them to pick up any - * change in PID and ACOP. - */ - if (atomic_read(&mm->mm_users) > 1) - smp_call_function(sync_cop, mm, 1); - - if (free_pid != COP_PID_NONE) - free_cop_pid(free_pid); - - spin_unlock(mm->context.cop_lockp); - spin_unlock(&mm->page_table_lock); -} -EXPORT_SYMBOL_GPL(drop_cop); - -static int acop_use_cop(int ct) -{ - /* There is no alternate policy, yet */ - return -1; -} - -/* - * Get the instruction word at the NIP - */ -static u32 acop_get_inst(struct pt_regs *regs) -{ - u32 inst; - u32 __user *p; - - p = (u32 __user *)regs->nip; - if (!access_ok(VERIFY_READ, p, sizeof(*p))) - return 0; - - if (__get_user(inst, p)) - return 0; - - return inst; -} - -/** - * @regs: registers at time of interrupt - * @address: storage address - * @error_code: Fault code, usually the DSISR or ESR depending on - * processor type - * - * Return 0 if we are able to resolve the data storage fault that - * results from a CT miss in the ACOP register. - */ -int acop_handle_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code) -{ - int ct; - u32 inst = 0; - - if (!cpu_has_feature(CPU_FTR_ICSWX)) { - pr_info("No coprocessors available"); - _exception(SIGILL, regs, ILL_ILLOPN, address); - } - - if (!user_mode(regs)) { - /* this could happen if the HV denies the - * kernel access, for now we just die */ - die("ICSWX from kernel failed", regs, SIGSEGV); - } - - /* Some implementations leave us a hint for the CT */ - ct = ICSWX_GET_CT_HINT(error_code); - if (ct < 0) { - /* we have to peek at the instruction word to figure out CT */ - u32 ccw; - u32 rs; - - inst = acop_get_inst(regs); - if (inst == 0) - return -1; - - rs = (inst >> (31 - 10)) & 0x1f; - ccw = regs->gpr[rs]; - ct = (ccw >> 16) & 0x3f; - } - - /* - * We could be here because another thread has enabled acop - * but the ACOP register has yet to be updated. - * - * This should have been taken care of by the IPI to sync all - * the threads (see smp_call_function(sync_cop, mm, 1)), but - * that could take forever if there are a significant amount - * of threads. - * - * Given the number of threads on some of these systems, - * perhaps this is the best way to sync ACOP rather than whack - * every thread with an IPI. - */ - if ((acop_copro_type_bit(ct) & current->active_mm->context.acop) != 0) { - sync_cop(current->active_mm); - return 0; - } - - /* check for alternate policy */ - if (!acop_use_cop(ct)) - return 0; - - /* at this point the CT is unknown to the system */ - pr_warn("%s[%d]: Coprocessor %d is unavailable\n", - current->comm, current->pid, ct); - - /* get inst if we don't already have it */ - if (inst == 0) { - inst = acop_get_inst(regs); - if (inst == 0) - return -1; - } - - /* Check if the instruction is the "record form" */ - if (inst & 1) { - /* - * the instruction is "record" form so we can reject - * using CR0 - */ - regs->ccr &= ~(0xful << 28); - regs->ccr |= ICSWX_RC_NOT_FOUND << 28; - - /* Move on to the next instruction */ - regs->nip += 4; - } else { - /* - * There is no architected mechanism to report a bad - * CT so we could either SIGILL or report nothing. - * Since the non-record version should only bu used - * for "hints" or "don't care" we should probably do - * nothing. However, I could see how some people - * might want an SIGILL so it here if you want it. - */ -#ifdef CONFIG_PPC_ICSWX_USE_SIGILL - _exception(SIGILL, regs, ILL_ILLOPN, address); -#else - regs->nip += 4; -#endif - } - - return 0; -} -EXPORT_SYMBOL_GPL(acop_handle_fault); diff --git a/arch/powerpc/mm/icswx.h b/arch/powerpc/mm/icswx.h deleted file mode 100644 index 6dedc08e62c8..000000000000 --- a/arch/powerpc/mm/icswx.h +++ /dev/null @@ -1,68 +0,0 @@ -#ifndef _ARCH_POWERPC_MM_ICSWX_H_ -#define _ARCH_POWERPC_MM_ICSWX_H_ - -/* - * ICSWX and ACOP Management - * - * Copyright (C) 2011 Anton Blanchard, IBM Corp. <anton@samba.org> - * - * 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/mmu_context.h> - -/* also used to denote that PIDs are not used */ -#define COP_PID_NONE 0 - -static inline void sync_cop(void *arg) -{ - struct mm_struct *mm = arg; - - if (mm == current->active_mm) - switch_cop(current->active_mm); -} - -#ifdef CONFIG_PPC_ICSWX_PID -extern int get_cop_pid(struct mm_struct *mm); -extern int disable_cop_pid(struct mm_struct *mm); -extern void free_cop_pid(int free_pid); -#else -#define get_cop_pid(m) (COP_PID_NONE) -#define disable_cop_pid(m) (COP_PID_NONE) -#define free_cop_pid(p) -#endif - -/* - * These are implementation bits for architected registers. If this - * ever becomes architecture the should be moved to reg.h et. al. - */ -/* UCT is the same bit for Server and Embedded */ -#define ICSWX_DSI_UCT 0x00004000 /* Unavailable Coprocessor Type */ - -#ifdef CONFIG_PPC_BOOK3E -/* Embedded implementation gives us no hints as to what the CT is */ -#define ICSWX_GET_CT_HINT(x) (-1) -#else -/* Server implementation contains the CT value in the DSISR */ -#define ICSWX_DSISR_CTMASK 0x00003f00 -#define ICSWX_GET_CT_HINT(x) (((x) & ICSWX_DSISR_CTMASK) >> 8) -#endif - -#define ICSWX_RC_STARTED 0x8 /* The request has been started */ -#define ICSWX_RC_NOT_IDLE 0x4 /* No coprocessor found idle */ -#define ICSWX_RC_NOT_FOUND 0x2 /* No coprocessor found */ -#define ICSWX_RC_UNDEFINED 0x1 /* Reserved */ - -extern int acop_handle_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code); - -static inline u64 acop_copro_type_bit(unsigned int type) -{ - return 1ULL << (63 - type); -} - -#endif /* !_ARCH_POWERPC_MM_ICSWX_H_ */ diff --git a/arch/powerpc/mm/icswx_pid.c b/arch/powerpc/mm/icswx_pid.c deleted file mode 100644 index 91e30eb7d054..000000000000 --- a/arch/powerpc/mm/icswx_pid.c +++ /dev/null @@ -1,87 +0,0 @@ -/* - * ICSWX and ACOP/PID Management - * - * Copyright (C) 2011 Anton Blanchard, IBM Corp. <anton@samba.org> - * - * 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/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/spinlock.h> -#include <linux/idr.h> -#include <linux/module.h> -#include "icswx.h" - -#define COP_PID_MIN (COP_PID_NONE + 1) -#define COP_PID_MAX (0xFFFF) - -static DEFINE_SPINLOCK(mmu_context_acop_lock); -static DEFINE_IDA(cop_ida); - -static int new_cop_pid(struct ida *ida, int min_id, int max_id, - spinlock_t *lock) -{ - int index; - int err; - -again: - if (!ida_pre_get(ida, GFP_KERNEL)) - return -ENOMEM; - - spin_lock(lock); - err = ida_get_new_above(ida, min_id, &index); - spin_unlock(lock); - - if (err == -EAGAIN) - goto again; - else if (err) - return err; - - if (index > max_id) { - spin_lock(lock); - ida_remove(ida, index); - spin_unlock(lock); - return -ENOMEM; - } - - return index; -} - -int get_cop_pid(struct mm_struct *mm) -{ - int pid; - - if (mm->context.cop_pid == COP_PID_NONE) { - pid = new_cop_pid(&cop_ida, COP_PID_MIN, COP_PID_MAX, - &mmu_context_acop_lock); - if (pid >= 0) - mm->context.cop_pid = pid; - } - return mm->context.cop_pid; -} - -int disable_cop_pid(struct mm_struct *mm) -{ - int free_pid = COP_PID_NONE; - - if ((!mm->context.acop) && (mm->context.cop_pid != COP_PID_NONE)) { - free_pid = mm->context.cop_pid; - mm->context.cop_pid = COP_PID_NONE; - } - return free_pid; -} - -void free_cop_pid(int free_pid) -{ - spin_lock(&mmu_context_acop_lock); - ida_remove(&cop_ida, free_pid); - spin_unlock(&mmu_context_acop_lock); -} diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 8a7c38b8d335..6419b33ca309 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -113,6 +113,12 @@ void __init MMU_setup(void) __map_without_bats = 1; __map_without_ltlbs = 1; } +#ifdef CONFIG_STRICT_KERNEL_RWX + if (rodata_enabled) { + __map_without_bats = 1; + __map_without_ltlbs = 1; + } +#endif } /* @@ -132,8 +138,6 @@ void __init MMU_init(void) * Reserve gigantic pages for hugetlb. This MUST occur before * lowmem_end_addr is initialized below. */ - reserve_hugetlb_gpages(); - if (memblock.memory.cnt > 1) { #ifndef CONFIG_WII memblock_enforce_memory_limit(memblock.memory.regions[0].size); diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 5b4c25d12ff3..588a521966ec 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -356,7 +356,7 @@ struct page *realmode_pfn_to_page(unsigned long pfn) } EXPORT_SYMBOL_GPL(realmode_pfn_to_page); -#elif defined(CONFIG_FLATMEM) +#else struct page *realmode_pfn_to_page(unsigned long pfn) { @@ -365,7 +365,7 @@ struct page *realmode_pfn_to_page(unsigned long pfn) } EXPORT_SYMBOL_GPL(realmode_pfn_to_page); -#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */ +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ #ifdef CONFIG_PPC_STD_MMU_64 static bool disable_radix; @@ -381,7 +381,7 @@ early_param("disable_radix", parse_disable_radix); * /chosen/ibm,architecture-vec-5 to see if the hypervisor is willing to do * radix. If not, we clear the radix feature bit so we fall back to hash. */ -static void early_check_vec5(void) +static void __init early_check_vec5(void) { unsigned long root, chosen; int size; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 46b4e67d2372..4362b86ef84c 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -436,7 +436,7 @@ void flush_dcache_icache_page(struct page *page) return; } #endif -#if defined(CONFIG_8xx) || defined(CONFIG_PPC64) +#if defined(CONFIG_PPC_8xx) || defined(CONFIG_PPC64) /* On 8xx there is no need to kmap since highmem is not supported */ __flush_dcache_icache(page_address(page)); #else diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c new file mode 100644 index 000000000000..0f613bc63c50 --- /dev/null +++ b/arch/powerpc/mm/mmu_context.c @@ -0,0 +1,99 @@ +/* + * Common implementation of switch_mm_irqs_off + * + * Copyright IBM Corp. 2017 + * + * 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/mm.h> +#include <linux/cpu.h> + +#include <asm/mmu_context.h> + +#if defined(CONFIG_PPC32) +static inline void switch_mm_pgdir(struct task_struct *tsk, + struct mm_struct *mm) +{ + /* 32-bit keeps track of the current PGDIR in the thread struct */ + tsk->thread.pgdir = mm->pgd; +} +#elif defined(CONFIG_PPC_BOOK3E_64) +static inline void switch_mm_pgdir(struct task_struct *tsk, + struct mm_struct *mm) +{ + /* 64-bit Book3E keeps track of current PGD in the PACA */ + get_paca()->pgd = mm->pgd; +} +#else +static inline void switch_mm_pgdir(struct task_struct *tsk, + struct mm_struct *mm) { } +#endif + +#ifdef CONFIG_PPC_BOOK3S_64 +static inline void inc_mm_active_cpus(struct mm_struct *mm) +{ + atomic_inc(&mm->context.active_cpus); +} +#else +static inline void inc_mm_active_cpus(struct mm_struct *mm) { } +#endif + +void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + bool new_on_cpu = false; + + /* Mark this context has been used on the new CPU */ + if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) { + cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); + inc_mm_active_cpus(next); + + /* + * This full barrier orders the store to the cpumask above vs + * a subsequent operation which allows this CPU to begin loading + * translations for next. + * + * When using the radix MMU that operation is the load of the + * MMU context id, which is then moved to SPRN_PID. + * + * For the hash MMU it is either the first load from slb_cache + * in switch_slb(), and/or the store of paca->mm_ctx_id in + * copy_mm_to_paca(). + * + * On the read side the barrier is in pte_xchg(), which orders + * the store to the PTE vs the load of mm_cpumask. + */ + smp_mb(); + + new_on_cpu = true; + } + + /* Some subarchs need to track the PGD elsewhere */ + switch_mm_pgdir(tsk, next); + + /* Nothing else to do if we aren't actually switching */ + if (prev == next) + return; + + /* + * We must stop all altivec streams before changing the HW + * context + */ + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + asm volatile ("dssall"); + + if (new_on_cpu) + radix_kvm_prefetch_workaround(next); + + /* + * The actual HW switching method differs between the various + * sub architectures. Out of line for now + */ + switch_mmu_context(prev, next, tsk); +} + diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index a75f63833284..05e15386d4cb 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -25,8 +25,6 @@ #include <asm/mmu_context.h> #include <asm/pgalloc.h> -#include "icswx.h" - static DEFINE_SPINLOCK(mmu_context_lock); static DEFINE_IDA(mmu_context_ida); @@ -165,16 +163,6 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) return index; mm->context.id = index; -#ifdef CONFIG_PPC_ICSWX - mm->context.cop_lockp = kmalloc(sizeof(spinlock_t), GFP_KERNEL); - if (!mm->context.cop_lockp) { - __destroy_context(index); - subpage_prot_free(mm); - mm->context.id = MMU_NO_CONTEXT; - return -ENOMEM; - } - spin_lock_init(mm->context.cop_lockp); -#endif /* CONFIG_PPC_ICSWX */ #ifdef CONFIG_PPC_64K_PAGES mm->context.pte_frag = NULL; @@ -182,6 +170,8 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) #ifdef CONFIG_SPAPR_TCE_IOMMU mm_iommu_init(mm); #endif + atomic_set(&mm->context.active_cpus, 0); + return 0; } @@ -226,12 +216,6 @@ void destroy_context(struct mm_struct *mm) #ifdef CONFIG_SPAPR_TCE_IOMMU WARN_ON_ONCE(!list_empty(&mm->context.iommu_group_mem_list)); #endif -#ifdef CONFIG_PPC_ICSWX - drop_cop(mm->context.acop, mm); - kfree(mm->context.cop_lockp); - mm->context.cop_lockp = NULL; -#endif /* CONFIG_PPC_ICSWX */ - if (radix_enabled()) { /* * Radix doesn't have a valid bit in the process table diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index d46128b22150..57fbc554c785 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -27,7 +27,7 @@ /* * On 40x and 8xx, we directly inline tlbia and tlbivax */ -#if defined(CONFIG_40x) || defined(CONFIG_8xx) +#if defined(CONFIG_40x) || defined(CONFIG_PPC_8xx) static inline void _tlbil_all(void) { asm volatile ("sync; tlbia; isync" : : : "memory"); @@ -38,7 +38,7 @@ static inline void _tlbil_pid(unsigned int pid) } #define _tlbil_pid_noind(pid) _tlbil_pid(pid) -#else /* CONFIG_40x || CONFIG_8xx */ +#else /* CONFIG_40x || CONFIG_PPC_8xx */ extern void _tlbil_all(void); extern void _tlbil_pid(unsigned int pid); #ifdef CONFIG_PPC_BOOK3E @@ -46,12 +46,12 @@ extern void _tlbil_pid_noind(unsigned int pid); #else #define _tlbil_pid_noind(pid) _tlbil_pid(pid) #endif -#endif /* !(CONFIG_40x || CONFIG_8xx) */ +#endif /* !(CONFIG_40x || CONFIG_PPC_8xx) */ /* * On 8xx, we directly inline tlbie, on others, it's extern */ -#ifdef CONFIG_8xx +#ifdef CONFIG_PPC_8xx static inline void _tlbil_va(unsigned long address, unsigned int pid, unsigned int tsize, unsigned int ind) { @@ -67,7 +67,7 @@ static inline void _tlbil_va(unsigned long address, unsigned int pid, { __tlbil_va(address, pid); } -#endif /* CONFIG_8xx */ +#endif /* CONFIG_PPC_8xx */ #if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_PPC_47x) extern void _tlbivax_bcast(unsigned long address, unsigned int pid, diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 31eed8fa8e99..3b65917785a5 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/mm_types.h> +#include <misc/cxl-base.h> #include <asm/pgalloc.h> #include <asm/tlb.h> @@ -64,6 +65,27 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, trace_hugepage_set_pmd(addr, pmd_val(pmd)); return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } + +static void do_nothing(void *unused) +{ + +} +/* + * Serialize against find_current_mm_pte which does lock-less + * lookup in page tables with local interrupts disabled. For huge pages + * it casts pmd_t to pte_t. Since format of pte_t is different from + * pmd_t we want to prevent transit from pmd pointing to page table + * to pmd pointing to huge page (and back) while interrupts are disabled. + * We clear pmd to possibly replace it with page table pointer in + * different code paths. So make sure we wait for the parallel + * find_current_mm_pte to finish. + */ +void serialize_against_pte_lookup(struct mm_struct *mm) +{ + smp_mb(); + smp_call_function_many(mm_cpumask(mm), do_nothing, NULL, 1); +} + /* * We use this to invalidate a pmdp entry before switching from a * hugepte to regular pmd entry. @@ -77,7 +99,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, * This ensures that generic code that rely on IRQ disabling * to prevent a parallel THP split work as expected. */ - kick_all_cpus_sync(); + serialize_against_pte_lookup(vma->vm_mm); } static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot) diff --git a/arch/powerpc/mm/pgtable-hash64.c b/arch/powerpc/mm/pgtable-hash64.c index 443a2c66a304..ec277913e01b 100644 --- a/arch/powerpc/mm/pgtable-hash64.c +++ b/arch/powerpc/mm/pgtable-hash64.c @@ -239,7 +239,7 @@ pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addres * by sending an IPI to all the cpus and executing a dummy * function there. */ - kick_all_cpus_sync(); + serialize_against_pte_lookup(vma->vm_mm); /* * Now invalidate the hpte entries in the range * covered by pmd. This make sure we take a @@ -329,7 +329,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, unsigned int psize; unsigned long vsid; unsigned long flags = 0; - const struct cpumask *tmp; /* get the base page size,vsid and segment size */ #ifdef CONFIG_DEBUG_VM @@ -350,8 +349,7 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, ssize = mmu_kernel_ssize; } - tmp = cpumask_of(smp_processor_id()); - if (cpumask_equal(mm_cpumask(mm), tmp)) + if (mm_is_thread_local(mm)) flags |= HPTE_LOCAL_UPDATE; return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, flags); @@ -380,16 +378,16 @@ pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm, */ memset(pgtable, 0, PTE_FRAG_SIZE); /* - * Serialize against find_linux_pte_or_hugepte which does lock-less + * Serialize against find_current_mm_pte variants which does lock-less * lookup in page tables with local interrupts disabled. For huge pages * it casts pmd_t to pte_t. Since format of pte_t is different from * pmd_t we want to prevent transit from pmd pointing to page table * to pmd pointing to huge page (and back) while interrupts are disabled. * We clear pmd to possibly replace it with page table pointer in * different code paths. So make sure we wait for the parallel - * find_linux_pte_or_hugepage to finish. + * find_curren_mm_pte to finish. */ - kick_all_cpus_sync(); + serialize_against_pte_lookup(mm); return old_pmd; } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 671a45d86c18..39c252b54d16 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -8,10 +8,15 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ + +#define pr_fmt(fmt) "radix-mmu: " fmt + +#include <linux/kernel.h> #include <linux/sched/mm.h> #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/mm.h> +#include <linux/string_helpers.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -31,9 +36,13 @@ unsigned int mmu_base_pid; static int native_register_process_table(unsigned long base, unsigned long pg_sz, unsigned long table_size) { - unsigned long patb1 = base | table_size | PATB_GR; + unsigned long patb0, patb1; + + patb0 = be64_to_cpu(partition_tb[0].patb0); + patb1 = base | table_size | PATB_GR; + + mmu_partition_table_set_entry(0, patb0, patb1); - partition_tb->patb1 = cpu_to_be64(patb1); return 0; } @@ -179,10 +188,14 @@ static inline void __meminit print_mapping(unsigned long start, unsigned long end, unsigned long size) { + char buf[10]; + if (end <= start) return; - pr_info("Mapped range 0x%lx - 0x%lx with 0x%lx\n", start, end, size); + string_get_size(size, 1, STRING_UNITS_2, buf, sizeof(buf)); + + pr_info("Mapped 0x%016lx-0x%016lx with %s pages\n", start, end, buf); } static int __meminit create_physical_mapping(unsigned long start, @@ -526,6 +539,7 @@ void __init radix__early_init_mmu(void) __kernel_virt_size = RADIX_KERN_VIRT_SIZE; __vmalloc_start = RADIX_VMALLOC_START; __vmalloc_end = RADIX_VMALLOC_END; + __kernel_io_start = RADIX_KERN_IO_START; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; @@ -836,9 +850,12 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre */ pmd = *pmdp; pmd_clear(pmdp); + /*FIXME!! Verify whether we need this kick below */ - kick_all_cpus_sync(); - flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + serialize_against_pte_lookup(vma->vm_mm); + + radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); + return pmd; } @@ -897,16 +914,16 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm, old = radix__pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); old_pmd = __pmd(old); /* - * Serialize against find_linux_pte_or_hugepte which does lock-less + * Serialize against find_current_mm_pte which does lock-less * lookup in page tables with local interrupts disabled. For huge pages * it casts pmd_t to pte_t. Since format of pte_t is different from * pmd_t we want to prevent transit from pmd pointing to page table * to pmd pointing to huge page (and back) while interrupts are disabled. * We clear pmd to possibly replace it with page table pointer in * different code paths. So make sure we wait for the parallel - * find_linux_pte_or_hugepage to finish. + * find_current_mm_pte to finish. */ - kick_all_cpus_sync(); + serialize_against_pte_lookup(mm); return old_pmd; } diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index a9e4bfc025bc..65eda1997c3f 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -34,6 +34,7 @@ #include <asm/fixmap.h> #include <asm/io.h> #include <asm/setup.h> +#include <asm/sections.h> #include "mmu_decl.h" @@ -242,7 +243,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, int flags) /* * Map in a chunk of physical memory starting at start. */ -void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) +static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) { unsigned long v, s, f; phys_addr_t p; @@ -294,7 +295,7 @@ void __init mapin_ram(void) * Returns true (1) if PTE was found, zero otherwise. The pointer to * the PTE pointer is unmodified if PTE is not found. */ -int +static int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp) { pgd_t *pgd; @@ -323,9 +324,7 @@ get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp) return(retval); } -#ifdef CONFIG_DEBUG_PAGEALLOC - -static int __change_page_attr(struct page *page, pgprot_t prot) +static int __change_page_attr_noflush(struct page *page, pgprot_t prot) { pte_t *kpte; pmd_t *kpmd; @@ -339,8 +338,6 @@ static int __change_page_attr(struct page *page, pgprot_t prot) if (!get_pteptr(&init_mm, address, &kpte, &kpmd)) return -EINVAL; __set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0); - wmb(); - flush_tlb_page(NULL, address); pte_unmap(kpte); return 0; @@ -349,44 +346,65 @@ static int __change_page_attr(struct page *page, pgprot_t prot) /* * Change the page attributes of an page in the linear mapping. * - * THIS CONFLICTS WITH BAT MAPPINGS, DEBUG USE ONLY + * THIS DOES NOTHING WITH BAT MAPPINGS, DEBUG USE ONLY */ static int change_page_attr(struct page *page, int numpages, pgprot_t prot) { int i, err = 0; unsigned long flags; + struct page *start = page; local_irq_save(flags); for (i = 0; i < numpages; i++, page++) { - err = __change_page_attr(page, prot); + err = __change_page_attr_noflush(page, prot); if (err) break; } + wmb(); + flush_tlb_kernel_range((unsigned long)page_address(start), + (unsigned long)page_address(page)); local_irq_restore(flags); return err; } - -void __kernel_map_pages(struct page *page, int numpages, int enable) +void mark_initmem_nx(void) { - if (PageHighMem(page)) - return; + struct page *page = virt_to_page(_sinittext); + unsigned long numpages = PFN_UP((unsigned long)_einittext) - + PFN_DOWN((unsigned long)_sinittext); - change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0)); + change_page_attr(page, numpages, PAGE_KERNEL); } -#endif /* CONFIG_DEBUG_PAGEALLOC */ -static int fixmaps; - -void __set_fixmap (enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) +#ifdef CONFIG_STRICT_KERNEL_RWX +void mark_rodata_ro(void) { - unsigned long address = __fix_to_virt(idx); + struct page *page; + unsigned long numpages; + + page = virt_to_page(_stext); + numpages = PFN_UP((unsigned long)_etext) - + PFN_DOWN((unsigned long)_stext); - if (idx >= __end_of_fixed_addresses) { - BUG(); + change_page_attr(page, numpages, PAGE_KERNEL_ROX); + /* + * mark .rodata as read only. Use __init_begin rather than __end_rodata + * to cover NOTES and EXCEPTION_TABLE. + */ + page = virt_to_page(__start_rodata); + numpages = PFN_UP((unsigned long)__init_begin) - + PFN_DOWN((unsigned long)__start_rodata); + + change_page_attr(page, numpages, PAGE_KERNEL_RO); +} +#endif + +#ifdef CONFIG_DEBUG_PAGEALLOC +void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + if (PageHighMem(page)) return; - } - map_kernel_page(address, phys, pgprot_val(flags)); - fixmaps++; + change_page_attr(page, numpages, enable ? PAGE_KERNEL : __pgprot(0)); } +#endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 0736e94c7615..ac0717a90ca6 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -104,6 +104,8 @@ unsigned long __vmalloc_start; EXPORT_SYMBOL(__vmalloc_start); unsigned long __vmalloc_end; EXPORT_SYMBOL(__vmalloc_end); +unsigned long __kernel_io_start; +EXPORT_SYMBOL(__kernel_io_start); struct page *vmemmap; EXPORT_SYMBOL(vmemmap); unsigned long __pte_frag_nr; diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index bde378559d01..906a86fe457b 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -121,12 +121,25 @@ slb_miss_kernel_load_vmemmap: 1: #endif /* CONFIG_SPARSEMEM_VMEMMAP */ - /* vmalloc mapping gets the encoding from the PACA as the mapping - * can be demoted from 64K -> 4K dynamically on some machines + /* + * r10 contains the ESID, which is the original faulting EA shifted + * right by 28 bits. We need to compare that with (H_VMALLOC_END >> 28) + * which is 0xd00038000. That can't be used as an immediate, even if we + * ignored the 0xd, so we have to load it into a register, and we only + * have one register free. So we must load all of (H_VMALLOC_END >> 28) + * into a register and compare ESID against that. + */ + lis r11,(H_VMALLOC_END >> 32)@h // r11 = 0xffffffffd0000000 + ori r11,r11,(H_VMALLOC_END >> 32)@l // r11 = 0xffffffffd0003800 + // Rotate left 4, then mask with 0xffffffff0 + rldic r11,r11,4,28 // r11 = 0xd00038000 + cmpld r10,r11 // if r10 >= r11 + bge 5f // goto io_mapping + + /* + * vmalloc mapping gets the encoding from the PACA as the mapping + * can be demoted from 64K -> 4K dynamically on some machines. */ - clrldi r11,r10,48 - cmpldi r11,(H_VMALLOC_SIZE >> 28) - 1 - bgt 5f lhz r11,PACAVMALLOCSLLP(r13) b 6f 5: diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 16ae1bbe13f0..b3e849c4886e 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -54,23 +54,15 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) */ __tlbiel_pid(pid, 0, ric); - if (ric == RIC_FLUSH_ALL) - /* For the remaining sets, just flush the TLB */ - ric = RIC_FLUSH_TLB; + /* For PWC, only one flush is needed */ + if (ric == RIC_FLUSH_PWC) { + asm volatile("ptesync": : :"memory"); + return; + } + /* For the remaining sets, just flush the TLB */ for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) - __tlbiel_pid(pid, set, ric); - - asm volatile("ptesync": : :"memory"); - asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); -} - -static inline void tlbiel_pwc(unsigned long pid) -{ - asm volatile("ptesync": : :"memory"); - - /* For PWC flush, we don't look at set number */ - __tlbiel_pid(pid, 0, RIC_FLUSH_PWC); + __tlbiel_pid(pid, set, RIC_FLUSH_TLB); asm volatile("ptesync": : :"memory"); asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); @@ -146,31 +138,23 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm) preempt_disable(); pid = mm->context.id; if (pid != MMU_NO_CONTEXT) - _tlbiel_pid(pid, RIC_FLUSH_ALL); + _tlbiel_pid(pid, RIC_FLUSH_TLB); preempt_enable(); } EXPORT_SYMBOL(radix__local_flush_tlb_mm); -void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +#ifndef CONFIG_SMP +static void radix__local_flush_all_mm(struct mm_struct *mm) { unsigned long pid; - struct mm_struct *mm = tlb->mm; - /* - * If we are doing a full mm flush, we will do a tlb flush - * with RIC_FLUSH_ALL later. - */ - if (tlb->fullmm) - return; preempt_disable(); - pid = mm->context.id; if (pid != MMU_NO_CONTEXT) - tlbiel_pwc(pid); - + _tlbiel_pid(pid, RIC_FLUSH_ALL); preempt_enable(); } -EXPORT_SYMBOL(radix__local_flush_tlb_pwc); +#endif /* CONFIG_SMP */ void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, int psize) @@ -208,38 +192,35 @@ void radix__flush_tlb_mm(struct mm_struct *mm) goto no_context; if (!mm_is_thread_local(mm)) - _tlbie_pid(pid, RIC_FLUSH_ALL); + _tlbie_pid(pid, RIC_FLUSH_TLB); else - _tlbiel_pid(pid, RIC_FLUSH_ALL); + _tlbiel_pid(pid, RIC_FLUSH_TLB); no_context: preempt_enable(); } EXPORT_SYMBOL(radix__flush_tlb_mm); -void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +static void radix__flush_all_mm(struct mm_struct *mm) { unsigned long pid; - struct mm_struct *mm = tlb->mm; - /* - * If we are doing a full mm flush, we will do a tlb flush - * with RIC_FLUSH_ALL later. - */ - if (tlb->fullmm) - return; preempt_disable(); - pid = mm->context.id; if (unlikely(pid == MMU_NO_CONTEXT)) goto no_context; if (!mm_is_thread_local(mm)) - _tlbie_pid(pid, RIC_FLUSH_PWC); + _tlbie_pid(pid, RIC_FLUSH_ALL); else - tlbiel_pwc(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); no_context: preempt_enable(); } + +void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + tlb->need_flush_all = 1; +} EXPORT_SYMBOL(radix__flush_tlb_pwc); void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, @@ -271,6 +252,8 @@ void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr) } EXPORT_SYMBOL(radix__flush_tlb_page); +#else /* CONFIG_SMP */ +#define radix__flush_all_mm radix__local_flush_all_mm #endif /* CONFIG_SMP */ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) @@ -288,6 +271,7 @@ void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start, { struct mm_struct *mm = vma->vm_mm; + radix__flush_tlb_mm(mm); } EXPORT_SYMBOL(radix__flush_tlb_range); @@ -319,7 +303,10 @@ void radix__tlb_flush(struct mmu_gather *tlb) */ if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all) radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize); - else + else if (tlb->need_flush_all) { + tlb->need_flush_all = 0; + radix__flush_all_mm(mm); + } else radix__flush_tlb_mm(mm); } @@ -364,6 +351,43 @@ err_out: preempt_enable(); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr) +{ + int local = mm_is_thread_local(mm); + unsigned long ap = mmu_get_ap(mmu_virtual_psize); + unsigned long pid, end; + + + pid = mm ? mm->context.id : 0; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto no_context; + + /* 4k page size, just blow the world */ + if (PAGE_SIZE == 0x1000) { + radix__flush_all_mm(mm); + return; + } + + /* Otherwise first do the PWC */ + if (local) + _tlbiel_pid(pid, RIC_FLUSH_PWC); + else + _tlbie_pid(pid, RIC_FLUSH_PWC); + + /* Then iterate the pages */ + end = addr + HPAGE_PMD_SIZE; + for (; addr < end; addr += PAGE_SIZE) { + if (local) + _tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB); + else + _tlbie_va(addr, pid, ap, RIC_FLUSH_TLB); + } +no_context: + preempt_enable(); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa, unsigned long page_size) { diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c index b5b0fb97b9c0..881ebd53ffc2 100644 --- a/arch/powerpc/mm/tlb_hash64.c +++ b/arch/powerpc/mm/tlb_hash64.c @@ -29,6 +29,8 @@ #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/bug.h> +#include <asm/pte-walk.h> + #include <trace/events/thp.h> @@ -138,13 +140,10 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, */ void __flush_tlb_pending(struct ppc64_tlb_batch *batch) { - const struct cpumask *tmp; - int i, local = 0; + int i, local; i = batch->index; - tmp = cpumask_of(smp_processor_id()); - if (cpumask_equal(mm_cpumask(batch->mm), tmp)) - local = 1; + local = mm_is_thread_local(batch->mm); if (i == 1) flush_hash_page(batch->vpn[0], batch->pte[0], batch->psize, batch->ssize, local); @@ -207,8 +206,8 @@ void __flush_hash_table_range(struct mm_struct *mm, unsigned long start, local_irq_save(flags); arch_enter_lazy_mmu_mode(); for (; start < end; start += PAGE_SIZE) { - pte_t *ptep = find_linux_pte_or_hugepte(mm->pgd, start, &is_thp, - &hugepage_shift); + pte_t *ptep = find_current_mm_pte(mm->pgd, start, &is_thp, + &hugepage_shift); unsigned long pte; if (ptep == NULL) diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S index eabecfcaef7c..048b8e9f4492 100644 --- a/arch/powerpc/mm/tlb_nohash_low.S +++ b/arch/powerpc/mm/tlb_nohash_low.S @@ -60,7 +60,7 @@ _GLOBAL(__tlbil_va) isync 1: blr -#elif defined(CONFIG_8xx) +#elif defined(CONFIG_PPC_8xx) /* * Nothing to do for 8xx, everything is inline diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 30cf03f53428..47fc6660845d 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -263,6 +263,7 @@ static inline bool is_nearbranch(int offset) #define COND_EQ (CR0_EQ | COND_CMP_TRUE) #define COND_NE (CR0_EQ | COND_CMP_FALSE) #define COND_LT (CR0_LT | COND_CMP_TRUE) +#define COND_LE (CR0_GT | COND_CMP_FALSE) #endif diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 861c5af1c9c4..a66e64b0b251 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -25,11 +25,7 @@ int bpf_jit_enable __read_mostly; static void bpf_jit_fill_ill_insns(void *area, unsigned int size) { - int *p = area; - - /* Fill whole space with trap instructions */ - while (p < (int *)((char *)area + size)) - *p++ = BREAKPOINT_INSTRUCTION; + memset32(area, BREAKPOINT_INSTRUCTION, size/4); } static inline void bpf_flush_icache(void *start, void *end) @@ -795,12 +791,24 @@ emit_clear: case BPF_JMP | BPF_JSGT | BPF_X: true_cond = COND_GT; goto cond_branch; + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_X: + true_cond = COND_LT; + goto cond_branch; case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSGE | BPF_X: true_cond = COND_GE; goto cond_branch; + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_X: + true_cond = COND_LE; + goto cond_branch; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: true_cond = COND_EQ; @@ -817,14 +825,18 @@ emit_clear: cond_branch: switch (code) { case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: /* unsigned comparison */ PPC_CMPLD(dst_reg, src_reg); break; case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: /* signed comparison */ PPC_CMPD(dst_reg, src_reg); break; @@ -834,7 +846,9 @@ cond_branch: case BPF_JMP | BPF_JNE | BPF_K: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: /* * Need sign-extended load, so only positive * values can be used as imm in cmpldi @@ -849,7 +863,9 @@ cond_branch: } break; case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: /* * signed comparison, so any 16-bit value * can be used in cmpdi diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 4d606b99a5cb..3f3a5ce66495 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -8,6 +8,7 @@ obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \ isa207-common.o power8-pmu.o power9-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o +obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o e6500-pmu.o diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c index 0fc26714780a..0af051a1974e 100644 --- a/arch/powerpc/perf/callchain.c +++ b/arch/powerpc/perf/callchain.c @@ -22,6 +22,7 @@ #ifdef CONFIG_PPC64 #include "../kernel/ppc32.h" #endif +#include <asm/pte-walk.h> /* @@ -127,7 +128,7 @@ static int read_user_stack_slow(void __user *ptr, void *buf, int nb) return -EFAULT; local_irq_save(flags); - ptep = find_linux_pte_or_hugepte(pgdir, addr, NULL, &shift); + ptep = find_current_mm_pte(pgdir, addr, NULL, &shift); if (!ptep) goto err_out; if (!shift) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 6c2d4168daec..2e3eb7431571 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2039,7 +2039,8 @@ static void record_and_restart(struct perf_event *event, unsigned long val, perf_sample_data_init(&data, ~0ULL, event->hw.last_period); - if (event->attr.sample_type & PERF_SAMPLE_ADDR) + if (event->attr.sample_type & + (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR)) perf_get_data_addr(regs, &data.addr); if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) { diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c new file mode 100644 index 000000000000..9ccac86f3463 --- /dev/null +++ b/arch/powerpc/perf/imc-pmu.c @@ -0,0 +1,1306 @@ +/* + * In-Memory Collection (IMC) Performance Monitor counter support. + * + * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation. + * (C) 2017 Anju T Sudhakar, IBM Corporation. + * (C) 2017 Hemant K Shaw, IBM Corporation. + * + * 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 later version. + */ +#include <linux/perf_event.h> +#include <linux/slab.h> +#include <asm/opal.h> +#include <asm/imc-pmu.h> +#include <asm/cputhreads.h> +#include <asm/smp.h> +#include <linux/string.h> + +/* Nest IMC data structures and variables */ + +/* + * Used to avoid races in counting the nest-pmu units during hotplug + * register and unregister + */ +static DEFINE_MUTEX(nest_init_lock); +static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); +static struct imc_pmu *per_nest_pmu_arr[IMC_MAX_PMUS]; +static cpumask_t nest_imc_cpumask; +struct imc_pmu_ref *nest_imc_refc; +static int nest_pmus; + +/* Core IMC data structures and variables */ + +static cpumask_t core_imc_cpumask; +struct imc_pmu_ref *core_imc_refc; +static struct imc_pmu *core_imc_pmu; + +/* Thread IMC data structures and variables */ + +static DEFINE_PER_CPU(u64 *, thread_imc_mem); +static struct imc_pmu *thread_imc_pmu; +static int thread_imc_mem_size; + +struct imc_pmu *imc_event_to_pmu(struct perf_event *event) +{ + return container_of(event->pmu, struct imc_pmu, pmu); +} + +PMU_FORMAT_ATTR(event, "config:0-40"); +PMU_FORMAT_ATTR(offset, "config:0-31"); +PMU_FORMAT_ATTR(rvalue, "config:32"); +PMU_FORMAT_ATTR(mode, "config:33-40"); +static struct attribute *imc_format_attrs[] = { + &format_attr_event.attr, + &format_attr_offset.attr, + &format_attr_rvalue.attr, + &format_attr_mode.attr, + NULL, +}; + +static struct attribute_group imc_format_group = { + .name = "format", + .attrs = imc_format_attrs, +}; + +/* Get the cpumask printed to a buffer "buf" */ +static ssize_t imc_pmu_cpumask_get_attr(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pmu *pmu = dev_get_drvdata(dev); + struct imc_pmu *imc_pmu = container_of(pmu, struct imc_pmu, pmu); + cpumask_t *active_mask; + + switch(imc_pmu->domain){ + case IMC_DOMAIN_NEST: + active_mask = &nest_imc_cpumask; + break; + case IMC_DOMAIN_CORE: + active_mask = &core_imc_cpumask; + break; + default: + return 0; + } + + return cpumap_print_to_pagebuf(true, buf, active_mask); +} + +static DEVICE_ATTR(cpumask, S_IRUGO, imc_pmu_cpumask_get_attr, NULL); + +static struct attribute *imc_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group imc_pmu_cpumask_attr_group = { + .attrs = imc_pmu_cpumask_attrs, +}; + +/* device_str_attr_create : Populate event "name" and string "str" in attribute */ +static struct attribute *device_str_attr_create(const char *name, const char *str) +{ + struct perf_pmu_events_attr *attr; + + attr = kzalloc(sizeof(*attr), GFP_KERNEL); + if (!attr) + return NULL; + sysfs_attr_init(&attr->attr.attr); + + attr->event_str = str; + attr->attr.attr.name = name; + attr->attr.attr.mode = 0444; + attr->attr.show = perf_event_sysfs_show; + + return &attr->attr.attr; +} + +struct imc_events *imc_parse_event(struct device_node *np, const char *scale, + const char *unit, const char *prefix, u32 base) +{ + struct imc_events *event; + const char *s; + u32 reg; + + event = kzalloc(sizeof(struct imc_events), GFP_KERNEL); + if (!event) + return NULL; + + if (of_property_read_u32(np, "reg", ®)) + goto error; + /* Add the base_reg value to the "reg" */ + event->value = base + reg; + + if (of_property_read_string(np, "event-name", &s)) + goto error; + + event->name = kasprintf(GFP_KERNEL, "%s%s", prefix, s); + if (!event->name) + goto error; + + if (of_property_read_string(np, "scale", &s)) + s = scale; + + if (s) { + event->scale = kstrdup(s, GFP_KERNEL); + if (!event->scale) + goto error; + } + + if (of_property_read_string(np, "unit", &s)) + s = unit; + + if (s) { + event->unit = kstrdup(s, GFP_KERNEL); + if (!event->unit) + goto error; + } + + return event; +error: + kfree(event->unit); + kfree(event->scale); + kfree(event->name); + kfree(event); + + return NULL; +} + +/* + * update_events_in_group: Update the "events" information in an attr_group + * and assign the attr_group to the pmu "pmu". + */ +static int update_events_in_group(struct device_node *node, struct imc_pmu *pmu) +{ + struct attribute_group *attr_group; + struct attribute **attrs, *dev_str; + struct device_node *np, *pmu_events; + struct imc_events *ev; + u32 handle, base_reg; + int i=0, j=0, ct; + const char *prefix, *g_scale, *g_unit; + const char *ev_val_str, *ev_scale_str, *ev_unit_str; + + if (!of_property_read_u32(node, "events", &handle)) + pmu_events = of_find_node_by_phandle(handle); + else + return 0; + + /* Did not find any node with a given phandle */ + if (!pmu_events) + return 0; + + /* Get a count of number of child nodes */ + ct = of_get_child_count(pmu_events); + + /* Get the event prefix */ + if (of_property_read_string(node, "events-prefix", &prefix)) + return 0; + + /* Get a global unit and scale data if available */ + if (of_property_read_string(node, "scale", &g_scale)) + g_scale = NULL; + + if (of_property_read_string(node, "unit", &g_unit)) + g_unit = NULL; + + /* "reg" property gives out the base offset of the counters data */ + of_property_read_u32(node, "reg", &base_reg); + + /* Allocate memory for the events */ + pmu->events = kcalloc(ct, sizeof(struct imc_events), GFP_KERNEL); + if (!pmu->events) + return -ENOMEM; + + ct = 0; + /* Parse the events and update the struct */ + for_each_child_of_node(pmu_events, np) { + ev = imc_parse_event(np, g_scale, g_unit, prefix, base_reg); + if (ev) + pmu->events[ct++] = ev; + } + + /* Allocate memory for attribute group */ + attr_group = kzalloc(sizeof(*attr_group), GFP_KERNEL); + if (!attr_group) + return -ENOMEM; + + /* + * Allocate memory for attributes. + * Since we have count of events for this pmu, we also allocate + * memory for the scale and unit attribute for now. + * "ct" has the total event structs added from the events-parent node. + * So allocate three times the "ct" (this includes event, event_scale and + * event_unit). + */ + attrs = kcalloc(((ct * 3) + 1), sizeof(struct attribute *), GFP_KERNEL); + if (!attrs) { + kfree(attr_group); + kfree(pmu->events); + return -ENOMEM; + } + + attr_group->name = "events"; + attr_group->attrs = attrs; + do { + ev_val_str = kasprintf(GFP_KERNEL, "event=0x%x", pmu->events[i]->value); + dev_str = device_str_attr_create(pmu->events[i]->name, ev_val_str); + if (!dev_str) + continue; + + attrs[j++] = dev_str; + if (pmu->events[i]->scale) { + ev_scale_str = kasprintf(GFP_KERNEL, "%s.scale",pmu->events[i]->name); + dev_str = device_str_attr_create(ev_scale_str, pmu->events[i]->scale); + if (!dev_str) + continue; + + attrs[j++] = dev_str; + } + + if (pmu->events[i]->unit) { + ev_unit_str = kasprintf(GFP_KERNEL, "%s.unit",pmu->events[i]->name); + dev_str = device_str_attr_create(ev_unit_str, pmu->events[i]->unit); + if (!dev_str) + continue; + + attrs[j++] = dev_str; + } + } while (++i < ct); + + /* Save the event attribute */ + pmu->attr_groups[IMC_EVENT_ATTR] = attr_group; + + kfree(pmu->events); + return 0; +} + +/* get_nest_pmu_ref: Return the imc_pmu_ref struct for the given node */ +static struct imc_pmu_ref *get_nest_pmu_ref(int cpu) +{ + return per_cpu(local_nest_imc_refc, cpu); +} + +static void nest_change_cpu_context(int old_cpu, int new_cpu) +{ + struct imc_pmu **pn = per_nest_pmu_arr; + int i; + + if (old_cpu < 0 || new_cpu < 0) + return; + + for (i = 0; *pn && i < IMC_MAX_PMUS; i++, pn++) + perf_pmu_migrate_context(&(*pn)->pmu, old_cpu, new_cpu); +} + +static int ppc_nest_imc_cpu_offline(unsigned int cpu) +{ + int nid, target = -1; + const struct cpumask *l_cpumask; + struct imc_pmu_ref *ref; + + /* + * Check in the designated list for this cpu. Dont bother + * if not one of them. + */ + if (!cpumask_test_and_clear_cpu(cpu, &nest_imc_cpumask)) + return 0; + + /* + * Now that this cpu is one of the designated, + * find a next cpu a) which is online and b) in same chip. + */ + nid = cpu_to_node(cpu); + l_cpumask = cpumask_of_node(nid); + target = cpumask_any_but(l_cpumask, cpu); + + /* + * Update the cpumask with the target cpu and + * migrate the context if needed + */ + if (target >= 0 && target < nr_cpu_ids) { + cpumask_set_cpu(target, &nest_imc_cpumask); + nest_change_cpu_context(cpu, target); + } else { + opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, + get_hard_smp_processor_id(cpu)); + /* + * If this is the last cpu in this chip then, skip the reference + * count mutex lock and make the reference count on this chip zero. + */ + ref = get_nest_pmu_ref(cpu); + if (!ref) + return -EINVAL; + + ref->refc = 0; + } + return 0; +} + +static int ppc_nest_imc_cpu_online(unsigned int cpu) +{ + const struct cpumask *l_cpumask; + static struct cpumask tmp_mask; + int res; + + /* Get the cpumask of this node */ + l_cpumask = cpumask_of_node(cpu_to_node(cpu)); + + /* + * If this is not the first online CPU on this node, then + * just return. + */ + if (cpumask_and(&tmp_mask, l_cpumask, &nest_imc_cpumask)) + return 0; + + /* + * If this is the first online cpu on this node + * disable the nest counters by making an OPAL call. + */ + res = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, + get_hard_smp_processor_id(cpu)); + if (res) + return res; + + /* Make this CPU the designated target for counter collection */ + cpumask_set_cpu(cpu, &nest_imc_cpumask); + return 0; +} + +static int nest_pmu_cpumask_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, + "perf/powerpc/imc:online", + ppc_nest_imc_cpu_online, + ppc_nest_imc_cpu_offline); +} + +static void nest_imc_counters_release(struct perf_event *event) +{ + int rc, node_id; + struct imc_pmu_ref *ref; + + if (event->cpu < 0) + return; + + node_id = cpu_to_node(event->cpu); + + /* + * See if we need to disable the nest PMU. + * If no events are currently in use, then we have to take a + * mutex to ensure that we don't race with another task doing + * enable or disable the nest counters. + */ + ref = get_nest_pmu_ref(event->cpu); + if (!ref) + return; + + /* Take the mutex lock for this node and then decrement the reference count */ + mutex_lock(&ref->lock); + ref->refc--; + if (ref->refc == 0) { + rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, + get_hard_smp_processor_id(event->cpu)); + if (rc) { + mutex_unlock(&ref->lock); + pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id); + return; + } + } else if (ref->refc < 0) { + WARN(1, "nest-imc: Invalid event reference count\n"); + ref->refc = 0; + } + mutex_unlock(&ref->lock); +} + +static int nest_imc_event_init(struct perf_event *event) +{ + int chip_id, rc, node_id; + u32 l_config, config = event->attr.config; + struct imc_mem_info *pcni; + struct imc_pmu *pmu; + struct imc_pmu_ref *ref; + bool flag = false; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* Sampling not supported */ + if (event->hw.sample_period) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + pmu = imc_event_to_pmu(event); + + /* Sanity check for config (event offset) */ + if ((config & IMC_EVENT_OFFSET_MASK) > pmu->counter_mem_size) + return -EINVAL; + + /* + * Nest HW counter memory resides in a per-chip reserve-memory (HOMER). + * Get the base memory addresss for this cpu. + */ + chip_id = topology_physical_package_id(event->cpu); + pcni = pmu->mem_info; + do { + if (pcni->id == chip_id) { + flag = true; + break; + } + pcni++; + } while (pcni); + + if (!flag) + return -ENODEV; + + /* + * Add the event offset to the base address. + */ + l_config = config & IMC_EVENT_OFFSET_MASK; + event->hw.event_base = (u64)pcni->vbase + l_config; + node_id = cpu_to_node(event->cpu); + + /* + * Get the imc_pmu_ref struct for this node. + * Take the mutex lock and then increment the count of nest pmu events + * inited. + */ + ref = get_nest_pmu_ref(event->cpu); + if (!ref) + return -EINVAL; + + mutex_lock(&ref->lock); + if (ref->refc == 0) { + rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST, + get_hard_smp_processor_id(event->cpu)); + if (rc) { + mutex_unlock(&ref->lock); + pr_err("nest-imc: Unable to start the counters for node %d\n", + node_id); + return rc; + } + } + ++ref->refc; + mutex_unlock(&ref->lock); + + event->destroy = nest_imc_counters_release; + return 0; +} + +/* + * core_imc_mem_init : Initializes memory for the current core. + * + * Uses alloc_pages_node() and uses the returned address as an argument to + * an opal call to configure the pdbar. The address sent as an argument is + * converted to physical address before the opal call is made. This is the + * base address at which the core imc counters are populated. + */ +static int core_imc_mem_init(int cpu, int size) +{ + int phys_id, rc = 0, core_id = (cpu / threads_per_core); + struct imc_mem_info *mem_info; + + /* + * alloc_pages_node() will allocate memory for core in the + * local node only. + */ + phys_id = topology_physical_package_id(cpu); + mem_info = &core_imc_pmu->mem_info[core_id]; + mem_info->id = core_id; + + /* We need only vbase for core counters */ + mem_info->vbase = page_address(alloc_pages_node(phys_id, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, + get_order(size))); + if (!mem_info->vbase) + return -ENOMEM; + + /* Init the mutex */ + core_imc_refc[core_id].id = core_id; + mutex_init(&core_imc_refc[core_id].lock); + + rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE, + __pa((void *)mem_info->vbase), + get_hard_smp_processor_id(cpu)); + if (rc) { + free_pages((u64)mem_info->vbase, get_order(size)); + mem_info->vbase = NULL; + } + + return rc; +} + +static bool is_core_imc_mem_inited(int cpu) +{ + struct imc_mem_info *mem_info; + int core_id = (cpu / threads_per_core); + + mem_info = &core_imc_pmu->mem_info[core_id]; + if (!mem_info->vbase) + return false; + + return true; +} + +static int ppc_core_imc_cpu_online(unsigned int cpu) +{ + const struct cpumask *l_cpumask; + static struct cpumask tmp_mask; + int ret = 0; + + /* Get the cpumask for this core */ + l_cpumask = cpu_sibling_mask(cpu); + + /* If a cpu for this core is already set, then, don't do anything */ + if (cpumask_and(&tmp_mask, l_cpumask, &core_imc_cpumask)) + return 0; + + if (!is_core_imc_mem_inited(cpu)) { + ret = core_imc_mem_init(cpu, core_imc_pmu->counter_mem_size); + if (ret) { + pr_info("core_imc memory allocation for cpu %d failed\n", cpu); + return ret; + } + } + + /* set the cpu in the mask */ + cpumask_set_cpu(cpu, &core_imc_cpumask); + return 0; +} + +static int ppc_core_imc_cpu_offline(unsigned int cpu) +{ + unsigned int ncpu, core_id; + struct imc_pmu_ref *ref; + + /* + * clear this cpu out of the mask, if not present in the mask, + * don't bother doing anything. + */ + if (!cpumask_test_and_clear_cpu(cpu, &core_imc_cpumask)) + return 0; + + /* Find any online cpu in that core except the current "cpu" */ + ncpu = cpumask_any_but(cpu_sibling_mask(cpu), cpu); + + if (ncpu >= 0 && ncpu < nr_cpu_ids) { + cpumask_set_cpu(ncpu, &core_imc_cpumask); + perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu); + } else { + /* + * If this is the last cpu in this core then, skip taking refernce + * count mutex lock for this core and directly zero "refc" for + * this core. + */ + opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(cpu)); + core_id = cpu / threads_per_core; + ref = &core_imc_refc[core_id]; + if (!ref) + return -EINVAL; + + ref->refc = 0; + } + return 0; +} + +static int core_imc_pmu_cpumask_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, + "perf/powerpc/imc_core:online", + ppc_core_imc_cpu_online, + ppc_core_imc_cpu_offline); +} + +static void core_imc_counters_release(struct perf_event *event) +{ + int rc, core_id; + struct imc_pmu_ref *ref; + + if (event->cpu < 0) + return; + /* + * See if we need to disable the IMC PMU. + * If no events are currently in use, then we have to take a + * mutex to ensure that we don't race with another task doing + * enable or disable the core counters. + */ + core_id = event->cpu / threads_per_core; + + /* Take the mutex lock and decrement the refernce count for this core */ + ref = &core_imc_refc[core_id]; + if (!ref) + return; + + mutex_lock(&ref->lock); + ref->refc--; + if (ref->refc == 0) { + rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(event->cpu)); + if (rc) { + mutex_unlock(&ref->lock); + pr_err("IMC: Unable to stop the counters for core %d\n", core_id); + return; + } + } else if (ref->refc < 0) { + WARN(1, "core-imc: Invalid event reference count\n"); + ref->refc = 0; + } + mutex_unlock(&ref->lock); +} + +static int core_imc_event_init(struct perf_event *event) +{ + int core_id, rc; + u64 config = event->attr.config; + struct imc_mem_info *pcmi; + struct imc_pmu *pmu; + struct imc_pmu_ref *ref; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* Sampling not supported */ + if (event->hw.sample_period) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + event->hw.idx = -1; + pmu = imc_event_to_pmu(event); + + /* Sanity check for config (event offset) */ + if (((config & IMC_EVENT_OFFSET_MASK) > pmu->counter_mem_size)) + return -EINVAL; + + if (!is_core_imc_mem_inited(event->cpu)) + return -ENODEV; + + core_id = event->cpu / threads_per_core; + pcmi = &core_imc_pmu->mem_info[core_id]; + if ((!pcmi->vbase)) + return -ENODEV; + + /* Get the core_imc mutex for this core */ + ref = &core_imc_refc[core_id]; + if (!ref) + return -EINVAL; + + /* + * Core pmu units are enabled only when it is used. + * See if this is triggered for the first time. + * If yes, take the mutex lock and enable the core counters. + * If not, just increment the count in core_imc_refc struct. + */ + mutex_lock(&ref->lock); + if (ref->refc == 0) { + rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(event->cpu)); + if (rc) { + mutex_unlock(&ref->lock); + pr_err("core-imc: Unable to start the counters for core %d\n", + core_id); + return rc; + } + } + ++ref->refc; + mutex_unlock(&ref->lock); + + event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); + event->destroy = core_imc_counters_release; + return 0; +} + +/* + * Allocates a page of memory for each of the online cpus, and write the + * physical base address of that page to the LDBAR for that cpu. + * + * LDBAR Register Layout: + * + * 0 4 8 12 16 20 24 28 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * | | [ ] [ Counter Address [8:50] + * | * Mode | + * | * PB Scope + * * Enable/Disable + * + * 32 36 40 44 48 52 56 60 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * Counter Address [8:50] ] + * + */ +static int thread_imc_mem_alloc(int cpu_id, int size) +{ + u64 ldbar_value, *local_mem = per_cpu(thread_imc_mem, cpu_id); + int phys_id = topology_physical_package_id(cpu_id); + + if (!local_mem) { + /* + * This case could happen only once at start, since we dont + * free the memory in cpu offline path. + */ + local_mem = page_address(alloc_pages_node(phys_id, + GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, + get_order(size))); + if (!local_mem) + return -ENOMEM; + + per_cpu(thread_imc_mem, cpu_id) = local_mem; + } + + ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | THREAD_IMC_ENABLE; + + mtspr(SPRN_LDBAR, ldbar_value); + return 0; +} + +static int ppc_thread_imc_cpu_online(unsigned int cpu) +{ + return thread_imc_mem_alloc(cpu, thread_imc_mem_size); +} + +static int ppc_thread_imc_cpu_offline(unsigned int cpu) +{ + mtspr(SPRN_LDBAR, 0); + return 0; +} + +static int thread_imc_cpu_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, + "perf/powerpc/imc_thread:online", + ppc_thread_imc_cpu_online, + ppc_thread_imc_cpu_offline); +} + +void thread_imc_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + int core_id; + struct imc_pmu_ref *ref; + + if (!is_core_imc_mem_inited(smp_processor_id())) + return; + + core_id = smp_processor_id() / threads_per_core; + /* + * imc pmus are enabled only when it is used. + * See if this is triggered for the first time. + * If yes, take the mutex lock and enable the counters. + * If not, just increment the count in ref count struct. + */ + ref = &core_imc_refc[core_id]; + if (!ref) + return; + + if (sched_in) { + mutex_lock(&ref->lock); + if (ref->refc == 0) { + if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(smp_processor_id()))) { + mutex_unlock(&ref->lock); + pr_err("thread-imc: Unable to start the counter\ + for core %d\n", core_id); + return; + } + } + ++ref->refc; + mutex_unlock(&ref->lock); + } else { + mutex_lock(&ref->lock); + ref->refc--; + if (ref->refc == 0) { + if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(smp_processor_id()))) { + mutex_unlock(&ref->lock); + pr_err("thread-imc: Unable to stop the counters\ + for core %d\n", core_id); + return; + } + } else if (ref->refc < 0) { + ref->refc = 0; + } + mutex_unlock(&ref->lock); + } + + return; +} + +static int thread_imc_event_init(struct perf_event *event) +{ + u32 config = event->attr.config; + struct task_struct *target; + struct imc_pmu *pmu; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* Sampling not supported */ + if (event->hw.sample_period) + return -EINVAL; + + event->hw.idx = -1; + pmu = imc_event_to_pmu(event); + + /* Sanity check for config offset */ + if (((config & IMC_EVENT_OFFSET_MASK) > pmu->counter_mem_size)) + return -EINVAL; + + target = event->hw.target; + if (!target) + return -EINVAL; + + event->pmu->task_ctx_nr = perf_sw_context; + return 0; +} + +static bool is_thread_imc_pmu(struct perf_event *event) +{ + if (!strncmp(event->pmu->name, "thread_imc", strlen("thread_imc"))) + return true; + + return false; +} + +static u64 * get_event_base_addr(struct perf_event *event) +{ + u64 addr; + + if (is_thread_imc_pmu(event)) { + addr = (u64)per_cpu(thread_imc_mem, smp_processor_id()); + return (u64 *)(addr + (event->attr.config & IMC_EVENT_OFFSET_MASK)); + } + + return (u64 *)event->hw.event_base; +} + +static void thread_imc_pmu_start_txn(struct pmu *pmu, + unsigned int txn_flags) +{ + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + perf_pmu_disable(pmu); +} + +static void thread_imc_pmu_cancel_txn(struct pmu *pmu) +{ + perf_pmu_enable(pmu); +} + +static int thread_imc_pmu_commit_txn(struct pmu *pmu) +{ + perf_pmu_enable(pmu); + return 0; +} + +static u64 imc_read_counter(struct perf_event *event) +{ + u64 *addr, data; + + /* + * In-Memory Collection (IMC) counters are free flowing counters. + * So we take a snapshot of the counter value on enable and save it + * to calculate the delta at later stage to present the event counter + * value. + */ + addr = get_event_base_addr(event); + data = be64_to_cpu(READ_ONCE(*addr)); + local64_set(&event->hw.prev_count, data); + + return data; +} + +static void imc_event_update(struct perf_event *event) +{ + u64 counter_prev, counter_new, final_count; + + counter_prev = local64_read(&event->hw.prev_count); + counter_new = imc_read_counter(event); + final_count = counter_new - counter_prev; + + /* Update the delta to the event count */ + local64_add(final_count, &event->count); +} + +static void imc_event_start(struct perf_event *event, int flags) +{ + /* + * In Memory Counters are free flowing counters. HW or the microcode + * keeps adding to the counter offset in memory. To get event + * counter value, we snapshot the value here and we calculate + * delta at later point. + */ + imc_read_counter(event); +} + +static void imc_event_stop(struct perf_event *event, int flags) +{ + /* + * Take a snapshot and calculate the delta and update + * the event counter values. + */ + imc_event_update(event); +} + +static int imc_event_add(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_START) + imc_event_start(event, flags); + + return 0; +} + +static int thread_imc_event_add(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_START) + imc_event_start(event, flags); + + /* Enable the sched_task to start the engine */ + perf_sched_cb_inc(event->ctx->pmu); + return 0; +} + +static void thread_imc_event_del(struct perf_event *event, int flags) +{ + /* + * Take a snapshot and calculate the delta and update + * the event counter values. + */ + imc_event_update(event); + perf_sched_cb_dec(event->ctx->pmu); +} + +/* update_pmu_ops : Populate the appropriate operations for "pmu" */ +static int update_pmu_ops(struct imc_pmu *pmu) +{ + pmu->pmu.task_ctx_nr = perf_invalid_context; + pmu->pmu.add = imc_event_add; + pmu->pmu.del = imc_event_stop; + pmu->pmu.start = imc_event_start; + pmu->pmu.stop = imc_event_stop; + pmu->pmu.read = imc_event_update; + pmu->pmu.attr_groups = pmu->attr_groups; + pmu->attr_groups[IMC_FORMAT_ATTR] = &imc_format_group; + + switch (pmu->domain) { + case IMC_DOMAIN_NEST: + pmu->pmu.event_init = nest_imc_event_init; + pmu->attr_groups[IMC_CPUMASK_ATTR] = &imc_pmu_cpumask_attr_group; + break; + case IMC_DOMAIN_CORE: + pmu->pmu.event_init = core_imc_event_init; + pmu->attr_groups[IMC_CPUMASK_ATTR] = &imc_pmu_cpumask_attr_group; + break; + case IMC_DOMAIN_THREAD: + pmu->pmu.event_init = thread_imc_event_init; + pmu->pmu.sched_task = thread_imc_pmu_sched_task; + pmu->pmu.add = thread_imc_event_add; + pmu->pmu.del = thread_imc_event_del; + pmu->pmu.start_txn = thread_imc_pmu_start_txn; + pmu->pmu.cancel_txn = thread_imc_pmu_cancel_txn; + pmu->pmu.commit_txn = thread_imc_pmu_commit_txn; + break; + default: + break; + } + + return 0; +} + +/* init_nest_pmu_ref: Initialize the imc_pmu_ref struct for all the nodes */ +static int init_nest_pmu_ref(void) +{ + int nid, i, cpu; + + nest_imc_refc = kcalloc(num_possible_nodes(), sizeof(*nest_imc_refc), + GFP_KERNEL); + + if (!nest_imc_refc) + return -ENOMEM; + + i = 0; + for_each_node(nid) { + /* + * Mutex lock to avoid races while tracking the number of + * sessions using the chip's nest pmu units. + */ + mutex_init(&nest_imc_refc[i].lock); + + /* + * Loop to init the "id" with the node_id. Variable "i" initialized to + * 0 and will be used as index to the array. "i" will not go off the + * end of the array since the "for_each_node" loops for "N_POSSIBLE" + * nodes only. + */ + nest_imc_refc[i++].id = nid; + } + + /* + * Loop to init the per_cpu "local_nest_imc_refc" with the proper + * "nest_imc_refc" index. This makes get_nest_pmu_ref() alot simple. + */ + for_each_possible_cpu(cpu) { + nid = cpu_to_node(cpu); + for (i = 0; i < num_possible_nodes(); i++) { + if (nest_imc_refc[i].id == nid) { + per_cpu(local_nest_imc_refc, cpu) = &nest_imc_refc[i]; + break; + } + } + } + return 0; +} + +static void cleanup_all_core_imc_memory(void) +{ + int i, nr_cores = num_present_cpus() / threads_per_core; + struct imc_mem_info *ptr = core_imc_pmu->mem_info; + int size = core_imc_pmu->counter_mem_size; + + /* mem_info will never be NULL */ + for (i = 0; i < nr_cores; i++) { + if (ptr[i].vbase) + free_pages((u64)ptr->vbase, get_order(size)); + } + + kfree(ptr); + kfree(core_imc_refc); +} + +static void thread_imc_ldbar_disable(void *dummy) +{ + /* + * By Zeroing LDBAR, we disable thread-imc + * updates. + */ + mtspr(SPRN_LDBAR, 0); +} + +void thread_imc_disable(void) +{ + on_each_cpu(thread_imc_ldbar_disable, NULL, 1); +} + +static void cleanup_all_thread_imc_memory(void) +{ + int i, order = get_order(thread_imc_mem_size); + + for_each_online_cpu(i) { + if (per_cpu(thread_imc_mem, i)) + free_pages((u64)per_cpu(thread_imc_mem, i), order); + + } +} + +/* + * Common function to unregister cpu hotplug callback and + * free the memory. + * TODO: Need to handle pmu unregistering, which will be + * done in followup series. + */ +static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) +{ + if (pmu_ptr->domain == IMC_DOMAIN_NEST) { + mutex_lock(&nest_init_lock); + if (nest_pmus == 1) { + cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); + kfree(nest_imc_refc); + } + + if (nest_pmus > 0) + nest_pmus--; + mutex_unlock(&nest_init_lock); + } + + /* Free core_imc memory */ + if (pmu_ptr->domain == IMC_DOMAIN_CORE) { + cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE); + cleanup_all_core_imc_memory(); + } + + /* Free thread_imc memory */ + if (pmu_ptr->domain == IMC_DOMAIN_THREAD) { + cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE); + cleanup_all_thread_imc_memory(); + } + + /* Only free the attr_groups which are dynamically allocated */ + kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); + kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]); + kfree(pmu_ptr); + return; +} + + +/* + * imc_mem_init : Function to support memory allocation for core imc. + */ +static int imc_mem_init(struct imc_pmu *pmu_ptr, struct device_node *parent, + int pmu_index) +{ + const char *s; + int nr_cores, cpu, res; + + if (of_property_read_string(parent, "name", &s)) + return -ENODEV; + + switch (pmu_ptr->domain) { + case IMC_DOMAIN_NEST: + /* Update the pmu name */ + pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s_imc", "nest_", s); + if (!pmu_ptr->pmu.name) + return -ENOMEM; + + /* Needed for hotplug/migration */ + per_nest_pmu_arr[pmu_index] = pmu_ptr; + break; + case IMC_DOMAIN_CORE: + /* Update the pmu name */ + pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc"); + if (!pmu_ptr->pmu.name) + return -ENOMEM; + + nr_cores = num_present_cpus() / threads_per_core; + pmu_ptr->mem_info = kcalloc(nr_cores, sizeof(struct imc_mem_info), + GFP_KERNEL); + + if (!pmu_ptr->mem_info) + return -ENOMEM; + + core_imc_refc = kcalloc(nr_cores, sizeof(struct imc_pmu_ref), + GFP_KERNEL); + + if (!core_imc_refc) + return -ENOMEM; + + core_imc_pmu = pmu_ptr; + break; + case IMC_DOMAIN_THREAD: + /* Update the pmu name */ + pmu_ptr->pmu.name = kasprintf(GFP_KERNEL, "%s%s", s, "_imc"); + if (!pmu_ptr->pmu.name) + return -ENOMEM; + + thread_imc_mem_size = pmu_ptr->counter_mem_size; + for_each_online_cpu(cpu) { + res = thread_imc_mem_alloc(cpu, pmu_ptr->counter_mem_size); + if (res) + return res; + } + + thread_imc_pmu = pmu_ptr; + break; + default: + return -EINVAL; + } + + return 0; +} + +/* + * init_imc_pmu : Setup and register the IMC pmu device. + * + * @parent: Device tree unit node + * @pmu_ptr: memory allocated for this pmu + * @pmu_idx: Count of nest pmc registered + * + * init_imc_pmu() setup pmu cpumask and registers for a cpu hotplug callback. + * Handles failure cases and accordingly frees memory. + */ +int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_idx) +{ + int ret; + + ret = imc_mem_init(pmu_ptr, parent, pmu_idx); + if (ret) + goto err_free; + + switch (pmu_ptr->domain) { + case IMC_DOMAIN_NEST: + /* + * Nest imc pmu need only one cpu per chip, we initialize the + * cpumask for the first nest imc pmu and use the same for the + * rest. To handle the cpuhotplug callback unregister, we track + * the number of nest pmus in "nest_pmus". + */ + mutex_lock(&nest_init_lock); + if (nest_pmus == 0) { + ret = init_nest_pmu_ref(); + if (ret) { + mutex_unlock(&nest_init_lock); + goto err_free; + } + /* Register for cpu hotplug notification. */ + ret = nest_pmu_cpumask_init(); + if (ret) { + mutex_unlock(&nest_init_lock); + goto err_free; + } + } + nest_pmus++; + mutex_unlock(&nest_init_lock); + break; + case IMC_DOMAIN_CORE: + ret = core_imc_pmu_cpumask_init(); + if (ret) { + cleanup_all_core_imc_memory(); + return ret; + } + + break; + case IMC_DOMAIN_THREAD: + ret = thread_imc_cpu_init(); + if (ret) { + cleanup_all_thread_imc_memory(); + return ret; + } + + break; + default: + return -1; /* Unknown domain */ + } + + ret = update_events_in_group(parent, pmu_ptr); + if (ret) + goto err_free; + + ret = update_pmu_ops(pmu_ptr); + if (ret) + goto err_free; + + ret = perf_pmu_register(&pmu_ptr->pmu, pmu_ptr->pmu.name, -1); + if (ret) + goto err_free; + + pr_info("%s performance monitor hardware support registered\n", + pmu_ptr->pmu.name); + + return 0; + +err_free: + imc_common_cpuhp_mem_free(pmu_ptr); + return ret; +} diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 3f3aa9a7063a..2efee3f196f5 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -99,7 +99,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) else if (!cpu_has_feature(CPU_FTR_POWER9_DD1) && p9_SDAR_MODE(event)) *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; else - *mmcra |= MMCRA_SDAR_MODE_TLB; + *mmcra |= MMCRA_SDAR_MODE_DCACHE; } else *mmcra |= MMCRA_SDAR_MODE_TLB; } @@ -488,8 +488,8 @@ static int find_alternative(u64 event, const unsigned int ev_alt[][MAX_ALT], int return -1; } -int isa207_get_alternatives(u64 event, u64 alt[], - const unsigned int ev_alt[][MAX_ALT], int size) +int isa207_get_alternatives(u64 event, u64 alt[], int size, unsigned int flags, + const unsigned int ev_alt[][MAX_ALT]) { int i, j, num_alt = 0; u64 alt_event; @@ -505,5 +505,30 @@ int isa207_get_alternatives(u64 event, u64 alt[], } } + if (flags & PPMU_ONLY_COUNT_RUN) { + /* + * We're only counting in RUN state, so PM_CYC is equivalent to + * PM_RUN_CYC and PM_INST_CMPL === PM_RUN_INST_CMPL. + */ + j = num_alt; + for (i = 0; i < num_alt; ++i) { + switch (alt[i]) { + case 0x1e: /* PMC_CYC */ + alt[j++] = 0x600f4; /* PM_RUN_CYC */ + break; + case 0x600f4: + alt[j++] = 0x1e; + break; + case 0x2: /* PM_INST_CMPL */ + alt[j++] = 0x500fa; /* PM_RUN_INST_CMPL */ + break; + case 0x500fa: + alt[j++] = 0x2; + break; + } + } + num_alt = j; + } + return num_alt; } diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 8acbe6e802c7..6c737d675792 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -247,6 +247,7 @@ #define MMCRA_SDAR_MODE_SHIFT 42 #define MMCRA_SDAR_MODE_TLB (1ull << MMCRA_SDAR_MODE_SHIFT) #define MMCRA_SDAR_MODE_NO_UPDATES ~(0x3ull << MMCRA_SDAR_MODE_SHIFT) +#define MMCRA_SDAR_MODE_DCACHE (2ull << MMCRA_SDAR_MODE_SHIFT) #define MMCRA_IFM_SHIFT 30 #define MMCRA_THR_CTR_MANT_SHIFT 19 #define MMCRA_THR_CTR_MANT_MASK 0x7Ful @@ -287,8 +288,8 @@ int isa207_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[]); void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]); -int isa207_get_alternatives(u64 event, u64 alt[], - const unsigned int ev_alt[][MAX_ALT], int size); +int isa207_get_alternatives(u64 event, u64 alt[], int size, unsigned int flags, + const unsigned int ev_alt[][MAX_ALT]); void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags, struct pt_regs *regs); void isa207_get_mem_weight(u64 *weight); diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index 5463516e369b..c9356955cab4 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -50,34 +50,11 @@ static const unsigned int event_alternatives[][MAX_ALT] = { static int power8_get_alternatives(u64 event, unsigned int flags, u64 alt[]) { - int i, j, num_alt = 0; - - num_alt = isa207_get_alternatives(event, alt, event_alternatives, - (int)ARRAY_SIZE(event_alternatives)); - if (flags & PPMU_ONLY_COUNT_RUN) { - /* - * We're only counting in RUN state, so PM_CYC is equivalent to - * PM_RUN_CYC and PM_INST_CMPL === PM_RUN_INST_CMPL. - */ - j = num_alt; - for (i = 0; i < num_alt; ++i) { - switch (alt[i]) { - case PM_CYC: - alt[j++] = PM_RUN_CYC; - break; - case PM_RUN_CYC: - alt[j++] = PM_CYC; - break; - case PM_INST_CMPL: - alt[j++] = PM_RUN_INST_CMPL; - break; - case PM_RUN_INST_CMPL: - alt[j++] = PM_INST_CMPL; - break; - } - } - num_alt = j; - } + int num_alt = 0; + + num_alt = isa207_get_alternatives(event, alt, + ARRAY_SIZE(event_alternatives), flags, + event_alternatives); return num_alt; } diff --git a/arch/powerpc/perf/power9-events-list.h b/arch/powerpc/perf/power9-events-list.h index 50689180a6c1..e99c6bf4d391 100644 --- a/arch/powerpc/perf/power9-events-list.h +++ b/arch/powerpc/perf/power9-events-list.h @@ -16,13 +16,16 @@ EVENT(PM_CYC, 0x0001e) EVENT(PM_ICT_NOSLOT_CYC, 0x100f8) EVENT(PM_CMPLU_STALL, 0x1e054) EVENT(PM_INST_CMPL, 0x00002) -EVENT(PM_BRU_CMPL, 0x4d05e) +EVENT(PM_BR_CMPL, 0x4d05e) EVENT(PM_BR_MPRED_CMPL, 0x400f6) /* All L1 D cache load references counted at finish, gated by reject */ EVENT(PM_LD_REF_L1, 0x100fc) /* Load Missed L1 */ EVENT(PM_LD_MISS_L1_FIN, 0x2c04e) +EVENT(PM_LD_MISS_L1, 0x3e054) +/* Alternate event code for PM_LD_MISS_L1 */ +EVENT(PM_LD_MISS_L1_ALT, 0x400f0) /* Store Missed L1 */ EVENT(PM_ST_MISS_L1, 0x300f0) /* L1 cache data prefetches */ @@ -62,3 +65,7 @@ EVENT(PM_INST_DISP, 0x200f2) EVENT(PM_INST_DISP_ALT, 0x300f2) /* Alternate Branch event code */ EVENT(PM_BR_CMPL_ALT, 0x10012) +/* Branch event that are not strongly biased */ +EVENT(PM_BR_2PATH, 0x20036) +/* ALternate branch event that are not strongly biased */ +EVENT(PM_BR_2PATH_ALT, 0x40036) diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 2280cf87ff9c..24b5b5b7a206 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -109,14 +109,17 @@ static const unsigned int power9_event_alternatives[][MAX_ALT] = { { PM_INST_DISP, PM_INST_DISP_ALT }, { PM_RUN_CYC_ALT, PM_RUN_CYC }, { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, + { PM_LD_MISS_L1, PM_LD_MISS_L1_ALT }, + { PM_BR_2PATH, PM_BR_2PATH_ALT }, }; static int power9_get_alternatives(u64 event, unsigned int flags, u64 alt[]) { int num_alt = 0; - num_alt = isa207_get_alternatives(event, alt, power9_event_alternatives, - (int)ARRAY_SIZE(power9_event_alternatives)); + num_alt = isa207_get_alternatives(event, alt, + ARRAY_SIZE(power9_event_alternatives), flags, + power9_event_alternatives); return num_alt; } @@ -125,7 +128,7 @@ GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC); GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_ICT_NOSLOT_CYC); GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL); GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL); -GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_CMPL); +GENERIC_EVENT_ATTR(branch-instructions, PM_BR_CMPL); GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL); GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1); GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1_FIN); @@ -143,7 +146,7 @@ CACHE_EVENT_ATTR(LLC-prefetches, PM_L3_PREF_ALL); CACHE_EVENT_ATTR(LLC-store-misses, PM_L2_ST_MISS); CACHE_EVENT_ATTR(LLC-stores, PM_L2_ST); CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL); -CACHE_EVENT_ATTR(branch-loads, PM_BRU_CMPL); +CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL); CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS); CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS); @@ -152,7 +155,7 @@ static struct attribute *power9_events_attr[] = { GENERIC_EVENT_PTR(PM_ICT_NOSLOT_CYC), GENERIC_EVENT_PTR(PM_CMPLU_STALL), GENERIC_EVENT_PTR(PM_INST_CMPL), - GENERIC_EVENT_PTR(PM_BRU_CMPL), + GENERIC_EVENT_PTR(PM_BR_CMPL), GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL), GENERIC_EVENT_PTR(PM_LD_REF_L1), GENERIC_EVENT_PTR(PM_LD_MISS_L1_FIN), @@ -169,7 +172,7 @@ static struct attribute *power9_events_attr[] = { CACHE_EVENT_PTR(PM_L2_ST_MISS), CACHE_EVENT_PTR(PM_L2_ST), CACHE_EVENT_PTR(PM_BR_MPRED_CMPL), - CACHE_EVENT_PTR(PM_BRU_CMPL), + CACHE_EVENT_PTR(PM_BR_CMPL), CACHE_EVENT_PTR(PM_DTLB_MISS), CACHE_EVENT_PTR(PM_ITLB_MISS), NULL @@ -244,7 +247,7 @@ static int power9_generic_events[] = { [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = PM_ICT_NOSLOT_CYC, [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = PM_CMPLU_STALL, [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_CMPL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL, [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1_FIN, @@ -370,7 +373,7 @@ static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { }, [ C(BPU) ] = { [ C(OP_READ) ] = { - [ C(RESULT_ACCESS) ] = PM_BRU_CMPL, + [ C(RESULT_ACCESS) ] = PM_BR_CMPL, [ C(RESULT_MISS) ] = PM_BR_MPRED_CMPL, }, [ C(OP_WRITE) ] = { @@ -459,8 +462,8 @@ static int __init init_power9_pmu(void) * Power9 DD1 should use PM_BR_CMPL_ALT event code for * "branches" to provide correct counter value. */ - EVENT_VAR(PM_BRU_CMPL, _g).id = PM_BR_CMPL_ALT; - EVENT_VAR(PM_BRU_CMPL, _c).id = PM_BR_CMPL_ALT; + EVENT_VAR(PM_BR_CMPL, _g).id = PM_BR_CMPL_ALT; + EVENT_VAR(PM_BR_CMPL, _c).id = PM_BR_CMPL_ALT; rc = register_power_pmu(&power9_isa207_pmu); } else { rc = register_power_pmu(&power9_pmu); diff --git a/arch/powerpc/platforms/44x/Makefile b/arch/powerpc/platforms/44x/Makefile index 72b824160660..2c5651992369 100644 --- a/arch/powerpc/platforms/44x/Makefile +++ b/arch/powerpc/platforms/44x/Makefile @@ -1,6 +1,6 @@ -obj-$(CONFIG_44x) += misc_44x.o +obj-y += misc_44x.o machine_check.o ifneq ($(CONFIG_PPC4xx_CPM),y) -obj-$(CONFIG_44x) += idle.o +obj-y += idle.o endif obj-$(CONFIG_PPC44x_SIMPLE) += ppc44x_simple.o obj-$(CONFIG_EBONY) += ebony.o diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c new file mode 100644 index 000000000000..034d70d6d335 --- /dev/null +++ b/arch/powerpc/platforms/44x/machine_check.c @@ -0,0 +1,89 @@ +/* + * 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/kernel.h> +#include <linux/printk.h> +#include <linux/ptrace.h> + +#include <asm/reg.h> + +int machine_check_440A(struct pt_regs *regs) +{ + unsigned long reason = regs->dsisr; + + printk("Machine check in kernel mode.\n"); + if (reason & ESR_IMCP){ + printk("Instruction Synchronous Machine Check exception\n"); + mtspr(SPRN_ESR, reason & ~ESR_IMCP); + } + else { + u32 mcsr = mfspr(SPRN_MCSR); + if (mcsr & MCSR_IB) + printk("Instruction Read PLB Error\n"); + if (mcsr & MCSR_DRB) + printk("Data Read PLB Error\n"); + if (mcsr & MCSR_DWB) + printk("Data Write PLB Error\n"); + if (mcsr & MCSR_TLBP) + printk("TLB Parity Error\n"); + if (mcsr & MCSR_ICP){ + flush_instruction_cache(); + printk("I-Cache Parity Error\n"); + } + if (mcsr & MCSR_DCSP) + printk("D-Cache Search Parity Error\n"); + if (mcsr & MCSR_DCFP) + printk("D-Cache Flush Parity Error\n"); + if (mcsr & MCSR_IMPE) + printk("Machine Check exception is imprecise\n"); + + /* Clear MCSR */ + mtspr(SPRN_MCSR, mcsr); + } + return 0; +} + +#ifdef CONFIG_PPC_47x +int machine_check_47x(struct pt_regs *regs) +{ + unsigned long reason = regs->dsisr; + u32 mcsr; + + printk(KERN_ERR "Machine check in kernel mode.\n"); + if (reason & ESR_IMCP) { + printk(KERN_ERR "Instruction Synchronous Machine Check exception\n"); + mtspr(SPRN_ESR, reason & ~ESR_IMCP); + return 0; + } + mcsr = mfspr(SPRN_MCSR); + if (mcsr & MCSR_IB) + printk(KERN_ERR "Instruction Read PLB Error\n"); + if (mcsr & MCSR_DRB) + printk(KERN_ERR "Data Read PLB Error\n"); + if (mcsr & MCSR_DWB) + printk(KERN_ERR "Data Write PLB Error\n"); + if (mcsr & MCSR_TLBP) + printk(KERN_ERR "TLB Parity Error\n"); + if (mcsr & MCSR_ICP) { + flush_instruction_cache(); + printk(KERN_ERR "I-Cache Parity Error\n"); + } + if (mcsr & MCSR_DCSP) + printk(KERN_ERR "D-Cache Search Parity Error\n"); + if (mcsr & PPC47x_MCSR_GPR) + printk(KERN_ERR "GPR Parity Error\n"); + if (mcsr & PPC47x_MCSR_FPR) + printk(KERN_ERR "FPR Parity Error\n"); + if (mcsr & PPC47x_MCSR_IPR) + printk(KERN_ERR "Machine Check exception is imprecise\n"); + + /* Clear MCSR */ + mtspr(SPRN_MCSR, mcsr); + + return 0; +} +#endif /* CONFIG_PPC_47x */ diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile new file mode 100644 index 000000000000..9779c32db34e --- /dev/null +++ b/arch/powerpc/platforms/4xx/Makefile @@ -0,0 +1,8 @@ +obj-y += uic.o machine_check.o +obj-$(CONFIG_PPC4xx_OCM) += ocm.o +obj-$(CONFIG_4xx_SOC) += soc.o +obj-$(CONFIG_PCI) += pci.o +obj-$(CONFIG_PPC4xx_HSTA_MSI) += hsta_msi.o +obj-$(CONFIG_PPC4xx_MSI) += msi.o +obj-$(CONFIG_PPC4xx_CPM) += cpm.o +obj-$(CONFIG_PPC4xx_GPIO) += gpio.o diff --git a/arch/powerpc/sysdev/ppc4xx_cpm.c b/arch/powerpc/platforms/4xx/cpm.c index ba95adf81d8d..53ff81ca8a3c 100644 --- a/arch/powerpc/sysdev/ppc4xx_cpm.c +++ b/arch/powerpc/platforms/4xx/cpm.c @@ -240,7 +240,7 @@ static int cpm_suspend_enter(suspend_state_t state) return 0; } -static struct platform_suspend_ops cpm_suspend_ops = { +static const struct platform_suspend_ops cpm_suspend_ops = { .valid = cpm_suspend_valid, .enter = cpm_suspend_enter, }; @@ -278,8 +278,8 @@ static int __init cpm_init(void) dcr_len = dcr_resource_len(np, 0); if (dcr_base == 0 || dcr_len == 0) { - printk(KERN_ERR "cpm: could not parse dcr property for %s\n", - np->full_name); + printk(KERN_ERR "cpm: could not parse dcr property for %pOF\n", + np); ret = -EINVAL; goto node_put; } @@ -287,8 +287,8 @@ static int __init cpm_init(void) cpm.dcr_host = dcr_map(np, dcr_base, dcr_len); if (!DCR_MAP_OK(cpm.dcr_host)) { - printk(KERN_ERR "cpm: failed to map dcr property for %s\n", - np->full_name); + printk(KERN_ERR "cpm: failed to map dcr property for %pOF\n", + np); ret = -EINVAL; goto node_put; } diff --git a/arch/powerpc/sysdev/ppc4xx_gpio.c b/arch/powerpc/platforms/4xx/gpio.c index 5382d04dd872..2238e369cde4 100644 --- a/arch/powerpc/sysdev/ppc4xx_gpio.c +++ b/arch/powerpc/platforms/4xx/gpio.c @@ -198,8 +198,7 @@ static int __init ppc4xx_add_gpiochips(void) goto err; continue; err: - pr_err("%s: registration failed with status %d\n", - np->full_name, ret); + pr_err("%pOF: registration failed with status %d\n", np, ret); kfree(ppc4xx_gc); /* try others anyway */ } diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/platforms/4xx/hsta_msi.c index 9926ad67af76..9926ad67af76 100644 --- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c +++ b/arch/powerpc/platforms/4xx/hsta_msi.c diff --git a/arch/powerpc/platforms/4xx/machine_check.c b/arch/powerpc/platforms/4xx/machine_check.c new file mode 100644 index 000000000000..aa039dfaf82f --- /dev/null +++ b/arch/powerpc/platforms/4xx/machine_check.c @@ -0,0 +1,26 @@ +/* + * 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/kernel.h> +#include <linux/printk.h> +#include <linux/ptrace.h> + +#include <asm/reg.h> + +int machine_check_4xx(struct pt_regs *regs) +{ + unsigned long reason = regs->dsisr; + + if (reason & ESR_IMCP) { + printk("Instruction"); + mtspr(SPRN_ESR, reason & ~ESR_IMCP); + } else + printk("Data"); + printk(" machine check in kernel mode.\n"); + + return 0; +} diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/platforms/4xx/msi.c index 590dab4f47d6..d50417e23add 100644 --- a/arch/powerpc/sysdev/ppc4xx_msi.c +++ b/arch/powerpc/platforms/4xx/msi.c @@ -233,8 +233,7 @@ static int ppc4xx_msi_probe(struct platform_device *dev) /* Get MSI ranges */ err = of_address_to_resource(dev->dev.of_node, 0, &res); if (err) { - dev_err(&dev->dev, "%s resource error!\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "%pOF resource error!\n", dev->dev.of_node); goto error_out; } diff --git a/arch/powerpc/sysdev/ppc4xx_ocm.c b/arch/powerpc/platforms/4xx/ocm.c index 85d9e37f5ccb..85d9e37f5ccb 100644 --- a/arch/powerpc/sysdev/ppc4xx_ocm.c +++ b/arch/powerpc/platforms/4xx/ocm.c diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/platforms/4xx/pci.c index 086aca69ecae..73e6b36bcd51 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -32,7 +32,7 @@ #include <asm/dcr-regs.h> #include <mm/mmu_decl.h> -#include "ppc4xx_pci.h" +#include "pci.h" static int dma_offset_set; @@ -127,9 +127,9 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose, * within 32 bits space */ if (cpu_addr != 0 || pci_addr > 0xffffffff) { - printk(KERN_WARNING "%s: Ignored unsupported dma range" + printk(KERN_WARNING "%pOF: Ignored unsupported dma range" " 0x%016llx...0x%016llx -> 0x%016llx\n", - hose->dn->full_name, + hose->dn, pci_addr, pci_addr + size - 1, cpu_addr); continue; } @@ -152,8 +152,7 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose, /* We only support one global DMA offset */ if (dma_offset_set && pci_dram_offset != res->start) { - printk(KERN_ERR "%s: dma-ranges(s) mismatch\n", - hose->dn->full_name); + printk(KERN_ERR "%pOF: dma-ranges(s) mismatch\n", hose->dn); return -ENXIO; } @@ -161,17 +160,16 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose, * DMA bounce buffers */ if (size < total_memory) { - printk(KERN_ERR "%s: dma-ranges too small " + printk(KERN_ERR "%pOF: dma-ranges too small " "(size=%llx total_memory=%llx)\n", - hose->dn->full_name, size, (u64)total_memory); + hose->dn, size, (u64)total_memory); return -ENXIO; } /* Check we are a power of 2 size and that base is a multiple of size*/ if ((size & (size - 1)) != 0 || (res->start & (size - 1)) != 0) { - printk(KERN_ERR "%s: dma-ranges unaligned\n", - hose->dn->full_name); + printk(KERN_ERR "%pOF: dma-ranges unaligned\n", hose->dn); return -ENXIO; } @@ -181,8 +179,8 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose, if (res->end > 0xffffffff && !(of_device_is_compatible(hose->dn, "ibm,plb-pciex-460sx") || of_device_is_compatible(hose->dn, "ibm,plb-pciex-476fpe"))) { - printk(KERN_ERR "%s: dma-ranges outside of 32 bits space\n", - hose->dn->full_name); + printk(KERN_ERR "%pOF: dma-ranges outside of 32 bits space\n", + hose->dn); return -ENXIO; } out: @@ -233,8 +231,7 @@ static int __init ppc4xx_setup_one_pci_PMM(struct pci_controller *hose, */ if ((plb_addr + size) > 0xffffffffull || !is_power_of_2(size) || size < 0x1000 || (plb_addr & (size - 1)) != 0) { - printk(KERN_WARNING "%s: Resource out of range\n", - hose->dn->full_name); + printk(KERN_WARNING "%pOF: Resource out of range\n", hose->dn); return -1; } ma = (0xffffffffu << ilog2(size)) | 1; @@ -266,8 +263,7 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose, if (!(res->flags & IORESOURCE_MEM)) continue; if (j > 2) { - printk(KERN_WARNING "%s: Too many ranges\n", - hose->dn->full_name); + printk(KERN_WARNING "%pOF: Too many ranges\n", hose->dn); break; } @@ -292,8 +288,8 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose, if (j <= 2 && !found_isa_hole && hose->isa_mem_size) if (ppc4xx_setup_one_pci_PMM(hose, reg, hose->isa_mem_phys, 0, hose->isa_mem_size, 0, j) == 0) - printk(KERN_INFO "%s: Legacy ISA memory support enabled\n", - hose->dn->full_name); + printk(KERN_INFO "%pOF: Legacy ISA memory support enabled\n", + hose->dn); } static void __init ppc4xx_configure_pci_PTMs(struct pci_controller *hose, @@ -333,21 +329,20 @@ static void __init ppc4xx_probe_pci_bridge(struct device_node *np) /* Check if device is enabled */ if (!of_device_is_available(np)) { - printk(KERN_INFO "%s: Port disabled via device-tree\n", - np->full_name); + printk(KERN_INFO "%pOF: Port disabled via device-tree\n", np); return; } /* Fetch config space registers address */ if (of_address_to_resource(np, 0, &rsrc_cfg)) { - printk(KERN_ERR "%s: Can't get PCI config register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get PCI config register base !", + np); return; } /* Fetch host bridge internal registers address */ if (of_address_to_resource(np, 3, &rsrc_reg)) { - printk(KERN_ERR "%s: Can't get PCI internal register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get PCI internal register base !", + np); return; } @@ -361,7 +356,7 @@ static void __init ppc4xx_probe_pci_bridge(struct device_node *np) /* Map registers */ reg = ioremap(rsrc_reg.start, resource_size(&rsrc_reg)); if (reg == NULL) { - printk(KERN_ERR "%s: Can't map registers !", np->full_name); + printk(KERN_ERR "%pOF: Can't map registers !", np); goto fail; } @@ -423,8 +418,8 @@ static int __init ppc4xx_setup_one_pcix_POM(struct pci_controller *hose, if (!is_power_of_2(size) || size < 0x1000 || (plb_addr & (size - 1)) != 0) { - printk(KERN_WARNING "%s: Resource out of range\n", - hose->dn->full_name); + printk(KERN_WARNING "%pOF: Resource out of range\n", + hose->dn); return -1; } @@ -467,8 +462,7 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose, if (!(res->flags & IORESOURCE_MEM)) continue; if (j > 1) { - printk(KERN_WARNING "%s: Too many ranges\n", - hose->dn->full_name); + printk(KERN_WARNING "%pOF: Too many ranges\n", hose->dn); break; } @@ -493,8 +487,8 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose, if (j <= 1 && !found_isa_hole && hose->isa_mem_size) if (ppc4xx_setup_one_pcix_POM(hose, reg, hose->isa_mem_phys, 0, hose->isa_mem_size, 0, j) == 0) - printk(KERN_INFO "%s: Legacy ISA memory support enabled\n", - hose->dn->full_name); + printk(KERN_INFO "%pOF: Legacy ISA memory support enabled\n", + hose->dn); } static void __init ppc4xx_configure_pcix_PIMs(struct pci_controller *hose, @@ -539,14 +533,14 @@ static void __init ppc4xx_probe_pcix_bridge(struct device_node *np) /* Fetch config space registers address */ if (of_address_to_resource(np, 0, &rsrc_cfg)) { - printk(KERN_ERR "%s:Can't get PCI-X config register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get PCI-X config register base !", + np); return; } /* Fetch host bridge internal registers address */ if (of_address_to_resource(np, 3, &rsrc_reg)) { - printk(KERN_ERR "%s: Can't get PCI-X internal register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get PCI-X internal register base !", + np); return; } @@ -568,7 +562,7 @@ static void __init ppc4xx_probe_pcix_bridge(struct device_node *np) /* Map registers */ reg = ioremap(rsrc_reg.start, resource_size(&rsrc_reg)); if (reg == NULL) { - printk(KERN_ERR "%s: Can't map registers !", np->full_name); + printk(KERN_ERR "%pOF: Can't map registers !", np); goto fail; } @@ -1246,8 +1240,8 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) mbase = ioremap(port->cfg_space.start + 0x10000000, 0x1000); if (mbase == NULL) { - printk(KERN_ERR "%s: Can't map internal config space !", - port->node->full_name); + printk(KERN_ERR "%pOF: Can't map internal config space !", + port->node); goto done; } @@ -1389,7 +1383,7 @@ static void __init ppc_476fpe_pciex_check_link(struct ppc4xx_pciex_port *port) port->index); return; } - + while (timeout_ms--) { val = in_le32(mbase + PECFG_TLDLP); @@ -1448,8 +1442,7 @@ static int __init ppc4xx_pciex_check_core_init(struct device_node *np) ppc4xx_pciex_hwops = &ppc_476fpe_pcie_hwops; #endif if (ppc4xx_pciex_hwops == NULL) { - printk(KERN_WARNING "PCIE: unknown host type %s\n", - np->full_name); + printk(KERN_WARNING "PCIE: unknown host type %pOF\n", np); return -ENODEV; } @@ -1730,8 +1723,7 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port *port, (index < 2 && size < 0x100000) || (index == 2 && size < 0x100) || (plb_addr & (size - 1)) != 0) { - printk(KERN_WARNING "%s: Resource out of range\n", - hose->dn->full_name); + printk(KERN_WARNING "%pOF: Resource out of range\n", hose->dn); return -1; } @@ -1807,8 +1799,8 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port, if (!(res->flags & IORESOURCE_MEM)) continue; if (j > 1) { - printk(KERN_WARNING "%s: Too many ranges\n", - port->node->full_name); + printk(KERN_WARNING "%pOF: Too many ranges\n", + port->node); break; } @@ -1834,8 +1826,8 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port, if (ppc4xx_setup_one_pciex_POM(port, hose, mbase, hose->isa_mem_phys, 0, hose->isa_mem_size, 0, j) == 0) - printk(KERN_INFO "%s: Legacy ISA memory support enabled\n", - hose->dn->full_name); + printk(KERN_INFO "%pOF: Legacy ISA memory support enabled\n", + hose->dn); /* Configure IO, always 64K starting at 0. We hard wire it to 64K ! * Note also that it -has- to be region index 2 on this HW @@ -1970,8 +1962,8 @@ static void __init ppc4xx_pciex_port_setup_hose(struct ppc4xx_pciex_port *port) (hose->first_busno + 1) * 0x100000, busses * 0x100000); if (cfg_data == NULL) { - printk(KERN_ERR "%s: Can't map external config space !", - port->node->full_name); + printk(KERN_ERR "%pOF: Can't map external config space !", + port->node); goto fail; } hose->cfg_data = cfg_data; @@ -1982,13 +1974,13 @@ static void __init ppc4xx_pciex_port_setup_hose(struct ppc4xx_pciex_port *port) */ mbase = ioremap(port->cfg_space.start + 0x10000000, 0x1000); if (mbase == NULL) { - printk(KERN_ERR "%s: Can't map internal config space !", - port->node->full_name); + printk(KERN_ERR "%pOF: Can't map internal config space !", + port->node); goto fail; } hose->cfg_addr = mbase; - pr_debug("PCIE %s, bus %d..%d\n", port->node->full_name, + pr_debug("PCIE %pOF, bus %d..%d\n", port->node, hose->first_busno, hose->last_busno); pr_debug(" config space mapped at: root @0x%p, other @0x%p\n", hose->cfg_addr, hose->cfg_data); @@ -2100,14 +2092,13 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) /* Get the port number from the device-tree */ pval = of_get_property(np, "port", NULL); if (pval == NULL) { - printk(KERN_ERR "PCIE: Can't find port number for %s\n", - np->full_name); + printk(KERN_ERR "PCIE: Can't find port number for %pOF\n", np); return; } portno = *pval; if (portno >= ppc4xx_pciex_port_count) { - printk(KERN_ERR "PCIE: port number out of range for %s\n", - np->full_name); + printk(KERN_ERR "PCIE: port number out of range for %pOF\n", + np); return; } port = &ppc4xx_pciex_ports[portno]; @@ -2125,8 +2116,8 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) if (ppc4xx_pciex_hwops->want_sdr) { pval = of_get_property(np, "sdr-base", NULL); if (pval == NULL) { - printk(KERN_ERR "PCIE: missing sdr-base for %s\n", - np->full_name); + printk(KERN_ERR "PCIE: missing sdr-base for %pOF\n", + np); return; } port->sdr_base = *pval; @@ -2142,29 +2133,26 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) } else if (!strcmp(val, "pci")) { port->endpoint = 0; } else { - printk(KERN_ERR "PCIE: missing or incorrect device_type for %s\n", - np->full_name); + printk(KERN_ERR "PCIE: missing or incorrect device_type for %pOF\n", + np); return; } /* Fetch config space registers address */ if (of_address_to_resource(np, 0, &port->cfg_space)) { - printk(KERN_ERR "%s: Can't get PCI-E config space !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get PCI-E config space !", np); return; } /* Fetch host bridge internal registers address */ if (of_address_to_resource(np, 1, &port->utl_regs)) { - printk(KERN_ERR "%s: Can't get UTL register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get UTL register base !", np); return; } /* Map DCRs */ dcrs = dcr_resource_start(np, 0); if (dcrs == 0) { - printk(KERN_ERR "%s: Can't get DCR register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get DCR register base !", np); return; } port->dcrs = dcr_map(np, dcrs, dcr_resource_len(np, 0)); diff --git a/arch/powerpc/sysdev/ppc4xx_pci.h b/arch/powerpc/platforms/4xx/pci.h index bb4821938ab1..bb4821938ab1 100644 --- a/arch/powerpc/sysdev/ppc4xx_pci.h +++ b/arch/powerpc/platforms/4xx/pci.h diff --git a/arch/powerpc/sysdev/ppc4xx_soc.c b/arch/powerpc/platforms/4xx/soc.c index d41134d2f786..5e36508b2a70 100644 --- a/arch/powerpc/sysdev/ppc4xx_soc.c +++ b/arch/powerpc/platforms/4xx/soc.c @@ -90,7 +90,7 @@ static int __init ppc4xx_l2c_probe(void) /* Get l2 cache size */ prop = of_get_property(np, "cache-size", NULL); if (prop == NULL) { - printk(KERN_ERR "%s: Can't get cache-size!\n", np->full_name); + printk(KERN_ERR "%pOF: Can't get cache-size!\n", np); of_node_put(np); return -ENODEV; } @@ -99,8 +99,7 @@ static int __init ppc4xx_l2c_probe(void) /* Map DCRs */ dcrreg = of_get_property(np, "dcr-reg", &len); if (!dcrreg || (len != 4 * sizeof(u32))) { - printk(KERN_ERR "%s: Can't get DCR register base !", - np->full_name); + printk(KERN_ERR "%pOF: Can't get DCR register base !", np); of_node_put(np); return -ENODEV; } diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/platforms/4xx/uic.c index a00949f3e378..8b4dd0da0839 100644 --- a/arch/powerpc/sysdev/uic.c +++ b/arch/powerpc/platforms/4xx/uic.c @@ -243,16 +243,16 @@ static struct uic * __init uic_init_one(struct device_node *node) raw_spin_lock_init(&uic->lock); indexp = of_get_property(node, "cell-index", &len); if (!indexp || (len != sizeof(u32))) { - printk(KERN_ERR "uic: Device node %s has missing or invalid " - "cell-index property\n", node->full_name); + printk(KERN_ERR "uic: Device node %pOF has missing or invalid " + "cell-index property\n", node); return NULL; } uic->index = *indexp; dcrreg = of_get_property(node, "dcr-reg", &len); if (!dcrreg || (len != 2*sizeof(u32))) { - printk(KERN_ERR "uic: Device node %s has missing or invalid " - "dcr-reg property\n", node->full_name); + printk(KERN_ERR "uic: Device node %pOF has missing or invalid " + "dcr-reg property\n", node); return NULL; } uic->dcrbase = *dcrreg; @@ -292,7 +292,7 @@ void __init uic_init_tree(void) * top-level interrupt controller */ primary_uic = uic_init_one(np); if (!primary_uic) - panic("Unable to initialize primary UIC %s\n", np->full_name); + panic("Unable to initialize primary UIC %pOF\n", np); irq_set_default_host(primary_uic->irqhost); of_node_put(np); @@ -306,8 +306,8 @@ void __init uic_init_tree(void) uic = uic_init_one(np); if (! uic) - panic("Unable to initialize a secondary UIC %s\n", - np->full_name); + panic("Unable to initialize a secondary UIC %pOF\n", + np); cascade_virq = irq_of_parse_and_map(np, 0); diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index add5a5374fa0..b3097fe6441b 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -363,7 +363,7 @@ static int get_cpmf_mult_x2(void) */ /* applies to the IPS_DIV, and PCI_DIV values */ -static struct clk_div_table divtab_2346[] = { +static const struct clk_div_table divtab_2346[] = { { .val = 2, .div = 2, }, { .val = 3, .div = 3, }, { .val = 4, .div = 4, }, @@ -372,7 +372,7 @@ static struct clk_div_table divtab_2346[] = { }; /* applies to the MBX_DIV, LPC_DIV, and NFC_DIV values */ -static struct clk_div_table divtab_1234[] = { +static const struct clk_div_table divtab_1234[] = { { .val = 1, .div = 1, }, { .val = 2, .div = 2, }, { .val = 3, .div = 3, }, diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index 6b4f4cb7009a..f99e79ee060e 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -387,8 +387,8 @@ static unsigned int __init get_fifo_size(struct device_node *np, if (fp) return *fp; - pr_warning("no %s property in %s node, defaulting to %d\n", - prop_name, np->full_name, DEFAULT_FIFO_SIZE); + pr_warning("no %s property in %pOF node, defaulting to %d\n", + prop_name, np, DEFAULT_FIFO_SIZE); return DEFAULT_FIFO_SIZE; } @@ -426,15 +426,15 @@ static void __init mpc512x_psc_fifo_init(void) psc = of_iomap(np, 0); if (!psc) { - pr_err("%s: Can't map %s device\n", - __func__, np->full_name); + pr_err("%s: Can't map %pOF device\n", + __func__, np); continue; } /* FIFO space is 4KiB, check if requested size is available */ if ((fifobase + tx_fifo_size + rx_fifo_size) > 0x1000) { - pr_err("%s: no fifo space available for %s\n", - __func__, np->full_name); + pr_err("%s: no fifo space available for %pOF\n", + __func__, np); iounmap(psc); /* * chances are that another device requests less diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c index 39b49822ace1..1ecbf176d35a 100644 --- a/arch/powerpc/platforms/52xx/efika.c +++ b/arch/powerpc/platforms/52xx/efika.c @@ -99,7 +99,7 @@ static void __init efika_pcisetup(void) bus_range = of_get_property(pcictrl, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { printk(KERN_WARNING EFIKA_PLATFORM_NAME - ": Can't get bus-range for %s\n", pcictrl->full_name); + ": Can't get bus-range for %pOF\n", pcictrl); goto out_put; } @@ -109,14 +109,14 @@ static void __init efika_pcisetup(void) else printk(KERN_INFO EFIKA_PLATFORM_NAME ": PCI buses %d..%d", bus_range[0], bus_range[1]); - printk(" controlled by %s\n", pcictrl->full_name); + printk(" controlled by %pOF\n", pcictrl); printk("\n"); hose = pcibios_alloc_controller(pcictrl); if (!hose) { printk(KERN_WARNING EFIKA_PLATFORM_NAME - ": Can't allocate PCI controller structure for %s\n", - pcictrl->full_name); + ": Can't allocate PCI controller structure for %pOF\n", + pcictrl); goto out_put; } diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c index a3227040cc86..1fcab233d2f2 100644 --- a/arch/powerpc/platforms/52xx/media5200.c +++ b/arch/powerpc/platforms/52xx/media5200.c @@ -156,7 +156,7 @@ static void __init media5200_init_irq(void) fpga_np = of_find_compatible_node(NULL, NULL, "fsl,media5200-fpga"); if (!fpga_np) goto out; - pr_debug("%s: found fpga node: %s\n", __func__, fpga_np->full_name); + pr_debug("%s: found fpga node: %pOF\n", __func__, fpga_np); media5200_irq.regs = of_iomap(fpga_np, 0); if (!media5200_irq.regs) diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 22645a7c6b8a..9e974b1e1697 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -226,7 +226,7 @@ static int mpc52xx_gpt_irq_xlate(struct irq_domain *h, struct device_node *ct, dev_dbg(gpt->dev, "%s: flags=%i\n", __func__, intspec[0]); if ((intsize < 1) || (intspec[0] > 3)) { - dev_err(gpt->dev, "bad irq specifier in %s\n", ct->full_name); + dev_err(gpt->dev, "bad irq specifier in %pOF\n", ct); return -EINVAL; } @@ -331,7 +331,7 @@ mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) if (!of_find_property(node, "gpio-controller", NULL)) return; - gpt->gc.label = kstrdup(node->full_name, GFP_KERNEL); + gpt->gc.label = kasprintf(GFP_KERNEL, "%pOF", node); if (!gpt->gc.label) { dev_err(gpt->dev, "out of memory\n"); return; diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pci.c b/arch/powerpc/platforms/52xx/mpc52xx_pci.c index 00282c2b0cae..af0f79995214 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_pci.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_pci.c @@ -369,19 +369,19 @@ mpc52xx_add_bridge(struct device_node *node) const int *bus_range; struct resource rsrc; - pr_debug("Adding MPC52xx PCI host bridge %s\n", node->full_name); + pr_debug("Adding MPC52xx PCI host bridge %pOF\n", node); pci_add_flags(PCI_REASSIGN_ALL_BUS); if (of_address_to_resource(node, 0, &rsrc) != 0) { - printk(KERN_ERR "Can't get %s resources\n", node->full_name); + printk(KERN_ERR "Can't get %pOF resources\n", node); return -EINVAL; } bus_range = of_get_property(node, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get %s bus-range, assume bus 0\n", - node->full_name); + printk(KERN_WARNING "Can't get %pOF bus-range, assume bus 0\n", + node); bus_range = NULL; } diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 63c5ab6489c9..96bb55ca61d3 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -128,7 +128,7 @@ static int mcu_gpiochip_add(struct mcu *mcu) return -ENODEV; gc->owner = THIS_MODULE; - gc->label = np->full_name; + gc->label = kasprintf(GFP_KERNEL, "%pOF", np); gc->can_sleep = 1; gc->ngpio = MCU_NUM_GPIO; gc->base = -1; @@ -141,6 +141,7 @@ static int mcu_gpiochip_add(struct mcu *mcu) static int mcu_gpiochip_remove(struct mcu *mcu) { + kfree(mcu->gc.label); gpiochip_remove(&mcu->gc); return 0; } diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c index d7c9b186954d..a4539c5accb0 100644 --- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c +++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c @@ -89,7 +89,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk, goto err; ret = of_irq_to_resource(np, 0, &res[1]); - if (!ret) + if (ret <= 0) goto err; pdev = platform_device_alloc("mpc83xx_spi", i); @@ -113,7 +113,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk, unreg: platform_device_del(pdev); err: - pr_err("%s: registration failed\n", np->full_name); + pr_err("%pOF: registration failed\n", np); next: i++; } diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 978b85bb3233..7fa3e197871a 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -361,7 +361,7 @@ static int pmc_probe(struct platform_device *ofdev) return -EBUSY; } - pmc_regs = ioremap(res.start, sizeof(struct mpc83xx_pmc)); + pmc_regs = ioremap(res.start, sizeof(*pmc_regs)); if (!pmc_regs) { ret = -ENOMEM; @@ -374,7 +374,7 @@ static int pmc_probe(struct platform_device *ofdev) goto out_pmc; } - clock_regs = ioremap(res.start, sizeof(struct mpc83xx_pmc)); + clock_regs = ioremap(res.start, sizeof(*clock_regs)); if (!clock_regs) { ret = -ENOMEM; diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c index 0908abd7e36f..9fb57f78cdbe 100644 --- a/arch/powerpc/platforms/85xx/p1022_ds.c +++ b/arch/powerpc/platforms/85xx/p1022_ds.c @@ -508,8 +508,8 @@ static void __init p1022_ds_setup_arch(void) * allocate one static local variable for each * call to this function. */ - pr_info("p1022ds: disabling %s node", - np2->full_name); + pr_info("p1022ds: disabling %pOF node", + np2); of_update_property(np2, &nor_status); of_node_put(np2); } @@ -524,8 +524,8 @@ static void __init p1022_ds_setup_arch(void) .length = sizeof("disabled"), }; - pr_info("p1022ds: disabling %s node", - np2->full_name); + pr_info("p1022ds: disabling %pOF node", + np2); of_update_property(np2, &nand_status); of_node_put(np2); } diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c index cd6ce845f398..77e618dce4a8 100644 --- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c +++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c @@ -100,8 +100,8 @@ static void xes_mpc85xx_fixups(void) err = of_address_to_resource(np, 0, &r[0]); if (err) { printk(KERN_WARNING "xes_mpc85xx: Could not get " - "resource for device tree node '%s'", - np->full_name); + "resource for device tree node '%pOF'", + np); continue; } diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig index 80cbcb0ad9b1..536b0c5d5ce3 100644 --- a/arch/powerpc/platforms/8xx/Kconfig +++ b/arch/powerpc/platforms/8xx/Kconfig @@ -5,7 +5,6 @@ config CPM1 choice prompt "8xx Machine Type" depends on PPC_8xx - depends on 8xx default MPC885ADS config MPC8XXFADS @@ -92,7 +91,7 @@ endmenu # menu "MPC8xx CPM Options" - depends on 8xx + depends on PPC_8xx # This doesn't really belong here, but it is convenient to ask # 8xx specific questions. diff --git a/arch/powerpc/platforms/8xx/Makefile b/arch/powerpc/platforms/8xx/Makefile index 76a81c3350a8..f9af3218bd9c 100644 --- a/arch/powerpc/platforms/8xx/Makefile +++ b/arch/powerpc/platforms/8xx/Makefile @@ -1,7 +1,7 @@ # # Makefile for the PowerPC 8xx linux kernel. # -obj-$(CONFIG_PPC_8xx) += m8xx_setup.o +obj-y += m8xx_setup.o machine_check.o pic.o obj-$(CONFIG_MPC885ADS) += mpc885ads_setup.o obj-$(CONFIG_MPC86XADS) += mpc86xads_setup.o obj-$(CONFIG_PPC_EP88XC) += ep88xc.o diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c index f81069f79a94..1917d69f84df 100644 --- a/arch/powerpc/platforms/8xx/m8xx_setup.c +++ b/arch/powerpc/platforms/8xx/m8xx_setup.c @@ -23,7 +23,7 @@ #include <asm/fs_pd.h> #include <mm/mmu_decl.h> -#include <sysdev/mpc8xx_pic.h> +#include "pic.h" #include "mpc8xx.h" diff --git a/arch/powerpc/platforms/8xx/machine_check.c b/arch/powerpc/platforms/8xx/machine_check.c new file mode 100644 index 000000000000..402016705a39 --- /dev/null +++ b/arch/powerpc/platforms/8xx/machine_check.c @@ -0,0 +1,37 @@ +/* + * 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/kernel.h> +#include <linux/printk.h> +#include <linux/ptrace.h> + +#include <asm/reg.h> + +int machine_check_8xx(struct pt_regs *regs) +{ + unsigned long reason = regs->msr; + + pr_err("Machine check in kernel mode.\n"); + pr_err("Caused by (from SRR1=%lx): ", reason); + if (reason & 0x40000000) + pr_err("Fetch error at address %lx\n", regs->nip); + else + pr_err("Data access error at address %lx\n", regs->dar); + +#ifdef CONFIG_PCI + /* the qspan pci read routines can cause machine checks -- Cort + * + * yuck !!! that totally needs to go away ! There are better ways + * to deal with that than having a wart in the mcheck handler. + * -- BenH + */ + bad_page_fault(regs, regs->dar, SIGBUS); + return 1; +#else + return 0; +#endif +} diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/platforms/8xx/pic.c index 2842f9d63d21..8d5a25d43ef3 100644 --- a/arch/powerpc/sysdev/mpc8xx_pic.c +++ b/arch/powerpc/platforms/8xx/pic.c @@ -9,7 +9,7 @@ #include <asm/io.h> #include <asm/8xx_immap.h> -#include "mpc8xx_pic.h" +#include "pic.h" #define PIC_VEC_SPURRIOUS 15 diff --git a/arch/powerpc/sysdev/mpc8xx_pic.h b/arch/powerpc/platforms/8xx/pic.h index 9fe00eebdc8b..9fe00eebdc8b 100644 --- a/arch/powerpc/sysdev/mpc8xx_pic.h +++ b/arch/powerpc/platforms/8xx/pic.h diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 2f629e0551e9..13663efc1d31 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -32,7 +32,6 @@ config PPC_85xx config PPC_8xx bool "Freescale 8xx" select FSL_SOC - select 8xx select PPC_LIB_RHEAP select SYS_SUPPORTS_HUGETLBFS @@ -149,10 +148,6 @@ config 6xx depends on PPC32 && PPC_BOOK3S select PPC_HAVE_PMU_SUPPORT -# this is temp to handle compat with arch=ppc -config 8xx - bool - config E500 select FSL_EMB_PERFMON select PPC_FSL_BOOK3E @@ -271,44 +266,6 @@ config VSX If in doubt, say Y here. -config PPC_ICSWX - bool "Support for PowerPC icswx coprocessor instruction" - depends on PPC_BOOK3S_64 - default n - ---help--- - - This option enables kernel support for the PowerPC Initiate - Coprocessor Store Word (icswx) coprocessor instruction on POWER7 - and POWER8 processors. POWER9 uses new copy/paste instructions - to invoke the coprocessor. - - This option is only useful if you have a processor that supports - the icswx coprocessor instruction. It does not have any effect - on processors without the icswx coprocessor instruction. - - This option slightly increases kernel memory usage. - - If in doubt, say N here. - -config PPC_ICSWX_PID - bool "icswx requires direct PID management" - depends on PPC_ICSWX - default y - ---help--- - The PID register in server is used explicitly for ICSWX. In - embedded systems PID management is done by the system. - -config PPC_ICSWX_USE_SIGILL - bool "Should a bad CT cause a SIGILL?" - depends on PPC_ICSWX - default n - ---help--- - Should a bad CT used for "non-record form ICSWX" cause an - illegal instruction signal or should it be silent as - architected. - - If in doubt, say N here. - config SPE_POSSIBLE def_bool y depends on E200 || (E500 && !PPC_E500MC) @@ -413,7 +370,7 @@ config NR_CPUS config NOT_COHERENT_CACHE bool - depends on 4xx || 8xx || E200 || PPC_MPC512x || GAMECUBE_COMMON + depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || GAMECUBE_COMMON default n if PPC_47x default y diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile index 469ef170d218..d7a55ecfaee5 100644 --- a/arch/powerpc/platforms/Makefile +++ b/arch/powerpc/platforms/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_FSL_ULI1575) += fsl_uli1575.o obj-$(CONFIG_PPC_PMAC) += powermac/ obj-$(CONFIG_PPC_CHRP) += chrp/ +obj-$(CONFIG_4xx) += 4xx/ obj-$(CONFIG_40x) += 40x/ obj-$(CONFIG_44x) += 44x/ obj-$(CONFIG_PPC_MPC512x) += 512x/ diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c index 45cb9821173c..b9d466cc2b8a 100644 --- a/arch/powerpc/platforms/amigaone/setup.c +++ b/arch/powerpc/platforms/amigaone/setup.c @@ -40,7 +40,7 @@ static int __init amigaone_add_bridge(struct device_node *dev) const int *bus_range; struct pci_controller *hose; - printk(KERN_INFO "Adding PCI host bridge %s\n", dev->full_name); + printk(KERN_INFO "Adding PCI host bridge %pOF\n", dev); cfg_addr = of_get_address(dev, 0, NULL, NULL); cfg_data = of_get_address(dev, 1, NULL, NULL); @@ -49,8 +49,8 @@ static int __init amigaone_add_bridge(struct device_node *dev) bus_range = of_get_property(dev, "bus-range", &len); if ((bus_range == NULL) || (len < 2 * sizeof(int))) - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); hose = pcibios_alloc_controller(dev); if (hose == NULL) diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 8d3ae2cc52bf..6ea3f248b155 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -187,8 +187,8 @@ static struct axon_msic *find_msi_translator(struct pci_dev *dev) irq_domain = irq_find_host(dn); if (!irq_domain) { - dev_dbg(&dev->dev, "axon_msi: no irq_domain found for node %s\n", - dn->full_name); + dev_dbg(&dev->dev, "axon_msi: no irq_domain found for node %pOF\n", + dn); goto out_error; } @@ -326,8 +326,8 @@ static void axon_msi_shutdown(struct platform_device *device) struct axon_msic *msic = dev_get_drvdata(&device->dev); u32 tmp; - pr_devel("axon_msi: disabling %s\n", - irq_domain_get_of_node(msic->irq_domain)->full_name); + pr_devel("axon_msi: disabling %pOF\n", + irq_domain_get_of_node(msic->irq_domain)); tmp = dcr_read(msic->dcr_host, MSIC_CTRL_REG); tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE; msic_dcr_write(msic, MSIC_CTRL_REG, tmp); @@ -340,12 +340,12 @@ static int axon_msi_probe(struct platform_device *device) unsigned int virq; int dcr_base, dcr_len; - pr_devel("axon_msi: setting up dn %s\n", dn->full_name); + pr_devel("axon_msi: setting up dn %pOF\n", dn); msic = kzalloc(sizeof(struct axon_msic), GFP_KERNEL); if (!msic) { - printk(KERN_ERR "axon_msi: couldn't allocate msic for %s\n", - dn->full_name); + printk(KERN_ERR "axon_msi: couldn't allocate msic for %pOF\n", + dn); goto out; } @@ -354,30 +354,30 @@ static int axon_msi_probe(struct platform_device *device) if (dcr_base == 0 || dcr_len == 0) { printk(KERN_ERR - "axon_msi: couldn't parse dcr properties on %s\n", - dn->full_name); + "axon_msi: couldn't parse dcr properties on %pOF\n", + dn); goto out_free_msic; } msic->dcr_host = dcr_map(dn, dcr_base, dcr_len); if (!DCR_MAP_OK(msic->dcr_host)) { - printk(KERN_ERR "axon_msi: dcr_map failed for %s\n", - dn->full_name); + printk(KERN_ERR "axon_msi: dcr_map failed for %pOF\n", + dn); goto out_free_msic; } msic->fifo_virt = dma_alloc_coherent(&device->dev, MSIC_FIFO_SIZE_BYTES, &msic->fifo_phys, GFP_KERNEL); if (!msic->fifo_virt) { - printk(KERN_ERR "axon_msi: couldn't allocate fifo for %s\n", - dn->full_name); + printk(KERN_ERR "axon_msi: couldn't allocate fifo for %pOF\n", + dn); goto out_free_msic; } virq = irq_of_parse_and_map(dn, 0); if (!virq) { - printk(KERN_ERR "axon_msi: irq parse and map failed for %s\n", - dn->full_name); + printk(KERN_ERR "axon_msi: irq parse and map failed for %pOF\n", + dn); goto out_free_fifo; } memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES); @@ -385,8 +385,8 @@ static int axon_msi_probe(struct platform_device *device) /* We rely on being able to stash a virq in a u16, so limit irqs to < 65536 */ msic->irq_domain = irq_domain_add_nomap(dn, 65536, &msic_host_ops, msic); if (!msic->irq_domain) { - printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n", - dn->full_name); + printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %pOF\n", + dn); goto out_free_fifo; } @@ -412,7 +412,7 @@ static int axon_msi_probe(struct platform_device *device) axon_msi_debug_setup(dn, msic); - printk(KERN_DEBUG "axon_msi: setup MSIC on %s\n", dn->full_name); + printk(KERN_DEBUG "axon_msi: setup MSIC on %pOF\n", dn); return 0; diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c index 871d38479a25..6fc85e29dc08 100644 --- a/arch/powerpc/platforms/cell/interrupt.c +++ b/arch/powerpc/platforms/cell/interrupt.c @@ -303,8 +303,8 @@ static void __init init_one_iic(unsigned int hw_cpu, unsigned long addr, iic->node = of_node_get(node); out_be64(&iic->regs->prio, 0); - printk(KERN_INFO "IIC for CPU %d target id 0x%x : %s\n", - hw_cpu, iic->target_id, node->full_name); + printk(KERN_INFO "IIC for CPU %d target id 0x%x : %pOF\n", + hw_cpu, iic->target_id, node); } static int __init setup_iic(void) diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 29d4f96ed33e..4b91ad08eefd 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -278,8 +278,8 @@ static int cell_iommu_find_ioc(int nid, unsigned long *base) if (of_node_to_nid(np) != nid) continue; if (of_address_to_resource(np, 0, &r)) { - printk(KERN_ERR "iommu: can't get address for %s\n", - np->full_name); + printk(KERN_ERR "iommu: can't get address for %pOF\n", + np); continue; } *base = r.start; @@ -458,8 +458,8 @@ static inline u32 cell_iommu_get_ioid(struct device_node *np) ioid = of_get_property(np, "ioid", NULL); if (ioid == NULL) { - printk(KERN_WARNING "iommu: missing ioid for %s using 0\n", - np->full_name); + printk(KERN_WARNING "iommu: missing ioid for %pOF using 0\n", + np); return 0; } @@ -559,8 +559,8 @@ static struct iommu_table *cell_get_iommu_table(struct device *dev) */ iommu = cell_iommu_for_node(dev_to_node(dev)); if (iommu == NULL || list_empty(&iommu->windows)) { - dev_err(dev, "iommu: missing iommu for %s (node %d)\n", - of_node_full_name(dev->of_node), dev_to_node(dev)); + dev_err(dev, "iommu: missing iommu for %pOF (node %d)\n", + dev->of_node, dev_to_node(dev)); return NULL; } window = list_entry(iommu->windows.next, struct iommu_window, list); @@ -720,12 +720,12 @@ static struct cbe_iommu * __init cell_iommu_alloc(struct device_node *np) /* Get node ID */ nid = of_node_to_nid(np); if (nid < 0) { - printk(KERN_ERR "iommu: failed to get node for %s\n", - np->full_name); + printk(KERN_ERR "iommu: failed to get node for %pOF\n", + np); return NULL; } - pr_debug("iommu: setting up iommu for node %d (%s)\n", - nid, np->full_name); + pr_debug("iommu: setting up iommu for node %d (%pOF)\n", + nid, np); /* XXX todo: If we can have multiple windows on the same IOMMU, which * isn't the case today, we probably want here to check whether the @@ -736,8 +736,8 @@ static struct cbe_iommu * __init cell_iommu_alloc(struct device_node *np) */ if (cbe_nr_iommus >= NR_IOMMUS) { - printk(KERN_ERR "iommu: too many IOMMUs detected ! (%s)\n", - np->full_name); + printk(KERN_ERR "iommu: too many IOMMUs detected ! (%pOF)\n", + np); return NULL; } diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index 460ab392f0e7..2f704afe9af3 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -196,8 +196,8 @@ static int __init cbe_ptcal_enable(void) for_each_node_by_type(np, "cpu") { const u32 *nid = of_get_property(np, "node-id", NULL); if (!nid) { - printk(KERN_ERR "%s: node %s is missing node-id?\n", - __func__, np->full_name); + printk(KERN_ERR "%s: node %pOF is missing node-id?\n", + __func__, np); continue; } cbe_ptcal_enable_on_node(*nid, order); diff --git a/arch/powerpc/platforms/cell/spider-pci.c b/arch/powerpc/platforms/cell/spider-pci.c index f1f7878893f3..d1e61e273e64 100644 --- a/arch/powerpc/platforms/cell/spider-pci.c +++ b/arch/powerpc/platforms/cell/spider-pci.c @@ -130,8 +130,8 @@ int __init spiderpci_iowa_init(struct iowa_bus *bus, void *data) struct resource r; unsigned long offset = (unsigned long)data; - pr_debug("SPIDERPCI-IOWA:Bus initialize for spider(%s)\n", - np->full_name); + pr_debug("SPIDERPCI-IOWA:Bus initialize for spider(%pOF)\n", + np); priv = kzalloc(sizeof(struct spiderpci_iowa_private), GFP_KERNEL); if (!priv) { diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c index ff924af00e78..aa44bfc46467 100644 --- a/arch/powerpc/platforms/cell/spider-pic.c +++ b/arch/powerpc/platforms/cell/spider-pic.c @@ -323,8 +323,8 @@ static void __init spider_init_one(struct device_node *of_node, int chip, irq_set_handler_data(virq, pic); irq_set_chained_handler(virq, spider_irq_cascade); - printk(KERN_INFO "spider_pic: node %d, addr: 0x%lx %s\n", - pic->node_id, addr, of_node->full_name); + printk(KERN_INFO "spider_pic: node %d, addr: 0x%lx %pOF\n", + pic->node_id, addr, of_node); /* Enable the interrupt detection enable bit. Do this last! */ out_be32(pic->regs + TIR_DEN, in_be32(pic->regs + TIR_DEN) | 0x1); diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c index 672d310dcf14..f636ee22b203 100644 --- a/arch/powerpc/platforms/cell/spu_manage.c +++ b/arch/powerpc/platforms/cell/spu_manage.c @@ -191,8 +191,8 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np) goto err; } ret = -EINVAL; - pr_debug(" irq %d no 0x%x on %s\n", i, oirq.args[0], - oirq.np->full_name); + pr_debug(" irq %d no 0x%x on %pOF\n", i, oirq.args[0], + oirq.np); spu->irqs[i] = irq_create_of_mapping(&oirq); if (!spu->irqs[i]) { pr_debug("spu_new: failed to map it !\n"); @@ -243,32 +243,32 @@ static int __init spu_map_device(struct spu *spu) ret = spu_map_resource(spu, 0, (void __iomem**)&spu->local_store, &spu->local_store_phys); if (ret) { - pr_debug("spu_new: failed to map %s resource 0\n", - np->full_name); + pr_debug("spu_new: failed to map %pOF resource 0\n", + np); goto out; } ret = spu_map_resource(spu, 1, (void __iomem**)&spu->problem, &spu->problem_phys); if (ret) { - pr_debug("spu_new: failed to map %s resource 1\n", - np->full_name); + pr_debug("spu_new: failed to map %pOF resource 1\n", + np); goto out_unmap; } ret = spu_map_resource(spu, 2, (void __iomem**)&spu->priv2, NULL); if (ret) { - pr_debug("spu_new: failed to map %s resource 2\n", - np->full_name); + pr_debug("spu_new: failed to map %pOF resource 2\n", + np); goto out_unmap; } if (!firmware_has_feature(FW_FEATURE_LPAR)) ret = spu_map_resource(spu, 3, (void __iomem**)&spu->priv1, NULL); if (ret) { - pr_debug("spu_new: failed to map %s resource 3\n", - np->full_name); + pr_debug("spu_new: failed to map %pOF resource 3\n", + np); goto out_unmap; } - pr_debug("spu_new: %s maps:\n", np->full_name); + pr_debug("spu_new: %pOF maps:\n", np); pr_debug(" local store : 0x%016lx -> 0x%p\n", spu->local_store_phys, spu->local_store); pr_debug(" problem state : 0x%016lx -> 0x%p\n", @@ -316,8 +316,8 @@ static int __init of_create_spu(struct spu *spu, void *data) spu->node = of_node_to_nid(spe); if (spu->node >= MAX_NUMNODES) { - printk(KERN_WARNING "SPE %s on node %d ignored," - " node number too big\n", spe->full_name, spu->node); + printk(KERN_WARNING "SPE %pOF on node %d ignored," + " node number too big\n", spe, spu->node); printk(KERN_WARNING "Check if CONFIG_NUMA is enabled.\n"); ret = -ENODEV; goto out; diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index ae2f740a82f1..5ffcdeb1eb17 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1749,7 +1749,7 @@ out: static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file_inode(file); - int err = filemap_write_and_wait_range(inode->i_mapping, start, end); + int err = file_write_and_wait_range(file, start, end); if (!err) { inode_lock(inode); err = spufs_mfc_flush(file, NULL); diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c index 1b87e198faa7..27264794f5c0 100644 --- a/arch/powerpc/platforms/chrp/pci.c +++ b/arch/powerpc/platforms/chrp/pci.c @@ -235,14 +235,14 @@ chrp_find_bridges(void) ++index; /* The GG2 bridge on the LongTrail doesn't have an address */ if (of_address_to_resource(dev, 0, &r) && !is_longtrail) { - printk(KERN_WARNING "Can't use %s: no address\n", - dev->full_name); + printk(KERN_WARNING "Can't use %pOF: no address\n", + dev); continue; } bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s\n", - dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF\n", + dev); continue; } if (bus_range[1] == bus_range[0]) @@ -250,15 +250,15 @@ chrp_find_bridges(void) else printk(KERN_INFO "PCI buses %d..%d", bus_range[0], bus_range[1]); - printk(" controlled by %s", dev->full_name); + printk(" controlled by %pOF", dev); if (!is_longtrail) printk(" at %llx", (unsigned long long)r.start); printk("\n"); hose = pcibios_alloc_controller(dev); if (!hose) { - printk("Can't allocate PCI controller structure for %s\n", - dev->full_name); + printk("Can't allocate PCI controller structure for %pOF\n", + dev); continue; } hose->first_busno = hose->self_busno = bus_range[0]; @@ -297,8 +297,8 @@ chrp_find_bridges(void) } } } else { - printk("No methods for %s (model %s), using RTAS\n", - dev->full_name, model); + printk("No methods for %pOF (model %s), using RTAS\n", + dev, model); hose->ops = &rtas_pci_ops; } diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c index 2b4dc6abde6c..19760712b39d 100644 --- a/arch/powerpc/platforms/chrp/pegasos_eth.c +++ b/arch/powerpc/platforms/chrp/pegasos_eth.c @@ -63,7 +63,7 @@ static struct platform_device mv643xx_eth_mvmdio_device = { .name = "orion-mdio", .id = -1, .num_resources = ARRAY_SIZE(mv643xx_eth_mvmdio_resources), - .resource = mv643xx_eth_shared_resources, + .resource = mv643xx_eth_mvmdio_resources, }; static struct resource mv643xx_eth_port1_resources[] = { diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c index f29cf29b11f8..f514d5d28cd4 100644 --- a/arch/powerpc/platforms/embedded6xx/linkstation.c +++ b/arch/powerpc/platforms/embedded6xx/linkstation.c @@ -41,12 +41,12 @@ static int __init linkstation_add_bridge(struct device_node *dev) struct pci_controller *hose; const int *bus_range; - printk("Adding PCI host bridge %s\n", dev->full_name); + printk("Adding PCI host bridge %pOF\n", dev); bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); hose = pcibios_alloc_controller(dev); if (hose == NULL) diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c index 8e3590941960..273dfa3f0252 100644 --- a/arch/powerpc/platforms/embedded6xx/mvme5100.c +++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c @@ -115,7 +115,7 @@ static int __init mvme5100_add_bridge(struct device_node *dev) struct pci_controller *hose; unsigned short devid; - pr_info("Adding PCI host bridge %s\n", dev->full_name); + pr_info("Adding PCI host bridge %pOF\n", dev); bus_range = of_get_property(dev, "bus-range", &len); diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index 471a50bcd074..ed1914dd34bb 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -44,7 +44,7 @@ static int __init storcenter_add_bridge(struct device_node *dev) struct pci_controller *hose; const int *bus_range; - printk("Adding PCI host bridge %s\n", dev->full_name); + printk("Adding PCI host bridge %pOF\n", dev); hose = pcibios_alloc_controller(dev); if (hose == NULL) diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index 69794d9389c2..e3821379e86f 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -73,8 +73,8 @@ static void __init fixup_bus_range(struct device_node *bridge) /* Lookup the "bus-range" property for the hose */ prop = of_find_property(bridge, "bus-range", &len); if (prop == NULL || prop->value == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s\n", - bridge->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF\n", + bridge); return; } bus_range = prop->value; @@ -498,12 +498,12 @@ static int __init maple_add_bridge(struct device_node *dev) const int *bus_range; int primary = 1; - DBG("Adding PCI host bridge %s\n", dev->full_name); + DBG("Adding PCI host bridge %pOF\n", dev); bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s, assume bus 0\n", - dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume bus 0\n", + dev); } hose = pcibios_alloc_controller(dev); diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index 10c4e8fc6ea9..5ff6108f19e9 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -193,7 +193,7 @@ static int __init pas_add_bridge(struct device_node *dev) { struct pci_controller *hose; - pr_debug("Adding PCI host bridge %s\n", dev->full_name); + pr_debug("Adding PCI host bridge %pOF\n", dev); hose = pcibios_alloc_controller(dev); if (!hose) diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 1e02328c3f2d..9e3f39d36e88 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -2658,25 +2658,25 @@ static void __init probe_one_macio(const char *name, const char *compat, int typ if (i >= MAX_MACIO_CHIPS) { printk(KERN_ERR "pmac_feature: Please increase MAX_MACIO_CHIPS !\n"); - printk(KERN_ERR "pmac_feature: %s skipped\n", node->full_name); + printk(KERN_ERR "pmac_feature: %pOF skipped\n", node); return; } addrp = of_get_pci_address(node, 0, &size, NULL); if (addrp == NULL) { - printk(KERN_ERR "pmac_feature: %s: can't find base !\n", - node->full_name); + printk(KERN_ERR "pmac_feature: %pOF: can't find base !\n", + node); return; } addr = of_translate_address(node, addrp); if (addr == 0) { - printk(KERN_ERR "pmac_feature: %s, can't translate base !\n", - node->full_name); + printk(KERN_ERR "pmac_feature: %pOF, can't translate base !\n", + node); return; } base = ioremap(addr, (unsigned long)size); if (!base) { - printk(KERN_ERR "pmac_feature: %s, can't map mac-io chip !\n", - node->full_name); + printk(KERN_ERR "pmac_feature: %pOF, can't map mac-io chip !\n", + node); return; } if (type == macio_keylargo || type == macio_keylargo2) { diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index f627c9fd7b48..70183eb3d5c8 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -494,8 +494,8 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np) host = kzalloc(sizeof(struct pmac_i2c_host_kw), GFP_KERNEL); if (host == NULL) { - printk(KERN_ERR "low_i2c: Can't allocate host for %s\n", - np->full_name); + printk(KERN_ERR "low_i2c: Can't allocate host for %pOF\n", + np); return NULL; } @@ -505,8 +505,8 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np) */ addrp = of_get_property(np, "AAPL,address", NULL); if (addrp == NULL) { - printk(KERN_ERR "low_i2c: Can't find address for %s\n", - np->full_name); + printk(KERN_ERR "low_i2c: Can't find address for %pOF\n", + np); kfree(host); return NULL; } @@ -538,13 +538,13 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np) host->irq = irq_of_parse_and_map(np, 0); if (!host->irq) printk(KERN_WARNING - "low_i2c: Failed to map interrupt for %s\n", - np->full_name); + "low_i2c: Failed to map interrupt for %pOF\n", + np); host->base = ioremap((*addrp), 0x1000); if (host->base == NULL) { - printk(KERN_ERR "low_i2c: Can't map registers for %s\n", - np->full_name); + printk(KERN_ERR "low_i2c: Can't map registers for %pOF\n", + np); kfree(host); return NULL; } @@ -560,8 +560,8 @@ static struct pmac_i2c_host_kw *__init kw_i2c_host_init(struct device_node *np) "keywest i2c", host)) host->irq = 0; - printk(KERN_INFO "KeyWest i2c @0x%08x irq %d %s\n", - *addrp, host->irq, np->full_name); + printk(KERN_INFO "KeyWest i2c @0x%08x irq %d %pOF\n", + *addrp, host->irq, np); return host; } @@ -798,7 +798,7 @@ static void __init pmu_i2c_probe(void) if (busnode == NULL) return; - printk(KERN_INFO "PMU i2c %s\n", busnode->full_name); + printk(KERN_INFO "PMU i2c %pOF\n", busnode); /* * We add bus 1 and 2 only for now, bus 0 is "special" @@ -913,7 +913,7 @@ static void __init smu_i2c_probe(void) if (controller == NULL) return; - printk(KERN_INFO "SMU i2c %s\n", controller->full_name); + printk(KERN_INFO "SMU i2c %pOF\n", controller); /* Look for childs, note that they might not be of the right * type as older device trees mix i2c busses and other things @@ -945,8 +945,8 @@ static void __init smu_i2c_probe(void) bus->flags = 0; list_add(&bus->link, &pmac_i2c_busses); - printk(KERN_INFO " channel %x bus %s\n", - bus->channel, busnode->full_name); + printk(KERN_INFO " channel %x bus %pOF\n", + bus->channel, busnode); } } @@ -1129,7 +1129,7 @@ int pmac_i2c_setmode(struct pmac_i2c_bus *bus, int mode) */ if (mode < pmac_i2c_mode_dumb || mode > pmac_i2c_mode_combined) { printk(KERN_ERR "low_i2c: Invalid mode %d requested on" - " bus %s !\n", mode, bus->busnode->full_name); + " bus %pOF !\n", mode, bus->busnode); return -EINVAL; } bus->mode = mode; @@ -1146,8 +1146,8 @@ int pmac_i2c_xfer(struct pmac_i2c_bus *bus, u8 addrdir, int subsize, WARN_ON(!bus->opened); DBG("xfer() chan=%d, addrdir=0x%x, mode=%d, subsize=%d, subaddr=0x%x," - " %d bytes, bus %s\n", bus->channel, addrdir, bus->mode, subsize, - subaddr, len, bus->busnode->full_name); + " %d bytes, bus %pOF\n", bus->channel, addrdir, bus->mode, subsize, + subaddr, len, bus->busnode); rc = bus->xfer(bus, addrdir, subsize, subaddr, data, len); @@ -1241,13 +1241,13 @@ static void* pmac_i2c_do_begin(struct pmf_function *func, struct pmf_args *args) bus = pmac_i2c_find_bus(func->node); if (bus == NULL) { - printk(KERN_ERR "low_i2c: Can't find bus for %s (pfunc)\n", - func->node->full_name); + printk(KERN_ERR "low_i2c: Can't find bus for %pOF (pfunc)\n", + func->node); return NULL; } if (pmac_i2c_open(bus, 0)) { - printk(KERN_ERR "low_i2c: Can't open i2c bus for %s (pfunc)\n", - func->node->full_name); + printk(KERN_ERR "low_i2c: Can't open i2c bus for %pOF (pfunc)\n", + func->node); return NULL; } @@ -1417,7 +1417,7 @@ static struct pmf_handlers pmac_i2c_pfunc_handlers = { static void __init pmac_i2c_dev_create(struct device_node *np, int quirks) { - DBG("dev_create(%s)\n", np->full_name); + DBG("dev_create(%pOF)\n", np); pmf_register_driver(np, &pmac_i2c_pfunc_handlers, (void *)(long)quirks); @@ -1425,20 +1425,20 @@ static void __init pmac_i2c_dev_create(struct device_node *np, int quirks) static void __init pmac_i2c_dev_init(struct device_node *np, int quirks) { - DBG("dev_create(%s)\n", np->full_name); + DBG("dev_create(%pOF)\n", np); pmf_do_functions(np, NULL, 0, PMF_FLAGS_ON_INIT, NULL); } static void pmac_i2c_dev_suspend(struct device_node *np, int quirks) { - DBG("dev_suspend(%s)\n", np->full_name); + DBG("dev_suspend(%pOF)\n", np); pmf_do_functions(np, NULL, 0, PMF_FLAGS_ON_SLEEP, NULL); } static void pmac_i2c_dev_resume(struct device_node *np, int quirks) { - DBG("dev_resume(%s)\n", np->full_name); + DBG("dev_resume(%pOF)\n", np); pmf_do_functions(np, NULL, 0, PMF_FLAGS_ON_WAKE, NULL); } diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c index 6e06c3be2e9a..0b8174a79993 100644 --- a/arch/powerpc/platforms/powermac/pci.c +++ b/arch/powerpc/platforms/powermac/pci.c @@ -783,7 +783,7 @@ static int __init pmac_add_bridge(struct device_node *dev) const int *bus_range; int primary = 1, has_address = 0; - DBG("Adding PCI host bridge %s\n", dev->full_name); + DBG("Adding PCI host bridge %pOF\n", dev); /* Fetch host bridge registers address */ has_address = (of_address_to_resource(dev, 0, &rsrc) == 0); @@ -791,8 +791,8 @@ static int __init pmac_add_bridge(struct device_node *dev) /* Get bus range if any */ bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); } hose = pcibios_alloc_controller(dev); diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c index 459138ed4571..860159d46ab8 100644 --- a/arch/powerpc/platforms/powermac/pfunc_base.c +++ b/arch/powerpc/platforms/powermac/pfunc_base.c @@ -54,8 +54,8 @@ static int macio_do_gpio_write(PMF_STD_ARGS, u8 value, u8 mask) raw_spin_lock_irqsave(&feature_lock, flags); tmp = readb(addr); tmp = (tmp & ~mask) | (value & mask); - DBG("Do write 0x%02x to GPIO %s (%p)\n", - tmp, func->node->full_name, addr); + DBG("Do write 0x%02x to GPIO %pOF (%p)\n", + tmp, func->node, addr); writeb(tmp, addr); raw_spin_unlock_irqrestore(&feature_lock, flags); @@ -107,8 +107,8 @@ static void macio_gpio_init_one(struct macio_chip *macio) if (gparent == NULL) return; - DBG("Installing GPIO functions for macio %s\n", - macio->of_node->full_name); + DBG("Installing GPIO functions for macio %pOF\n", + macio->of_node); /* * Ok, got one, we dont need anything special to track them down, so @@ -129,8 +129,8 @@ static void macio_gpio_init_one(struct macio_chip *macio) pmf_register_driver(gp, &macio_gpio_handlers, (void *)offset); } - DBG("Calling initial GPIO functions for macio %s\n", - macio->of_node->full_name); + DBG("Calling initial GPIO functions for macio %pOF\n", + macio->of_node); /* And now we run all the init ones */ for (gp = NULL; (gp = of_get_next_child(gparent, gp)) != NULL;) @@ -267,8 +267,8 @@ static struct pmf_handlers macio_mmio_handlers = { static void macio_mmio_init_one(struct macio_chip *macio) { - DBG("Installing MMIO functions for macio %s\n", - macio->of_node->full_name); + DBG("Installing MMIO functions for macio %pOF\n", + macio->of_node); pmf_register_driver(macio->of_node, &macio_mmio_handlers, macio); } @@ -298,8 +298,8 @@ static void uninorth_install_pfunc(void) { struct device_node *np; - DBG("Installing functions for UniN %s\n", - uninorth_node->full_name); + DBG("Installing functions for UniN %pOF\n", + uninorth_node); /* * Install handlers for the bridge itself @@ -317,8 +317,8 @@ static void uninorth_install_pfunc(void) break; } if (unin_hwclock) { - DBG("Installing functions for UniN clock %s\n", - unin_hwclock->full_name); + DBG("Installing functions for UniN clock %pOF\n", + unin_hwclock); pmf_register_driver(unin_hwclock, &unin_mmio_handlers, NULL); pmf_do_functions(unin_hwclock, NULL, 0, PMF_FLAGS_ON_INIT, NULL); diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c index 695e8c4d4224..df3c93bef228 100644 --- a/arch/powerpc/platforms/powermac/pfunc_core.c +++ b/arch/powerpc/platforms/powermac/pfunc_core.c @@ -708,7 +708,7 @@ int pmf_register_driver(struct device_node *np, if (handlers == NULL) return -EINVAL; - DBG("pmf: registering driver for node %s\n", np->full_name); + DBG("pmf: registering driver for node %pOF\n", np); spin_lock_irqsave(&pmf_lock, flags); dev = pmf_find_device(np); @@ -781,7 +781,7 @@ void pmf_unregister_driver(struct device_node *np) struct pmf_device *dev; unsigned long flags; - DBG("pmf: unregistering driver for node %s\n", np->full_name); + DBG("pmf: unregistering driver for node %pOF\n", np); spin_lock_irqsave(&pmf_lock, flags); dev = pmf_find_device(np); @@ -940,7 +940,7 @@ int pmf_call_one(struct pmf_function *func, struct pmf_args *args) void *instdata = NULL; int rc = 0; - DBG(" ** pmf_call_one(%s/%s) **\n", dev->node->full_name, func->name); + DBG(" ** pmf_call_one(%pOF/%s) **\n", dev->node, func->name); if (dev->handlers->begin) instdata = dev->handlers->begin(func, args); diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index f5f9ad7c3398..5e0719b27294 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -364,8 +364,8 @@ static void __init pmac_pic_probe_oldstyle(void) (addr + 0x10); of_node_put(master); - printk(KERN_INFO "irq: Found primary Apple PIC %s for %d irqs\n", - master->full_name, max_real_irqs); + printk(KERN_INFO "irq: Found primary Apple PIC %pOF for %d irqs\n", + master, max_real_irqs); /* Map interrupts of cascaded controller */ if (slave && !of_address_to_resource(slave, 0, &r)) { @@ -378,8 +378,8 @@ static void __init pmac_pic_probe_oldstyle(void) (addr + 0x10); pmac_irq_cascade = irq_of_parse_and_map(slave, 0); - printk(KERN_INFO "irq: Found slave Apple PIC %s for %d irqs" - " cascade: %d\n", slave->full_name, + printk(KERN_INFO "irq: Found slave Apple PIC %pOF for %d irqs" + " cascade: %d\n", slave, max_irqs - max_real_irqs, pmac_irq_cascade); } of_node_put(slave); diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index 6b4e9d181126..ab668cb72263 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -556,7 +556,7 @@ static int __init check_pmac_serial_console(void) pr_debug(" can't find stdout package %s !\n", name); return -ENODEV; } - pr_debug("stdout is %s\n", prom_stdout->full_name); + pr_debug("stdout is %pOF\n", prom_stdout); name = of_get_property(prom_stdout, "name", NULL); if (!name) { diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 6a6f4ef46b9e..340cbe263b33 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -30,3 +30,25 @@ config OPAL_PRD help This enables the opal-prd driver, a facility to run processor recovery diagnostics on OpenPower machines + +config PPC_MEMTRACE + bool "Enable removal of RAM from kernel mappings for tracing" + depends on PPC_POWERNV && MEMORY_HOTREMOVE + default n + help + Enabling this option allows for the removal of memory (RAM) + from the kernel mappings to be used for hardware tracing. + +config PPC_VAS + bool "IBM Virtual Accelerator Switchboard (VAS)" + depends on PPC_POWERNV && PPC_64K_PAGES + default y + help + This enables support for IBM Virtual Accelerator Switchboard (VAS). + + VAS allows accelerators in co-processors like NX-GZIP and NX-842 + to be accessible to kernel subsystems and user processes. + + VAS adapters are found in POWER9 based systems. + + If unsure, say N. diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index b5d98cb3f482..37d60f7dd86d 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -2,7 +2,7 @@ obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o -obj-y += opal-kmsg.o +obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o @@ -12,3 +12,6 @@ obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o obj-$(CONFIG_OPAL_PRD) += opal-prd.o +obj-$(CONFIG_PERF_EVENTS) += opal-imc.o +obj-$(CONFIG_PPC_MEMTRACE) += memtrace.o +obj-$(CONFIG_PPC_VAS) += vas.o vas-window.o diff --git a/arch/powerpc/platforms/powernv/copy-paste.h b/arch/powerpc/platforms/powernv/copy-paste.h new file mode 100644 index 000000000000..c9a503623431 --- /dev/null +++ b/arch/powerpc/platforms/powernv/copy-paste.h @@ -0,0 +1,46 @@ +/* + * Copyright 2016-17 IBM Corp. + * + * 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/ppc-opcode.h> + +#define CR0_SHIFT 28 +#define CR0_MASK 0xF +/* + * Copy/paste instructions: + * + * copy RA,RB + * Copy contents of address (RA) + effective_address(RB) + * to internal copy-buffer. + * + * paste RA,RB + * Paste contents of internal copy-buffer to the address + * (RA) + effective_address(RB) + */ +static inline int vas_copy(void *crb, int offset) +{ + asm volatile(PPC_COPY(%0, %1)";" + : + : "b" (offset), "b" (crb) + : "memory"); + + return 0; +} + +static inline int vas_paste(void *paste_address, int offset) +{ + u32 cr; + + cr = 0; + asm volatile(PPC_PASTE(%1, %2)";" + "mfocrf %0, 0x80;" + : "=r" (cr) + : "b" (offset), "b" (paste_address) + : "memory", "cr0"); + + return (cr >> CR0_SHIFT) & CR0_MASK; +} diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 3f48f6df1cf3..8864065eba22 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -113,7 +113,6 @@ static ssize_t pnv_eeh_ei_write(struct file *filp, size_t count, loff_t *ppos) { struct pci_controller *hose = filp->private_data; - struct eeh_dev *edev; struct eeh_pe *pe; int pe_no, type, func; unsigned long addr, mask; @@ -135,13 +134,7 @@ static ssize_t pnv_eeh_ei_write(struct file *filp, return -EINVAL; /* Retrieve PE */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return -ENOMEM; - edev->phb = hose; - edev->pe_config_addr = pe_no; - pe = eeh_pe_get(edev); - kfree(edev); + pe = eeh_pe_get(hose, pe_no, 0); if (!pe) return -ENODEV; @@ -359,6 +352,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) struct eeh_dev *edev = pdn_to_eeh_dev(pdn); uint32_t pcie_flags; int ret; + int config_addr = (pdn->busno << 8) | (pdn->devfn); /* * When probing the root bridge, which doesn't have any @@ -393,8 +387,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) } } - edev->config_addr = (pdn->busno << 8) | (pdn->devfn); - edev->pe_config_addr = phb->ioda.pe_rmap[edev->config_addr]; + edev->pe_config_addr = phb->ioda.pe_rmap[config_addr]; /* Create PE */ ret = eeh_add_to_parent_pe(edev); @@ -933,7 +926,6 @@ void pnv_pci_reset_secondary_bus(struct pci_dev *dev) static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type, int pos, u16 mask) { - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); int i, status = 0; /* Wait for Transaction Pending bit to be cleared */ @@ -947,7 +939,7 @@ static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type, pr_warn("%s: Pending transaction while issuing %sFLR to %04x:%02x:%02x.%01x\n", __func__, type, - edev->phb->global_number, pdn->busno, + pdn->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); } @@ -1381,7 +1373,6 @@ static int pnv_eeh_get_pe(struct pci_controller *hose, struct pnv_phb *phb = hose->private_data; struct pnv_ioda_pe *pnv_pe; struct eeh_pe *dev_pe; - struct eeh_dev edev; /* * If PHB supports compound PE, to fetch @@ -1397,10 +1388,7 @@ static int pnv_eeh_get_pe(struct pci_controller *hose, } /* Find the PE according to PE# */ - memset(&edev, 0, sizeof(struct eeh_dev)); - edev.phb = hose; - edev.pe_config_addr = pe_no; - dev_pe = eeh_pe_get(&edev); + dev_pe = eeh_pe_get(hose, pe_no, 0); if (!dev_pe) return -EEXIST; @@ -1711,6 +1699,7 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn) struct eeh_dev *edev = pdn_to_eeh_dev(pdn); struct pnv_phb *phb; s64 ret; + int config_addr = (pdn->busno << 8) | (pdn->devfn); if (!edev) return -EEXIST; @@ -1725,14 +1714,14 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn) if (edev->physfn) { ret = pnv_eeh_restore_vf_config(pdn); } else { - phb = edev->phb->private_data; + phb = pdn->phb->private_data; ret = opal_pci_reinit(phb->opal_id, - OPAL_REINIT_PCI_DEV, edev->config_addr); + OPAL_REINIT_PCI_DEV, config_addr); } if (ret) { pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", - __func__, edev->config_addr, ret); + __func__, config_addr, ret); return -EIO; } diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 2abee070373f..9f59041a172b 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -56,6 +56,7 @@ u64 pnv_first_deep_stop_state = MAX_STOP_STATE; */ static u64 pnv_deepest_stop_psscr_val; static u64 pnv_deepest_stop_psscr_mask; +static u64 pnv_deepest_stop_flag; static bool deepest_stop_found; static int pnv_save_sprs_for_deep_states(void) @@ -68,7 +69,7 @@ static int pnv_save_sprs_for_deep_states(void) * all cpus at boot. Get these reg values of current cpu and use the * same across all cpus. */ - uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1; + uint64_t lpcr_val = mfspr(SPRN_LPCR); uint64_t hid0_val = mfspr(SPRN_HID0); uint64_t hid1_val = mfspr(SPRN_HID1); uint64_t hid4_val = mfspr(SPRN_HID4); @@ -185,8 +186,40 @@ static void pnv_alloc_idle_core_states(void) update_subcore_sibling_mask(); - if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) - pnv_save_sprs_for_deep_states(); + if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT) { + int rc = pnv_save_sprs_for_deep_states(); + + if (likely(!rc)) + return; + + /* + * The stop-api is unable to restore hypervisor + * resources on wakeup from platform idle states which + * lose full context. So disable such states. + */ + supported_cpuidle_states &= ~OPAL_PM_LOSE_FULL_CONTEXT; + pr_warn("cpuidle-powernv: Disabling idle states that lose full context\n"); + pr_warn("cpuidle-powernv: Idle power-savings, CPU-Hotplug affected\n"); + + if (cpu_has_feature(CPU_FTR_ARCH_300) && + (pnv_deepest_stop_flag & OPAL_PM_LOSE_FULL_CONTEXT)) { + /* + * Use the default stop state for CPU-Hotplug + * if available. + */ + if (default_stop_found) { + pnv_deepest_stop_psscr_val = + pnv_default_stop_val; + pnv_deepest_stop_psscr_mask = + pnv_default_stop_mask; + pr_warn("cpuidle-powernv: Offlined CPUs will stop with psscr = 0x%016llx\n", + pnv_deepest_stop_psscr_val); + } else { /* Fallback to snooze loop for CPU-Hotplug */ + deepest_stop_found = false; + pr_warn("cpuidle-powernv: Offlined CPUs will busy wait\n"); + } + } + } } u32 pnv_get_supported_cpuidle_states(void) @@ -355,6 +388,14 @@ void power9_idle(void) } #ifdef CONFIG_HOTPLUG_CPU +static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val) +{ + u64 pir = get_hard_smp_processor_id(cpu); + + mtspr(SPRN_LPCR, lpcr_val); + opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val); +} + /* * pnv_cpu_offline: A function that puts the CPU into the deepest * available platform idle state on a CPU-Offline. @@ -364,6 +405,20 @@ unsigned long pnv_cpu_offline(unsigned int cpu) { unsigned long srr1; u32 idle_states = pnv_get_supported_cpuidle_states(); + u64 lpcr_val; + + /* + * We don't want to take decrementer interrupts while we are + * offline, so clear LPCR:PECE1. We keep PECE2 (and + * LPCR_PECE_HVEE on P9) enabled as to let IPIs in. + * + * If the CPU gets woken up by a special wakeup, ensure that + * the SLW engine sets LPCR with decrementer bit cleared, else + * the CPU will come back to the kernel due to a spurious + * wakeup. + */ + lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1; + pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); __ppc64_runlatch_off(); @@ -375,7 +430,8 @@ unsigned long pnv_cpu_offline(unsigned int cpu) pnv_deepest_stop_psscr_val; srr1 = power9_idle_stop(psscr); - } else if (idle_states & OPAL_PM_WINKLE_ENABLED) { + } else if ((idle_states & OPAL_PM_WINKLE_ENABLED) && + (idle_states & OPAL_PM_LOSE_FULL_CONTEXT)) { srr1 = power7_idle_insn(PNV_THREAD_WINKLE); } else if ((idle_states & OPAL_PM_SLEEP_ENABLED) || (idle_states & OPAL_PM_SLEEP_ENABLED_ER1)) { @@ -394,6 +450,16 @@ unsigned long pnv_cpu_offline(unsigned int cpu) __ppc64_runlatch_on(); + /* + * Re-enable decrementer interrupts in LPCR. + * + * Further, we want stop states to be woken up by decrementer + * for non-hotplug cases. So program the LPCR via stop api as + * well. + */ + lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; + pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); + return srr1; } #endif @@ -553,6 +619,7 @@ static int __init pnv_power9_idle_init(struct device_node *np, u32 *flags, max_residency_ns = residency_ns[i]; pnv_deepest_stop_psscr_val = psscr_val[i]; pnv_deepest_stop_psscr_mask = psscr_mask[i]; + pnv_deepest_stop_flag = flags[i]; deepest_stop_found = true; } diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c new file mode 100644 index 000000000000..de470caf0784 --- /dev/null +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -0,0 +1,282 @@ +/* + * Copyright (C) IBM Corporation, 2014, 2017 + * Anton Blanchard, Rashmica Gupta. + * + * 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. + */ + +#define pr_fmt(fmt) "memtrace: " fmt + +#include <linux/bitops.h> +#include <linux/string.h> +#include <linux/memblock.h> +#include <linux/init.h> +#include <linux/moduleparam.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/slab.h> +#include <linux/memory.h> +#include <linux/memory_hotplug.h> +#include <asm/machdep.h> +#include <asm/debugfs.h> + +/* This enables us to keep track of the memory removed from each node. */ +struct memtrace_entry { + void *mem; + u64 start; + u64 size; + u32 nid; + struct dentry *dir; + char name[16]; +}; + +static u64 memtrace_size; + +static struct memtrace_entry *memtrace_array; +static unsigned int memtrace_array_nr; + + +static ssize_t memtrace_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct memtrace_entry *ent = filp->private_data; + + return simple_read_from_buffer(ubuf, count, ppos, ent->mem, ent->size); +} + +static bool valid_memtrace_range(struct memtrace_entry *dev, + unsigned long start, unsigned long size) +{ + if ((start >= dev->start) && + ((start + size) <= (dev->start + dev->size))) + return true; + + return false; +} + +static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long size = vma->vm_end - vma->vm_start; + struct memtrace_entry *dev = filp->private_data; + + if (!valid_memtrace_range(dev, vma->vm_pgoff << PAGE_SHIFT, size)) + return -EINVAL; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + if (remap_pfn_range(vma, vma->vm_start, + vma->vm_pgoff + (dev->start >> PAGE_SHIFT), + size, vma->vm_page_prot)) + return -EAGAIN; + + return 0; +} + +static const struct file_operations memtrace_fops = { + .llseek = default_llseek, + .read = memtrace_read, + .mmap = memtrace_mmap, + .open = simple_open, +}; + +static void flush_memory_region(u64 base, u64 size) +{ + unsigned long line_size = ppc64_caches.l1d.size; + u64 end = base + size; + u64 addr; + + base = round_down(base, line_size); + end = round_up(end, line_size); + + for (addr = base; addr < end; addr += line_size) + asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory"); +} + +static int check_memblock_online(struct memory_block *mem, void *arg) +{ + if (mem->state != MEM_ONLINE) + return -1; + + return 0; +} + +static int change_memblock_state(struct memory_block *mem, void *arg) +{ + unsigned long state = (unsigned long)arg; + + mem->state = state; + + return 0; +} + +static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages) +{ + u64 end_pfn = start_pfn + nr_pages - 1; + + if (walk_memory_range(start_pfn, end_pfn, NULL, + check_memblock_online)) + return false; + + walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE, + change_memblock_state); + + if (offline_pages(start_pfn, nr_pages)) { + walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE, + change_memblock_state); + return false; + } + + walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE, + change_memblock_state); + + /* RCU grace period? */ + flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT), + nr_pages << PAGE_SHIFT); + + lock_device_hotplug(); + remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); + unlock_device_hotplug(); + + return true; +} + +static u64 memtrace_alloc_node(u32 nid, u64 size) +{ + u64 start_pfn, end_pfn, nr_pages; + u64 base_pfn; + + if (!NODE_DATA(nid) || !node_spanned_pages(nid)) + return 0; + + start_pfn = node_start_pfn(nid); + end_pfn = node_end_pfn(nid); + nr_pages = size >> PAGE_SHIFT; + + /* Trace memory needs to be aligned to the size */ + end_pfn = round_down(end_pfn - nr_pages, nr_pages); + + for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) { + if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) + return base_pfn << PAGE_SHIFT; + } + + return 0; +} + +static int memtrace_init_regions_runtime(u64 size) +{ + u32 nid; + u64 m; + + memtrace_array = kcalloc(num_online_nodes(), + sizeof(struct memtrace_entry), GFP_KERNEL); + if (!memtrace_array) { + pr_err("Failed to allocate memtrace_array\n"); + return -EINVAL; + } + + for_each_online_node(nid) { + m = memtrace_alloc_node(nid, size); + + /* + * A node might not have any local memory, so warn but + * continue on. + */ + if (!m) { + pr_err("Failed to allocate trace memory on node %d\n", nid); + continue; + } + + pr_info("Allocated trace memory on node %d at 0x%016llx\n", nid, m); + + memtrace_array[memtrace_array_nr].start = m; + memtrace_array[memtrace_array_nr].size = size; + memtrace_array[memtrace_array_nr].nid = nid; + memtrace_array_nr++; + } + + return 0; +} + +static struct dentry *memtrace_debugfs_dir; + +static int memtrace_init_debugfs(void) +{ + int ret = 0; + int i; + + for (i = 0; i < memtrace_array_nr; i++) { + struct dentry *dir; + struct memtrace_entry *ent = &memtrace_array[i]; + + ent->mem = ioremap(ent->start, ent->size); + /* Warn but continue on */ + if (!ent->mem) { + pr_err("Failed to map trace memory at 0x%llx\n", + ent->start); + ret = -1; + continue; + } + + snprintf(ent->name, 16, "%08x", ent->nid); + dir = debugfs_create_dir(ent->name, memtrace_debugfs_dir); + if (!dir) + return -1; + + ent->dir = dir; + debugfs_create_file("trace", 0400, dir, ent, &memtrace_fops); + debugfs_create_x64("start", 0400, dir, &ent->start); + debugfs_create_x64("size", 0400, dir, &ent->size); + } + + return ret; +} + +static int memtrace_enable_set(void *data, u64 val) +{ + if (memtrace_size) + return -EINVAL; + + if (!val) + return -EINVAL; + + /* Make sure size is aligned to a memory block */ + if (val & (memory_block_size_bytes() - 1)) + return -EINVAL; + + if (memtrace_init_regions_runtime(val)) + return -EINVAL; + + if (memtrace_init_debugfs()) + return -EINVAL; + + memtrace_size = val; + + return 0; +} + +static int memtrace_enable_get(void *data, u64 *val) +{ + *val = memtrace_size; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(memtrace_init_fops, memtrace_enable_get, + memtrace_enable_set, "0x%016llx\n"); + +static int memtrace_init(void) +{ + memtrace_debugfs_dir = debugfs_create_dir("memtrace", + powerpc_debugfs_root); + if (!memtrace_debugfs_dir) + return -1; + + debugfs_create_file("enable", 0600, memtrace_debugfs_dir, + NULL, &memtrace_init_fops); + + return 0; +} +machine_device_initcall(powernv, memtrace_init); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index b5d960d6db3d..2cb6cbea4b3b 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -546,6 +546,12 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, unsigned long pid = npu_context->mm->context.id; /* + * Unfortunately the nest mmu does not support flushing specific + * addresses so we have to flush the whole mm. + */ + flush_tlb_mm(npu_context->mm); + + /* * Loop over all the NPUs this process is active on and launch * an invalidate. */ @@ -576,12 +582,6 @@ static void mmio_invalidate(struct npu_context *npu_context, int va, } } - /* - * Unfortunately the nest mmu does not support flushing specific - * addresses so we have to flush the whole mm. - */ - flush_tlb_mm(npu_context->mm); - mmio_invalidate_wait(mmio_atsd_reg, flush); if (flush) /* Wait for the flush to complete */ @@ -614,15 +614,6 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, mmio_invalidate(npu_context, 1, address, true); } -static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct npu_context *npu_context = mn_to_npu_context(mn); - - mmio_invalidate(npu_context, 1, address, true); -} - static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) @@ -640,7 +631,6 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { .release = pnv_npu2_mn_release, .change_pte = pnv_npu2_mn_change_pte, - .invalidate_page = pnv_npu2_mn_invalidate_page, .invalidate_range = pnv_npu2_mn_invalidate_range, }; diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c index 83bebeec0fea..cf33769a7b72 100644 --- a/arch/powerpc/platforms/powernv/opal-async.c +++ b/arch/powerpc/platforms/powernv/opal-async.c @@ -171,8 +171,8 @@ int __init opal_async_comp_init(void) async = of_get_property(opal_node, "opal-msg-async-num", NULL); if (!async) { - pr_err("%s: %s has no opal-msg-async-num\n", - __func__, opal_node->full_name); + pr_err("%s: %pOF has no opal-msg-async-num\n", + __func__, opal_node); err = -ENOENT; goto out_opal_node; } diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 4ec6219287fc..2fa3ac80cb4e 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -520,7 +520,7 @@ out: * update_flash : Flash new firmware image * */ -static struct bin_attribute image_data_attr = { +static const struct bin_attribute image_data_attr = { .attr = {.name = "image", .mode = 0200}, .size = MAX_IMAGE_SIZE, /* Limit image size */ .write = image_data_write, diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c index 88f3c61eec95..d78fed728cdf 100644 --- a/arch/powerpc/platforms/powernv/opal-hmi.c +++ b/arch/powerpc/platforms/powernv/opal-hmi.c @@ -30,6 +30,8 @@ #include <asm/cputable.h> #include <asm/machdep.h> +#include "powernv.h" + static int opal_hmi_handler_nb_init; struct OpalHmiEvtNode { struct list_head list; @@ -267,8 +269,6 @@ static void hmi_event_handler(struct work_struct *work) spin_unlock_irqrestore(&opal_hmi_evt_lock, flags); if (unrecoverable) { - int ret; - /* Pull all HMI events from OPAL before we panic. */ while (opal_get_msg(__pa(&msg), sizeof(msg)) == OPAL_SUCCESS) { u32 type; @@ -284,23 +284,7 @@ static void hmi_event_handler(struct work_struct *work) print_hmi_event_info(hmi_evt); } - /* - * Unrecoverable HMI exception. We need to inform BMC/OCC - * about this error so that it can collect relevant data - * for error analysis before rebooting. - */ - ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, - "Unrecoverable HMI exception"); - if (ret == OPAL_UNSUPPORTED) { - pr_emerg("Reboot type %d not supported\n", - OPAL_REBOOT_PLATFORM_ERROR); - } - - /* - * Fall through and panic if opal_cec_reboot2() returns - * OPAL_UNSUPPORTED. - */ - panic("Unrecoverable HMI exception"); + pnv_platform_error_reboot(NULL, "Unrecoverable HMI exception"); } } diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c new file mode 100644 index 000000000000..21f6531fae20 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -0,0 +1,226 @@ +/* + * OPAL IMC interface detection driver + * Supported on POWERNV platform + * + * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation. + * (C) 2017 Anju T Sudhakar, IBM Corporation. + * (C) 2017 Hemant K Shaw, IBM Corporation. + * + * 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 later version. + */ +#include <linux/kernel.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/crash_dump.h> +#include <asm/opal.h> +#include <asm/io.h> +#include <asm/imc-pmu.h> +#include <asm/cputhreads.h> + +/* + * imc_get_mem_addr_nest: Function to get nest counter memory region + * for each chip + */ +static int imc_get_mem_addr_nest(struct device_node *node, + struct imc_pmu *pmu_ptr, + u32 offset) +{ + int nr_chips = 0, i; + u64 *base_addr_arr, baddr; + u32 *chipid_arr; + + nr_chips = of_property_count_u32_elems(node, "chip-id"); + if (nr_chips <= 0) + return -ENODEV; + + base_addr_arr = kcalloc(nr_chips, sizeof(u64), GFP_KERNEL); + if (!base_addr_arr) + return -ENOMEM; + + chipid_arr = kcalloc(nr_chips, sizeof(u32), GFP_KERNEL); + if (!chipid_arr) + return -ENOMEM; + + if (of_property_read_u32_array(node, "chip-id", chipid_arr, nr_chips)) + goto error; + + if (of_property_read_u64_array(node, "base-addr", base_addr_arr, + nr_chips)) + goto error; + + pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(struct imc_mem_info), + GFP_KERNEL); + if (!pmu_ptr->mem_info) + goto error; + + for (i = 0; i < nr_chips; i++) { + pmu_ptr->mem_info[i].id = chipid_arr[i]; + baddr = base_addr_arr[i] + offset; + pmu_ptr->mem_info[i].vbase = phys_to_virt(baddr); + } + + pmu_ptr->imc_counter_mmaped = true; + kfree(base_addr_arr); + kfree(chipid_arr); + return 0; + +error: + kfree(pmu_ptr->mem_info); + kfree(base_addr_arr); + kfree(chipid_arr); + return -1; +} + +/* + * imc_pmu_create : Takes the parent device which is the pmu unit, pmu_index + * and domain as the inputs. + * Allocates memory for the struct imc_pmu, sets up its domain, size and offsets + */ +static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) +{ + int ret = 0; + struct imc_pmu *pmu_ptr; + u32 offset; + + /* memory for pmu */ + pmu_ptr = kzalloc(sizeof(struct imc_pmu), GFP_KERNEL); + if (!pmu_ptr) + return -ENOMEM; + + /* Set the domain */ + pmu_ptr->domain = domain; + + ret = of_property_read_u32(parent, "size", &pmu_ptr->counter_mem_size); + if (ret) { + ret = -EINVAL; + goto free_pmu; + } + + if (!of_property_read_u32(parent, "offset", &offset)) { + if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) { + ret = -EINVAL; + goto free_pmu; + } + } + + /* Function to register IMC pmu */ + ret = init_imc_pmu(parent, pmu_ptr, pmu_index); + if (ret) + pr_err("IMC PMU %s Register failed\n", pmu_ptr->pmu.name); + + return 0; + +free_pmu: + kfree(pmu_ptr); + return ret; +} + +static void disable_nest_pmu_counters(void) +{ + int nid, cpu; + const struct cpumask *l_cpumask; + + get_online_cpus(); + for_each_online_node(nid) { + l_cpumask = cpumask_of_node(nid); + cpu = cpumask_first(l_cpumask); + opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, + get_hard_smp_processor_id(cpu)); + } + put_online_cpus(); +} + +static void disable_core_pmu_counters(void) +{ + cpumask_t cores_map; + int cpu, rc; + + get_online_cpus(); + /* Disable the IMC Core functions */ + cores_map = cpu_online_cores_map(); + for_each_cpu(cpu, &cores_map) { + rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, + get_hard_smp_processor_id(cpu)); + if (rc) + pr_err("%s: Failed to stop Core (cpu = %d)\n", + __FUNCTION__, cpu); + } + put_online_cpus(); +} + +static int opal_imc_counters_probe(struct platform_device *pdev) +{ + struct device_node *imc_dev = pdev->dev.of_node; + int pmu_count = 0, domain; + u32 type; + + /* + * Check whether this is kdump kernel. If yes, force the engines to + * stop and return. + */ + if (is_kdump_kernel()) { + disable_nest_pmu_counters(); + disable_core_pmu_counters(); + return -ENODEV; + } + + for_each_compatible_node(imc_dev, NULL, IMC_DTB_UNIT_COMPAT) { + if (of_property_read_u32(imc_dev, "type", &type)) { + pr_warn("IMC Device without type property\n"); + continue; + } + + switch (type) { + case IMC_TYPE_CHIP: + domain = IMC_DOMAIN_NEST; + break; + case IMC_TYPE_CORE: + domain =IMC_DOMAIN_CORE; + break; + case IMC_TYPE_THREAD: + domain = IMC_DOMAIN_THREAD; + break; + default: + pr_warn("IMC Unknown Device type \n"); + domain = -1; + break; + } + + if (!imc_pmu_create(imc_dev, pmu_count, domain)) + pmu_count++; + } + + return 0; +} + +static void opal_imc_counters_shutdown(struct platform_device *pdev) +{ + /* + * Function only stops the engines which is bare minimum. + * TODO: Need to handle proper memory cleanup and pmu + * unregister. + */ + disable_nest_pmu_counters(); + disable_core_pmu_counters(); +} + +static const struct of_device_id opal_imc_match[] = { + { .compatible = IMC_DTB_COMPAT }, + {}, +}; + +static struct platform_driver opal_imc_driver = { + .driver = { + .name = "opal-imc-counters", + .of_match_table = opal_imc_match, + }, + .probe = opal_imc_counters_probe, + .shutdown = opal_imc_counters_shutdown, +}; + +builtin_platform_driver(opal_imc_driver); diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c new file mode 100644 index 000000000000..badb29bde93f --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-powercap.c @@ -0,0 +1,244 @@ +/* + * PowerNV OPAL Powercap interface + * + * Copyright 2017 IBM Corp. + * + * 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. + */ + +#define pr_fmt(fmt) "opal-powercap: " fmt + +#include <linux/of.h> +#include <linux/kobject.h> +#include <linux/slab.h> + +#include <asm/opal.h> + +DEFINE_MUTEX(powercap_mutex); + +static struct kobject *powercap_kobj; + +struct powercap_attr { + u32 handle; + struct kobj_attribute attr; +}; + +static struct pcap { + struct attribute_group pg; + struct powercap_attr *pattrs; +} *pcaps; + +static ssize_t powercap_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct powercap_attr *pcap_attr = container_of(attr, + struct powercap_attr, attr); + struct opal_msg msg; + u32 pcap; + int ret, token; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + pr_devel("Failed to get token\n"); + return token; + } + + ret = mutex_lock_interruptible(&powercap_mutex); + if (ret) + goto out_token; + + ret = opal_get_powercap(pcap_attr->handle, token, (u32 *)__pa(&pcap)); + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_devel("Failed to wait for the async response\n"); + ret = -EIO; + goto out; + } + ret = opal_error_code(opal_get_async_rc(msg)); + if (!ret) { + ret = sprintf(buf, "%u\n", be32_to_cpu(pcap)); + if (ret < 0) + ret = -EIO; + } + break; + case OPAL_SUCCESS: + ret = sprintf(buf, "%u\n", be32_to_cpu(pcap)); + if (ret < 0) + ret = -EIO; + break; + default: + ret = opal_error_code(ret); + } + +out: + mutex_unlock(&powercap_mutex); +out_token: + opal_async_release_token(token); + return ret; +} + +static ssize_t powercap_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, + size_t count) +{ + struct powercap_attr *pcap_attr = container_of(attr, + struct powercap_attr, attr); + struct opal_msg msg; + u32 pcap; + int ret, token; + + ret = kstrtoint(buf, 0, &pcap); + if (ret) + return ret; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + pr_devel("Failed to get token\n"); + return token; + } + + ret = mutex_lock_interruptible(&powercap_mutex); + if (ret) + goto out_token; + + ret = opal_set_powercap(pcap_attr->handle, token, pcap); + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_devel("Failed to wait for the async response\n"); + ret = -EIO; + goto out; + } + ret = opal_error_code(opal_get_async_rc(msg)); + if (!ret) + ret = count; + break; + case OPAL_SUCCESS: + ret = count; + break; + default: + ret = opal_error_code(ret); + } + +out: + mutex_unlock(&powercap_mutex); +out_token: + opal_async_release_token(token); + return ret; +} + +static void powercap_add_attr(int handle, const char *name, + struct powercap_attr *attr) +{ + attr->handle = handle; + sysfs_attr_init(&attr->attr.attr); + attr->attr.attr.name = name; + attr->attr.attr.mode = 0444; + attr->attr.show = powercap_show; +} + +void __init opal_powercap_init(void) +{ + struct device_node *powercap, *node; + int i = 0; + + powercap = of_find_compatible_node(NULL, NULL, "ibm,opal-powercap"); + if (!powercap) { + pr_devel("Powercap node not found\n"); + return; + } + + pcaps = kcalloc(of_get_child_count(powercap), sizeof(*pcaps), + GFP_KERNEL); + if (!pcaps) + return; + + powercap_kobj = kobject_create_and_add("powercap", opal_kobj); + if (!powercap_kobj) { + pr_warn("Failed to create powercap kobject\n"); + goto out_pcaps; + } + + i = 0; + for_each_child_of_node(powercap, node) { + u32 cur, min, max; + int j = 0; + bool has_cur = false, has_min = false, has_max = false; + + if (!of_property_read_u32(node, "powercap-min", &min)) { + j++; + has_min = true; + } + + if (!of_property_read_u32(node, "powercap-max", &max)) { + j++; + has_max = true; + } + + if (!of_property_read_u32(node, "powercap-current", &cur)) { + j++; + has_cur = true; + } + + pcaps[i].pattrs = kcalloc(j, sizeof(struct powercap_attr), + GFP_KERNEL); + if (!pcaps[i].pattrs) + goto out_pcaps_pattrs; + + pcaps[i].pg.attrs = kcalloc(j + 1, sizeof(struct attribute *), + GFP_KERNEL); + if (!pcaps[i].pg.attrs) { + kfree(pcaps[i].pattrs); + goto out_pcaps_pattrs; + } + + j = 0; + pcaps[i].pg.name = node->name; + if (has_min) { + powercap_add_attr(min, "powercap-min", + &pcaps[i].pattrs[j]); + pcaps[i].pg.attrs[j] = &pcaps[i].pattrs[j].attr.attr; + j++; + } + + if (has_max) { + powercap_add_attr(max, "powercap-max", + &pcaps[i].pattrs[j]); + pcaps[i].pg.attrs[j] = &pcaps[i].pattrs[j].attr.attr; + j++; + } + + if (has_cur) { + powercap_add_attr(cur, "powercap-current", + &pcaps[i].pattrs[j]); + pcaps[i].pattrs[j].attr.attr.mode |= 0220; + pcaps[i].pattrs[j].attr.store = powercap_store; + pcaps[i].pg.attrs[j] = &pcaps[i].pattrs[j].attr.attr; + j++; + } + + if (sysfs_create_group(powercap_kobj, &pcaps[i].pg)) { + pr_warn("Failed to create powercap attribute group %s\n", + pcaps[i].pg.name); + goto out_pcaps_pattrs; + } + i++; + } + + return; + +out_pcaps_pattrs: + while (--i >= 0) { + kfree(pcaps[i].pattrs); + kfree(pcaps[i].pg.attrs); + } + kobject_put(powercap_kobj); +out_pcaps: + kfree(pcaps); +} diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 2d6ee1c5ad85..de4dd09f4a15 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -241,15 +241,9 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf, size = be16_to_cpu(hdr.size); - msg = kmalloc(size, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - rc = copy_from_user(msg, buf, size); - if (rc) { - size = -EFAULT; - goto out_free; - } + msg = memdup_user(buf, size); + if (IS_ERR(msg)) + return PTR_ERR(msg); rc = opal_prd_msg(msg); if (rc) { @@ -257,7 +251,6 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf, size = -EIO; } -out_free: kfree(msg); return size; diff --git a/arch/powerpc/platforms/powernv/opal-psr.c b/arch/powerpc/platforms/powernv/opal-psr.c new file mode 100644 index 000000000000..7313b7fc9071 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-psr.c @@ -0,0 +1,175 @@ +/* + * PowerNV OPAL Power-Shift-Ratio interface + * + * Copyright 2017 IBM Corp. + * + * 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. + */ + +#define pr_fmt(fmt) "opal-psr: " fmt + +#include <linux/of.h> +#include <linux/kobject.h> +#include <linux/slab.h> + +#include <asm/opal.h> + +DEFINE_MUTEX(psr_mutex); + +static struct kobject *psr_kobj; + +struct psr_attr { + u32 handle; + struct kobj_attribute attr; +} *psr_attrs; + +static ssize_t psr_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct psr_attr *psr_attr = container_of(attr, struct psr_attr, attr); + struct opal_msg msg; + int psr, ret, token; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + pr_devel("Failed to get token\n"); + return token; + } + + ret = mutex_lock_interruptible(&psr_mutex); + if (ret) + goto out_token; + + ret = opal_get_power_shift_ratio(psr_attr->handle, token, + (u32 *)__pa(&psr)); + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_devel("Failed to wait for the async response\n"); + ret = -EIO; + goto out; + } + ret = opal_error_code(opal_get_async_rc(msg)); + if (!ret) { + ret = sprintf(buf, "%u\n", be32_to_cpu(psr)); + if (ret < 0) + ret = -EIO; + } + break; + case OPAL_SUCCESS: + ret = sprintf(buf, "%u\n", be32_to_cpu(psr)); + if (ret < 0) + ret = -EIO; + break; + default: + ret = opal_error_code(ret); + } + +out: + mutex_unlock(&psr_mutex); +out_token: + opal_async_release_token(token); + return ret; +} + +static ssize_t psr_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct psr_attr *psr_attr = container_of(attr, struct psr_attr, attr); + struct opal_msg msg; + int psr, ret, token; + + ret = kstrtoint(buf, 0, &psr); + if (ret) + return ret; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + pr_devel("Failed to get token\n"); + return token; + } + + ret = mutex_lock_interruptible(&psr_mutex); + if (ret) + goto out_token; + + ret = opal_set_power_shift_ratio(psr_attr->handle, token, psr); + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_devel("Failed to wait for the async response\n"); + ret = -EIO; + goto out; + } + ret = opal_error_code(opal_get_async_rc(msg)); + if (!ret) + ret = count; + break; + case OPAL_SUCCESS: + ret = count; + break; + default: + ret = opal_error_code(ret); + } + +out: + mutex_unlock(&psr_mutex); +out_token: + opal_async_release_token(token); + return ret; +} + +void __init opal_psr_init(void) +{ + struct device_node *psr, *node; + int i = 0; + + psr = of_find_compatible_node(NULL, NULL, + "ibm,opal-power-shift-ratio"); + if (!psr) { + pr_devel("Power-shift-ratio node not found\n"); + return; + } + + psr_attrs = kcalloc(of_get_child_count(psr), sizeof(struct psr_attr), + GFP_KERNEL); + if (!psr_attrs) + return; + + psr_kobj = kobject_create_and_add("psr", opal_kobj); + if (!psr_kobj) { + pr_warn("Failed to create psr kobject\n"); + goto out; + } + + for_each_child_of_node(psr, node) { + if (of_property_read_u32(node, "handle", + &psr_attrs[i].handle)) + goto out_kobj; + + sysfs_attr_init(&psr_attrs[i].attr.attr); + if (of_property_read_string(node, "label", + &psr_attrs[i].attr.attr.name)) + goto out_kobj; + psr_attrs[i].attr.attr.mode = 0664; + psr_attrs[i].attr.show = psr_show; + psr_attrs[i].attr.store = psr_store; + if (sysfs_create_file(psr_kobj, &psr_attrs[i].attr.attr)) { + pr_devel("Failed to create psr sysfs file %s\n", + psr_attrs[i].attr.attr.name); + goto out_kobj; + } + i++; + } + + return; +out_kobj: + kobject_put(psr_kobj); +out: + kfree(psr_attrs); +} diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c new file mode 100644 index 000000000000..7e5a235ebf76 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c @@ -0,0 +1,212 @@ +/* + * PowerNV OPAL Sensor-groups interface + * + * Copyright 2017 IBM Corp. + * + * 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. + */ + +#define pr_fmt(fmt) "opal-sensor-groups: " fmt + +#include <linux/of.h> +#include <linux/kobject.h> +#include <linux/slab.h> + +#include <asm/opal.h> + +DEFINE_MUTEX(sg_mutex); + +static struct kobject *sg_kobj; + +struct sg_attr { + u32 handle; + struct kobj_attribute attr; +}; + +static struct sensor_group { + char name[20]; + struct attribute_group sg; + struct sg_attr *sgattrs; +} *sgs; + +static ssize_t sg_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct sg_attr *sattr = container_of(attr, struct sg_attr, attr); + struct opal_msg msg; + u32 data; + int ret, token; + + ret = kstrtoint(buf, 0, &data); + if (ret) + return ret; + + if (data != 1) + return -EINVAL; + + token = opal_async_get_token_interruptible(); + if (token < 0) { + pr_devel("Failed to get token\n"); + return token; + } + + ret = mutex_lock_interruptible(&sg_mutex); + if (ret) + goto out_token; + + ret = opal_sensor_group_clear(sattr->handle, token); + switch (ret) { + case OPAL_ASYNC_COMPLETION: + ret = opal_async_wait_response(token, &msg); + if (ret) { + pr_devel("Failed to wait for the async response\n"); + ret = -EIO; + goto out; + } + ret = opal_error_code(opal_get_async_rc(msg)); + if (!ret) + ret = count; + break; + case OPAL_SUCCESS: + ret = count; + break; + default: + ret = opal_error_code(ret); + } + +out: + mutex_unlock(&sg_mutex); +out_token: + opal_async_release_token(token); + return ret; +} + +static struct sg_ops_info { + int opal_no; + const char *attr_name; + ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count); +} ops_info[] = { + { OPAL_SENSOR_GROUP_CLEAR, "clear", sg_store }, +}; + +static void add_attr(int handle, struct sg_attr *attr, int index) +{ + attr->handle = handle; + sysfs_attr_init(&attr->attr.attr); + attr->attr.attr.name = ops_info[index].attr_name; + attr->attr.attr.mode = 0220; + attr->attr.store = ops_info[index].store; +} + +static int add_attr_group(const __be32 *ops, int len, struct sensor_group *sg, + u32 handle) +{ + int i, j; + int count = 0; + + for (i = 0; i < len; i++) + for (j = 0; j < ARRAY_SIZE(ops_info); j++) + if (be32_to_cpu(ops[i]) == ops_info[j].opal_no) { + add_attr(handle, &sg->sgattrs[count], j); + sg->sg.attrs[count] = + &sg->sgattrs[count].attr.attr; + count++; + } + + return sysfs_create_group(sg_kobj, &sg->sg); +} + +static int get_nr_attrs(const __be32 *ops, int len) +{ + int i, j; + int nr_attrs = 0; + + for (i = 0; i < len; i++) + for (j = 0; j < ARRAY_SIZE(ops_info); j++) + if (be32_to_cpu(ops[i]) == ops_info[j].opal_no) + nr_attrs++; + + return nr_attrs; +} + +void __init opal_sensor_groups_init(void) +{ + struct device_node *sg, *node; + int i = 0; + + sg = of_find_compatible_node(NULL, NULL, "ibm,opal-sensor-group"); + if (!sg) { + pr_devel("Sensor groups node not found\n"); + return; + } + + sgs = kcalloc(of_get_child_count(sg), sizeof(*sgs), GFP_KERNEL); + if (!sgs) + return; + + sg_kobj = kobject_create_and_add("sensor_groups", opal_kobj); + if (!sg_kobj) { + pr_warn("Failed to create sensor group kobject\n"); + goto out_sgs; + } + + for_each_child_of_node(sg, node) { + const __be32 *ops; + u32 sgid, len, nr_attrs, chipid; + + ops = of_get_property(node, "ops", &len); + if (!ops) + continue; + + nr_attrs = get_nr_attrs(ops, len); + if (!nr_attrs) + continue; + + sgs[i].sgattrs = kcalloc(nr_attrs, sizeof(struct sg_attr), + GFP_KERNEL); + if (!sgs[i].sgattrs) + goto out_sgs_sgattrs; + + sgs[i].sg.attrs = kcalloc(nr_attrs + 1, + sizeof(struct attribute *), + GFP_KERNEL); + + if (!sgs[i].sg.attrs) { + kfree(sgs[i].sgattrs); + goto out_sgs_sgattrs; + } + + if (of_property_read_u32(node, "sensor-group-id", &sgid)) { + pr_warn("sensor-group-id property not found\n"); + goto out_sgs_sgattrs; + } + + if (!of_property_read_u32(node, "ibm,chip-id", &chipid)) + sprintf(sgs[i].name, "%s%d", node->name, chipid); + else + sprintf(sgs[i].name, "%s", node->name); + + sgs[i].sg.name = sgs[i].name; + if (add_attr_group(ops, len, &sgs[i], sgid)) { + pr_warn("Failed to create sensor attribute group %s\n", + sgs[i].sg.name); + goto out_sgs_sgattrs; + } + i++; + } + + return; + +out_sgs_sgattrs: + while (--i >= 0) { + kfree(sgs[i].sgattrs); + kfree(sgs[i].sg.attrs); + } + kobject_put(sg_kobj); +out_sgs: + kfree(sgs); +} diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index 4ca6c26a56d5..8c1ede2d3f7e 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -27,7 +27,7 @@ .globl opal_tracepoint_refcount opal_tracepoint_refcount: - .llong 0 + .8byte 0 .section ".text" @@ -310,3 +310,12 @@ OPAL_CALL(opal_xive_dump, OPAL_XIVE_DUMP); OPAL_CALL(opal_npu_init_context, OPAL_NPU_INIT_CONTEXT); OPAL_CALL(opal_npu_destroy_context, OPAL_NPU_DESTROY_CONTEXT); OPAL_CALL(opal_npu_map_lpar, OPAL_NPU_MAP_LPAR); +OPAL_CALL(opal_imc_counters_init, OPAL_IMC_COUNTERS_INIT); +OPAL_CALL(opal_imc_counters_start, OPAL_IMC_COUNTERS_START); +OPAL_CALL(opal_imc_counters_stop, OPAL_IMC_COUNTERS_STOP); +OPAL_CALL(opal_pci_set_p2p, OPAL_PCI_SET_P2P); +OPAL_CALL(opal_get_powercap, OPAL_GET_POWERCAP); +OPAL_CALL(opal_set_powercap, OPAL_SET_POWERCAP); +OPAL_CALL(opal_get_power_shift_ratio, OPAL_GET_POWER_SHIFT_RATIO); +OPAL_CALL(opal_set_power_shift_ratio, OPAL_SET_POWER_SHIFT_RATIO); +OPAL_CALL(opal_sensor_group_clear, OPAL_SENSOR_GROUP_CLEAR); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 28651fb25417..81c0a943dea9 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -36,14 +36,14 @@ static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count) const __be32 *gcid; if (!of_get_property(dev, "scom-controller", NULL)) { - pr_err("%s: device %s is not a SCOM controller\n", - __func__, dev->full_name); + pr_err("%s: device %pOF is not a SCOM controller\n", + __func__, dev); return SCOM_MAP_INVALID; } gcid = of_get_property(dev, "ibm,chip-id", NULL); if (!gcid) { - pr_err("%s: device %s has no ibm,chip-id\n", - __func__, dev->full_name); + pr_err("%s: device %pOF has no ibm,chip-id\n", + __func__, dev); return SCOM_MAP_INVALID; } m = kmalloc(sizeof(struct opal_scom_map), GFP_KERNEL); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index cad6b57ce494..65c79ecf5a4d 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -16,6 +16,7 @@ #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> +#include <linux/of_address.h> #include <linux/interrupt.h> #include <linux/notifier.h> #include <linux/slab.h> @@ -25,11 +26,17 @@ #include <linux/memblock.h> #include <linux/kthread.h> #include <linux/freezer.h> +#include <linux/printk.h> +#include <linux/kmsg_dump.h> +#include <linux/console.h> +#include <linux/sched/debug.h> #include <asm/machdep.h> #include <asm/opal.h> #include <asm/firmware.h> #include <asm/mce.h> +#include <asm/imc-pmu.h> +#include <asm/bug.h> #include "powernv.h" @@ -162,12 +169,9 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node, sizeof(struct mcheck_recoverable_range); /* - * Allocate a buffer to hold the MC recoverable ranges. We would be - * accessing them in real mode, hence it needs to be within - * RMO region. + * Allocate a buffer to hold the MC recoverable ranges. */ - mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64), - ppc64_rma_size)); + mc_recoverable_range =__va(memblock_alloc(size, __alignof__(u64))); memset(mc_recoverable_range, 0, size); for (i = 0; i < mc_recoverable_range_len; i++) { @@ -422,24 +426,88 @@ static int opal_recover_mce(struct pt_regs *regs, /* Fatal machine check */ pr_err("Machine check interrupt is fatal\n"); recovered = 0; - } else if ((evt->severity == MCE_SEV_ERROR_SYNC) && - (user_mode(regs) && !is_global_init(current))) { + } + + if (!recovered && evt->severity == MCE_SEV_ERROR_SYNC) { /* - * For now, kill the task if we have received exception when - * in userspace. + * Try to kill processes if we get a synchronous machine check + * (e.g., one caused by execution of this instruction). This + * will devolve into a panic if we try to kill init or are in + * an interrupt etc. * * TODO: Queue up this address for hwpoisioning later. + * TODO: This is not quite right for d-side machine + * checks ->nip is not necessarily the important + * address. */ - _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); - recovered = 1; + if ((user_mode(regs))) { + _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip); + recovered = 1; + } else if (die_will_crash()) { + /* + * die() would kill the kernel, so better to go via + * the platform reboot code that will log the + * machine check. + */ + recovered = 0; + } else { + die("Machine check", regs, SIGBUS); + recovered = 1; + } } + return recovered; } +void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) +{ + /* + * This is mostly taken from kernel/panic.c, but tries to do + * relatively minimal work. Don't use delay functions (TB may + * be broken), don't crash dump (need to set a firmware log), + * don't run notifiers. We do want to get some information to + * Linux console. + */ + console_verbose(); + bust_spinlocks(1); + pr_emerg("Hardware platform error: %s\n", msg); + if (regs) + show_regs(regs); + smp_send_stop(); + printk_safe_flush_on_panic(); + kmsg_dump(KMSG_DUMP_PANIC); + bust_spinlocks(0); + debug_locks_off(); + console_flush_on_panic(); + + /* + * Don't bother to shut things down because this will + * xstop the system. + */ + if (opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, msg) + == OPAL_UNSUPPORTED) { + pr_emerg("Reboot type %d not supported for %s\n", + OPAL_REBOOT_PLATFORM_ERROR, msg); + } + + /* + * We reached here. There can be three possibilities: + * 1. We are running on a firmware level that do not support + * opal_cec_reboot2() + * 2. We are running on a firmware level that do not support + * OPAL_REBOOT_PLATFORM_ERROR reboot type. + * 3. We are running on FSP based system that does not need + * opal to trigger checkstop explicitly for error analysis. + * The FSP PRD component would have already got notified + * about this error through other channels. + */ + + ppc_md.restart(NULL); +} + int opal_machine_check(struct pt_regs *regs) { struct machine_check_event evt; - int ret; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return 0; @@ -455,43 +523,7 @@ int opal_machine_check(struct pt_regs *regs) if (opal_recover_mce(regs, &evt)) return 1; - /* - * Unrecovered machine check, we are heading to panic path. - * - * We may have hit this MCE in very early stage of kernel - * initialization even before opal-prd has started running. If - * this is the case then this MCE error may go un-noticed or - * un-analyzed if we go down panic path. We need to inform - * BMC/OCC about this error so that they can collect relevant - * data for error analysis before rebooting. - * Use opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR) to do so. - * This function may not return on BMC based system. - */ - ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, - "Unrecoverable Machine Check exception"); - if (ret == OPAL_UNSUPPORTED) { - pr_emerg("Reboot type %d not supported\n", - OPAL_REBOOT_PLATFORM_ERROR); - } - - /* - * We reached here. There can be three possibilities: - * 1. We are running on a firmware level that do not support - * opal_cec_reboot2() - * 2. We are running on a firmware level that do not support - * OPAL_REBOOT_PLATFORM_ERROR reboot type. - * 3. We are running on FSP based system that does not need opal - * to trigger checkstop explicitly for error analysis. The FSP - * PRD component would have already got notified about this - * error through other channels. - * - * If hardware marked this as an unrecoverable MCE, we are - * going to panic anyway. Even if it didn't, it's not safe to - * continue at this point, so we should explicitly panic. - */ - - panic("PowerNV Unrecovered Machine Check"); - return 0; + pnv_platform_error_reboot(regs, "Unrecoverable Machine Check exception"); } /* Early hmi handler called in real mode. */ @@ -720,6 +752,15 @@ static void opal_pdev_init(const char *compatible) of_platform_device_create(np, NULL, NULL); } +static void __init opal_imc_init_dev(void) +{ + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, IMC_DTB_COMPAT); + if (np) + of_platform_device_create(np, NULL, NULL); +} + static int kopald(void *unused) { unsigned long timeout = msecs_to_jiffies(opal_heartbeat) + 1; @@ -793,6 +834,9 @@ static int __init opal_init(void) /* Setup a heatbeat thread if requested by OPAL */ opal_init_heartbeat(); + /* Detect In-Memory Collection counters and create devices*/ + opal_imc_init_dev(); + /* Create leds platform devices */ leds = of_find_node_by_path("/ibm,opal/leds"); if (leds) { @@ -836,6 +880,15 @@ static int __init opal_init(void) /* Initialise OPAL kmsg dumper for flushing console on panic */ opal_kmsg_init(); + /* Initialise OPAL powercap interface */ + opal_powercap_init(); + + /* Initialise OPAL Power-Shifting-Ratio interface */ + opal_psr_init(); + + /* Initialise OPAL sensor groups */ + opal_sensor_groups_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); @@ -952,6 +1005,7 @@ int opal_error_code(int rc) case OPAL_UNSUPPORTED: return -EIO; case OPAL_HARDWARE: return -EIO; case OPAL_INTERNAL_ERROR: return -EIO; + case OPAL_TIMEOUT: return -ETIMEDOUT; default: pr_err("%s: unexpected OPAL error %d\n", __func__, rc); return -EIO; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 437613588df1..57f9e55f4352 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -444,8 +444,8 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb) r = of_get_property(dn, "ibm,opal-m64-window", NULL); if (!r) { - pr_info(" No <ibm,opal-m64-window> on %s\n", - dn->full_name); + pr_info(" No <ibm,opal-m64-window> on %pOF\n", + dn); return; } @@ -1408,7 +1408,6 @@ m64_failed: static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, int num); -static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe) { @@ -1852,6 +1851,14 @@ static int pnv_pci_ioda_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) /* 4GB offset bypasses 32-bit space */ set_dma_offset(&pdev->dev, (1ULL << 32)); set_dma_ops(&pdev->dev, &dma_direct_ops); + } else if (dma_mask >> 32 && dma_mask != DMA_BIT_MASK(64)) { + /* + * Fail the request if a DMA mask between 32 and 64 bits + * was requested but couldn't be fulfilled. Ideally we + * would do this for 64-bits but historically we have + * always fallen back to 32-bits. + */ + return -ENOMEM; } else { dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); set_dma_ops(&pdev->dev, &dma_iommu_ops); @@ -2394,7 +2401,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group, return 0; } -static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) +void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) { uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -3789,8 +3796,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!of_device_is_available(np)) return; - pr_info("Initializing %s PHB (%s)\n", - pnv_phb_names[ioda_type], of_node_full_name(np)); + pr_info("Initializing %s PHB (%pOF)\n", pnv_phb_names[ioda_type], np); prop64 = of_get_property(np, "ibm,opal-phbid", NULL); if (!prop64) { @@ -3805,8 +3811,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, /* Allocate PCI controller */ phb->hose = hose = pcibios_alloc_controller(np); if (!phb->hose) { - pr_err(" Can't allocate PCI controller for %s\n", - np->full_name); + pr_err(" Can't allocate PCI controller for %pOF\n", + np); memblock_free(__pa(phb), sizeof(struct pnv_phb)); return; } @@ -3817,7 +3823,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, hose->first_busno = be32_to_cpu(prop32[0]); hose->last_busno = be32_to_cpu(prop32[1]); } else { - pr_warn(" Broken <bus-range> on %s\n", np->full_name); + pr_warn(" Broken <bus-range> on %pOF\n", np); hose->first_busno = 0; hose->last_busno = 0xff; } @@ -4038,7 +4044,7 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np) const __be64 *prop64; u64 hub_id; - pr_info("Probing IODA IO-Hub %s\n", np->full_name); + pr_info("Probing IODA IO-Hub %pOF\n", np); prop64 = of_get_property(np, "ibm,opal-hubid", NULL); if (!prop64) { diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 7905d179d036..5422f4a6317c 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -37,6 +37,8 @@ #include "powernv.h" #include "pci.h" +static DEFINE_MUTEX(p2p_mutex); + int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id) { struct device_node *parent = np; @@ -1017,6 +1019,79 @@ void pnv_pci_dma_bus_setup(struct pci_bus *bus) } } +int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target, u64 desc) +{ + struct pci_controller *hose; + struct pnv_phb *phb_init, *phb_target; + struct pnv_ioda_pe *pe_init; + int rc; + + if (!opal_check_token(OPAL_PCI_SET_P2P)) + return -ENXIO; + + hose = pci_bus_to_host(initiator->bus); + phb_init = hose->private_data; + + hose = pci_bus_to_host(target->bus); + phb_target = hose->private_data; + + pe_init = pnv_ioda_get_pe(initiator); + if (!pe_init) + return -ENODEV; + + /* + * Configuring the initiator's PHB requires to adjust its + * TVE#1 setting. Since the same device can be an initiator + * several times for different target devices, we need to keep + * a reference count to know when we can restore the default + * bypass setting on its TVE#1 when disabling. Opal is not + * tracking PE states, so we add a reference count on the PE + * in linux. + * + * For the target, the configuration is per PHB, so we keep a + * target reference count on the PHB. + */ + mutex_lock(&p2p_mutex); + + if (desc & OPAL_PCI_P2P_ENABLE) { + /* always go to opal to validate the configuration */ + rc = opal_pci_set_p2p(phb_init->opal_id, phb_target->opal_id, + desc, pe_init->pe_number); + + if (rc != OPAL_SUCCESS) { + rc = -EIO; + goto out; + } + + pe_init->p2p_initiator_count++; + phb_target->p2p_target_count++; + } else { + if (!pe_init->p2p_initiator_count || + !phb_target->p2p_target_count) { + rc = -EINVAL; + goto out; + } + + if (--pe_init->p2p_initiator_count == 0) + pnv_pci_ioda2_set_bypass(pe_init, true); + + if (--phb_target->p2p_target_count == 0) { + rc = opal_pci_set_p2p(phb_init->opal_id, + phb_target->opal_id, desc, + pe_init->pe_number); + if (rc != OPAL_SUCCESS) { + rc = -EIO; + goto out; + } + } + } + rc = 0; +out: + mutex_unlock(&p2p_mutex); + return rc; +} +EXPORT_SYMBOL_GPL(pnv_pci_set_p2p); + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index f16bc403ec03..a95273c524f6 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -78,6 +78,9 @@ struct pnv_ioda_pe { struct pnv_ioda_pe *master; struct list_head slaves; + /* PCI peer-to-peer*/ + int p2p_initiator_count; + /* Link in list of PE#s */ struct list_head list; }; @@ -189,6 +192,7 @@ struct pnv_phb { #ifdef CONFIG_CXL_BASE struct cxl_afu *cxl_afu; #endif + int p2p_target_count; }; extern struct pci_ops pnv_pci_ops; @@ -229,6 +233,7 @@ extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev); extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq); extern bool pnv_pci_enable_device_hook(struct pci_dev *dev); +extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable); extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level, const char *fmt, ...); diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 6dbc0a1da1f6..a159d48573d7 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -7,6 +7,8 @@ extern void pnv_smp_init(void); static inline void pnv_smp_init(void) { } #endif +extern void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) __noreturn; + struct pci_dev; #ifdef CONFIG_PCI diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 1a9d84371a4d..718f50ed22f1 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -16,11 +16,13 @@ #include <linux/slab.h> #include <linux/smp.h> #include <asm/archrandom.h> +#include <asm/cputable.h> #include <asm/io.h> #include <asm/prom.h> #include <asm/machdep.h> #include <asm/smp.h> +#define DARN_ERR 0xFFFFFFFFFFFFFFFFul struct powernv_rng { void __iomem *regs; @@ -67,6 +69,41 @@ int powernv_get_random_real_mode(unsigned long *v) return 1; } +int powernv_get_random_darn(unsigned long *v) +{ + unsigned long val; + + /* Using DARN with L=1 - 64-bit conditioned random number */ + asm volatile(PPC_DARN(%0, 1) : "=r"(val)); + + if (val == DARN_ERR) + return 0; + + *v = val; + + return 1; +} + +static int initialise_darn(void) +{ + unsigned long val; + int i; + + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return -ENODEV; + + for (i = 0; i < 10; i++) { + if (powernv_get_random_darn(&val)) { + ppc_md.get_random_seed = powernv_get_random_darn; + return 0; + } + } + + pr_warn("Unable to use DARN for get_random_seed()\n"); + + return -EIO; +} + int powernv_get_random_long(unsigned long *v) { struct powernv_rng *rng; @@ -88,7 +125,7 @@ static __init void rng_init_per_cpu(struct powernv_rng *rng, chip_id = of_get_ibm_chip_id(dn); if (chip_id == -1) - pr_warn("No ibm,chip-id found for %s.\n", dn->full_name); + pr_warn("No ibm,chip-id found for %pOF.\n", dn); for_each_possible_cpu(cpu) { if (per_cpu(powernv_rng, cpu) == NULL || @@ -141,8 +178,8 @@ static __init int rng_init(void) for_each_compatible_node(dn, NULL, "ibm,power-rng") { rc = rng_create(dn); if (rc) { - pr_err("Failed creating rng for %s (%d).\n", - dn->full_name, rc); + pr_err("Failed creating rng for %pOF (%d).\n", + dn, rc); continue; } @@ -150,6 +187,8 @@ static __init int rng_init(void) of_platform_device_create(dn, NULL, NULL); } + initialise_darn(); + return 0; } machine_subsys_initcall(powernv, rng_init); diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 40dae96f7e20..c17f81e433f7 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -57,7 +57,7 @@ static void pnv_smp_setup_cpu(int cpu) static int pnv_smp_kick_cpu(int nr) { - unsigned int pcpu = get_hard_smp_processor_id(nr); + unsigned int pcpu; unsigned long start_here = __pa(ppc_function_entry(generic_secondary_smp_init)); long rc; @@ -66,6 +66,7 @@ static int pnv_smp_kick_cpu(int nr) if (nr < 0 || nr >= nr_cpu_ids) return -EINVAL; + pcpu = get_hard_smp_processor_id(nr); /* * If we already started or OPAL is not supported, we just * kick the CPU via the PACA @@ -164,12 +165,6 @@ static void pnv_smp_cpu_kill_self(void) if (cpu_has_feature(CPU_FTR_ARCH_207S)) wmask = SRR1_WAKEMASK_P8; - /* We don't want to take decrementer interrupts while we are offline, - * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9) - * enabled as to let IPIs in. - */ - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); - while (!generic_check_cpu_restart(cpu)) { /* * Clear IPI flag, since we don't handle IPIs while @@ -219,8 +214,6 @@ static void pnv_smp_cpu_kill_self(void) } - /* Re-enable decrementer interrupts */ - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c new file mode 100644 index 000000000000..5aae845b8cd9 --- /dev/null +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -0,0 +1,1134 @@ +/* + * Copyright 2016-17 IBM Corp. + * + * 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. + */ + +#define pr_fmt(fmt) "vas: " fmt + +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/io.h> +#include <linux/log2.h> +#include <linux/rcupdate.h> +#include <linux/cred.h> + +#include "vas.h" +#include "copy-paste.h" + +/* + * Compute the paste address region for the window @window using the + * ->paste_base_addr and ->paste_win_id_shift we got from device tree. + */ +static void compute_paste_address(struct vas_window *window, u64 *addr, int *len) +{ + int winid; + u64 base, shift; + + base = window->vinst->paste_base_addr; + shift = window->vinst->paste_win_id_shift; + winid = window->winid; + + *addr = base + (winid << shift); + if (len) + *len = PAGE_SIZE; + + pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr); +} + +static inline void get_hvwc_mmio_bar(struct vas_window *window, + u64 *start, int *len) +{ + u64 pbaddr; + + pbaddr = window->vinst->hvwc_bar_start; + *start = pbaddr + window->winid * VAS_HVWC_SIZE; + *len = VAS_HVWC_SIZE; +} + +static inline void get_uwc_mmio_bar(struct vas_window *window, + u64 *start, int *len) +{ + u64 pbaddr; + + pbaddr = window->vinst->uwc_bar_start; + *start = pbaddr + window->winid * VAS_UWC_SIZE; + *len = VAS_UWC_SIZE; +} + +/* + * Map the paste bus address of the given send window into kernel address + * space. Unlike MMIO regions (map_mmio_region() below), paste region must + * be mapped cache-able and is only applicable to send windows. + */ +static void *map_paste_region(struct vas_window *txwin) +{ + int len; + void *map; + char *name; + u64 start; + + name = kasprintf(GFP_KERNEL, "window-v%d-w%d", txwin->vinst->vas_id, + txwin->winid); + if (!name) + goto free_name; + + txwin->paste_addr_name = name; + compute_paste_address(txwin, &start, &len); + + if (!request_mem_region(start, len, name)) { + pr_devel("%s(): request_mem_region(0x%llx, %d) failed\n", + __func__, start, len); + goto free_name; + } + + map = ioremap_cache(start, len); + if (!map) { + pr_devel("%s(): ioremap_cache(0x%llx, %d) failed\n", __func__, + start, len); + goto free_name; + } + + pr_devel("Mapped paste addr 0x%llx to kaddr 0x%p\n", start, map); + return map; + +free_name: + kfree(name); + return ERR_PTR(-ENOMEM); +} + +static void *map_mmio_region(char *name, u64 start, int len) +{ + void *map; + + if (!request_mem_region(start, len, name)) { + pr_devel("%s(): request_mem_region(0x%llx, %d) failed\n", + __func__, start, len); + return NULL; + } + + map = ioremap(start, len); + if (!map) { + pr_devel("%s(): ioremap(0x%llx, %d) failed\n", __func__, start, + len); + return NULL; + } + + return map; +} + +static void unmap_region(void *addr, u64 start, int len) +{ + iounmap(addr); + release_mem_region((phys_addr_t)start, len); +} + +/* + * Unmap the paste address region for a window. + */ +static void unmap_paste_region(struct vas_window *window) +{ + int len; + u64 busaddr_start; + + if (window->paste_kaddr) { + compute_paste_address(window, &busaddr_start, &len); + unmap_region(window->paste_kaddr, busaddr_start, len); + window->paste_kaddr = NULL; + kfree(window->paste_addr_name); + window->paste_addr_name = NULL; + } +} + +/* + * Unmap the MMIO regions for a window. + */ +static void unmap_winctx_mmio_bars(struct vas_window *window) +{ + int len; + u64 busaddr_start; + + if (window->hvwc_map) { + get_hvwc_mmio_bar(window, &busaddr_start, &len); + unmap_region(window->hvwc_map, busaddr_start, len); + window->hvwc_map = NULL; + } + + if (window->uwc_map) { + get_uwc_mmio_bar(window, &busaddr_start, &len); + unmap_region(window->uwc_map, busaddr_start, len); + window->uwc_map = NULL; + } +} + +/* + * Find the Hypervisor Window Context (HVWC) MMIO Base Address Region and the + * OS/User Window Context (UWC) MMIO Base Address Region for the given window. + * Map these bus addresses and save the mapped kernel addresses in @window. + */ +int map_winctx_mmio_bars(struct vas_window *window) +{ + int len; + u64 start; + + get_hvwc_mmio_bar(window, &start, &len); + window->hvwc_map = map_mmio_region("HVWCM_Window", start, len); + + get_uwc_mmio_bar(window, &start, &len); + window->uwc_map = map_mmio_region("UWCM_Window", start, len); + + if (!window->hvwc_map || !window->uwc_map) { + unmap_winctx_mmio_bars(window); + return -1; + } + + return 0; +} + +/* + * Reset all valid registers in the HV and OS/User Window Contexts for + * the window identified by @window. + * + * NOTE: We cannot really use a for loop to reset window context. Not all + * offsets in a window context are valid registers and the valid + * registers are not sequential. And, we can only write to offsets + * with valid registers. + */ +void reset_window_regs(struct vas_window *window) +{ + write_hvwc_reg(window, VREG(LPID), 0ULL); + write_hvwc_reg(window, VREG(PID), 0ULL); + write_hvwc_reg(window, VREG(XLATE_MSR), 0ULL); + write_hvwc_reg(window, VREG(XLATE_LPCR), 0ULL); + write_hvwc_reg(window, VREG(XLATE_CTL), 0ULL); + write_hvwc_reg(window, VREG(AMR), 0ULL); + write_hvwc_reg(window, VREG(SEIDR), 0ULL); + write_hvwc_reg(window, VREG(FAULT_TX_WIN), 0ULL); + write_hvwc_reg(window, VREG(OSU_INTR_SRC_RA), 0ULL); + write_hvwc_reg(window, VREG(HV_INTR_SRC_RA), 0ULL); + write_hvwc_reg(window, VREG(PSWID), 0ULL); + write_hvwc_reg(window, VREG(LFIFO_BAR), 0ULL); + write_hvwc_reg(window, VREG(LDATA_STAMP_CTL), 0ULL); + write_hvwc_reg(window, VREG(LDMA_CACHE_CTL), 0ULL); + write_hvwc_reg(window, VREG(LRFIFO_PUSH), 0ULL); + write_hvwc_reg(window, VREG(CURR_MSG_COUNT), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_AFTER_COUNT), 0ULL); + write_hvwc_reg(window, VREG(LRX_WCRED), 0ULL); + write_hvwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL); + write_hvwc_reg(window, VREG(TX_WCRED), 0ULL); + write_hvwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL); + write_hvwc_reg(window, VREG(LFIFO_SIZE), 0ULL); + write_hvwc_reg(window, VREG(WINCTL), 0ULL); + write_hvwc_reg(window, VREG(WIN_STATUS), 0ULL); + write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), 0ULL); + write_hvwc_reg(window, VREG(TX_RSVD_BUF_COUNT), 0ULL); + write_hvwc_reg(window, VREG(LRFIFO_WIN_PTR), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_CTL), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_PID), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_LPID), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_TID), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_SCOPE), 0ULL); + write_hvwc_reg(window, VREG(NX_UTIL_ADDER), 0ULL); + + /* Skip read-only registers: NX_UTIL and NX_UTIL_SE */ + + /* + * The send and receive window credit adder registers are also + * accessible from HVWC and have been initialized above. We don't + * need to initialize from the OS/User Window Context, so skip + * following calls: + * + * write_uwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL); + * write_uwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL); + */ +} + +/* + * Initialize window context registers related to Address Translation. + * These registers are common to send/receive windows although they + * differ for user/kernel windows. As we resolve the TODOs we may + * want to add fields to vas_winctx and move the initialization to + * init_vas_winctx_regs(). + */ +static void init_xlate_regs(struct vas_window *window, bool user_win) +{ + u64 lpcr, val; + + /* + * MSR_TA, MSR_US are false for both kernel and user. + * MSR_DR and MSR_PR are false for kernel. + */ + val = 0ULL; + val = SET_FIELD(VAS_XLATE_MSR_HV, val, 1); + val = SET_FIELD(VAS_XLATE_MSR_SF, val, 1); + if (user_win) { + val = SET_FIELD(VAS_XLATE_MSR_DR, val, 1); + val = SET_FIELD(VAS_XLATE_MSR_PR, val, 1); + } + write_hvwc_reg(window, VREG(XLATE_MSR), val); + + lpcr = mfspr(SPRN_LPCR); + val = 0ULL; + /* + * NOTE: From Section 5.7.8.1 Segment Lookaside Buffer of the + * Power ISA, v3.0B, Page size encoding is 0 = 4KB, 5 = 64KB. + * + * NOTE: From Section 1.3.1, Address Translation Context of the + * Nest MMU Workbook, LPCR_SC should be 0 for Power9. + */ + val = SET_FIELD(VAS_XLATE_LPCR_PAGE_SIZE, val, 5); + val = SET_FIELD(VAS_XLATE_LPCR_ISL, val, lpcr & LPCR_ISL); + val = SET_FIELD(VAS_XLATE_LPCR_TC, val, lpcr & LPCR_TC); + val = SET_FIELD(VAS_XLATE_LPCR_SC, val, 0); + write_hvwc_reg(window, VREG(XLATE_LPCR), val); + + /* + * Section 1.3.1 (Address translation Context) of NMMU workbook. + * 0b00 Hashed Page Table mode + * 0b01 Reserved + * 0b10 Radix on HPT + * 0b11 Radix on Radix + */ + val = 0ULL; + val = SET_FIELD(VAS_XLATE_MODE, val, radix_enabled() ? 3 : 2); + write_hvwc_reg(window, VREG(XLATE_CTL), val); + + /* + * TODO: Can we mfspr(AMR) even for user windows? + */ + val = 0ULL; + val = SET_FIELD(VAS_AMR, val, mfspr(SPRN_AMR)); + write_hvwc_reg(window, VREG(AMR), val); + + val = 0ULL; + val = SET_FIELD(VAS_SEIDR, val, 0); + write_hvwc_reg(window, VREG(SEIDR), val); +} + +/* + * Initialize Reserved Send Buffer Count for the send window. It involves + * writing to the register, reading it back to confirm that the hardware + * has enough buffers to reserve. See section 1.3.1.2.1 of VAS workbook. + * + * Since we can only make a best-effort attempt to fulfill the request, + * we don't return any errors if we cannot. + * + * TODO: Reserved (aka dedicated) send buffers are not supported yet. + */ +static void init_rsvd_tx_buf_count(struct vas_window *txwin, + struct vas_winctx *winctx) +{ + write_hvwc_reg(txwin, VREG(TX_RSVD_BUF_COUNT), 0ULL); +} + +/* + * init_winctx_regs() + * Initialize window context registers for a receive window. + * Except for caching control and marking window open, the registers + * are initialized in the order listed in Section 3.1.4 (Window Context + * Cache Register Details) of the VAS workbook although they don't need + * to be. + * + * Design note: For NX receive windows, NX allocates the FIFO buffer in OPAL + * (so that it can get a large contiguous area) and passes that buffer + * to kernel via device tree. We now write that buffer address to the + * FIFO BAR. Would it make sense to do this all in OPAL? i.e have OPAL + * write the per-chip RX FIFO addresses to the windows during boot-up + * as a one-time task? That could work for NX but what about other + * receivers? Let the receivers tell us the rx-fifo buffers for now. + */ +int init_winctx_regs(struct vas_window *window, struct vas_winctx *winctx) +{ + u64 val; + int fifo_size; + + reset_window_regs(window); + + val = 0ULL; + val = SET_FIELD(VAS_LPID, val, winctx->lpid); + write_hvwc_reg(window, VREG(LPID), val); + + val = 0ULL; + val = SET_FIELD(VAS_PID_ID, val, winctx->pidr); + write_hvwc_reg(window, VREG(PID), val); + + init_xlate_regs(window, winctx->user_win); + + val = 0ULL; + val = SET_FIELD(VAS_FAULT_TX_WIN, val, 0); + write_hvwc_reg(window, VREG(FAULT_TX_WIN), val); + + /* In PowerNV, interrupts go to HV. */ + write_hvwc_reg(window, VREG(OSU_INTR_SRC_RA), 0ULL); + + val = 0ULL; + val = SET_FIELD(VAS_HV_INTR_SRC_RA, val, winctx->irq_port); + write_hvwc_reg(window, VREG(HV_INTR_SRC_RA), val); + + val = 0ULL; + val = SET_FIELD(VAS_PSWID_EA_HANDLE, val, winctx->pswid); + write_hvwc_reg(window, VREG(PSWID), val); + + write_hvwc_reg(window, VREG(SPARE1), 0ULL); + write_hvwc_reg(window, VREG(SPARE2), 0ULL); + write_hvwc_reg(window, VREG(SPARE3), 0ULL); + + /* + * NOTE: VAS expects the FIFO address to be copied into the LFIFO_BAR + * register as is - do NOT shift the address into VAS_LFIFO_BAR + * bit fields! Ok to set the page migration select fields - + * VAS ignores the lower 10+ bits in the address anyway, because + * the minimum FIFO size is 1K? + * + * See also: Design note in function header. + */ + val = __pa(winctx->rx_fifo); + val = SET_FIELD(VAS_PAGE_MIGRATION_SELECT, val, 0); + write_hvwc_reg(window, VREG(LFIFO_BAR), val); + + val = 0ULL; + val = SET_FIELD(VAS_LDATA_STAMP, val, winctx->data_stamp); + write_hvwc_reg(window, VREG(LDATA_STAMP_CTL), val); + + val = 0ULL; + val = SET_FIELD(VAS_LDMA_TYPE, val, winctx->dma_type); + val = SET_FIELD(VAS_LDMA_FIFO_DISABLE, val, winctx->fifo_disable); + write_hvwc_reg(window, VREG(LDMA_CACHE_CTL), val); + + write_hvwc_reg(window, VREG(LRFIFO_PUSH), 0ULL); + write_hvwc_reg(window, VREG(CURR_MSG_COUNT), 0ULL); + write_hvwc_reg(window, VREG(LNOTIFY_AFTER_COUNT), 0ULL); + + val = 0ULL; + val = SET_FIELD(VAS_LRX_WCRED, val, winctx->wcreds_max); + write_hvwc_reg(window, VREG(LRX_WCRED), val); + + val = 0ULL; + val = SET_FIELD(VAS_TX_WCRED, val, winctx->wcreds_max); + write_hvwc_reg(window, VREG(TX_WCRED), val); + + write_hvwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL); + write_hvwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL); + + fifo_size = winctx->rx_fifo_size / 1024; + + val = 0ULL; + val = SET_FIELD(VAS_LFIFO_SIZE, val, ilog2(fifo_size)); + write_hvwc_reg(window, VREG(LFIFO_SIZE), val); + + /* Update window control and caching control registers last so + * we mark the window open only after fully initializing it and + * pushing context to cache. + */ + + write_hvwc_reg(window, VREG(WIN_STATUS), 0ULL); + + init_rsvd_tx_buf_count(window, winctx); + + /* for a send window, point to the matching receive window */ + val = 0ULL; + val = SET_FIELD(VAS_LRX_WIN_ID, val, winctx->rx_win_id); + write_hvwc_reg(window, VREG(LRFIFO_WIN_PTR), val); + + write_hvwc_reg(window, VREG(SPARE4), 0ULL); + + val = 0ULL; + val = SET_FIELD(VAS_NOTIFY_DISABLE, val, winctx->notify_disable); + val = SET_FIELD(VAS_INTR_DISABLE, val, winctx->intr_disable); + val = SET_FIELD(VAS_NOTIFY_EARLY, val, winctx->notify_early); + val = SET_FIELD(VAS_NOTIFY_OSU_INTR, val, winctx->notify_os_intr_reg); + write_hvwc_reg(window, VREG(LNOTIFY_CTL), val); + + val = 0ULL; + val = SET_FIELD(VAS_LNOTIFY_PID, val, winctx->lnotify_pid); + write_hvwc_reg(window, VREG(LNOTIFY_PID), val); + + val = 0ULL; + val = SET_FIELD(VAS_LNOTIFY_LPID, val, winctx->lnotify_lpid); + write_hvwc_reg(window, VREG(LNOTIFY_LPID), val); + + val = 0ULL; + val = SET_FIELD(VAS_LNOTIFY_TID, val, winctx->lnotify_tid); + write_hvwc_reg(window, VREG(LNOTIFY_TID), val); + + val = 0ULL; + val = SET_FIELD(VAS_LNOTIFY_MIN_SCOPE, val, winctx->min_scope); + val = SET_FIELD(VAS_LNOTIFY_MAX_SCOPE, val, winctx->max_scope); + write_hvwc_reg(window, VREG(LNOTIFY_SCOPE), val); + + /* Skip read-only registers NX_UTIL and NX_UTIL_SE */ + + write_hvwc_reg(window, VREG(SPARE5), 0ULL); + write_hvwc_reg(window, VREG(NX_UTIL_ADDER), 0ULL); + write_hvwc_reg(window, VREG(SPARE6), 0ULL); + + /* Finally, push window context to memory and... */ + val = 0ULL; + val = SET_FIELD(VAS_PUSH_TO_MEM, val, 1); + write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), val); + + /* ... mark the window open for business */ + val = 0ULL; + val = SET_FIELD(VAS_WINCTL_REJ_NO_CREDIT, val, winctx->rej_no_credit); + val = SET_FIELD(VAS_WINCTL_PIN, val, winctx->pin_win); + val = SET_FIELD(VAS_WINCTL_TX_WCRED_MODE, val, winctx->tx_wcred_mode); + val = SET_FIELD(VAS_WINCTL_RX_WCRED_MODE, val, winctx->rx_wcred_mode); + val = SET_FIELD(VAS_WINCTL_TX_WORD_MODE, val, winctx->tx_word_mode); + val = SET_FIELD(VAS_WINCTL_RX_WORD_MODE, val, winctx->rx_word_mode); + val = SET_FIELD(VAS_WINCTL_FAULT_WIN, val, winctx->fault_win); + val = SET_FIELD(VAS_WINCTL_NX_WIN, val, winctx->nx_win); + val = SET_FIELD(VAS_WINCTL_OPEN, val, 1); + write_hvwc_reg(window, VREG(WINCTL), val); + + return 0; +} + +static DEFINE_SPINLOCK(vas_ida_lock); + +static void vas_release_window_id(struct ida *ida, int winid) +{ + spin_lock(&vas_ida_lock); + ida_remove(ida, winid); + spin_unlock(&vas_ida_lock); +} + +static int vas_assign_window_id(struct ida *ida) +{ + int rc, winid; + + do { + rc = ida_pre_get(ida, GFP_KERNEL); + if (!rc) + return -EAGAIN; + + spin_lock(&vas_ida_lock); + rc = ida_get_new(ida, &winid); + spin_unlock(&vas_ida_lock); + } while (rc == -EAGAIN); + + if (rc) + return rc; + + if (winid > VAS_WINDOWS_PER_CHIP) { + pr_err("Too many (%d) open windows\n", winid); + vas_release_window_id(ida, winid); + return -EAGAIN; + } + + return winid; +} + +static void vas_window_free(struct vas_window *window) +{ + int winid = window->winid; + struct vas_instance *vinst = window->vinst; + + unmap_winctx_mmio_bars(window); + kfree(window); + + vas_release_window_id(&vinst->ida, winid); +} + +static struct vas_window *vas_window_alloc(struct vas_instance *vinst) +{ + int winid; + struct vas_window *window; + + winid = vas_assign_window_id(&vinst->ida); + if (winid < 0) + return ERR_PTR(winid); + + window = kzalloc(sizeof(*window), GFP_KERNEL); + if (!window) + goto out_free; + + window->vinst = vinst; + window->winid = winid; + + if (map_winctx_mmio_bars(window)) + goto out_free; + + return window; + +out_free: + kfree(window); + vas_release_window_id(&vinst->ida, winid); + return ERR_PTR(-ENOMEM); +} + +static void put_rx_win(struct vas_window *rxwin) +{ + /* Better not be a send window! */ + WARN_ON_ONCE(rxwin->tx_win); + + atomic_dec(&rxwin->num_txwins); +} + +/* + * Get the VAS receive window associated with NX engine identified + * by @cop and if applicable, @pswid. + * + * See also function header of set_vinst_win(). + */ +static struct vas_window *get_vinst_rxwin(struct vas_instance *vinst, + enum vas_cop_type cop, u32 pswid) +{ + struct vas_window *rxwin; + + mutex_lock(&vinst->mutex); + + if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI) + rxwin = vinst->rxwin[cop] ?: ERR_PTR(-EINVAL); + else + rxwin = ERR_PTR(-EINVAL); + + if (!IS_ERR(rxwin)) + atomic_inc(&rxwin->num_txwins); + + mutex_unlock(&vinst->mutex); + + return rxwin; +} + +/* + * We have two tables of windows in a VAS instance. The first one, + * ->windows[], contains all the windows in the instance and allows + * looking up a window by its id. It is used to look up send windows + * during fault handling and receive windows when pairing user space + * send/receive windows. + * + * The second table, ->rxwin[], contains receive windows that are + * associated with NX engines. This table has VAS_COP_TYPE_MAX + * entries and is used to look up a receive window by its + * coprocessor type. + * + * Here, we save @window in the ->windows[] table. If it is a receive + * window, we also save the window in the ->rxwin[] table. + */ +static void set_vinst_win(struct vas_instance *vinst, + struct vas_window *window) +{ + int id = window->winid; + + mutex_lock(&vinst->mutex); + + /* + * There should only be one receive window for a coprocessor type + * unless its a user (FTW) window. + */ + if (!window->user_win && !window->tx_win) { + WARN_ON_ONCE(vinst->rxwin[window->cop]); + vinst->rxwin[window->cop] = window; + } + + WARN_ON_ONCE(vinst->windows[id] != NULL); + vinst->windows[id] = window; + + mutex_unlock(&vinst->mutex); +} + +/* + * Clear this window from the table(s) of windows for this VAS instance. + * See also function header of set_vinst_win(). + */ +static void clear_vinst_win(struct vas_window *window) +{ + int id = window->winid; + struct vas_instance *vinst = window->vinst; + + mutex_lock(&vinst->mutex); + + if (!window->user_win && !window->tx_win) { + WARN_ON_ONCE(!vinst->rxwin[window->cop]); + vinst->rxwin[window->cop] = NULL; + } + + WARN_ON_ONCE(vinst->windows[id] != window); + vinst->windows[id] = NULL; + + mutex_unlock(&vinst->mutex); +} + +static void init_winctx_for_rxwin(struct vas_window *rxwin, + struct vas_rx_win_attr *rxattr, + struct vas_winctx *winctx) +{ + /* + * We first zero (memset()) all fields and only set non-zero fields. + * Following fields are 0/false but maybe deserve a comment: + * + * ->notify_os_intr_reg In powerNV, send intrs to HV + * ->notify_disable False for NX windows + * ->intr_disable False for Fault Windows + * ->xtra_write False for NX windows + * ->notify_early NA for NX windows + * ->rsvd_txbuf_count NA for Rx windows + * ->lpid, ->pid, ->tid NA for Rx windows + */ + + memset(winctx, 0, sizeof(struct vas_winctx)); + + winctx->rx_fifo = rxattr->rx_fifo; + winctx->rx_fifo_size = rxattr->rx_fifo_size; + winctx->wcreds_max = rxattr->wcreds_max ?: VAS_WCREDS_DEFAULT; + winctx->pin_win = rxattr->pin_win; + + winctx->nx_win = rxattr->nx_win; + winctx->fault_win = rxattr->fault_win; + winctx->rx_word_mode = rxattr->rx_win_ord_mode; + winctx->tx_word_mode = rxattr->tx_win_ord_mode; + winctx->rx_wcred_mode = rxattr->rx_wcred_mode; + winctx->tx_wcred_mode = rxattr->tx_wcred_mode; + + if (winctx->nx_win) { + winctx->data_stamp = true; + winctx->intr_disable = true; + winctx->pin_win = true; + + WARN_ON_ONCE(winctx->fault_win); + WARN_ON_ONCE(!winctx->rx_word_mode); + WARN_ON_ONCE(!winctx->tx_word_mode); + WARN_ON_ONCE(winctx->notify_after_count); + } else if (winctx->fault_win) { + winctx->notify_disable = true; + } else if (winctx->user_win) { + /* + * Section 1.8.1 Low Latency Core-Core Wake up of + * the VAS workbook: + * + * - disable credit checks ([tr]x_wcred_mode = false) + * - disable FIFO writes + * - enable ASB_Notify, disable interrupt + */ + winctx->fifo_disable = true; + winctx->intr_disable = true; + winctx->rx_fifo = NULL; + } + + winctx->lnotify_lpid = rxattr->lnotify_lpid; + winctx->lnotify_pid = rxattr->lnotify_pid; + winctx->lnotify_tid = rxattr->lnotify_tid; + winctx->pswid = rxattr->pswid; + winctx->dma_type = VAS_DMA_TYPE_INJECT; + winctx->tc_mode = rxattr->tc_mode; + + winctx->min_scope = VAS_SCOPE_LOCAL; + winctx->max_scope = VAS_SCOPE_VECTORED_GROUP; +} + +static bool rx_win_args_valid(enum vas_cop_type cop, + struct vas_rx_win_attr *attr) +{ + dump_rx_win_attr(attr); + + if (cop >= VAS_COP_TYPE_MAX) + return false; + + if (cop != VAS_COP_TYPE_FTW && + attr->rx_fifo_size < VAS_RX_FIFO_SIZE_MIN) + return false; + + if (attr->rx_fifo_size > VAS_RX_FIFO_SIZE_MAX) + return false; + + if (attr->nx_win) { + /* cannot be fault or user window if it is nx */ + if (attr->fault_win || attr->user_win) + return false; + /* + * Section 3.1.4.32: NX Windows must not disable notification, + * and must not enable interrupts or early notification. + */ + if (attr->notify_disable || !attr->intr_disable || + attr->notify_early) + return false; + } else if (attr->fault_win) { + /* cannot be both fault and user window */ + if (attr->user_win) + return false; + + /* + * Section 3.1.4.32: Fault windows must disable notification + * but not interrupts. + */ + if (!attr->notify_disable || attr->intr_disable) + return false; + + } else if (attr->user_win) { + /* + * User receive windows are only for fast-thread-wakeup + * (FTW). They don't need a FIFO and must disable interrupts + */ + if (attr->rx_fifo || attr->rx_fifo_size || !attr->intr_disable) + return false; + } else { + /* Rx window must be one of NX or Fault or User window. */ + return false; + } + + return true; +} + +void vas_init_rx_win_attr(struct vas_rx_win_attr *rxattr, enum vas_cop_type cop) +{ + memset(rxattr, 0, sizeof(*rxattr)); + + if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI) { + rxattr->pin_win = true; + rxattr->nx_win = true; + rxattr->fault_win = false; + rxattr->intr_disable = true; + rxattr->rx_wcred_mode = true; + rxattr->tx_wcred_mode = true; + rxattr->rx_win_ord_mode = true; + rxattr->tx_win_ord_mode = true; + } else if (cop == VAS_COP_TYPE_FAULT) { + rxattr->pin_win = true; + rxattr->fault_win = true; + rxattr->notify_disable = true; + rxattr->rx_wcred_mode = true; + rxattr->tx_wcred_mode = true; + rxattr->rx_win_ord_mode = true; + rxattr->tx_win_ord_mode = true; + } else if (cop == VAS_COP_TYPE_FTW) { + rxattr->user_win = true; + rxattr->intr_disable = true; + + /* + * As noted in the VAS Workbook we disable credit checks. + * If we enable credit checks in the future, we must also + * implement a mechanism to return the user credits or new + * paste operations will fail. + */ + } +} +EXPORT_SYMBOL_GPL(vas_init_rx_win_attr); + +struct vas_window *vas_rx_win_open(int vasid, enum vas_cop_type cop, + struct vas_rx_win_attr *rxattr) +{ + struct vas_window *rxwin; + struct vas_winctx winctx; + struct vas_instance *vinst; + + if (!rx_win_args_valid(cop, rxattr)) + return ERR_PTR(-EINVAL); + + vinst = find_vas_instance(vasid); + if (!vinst) { + pr_devel("vasid %d not found!\n", vasid); + return ERR_PTR(-EINVAL); + } + pr_devel("Found instance %d\n", vasid); + + rxwin = vas_window_alloc(vinst); + if (IS_ERR(rxwin)) { + pr_devel("Unable to allocate memory for Rx window\n"); + return rxwin; + } + + rxwin->tx_win = false; + rxwin->nx_win = rxattr->nx_win; + rxwin->user_win = rxattr->user_win; + rxwin->cop = cop; + if (rxattr->user_win) + rxwin->pid = task_pid_vnr(current); + + init_winctx_for_rxwin(rxwin, rxattr, &winctx); + init_winctx_regs(rxwin, &winctx); + + set_vinst_win(vinst, rxwin); + + return rxwin; +} +EXPORT_SYMBOL_GPL(vas_rx_win_open); + +void vas_init_tx_win_attr(struct vas_tx_win_attr *txattr, enum vas_cop_type cop) +{ + memset(txattr, 0, sizeof(*txattr)); + + if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI) { + txattr->rej_no_credit = false; + txattr->rx_wcred_mode = true; + txattr->tx_wcred_mode = true; + txattr->rx_win_ord_mode = true; + txattr->tx_win_ord_mode = true; + } else if (cop == VAS_COP_TYPE_FTW) { + txattr->user_win = true; + } +} +EXPORT_SYMBOL_GPL(vas_init_tx_win_attr); + +static void init_winctx_for_txwin(struct vas_window *txwin, + struct vas_tx_win_attr *txattr, + struct vas_winctx *winctx) +{ + /* + * We first zero all fields and only set non-zero ones. Following + * are some fields set to 0/false for the stated reason: + * + * ->notify_os_intr_reg In powernv, send intrs to HV + * ->rsvd_txbuf_count Not supported yet. + * ->notify_disable False for NX windows + * ->xtra_write False for NX windows + * ->notify_early NA for NX windows + * ->lnotify_lpid NA for Tx windows + * ->lnotify_pid NA for Tx windows + * ->lnotify_tid NA for Tx windows + * ->tx_win_cred_mode Ignore for now for NX windows + * ->rx_win_cred_mode Ignore for now for NX windows + */ + memset(winctx, 0, sizeof(struct vas_winctx)); + + winctx->wcreds_max = txattr->wcreds_max ?: VAS_WCREDS_DEFAULT; + + winctx->user_win = txattr->user_win; + winctx->nx_win = txwin->rxwin->nx_win; + winctx->pin_win = txattr->pin_win; + + winctx->rx_wcred_mode = txattr->rx_wcred_mode; + winctx->tx_wcred_mode = txattr->tx_wcred_mode; + winctx->rx_word_mode = txattr->rx_win_ord_mode; + winctx->tx_word_mode = txattr->tx_win_ord_mode; + + if (winctx->nx_win) { + winctx->data_stamp = true; + winctx->intr_disable = true; + } + + winctx->lpid = txattr->lpid; + winctx->pidr = txattr->pidr; + winctx->rx_win_id = txwin->rxwin->winid; + + winctx->dma_type = VAS_DMA_TYPE_INJECT; + winctx->tc_mode = txattr->tc_mode; + winctx->min_scope = VAS_SCOPE_LOCAL; + winctx->max_scope = VAS_SCOPE_VECTORED_GROUP; + + winctx->pswid = 0; +} + +static bool tx_win_args_valid(enum vas_cop_type cop, + struct vas_tx_win_attr *attr) +{ + if (attr->tc_mode != VAS_THRESH_DISABLED) + return false; + + if (cop > VAS_COP_TYPE_MAX) + return false; + + if (attr->user_win && + (cop != VAS_COP_TYPE_FTW || attr->rsvd_txbuf_count)) + return false; + + return true; +} + +struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, + struct vas_tx_win_attr *attr) +{ + int rc; + struct vas_window *txwin; + struct vas_window *rxwin; + struct vas_winctx winctx; + struct vas_instance *vinst; + + if (!tx_win_args_valid(cop, attr)) + return ERR_PTR(-EINVAL); + + vinst = find_vas_instance(vasid); + if (!vinst) { + pr_devel("vasid %d not found!\n", vasid); + return ERR_PTR(-EINVAL); + } + + rxwin = get_vinst_rxwin(vinst, cop, attr->pswid); + if (IS_ERR(rxwin)) { + pr_devel("No RxWin for vasid %d, cop %d\n", vasid, cop); + return rxwin; + } + + txwin = vas_window_alloc(vinst); + if (IS_ERR(txwin)) { + rc = PTR_ERR(txwin); + goto put_rxwin; + } + + txwin->tx_win = 1; + txwin->rxwin = rxwin; + txwin->nx_win = txwin->rxwin->nx_win; + txwin->pid = attr->pid; + txwin->user_win = attr->user_win; + + init_winctx_for_txwin(txwin, attr, &winctx); + + init_winctx_regs(txwin, &winctx); + + /* + * If its a kernel send window, map the window address into the + * kernel's address space. For user windows, user must issue an + * mmap() to map the window into their address space. + * + * NOTE: If kernel ever resubmits a user CRB after handling a page + * fault, we will need to map this into kernel as well. + */ + if (!txwin->user_win) { + txwin->paste_kaddr = map_paste_region(txwin); + if (IS_ERR(txwin->paste_kaddr)) { + rc = PTR_ERR(txwin->paste_kaddr); + goto free_window; + } + } + + set_vinst_win(vinst, txwin); + + return txwin; + +free_window: + vas_window_free(txwin); + +put_rxwin: + put_rx_win(rxwin); + return ERR_PTR(rc); + +} +EXPORT_SYMBOL_GPL(vas_tx_win_open); + +int vas_copy_crb(void *crb, int offset) +{ + return vas_copy(crb, offset); +} +EXPORT_SYMBOL_GPL(vas_copy_crb); + +#define RMA_LSMP_REPORT_ENABLE PPC_BIT(53) +int vas_paste_crb(struct vas_window *txwin, int offset, bool re) +{ + int rc; + void *addr; + uint64_t val; + + /* + * Only NX windows are supported for now and hardware assumes + * report-enable flag is set for NX windows. Ensure software + * complies too. + */ + WARN_ON_ONCE(txwin->nx_win && !re); + + addr = txwin->paste_kaddr; + if (re) { + /* + * Set the REPORT_ENABLE bit (equivalent to writing + * to 1K offset of the paste address) + */ + val = SET_FIELD(RMA_LSMP_REPORT_ENABLE, 0ULL, 1); + addr += val; + } + + /* + * Map the raw CR value from vas_paste() to an error code (there + * is just pass or fail for now though). + */ + rc = vas_paste(addr, offset); + if (rc == 2) + rc = 0; + else + rc = -EINVAL; + + print_fifo_msg_count(txwin); + + return rc; +} +EXPORT_SYMBOL_GPL(vas_paste_crb); + +static void poll_window_busy_state(struct vas_window *window) +{ + int busy; + u64 val; + +retry: + /* + * Poll Window Busy flag + */ + val = read_hvwc_reg(window, VREG(WIN_STATUS)); + busy = GET_FIELD(VAS_WIN_BUSY, val); + if (busy) { + val = 0; + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(HZ); + goto retry; + } +} + +static void poll_window_castout(struct vas_window *window) +{ + int cached; + u64 val; + + /* Cast window context out of the cache */ +retry: + val = read_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL)); + cached = GET_FIELD(VAS_WIN_CACHE_STATUS, val); + if (cached) { + val = 0ULL; + val = SET_FIELD(VAS_CASTOUT_REQ, val, 1); + val = SET_FIELD(VAS_PUSH_TO_MEM, val, 0); + write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), val); + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_timeout(HZ); + goto retry; + } +} + +/* + * Close a window. + * + * See Section 1.12.1 of VAS workbook v1.05 for details on closing window: + * - Disable new paste operations (unmap paste address) + * - Poll for the "Window Busy" bit to be cleared + * - Clear the Open/Enable bit for the Window. + * - Poll for return of window Credits (implies FIFO empty for Rx win?) + * - Unpin and cast window context out of cache + * + * Besides the hardware, kernel has some bookkeeping of course. + */ +int vas_win_close(struct vas_window *window) +{ + u64 val; + + if (!window) + return 0; + + if (!window->tx_win && atomic_read(&window->num_txwins) != 0) { + pr_devel("Attempting to close an active Rx window!\n"); + WARN_ON_ONCE(1); + return -EBUSY; + } + + unmap_paste_region(window); + + clear_vinst_win(window); + + poll_window_busy_state(window); + + /* Unpin window from cache and close it */ + val = read_hvwc_reg(window, VREG(WINCTL)); + val = SET_FIELD(VAS_WINCTL_PIN, val, 0); + val = SET_FIELD(VAS_WINCTL_OPEN, val, 0); + write_hvwc_reg(window, VREG(WINCTL), val); + + poll_window_castout(window); + + /* if send window, drop reference to matching receive window */ + if (window->tx_win) + put_rx_win(window->rxwin); + + vas_window_free(window); + + return 0; +} +EXPORT_SYMBOL_GPL(vas_win_close); diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c new file mode 100644 index 000000000000..565a4878fefa --- /dev/null +++ b/arch/powerpc/platforms/powernv/vas.c @@ -0,0 +1,151 @@ +/* + * Copyright 2016-17 IBM Corp. + * + * 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. + */ + +#define pr_fmt(fmt) "vas: " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/platform_device.h> +#include <linux/of_platform.h> +#include <linux/of_address.h> +#include <linux/of.h> + +#include "vas.h" + +static DEFINE_MUTEX(vas_mutex); +static LIST_HEAD(vas_instances); + +static int init_vas_instance(struct platform_device *pdev) +{ + int rc, vasid; + struct resource *res; + struct vas_instance *vinst; + struct device_node *dn = pdev->dev.of_node; + + rc = of_property_read_u32(dn, "ibm,vas-id", &vasid); + if (rc) { + pr_err("No ibm,vas-id property for %s?\n", pdev->name); + return -ENODEV; + } + + if (pdev->num_resources != 4) { + pr_err("Unexpected DT configuration for [%s, %d]\n", + pdev->name, vasid); + return -ENODEV; + } + + vinst = kzalloc(sizeof(*vinst), GFP_KERNEL); + if (!vinst) + return -ENOMEM; + + INIT_LIST_HEAD(&vinst->node); + ida_init(&vinst->ida); + mutex_init(&vinst->mutex); + vinst->vas_id = vasid; + vinst->pdev = pdev; + + res = &pdev->resource[0]; + vinst->hvwc_bar_start = res->start; + + res = &pdev->resource[1]; + vinst->uwc_bar_start = res->start; + + res = &pdev->resource[2]; + vinst->paste_base_addr = res->start; + + res = &pdev->resource[3]; + if (res->end > 62) { + pr_err("Bad 'paste_win_id_shift' in DT, %llx\n", res->end); + goto free_vinst; + } + + vinst->paste_win_id_shift = 63 - res->end; + + pr_devel("Initialized instance [%s, %d], paste_base 0x%llx, " + "paste_win_id_shift 0x%llx\n", pdev->name, vasid, + vinst->paste_base_addr, vinst->paste_win_id_shift); + + mutex_lock(&vas_mutex); + list_add(&vinst->node, &vas_instances); + mutex_unlock(&vas_mutex); + + dev_set_drvdata(&pdev->dev, vinst); + + return 0; + +free_vinst: + kfree(vinst); + return -ENODEV; + +} + +/* + * Although this is read/used multiple times, it is written to only + * during initialization. + */ +struct vas_instance *find_vas_instance(int vasid) +{ + struct list_head *ent; + struct vas_instance *vinst; + + mutex_lock(&vas_mutex); + list_for_each(ent, &vas_instances) { + vinst = list_entry(ent, struct vas_instance, node); + if (vinst->vas_id == vasid) { + mutex_unlock(&vas_mutex); + return vinst; + } + } + mutex_unlock(&vas_mutex); + + pr_devel("Instance %d not found\n", vasid); + return NULL; +} + +static int vas_probe(struct platform_device *pdev) +{ + return init_vas_instance(pdev); +} + +static const struct of_device_id powernv_vas_match[] = { + { .compatible = "ibm,vas",}, + {}, +}; + +static struct platform_driver vas_driver = { + .driver = { + .name = "vas", + .of_match_table = powernv_vas_match, + }, + .probe = vas_probe, +}; + +static int __init vas_init(void) +{ + int found = 0; + struct device_node *dn; + + platform_driver_register(&vas_driver); + + for_each_compatible_node(dn, NULL, "ibm,vas") { + of_platform_device_create(dn, NULL, NULL); + found++; + } + + if (!found) + return -ENODEV; + + pr_devel("Found %d instances\n", found); + + return 0; +} +device_initcall(vas_init); diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h new file mode 100644 index 000000000000..38dee5d50f31 --- /dev/null +++ b/arch/powerpc/platforms/powernv/vas.h @@ -0,0 +1,467 @@ +/* + * Copyright 2016-17 IBM Corp. + * + * 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. + */ + +#ifndef _VAS_H +#define _VAS_H +#include <linux/atomic.h> +#include <linux/idr.h> +#include <asm/vas.h> +#include <linux/io.h> + +/* + * Overview of Virtual Accelerator Switchboard (VAS). + * + * VAS is a hardware "switchboard" that allows senders and receivers to + * exchange messages with _minimal_ kernel involvment. The receivers are + * typically NX coprocessor engines that perform compression or encryption + * in hardware, but receivers can also be other software threads. + * + * Senders are user/kernel threads that submit compression/encryption or + * other requests to the receivers. Senders must format their messages as + * Coprocessor Request Blocks (CRB)s and submit them using the "copy" and + * "paste" instructions which were introduced in Power9. + * + * A Power node can have (upto?) 8 Power chips. There is one instance of + * VAS in each Power9 chip. Each instance of VAS has 64K windows or ports, + * Senders and receivers must each connect to a separate window before they + * can exchange messages through the switchboard. + * + * Each window is described by two types of window contexts: + * + * Hypervisor Window Context (HVWC) of size VAS_HVWC_SIZE bytes + * + * OS/User Window Context (UWC) of size VAS_UWC_SIZE bytes. + * + * A window context can be viewed as a set of 64-bit registers. The settings + * in these registers configure/control/determine the behavior of the VAS + * hardware when messages are sent/received through the window. The registers + * in the HVWC are configured by the kernel while the registers in the UWC can + * be configured by the kernel or by the user space application that is using + * the window. + * + * The HVWCs for all windows on a specific instance of VAS are in a contiguous + * range of hardware addresses or Base address region (BAR) referred to as the + * HVWC BAR for the instance. Similarly the UWCs for all windows on an instance + * are referred to as the UWC BAR for the instance. + * + * The two BARs for each instance are defined Power9 MMIO Ranges spreadsheet + * and available to the kernel in the VAS node's "reg" property in the device + * tree: + * + * /proc/device-tree/vasm@.../reg + * + * (see vas_probe() for details on the reg property). + * + * The kernel maps the HVWC and UWC BAR regions into the kernel address + * space (hvwc_map and uwc_map). The kernel can then access the window + * contexts of a specific window using: + * + * hvwc = hvwc_map + winid * VAS_HVWC_SIZE. + * uwc = uwc_map + winid * VAS_UWC_SIZE. + * + * where winid is the window index (0..64K). + * + * As mentioned, a window context is used to "configure" a window. Besides + * this configuration address, each _send_ window also has a unique hardware + * "paste" address that is used to submit requests/CRBs (see vas_paste_crb()). + * + * The hardware paste address for a window is computed using the "paste + * base address" and "paste win id shift" reg properties in the VAS device + * tree node using: + * + * paste_addr = paste_base + ((winid << paste_win_id_shift)) + * + * (again, see vas_probe() for ->paste_base_addr and ->paste_win_id_shift). + * + * The kernel maps this hardware address into the sender's address space + * after which they can use the 'paste' instruction (new in Power9) to + * send a message (submit a request aka CRB) to the coprocessor. + * + * NOTE: In the initial version, senders can only in-kernel drivers/threads. + * Support for user space threads will be added in follow-on patches. + * + * TODO: Do we need to map the UWC into user address space so they can return + * credits? Its NA for NX but may be needed for other receive windows. + * + */ + +#define VAS_WINDOWS_PER_CHIP (64 << 10) + +/* + * Hypervisor and OS/USer Window Context sizes + */ +#define VAS_HVWC_SIZE 512 +#define VAS_UWC_SIZE PAGE_SIZE + +/* + * Initial per-process credits. + * Max send window credits: 4K-1 (12-bits in VAS_TX_WCRED) + * Max receive window credits: 64K-1 (16 bits in VAS_LRX_WCRED) + * + * TODO: Needs tuning for per-process credits + */ +#define VAS_WCREDS_MIN 16 +#define VAS_WCREDS_MAX ((64 << 10) - 1) +#define VAS_WCREDS_DEFAULT (1 << 10) + +/* + * VAS Window Context Register Offsets and bitmasks. + * See Section 3.1.4 of VAS Work book + */ +#define VAS_LPID_OFFSET 0x010 +#define VAS_LPID PPC_BITMASK(0, 11) + +#define VAS_PID_OFFSET 0x018 +#define VAS_PID_ID PPC_BITMASK(0, 19) + +#define VAS_XLATE_MSR_OFFSET 0x020 +#define VAS_XLATE_MSR_DR PPC_BIT(0) +#define VAS_XLATE_MSR_TA PPC_BIT(1) +#define VAS_XLATE_MSR_PR PPC_BIT(2) +#define VAS_XLATE_MSR_US PPC_BIT(3) +#define VAS_XLATE_MSR_HV PPC_BIT(4) +#define VAS_XLATE_MSR_SF PPC_BIT(5) + +#define VAS_XLATE_LPCR_OFFSET 0x028 +#define VAS_XLATE_LPCR_PAGE_SIZE PPC_BITMASK(0, 2) +#define VAS_XLATE_LPCR_ISL PPC_BIT(3) +#define VAS_XLATE_LPCR_TC PPC_BIT(4) +#define VAS_XLATE_LPCR_SC PPC_BIT(5) + +#define VAS_XLATE_CTL_OFFSET 0x030 +#define VAS_XLATE_MODE PPC_BITMASK(0, 1) + +#define VAS_AMR_OFFSET 0x040 +#define VAS_AMR PPC_BITMASK(0, 63) + +#define VAS_SEIDR_OFFSET 0x048 +#define VAS_SEIDR PPC_BITMASK(0, 63) + +#define VAS_FAULT_TX_WIN_OFFSET 0x050 +#define VAS_FAULT_TX_WIN PPC_BITMASK(48, 63) + +#define VAS_OSU_INTR_SRC_RA_OFFSET 0x060 +#define VAS_OSU_INTR_SRC_RA PPC_BITMASK(8, 63) + +#define VAS_HV_INTR_SRC_RA_OFFSET 0x070 +#define VAS_HV_INTR_SRC_RA PPC_BITMASK(8, 63) + +#define VAS_PSWID_OFFSET 0x078 +#define VAS_PSWID_EA_HANDLE PPC_BITMASK(0, 31) + +#define VAS_SPARE1_OFFSET 0x080 +#define VAS_SPARE2_OFFSET 0x088 +#define VAS_SPARE3_OFFSET 0x090 +#define VAS_SPARE4_OFFSET 0x130 +#define VAS_SPARE5_OFFSET 0x160 +#define VAS_SPARE6_OFFSET 0x188 + +#define VAS_LFIFO_BAR_OFFSET 0x0A0 +#define VAS_LFIFO_BAR PPC_BITMASK(8, 53) +#define VAS_PAGE_MIGRATION_SELECT PPC_BITMASK(54, 56) + +#define VAS_LDATA_STAMP_CTL_OFFSET 0x0A8 +#define VAS_LDATA_STAMP PPC_BITMASK(0, 1) +#define VAS_XTRA_WRITE PPC_BIT(2) + +#define VAS_LDMA_CACHE_CTL_OFFSET 0x0B0 +#define VAS_LDMA_TYPE PPC_BITMASK(0, 1) +#define VAS_LDMA_FIFO_DISABLE PPC_BIT(2) + +#define VAS_LRFIFO_PUSH_OFFSET 0x0B8 +#define VAS_LRFIFO_PUSH PPC_BITMASK(0, 15) + +#define VAS_CURR_MSG_COUNT_OFFSET 0x0C0 +#define VAS_CURR_MSG_COUNT PPC_BITMASK(0, 7) + +#define VAS_LNOTIFY_AFTER_COUNT_OFFSET 0x0C8 +#define VAS_LNOTIFY_AFTER_COUNT PPC_BITMASK(0, 7) + +#define VAS_LRX_WCRED_OFFSET 0x0E0 +#define VAS_LRX_WCRED PPC_BITMASK(0, 15) + +#define VAS_LRX_WCRED_ADDER_OFFSET 0x190 +#define VAS_LRX_WCRED_ADDER PPC_BITMASK(0, 15) + +#define VAS_TX_WCRED_OFFSET 0x0F0 +#define VAS_TX_WCRED PPC_BITMASK(4, 15) + +#define VAS_TX_WCRED_ADDER_OFFSET 0x1A0 +#define VAS_TX_WCRED_ADDER PPC_BITMASK(4, 15) + +#define VAS_LFIFO_SIZE_OFFSET 0x100 +#define VAS_LFIFO_SIZE PPC_BITMASK(0, 3) + +#define VAS_WINCTL_OFFSET 0x108 +#define VAS_WINCTL_OPEN PPC_BIT(0) +#define VAS_WINCTL_REJ_NO_CREDIT PPC_BIT(1) +#define VAS_WINCTL_PIN PPC_BIT(2) +#define VAS_WINCTL_TX_WCRED_MODE PPC_BIT(3) +#define VAS_WINCTL_RX_WCRED_MODE PPC_BIT(4) +#define VAS_WINCTL_TX_WORD_MODE PPC_BIT(5) +#define VAS_WINCTL_RX_WORD_MODE PPC_BIT(6) +#define VAS_WINCTL_RSVD_TXBUF PPC_BIT(7) +#define VAS_WINCTL_THRESH_CTL PPC_BITMASK(8, 9) +#define VAS_WINCTL_FAULT_WIN PPC_BIT(10) +#define VAS_WINCTL_NX_WIN PPC_BIT(11) + +#define VAS_WIN_STATUS_OFFSET 0x110 +#define VAS_WIN_BUSY PPC_BIT(1) + +#define VAS_WIN_CTX_CACHING_CTL_OFFSET 0x118 +#define VAS_CASTOUT_REQ PPC_BIT(0) +#define VAS_PUSH_TO_MEM PPC_BIT(1) +#define VAS_WIN_CACHE_STATUS PPC_BIT(4) + +#define VAS_TX_RSVD_BUF_COUNT_OFFSET 0x120 +#define VAS_RXVD_BUF_COUNT PPC_BITMASK(58, 63) + +#define VAS_LRFIFO_WIN_PTR_OFFSET 0x128 +#define VAS_LRX_WIN_ID PPC_BITMASK(0, 15) + +/* + * Local Notification Control Register controls what happens in _response_ + * to a paste command and hence applies only to receive windows. + */ +#define VAS_LNOTIFY_CTL_OFFSET 0x138 +#define VAS_NOTIFY_DISABLE PPC_BIT(0) +#define VAS_INTR_DISABLE PPC_BIT(1) +#define VAS_NOTIFY_EARLY PPC_BIT(2) +#define VAS_NOTIFY_OSU_INTR PPC_BIT(3) + +#define VAS_LNOTIFY_PID_OFFSET 0x140 +#define VAS_LNOTIFY_PID PPC_BITMASK(0, 19) + +#define VAS_LNOTIFY_LPID_OFFSET 0x148 +#define VAS_LNOTIFY_LPID PPC_BITMASK(0, 11) + +#define VAS_LNOTIFY_TID_OFFSET 0x150 +#define VAS_LNOTIFY_TID PPC_BITMASK(0, 15) + +#define VAS_LNOTIFY_SCOPE_OFFSET 0x158 +#define VAS_LNOTIFY_MIN_SCOPE PPC_BITMASK(0, 1) +#define VAS_LNOTIFY_MAX_SCOPE PPC_BITMASK(2, 3) + +#define VAS_NX_UTIL_OFFSET 0x1B0 +#define VAS_NX_UTIL PPC_BITMASK(0, 63) + +/* SE: Side effects */ +#define VAS_NX_UTIL_SE_OFFSET 0x1B8 +#define VAS_NX_UTIL_SE PPC_BITMASK(0, 63) + +#define VAS_NX_UTIL_ADDER_OFFSET 0x180 +#define VAS_NX_UTIL_ADDER PPC_BITMASK(32, 63) + +/* + * Local Notify Scope Control Register. (Receive windows only). + */ +enum vas_notify_scope { + VAS_SCOPE_LOCAL, + VAS_SCOPE_GROUP, + VAS_SCOPE_VECTORED_GROUP, + VAS_SCOPE_UNUSED, +}; + +/* + * Local DMA Cache Control Register (Receive windows only). + */ +enum vas_dma_type { + VAS_DMA_TYPE_INJECT, + VAS_DMA_TYPE_WRITE, +}; + +/* + * Local Notify Scope Control Register. (Receive windows only). + * Not applicable to NX receive windows. + */ +enum vas_notify_after_count { + VAS_NOTIFY_AFTER_256 = 0, + VAS_NOTIFY_NONE, + VAS_NOTIFY_AFTER_2 +}; + +/* + * One per instance of VAS. Each instance will have a separate set of + * receive windows, one per coprocessor type. + * + * See also function header of set_vinst_win() for details on ->windows[] + * and ->rxwin[] tables. + */ +struct vas_instance { + int vas_id; + struct ida ida; + struct list_head node; + struct platform_device *pdev; + + u64 hvwc_bar_start; + u64 uwc_bar_start; + u64 paste_base_addr; + u64 paste_win_id_shift; + + struct mutex mutex; + struct vas_window *rxwin[VAS_COP_TYPE_MAX]; + struct vas_window *windows[VAS_WINDOWS_PER_CHIP]; +}; + +/* + * In-kernel state a VAS window. One per window. + */ +struct vas_window { + /* Fields common to send and receive windows */ + struct vas_instance *vinst; + int winid; + bool tx_win; /* True if send window */ + bool nx_win; /* True if NX window */ + bool user_win; /* True if user space window */ + void *hvwc_map; /* HV window context */ + void *uwc_map; /* OS/User window context */ + pid_t pid; /* Linux process id of owner */ + + /* Fields applicable only to send windows */ + void *paste_kaddr; + char *paste_addr_name; + struct vas_window *rxwin; + + /* Feilds applicable only to receive windows */ + enum vas_cop_type cop; + atomic_t num_txwins; +}; + +/* + * Container for the hardware state of a window. One per-window. + * + * A VAS Window context is a 512-byte area in the hardware that contains + * a set of 64-bit registers. Individual bit-fields in these registers + * determine the configuration/operation of the hardware. struct vas_winctx + * is a container for the register fields in the window context. + */ +struct vas_winctx { + void *rx_fifo; + int rx_fifo_size; + int wcreds_max; + int rsvd_txbuf_count; + + bool user_win; + bool nx_win; + bool fault_win; + bool rsvd_txbuf_enable; + bool pin_win; + bool rej_no_credit; + bool tx_wcred_mode; + bool rx_wcred_mode; + bool tx_word_mode; + bool rx_word_mode; + bool data_stamp; + bool xtra_write; + bool notify_disable; + bool intr_disable; + bool fifo_disable; + bool notify_early; + bool notify_os_intr_reg; + + int lpid; + int pidr; /* value from SPRN_PID, not linux pid */ + int lnotify_lpid; + int lnotify_pid; + int lnotify_tid; + u32 pswid; + int rx_win_id; + int fault_win_id; + int tc_mode; + + u64 irq_port; + + enum vas_dma_type dma_type; + enum vas_notify_scope min_scope; + enum vas_notify_scope max_scope; + enum vas_notify_after_count notify_after_count; +}; + +extern struct vas_instance *find_vas_instance(int vasid); + +/* + * VREG(x): + * Expand a register's short name (eg: LPID) into two parameters: + * - the register's short name in string form ("LPID"), and + * - the name of the macro (eg: VAS_LPID_OFFSET), defining the + * register's offset in the window context + */ +#define VREG_SFX(n, s) __stringify(n), VAS_##n##s +#define VREG(r) VREG_SFX(r, _OFFSET) + +#ifdef vas_debug +static inline void dump_rx_win_attr(struct vas_rx_win_attr *attr) +{ + pr_err("fault %d, notify %d, intr %d early %d\n", + attr->fault_win, attr->notify_disable, + attr->intr_disable, attr->notify_early); + + pr_err("rx_fifo_size %d, max value %d\n", + attr->rx_fifo_size, VAS_RX_FIFO_SIZE_MAX); +} + +static inline void vas_log_write(struct vas_window *win, char *name, + void *regptr, u64 val) +{ + if (val) + pr_err("%swin #%d: %s reg %p, val 0x%016llx\n", + win->tx_win ? "Tx" : "Rx", win->winid, name, + regptr, val); +} + +#else /* vas_debug */ + +#define vas_log_write(win, name, reg, val) +#define dump_rx_win_attr(attr) + +#endif /* vas_debug */ + +static inline void write_uwc_reg(struct vas_window *win, char *name, + s32 reg, u64 val) +{ + void *regptr; + + regptr = win->uwc_map + reg; + vas_log_write(win, name, regptr, val); + + out_be64(regptr, val); +} + +static inline void write_hvwc_reg(struct vas_window *win, char *name, + s32 reg, u64 val) +{ + void *regptr; + + regptr = win->hvwc_map + reg; + vas_log_write(win, name, regptr, val); + + out_be64(regptr, val); +} + +static inline u64 read_hvwc_reg(struct vas_window *win, + char *name __maybe_unused, s32 reg) +{ + return in_be64(win->hvwc_map+reg); +} + +#ifdef vas_debug + +static void print_fifo_msg_count(struct vas_window *txwin) +{ + uint64_t read_hvwc_reg(struct vas_window *w, char *n, uint64_t o); + pr_devel("Winid %d, Msg count %llu\n", txwin->winid, + (uint64_t)read_hvwc_reg(txwin, VREG(LRFIFO_PUSH))); +} +#else /* vas_debug */ + +#define print_fifo_msg_count(window) + +#endif /* vas_debug */ + +#endif /* _VAS_H */ diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c index 814a7eaa7769..50dbaf24b1ee 100644 --- a/arch/powerpc/platforms/ps3/repository.c +++ b/arch/powerpc/platforms/ps3/repository.c @@ -170,14 +170,8 @@ int ps3_repository_read_bus_str(unsigned int bus_index, const char *bus_str, int ps3_repository_read_bus_id(unsigned int bus_index, u64 *bus_id) { - int result; - - result = read_node(PS3_LPAR_ID_PME, - make_first_field("bus", bus_index), - make_field("id", 0), - 0, 0, - bus_id, NULL); - return result; + return read_node(PS3_LPAR_ID_PME, make_first_field("bus", bus_index), + make_field("id", 0), 0, 0, bus_id, NULL); } int ps3_repository_read_bus_type(unsigned int bus_index, @@ -224,15 +218,9 @@ int ps3_repository_read_dev_str(unsigned int bus_index, int ps3_repository_read_dev_id(unsigned int bus_index, unsigned int dev_index, u64 *dev_id) { - int result; - - result = read_node(PS3_LPAR_ID_PME, - make_first_field("bus", bus_index), - make_field("dev", dev_index), - make_field("id", 0), - 0, - dev_id, NULL); - return result; + return read_node(PS3_LPAR_ID_PME, make_first_field("bus", bus_index), + make_field("dev", dev_index), make_field("id", 0), 0, + dev_id, NULL); } int ps3_repository_read_dev_type(unsigned int bus_index, diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 6244bc849469..9dabea6e1443 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -104,20 +104,6 @@ static void __noreturn ps3_halt(void) ps3_sys_manager_halt(); /* never returns */ } -static void ps3_panic(char *str) -{ - DBG("%s:%d %s\n", __func__, __LINE__, str); - - smp_send_stop(); - printk("\n"); - printk(" System does not reboot automatically.\n"); - printk(" Please press POWER button.\n"); - printk("\n"); - - while(1) - lv1_pause(1); -} - #if defined(CONFIG_FB_PS3) || defined(CONFIG_FB_PS3_MODULE) || \ defined(CONFIG_PS3_FLASH) || defined(CONFIG_PS3_FLASH_MODULE) static void __init prealloc(struct ps3_prealloc *p) @@ -269,7 +255,6 @@ define_machine(ps3) { .probe = ps3_probe, .setup_arch = ps3_setup_arch, .init_IRQ = ps3_init_IRQ, - .panic = ps3_panic, .get_boot_time = ps3_get_boot_time, .set_dabr = ps3_set_dabr, .calibrate_decr = ps3_calibrate_decr, diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 3a6dfd14f64b..71dd69d9ec64 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -7,6 +7,7 @@ config PPC_PSERIES select PCI select PCI_MSI select PPC_XICS + select PPC_XIVE_SPAPR select PPC_ICP_NATIVE select PPC_ICP_HV select PPC_ICS_RTAS diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 39187696ee74..783f36364690 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -254,18 +254,15 @@ cc_error: return first_dn; } -int dlpar_attach_node(struct device_node *dn) +int dlpar_attach_node(struct device_node *dn, struct device_node *parent) { int rc; - dn->parent = pseries_of_derive_parent(dn->full_name); - if (IS_ERR(dn->parent)) - return PTR_ERR(dn->parent); + dn->parent = parent; rc = of_attach_node(dn); if (rc) { - printk(KERN_ERR "Failed to add device node %s\n", - dn->full_name); + printk(KERN_ERR "Failed to add device node %pOF\n", dn); return rc; } diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 1eef46d9cf30..6b812ad990e4 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -247,14 +247,13 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) /* Initialize the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); - pe.phb = edev->phb; + pe.phb = pdn->phb; pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); /* Enable EEH on the device */ ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (!ret) { /* Retrieve PE address */ - edev->config_addr = (pdn->busno << 16) | (pdn->devfn << 8); edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); pe.addr = edev->pe_config_addr; @@ -279,7 +278,6 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data) /* This device doesn't support EEH, but it may have an * EEH parent, in which case we mark it as supported. */ - edev->config_addr = pdn_to_eeh_dev(pdn->parent)->config_addr; edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; eeh_add_to_parent_pe(edev); } diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c index 32187dc76730..6eeb0d4bab61 100644 --- a/arch/powerpc/platforms/pseries/event_sources.c +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -36,8 +36,8 @@ void request_event_sources_irqs(struct device_node *np, virqs[count] = irq_create_of_mapping(&oirq); if (!virqs[count]) { pr_err("event-sources: Unable to allocate " - "interrupt number for %s\n", - np->full_name); + "interrupt number for %pOF\n", + np); WARN_ON(1); } else { count++; @@ -48,7 +48,7 @@ void request_event_sources_irqs(struct device_node *np, for (i = 0; i < count; i++) { if (request_irq(virqs[i], handler, 0, name, NULL)) { pr_err("event-sources: Unable to request interrupt " - "%d for %s\n", virqs[i], np->full_name); + "%d for %pOF\n", virqs[i], np); WARN_ON(1); return; } diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 6afd1efd3633..fc0d8f97c03a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -34,6 +34,7 @@ #include <asm/machdep.h> #include <asm/vdso_datapage.h> #include <asm/xics.h> +#include <asm/xive.h> #include <asm/plpar_wrappers.h> #include "pseries.h" @@ -109,7 +110,10 @@ static void pseries_mach_cpu_die(void) local_irq_disable(); idle_task_exit(); - xics_teardown_cpu(); + if (xive_enabled()) + xive_teardown_cpu(); + else + xics_teardown_cpu(); if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { set_cpu_current_state(cpu, CPU_STATE_INACTIVE); @@ -174,7 +178,10 @@ static int pseries_cpu_disable(void) boot_cpuid = cpumask_any(cpu_online_mask); /* FIXME: abstract this to not be platform specific later on */ - xics_migrate_irqs_away(); + if (xive_enabled()) + xive_smp_disable_cpu(); + else + xics_migrate_irqs_away(); return 0; } @@ -264,8 +271,8 @@ static int pseries_add_processor(struct device_node *np) /* If we get here, it most likely means that NR_CPUS is * less than the partition's max processors setting. */ - printk(KERN_ERR "Cannot add cpu %s; this system configuration" - " supports %d logical cpus.\n", np->full_name, + printk(KERN_ERR "Cannot add cpu %pOF; this system configuration" + " supports %d logical cpus.\n", np, num_possible_cpus()); goto out_unlock; } @@ -463,7 +470,7 @@ static ssize_t dlpar_cpu_add(u32 drc_index) return -EINVAL; } - rc = dlpar_attach_node(dn); + rc = dlpar_attach_node(dn, parent); if (rc) { saved_rc = rc; pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n", diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index ca9b2f4aaa22..1d48ab424bd9 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -336,7 +336,38 @@ static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) return mem_block; } +static int dlpar_change_lmb_state(struct of_drconf_cell *lmb, bool online) +{ + struct memory_block *mem_block; + int rc; + + mem_block = lmb_to_memblock(lmb); + if (!mem_block) + return -EINVAL; + + if (online && mem_block->dev.offline) + rc = device_online(&mem_block->dev); + else if (!online && !mem_block->dev.offline) + rc = device_offline(&mem_block->dev); + else + rc = 0; + + put_device(&mem_block->dev); + + return rc; +} + +static int dlpar_online_lmb(struct of_drconf_cell *lmb) +{ + return dlpar_change_lmb_state(lmb, true); +} + #ifdef CONFIG_MEMORY_HOTREMOVE +static int dlpar_offline_lmb(struct of_drconf_cell *lmb) +{ + return dlpar_change_lmb_state(lmb, false); +} + static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { unsigned long block_sz, start_pfn; @@ -431,19 +462,13 @@ static int dlpar_add_lmb(struct of_drconf_cell *); static int dlpar_remove_lmb(struct of_drconf_cell *lmb) { - struct memory_block *mem_block; unsigned long block_sz; int nid, rc; if (!lmb_is_removable(lmb)) return -EINVAL; - mem_block = lmb_to_memblock(lmb); - if (!mem_block) - return -EINVAL; - - rc = device_offline(&mem_block->dev); - put_device(&mem_block->dev); + rc = dlpar_offline_lmb(lmb); if (rc) return rc; @@ -737,20 +762,6 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index, } #endif /* CONFIG_MEMORY_HOTREMOVE */ -static int dlpar_online_lmb(struct of_drconf_cell *lmb) -{ - struct memory_block *mem_block; - int rc; - - mem_block = lmb_to_memblock(lmb); - if (!mem_block) - return -EINVAL; - - rc = device_online(&mem_block->dev); - put_device(&mem_block->dev); - return rc; -} - static int dlpar_add_lmb(struct of_drconf_cell *lmb) { unsigned long block_sz; @@ -817,6 +828,9 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop) return -EINVAL; for (i = 0; i < num_lmbs && lmbs_to_add != lmbs_added; i++) { + if (lmbs[i].flags & DRCONF_MEM_ASSIGNED) + continue; + rc = dlpar_acquire_drc(lmbs[i].drc_index); if (rc) continue; @@ -859,6 +873,7 @@ static int dlpar_memory_add_by_count(u32 lmbs_to_add, struct property *prop) lmbs[i].base_addr, lmbs[i].drc_index); lmbs[i].reserved = 0; } + rc = 0; } return rc; diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 74b5b8e239c8..c511a1743a44 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -23,7 +23,7 @@ .globl hcall_tracepoint_refcount hcall_tracepoint_refcount: - .llong 0 + .8byte 0 .section ".text" #endif diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index 52146b1356d2..408a86044133 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -150,8 +150,7 @@ static const struct dma_map_ops ibmebus_dma_ops = { static int ibmebus_match_path(struct device *dev, void *data) { struct device_node *dn = to_platform_device(dev)->dev.of_node; - return (dn->full_name && - (strcasecmp((char *)data, dn->full_name) == 0)); + return (of_find_node_by_path(data) == dn); } static int ibmebus_match_node(struct device *dev, void *data) @@ -395,7 +394,7 @@ static ssize_t devspec_show(struct device *dev, struct platform_device *ofdev; ofdev = to_platform_device(dev); - return sprintf(buf, "%s\n", ofdev->dev.of_node->full_name); + return sprintf(buf, "%pOF\n", ofdev->dev.of_node); } static DEVICE_ATTR_RO(devspec); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 8374adee27e3..7c181467d0ad 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -511,8 +511,8 @@ static void iommu_table_setparms(struct pci_controller *phb, basep = of_get_property(node, "linux,tce-base", NULL); sizep = of_get_property(node, "linux,tce-size", NULL); if (basep == NULL || sizep == NULL) { - printk(KERN_ERR "PCI_DMA: iommu_table_setparms: %s has " - "missing tce entries !\n", dn->full_name); + printk(KERN_ERR "PCI_DMA: iommu_table_setparms: %pOF has " + "missing tce entries !\n", dn); return; } @@ -587,7 +587,7 @@ static void pci_dma_bus_setup_pSeries(struct pci_bus *bus) dn = pci_bus_to_OF_node(bus); - pr_debug("pci_dma_bus_setup_pSeries: setting up bus %s\n", dn->full_name); + pr_debug("pci_dma_bus_setup_pSeries: setting up bus %pOF\n", dn); if (bus->self) { /* This is not a root bus, any setup will be done for the @@ -701,8 +701,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) dn = pci_bus_to_OF_node(bus); - pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %s\n", - dn->full_name); + pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", + dn); /* Find nearest ibm,dma-window, walking up the device tree */ for (pdn = dn; pdn != NULL; pdn = pdn->parent) { @@ -718,8 +718,8 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) ppci = PCI_DN(pdn); - pr_debug(" parent is %s, iommu_table: 0x%p\n", - pdn->full_name, ppci->table_group); + pr_debug(" parent is %pOF, iommu_table: 0x%p\n", + pdn, ppci->table_group); if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); @@ -817,28 +817,28 @@ static void remove_ddw(struct device_node *np, bool remove_prop) ret = tce_clearrange_multi_pSeriesLP(0, 1ULL << (be32_to_cpu(dwp->window_shift) - PAGE_SHIFT), dwp); if (ret) - pr_warning("%s failed to clear tces in window.\n", - np->full_name); + pr_warning("%pOF failed to clear tces in window.\n", + np); else - pr_debug("%s successfully cleared tces in window.\n", - np->full_name); + pr_debug("%pOF successfully cleared tces in window.\n", + np); ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); if (ret) - pr_warning("%s: failed to remove direct window: rtas returned " + pr_warning("%pOF: failed to remove direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[2], liobn); else - pr_debug("%s: successfully removed direct window: rtas returned " + pr_debug("%pOF: successfully removed direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np->full_name, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[2], liobn); delprop: if (remove_prop) ret = of_remove_property(np, win64); if (ret) - pr_warning("%s: failed to remove direct window property: %d\n", - np->full_name, ret); + pr_warning("%pOF: failed to remove direct window property: %d\n", + np, ret); } static u64 find_existing_ddw(struct device_node *pdn) @@ -1004,7 +1004,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * list. */ list_for_each_entry(fpdn, &failed_ddw_pdn_list, list) { - if (!strcmp(fpdn->pdn->full_name, pdn->full_name)) + if (fpdn->pdn == pdn) goto out_unlock; } @@ -1087,8 +1087,8 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) ddwprop->tce_shift = cpu_to_be32(page_shift); ddwprop->window_shift = cpu_to_be32(len); - dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %s\n", - create.liobn, dn->full_name); + dev_dbg(&dev->dev, "created tce table LIOBN 0x%x for %pOF\n", + create.liobn, dn); window = kzalloc(sizeof(*window), GFP_KERNEL); if (!window) @@ -1097,15 +1097,15 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) ret = walk_system_ram_range(0, memblock_end_of_DRAM() >> PAGE_SHIFT, win64->value, tce_setrange_multi_pSeriesLP_walk); if (ret) { - dev_info(&dev->dev, "failed to map direct window for %s: %d\n", - dn->full_name, ret); + dev_info(&dev->dev, "failed to map direct window for %pOF: %d\n", + dn, ret); goto out_free_window; } ret = of_add_property(pdn, win64); if (ret) { - dev_err(&dev->dev, "unable to add dma window property for %s: %d", - pdn->full_name, ret); + dev_err(&dev->dev, "unable to add dma window property for %pOF: %d", + pdn, ret); goto out_free_window; } @@ -1158,7 +1158,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) * already allocated. */ dn = pci_device_to_OF_node(dev); - pr_debug(" node is %s\n", dn->full_name); + pr_debug(" node is %pOF\n", dn); for (pdn = dn; pdn && PCI_DN(pdn) && !PCI_DN(pdn)->table_group; pdn = pdn->parent) { @@ -1169,11 +1169,11 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " - "no DMA window found for pci dev=%s dn=%s\n", - pci_name(dev), of_node_full_name(dn)); + "no DMA window found for pci dev=%s dn=%pOF\n", + pci_name(dev), dn); return; } - pr_debug(" parent is %s\n", pdn->full_name); + pr_debug(" parent is %pOF\n", pdn); pci = PCI_DN(pdn); if (!pci->table_group) { @@ -1213,7 +1213,7 @@ static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask) /* only attempt to use a new window if 64-bit DMA is requested */ if (!disable_ddw && dma_mask == DMA_BIT_MASK(64)) { dn = pci_device_to_OF_node(pdev); - dev_dbg(dev, "node is %s\n", dn->full_name); + dev_dbg(dev, "node is %pOF\n", dn); /* * the device tree might contain the dma-window properties diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c index 6681ac97fb18..eeb13429d685 100644 --- a/arch/powerpc/platforms/pseries/kexec.c +++ b/arch/powerpc/platforms/pseries/kexec.c @@ -15,6 +15,7 @@ #include <asm/firmware.h> #include <asm/kexec.h> #include <asm/xics.h> +#include <asm/xive.h> #include <asm/smp.h> #include <asm/plpar_wrappers.h> @@ -51,5 +52,8 @@ void pseries_kexec_cpu_down(int crash_shutdown, int secondary) } } - xics_kexec_teardown_cpu(secondary); + if (xive_enabled()) + xive_kexec_teardown_cpu(secondary); + else + xics_kexec_teardown_cpu(secondary); } diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 2da4851eff99..210ce632d63e 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -229,7 +229,7 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index) if (!dn) return -ENOENT; - rc = dlpar_attach_node(dn); + rc = dlpar_attach_node(dn, parent_dn); if (rc) dlpar_free_cc_nodes(dn); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 326ef0dd6038..b7496948129e 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -132,19 +132,14 @@ static void rtas_teardown_msi_irqs(struct pci_dev *pdev) static int check_req(struct pci_dev *pdev, int nvec, char *prop_name) { struct device_node *dn; - struct pci_dn *pdn; const __be32 *p; u32 req_msi; - pdn = pci_get_pdn(pdev); - if (!pdn) - return -ENODEV; - - dn = pdn->node; + dn = pci_device_to_OF_node(pdev); p = of_get_property(dn, prop_name, NULL); if (!p) { - pr_debug("rtas_msi: No %s on %s\n", prop_name, dn->full_name); + pr_debug("rtas_msi: No %s on %pOF\n", prop_name, dn); return -ENOENT; } @@ -182,8 +177,8 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) while (dn) { p = of_get_property(dn, "ibm,pe-total-#msi", NULL); if (p) { - pr_debug("rtas_msi: found prop on dn %s\n", - dn->full_name); + pr_debug("rtas_msi: found prop on dn %pOF\n", + dn); *total = be32_to_cpup(p); return dn; } @@ -197,7 +192,6 @@ static struct device_node *find_pe_total_msi(struct pci_dev *dev, int *total) static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) { struct device_node *dn; - struct pci_dn *pdn; struct eeh_dev *edev; /* Found our PE and assume 8 at that point. */ @@ -210,8 +204,7 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) edev = pdn_to_eeh_dev(PCI_DN(dn)); if (edev->pe) edev = list_first_entry(&edev->pe->edevs, struct eeh_dev, list); - pdn = eeh_dev_to_pdn(edev); - dn = pdn ? pdn->node : NULL; + dn = pci_device_to_OF_node(edev->pdev); if (!dn) return NULL; @@ -222,7 +215,7 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total) /* Hardcode of 8 for old firmwares */ *total = 8; - pr_debug("rtas_msi: using PE dn %s\n", dn->full_name); + pr_debug("rtas_msi: using PE dn %pOF\n", dn); return dn; } @@ -242,7 +235,7 @@ static void *count_non_bridge_devices(struct device_node *dn, void *data) const __be32 *p; u32 class; - pr_debug("rtas_msi: counting %s\n", dn->full_name); + pr_debug("rtas_msi: counting %pOF\n", dn); p = of_get_property(dn, "class-code", NULL); class = p ? be32_to_cpup(p) : 0; @@ -300,7 +293,7 @@ static int msi_quota_for_device(struct pci_dev *dev, int request) goto out; } - pr_debug("rtas_msi: found PE %s\n", pe_dn->full_name); + pr_debug("rtas_msi: found PE %pOF\n", pe_dn); memset(&counts, 0, sizeof(struct msi_counts)); diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 547fd13e4f8e..561917fa54a8 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -38,7 +38,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) { struct pci_controller *phb; - pr_debug("PCI: Initializing new hotplug PHB %s\n", dn->full_name); + pr_debug("PCI: Initializing new hotplug PHB %pOF\n", dn); phb = pcibios_alloc_controller(dn); if (!phb) diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 1361a9db534b..4470a3194311 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -46,7 +46,7 @@ extern void dlpar_free_cc_nodes(struct device_node *); extern void dlpar_free_cc_property(struct property *); extern struct device_node *dlpar_configure_connector(__be32, struct device_node *); -extern int dlpar_attach_node(struct device_node *); +extern int dlpar_attach_node(struct device_node *, struct device_node *); extern int dlpar_detach_node(struct device_node *); extern int dlpar_acquire_drc(u32 drc_index); extern int dlpar_release_drc(u32 drc_index); diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c index 164a13d3998a..35c891aabef0 100644 --- a/arch/powerpc/platforms/pseries/pseries_energy.c +++ b/arch/powerpc/platforms/pseries/pseries_energy.c @@ -229,10 +229,9 @@ static int __init pseries_energy_init(void) int cpu, err; struct device *cpu_dev; - if (!firmware_has_feature(FW_FEATURE_BEST_ENERGY)) { - printk(KERN_INFO "Hypercall H_BEST_ENERGY not supported\n"); - return 0; - } + if (!firmware_has_feature(FW_FEATURE_BEST_ENERGY)) + return 0; /* H_BEST_ENERGY hcall not supported */ + /* Create the sysfs files */ err = device_create_file(cpu_subsys.dev_root, &attr_cpu_activate_hint_list); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index bb70b26334f0..4923ffe230cf 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -379,6 +379,21 @@ static void fwnmi_release_errinfo(void) int pSeries_system_reset_exception(struct pt_regs *regs) { +#ifdef __LITTLE_ENDIAN__ + /* + * Some firmware byteswaps SRR registers and gives incorrect SRR1. Try + * to detect the bad SRR1 pattern here. Flip the NIP back to correct + * endian for reporting purposes. Unfortunately the MSR can't be fixed, + * so clear it. It will be missing MSR_RI so we won't try to recover. + */ + if ((be64_to_cpu(regs->msr) & + (MSR_LE|MSR_RI|MSR_DR|MSR_IR|MSR_ME|MSR_PR| + MSR_ILE|MSR_HV|MSR_SF)) == (MSR_DR|MSR_SF)) { + regs->nip = be64_to_cpu((__be64)regs->nip); + regs->msr = 0; + } +#endif + if (fwnmi_active) { struct rtas_error_log *errhdr = fwnmi_get_errinfo(regs); if (errhdr) { diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 011ef2180fe6..296c188fd5ca 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -362,20 +362,13 @@ static int do_update_property(char *buf, size_t bufsize) static ssize_t ofdt_write(struct file *file, const char __user *buf, size_t count, loff_t *off) { - int rv = 0; + int rv; char *kbuf; char *tmp; - if (!(kbuf = kmalloc(count + 1, GFP_KERNEL))) { - rv = -ENOMEM; - goto out; - } - if (copy_from_user(kbuf, buf, count)) { - rv = -EFAULT; - goto out; - } - - kbuf[count] = '\0'; + kbuf = memdup_user_nul(buf, count); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); tmp = strchr(kbuf, ' '); if (!tmp) { diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index b5d86426e97b..5f1beb8367ac 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -57,6 +57,7 @@ #include <asm/nvram.h> #include <asm/pmc.h> #include <asm/xics.h> +#include <asm/xive.h> #include <asm/ppc-pci.h> #include <asm/i8259.h> #include <asm/udbg.h> @@ -176,8 +177,11 @@ static void __init pseries_setup_i8259_cascade(void) static void __init pseries_init_irq(void) { - xics_init(); - pseries_setup_i8259_cascade(); + /* Try using a XIVE if available, otherwise use a XICS */ + if (!xive_spapr_init()) { + xics_init(); + pseries_setup_i8259_cascade(); + } } static void pseries_lpar_enable_pmcs(void) @@ -722,7 +726,6 @@ define_machine(pseries) { .pcibios_fixup = pSeries_final_fixup, .restart = rtas_restart, .halt = rtas_halt, - .panic = rtas_os_term, .get_boot_time = rtas_get_boot_time, .get_rtc_time = rtas_get_rtc_time, .set_rtc_time = rtas_set_rtc_time, diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 24785f63fb40..2e184829e5d4 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -41,6 +41,7 @@ #include <asm/vdso_datapage.h> #include <asm/cputhreads.h> #include <asm/xics.h> +#include <asm/xive.h> #include <asm/dbell.h> #include <asm/plpar_wrappers.h> #include <asm/code-patching.h> @@ -136,7 +137,9 @@ out: static void smp_setup_cpu(int cpu) { - if (cpu != boot_cpuid) + if (xive_enabled()) + xive_smp_setup_cpu(); + else if (cpu != boot_cpuid) xics_setup_cpu(); if (firmware_has_feature(FW_FEATURE_SPLPAR)) @@ -181,6 +184,13 @@ static int smp_pSeries_kick_cpu(int nr) return 0; } +static int pseries_smp_prepare_cpu(int cpu) +{ + if (xive_enabled()) + return xive_smp_prepare_cpu(cpu); + return 0; +} + static void smp_pseries_cause_ipi(int cpu) { /* POWER9 should not use this handler */ @@ -211,7 +221,7 @@ static int pseries_cause_nmi_ipi(int cpu) return 0; } -static __init void pSeries_smp_probe(void) +static __init void pSeries_smp_probe_xics(void) { xics_smp_probe(); @@ -221,11 +231,24 @@ static __init void pSeries_smp_probe(void) smp_ops->cause_ipi = icp_ops->cause_ipi; } +static __init void pSeries_smp_probe(void) +{ + if (xive_enabled()) + /* + * Don't use P9 doorbells when XIVE is enabled. IPIs + * using MMIOs should be faster + */ + xive_smp_probe(); + else + pSeries_smp_probe_xics(); +} + static struct smp_ops_t pseries_smp_ops = { .message_pass = NULL, /* Use smp_muxed_ipi_message_pass */ .cause_ipi = NULL, /* Filled at runtime by pSeries_smp_probe() */ .cause_nmi_ipi = pseries_cause_nmi_ipi, .probe = pSeries_smp_probe, + .prepare_cpu = pseries_smp_prepare_cpu, .kick_cpu = smp_pSeries_kick_cpu, .setup_cpu = smp_setup_cpu, .cpu_bootable = smp_generic_cpu_bootable, diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 8a47f168476b..12277bc9fd9e 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1357,14 +1357,14 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) */ parent_node = of_get_parent(of_node); if (parent_node) { - if (!strcmp(parent_node->full_name, "/ibm,platform-facilities")) + if (!strcmp(parent_node->type, "ibm,platform-facilities")) family = PFO; - else if (!strcmp(parent_node->full_name, "/vdevice")) + else if (!strcmp(parent_node->type, "vdevice")) family = VDEVICE; else { - pr_warn("%s: parent(%s) of %s not recognized.\n", + pr_warn("%s: parent(%pOF) of %s not recognized.\n", __func__, - parent_node->full_name, + parent_node, of_node_name); of_node_put(parent_node); return NULL; @@ -1555,7 +1555,7 @@ static ssize_t devspec_show(struct device *dev, { struct device_node *of_node = dev->of_node; - return sprintf(buf, "%s\n", of_node_full_name(of_node)); + return sprintf(buf, "%pOF\n", of_node); } static DEVICE_ATTR_RO(devspec); diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline.S index 3696ea6c4826..4aad9dd10ace 100644 --- a/arch/powerpc/purgatory/trampoline.S +++ b/arch/powerpc/purgatory/trampoline.S @@ -67,7 +67,7 @@ master: mr %r16,%r3 /* save dt address in reg16 */ li %r4,20 LWZX_BE %r6,%r3,%r4 /* fetch __be32 version number at byte 20 */ - cmpwi %r0,%r6,2 /* v2 or later? */ + cmpwi %cr0,%r6,2 /* v2 or later? */ blt 1f li %r4,28 STWX_BE %r17,%r3,%r4 /* Store my cpu as __be32 at byte 28 */ @@ -104,13 +104,13 @@ master: .balign 8 .globl kernel kernel: - .llong 0x0 + .8byte 0x0 .size kernel, . - kernel .balign 8 .globl dt_offset dt_offset: - .llong 0x0 + .8byte 0x0 .size dt_offset, . - dt_offset diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index c0ae11d4f62f..79416fa2e3ba 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -36,25 +36,15 @@ obj-$(CONFIG_AXON_RAM) += axonram.o obj-$(CONFIG_PPC_INDIRECT_PCI) += indirect_pci.o obj-$(CONFIG_PPC_I8259) += i8259.o obj-$(CONFIG_IPIC) += ipic.o -obj-$(CONFIG_4xx) += uic.o -obj-$(CONFIG_PPC4xx_OCM) += ppc4xx_ocm.o -obj-$(CONFIG_4xx_SOC) += ppc4xx_soc.o obj-$(CONFIG_XILINX_VIRTEX) += xilinx_intc.o obj-$(CONFIG_XILINX_PCI) += xilinx_pci.o obj-$(CONFIG_OF_RTC) += of_rtc.o -ifeq ($(CONFIG_PCI),y) -obj-$(CONFIG_4xx) += ppc4xx_pci.o -endif -obj-$(CONFIG_PPC4xx_HSTA_MSI) += ppc4xx_hsta_msi.o -obj-$(CONFIG_PPC4xx_MSI) += ppc4xx_msi.o -obj-$(CONFIG_PPC4xx_CPM) += ppc4xx_cpm.o -obj-$(CONFIG_PPC4xx_GPIO) += ppc4xx_gpio.o obj-$(CONFIG_CPM) += cpm_common.o +obj-$(CONFIG_CPM1) += cpm1.o obj-$(CONFIG_CPM2) += cpm2.o cpm2_pic.o obj-$(CONFIG_QUICC_ENGINE) += cpm_common.o obj-$(CONFIG_PPC_DCR) += dcr.o -obj-$(CONFIG_8xx) += mpc8xx_pic.o cpm1.o obj-$(CONFIG_UCODE_PATCH) += micropatch.o obj-$(CONFIG_PPC_MPC512x) += mpc5xxx_clocks.o diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 1e15deacccaf..c60e84e4558d 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -188,15 +188,12 @@ static int axon_ram_probe(struct platform_device *device) axon_ram_bank_id++; - dev_info(&device->dev, "Found memory controller on %s\n", - device->dev.of_node->full_name); + dev_info(&device->dev, "Found memory controller on %pOF\n", + device->dev.of_node); - bank = kzalloc(sizeof(struct axon_ram_bank), GFP_KERNEL); - if (bank == NULL) { - dev_err(&device->dev, "Out of memory\n"); - rc = -ENOMEM; - goto failed; - } + bank = kzalloc(sizeof(*bank), GFP_KERNEL); + if (!bank) + return -ENOMEM; device->dev.platform_data = bank; @@ -292,25 +289,22 @@ static int axon_ram_probe(struct platform_device *device) return 0; failed: - if (bank != NULL) { - if (bank->irq_id) - free_irq(bank->irq_id, device); - if (bank->disk != NULL) { - if (bank->disk->major > 0) - unregister_blkdev(bank->disk->major, - bank->disk->disk_name); - if (bank->disk->flags & GENHD_FL_UP) - del_gendisk(bank->disk); - put_disk(bank->disk); - } - kill_dax(bank->dax_dev); - put_dax(bank->dax_dev); - device->dev.platform_data = NULL; - if (bank->io_addr != 0) - iounmap((void __iomem *) bank->io_addr); - kfree(bank); + if (bank->irq_id) + free_irq(bank->irq_id, device); + if (bank->disk != NULL) { + if (bank->disk->major > 0) + unregister_blkdev(bank->disk->major, + bank->disk->disk_name); + if (bank->disk->flags & GENHD_FL_UP) + del_gendisk(bank->disk); + put_disk(bank->disk); } - + kill_dax(bank->dax_dev); + put_dax(bank->dax_dev); + device->dev.platform_data = NULL; + if (bank->io_addr != 0) + iounmap((void __iomem *) bank->io_addr); + kfree(bank); return rc; } diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c index 121e26fffd50..d72eda568b7d 100644 --- a/arch/powerpc/sysdev/dcr.c +++ b/arch/powerpc/sysdev/dcr.c @@ -195,8 +195,8 @@ dcr_host_mmio_t dcr_map_mmio(struct device_node *dev, dcr_host_mmio_t ret = { .token = NULL, .stride = 0, .base = dcr_n }; u64 addr; - pr_debug("dcr_map(%s, 0x%x, 0x%x)\n", - dev->full_name, dcr_n, dcr_c); + pr_debug("dcr_map(%pOF, 0x%x, 0x%x)\n", + dev, dcr_n, dcr_c); addr = of_translate_dcr_address(dev, dcr_n, &ret.stride); pr_debug("translates to addr: 0x%llx, stride: 0x%x\n", diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c index 37a69097e022..00ccf3e4fcb4 100644 --- a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c +++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c @@ -101,8 +101,8 @@ int __init instantiate_cache_sram(struct platform_device *dev, if (!request_mem_region(cache_sram->base_phys, cache_sram->size, "fsl_85xx_cache_sram")) { - dev_err(&dev->dev, "%s: request memory failed\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "%pOF: request memory failed\n", + dev->dev.of_node); ret = -ENXIO; goto out_free; } @@ -110,16 +110,16 @@ int __init instantiate_cache_sram(struct platform_device *dev, cache_sram->base_virt = ioremap_prot(cache_sram->base_phys, cache_sram->size, _PAGE_COHERENT | PAGE_KERNEL); if (!cache_sram->base_virt) { - dev_err(&dev->dev, "%s: ioremap_prot failed\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "%pOF: ioremap_prot failed\n", + dev->dev.of_node); ret = -ENOMEM; goto out_release; } cache_sram->rh = rh_create(sizeof(unsigned int)); if (IS_ERR(cache_sram->rh)) { - dev_err(&dev->dev, "%s: Unable to create remote heap\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "%pOF: Unable to create remote heap\n", + dev->dev.of_node); ret = PTR_ERR(cache_sram->rh); goto out_unmap; } diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c index a6f0b96ce2c9..d902306f4718 100644 --- a/arch/powerpc/sysdev/fsl_gtm.c +++ b/arch/powerpc/sysdev/fsl_gtm.c @@ -388,8 +388,8 @@ static int __init fsl_gtm_init(void) gtm = kzalloc(sizeof(*gtm), GFP_KERNEL); if (!gtm) { - pr_err("%s: unable to allocate memory\n", - np->full_name); + pr_err("%pOF: unable to allocate memory\n", + np); continue; } @@ -397,7 +397,7 @@ static int __init fsl_gtm_init(void) clock = of_get_property(np, "clock-frequency", &size); if (!clock || size != sizeof(*clock)) { - pr_err("%s: no clock-frequency\n", np->full_name); + pr_err("%pOF: no clock-frequency\n", np); goto err; } gtm->clock = *clock; @@ -407,8 +407,8 @@ static int __init fsl_gtm_init(void) irq = irq_of_parse_and_map(np, i); if (!irq) { - pr_err("%s: not enough interrupts specified\n", - np->full_name); + pr_err("%pOF: not enough interrupts specified\n", + np); goto err; } gtm->timers[i].irq = irq; @@ -417,8 +417,8 @@ static int __init fsl_gtm_init(void) gtm->regs = of_iomap(np, 0); if (!gtm->regs) { - pr_err("%s: unable to iomap registers\n", - np->full_name); + pr_err("%pOF: unable to iomap registers\n", + np); goto err; } diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 8a244828782e..44cbf4c12ea1 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -214,8 +214,8 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) phandle = np->phandle; else { dev_err(&pdev->dev, - "node %s has an invalid fsl,msi phandle %u\n", - hose->dn->full_name, np->phandle); + "node %pOF has an invalid fsl,msi phandle %u\n", + hose->dn, np->phandle); return -EINVAL; } } @@ -438,16 +438,16 @@ static int fsl_of_msi_probe(struct platform_device *dev) if ((features->fsl_pic_ip & FSL_PIC_IP_MASK) != FSL_PIC_IP_VMPIC) { err = of_address_to_resource(dev->dev.of_node, 0, &res); if (err) { - dev_err(&dev->dev, "invalid resource for node %s\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "invalid resource for node %pOF\n", + dev->dev.of_node); goto error_out; } msi->msi_regs = ioremap(res.start, resource_size(&res)); if (!msi->msi_regs) { err = -ENOMEM; - dev_err(&dev->dev, "could not map node %s\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "could not map node %pOF\n", + dev->dev.of_node); goto error_out; } msi->msiir_offset = @@ -522,8 +522,8 @@ static int fsl_of_msi_probe(struct platform_device *dev) for (irq_index = 0, i = 0; i < len / (2 * sizeof(u32)); i++) { if (p[i * 2] % IRQS_PER_MSI_REG || p[i * 2 + 1] % IRQS_PER_MSI_REG) { - pr_warn("%s: %s: msi available range of %u at %u is not IRQ-aligned\n", - __func__, dev->dev.of_node->full_name, + pr_warn("%s: %pOF: msi available range of %u at %u is not IRQ-aligned\n", + __func__, dev->dev.of_node, p[i * 2 + 1], p[i * 2]); err = -EINVAL; goto error_out; diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index d3a597456b6e..22d98057f773 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -202,7 +202,6 @@ static void setup_pci_atmu(struct pci_controller *hose) u32 pcicsrbar = 0, pcicsrbar_sz; u32 piwar = PIWAR_EN | PIWAR_PF | PIWAR_TGI_LOCAL | PIWAR_READ_SNOOP | PIWAR_WRITE_SNOOP; - const char *name = hose->dn->full_name; const u64 *reg; int len; bool setup_inbound; @@ -290,12 +289,12 @@ static void setup_pci_atmu(struct pci_controller *hose) paddr_lo -= offset; if (paddr_hi == paddr_lo) { - pr_err("%s: No outbound window space\n", name); + pr_err("%pOF: No outbound window space\n", hose->dn); return; } if (paddr_lo == 0) { - pr_err("%s: No space for inbound window\n", name); + pr_err("%pOF: No space for inbound window\n", hose->dn); return; } @@ -313,7 +312,7 @@ static void setup_pci_atmu(struct pci_controller *hose) paddr_lo = min(paddr_lo, (u64)pcicsrbar); - pr_info("%s: PCICSRBAR @ 0x%x\n", name, pcicsrbar); + pr_info("%pOF: PCICSRBAR @ 0x%x\n", hose->dn, pcicsrbar); /* Setup inbound mem window */ mem = memblock_end_of_DRAM(); @@ -336,12 +335,12 @@ static void setup_pci_atmu(struct pci_controller *hose) u64 address = be64_to_cpup(reg); if ((address >= mem) && (address < (mem + PAGE_SIZE))) { - pr_info("%s: extending DDR ATMU to cover MSIIR", name); + pr_info("%pOF: extending DDR ATMU to cover MSIIR", hose->dn); mem += PAGE_SIZE; } else { /* TODO: Create a new ATMU for MSIIR */ - pr_warn("%s: msi-address-64 address of %llx is " - "unsupported\n", name, address); + pr_warn("%pOF: msi-address-64 address of %llx is " + "unsupported\n", hose->dn, address); } } @@ -354,8 +353,8 @@ static void setup_pci_atmu(struct pci_controller *hose) if ((1ull << mem_log) != mem) { mem_log++; if ((1ull << mem_log) > mem) - pr_info("%s: Setting PCI inbound window " - "greater than memory size\n", name); + pr_info("%pOF: Setting PCI inbound window " + "greater than memory size\n", hose->dn); } piwar |= ((mem_log - 1) & PIWAR_SZ_MASK); @@ -402,7 +401,7 @@ static void setup_pci_atmu(struct pci_controller *hose) */ ppc_md.dma_set_mask = fsl_pci_dma_set_mask; - pr_info("%s: Setup 64-bit PCI DMA window\n", name); + pr_info("%pOF: Setup 64-bit PCI DMA window\n", hose->dn); } } else { u64 paddr = 0; @@ -443,18 +442,18 @@ static void setup_pci_atmu(struct pci_controller *hose) #ifdef CONFIG_SWIOTLB ppc_swiotlb_enable = 1; #else - pr_err("%s: ERROR: Memory size exceeds PCI ATMU ability to " + pr_err("%pOF: ERROR: Memory size exceeds PCI ATMU ability to " "map - enable CONFIG_SWIOTLB to avoid dma errors.\n", - name); + hose->dn); #endif /* adjusting outbound windows could reclaim space in mem map */ if (paddr_hi < 0xffffffffull) - pr_warning("%s: WARNING: Outbound window cfg leaves " + pr_warning("%pOF: WARNING: Outbound window cfg leaves " "gaps in memory map. Adjusting the memory map " "could reduce unnecessary bounce buffering.\n", - name); + hose->dn); - pr_info("%s: DMA window size is 0x%llx\n", name, + pr_info("%pOF: DMA window size is 0x%llx\n", hose->dn, (u64)hose->dma_window_size); } } @@ -532,11 +531,11 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary) dev = pdev->dev.of_node; if (!of_device_is_available(dev)) { - pr_warning("%s: disabled\n", dev->full_name); + pr_warning("%pOF: disabled\n", dev); return -ENODEV; } - pr_debug("Adding PCI host bridge %s\n", dev->full_name); + pr_debug("Adding PCI host bridge %pOF\n", dev); /* Fetch host bridge registers address */ if (of_address_to_resource(dev, 0, &rsrc)) { @@ -547,8 +546,8 @@ int fsl_add_bridge(struct platform_device *pdev, int is_primary) /* Get bus range if any */ bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); pci_add_flags(PCI_REASSIGN_ALL_BUS); hose = pcibios_alloc_controller(dev); @@ -809,11 +808,11 @@ int __init mpc83xx_add_bridge(struct device_node *dev) is_mpc83xx_pci = 1; if (!of_device_is_available(dev)) { - pr_warning("%s: disabled by the firmware.\n", - dev->full_name); + pr_warning("%pOF: disabled by the firmware.\n", + dev); return -ENODEV; } - pr_debug("Adding PCI host bridge %s\n", dev->full_name); + pr_debug("Adding PCI host bridge %pOF\n", dev); /* Fetch host bridge registers address */ if (of_address_to_resource(dev, 0, &rsrc_reg)) { @@ -848,8 +847,8 @@ int __init mpc83xx_add_bridge(struct device_node *dev) /* Get bus range if any */ bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); } pci_add_flags(PCI_REASSIGN_ALL_BUS); diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 1c41c51f22cb..9234be1e66f5 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -450,12 +450,12 @@ int fsl_rio_setup(struct platform_device *dev) rc = of_address_to_resource(dev->dev.of_node, 0, ®s); if (rc) { - dev_err(&dev->dev, "Can't get %s property 'reg'\n", - dev->dev.of_node->full_name); + dev_err(&dev->dev, "Can't get %pOF property 'reg'\n", + dev->dev.of_node); return -EFAULT; } - dev_info(&dev->dev, "Of-device full name %s\n", - dev->dev.of_node->full_name); + dev_info(&dev->dev, "Of-device full name %pOF\n", + dev->dev.of_node); dev_info(&dev->dev, "Regs: %pR\n", ®s); rio_regs_win = ioremap(regs.start, resource_size(®s)); @@ -494,8 +494,8 @@ int fsl_rio_setup(struct platform_device *dev) } rc = of_address_to_resource(rmu_node, 0, &rmu_regs); if (rc) { - dev_err(&dev->dev, "Can't get %s property 'reg'\n", - rmu_node->full_name); + dev_err(&dev->dev, "Can't get %pOF property 'reg'\n", + rmu_node); goto err_rmu; } rmu_regs_win = ioremap(rmu_regs.start, resource_size(&rmu_regs)); @@ -529,8 +529,8 @@ int fsl_rio_setup(struct platform_device *dev) aw = of_n_addr_cells(np); dt_range = of_get_property(np, "reg", &rlen); if (!dt_range) { - pr_err("%s: unable to find 'reg' property\n", - np->full_name); + pr_err("%pOF: unable to find 'reg' property\n", + np); rc = -ENOMEM; goto err_pw; } @@ -557,8 +557,8 @@ int fsl_rio_setup(struct platform_device *dev) aw = of_n_addr_cells(np); dt_range = of_get_property(np, "reg", &rlen); if (!dt_range) { - pr_err("%s: unable to find 'reg' property\n", - np->full_name); + pr_err("%pOF: unable to find 'reg' property\n", + np); rc = -ENOMEM; goto err; } @@ -569,15 +569,15 @@ int fsl_rio_setup(struct platform_device *dev) for_each_child_of_node(dev->dev.of_node, np) { port_index = of_get_property(np, "cell-index", NULL); if (!port_index) { - dev_err(&dev->dev, "Can't get %s property 'cell-index'\n", - np->full_name); + dev_err(&dev->dev, "Can't get %pOF property 'cell-index'\n", + np); continue; } dt_range = of_get_property(np, "ranges", &rlen); if (!dt_range) { - dev_err(&dev->dev, "Can't get %s property 'ranges'\n", - np->full_name); + dev_err(&dev->dev, "Can't get %pOF property 'ranges'\n", + np); continue; } @@ -598,8 +598,8 @@ int fsl_rio_setup(struct platform_device *dev) range_start = of_read_number(dt_range + aw, paw); range_size = of_read_number(dt_range + aw + paw, sw); - dev_info(&dev->dev, "%s: LAW start 0x%016llx, size 0x%016llx.\n", - np->full_name, range_start, range_size); + dev_info(&dev->dev, "%pOF: LAW start 0x%016llx, size 0x%016llx.\n", + np, range_start, range_size); port = kzalloc(sizeof(struct rio_mport), GFP_KERNEL); if (!port) @@ -757,8 +757,8 @@ err_rio_regs: */ static int fsl_of_rio_rpn_probe(struct platform_device *dev) { - printk(KERN_INFO "Setting up RapidIO peer-to-peer network %s\n", - dev->dev.of_node->full_name); + printk(KERN_INFO "Setting up RapidIO peer-to-peer network %pOF\n", + dev->dev.of_node); return fsl_rio_setup(dev); }; diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c index c1826de4e749..ab7a74c75be8 100644 --- a/arch/powerpc/sysdev/fsl_rmu.c +++ b/arch/powerpc/sysdev/fsl_rmu.c @@ -1074,8 +1074,8 @@ int fsl_rio_setup_rmu(struct rio_mport *mport, struct device_node *node) priv = mport->priv; if (!node) { - dev_warn(priv->dev, "Can't get %s property 'fsl,rmu'\n", - priv->dev->of_node->full_name); + dev_warn(priv->dev, "Can't get %pOF property 'fsl,rmu'\n", + priv->dev->of_node); return -EINVAL; } @@ -1086,8 +1086,8 @@ int fsl_rio_setup_rmu(struct rio_mport *mport, struct device_node *node) aw = of_n_addr_cells(node); msg_addr = of_get_property(node, "reg", &mlen); if (!msg_addr) { - pr_err("%s: unable to find 'reg' property of message-unit\n", - node->full_name); + pr_err("%pOF: unable to find 'reg' property of message-unit\n", + node); kfree(rmu); return -ENOMEM; } @@ -1098,8 +1098,8 @@ int fsl_rio_setup_rmu(struct rio_mport *mport, struct device_node *node) rmu->txirq = irq_of_parse_and_map(node, 0); rmu->rxirq = irq_of_parse_and_map(node, 1); - printk(KERN_INFO "%s: txirq: %d, rxirq %d\n", - node->full_name, rmu->txirq, rmu->rxirq); + printk(KERN_INFO "%pOF: txirq: %d, rxirq %d\n", + node, rmu->txirq, rmu->rxirq); priv->rmm_handle = rmu; diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index 19101f9cfcfc..1f614fb2be56 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -98,7 +98,7 @@ u32 fsl_get_sys_freq(void) } EXPORT_SYMBOL(fsl_get_sys_freq); -#if defined(CONFIG_CPM2) || defined(CONFIG_QUICC_ENGINE) || defined(CONFIG_8xx) +#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) u32 get_brgfreq(void) { diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h index d73daa4f0ccf..2640446f8bc4 100644 --- a/arch/powerpc/sysdev/fsl_soc.h +++ b/arch/powerpc/sysdev/fsl_soc.h @@ -7,7 +7,7 @@ struct spi_device; extern phys_addr_t get_immrbase(void); -#if defined(CONFIG_CPM2) || defined(CONFIG_QUICC_ENGINE) || defined(CONFIG_8xx) +#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) extern u32 get_brgfreq(void); extern u32 get_baudrate(void); #else diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c index f267ee0afc08..16f1edd78c40 100644 --- a/arch/powerpc/sysdev/ipic.c +++ b/arch/powerpc/sysdev/ipic.c @@ -315,6 +315,7 @@ static struct ipic_info ipic_info[] = { .prio_mask = 7, }, [48] = { + .ack = IPIC_SEPNR, .mask = IPIC_SEMSR, .prio = IPIC_SMPRR_A, .force = IPIC_SEFCR, diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index b9aac951a90f..ead3e2549ebf 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1650,8 +1650,8 @@ void __init mpic_init(struct mpic *mpic) if (mpic->flags & MPIC_SECONDARY) { int virq = irq_of_parse_and_map(mpic->node, 0); if (virq) { - printk(KERN_INFO "%s: hooking up to IRQ %d\n", - mpic->node->full_name, virq); + printk(KERN_INFO "%pOF: hooking up to IRQ %d\n", + mpic->node, virq); irq_set_handler_data(virq, mpic); irq_set_chained_handler(virq, &mpic_cascade); } diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index db2286be5d9a..eb69a5186243 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -192,7 +192,7 @@ static int mpic_msgr_probe(struct platform_device *dev) return -ENOMEM; } } - dev_info(&dev->dev, "Of-device full name %s\n", np->full_name); + dev_info(&dev->dev, "Of-device full name %pOF\n", np); /* IO map the message register block. */ of_address_to_resource(np, 0, &rsrc); diff --git a/arch/powerpc/sysdev/mpic_msi.c b/arch/powerpc/sysdev/mpic_msi.c index 1d48a5385905..9ed860aee9c3 100644 --- a/arch/powerpc/sysdev/mpic_msi.c +++ b/arch/powerpc/sysdev/mpic_msi.c @@ -60,7 +60,7 @@ static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic) np = NULL; while ((np = of_find_all_nodes(np))) { - pr_debug("mpic: mapping hwirqs for %s\n", np->full_name); + pr_debug("mpic: mapping hwirqs for %pOF\n", np); index = 0; while (of_irq_parse_one(np, index++, &oirq) == 0) { diff --git a/arch/powerpc/sysdev/mpic_timer.c b/arch/powerpc/sysdev/mpic_timer.c index 9d9b06217f8b..a418579591be 100644 --- a/arch/powerpc/sysdev/mpic_timer.c +++ b/arch/powerpc/sysdev/mpic_timer.c @@ -466,8 +466,7 @@ static int timer_group_get_irq(struct device_node *np, p = of_get_property(np, "fsl,available-ranges", &len); if (p && len % (2 * sizeof(u32)) != 0) { - pr_err("%s: malformed available-ranges property.\n", - np->full_name); + pr_err("%pOF: malformed available-ranges property.\n", np); return -EINVAL; } @@ -484,8 +483,7 @@ static int timer_group_get_irq(struct device_node *np, for (j = 0; j < count; j++) { irq = irq_of_parse_and_map(np, irq_index); if (!irq) { - pr_err("%s: irq parse and map failed.\n", - np->full_name); + pr_err("%pOF: irq parse and map failed.\n", np); return -EINVAL; } @@ -508,8 +506,7 @@ static void timer_group_init(struct device_node *np) priv = kzalloc(sizeof(struct timer_group_priv), GFP_KERNEL); if (!priv) { - pr_err("%s: cannot allocate memory for group.\n", - np->full_name); + pr_err("%pOF: cannot allocate memory for group.\n", np); return; } @@ -518,29 +515,27 @@ static void timer_group_init(struct device_node *np) priv->regs = of_iomap(np, i++); if (!priv->regs) { - pr_err("%s: cannot ioremap timer register address.\n", - np->full_name); + pr_err("%pOF: cannot ioremap timer register address.\n", np); goto out; } if (priv->flags & FSL_GLOBAL_TIMER) { priv->group_tcr = of_iomap(np, i++); if (!priv->group_tcr) { - pr_err("%s: cannot ioremap tcr address.\n", - np->full_name); + pr_err("%pOF: cannot ioremap tcr address.\n", np); goto out; } } ret = timer_group_get_freq(np, priv); if (ret < 0) { - pr_err("%s: cannot get timer frequency.\n", np->full_name); + pr_err("%pOF: cannot get timer frequency.\n", np); goto out; } ret = timer_group_get_irq(np, priv); if (ret < 0) { - pr_err("%s: cannot get timer irqs.\n", np->full_name); + pr_err("%pOF: cannot get timer irqs.\n", np); goto out; } diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 5ebd3f018295..c4dae27172b3 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -86,13 +86,13 @@ int msi_bitmap_reserve_dt_hwirqs(struct msi_bitmap *bmp) p = of_get_property(bmp->of_node, "msi-available-ranges", &len); if (!p) { pr_debug("msi_bitmap: no msi-available-ranges property " \ - "found on %s\n", bmp->of_node->full_name); + "found on %pOF\n", bmp->of_node); return 1; } if (len % (2 * sizeof(u32)) != 0) { printk(KERN_WARNING "msi_bitmap: Malformed msi-available-ranges" - " property on %s\n", bmp->of_node->full_name); + " property on %pOF\n", bmp->of_node); return -EINVAL; } diff --git a/arch/powerpc/sysdev/mv64x60_dev.c b/arch/powerpc/sysdev/mv64x60_dev.c index 026bbc3b2c47..185a67e742a6 100644 --- a/arch/powerpc/sysdev/mv64x60_dev.c +++ b/arch/powerpc/sysdev/mv64x60_dev.c @@ -452,8 +452,8 @@ static int __init mv64x60_device_setup(void) err = mv64x60_mpsc_device_setup(np, id++); if (err) printk(KERN_ERR "Failed to initialize MV64x60 " - "serial device %s: error %d.\n", - np->full_name, err); + "serial device %pOF: error %d.\n", + np, err); } id = 0; @@ -463,8 +463,8 @@ static int __init mv64x60_device_setup(void) if (IS_ERR(pdev)) { err = PTR_ERR(pdev); printk(KERN_ERR "Failed to initialize MV64x60 " - "network block %s: error %d.\n", - np->full_name, err); + "network block %pOF: error %d.\n", + np, err); continue; } for_each_child_of_node(np, np2) { @@ -474,9 +474,9 @@ static int __init mv64x60_device_setup(void) err = mv64x60_eth_device_setup(np2, id2++, pdev); if (err) printk(KERN_ERR "Failed to initialize " - "MV64x60 network device %s: " + "MV64x60 network device %pOF: " "error %d.\n", - np2->full_name, err); + np2, err); } } @@ -485,8 +485,8 @@ static int __init mv64x60_device_setup(void) err = mv64x60_i2c_device_setup(np, id++); if (err) printk(KERN_ERR "Failed to initialize MV64x60 I2C " - "bus %s: error %d.\n", - np->full_name, err); + "bus %pOF: error %d.\n", + np, err); } /* support up to one watchdog timer */ @@ -494,8 +494,8 @@ static int __init mv64x60_device_setup(void) if (np) { if ((err = mv64x60_wdt_device_setup(np, id))) printk(KERN_ERR "Failed to initialize MV64x60 " - "Watchdog %s: error %d.\n", - np->full_name, err); + "Watchdog %pOF: error %d.\n", + np, err); of_node_put(np); } diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c index 330d56613c5a..d52b3b81e05f 100644 --- a/arch/powerpc/sysdev/mv64x60_pci.c +++ b/arch/powerpc/sysdev/mv64x60_pci.c @@ -70,7 +70,7 @@ static ssize_t mv64x60_hs_reg_write(struct file *filp, struct kobject *kobj, return count; } -static struct bin_attribute mv64x60_hs_reg_attr = { /* Hotswap register */ +static const struct bin_attribute mv64x60_hs_reg_attr = { /* Hotswap register */ .attr = { .name = "hs_reg", .mode = S_IRUGO | S_IWUSR, @@ -136,8 +136,8 @@ static int __init mv64x60_add_bridge(struct device_node *dev) /* Get bus range if any */ bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); hose = pcibios_alloc_controller(dev); if (!hose) diff --git a/arch/powerpc/sysdev/of_rtc.c b/arch/powerpc/sysdev/of_rtc.c index 6f54b54b1328..153fdac4720f 100644 --- a/arch/powerpc/sysdev/of_rtc.c +++ b/arch/powerpc/sysdev/of_rtc.c @@ -38,21 +38,21 @@ void __init of_instantiate_rtc(void) res = kmalloc(sizeof(*res), GFP_KERNEL); if (!res) { printk(KERN_ERR "OF RTC: Out of memory " - "allocating resource structure for %s\n", - node->full_name); + "allocating resource structure for %pOF\n", + node); continue; } err = of_address_to_resource(node, 0, res); if (err) { printk(KERN_ERR "OF RTC: Error " - "translating resources for %s\n", - node->full_name); + "translating resources for %pOF\n", + node); continue; } - printk(KERN_INFO "OF_RTC: %s is a %s @ 0x%llx-0x%llx\n", - node->full_name, plat_name, + printk(KERN_INFO "OF_RTC: %pOF is a %s @ 0x%llx-0x%llx\n", + node, plat_name, (unsigned long long)res->start, (unsigned long long)res->end); platform_device_register_simple(plat_name, -1, res, 1); diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c index 76ea32c1b664..0f6fd5d04d33 100644 --- a/arch/powerpc/sysdev/scom.c +++ b/arch/powerpc/sysdev/scom.c @@ -194,12 +194,13 @@ static int scom_debug_init_one(struct dentry *root, struct device_node *dn, ent->dn = of_node_get(dn); snprintf(ent->name, 16, "%08x", i); - ent->path.data = (void*) dn->full_name; - ent->path.size = strlen(dn->full_name); + ent->path.data = (void*)kasprintf(GFP_KERNEL, "%pOF", dn); + ent->path.size = strlen((char *)ent->path.data); dir = debugfs_create_dir(ent->name, root); if (!dir) { of_node_put(dn); + kfree(ent->path.data); kfree(ent); return -1; } diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c index 6afddae2fb47..f02d4576138c 100644 --- a/arch/powerpc/sysdev/simple_gpio.c +++ b/arch/powerpc/sysdev/simple_gpio.c @@ -142,7 +142,6 @@ void __init simple_gpiochip_init(const char *compatible) } continue; err: - pr_err("%s: registration failed, status %d\n", - np->full_name, ret); + pr_err("%pOF: registration failed, status %d\n", np, ret); } } diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c index 5692dd569b9b..28ff1f53cefc 100644 --- a/arch/powerpc/sysdev/tsi108_pci.c +++ b/arch/powerpc/sysdev/tsi108_pci.c @@ -213,8 +213,8 @@ int __init tsi108_setup_pci(struct device_node *dev, u32 cfg_phys, int primary) /* Get bus range if any */ bus_range = of_get_property(dev, "bus-range", &len); if (bus_range == NULL || len < 2 * sizeof(int)) { - printk(KERN_WARNING "Can't get bus-range for %s, assume" - " bus 0\n", dev->full_name); + printk(KERN_WARNING "Can't get bus-range for %pOF, assume" + " bus 0\n", dev); } hose = pcibios_alloc_controller(dev); diff --git a/arch/powerpc/sysdev/xive/Kconfig b/arch/powerpc/sysdev/xive/Kconfig index 12ccd7373d2f..3e3e25b5e30d 100644 --- a/arch/powerpc/sysdev/xive/Kconfig +++ b/arch/powerpc/sysdev/xive/Kconfig @@ -9,3 +9,8 @@ config PPC_XIVE_NATIVE default n select PPC_XIVE depends on PPC_POWERNV + +config PPC_XIVE_SPAPR + bool + default n + select PPC_XIVE diff --git a/arch/powerpc/sysdev/xive/Makefile b/arch/powerpc/sysdev/xive/Makefile index 3fab303fc169..536d6e5706e3 100644 --- a/arch/powerpc/sysdev/xive/Makefile +++ b/arch/powerpc/sysdev/xive/Makefile @@ -2,3 +2,4 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror obj-y += common.o obj-$(CONFIG_PPC_XIVE_NATIVE) += native.o +obj-$(CONFIG_PPC_XIVE_SPAPR) += spapr.o diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 6595462b1fc8..f387318678b9 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -40,7 +40,8 @@ #undef DEBUG_ALL #ifdef DEBUG_ALL -#define DBG_VERBOSE(fmt...) pr_devel(fmt) +#define DBG_VERBOSE(fmt, ...) pr_devel("cpu %d - " fmt, \ + smp_processor_id(), ## __VA_ARGS__) #else #define DBG_VERBOSE(fmt...) do { } while(0) #endif @@ -190,7 +191,7 @@ static u32 xive_scan_interrupts(struct xive_cpu *xc, bool just_peek) * This is used to perform the magic loads from an ESB * described in xive.h */ -static u8 xive_poke_esb(struct xive_irq_data *xd, u32 offset) +static notrace u8 xive_esb_read(struct xive_irq_data *xd, u32 offset) { u64 val; @@ -198,13 +199,28 @@ static u8 xive_poke_esb(struct xive_irq_data *xd, u32 offset) if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG) offset |= offset << 4; - val = in_be64(xd->eoi_mmio + offset); + if ((xd->flags & XIVE_IRQ_FLAG_H_INT_ESB) && xive_ops->esb_rw) + val = xive_ops->esb_rw(xd->hw_irq, offset, 0, 0); + else + val = in_be64(xd->eoi_mmio + offset); return (u8)val; } +static void xive_esb_write(struct xive_irq_data *xd, u32 offset, u64 data) +{ + /* Handle HW errata */ + if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG) + offset |= offset << 4; + + if ((xd->flags & XIVE_IRQ_FLAG_H_INT_ESB) && xive_ops->esb_rw) + xive_ops->esb_rw(xd->hw_irq, offset, data, 1); + else + out_be64(xd->eoi_mmio + offset, data); +} + #ifdef CONFIG_XMON -static void xive_dump_eq(const char *name, struct xive_q *q) +static notrace void xive_dump_eq(const char *name, struct xive_q *q) { u32 i0, i1, idx; @@ -218,7 +234,7 @@ static void xive_dump_eq(const char *name, struct xive_q *q) q->toggle, i0, i1); } -void xmon_xive_do_dump(int cpu) +notrace void xmon_xive_do_dump(int cpu) { struct xive_cpu *xc = per_cpu(xive_cpu, cpu); @@ -227,7 +243,7 @@ void xmon_xive_do_dump(int cpu) xive_dump_eq("IRQ", &xc->queue[xive_irq_priority]); #ifdef CONFIG_SMP { - u64 val = xive_poke_esb(&xc->ipi_data, XIVE_ESB_GET); + u64 val = xive_esb_read(&xc->ipi_data, XIVE_ESB_GET); xmon_printf(" IPI state: %x:%c%c\n", xc->hw_ipi, val & XIVE_ESB_VAL_P ? 'P' : 'p', val & XIVE_ESB_VAL_P ? 'Q' : 'q'); @@ -297,7 +313,7 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) { /* If the XIVE supports the new "store EOI facility, use it */ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI) - out_be64(xd->eoi_mmio + XIVE_ESB_STORE_EOI, 0); + xive_esb_write(xd, XIVE_ESB_STORE_EOI, 0); else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) { /* * The FW told us to call it. This happens for some @@ -326,10 +342,10 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) * properly. */ if (xd->flags & XIVE_IRQ_FLAG_LSI) - in_be64(xd->eoi_mmio); + xive_esb_read(xd, XIVE_ESB_LOAD_EOI); else { - eoi_val = xive_poke_esb(xd, XIVE_ESB_SET_PQ_00); - DBG_VERBOSE("eoi_val=%x\n", offset, eoi_val); + eoi_val = xive_esb_read(xd, XIVE_ESB_SET_PQ_00); + DBG_VERBOSE("eoi_val=%x\n", eoi_val); /* Re-trigger if needed */ if ((eoi_val & XIVE_ESB_VAL_Q) && xd->trig_mmio) @@ -383,12 +399,12 @@ static void xive_do_source_set_mask(struct xive_irq_data *xd, * ESB accordingly on unmask. */ if (mask) { - val = xive_poke_esb(xd, XIVE_ESB_SET_PQ_01); + val = xive_esb_read(xd, XIVE_ESB_SET_PQ_01); xd->saved_p = !!(val & XIVE_ESB_VAL_P); } else if (xd->saved_p) - xive_poke_esb(xd, XIVE_ESB_SET_PQ_10); + xive_esb_read(xd, XIVE_ESB_SET_PQ_10); else - xive_poke_esb(xd, XIVE_ESB_SET_PQ_00); + xive_esb_read(xd, XIVE_ESB_SET_PQ_00); } /* @@ -447,7 +463,7 @@ static int xive_find_target_in_mask(const struct cpumask *mask, int cpu, first, num, i; /* Pick up a starting point CPU in the mask based on fuzz */ - num = cpumask_weight(mask); + num = min_t(int, cpumask_weight(mask), nr_cpu_ids); first = fuzz % num; /* Locate it */ @@ -672,6 +688,10 @@ static int xive_irq_set_affinity(struct irq_data *d, if (cpumask_any_and(cpumask, cpu_online_mask) >= nr_cpu_ids) return -EINVAL; + /* Don't do anything if the interrupt isn't started */ + if (!irqd_is_started(d)) + return IRQ_SET_MASK_OK; + /* * If existing target is already in the new mask, and is * online then do nothing. @@ -768,7 +788,7 @@ static int xive_irq_retrigger(struct irq_data *d) * To perform a retrigger, we first set the PQ bits to * 11, then perform an EOI. */ - xive_poke_esb(xd, XIVE_ESB_SET_PQ_11); + xive_esb_read(xd, XIVE_ESB_SET_PQ_11); /* * Note: We pass "0" to the hw_irq argument in order to @@ -803,7 +823,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) irqd_set_forwarded_to_vcpu(d); /* Set it to PQ=10 state to prevent further sends */ - pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_10); + pq = xive_esb_read(xd, XIVE_ESB_SET_PQ_10); /* No target ? nothing to do */ if (xd->target == XIVE_INVALID_TARGET) { @@ -832,7 +852,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) * for sure the queue slot is no longer in use. */ if (pq & 2) { - pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_11); + pq = xive_esb_read(xd, XIVE_ESB_SET_PQ_11); xd->saved_p = true; /* @@ -989,6 +1009,9 @@ static void xive_ipi_eoi(struct irq_data *d) { struct xive_cpu *xc = __this_cpu_read(xive_cpu); + DBG_VERBOSE("IPI eoi: irq=%d [0x%lx] (HW IRQ 0x%x) pending=%02x\n", + d->irq, irqd_to_hwirq(d), xc->hw_ipi, xc->pending_prio); + /* Handle possible race with unplug and drop stale IPIs */ if (!xc) return; @@ -1368,6 +1391,19 @@ void xive_flush_interrupt(void) #endif /* CONFIG_SMP */ +void xive_teardown_cpu(void) +{ + struct xive_cpu *xc = __this_cpu_read(xive_cpu); + unsigned int cpu = smp_processor_id(); + + /* Set CPPR to 0 to disable flow of interrupts */ + xc->cppr = 0; + out_8(xive_tima + xive_tima_offset + TM_CPPR, 0); + + if (xive_ops->teardown_cpu) + xive_ops->teardown_cpu(cpu, xc); +} + void xive_kexec_teardown_cpu(int secondary) { struct xive_cpu *xc = __this_cpu_read(xive_cpu); @@ -1395,8 +1431,8 @@ void xive_shutdown(void) xive_ops->shutdown(); } -bool xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset, - u8 max_prio) +bool __init xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset, + u8 max_prio) { xive_tima = area; xive_tima_offset = offset; @@ -1424,6 +1460,22 @@ bool xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset, return true; } +__be32 *xive_queue_page_alloc(unsigned int cpu, u32 queue_shift) +{ + unsigned int alloc_order; + struct page *pages; + __be32 *qpage; + + alloc_order = xive_alloc_order(queue_shift); + pages = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, alloc_order); + if (!pages) + return ERR_PTR(-ENOMEM); + qpage = (__be32 *)page_address(pages); + memset(qpage, 0, 1 << queue_shift); + + return qpage; +} + static int __init xive_off(char *arg) { xive_cmdline_disabled = true; diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 0f95476b01f6..44f3a25ca630 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -82,6 +82,8 @@ int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) return -ENOMEM; } + data->hw_irq = hw_irq; + if (!data->trig_page) return 0; if (data->trig_page == data->eoi_page) { @@ -202,17 +204,12 @@ EXPORT_SYMBOL_GPL(xive_native_disable_queue); static int xive_native_setup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio) { struct xive_q *q = &xc->queue[prio]; - unsigned int alloc_order; - struct page *pages; __be32 *qpage; - alloc_order = (xive_queue_shift > PAGE_SHIFT) ? - (xive_queue_shift - PAGE_SHIFT) : 0; - pages = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, alloc_order); - if (!pages) - return -ENOMEM; - qpage = (__be32 *)page_address(pages); - memset(qpage, 0, 1 << xive_queue_shift); + qpage = xive_queue_page_alloc(cpu, xive_queue_shift); + if (IS_ERR(qpage)) + return PTR_ERR(qpage); + return xive_native_configure_queue(get_hard_smp_processor_id(cpu), q, prio, qpage, xive_queue_shift, false); } @@ -227,8 +224,7 @@ static void xive_native_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, u8 * from an IPI and iounmap isn't safe */ __xive_native_disable_queue(get_hard_smp_processor_id(cpu), q, prio); - alloc_order = (xive_queue_shift > PAGE_SHIFT) ? - (xive_queue_shift - PAGE_SHIFT) : 0; + alloc_order = xive_alloc_order(xive_queue_shift); free_pages((unsigned long)q->qpage, alloc_order); q->qpage = NULL; } @@ -531,7 +527,7 @@ u32 xive_native_default_eq_shift(void) } EXPORT_SYMBOL_GPL(xive_native_default_eq_shift); -bool xive_native_init(void) +bool __init xive_native_init(void) { struct device_node *np; struct resource r; @@ -551,7 +547,7 @@ bool xive_native_init(void) pr_devel("not found !\n"); return false; } - pr_devel("Found %s\n", np->full_name); + pr_devel("Found %pOF\n", np); /* Resource 1 is HV window */ if (of_address_to_resource(np, 1, &r)) { diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c new file mode 100644 index 000000000000..f24a70bc6855 --- /dev/null +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -0,0 +1,662 @@ +/* + * Copyright 2016,2017 IBM Corporation. + * + * 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. + */ + +#define pr_fmt(fmt) "xive: " fmt + +#include <linux/types.h> +#include <linux/irq.h> +#include <linux/smp.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/cpumask.h> +#include <linux/mm.h> + +#include <asm/prom.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/irq.h> +#include <asm/errno.h> +#include <asm/xive.h> +#include <asm/xive-regs.h> +#include <asm/hvcall.h> + +#include "xive-internal.h" + +static u32 xive_queue_shift; + +struct xive_irq_bitmap { + unsigned long *bitmap; + unsigned int base; + unsigned int count; + spinlock_t lock; + struct list_head list; +}; + +static LIST_HEAD(xive_irq_bitmaps); + +static int xive_irq_bitmap_add(int base, int count) +{ + struct xive_irq_bitmap *xibm; + + xibm = kzalloc(sizeof(*xibm), GFP_ATOMIC); + if (!xibm) + return -ENOMEM; + + spin_lock_init(&xibm->lock); + xibm->base = base; + xibm->count = count; + xibm->bitmap = kzalloc(xibm->count, GFP_KERNEL); + list_add(&xibm->list, &xive_irq_bitmaps); + + pr_info("Using IRQ range [%x-%x]", xibm->base, + xibm->base + xibm->count - 1); + return 0; +} + +static int __xive_irq_bitmap_alloc(struct xive_irq_bitmap *xibm) +{ + int irq; + + irq = find_first_zero_bit(xibm->bitmap, xibm->count); + if (irq != xibm->count) { + set_bit(irq, xibm->bitmap); + irq += xibm->base; + } else { + irq = -ENOMEM; + } + + return irq; +} + +static int xive_irq_bitmap_alloc(void) +{ + struct xive_irq_bitmap *xibm; + unsigned long flags; + int irq = -ENOENT; + + list_for_each_entry(xibm, &xive_irq_bitmaps, list) { + spin_lock_irqsave(&xibm->lock, flags); + irq = __xive_irq_bitmap_alloc(xibm); + spin_unlock_irqrestore(&xibm->lock, flags); + if (irq >= 0) + break; + } + return irq; +} + +static void xive_irq_bitmap_free(int irq) +{ + unsigned long flags; + struct xive_irq_bitmap *xibm; + + list_for_each_entry(xibm, &xive_irq_bitmaps, list) { + if ((irq >= xibm->base) && (irq < xibm->base + xibm->count)) { + spin_lock_irqsave(&xibm->lock, flags); + clear_bit(irq - xibm->base, xibm->bitmap); + spin_unlock_irqrestore(&xibm->lock, flags); + break; + } + } +} + +static long plpar_int_get_source_info(unsigned long flags, + unsigned long lisn, + unsigned long *src_flags, + unsigned long *eoi_page, + unsigned long *trig_page, + unsigned long *esb_shift) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_INT_GET_SOURCE_INFO, retbuf, flags, lisn); + if (rc) { + pr_err("H_INT_GET_SOURCE_INFO lisn=%ld failed %ld\n", lisn, rc); + return rc; + } + + *src_flags = retbuf[0]; + *eoi_page = retbuf[1]; + *trig_page = retbuf[2]; + *esb_shift = retbuf[3]; + + pr_devel("H_INT_GET_SOURCE_INFO flags=%lx eoi=%lx trig=%lx shift=%lx\n", + retbuf[0], retbuf[1], retbuf[2], retbuf[3]); + + return 0; +} + +#define XIVE_SRC_SET_EISN (1ull << (63 - 62)) +#define XIVE_SRC_MASK (1ull << (63 - 63)) /* unused */ + +static long plpar_int_set_source_config(unsigned long flags, + unsigned long lisn, + unsigned long target, + unsigned long prio, + unsigned long sw_irq) +{ + long rc; + + + pr_devel("H_INT_SET_SOURCE_CONFIG flags=%lx lisn=%lx target=%lx prio=%lx sw_irq=%lx\n", + flags, lisn, target, prio, sw_irq); + + + rc = plpar_hcall_norets(H_INT_SET_SOURCE_CONFIG, flags, lisn, + target, prio, sw_irq); + if (rc) { + pr_err("H_INT_SET_SOURCE_CONFIG lisn=%ld target=%lx prio=%lx failed %ld\n", + lisn, target, prio, rc); + return rc; + } + + return 0; +} + +static long plpar_int_get_queue_info(unsigned long flags, + unsigned long target, + unsigned long priority, + unsigned long *esn_page, + unsigned long *esn_size) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_INT_GET_QUEUE_INFO, retbuf, flags, target, priority); + if (rc) { + pr_err("H_INT_GET_QUEUE_INFO cpu=%ld prio=%ld failed %ld\n", + target, priority, rc); + return rc; + } + + *esn_page = retbuf[0]; + *esn_size = retbuf[1]; + + pr_devel("H_INT_GET_QUEUE_INFO page=%lx size=%lx\n", + retbuf[0], retbuf[1]); + + return 0; +} + +#define XIVE_EQ_ALWAYS_NOTIFY (1ull << (63 - 63)) + +static long plpar_int_set_queue_config(unsigned long flags, + unsigned long target, + unsigned long priority, + unsigned long qpage, + unsigned long qsize) +{ + long rc; + + pr_devel("H_INT_SET_QUEUE_CONFIG flags=%lx target=%lx priority=%lx qpage=%lx qsize=%lx\n", + flags, target, priority, qpage, qsize); + + rc = plpar_hcall_norets(H_INT_SET_QUEUE_CONFIG, flags, target, + priority, qpage, qsize); + if (rc) { + pr_err("H_INT_SET_QUEUE_CONFIG cpu=%ld prio=%ld qpage=%lx returned %ld\n", + target, priority, qpage, rc); + return rc; + } + + return 0; +} + +static long plpar_int_sync(unsigned long flags, unsigned long lisn) +{ + long rc; + + rc = plpar_hcall_norets(H_INT_SYNC, flags, lisn); + if (rc) { + pr_err("H_INT_SYNC lisn=%ld returned %ld\n", lisn, rc); + return rc; + } + + return 0; +} + +#define XIVE_ESB_FLAG_STORE (1ull << (63 - 63)) + +static long plpar_int_esb(unsigned long flags, + unsigned long lisn, + unsigned long offset, + unsigned long in_data, + unsigned long *out_data) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + pr_devel("H_INT_ESB flags=%lx lisn=%lx offset=%lx in=%lx\n", + flags, lisn, offset, in_data); + + rc = plpar_hcall(H_INT_ESB, retbuf, flags, lisn, offset, in_data); + if (rc) { + pr_err("H_INT_ESB lisn=%ld offset=%ld returned %ld\n", + lisn, offset, rc); + return rc; + } + + *out_data = retbuf[0]; + + return 0; +} + +static u64 xive_spapr_esb_rw(u32 lisn, u32 offset, u64 data, bool write) +{ + unsigned long read_data; + long rc; + + rc = plpar_int_esb(write ? XIVE_ESB_FLAG_STORE : 0, + lisn, offset, data, &read_data); + if (rc) + return -1; + + return write ? 0 : read_data; +} + +#define XIVE_SRC_H_INT_ESB (1ull << (63 - 60)) +#define XIVE_SRC_LSI (1ull << (63 - 61)) +#define XIVE_SRC_TRIGGER (1ull << (63 - 62)) +#define XIVE_SRC_STORE_EOI (1ull << (63 - 63)) + +static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data) +{ + long rc; + unsigned long flags; + unsigned long eoi_page; + unsigned long trig_page; + unsigned long esb_shift; + + memset(data, 0, sizeof(*data)); + + rc = plpar_int_get_source_info(0, hw_irq, &flags, &eoi_page, &trig_page, + &esb_shift); + if (rc) + return -EINVAL; + + if (flags & XIVE_SRC_H_INT_ESB) + data->flags |= XIVE_IRQ_FLAG_H_INT_ESB; + if (flags & XIVE_SRC_STORE_EOI) + data->flags |= XIVE_IRQ_FLAG_STORE_EOI; + if (flags & XIVE_SRC_LSI) + data->flags |= XIVE_IRQ_FLAG_LSI; + data->eoi_page = eoi_page; + data->esb_shift = esb_shift; + data->trig_page = trig_page; + + /* + * No chip-id for the sPAPR backend. This has an impact how we + * pick a target. See xive_pick_irq_target(). + */ + data->src_chip = XIVE_INVALID_CHIP_ID; + + data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift); + if (!data->eoi_mmio) { + pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq); + return -ENOMEM; + } + + data->hw_irq = hw_irq; + + /* Full function page supports trigger */ + if (flags & XIVE_SRC_TRIGGER) { + data->trig_mmio = data->eoi_mmio; + return 0; + } + + data->trig_mmio = ioremap(data->trig_page, 1u << data->esb_shift); + if (!data->trig_mmio) { + pr_err("Failed to map trigger page for irq 0x%x\n", hw_irq); + return -ENOMEM; + } + return 0; +} + +static int xive_spapr_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq) +{ + long rc; + + rc = plpar_int_set_source_config(XIVE_SRC_SET_EISN, hw_irq, target, + prio, sw_irq); + + return rc == 0 ? 0 : -ENXIO; +} + +/* This can be called multiple time to change a queue configuration */ +static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio, + __be32 *qpage, u32 order) +{ + s64 rc = 0; + unsigned long esn_page; + unsigned long esn_size; + u64 flags, qpage_phys; + + /* If there's an actual queue page, clean it */ + if (order) { + if (WARN_ON(!qpage)) + return -EINVAL; + qpage_phys = __pa(qpage); + } else { + qpage_phys = 0; + } + + /* Initialize the rest of the fields */ + q->msk = order ? ((1u << (order - 2)) - 1) : 0; + q->idx = 0; + q->toggle = 0; + + rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size); + if (rc) { + pr_err("Error %lld getting queue info prio %d\n", rc, prio); + rc = -EIO; + goto fail; + } + + /* TODO: add support for the notification page */ + q->eoi_phys = esn_page; + + /* Default is to always notify */ + flags = XIVE_EQ_ALWAYS_NOTIFY; + + /* Configure and enable the queue in HW */ + rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order); + if (rc) { + pr_err("Error %lld setting queue for prio %d\n", rc, prio); + rc = -EIO; + } else { + q->qpage = qpage; + } +fail: + return rc; +} + +static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc, + u8 prio) +{ + struct xive_q *q = &xc->queue[prio]; + __be32 *qpage; + + qpage = xive_queue_page_alloc(cpu, xive_queue_shift); + if (IS_ERR(qpage)) + return PTR_ERR(qpage); + + return xive_spapr_configure_queue(cpu, q, prio, qpage, + xive_queue_shift); +} + +static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc, + u8 prio) +{ + struct xive_q *q = &xc->queue[prio]; + unsigned int alloc_order; + long rc; + + rc = plpar_int_set_queue_config(0, cpu, prio, 0, 0); + if (rc) + pr_err("Error %ld setting queue for prio %d\n", rc, prio); + + alloc_order = xive_alloc_order(xive_queue_shift); + free_pages((unsigned long)q->qpage, alloc_order); + q->qpage = NULL; +} + +static bool xive_spapr_match(struct device_node *node) +{ + /* Ignore cascaded controllers for the moment */ + return 1; +} + +#ifdef CONFIG_SMP +static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc) +{ + int irq = xive_irq_bitmap_alloc(); + + if (irq < 0) { + pr_err("Failed to allocate IPI on CPU %d\n", cpu); + return -ENXIO; + } + + xc->hw_ipi = irq; + return 0; +} + +static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc) +{ + xive_irq_bitmap_free(xc->hw_ipi); +} +#endif /* CONFIG_SMP */ + +static void xive_spapr_shutdown(void) +{ + long rc; + + rc = plpar_hcall_norets(H_INT_RESET, 0); + if (rc) + pr_err("H_INT_RESET failed %ld\n", rc); +} + +/* + * Perform an "ack" cycle on the current thread. Grab the pending + * active priorities and update the CPPR to the most favored one. + */ +static void xive_spapr_update_pending(struct xive_cpu *xc) +{ + u8 nsr, cppr; + u16 ack; + + /* + * Perform the "Acknowledge O/S to Register" cycle. + * + * Let's speedup the access to the TIMA using the raw I/O + * accessor as we don't need the synchronisation routine of + * the higher level ones + */ + ack = be16_to_cpu(__raw_readw(xive_tima + TM_SPC_ACK_OS_REG)); + + /* Synchronize subsequent queue accesses */ + mb(); + + /* + * Grab the CPPR and the "NSR" field which indicates the source + * of the interrupt (if any) + */ + cppr = ack & 0xff; + nsr = ack >> 8; + + if (nsr & TM_QW1_NSR_EO) { + if (cppr == 0xff) + return; + /* Mark the priority pending */ + xc->pending_prio |= 1 << cppr; + + /* + * A new interrupt should never have a CPPR less favored + * than our current one. + */ + if (cppr >= xc->cppr) + pr_err("CPU %d odd ack CPPR, got %d at %d\n", + smp_processor_id(), cppr, xc->cppr); + + /* Update our idea of what the CPPR is */ + xc->cppr = cppr; + } +} + +static void xive_spapr_eoi(u32 hw_irq) +{ + /* Not used */; +} + +static void xive_spapr_setup_cpu(unsigned int cpu, struct xive_cpu *xc) +{ + /* Only some debug on the TIMA settings */ + pr_debug("(HW value: %08x %08x %08x)\n", + in_be32(xive_tima + TM_QW1_OS + TM_WORD0), + in_be32(xive_tima + TM_QW1_OS + TM_WORD1), + in_be32(xive_tima + TM_QW1_OS + TM_WORD2)); +} + +static void xive_spapr_teardown_cpu(unsigned int cpu, struct xive_cpu *xc) +{ + /* Nothing to do */; +} + +static void xive_spapr_sync_source(u32 hw_irq) +{ + /* Specs are unclear on what this is doing */ + plpar_int_sync(0, hw_irq); +} + +static const struct xive_ops xive_spapr_ops = { + .populate_irq_data = xive_spapr_populate_irq_data, + .configure_irq = xive_spapr_configure_irq, + .setup_queue = xive_spapr_setup_queue, + .cleanup_queue = xive_spapr_cleanup_queue, + .match = xive_spapr_match, + .shutdown = xive_spapr_shutdown, + .update_pending = xive_spapr_update_pending, + .eoi = xive_spapr_eoi, + .setup_cpu = xive_spapr_setup_cpu, + .teardown_cpu = xive_spapr_teardown_cpu, + .sync_source = xive_spapr_sync_source, + .esb_rw = xive_spapr_esb_rw, +#ifdef CONFIG_SMP + .get_ipi = xive_spapr_get_ipi, + .put_ipi = xive_spapr_put_ipi, +#endif /* CONFIG_SMP */ + .name = "spapr", +}; + +/* + * get max priority from "/ibm,plat-res-int-priorities" + */ +static bool xive_get_max_prio(u8 *max_prio) +{ + struct device_node *rootdn; + const __be32 *reg; + u32 len; + int prio, found; + + rootdn = of_find_node_by_path("/"); + if (!rootdn) { + pr_err("not root node found !\n"); + return false; + } + + reg = of_get_property(rootdn, "ibm,plat-res-int-priorities", &len); + if (!reg) { + pr_err("Failed to read 'ibm,plat-res-int-priorities' property\n"); + return false; + } + + if (len % (2 * sizeof(u32)) != 0) { + pr_err("invalid 'ibm,plat-res-int-priorities' property\n"); + return false; + } + + /* HW supports priorities in the range [0-7] and 0xFF is a + * wildcard priority used to mask. We scan the ranges reserved + * by the hypervisor to find the lowest priority we can use. + */ + found = 0xFF; + for (prio = 0; prio < 8; prio++) { + int reserved = 0; + int i; + + for (i = 0; i < len / (2 * sizeof(u32)); i++) { + int base = be32_to_cpu(reg[2 * i]); + int range = be32_to_cpu(reg[2 * i + 1]); + + if (prio >= base && prio < base + range) + reserved++; + } + + if (!reserved) + found = prio; + } + + if (found == 0xFF) { + pr_err("no valid priority found in 'ibm,plat-res-int-priorities'\n"); + return false; + } + + *max_prio = found; + return true; +} + +bool __init xive_spapr_init(void) +{ + struct device_node *np; + struct resource r; + void __iomem *tima; + struct property *prop; + u8 max_prio; + u32 val; + u32 len; + const __be32 *reg; + int i; + + if (xive_cmdline_disabled) + return false; + + pr_devel("%s()\n", __func__); + np = of_find_compatible_node(NULL, NULL, "ibm,power-ivpe"); + if (!np) { + pr_devel("not found !\n"); + return false; + } + pr_devel("Found %s\n", np->full_name); + + /* Resource 1 is the OS ring TIMA */ + if (of_address_to_resource(np, 1, &r)) { + pr_err("Failed to get thread mgmnt area resource\n"); + return false; + } + tima = ioremap(r.start, resource_size(&r)); + if (!tima) { + pr_err("Failed to map thread mgmnt area\n"); + return false; + } + + if (!xive_get_max_prio(&max_prio)) + return false; + + /* Feed the IRQ number allocator with the ranges given in the DT */ + reg = of_get_property(np, "ibm,xive-lisn-ranges", &len); + if (!reg) { + pr_err("Failed to read 'ibm,xive-lisn-ranges' property\n"); + return false; + } + + if (len % (2 * sizeof(u32)) != 0) { + pr_err("invalid 'ibm,xive-lisn-ranges' property\n"); + return false; + } + + for (i = 0; i < len / (2 * sizeof(u32)); i++, reg += 2) + xive_irq_bitmap_add(be32_to_cpu(reg[0]), + be32_to_cpu(reg[1])); + + /* Iterate the EQ sizes and pick one */ + of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, reg, val) { + xive_queue_shift = val; + if (val == PAGE_SHIFT) + break; + } + + /* Initialize XIVE core with our backend */ + if (!xive_core_init(&xive_spapr_ops, tima, TM_QW1_OS, max_prio)) + return false; + + pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10)); + return true; +} diff --git a/arch/powerpc/sysdev/xive/xive-internal.h b/arch/powerpc/sysdev/xive/xive-internal.h index d07ef2d29caf..f34abed0c05f 100644 --- a/arch/powerpc/sysdev/xive/xive-internal.h +++ b/arch/powerpc/sysdev/xive/xive-internal.h @@ -47,6 +47,7 @@ struct xive_ops { void (*update_pending)(struct xive_cpu *xc); void (*eoi)(u32 hw_irq); void (*sync_source)(u32 hw_irq); + u64 (*esb_rw)(u32 hw_irq, u32 offset, u64 data, bool write); #ifdef CONFIG_SMP int (*get_ipi)(unsigned int cpu, struct xive_cpu *xc); void (*put_ipi)(unsigned int cpu, struct xive_cpu *xc); @@ -56,6 +57,12 @@ struct xive_ops { bool xive_core_init(const struct xive_ops *ops, void __iomem *area, u32 offset, u8 max_prio); +__be32 *xive_queue_page_alloc(unsigned int cpu, u32 queue_shift); + +static inline u32 xive_alloc_order(u32 queue_shift) +{ + return (queue_shift > PAGE_SHIFT) ? (queue_shift - PAGE_SHIFT) : 0; +} extern bool xive_cmdline_disabled; diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 0b2f771593eb..1dd88315cff4 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -5,6 +5,10 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror GCOV_PROFILE := n UBSAN_SANITIZE := n +# Disable ftrace for the entire directory +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -mno-sched-epilog,,$(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))) + ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y += xmon.o nonstdio.o spr_access.o diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 08e367e3e8c3..33351c6704b1 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -89,6 +89,7 @@ static unsigned long nidump = 16; static unsigned long ncsum = 4096; static int termch; static char tmpstr[128]; +static int tracing_enabled; static long bus_error_jmp[JMP_BUF_LEN]; static int catch_memory_errors; @@ -234,6 +235,7 @@ Commands:\n\ "\ dr dump stream of raw bytes\n\ dt dump the tracing buffers (uses printk)\n\ + dtc dump the tracing buffers for current CPU (uses printk)\n\ " #ifdef CONFIG_PPC_POWERNV " dx# dump xive on CPU #\n\ @@ -461,6 +463,9 @@ static int xmon_core(struct pt_regs *regs, int fromipi) local_irq_save(flags); hard_irq_disable(); + tracing_enabled = tracing_is_on(); + tracing_off(); + bp = in_breakpoint_table(regs->nip, &offset); if (bp != NULL) { regs->nip = bp->address + offset; @@ -981,6 +986,8 @@ cmds(struct pt_regs *excp) break; case 'x': case 'X': + if (tracing_enabled) + tracing_on(); return cmd; case EOF: printf(" <no input ...>\n"); @@ -1732,23 +1739,25 @@ static void dump_206_sprs(void) /* Actually some of these pre-date 2.06, but whatevs */ - printf("srr0 = %.16x srr1 = %.16x dsisr = %.8x\n", + printf("srr0 = %.16lx srr1 = %.16lx dsisr = %.8x\n", mfspr(SPRN_SRR0), mfspr(SPRN_SRR1), mfspr(SPRN_DSISR)); - printf("dscr = %.16x ppr = %.16x pir = %.8x\n", + printf("dscr = %.16lx ppr = %.16lx pir = %.8x\n", mfspr(SPRN_DSCR), mfspr(SPRN_PPR), mfspr(SPRN_PIR)); + printf("amr = %.16lx uamor = %.16lx\n", + mfspr(SPRN_AMR), mfspr(SPRN_UAMOR)); if (!(mfmsr() & MSR_HV)) return; - printf("sdr1 = %.16x hdar = %.16x hdsisr = %.8x\n", + printf("sdr1 = %.16lx hdar = %.16lx hdsisr = %.8x\n", mfspr(SPRN_SDR1), mfspr(SPRN_HDAR), mfspr(SPRN_HDSISR)); - printf("hsrr0 = %.16x hsrr1 = %.16x hdec = %.8x\n", + printf("hsrr0 = %.16lx hsrr1 = %.16lx hdec = %.16lx\n", mfspr(SPRN_HSRR0), mfspr(SPRN_HSRR1), mfspr(SPRN_HDEC)); - printf("lpcr = %.16x pcr = %.16x lpidr = %.8x\n", + printf("lpcr = %.16lx pcr = %.16lx lpidr = %.8x\n", mfspr(SPRN_LPCR), mfspr(SPRN_PCR), mfspr(SPRN_LPID)); - printf("hsprg0 = %.16x hsprg1 = %.16x\n", - mfspr(SPRN_HSPRG0), mfspr(SPRN_HSPRG1)); - printf("dabr = %.16x dabrx = %.16x\n", + printf("hsprg0 = %.16lx hsprg1 = %.16lx amor = %.16lx\n", + mfspr(SPRN_HSPRG0), mfspr(SPRN_HSPRG1), mfspr(SPRN_AMOR)); + printf("dabr = %.16lx dabrx = %.16lx\n", mfspr(SPRN_DABR), mfspr(SPRN_DABRX)); #endif } @@ -1761,42 +1770,65 @@ static void dump_207_sprs(void) if (!cpu_has_feature(CPU_FTR_ARCH_207S)) return; - printf("dpdes = %.16x tir = %.16x cir = %.8x\n", + printf("dpdes = %.16lx tir = %.16lx cir = %.8x\n", mfspr(SPRN_DPDES), mfspr(SPRN_TIR), mfspr(SPRN_CIR)); - printf("fscr = %.16x tar = %.16x pspb = %.8x\n", + printf("fscr = %.16lx tar = %.16lx pspb = %.8x\n", mfspr(SPRN_FSCR), mfspr(SPRN_TAR), mfspr(SPRN_PSPB)); msr = mfmsr(); if (msr & MSR_TM) { /* Only if TM has been enabled in the kernel */ - printf("tfhar = %.16x tfiar = %.16x texasr = %.16x\n", + printf("tfhar = %.16lx tfiar = %.16lx texasr = %.16lx\n", mfspr(SPRN_TFHAR), mfspr(SPRN_TFIAR), mfspr(SPRN_TEXASR)); } - printf("mmcr0 = %.16x mmcr1 = %.16x mmcr2 = %.16x\n", + printf("mmcr0 = %.16lx mmcr1 = %.16lx mmcr2 = %.16lx\n", mfspr(SPRN_MMCR0), mfspr(SPRN_MMCR1), mfspr(SPRN_MMCR2)); printf("pmc1 = %.8x pmc2 = %.8x pmc3 = %.8x pmc4 = %.8x\n", mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), mfspr(SPRN_PMC3), mfspr(SPRN_PMC4)); - printf("mmcra = %.16x siar = %.16x pmc5 = %.8x\n", + printf("mmcra = %.16lx siar = %.16lx pmc5 = %.8x\n", mfspr(SPRN_MMCRA), mfspr(SPRN_SIAR), mfspr(SPRN_PMC5)); - printf("sdar = %.16x sier = %.16x pmc6 = %.8x\n", + printf("sdar = %.16lx sier = %.16lx pmc6 = %.8x\n", mfspr(SPRN_SDAR), mfspr(SPRN_SIER), mfspr(SPRN_PMC6)); - printf("ebbhr = %.16x ebbrr = %.16x bescr = %.16x\n", + printf("ebbhr = %.16lx ebbrr = %.16lx bescr = %.16lx\n", mfspr(SPRN_EBBHR), mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR)); + printf("iamr = %.16lx\n", mfspr(SPRN_IAMR)); if (!(msr & MSR_HV)) return; - printf("hfscr = %.16x dhdes = %.16x rpr = %.16x\n", + printf("hfscr = %.16lx dhdes = %.16lx rpr = %.16lx\n", mfspr(SPRN_HFSCR), mfspr(SPRN_DHDES), mfspr(SPRN_RPR)); - printf("dawr = %.16x dawrx = %.16x ciabr = %.16x\n", + printf("dawr = %.16lx dawrx = %.16lx ciabr = %.16lx\n", mfspr(SPRN_DAWR), mfspr(SPRN_DAWRX), mfspr(SPRN_CIABR)); #endif } +static void dump_300_sprs(void) +{ +#ifdef CONFIG_PPC64 + bool hv = mfmsr() & MSR_HV; + + if (!cpu_has_feature(CPU_FTR_ARCH_300)) + return; + + printf("pidr = %.16lx tidr = %.16lx\n", + mfspr(SPRN_PID), mfspr(SPRN_TIDR)); + printf("asdr = %.16lx psscr = %.16lx\n", + mfspr(SPRN_ASDR), hv ? mfspr(SPRN_PSSCR) + : mfspr(SPRN_PSSCR_PR)); + + if (!hv) + return; + + printf("ptcr = %.16lx\n", + mfspr(SPRN_PTCR)); +#endif +} + static void dump_one_spr(int spr, bool show_unimplemented) { unsigned long val; @@ -1850,6 +1882,7 @@ static void super_regs(void) dump_206_sprs(); dump_207_sprs(); + dump_300_sprs(); return; } @@ -2231,6 +2264,17 @@ static void xmon_rawdump (unsigned long adrs, long ndump) printf("\n"); } +static void dump_tracing(void) +{ + int c; + + c = inchar(); + if (c == 'c') + ftrace_dump(DUMP_ORIG); + else + ftrace_dump(DUMP_ALL); +} + #ifdef CONFIG_PPC64 static void dump_one_paca(int cpu) { @@ -2507,6 +2551,11 @@ dump(void) } #endif + if (c == 't') { + dump_tracing(); + return; + } + if (c == '\n') termch = c; @@ -2525,9 +2574,6 @@ dump(void) dump_log_buf(); } else if (c == 'o') { dump_opal_msglog(); - } else if (c == 't') { - ftrace_dump(DUMP_ALL); - tracing_on(); } else if (c == 'r') { scanhex(&ndump); if (ndump == 0) |