diff options
Diffstat (limited to 'arch/powerpc')
41 files changed, 288 insertions, 174 deletions
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 1c1aadc8c48f..c32ae5ce9fff 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -1,10 +1,6 @@ addnote empty.c hack-coff -infblock.c -infblock.h -infcodes.c -infcodes.h inffast.c inffast.h inffixed.h diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index f8b394a76ac3..29767a8dfea5 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -55,7 +55,6 @@ CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_NOTRACK=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index db27c82e0542..de7c4c53f5cf 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -92,7 +92,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_NOTRACK=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m @@ -487,7 +486,8 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_HW=y -CONFIG_CRYPTO_DEV_NX=m +CONFIG_CRYPTO_DEV_NX=y +CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 7bd1763877ba..f55c27609fc6 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -66,7 +66,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_NOTRACK=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_TCPMSS=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index c47f2becfbc3..be1cb6ea3a36 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -167,7 +167,6 @@ CONFIG_NETFILTER_XT_TARGET_DSCP=m CONFIG_NETFILTER_XT_TARGET_MARK=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m -CONFIG_NETFILTER_XT_TARGET_NOTRACK=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m CONFIG_NETFILTER_XT_TARGET_SECMARK=m diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 1f65b3c9b59a..9f4a9368f51b 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -369,7 +369,8 @@ CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_LZO=m # CONFIG_CRYPTO_ANSI_CPRNG is not set CONFIG_CRYPTO_HW=y -CONFIG_CRYPTO_DEV_NX=m +CONFIG_CRYPTO_DEV_NX=y +CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_VIRTUALIZATION=y CONFIG_KVM_BOOK3S_64=m CONFIG_KVM_BOOK3S_64_HV=y diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 42ce570812c1..f7706d722b39 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -214,6 +214,9 @@ struct machdep_calls { /* Called after scan and before resource survey */ void (*pcibios_fixup_phb)(struct pci_controller *hose); + /* Called during PCI resource reassignment */ + resource_size_t (*pcibios_window_alignment)(struct pci_bus *, unsigned long type); + /* Called to shutdown machine specific hardware not already controlled * by other drivers. */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 53b6dfa83344..54b73a28c205 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -386,6 +386,7 @@ extern unsigned long cpuidle_disable; enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ +extern void power7_nap(void); #ifdef CONFIG_PSERIES_IDLE extern void update_smt_snooze_delay(int snooze); diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h index 7f065e178ec4..0e15db4d703b 100644 --- a/arch/powerpc/include/asm/ps3.h +++ b/arch/powerpc/include/asm/ps3.h @@ -24,7 +24,7 @@ #include <linux/init.h> #include <linux/types.h> #include <linux/device.h> -#include "cell-pmu.h" +#include <asm/cell-pmu.h> union ps3_firmware_version { u64 raw; diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 559ae1ee6706..840838769853 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -189,7 +189,7 @@ SYSCALL_SPU(getcwd) SYSCALL_SPU(capget) SYSCALL_SPU(capset) COMPAT_SYS(sigaltstack) -SYSX_SPU(sys_sendfile64,compat_sys_sendfile,sys_sendfile) +SYSX_SPU(sys_sendfile,compat_sys_sendfile_wrapper,sys_sendfile) SYSCALL(ni_syscall) SYSCALL(ni_syscall) PPC_SYS(vfork) @@ -229,7 +229,7 @@ COMPAT_SYS_SPU(sched_setaffinity) COMPAT_SYS_SPU(sched_getaffinity) SYSCALL(ni_syscall) SYSCALL(ni_syscall) -SYS32ONLY(sendfile64) +SYSX(sys_ni_syscall,compat_sys_sendfile64_wrapper,sys_sendfile64) COMPAT_SYS_SPU(io_setup) SYSCALL_SPU(io_destroy) COMPAT_SYS_SPU(io_getevents) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 3b4b4a8da922..c1f267694acb 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -197,12 +197,6 @@ struct cpu_usage { DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array); -#if defined(CONFIG_VIRT_CPU_ACCOUNTING) -#define account_process_vtime(tsk) account_process_tick(tsk, 0) -#else -#define account_process_vtime(tsk) do { } while (0) -#endif - extern void secondary_cpu_time_init(void); DECLARE_PER_CPU(u64, decrementers_next_tb); diff --git a/arch/powerpc/include/asm/ucc_fast.h b/arch/powerpc/include/asm/ucc_fast.h index 839aab8bf37d..4644c840e2fa 100644 --- a/arch/powerpc/include/asm/ucc_fast.h +++ b/arch/powerpc/include/asm/ucc_fast.h @@ -19,7 +19,7 @@ #include <asm/immap_qe.h> #include <asm/qe.h> -#include "ucc.h" +#include <asm/ucc.h> /* Receive BD's status */ #define R_E 0x80000000 /* buffer empty */ diff --git a/arch/powerpc/include/asm/ucc_slow.h b/arch/powerpc/include/asm/ucc_slow.h index 0980e6ad335b..cf131ffdb8d1 100644 --- a/arch/powerpc/include/asm/ucc_slow.h +++ b/arch/powerpc/include/asm/ucc_slow.h @@ -20,7 +20,7 @@ #include <asm/immap_qe.h> #include <asm/qe.h> -#include "ucc.h" +#include <asm/ucc.h> /* transmit BD's status */ #define T_R 0x80000000 /* ready bit */ diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index bd377a368611..c683fa350add 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -419,6 +419,7 @@ #define __ARCH_WANT_COMPAT_SYS_TIME #define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND #define __ARCH_WANT_SYS_NEWFSTATAT +#define __ARCH_WANT_COMPAT_SYS_SENDFILE #endif /* diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild new file mode 100644 index 000000000000..baebb3da1d44 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/Kbuild @@ -0,0 +1,3 @@ +# UAPI Header export list +include include/uapi/asm-generic/Kbuild.asm + diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 85b05c463fae..e8995727b1c1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -76,6 +76,7 @@ int main(void) DEFINE(SIGSEGV, SIGSEGV); DEFINE(NMI_MASK, NMI_MASK); DEFINE(THREAD_DSCR, offsetof(struct thread_struct, dscr)); + DEFINE(THREAD_DSCR_INHERIT, offsetof(struct thread_struct, dscr_inherit)); #else DEFINE(THREAD_INFO, offsetof(struct task_struct, stack)); #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index 5b25c8060fd6..a892680668d8 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -28,6 +28,8 @@ void doorbell_setup_this_cpu(void) void doorbell_cause_ipi(int cpu, unsigned long data) { + /* Order previous accesses vs. msgsnd, which is treated as a store */ + mb(); ppc_msgsnd(PPC_DBELL, 0, data); } diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 4b01a25e29ef..b40e0b4815b3 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -370,6 +370,12 @@ _GLOBAL(ret_from_fork) li r3,0 b syscall_exit + .section ".toc","aw" +DSCR_DEFAULT: + .tc dscr_default[TC],dscr_default + + .section ".text" + /* * This routine switches between two different tasks. The process * state of one is saved on its kernel stack. Then the state @@ -509,9 +515,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT) mr r1,r8 /* start using new stack pointer */ std r7,PACAKSAVE(r13) - ld r6,_CCR(r1) - mtcrf 0xFF,r6 - #ifdef CONFIG_ALTIVEC BEGIN_FTR_SECTION ld r0,THREAD_VRSAVE(r4) @@ -520,14 +523,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_PPC64 BEGIN_FTR_SECTION + lwz r6,THREAD_DSCR_INHERIT(r4) + ld r7,DSCR_DEFAULT@toc(2) ld r0,THREAD_DSCR(r4) - cmpd r0,r25 - beq 1f + cmpwi r6,0 + bne 1f + ld r0,0(r7) +1: cmpd r0,r25 + beq 2f mtspr SPRN_DSCR,r0 -1: +2: END_FTR_SECTION_IFSET(CPU_FTR_DSCR) #endif + ld r6,_CCR(r1) + mtcrf 0xFF,r6 + /* r3-r13 are destroyed -- Cort */ REST_8GPRS(14, r1) REST_10GPRS(22, r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e894515e77bb..39aa97d3ff88 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -186,7 +186,7 @@ hardware_interrupt_hv: KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800) MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer) - MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer) + STD_EXCEPTION_HV(0x980, 0x982, hdecrementer) STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a) KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00) @@ -486,6 +486,7 @@ machine_check_common: STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ) STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt) + STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt) STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception) STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception) STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception) diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index 7140d838339e..e11863f4e595 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -28,7 +28,9 @@ _GLOBAL(power7_idle) lwz r4,ADDROFF(powersave_nap)(r3) cmpwi 0,r4,0 beqlr + /* fall through */ +_GLOBAL(power7_nap) /* NAP is a state loss, we create a regs frame on the * stack, fill it up with the state we care about and * stick a pointer to it in PACAR1. We really only diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 2aa04f29e1de..43fea543d686 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -99,6 +99,26 @@ void pcibios_free_controller(struct pci_controller *phb) kfree(phb); } +/* + * The function is used to return the minimal alignment + * for memory or I/O windows of the associated P2P bridge. + * By default, 4KiB alignment for I/O windows and 1MiB for + * memory windows. + */ +resource_size_t pcibios_window_alignment(struct pci_bus *bus, + unsigned long type) +{ + if (ppc_md.pcibios_window_alignment) + return ppc_md.pcibios_window_alignment(bus, type); + + /* + * PCI core will figure out the default + * alignment: 4KiB for I/O and 1MiB for + * memory window. + */ + return 1; +} + static resource_size_t pcibios_io_size(const struct pci_controller *hose) { #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 710f400476de..e9cb51f5f801 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -514,9 +514,6 @@ struct task_struct *__switch_to(struct task_struct *prev, local_irq_save(flags); - account_system_vtime(current); - account_process_vtime(current); - /* * We can't take a PMU exception inside _switch() since there is a * window where the kernel stack SLB and the kernel stack are out @@ -802,16 +799,8 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, #endif /* CONFIG_PPC_STD_MMU_64 */ #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_DSCR)) { - if (current->thread.dscr_inherit) { - p->thread.dscr_inherit = 1; - p->thread.dscr = current->thread.dscr; - } else if (0 != dscr_default) { - p->thread.dscr_inherit = 1; - p->thread.dscr = dscr_default; - } else { - p->thread.dscr_inherit = 0; - p->thread.dscr = 0; - } + p->thread.dscr_inherit = current->thread.dscr_inherit; + p->thread.dscr = current->thread.dscr; } #endif diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0794a3017b1b..47834a3f4938 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -705,6 +705,7 @@ static void __init early_cmdline_parse(void) #endif #define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */ #define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */ +#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */ #define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */ /* Option Vector 6: IBM PAPR hints */ @@ -774,8 +775,7 @@ static unsigned char ibm_architecture_vec[] = { 0, 0, 0, - OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR, - + OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842, /* option vector 6: IBM PAPR hints */ 4 - 2, /* length */ 0, @@ -1624,6 +1624,63 @@ static void __init prom_instantiate_rtas(void) #ifdef CONFIG_PPC64 /* + * Allocate room for and instantiate Stored Measurement Log (SML) + */ +static void __init prom_instantiate_sml(void) +{ + phandle ibmvtpm_node; + ihandle ibmvtpm_inst; + u32 entry = 0, size = 0; + u64 base; + + prom_debug("prom_instantiate_sml: start...\n"); + + ibmvtpm_node = call_prom("finddevice", 1, 1, ADDR("/ibm,vtpm")); + prom_debug("ibmvtpm_node: %x\n", ibmvtpm_node); + if (!PHANDLE_VALID(ibmvtpm_node)) + return; + + ibmvtpm_inst = call_prom("open", 1, 1, ADDR("/ibm,vtpm")); + if (!IHANDLE_VALID(ibmvtpm_inst)) { + prom_printf("opening vtpm package failed (%x)\n", ibmvtpm_inst); + return; + } + + if (call_prom_ret("call-method", 2, 2, &size, + ADDR("sml-get-handover-size"), + ibmvtpm_inst) != 0 || size == 0) { + prom_printf("SML get handover size failed\n"); + return; + } + + base = alloc_down(size, PAGE_SIZE, 0); + if (base == 0) + prom_panic("Could not allocate memory for sml\n"); + + prom_printf("instantiating sml at 0x%x...", base); + + if (call_prom_ret("call-method", 4, 2, &entry, + ADDR("sml-handover"), + ibmvtpm_inst, size, base) != 0 || entry == 0) { + prom_printf("SML handover failed\n"); + return; + } + prom_printf(" done\n"); + + reserve_mem(base, size); + + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-base", + &base, sizeof(base)); + prom_setprop(ibmvtpm_node, "/ibm,vtpm", "linux,sml-size", + &size, sizeof(size)); + + prom_debug("sml base = 0x%x\n", base); + prom_debug("sml size = 0x%x\n", (long)size); + + prom_debug("prom_instantiate_sml: end...\n"); +} + +/* * Allocate room for and initialize TCE tables */ static void __init prom_initialize_tce_table(void) @@ -2916,6 +2973,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, prom_instantiate_opal(); #endif +#ifdef CONFIG_PPC64 + /* instantiate sml */ + prom_instantiate_sml(); +#endif + /* * On non-powermacs, put all CPUs in spin-loops. * diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 0321007086f7..8d4214afc21d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -198,8 +198,15 @@ void smp_muxed_ipi_message_pass(int cpu, int msg) struct cpu_messages *info = &per_cpu(ipi_message, cpu); char *message = (char *)&info->messages; + /* + * Order previous accesses before accesses in the IPI handler. + */ + smp_mb(); message[msg] = 1; - mb(); + /* + * cause_ipi functions are required to include a full barrier + * before doing whatever causes the IPI. + */ smp_ops->cause_ipi(cpu, info->data); } @@ -211,7 +218,7 @@ irqreturn_t smp_ipi_demux(void) mb(); /* order any irq clear */ do { - all = xchg_local(&info->messages, 0); + all = xchg(&info->messages, 0); #ifdef __BIG_ENDIAN if (all & (1 << (24 - 8 * PPC_MSG_CALL_FUNCTION))) diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 81c570633ead..abd1112da54f 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -143,48 +143,17 @@ long compat_sys_ipc(u32 call, u32 first, u32 second, u32 third, compat_uptr_t pt * proper conversion (sign extension) between the register representation of a signed int (msr in 32-bit mode) * and the register representation of a signed int (msr in 64-bit mode) is performed. */ -asmlinkage long compat_sys_sendfile(u32 out_fd, u32 in_fd, compat_off_t __user * offset, u32 count) +asmlinkage long compat_sys_sendfile_wrapper(u32 out_fd, u32 in_fd, + compat_off_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - off_t of; - off_t __user *up; - - if (offset && get_user(of, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (off_t __user *) &of : NULL; - ret = sys_sendfile((int)out_fd, (int)in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(of, offset)) - return -EFAULT; - - return ret; + return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count); } -asmlinkage int compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, s32 count) +asmlinkage long compat_sys_sendfile64_wrapper(u32 out_fd, u32 in_fd, + compat_loff_t __user *offset, u32 count) { - mm_segment_t old_fs = get_fs(); - int ret; - loff_t lof; - loff_t __user *up; - - if (offset && get_user(lof, offset)) - return -EFAULT; - - /* The __user pointer cast is valid because of the set_fs() */ - set_fs(KERNEL_DS); - up = offset ? (loff_t __user *) &lof : NULL; - ret = sys_sendfile64(out_fd, in_fd, up, count); - set_fs(old_fs); - - if (offset && put_user(lof, offset)) - return -EFAULT; - - return ret; + return sys_sendfile((int)out_fd, (int)in_fd, + (off_t __user *)offset, count); } long compat_sys_execve(unsigned long a0, unsigned long a1, unsigned long a2, diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 3529446c2abd..8302af649219 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -194,6 +194,14 @@ static ssize_t show_dscr_default(struct device *dev, return sprintf(buf, "%lx\n", dscr_default); } +static void update_dscr(void *dummy) +{ + if (!current->thread.dscr_inherit) { + current->thread.dscr = dscr_default; + mtspr(SPRN_DSCR, dscr_default); + } +} + static ssize_t __used store_dscr_default(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -206,6 +214,8 @@ static ssize_t __used store_dscr_default(struct device *dev, return -EINVAL; dscr_default = val; + on_each_cpu(update_dscr, NULL, 1); + return count; } diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index be171ee73bf8..eaa9d0e6abca 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -291,13 +291,12 @@ static inline u64 calculate_stolen_time(u64 stop_tb) * Account time for a transition between system, hard irq * or soft irq state. */ -void account_system_vtime(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk, + u64 *sys_scaled, u64 *stolen) { - u64 now, nowscaled, delta, deltascaled; - unsigned long flags; - u64 stolen, udelta, sys_scaled, user_scaled; + u64 now, nowscaled, deltascaled; + u64 udelta, delta, user_scaled; - local_irq_save(flags); now = mftb(); nowscaled = read_spurr(now); get_paca()->system_time += now - get_paca()->starttime; @@ -305,7 +304,7 @@ void account_system_vtime(struct task_struct *tsk) deltascaled = nowscaled - get_paca()->startspurr; get_paca()->startspurr = nowscaled; - stolen = calculate_stolen_time(now); + *stolen = calculate_stolen_time(now); delta = get_paca()->system_time; get_paca()->system_time = 0; @@ -322,35 +321,45 @@ void account_system_vtime(struct task_struct *tsk) * the user ticks get saved up in paca->user_time_scaled to be * used by account_process_tick. */ - sys_scaled = delta; + *sys_scaled = delta; user_scaled = udelta; if (deltascaled != delta + udelta) { if (udelta) { - sys_scaled = deltascaled * delta / (delta + udelta); - user_scaled = deltascaled - sys_scaled; + *sys_scaled = deltascaled * delta / (delta + udelta); + user_scaled = deltascaled - *sys_scaled; } else { - sys_scaled = deltascaled; + *sys_scaled = deltascaled; } } get_paca()->user_time_scaled += user_scaled; - if (in_interrupt() || idle_task(smp_processor_id()) != tsk) { - account_system_time(tsk, 0, delta, sys_scaled); - if (stolen) - account_steal_time(stolen); - } else { - account_idle_time(delta + stolen); - } - local_irq_restore(flags); + return delta; +} + +void vtime_account_system(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_system_time(tsk, 0, delta, sys_scaled); + if (stolen) + account_steal_time(stolen); +} + +void vtime_account_idle(struct task_struct *tsk) +{ + u64 delta, sys_scaled, stolen; + + delta = vtime_delta(tsk, &sys_scaled, &stolen); + account_idle_time(delta + stolen); } -EXPORT_SYMBOL_GPL(account_system_vtime); /* * Transfer the user and system times accumulated in the paca * by the exception entry and exit code to the generic process * user and system time records. * Must be called with interrupts disabled. - * Assumes that account_system_vtime() has been called recently + * Assumes that vtime_account() has been called recently * (i.e. since the last entry from usermode) so that * get_paca()->user_time_scaled is up to date. */ @@ -366,6 +375,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick) account_user_time(tsk, utime, utimescaled); } +void vtime_task_switch(struct task_struct *prev) +{ + vtime_account(prev); + account_process_tick(prev, 0); +} + #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */ #define calc_cputime_factors() #endif @@ -535,6 +550,15 @@ void timer_interrupt(struct pt_regs * regs) trace_timer_interrupt_exit(regs); } +/* + * Hypervisor decrementer interrupts shouldn't occur but are sometimes + * left pending on exit from a KVM guest. We don't need to do anything + * to clear them, as they are edge-triggered. + */ +void hdec_interrupt(struct pt_regs *regs) +{ +} + #ifdef CONFIG_SUSPEND static void generic_suspend_disable_irqs(void) { diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 158972341a2d..ae0843fa7a61 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -972,8 +972,9 @@ static int emulate_instruction(struct pt_regs *regs) cpu_has_feature(CPU_FTR_DSCR)) { PPC_WARN_EMULATED(mtdscr, regs); rd = (instword >> 21) & 0x1f; - mtspr(SPRN_DSCR, regs->gpr[rd]); + current->thread.dscr = regs->gpr[rd]; current->thread.dscr_inherit = 1; + mtspr(SPRN_DSCR, current->thread.dscr); return 0; } #endif diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index dd223b3eb333..17e5b2364312 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -20,7 +20,7 @@ int patch_instruction(unsigned int *addr, unsigned int instr) { int err; - err = __put_user(instr, addr); + __put_user_size(instr, addr, 4, err); if (err) return err; asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr)); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 08ffcf52a856..e5f028b5794e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -470,7 +470,7 @@ bad_area_nosemaphore: 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, current_uid()); + address, from_kuid(&init_user_ns, current_uid())); return SIGSEGV; diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 39b159751c35..59213cfaeca9 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,11 +1436,11 @@ static long vphn_get_associativity(unsigned long cpu, /* * Update the node maps and sysfs entries for each cpu whose home node - * has changed. + * has changed. Returns 1 when the topology has changed, and 0 otherwise. */ int arch_update_cpu_topology(void) { - int cpu, nid, old_nid; + int cpu, nid, old_nid, changed = 0; unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0}; struct device *dev; @@ -1466,9 +1466,10 @@ int arch_update_cpu_topology(void) dev = get_cpu_device(cpu); if (dev) kobject_uevent(&dev->kobj, KOBJ_CHANGE); + changed = 1; } - return 1; + return changed; } static void topology_work_fn(struct work_struct *work) diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c index 1a046715e461..1d769a29249f 100644 --- a/arch/powerpc/platforms/83xx/suspend.c +++ b/arch/powerpc/platforms/83xx/suspend.c @@ -326,7 +326,7 @@ static int pmc_probe(struct platform_device *ofdev) const struct of_device_id *match; struct device_node *np = ofdev->dev.of_node; struct resource res; - struct pmc_type *type; + const struct pmc_type *type; int ret = 0; match = of_match_device(pmc_match, &ofdev->dev); diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 30fd01de6bed..72afd2888cad 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -1,6 +1,7 @@ config PPC64 bool "64-bit kernel" default n + select HAVE_VIRT_CPU_ACCOUNTING help This option selects whether a 32-bit or a 64-bit kernel will be built. @@ -337,21 +338,6 @@ config PPC_MM_SLICES default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES) default n -config VIRT_CPU_ACCOUNTING - bool "Deterministic task and CPU time accounting" - depends on PPC64 - default y - help - Select this option to enable more accurate task and CPU time - accounting. This is done by reading a CPU counter on each - kernel entry and exit and on transitions within the kernel - between system, softirq and hardirq state, so there is a - small performance impact. This also enables accounting of - stolen time on logically-partitioned systems running on - IBM POWER5-based machines. - - If in doubt, say Y here. - config PPC_HAVE_PMU_SUPPORT bool diff --git a/arch/powerpc/platforms/cell/celleb_pci.c b/arch/powerpc/platforms/cell/celleb_pci.c index 5822141aa63f..abc8af43ea7c 100644 --- a/arch/powerpc/platforms/cell/celleb_pci.c +++ b/arch/powerpc/platforms/cell/celleb_pci.c @@ -472,7 +472,7 @@ int __init celleb_setup_phb(struct pci_controller *phb) { struct device_node *dev = phb->dn; const struct of_device_id *match; - struct celleb_phb_spec *phb_spec; + const struct celleb_phb_spec *phb_spec; int rc; match = of_match_node(celleb_phb_match, dev); diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 23bc9db4317e..82607d621aca 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -76,7 +76,7 @@ static void spu_gov_work(struct work_struct *work) static void spu_gov_init_work(struct spu_gov_info_struct *info) { int delay = usecs_to_jiffies(info->poll_int); - INIT_DELAYED_WORK_DEFERRABLE(&info->work, spu_gov_work); + INIT_DEFERRABLE_WORK(&info->work, spu_gov_work); schedule_delayed_work_on(info->policy->cpu, &info->work, delay); } diff --git a/arch/powerpc/platforms/cell/spu_syscalls.c b/arch/powerpc/platforms/cell/spu_syscalls.c index 714bbfc3162c..db4e638cf408 100644 --- a/arch/powerpc/platforms/cell/spu_syscalls.c +++ b/arch/powerpc/platforms/cell/spu_syscalls.c @@ -69,8 +69,6 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, umode_t, mode, int, neighbor_fd) { long ret; - struct file *neighbor; - int fput_needed; struct spufs_calls *calls; calls = spufs_calls_get(); @@ -78,11 +76,11 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, return -ENOSYS; if (flags & SPU_CREATE_AFFINITY_SPU) { + struct fd neighbor = fdget(neighbor_fd); ret = -EBADF; - neighbor = fget_light(neighbor_fd, &fput_needed); - if (neighbor) { - ret = calls->create_thread(name, flags, mode, neighbor); - fput_light(neighbor, fput_needed); + if (neighbor.file) { + ret = calls->create_thread(name, flags, mode, neighbor.file); + fdput(neighbor); } } else ret = calls->create_thread(name, flags, mode, NULL); @@ -94,8 +92,7 @@ SYSCALL_DEFINE4(spu_create, const char __user *, name, unsigned int, flags, asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus) { long ret; - struct file *filp; - int fput_needed; + struct fd arg; struct spufs_calls *calls; calls = spufs_calls_get(); @@ -103,10 +100,10 @@ asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, __u32 __user *ustatus) return -ENOSYS; ret = -EBADF; - filp = fget_light(fd, &fput_needed); - if (filp) { - ret = calls->spu_run(filp, unpc, ustatus); - fput_light(filp, fput_needed); + arg = fdget(fd); + if (arg.file) { + ret = calls->spu_run(arg.file, unpc, ustatus); + fdput(arg); } spufs_calls_put(calls); diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index c2c5b078ba80..657e3f233a64 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -106,6 +106,17 @@ static int spufs_ctx_note_size(struct spu_context *ctx, int dfd) return total; } +static int match_context(const void *v, struct file *file, unsigned fd) +{ + struct spu_context *ctx; + if (file->f_op != &spufs_context_fops) + return 0; + ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx; + if (ctx->flags & SPU_CREATE_NOSCHED) + return 0; + return fd + 1; +} + /* * The additional architecture-specific notes for Cell are various * context files in the spu context. @@ -115,29 +126,18 @@ static int spufs_ctx_note_size(struct spu_context *ctx, int dfd) * internal functionality to dump them without needing to actually * open the files. */ +/* + * descriptor table is not shared, so files can't change or go away. + */ static struct spu_context *coredump_next_context(int *fd) { - struct fdtable *fdt = files_fdtable(current->files); struct file *file; - struct spu_context *ctx = NULL; - - for (; *fd < fdt->max_fds; (*fd)++) { - if (!fd_is_open(*fd, fdt)) - continue; - - file = fcheck(*fd); - - if (!file || file->f_op != &spufs_context_fops) - continue; - - ctx = SPUFS_I(file->f_dentry->d_inode)->i_ctx; - if (ctx->flags & SPU_CREATE_NOSCHED) - continue; - - break; - } - - return ctx; + int n = iterate_fd(current->files, *fd, match_context, NULL); + if (!n) + return NULL; + *fd = n - 1; + file = fcheck(*fd); + return SPUFS_I(file->f_dentry->d_inode)->i_ctx; } int spufs_coredump_extra_notes_size(void) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 9cda6a1ad0cf..0e7eccc0f88d 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -855,7 +855,7 @@ static void __devinit pnv_ioda_setup_PEs(struct pci_bus *bus) if (pe == NULL) continue; /* Leaving the PCIe domain ... single PE# */ - if (dev->pcie_type == PCI_EXP_TYPE_PCI_BRIDGE) + if (pci_pcie_type(dev) == PCI_EXP_TYPE_PCI_BRIDGE) pnv_ioda_setup_bus_PE(dev, pe); else if (dev->subordinate) pnv_ioda_setup_PEs(dev->subordinate); @@ -1139,6 +1139,44 @@ static void __devinit pnv_pci_ioda_fixup_phb(struct pci_controller *hose) } } +/* + * Returns the alignment for I/O or memory windows for P2P + * bridges. That actually depends on how PEs are segmented. + * For now, we return I/O or M32 segment size for PE sensitive + * P2P bridges. Otherwise, the default values (4KiB for I/O, + * 1MiB for memory) will be returned. + * + * The current PCI bus might be put into one PE, which was + * create against the parent PCI bridge. For that case, we + * needn't enlarge the alignment so that we can save some + * resources. + */ +static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, + unsigned long type) +{ + struct pci_dev *bridge; + struct pci_controller *hose = pci_bus_to_host(bus); + struct pnv_phb *phb = hose->private_data; + int num_pci_bridges = 0; + + bridge = bus->self; + while (bridge) { + if (pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE) { + num_pci_bridges++; + if (num_pci_bridges >= 2) + return 1; + } + + bridge = bridge->bus->self; + } + + /* We need support prefetchable memory window later */ + if (type & IORESOURCE_MEM) + return phb->ioda.m32_segsize; + + return phb->ioda.io_segsize; +} + /* Prevent enabling devices for which we couldn't properly * assign a PE */ @@ -1306,6 +1344,7 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np) */ ppc_md.pcibios_fixup_phb = pnv_pci_ioda_fixup_phb; ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook; + ppc_md.pcibios_window_alignment = pnv_pci_window_alignment; pci_add_flags(PCI_PROBE_ONLY | PCI_REASSIGN_ALL_RSRC); /* Reset IODA tables to a clean state */ diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 3ef46254c35b..7698b6e13c57 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -106,14 +106,6 @@ static void pnv_smp_cpu_kill_self(void) { unsigned int cpu; - /* If powersave_nap is enabled, use NAP mode, else just - * spin aimlessly - */ - if (!powersave_nap) { - generic_mach_cpu_die(); - return; - } - /* Standard hot unplug procedure */ local_irq_disable(); idle_task_exit(); @@ -128,7 +120,7 @@ static void pnv_smp_cpu_kill_self(void) */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); while (!generic_check_cpu_restart(cpu)) { - power7_idle(); + power7_nap(); if (!generic_check_cpu_restart(cpu)) { DBG("CPU%d Unexpected exit while offline !\n", cpu); /* We may be getting an IPI, so we re-enable diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 7e2b2f2e3ecd..63c5f04ea580 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -371,7 +371,7 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev) int err, i, j, irq_index, count; int rc; const u32 *p; - struct fsl_msi_feature *features; + const struct fsl_msi_feature *features; int len; u32 offset; static const u32 all_avail[] = { 0, NR_MSI_IRQS }; @@ -505,16 +505,16 @@ static const struct fsl_msi_feature vmpic_msi_feature = { static const struct of_device_id fsl_of_msi_ids[] = { { .compatible = "fsl,mpic-msi", - .data = (void *)&mpic_msi_feature, + .data = &mpic_msi_feature, }, { .compatible = "fsl,ipic-msi", - .data = (void *)&ipic_msi_feature, + .data = &ipic_msi_feature, }, #ifdef CONFIG_EPAPR_PARAVIRT { .compatible = "fsl,vmpic-msi", - .data = (void *)&vmpic_msi_feature, + .data = &vmpic_msi_feature, }, #endif {} diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index 14469cf9df68..df0fc5821469 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -65,7 +65,11 @@ static inline void icp_hv_set_xirr(unsigned int value) static inline void icp_hv_set_qirr(int n_cpu , u8 value) { int hw_cpu = get_hard_smp_processor_id(n_cpu); - long rc = plpar_hcall_norets(H_IPI, hw_cpu, value); + long rc; + + /* Make sure all previous accesses are ordered before IPI sending */ + mb(); + rc = plpar_hcall_norets(H_IPI, hw_cpu, value); if (rc != H_SUCCESS) { pr_err("%s: bad return code qirr cpu=%d hw_cpu=%d mfrr=0x%x " "returned %ld\n", __func__, n_cpu, hw_cpu, value, rc); |