diff options
Diffstat (limited to 'arch/powerpc')
29 files changed, 1793 insertions, 93 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5dbd375a3f2..0df57466e78 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -320,6 +320,10 @@ config HOTPLUG_CPU Say N if you are unsure. +config ARCH_CPU_PROBE_RELEASE + def_bool y + depends on HOTPLUG_CPU + config ARCH_ENABLE_MEMORY_HOTPLUG def_bool y diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h index c9ca97f43bc..81f3b0b5601 100644 --- a/arch/powerpc/include/asm/kvm.h +++ b/arch/powerpc/include/asm/kvm.h @@ -47,7 +47,23 @@ struct kvm_regs { struct kvm_sregs { __u32 pvr; - char pad[1020]; + union { + struct { + __u64 sdr1; + struct { + struct { + __u64 slbe; + __u64 slbv; + } slb[64]; + } ppc64; + struct { + __u32 sr[16]; + __u64 ibat[8]; + __u64 dbat[8]; + } ppc32; + } s; + __u8 pad[1020]; + } u; }; struct kvm_fpu { diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 19ddb352fd0..af2abe74f54 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -87,6 +87,7 @@ #define BOOK3S_IRQPRIO_MAX 16 #define BOOK3S_HFLAG_DCBZ32 0x1 +#define BOOK3S_HFLAG_SLB 0x2 #define RESUME_FLAG_NV (1<<0) /* Reload guest nonvolatile state? */ #define RESUME_FLAG_HOST (1<<1) /* Resume host? */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index c6011336371..74b7369770d 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -46,6 +46,7 @@ struct kvmppc_sr { }; struct kvmppc_bat { + u64 raw; u32 bepi; u32 bepi_mask; bool vs; @@ -113,6 +114,8 @@ extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, boo extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, bool data); extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr); extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec); +extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, + bool upper, u32 val); extern u32 kvmppc_trampoline_lowmem; extern u32 kvmppc_trampoline_enter; diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 9efa2be7833..9f0fc9e6ce0 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -266,6 +266,11 @@ struct machdep_calls { void (*suspend_disable_irqs)(void); void (*suspend_enable_irqs)(void); #endif + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + ssize_t (*cpu_probe)(const char *, size_t); + ssize_t (*cpu_release)(const char *, size_t); +#endif }; extern void e500_idle(void); diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h index 079c06eae44..a062c57696d 100644 --- a/arch/powerpc/include/asm/macio.h +++ b/arch/powerpc/include/asm/macio.h @@ -39,6 +39,7 @@ struct macio_dev struct macio_bus *bus; /* macio bus this device is on */ struct macio_dev *media_bay; /* Device is part of a media bay */ struct of_device ofdev; + struct device_dma_parameters dma_parms; /* ide needs that */ int n_resources; struct resource resource[MACIO_DEV_COUNT_RESOURCES]; int n_interrupts; @@ -78,6 +79,8 @@ static inline unsigned long macio_resource_len(struct macio_dev *dev, int resour return res->end - res->start + 1; } +extern int macio_enable_devres(struct macio_dev *dev); + extern int macio_request_resource(struct macio_dev *dev, int resource_no, const char *name); extern void macio_release_resource(struct macio_dev *dev, int resource_no); extern int macio_request_resources(struct macio_dev *dev, const char *name); @@ -131,6 +134,9 @@ struct macio_driver int (*resume)(struct macio_dev* dev); int (*shutdown)(struct macio_dev* dev); +#ifdef CONFIG_PMAC_MEDIABAY + void (*mediabay_event)(struct macio_dev* dev, int mb_state); +#endif struct device_driver driver; }; #define to_macio_driver(drv) container_of(drv,struct macio_driver, driver) diff --git a/arch/powerpc/include/asm/mediabay.h b/arch/powerpc/include/asm/mediabay.h index b2efb332580..11037a4133e 100644 --- a/arch/powerpc/include/asm/mediabay.h +++ b/arch/powerpc/include/asm/mediabay.h @@ -17,26 +17,31 @@ #define MB_POWER 6 /* media bay contains a Power device (???) */ #define MB_NO 7 /* media bay contains nothing */ -/* Number of bays in the machine or 0 */ -extern int media_bay_count; +struct macio_dev; -#ifdef CONFIG_BLK_DEV_IDE_PMAC -#include <linux/ide.h> +#ifdef CONFIG_PMAC_MEDIABAY -int check_media_bay_by_base(unsigned long base, int what); -/* called by IDE PMAC host driver to register IDE controller for media bay */ -int media_bay_set_ide_infos(struct device_node *which_bay, unsigned long base, - int irq, ide_hwif_t *hwif); +/* Check the content type of the bay, returns MB_NO if the bay is still + * transitionning + */ +extern int check_media_bay(struct macio_dev *bay); -int check_media_bay(struct device_node *which_bay, int what); +/* The ATA driver uses the calls below to temporarily hold on the + * media bay callbacks while initializing the interface + */ +extern void lock_media_bay(struct macio_dev *bay); +extern void unlock_media_bay(struct macio_dev *bay); #else -static inline int check_media_bay(struct device_node *which_bay, int what) +static inline int check_media_bay(struct macio_dev *bay) { - return -ENODEV; + return MB_NO; } +static inline void lock_media_bay(struct macio_dev *bay) { } +static inline void unlock_media_bay(struct macio_dev *bay) { } + #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h index 7514ec2f854..2102b214a87 100644 --- a/arch/powerpc/include/asm/mmu-hash64.h +++ b/arch/powerpc/include/asm/mmu-hash64.h @@ -373,6 +373,38 @@ extern void slb_set_size(u16 size); #ifndef __ASSEMBLY__ +#ifdef CONFIG_PPC_SUBPAGE_PROT +/* + * For the sub-page protection option, we extend the PGD with one of + * these. Basically we have a 3-level tree, with the top level being + * the protptrs array. To optimize speed and memory consumption when + * only addresses < 4GB are being protected, pointers to the first + * four pages of sub-page protection words are stored in the low_prot + * array. + * Each page of sub-page protection words protects 1GB (4 bytes + * protects 64k). For the 3-level tree, each page of pointers then + * protects 8TB. + */ +struct subpage_prot_table { + unsigned long maxaddr; /* only addresses < this are protected */ + unsigned int **protptrs[2]; + unsigned int *low_prot[4]; +}; + +#define SBP_L1_BITS (PAGE_SHIFT - 2) +#define SBP_L2_BITS (PAGE_SHIFT - 3) +#define SBP_L1_COUNT (1 << SBP_L1_BITS) +#define SBP_L2_COUNT (1 << SBP_L2_BITS) +#define SBP_L2_SHIFT (PAGE_SHIFT + SBP_L1_BITS) +#define SBP_L3_SHIFT (SBP_L2_SHIFT + SBP_L2_BITS) + +extern void subpage_prot_free(struct mm_struct *mm); +extern void subpage_prot_init_new_context(struct mm_struct *mm); +#else +static inline void subpage_prot_free(struct mm_struct *mm) {} +static inline void subpage_prot_init_new_context(struct mm_struct *mm) { } +#endif /* CONFIG_PPC_SUBPAGE_PROT */ + typedef unsigned long mm_context_id_t; typedef struct { @@ -386,6 +418,9 @@ typedef struct { u16 sllp; /* SLB page size encoding */ #endif unsigned long vdso_base; +#ifdef CONFIG_PPC_SUBPAGE_PROT + struct subpage_prot_table spt; +#endif /* CONFIG_PPC_SUBPAGE_PROT */ } mm_context_t; diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h index 1b4f697abbd..b664ce79a17 100644 --- a/arch/powerpc/include/asm/mpc52xx.h +++ b/arch/powerpc/include/asm/mpc52xx.h @@ -276,6 +276,53 @@ extern int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv); extern unsigned int mpc52xx_get_xtal_freq(struct device_node *node); extern void mpc52xx_restart(char *cmd); +/* mpc52xx_gpt.c */ +struct mpc52xx_gpt_priv; +extern struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq); +extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period, + int continuous); +extern u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt); +extern int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt); + +/* mpc52xx_lpbfifo.c */ +#define MPC52XX_LPBFIFO_FLAG_READ (0) +#define MPC52XX_LPBFIFO_FLAG_WRITE (1<<0) +#define MPC52XX_LPBFIFO_FLAG_NO_INCREMENT (1<<1) +#define MPC52XX_LPBFIFO_FLAG_NO_DMA (1<<2) +#define MPC52XX_LPBFIFO_FLAG_POLL_DMA (1<<3) + +struct mpc52xx_lpbfifo_request { + struct list_head list; + + /* localplus bus address */ + unsigned int cs; + size_t offset; + + /* Memory address */ + void *data; + phys_addr_t data_phys; + + /* Details of transfer */ + size_t size; + size_t pos; /* current position of transfer */ + int flags; + + /* What to do when finished */ + void (*callback)(struct mpc52xx_lpbfifo_request *); + + void *priv; /* Driver private data */ + + /* statistics */ + int irq_count; + int irq_ticks; + u8 last_byte; + int buffer_not_done_cnt; +}; + +extern int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req); +extern void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req); +extern void mpc52xx_lpbfifo_poll(void); + /* mpc52xx_pic.c */ extern void mpc52xx_init_irq(void); extern unsigned int mpc52xx_get_irq(void); diff --git a/arch/powerpc/include/asm/pSeries_reconfig.h b/arch/powerpc/include/asm/pSeries_reconfig.h index e482e5352e6..d4b4bfa26fb 100644 --- a/arch/powerpc/include/asm/pSeries_reconfig.h +++ b/arch/powerpc/include/asm/pSeries_reconfig.h @@ -17,6 +17,7 @@ #ifdef CONFIG_PPC_PSERIES extern int pSeries_reconfig_notifier_register(struct notifier_block *); extern void pSeries_reconfig_notifier_unregister(struct notifier_block *); +extern struct blocking_notifier_head pSeries_reconfig_chain; #else /* !CONFIG_PPC_PSERIES */ static inline int pSeries_reconfig_notifier_register(struct notifier_block *nb) { diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h index 5c1cd73dafa..605f5c5398d 100644 --- a/arch/powerpc/include/asm/pgalloc-64.h +++ b/arch/powerpc/include/asm/pgalloc-64.h @@ -28,10 +28,6 @@ */ #define MAX_PGTABLE_INDEX_SIZE 0xf -#ifndef CONFIG_PPC_SUBPAGE_PROT -static inline void subpage_prot_free(pgd_t *pgd) {} -#endif - extern struct kmem_cache *pgtable_cache[]; #define PGT_CACHE(shift) (pgtable_cache[(shift)-1]) @@ -42,7 +38,6 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - subpage_prot_free(pgd); kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd); } diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h index 82b72207c51..c4490f9c67c 100644 --- a/arch/powerpc/include/asm/pte-hash64-64k.h +++ b/arch/powerpc/include/asm/pte-hash64-64k.h @@ -76,41 +76,4 @@ remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, \ __pgprot(pgprot_val((prot)) | _PAGE_4K_PFN)) - -#ifdef CONFIG_PPC_SUBPAGE_PROT -/* - * For the sub-page protection option, we extend the PGD with one of - * these. Basically we have a 3-level tree, with the top level being - * the protptrs array. To optimize speed and memory consumption when - * only addresses < 4GB are being protected, pointers to the first - * four pages of sub-page protection words are stored in the low_prot - * array. - * Each page of sub-page protection words protects 1GB (4 bytes - * protects 64k). For the 3-level tree, each page of pointers then - * protects 8TB. - */ -struct subpage_prot_table { - unsigned long maxaddr; /* only addresses < this are protected */ - unsigned int **protptrs[2]; - unsigned int *low_prot[4]; -}; - -#undef PGD_TABLE_SIZE -#define PGD_TABLE_SIZE ((sizeof(pgd_t) << PGD_INDEX_SIZE) + \ - sizeof(struct subpage_prot_table)) - -#define SBP_L1_BITS (PAGE_SHIFT - 2) -#define SBP_L2_BITS (PAGE_SHIFT - 3) -#define SBP_L1_COUNT (1 << SBP_L1_BITS) -#define SBP_L2_COUNT (1 << SBP_L2_BITS) -#define SBP_L2_SHIFT (PAGE_SHIFT + SBP_L1_BITS) -#define SBP_L3_SHIFT (SBP_L2_SHIFT + SBP_L2_BITS) - -extern void subpage_prot_free(pgd_t *pgd); - -static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd) -{ - return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD); -} -#endif /* CONFIG_PPC_SUBPAGE_PROT */ #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c index 1882bf419fa..8dc7547c237 100644 --- a/arch/powerpc/kernel/io.c +++ b/arch/powerpc/kernel/io.c @@ -161,7 +161,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src, dest++; n--; } - while(n > 4) { + while(n >= 4) { *((u32 *)dest) = *((volatile u32 *)vsrc); eieio(); vsrc += 4; @@ -190,7 +190,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n) vdest++; n--; } - while(n > 4) { + while(n >= 4) { *((volatile u32 *)vdest) = *((volatile u32 *)src); src += 4; vdest += 4; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9b86a74d281..97196eefef3 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -218,6 +218,9 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) static void stop_this_cpu(void *dummy) { + /* Remove this CPU */ + set_cpu_online(smp_processor_id(), false); + local_irq_disable(); while (1) ; diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 956ab33fd73..e235e52dc4f 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -461,6 +461,25 @@ static void unregister_cpu_online(unsigned int cpu) cacheinfo_cpu_offline(cpu); } + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE +ssize_t arch_cpu_probe(const char *buf, size_t count) +{ + if (ppc_md.cpu_probe) + return ppc_md.cpu_probe(buf, count); + + return -EINVAL; +} + +ssize_t arch_cpu_release(const char *buf, size_t count) +{ + if (ppc_md.cpu_release) + return ppc_md.cpu_release(buf, count); + + return -EINVAL; +} +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ + #endif /* CONFIG_HOTPLUG_CPU */ static int __cpuinit sysfs_cpu_notify(struct notifier_block *self, diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 42037d46a41..3e294bd9b8c 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -281,6 +281,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu) void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr) { + vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB; vcpu->arch.pvr = pvr; if ((pvr >= 0x330000) && (pvr < 0x70330000)) { kvmppc_mmu_book3s_64_init(vcpu); @@ -762,14 +763,62 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int i; + sregs->pvr = vcpu->arch.pvr; + + sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1; + if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { + for (i = 0; i < 64; i++) { + sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i; + sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv; + } + } else { + for (i = 0; i < 16; i++) { + sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw; + sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw; + } + for (i = 0; i < 8; i++) { + sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw; + sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw; + } + } return 0; } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { + struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu); + int i; + kvmppc_set_pvr(vcpu, sregs->pvr); + + vcpu3s->sdr1 = sregs->u.s.sdr1; + if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) { + for (i = 0; i < 64; i++) { + vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv, + sregs->u.s.ppc64.slb[i].slbe); + } + } else { + for (i = 0; i < 16; i++) { + vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]); + } + for (i = 0; i < 8; i++) { + kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false, + (u32)sregs->u.s.ppc32.ibat[i]); + kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true, + (u32)(sregs->u.s.ppc32.ibat[i] >> 32)); + kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false, + (u32)sregs->u.s.ppc32.dbat[i]); + kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true, + (u32)(sregs->u.s.ppc32.dbat[i] >> 32)); + } + } + + /* Flush the MMU after messing with the segments */ + kvmppc_mmu_pte_flush(vcpu, 0, 0); return 0; } diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_64_emulate.c index c343e67306e..1027eac6d47 100644 --- a/arch/powerpc/kvm/book3s_64_emulate.c +++ b/arch/powerpc/kvm/book3s_64_emulate.c @@ -185,7 +185,27 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu, return emulated; } -static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u64 val) +void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper, + u32 val) +{ + if (upper) { + /* Upper BAT */ + u32 bl = (val >> 2) & 0x7ff; + bat->bepi_mask = (~bl << 17); + bat->bepi = val & 0xfffe0000; + bat->vs = (val & 2) ? 1 : 0; + bat->vp = (val & 1) ? 1 : 0; + bat->raw = (bat->raw & 0xffffffff00000000ULL) | val; + } else { + /* Lower BAT */ + bat->brpn = val & 0xfffe0000; + bat->wimg = (val >> 3) & 0xf; + bat->pp = val & 3; + bat->raw = (bat->raw & 0x00000000ffffffffULL) | ((u64)val << 32); + } +} + +static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val) { struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); struct kvmppc_bat *bat; @@ -207,19 +227,7 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u64 val) BUG(); } - if (!(sprn % 2)) { - /* Upper BAT */ - u32 bl = (val >> 2) & 0x7ff; - bat->bepi_mask = (~bl << 17); - bat->bepi = val & 0xfffe0000; - bat->vs = (val & 2) ? 1 : 0; - bat->vp = (val & 1) ? 1 : 0; - } else { - /* Lower BAT */ - bat->brpn = val & 0xfffe0000; - bat->wimg = (val >> 3) & 0xf; - bat->pp = val & 3; - } + kvmppc_set_bat(vcpu, bat, !(sprn % 2), val); } int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) @@ -243,7 +251,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs) case SPRN_IBAT4U ... SPRN_IBAT7L: case SPRN_DBAT0U ... SPRN_DBAT3L: case SPRN_DBAT4U ... SPRN_DBAT7L: - kvmppc_write_bat(vcpu, sprn, vcpu->arch.gpr[rs]); + kvmppc_write_bat(vcpu, sprn, (u32)vcpu->arch.gpr[rs]); /* BAT writes happen so rarely that we're ok to flush * everything here */ kvmppc_mmu_pte_flush(vcpu, 0, 0); diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index a31f9c677d2..5598f88f142 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -473,4 +473,6 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu) mmu->esid_to_vsid = kvmppc_mmu_book3s_64_esid_to_vsid; mmu->ea_to_vp = kvmppc_mmu_book3s_64_ea_to_vp; mmu->is_dcbz32 = kvmppc_mmu_book3s_64_is_dcbz32; + + vcpu->arch.hflags |= BOOK3S_HFLAG_SLB; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 692c3709011..d82551efbfb 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -144,6 +144,9 @@ int kvm_dev_ioctl_check_extension(long ext) int r; switch (ext) { + case KVM_CAP_PPC_SEGSTATE: + r = 1; + break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 6810128aba3..50f867d657d 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -835,9 +835,9 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr) * Result is 0: full permissions, _PAGE_RW: read-only, * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access. */ -static int subpage_protection(pgd_t *pgdir, unsigned long ea) +static int subpage_protection(struct mm_struct *mm, unsigned long ea) { - struct subpage_prot_table *spt = pgd_subpage_prot(pgdir); + struct subpage_prot_table *spt = &mm->context.spt; u32 spp = 0; u32 **sbpm, *sbpp; @@ -865,7 +865,7 @@ static int subpage_protection(pgd_t *pgdir, unsigned long ea) } #else /* CONFIG_PPC_SUBPAGE_PROT */ -static inline int subpage_protection(pgd_t *pgdir, unsigned long ea) +static inline int subpage_protection(struct mm_struct *mm, unsigned long ea) { return 0; } diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c index b9e4cc2c205..b910d37aea1 100644 --- a/arch/powerpc/mm/mmu_context_hash64.c +++ b/arch/powerpc/mm/mmu_context_hash64.c @@ -76,6 +76,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) */ if (slice_mm_new_context(mm)) slice_set_user_psize(mm, mmu_virtual_psize); + subpage_prot_init_new_context(mm); mm->context.id = index; return 0; @@ -92,5 +93,6 @@ EXPORT_SYMBOL_GPL(__destroy_context); void destroy_context(struct mm_struct *mm) { __destroy_context(mm->context.id); + subpage_prot_free(mm); mm->context.id = NO_CONTEXT; } diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index 4cafc0c33d0..a040b81e93b 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -24,9 +24,9 @@ * Also makes sure that the subpage_prot_table structure is * reinitialized for the next user. */ -void subpage_prot_free(pgd_t *pgd) +void subpage_prot_free(struct mm_struct *mm) { - struct subpage_prot_table *spt = pgd_subpage_prot(pgd); + struct subpage_prot_table *spt = &mm->context.spt; unsigned long i, j, addr; u32 **p; @@ -51,6 +51,13 @@ void subpage_prot_free(pgd_t *pgd) spt->maxaddr = 0; } +void subpage_prot_init_new_context(struct mm_struct *mm) +{ + struct subpage_prot_table *spt = &mm->context.spt; + + memset(spt, 0, sizeof(*spt)); +} + static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, int npages) { @@ -87,7 +94,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, static void subpage_prot_clear(unsigned long addr, unsigned long len) { struct mm_struct *mm = current->mm; - struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd); + struct subpage_prot_table *spt = &mm->context.spt; u32 **spm, *spp; int i, nw; unsigned long next, limit; @@ -136,7 +143,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len) long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map) { struct mm_struct *mm = current->mm; - struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd); + struct subpage_prot_table *spt = &mm->context.spt; u32 **spm, *spp; int i, nw; unsigned long next, limit; diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 8b8e9560a31..47ea1be1481 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -62,3 +62,8 @@ config PPC_MPC5200_GPIO select GENERIC_GPIO help Enable gpiolib support for mpc5200 based boards + +config PPC_MPC5200_LPBFIFO + tristate "MPC5200 LocalPlus bus FIFO driver" + depends on PPC_MPC52xx + select PPC_BESTCOMM_GEN_BD diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile index bfd4f52cf3d..2bc8cd0c5cf 100644 --- a/arch/powerpc/platforms/52xx/Makefile +++ b/arch/powerpc/platforms/52xx/Makefile @@ -15,3 +15,4 @@ ifeq ($(CONFIG_PPC_LITE5200),y) endif obj-$(CONFIG_PPC_MPC5200_GPIO) += mpc52xx_gpio.o +obj-$(CONFIG_PPC_MPC5200_LPBFIFO) += mpc52xx_lpbfifo.o diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 4d76b7f2336..17ecdf4c87a 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -16,8 +16,14 @@ * output signals or measure input signals. * * This driver supports the GPIO and IRQ controller functions of the GPT - * device. Timer functions are not yet supported, nor is the watchdog - * timer. + * device. Timer functions are not yet supported. + * + * The timer gpt0 can be used as watchdog (wdt). If the wdt mode is used, + * this prevents the use of any gpt0 gpt function (i.e. they will fail with + * -EBUSY). Thus, the safety wdt function always has precedence over the gpt + * function. If the kernel has been compiled with CONFIG_WATCHDOG_NOWAYOUT, + * this means that gpt0 is locked in wdt mode until the next reboot - this + * may be a requirement in safety applications. * * To use the GPIO function, the following two properties must be added * to the device tree node for the gpt device (typically in the .dts file @@ -46,17 +52,24 @@ * the output mode. This driver does not change the output mode setting. */ +#include <linux/device.h> #include <linux/irq.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/list.h> +#include <linux/mutex.h> #include <linux/of.h> #include <linux/of_platform.h> #include <linux/of_gpio.h> #include <linux/kernel.h> +#include <linux/watchdog.h> +#include <linux/miscdevice.h> +#include <linux/uaccess.h> +#include <asm/div64.h> #include <asm/mpc52xx.h> MODULE_DESCRIPTION("Freescale MPC52xx gpt driver"); -MODULE_AUTHOR("Sascha Hauer, Grant Likely"); +MODULE_AUTHOR("Sascha Hauer, Grant Likely, Albrecht Dreß"); MODULE_LICENSE("GPL"); /** @@ -66,18 +79,27 @@ MODULE_LICENSE("GPL"); * @lock: spinlock to coordinate between different functions. * @of_gc: of_gpio_chip instance structure; used when GPIO is enabled * @irqhost: Pointer to irq_host instance; used when IRQ mode is supported + * @wdt_mode: only relevant for gpt0: bit 0 (MPC52xx_GPT_CAN_WDT) indicates + * if the gpt may be used as wdt, bit 1 (MPC52xx_GPT_IS_WDT) indicates + * if the timer is actively used as wdt which blocks gpt functions */ struct mpc52xx_gpt_priv { + struct list_head list; /* List of all GPT devices */ struct device *dev; struct mpc52xx_gpt __iomem *regs; spinlock_t lock; struct irq_host *irqhost; + u32 ipb_freq; + u8 wdt_mode; #if defined(CONFIG_GPIOLIB) struct of_gpio_chip of_gc; #endif }; +LIST_HEAD(mpc52xx_gpt_list); +DEFINE_MUTEX(mpc52xx_gpt_list_mutex); + #define MPC52xx_GPT_MODE_MS_MASK (0x07) #define MPC52xx_GPT_MODE_MS_IC (0x01) #define MPC52xx_GPT_MODE_MS_OC (0x02) @@ -88,15 +110,25 @@ struct mpc52xx_gpt_priv { #define MPC52xx_GPT_MODE_GPIO_OUT_LOW (0x20) #define MPC52xx_GPT_MODE_GPIO_OUT_HIGH (0x30) +#define MPC52xx_GPT_MODE_COUNTER_ENABLE (0x1000) +#define MPC52xx_GPT_MODE_CONTINUOUS (0x0400) +#define MPC52xx_GPT_MODE_OPEN_DRAIN (0x0200) #define MPC52xx_GPT_MODE_IRQ_EN (0x0100) +#define MPC52xx_GPT_MODE_WDT_EN (0x8000) #define MPC52xx_GPT_MODE_ICT_MASK (0x030000) #define MPC52xx_GPT_MODE_ICT_RISING (0x010000) #define MPC52xx_GPT_MODE_ICT_FALLING (0x020000) #define MPC52xx_GPT_MODE_ICT_TOGGLE (0x030000) +#define MPC52xx_GPT_MODE_WDT_PING (0xa5) + #define MPC52xx_GPT_STATUS_IRQMASK (0x000f) +#define MPC52xx_GPT_CAN_WDT (1 << 0) +#define MPC52xx_GPT_IS_WDT (1 << 1) + + /* --------------------------------------------------------------------- * Cascaded interrupt controller hooks */ @@ -190,7 +222,7 @@ static int mpc52xx_gpt_irq_xlate(struct irq_host *h, struct device_node *ct, dev_dbg(gpt->dev, "%s: flags=%i\n", __func__, intspec[0]); - if ((intsize < 1) || (intspec[0] < 1) || (intspec[0] > 3)) { + if ((intsize < 1) || (intspec[0] > 3)) { dev_err(gpt->dev, "bad irq specifier in %s\n", ct->full_name); return -EINVAL; } @@ -211,13 +243,11 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) { int cascade_virq; unsigned long flags; - - /* Only setup cascaded IRQ if device tree claims the GPT is - * an interrupt controller */ - if (!of_find_property(node, "interrupt-controller", NULL)) - return; + u32 mode; cascade_virq = irq_of_parse_and_map(node, 0); + if (!cascade_virq) + return; gpt->irqhost = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR, 1, &mpc52xx_gpt_irq_ops, -1); @@ -227,14 +257,16 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node) } gpt->irqhost->host_data = gpt; - set_irq_data(cascade_virq, gpt); set_irq_chained_handler(cascade_virq, mpc52xx_gpt_irq_cascade); - /* Set to Input Capture mode */ + /* If the GPT is currently disabled, then change it to be in Input + * Capture mode. If the mode is non-zero, then the pin could be + * already in use for something. */ spin_lock_irqsave(&gpt->lock, flags); - clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_MS_MASK, - MPC52xx_GPT_MODE_MS_IC); + mode = in_be32(&gpt->regs->mode); + if ((mode & MPC52xx_GPT_MODE_MS_MASK) == 0) + out_be32(&gpt->regs->mode, mode | MPC52xx_GPT_MODE_MS_IC); spin_unlock_irqrestore(&gpt->lock, flags); dev_dbg(gpt->dev, "%s() complete. virq=%i\n", __func__, cascade_virq); @@ -335,6 +367,354 @@ static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *p, struct device_node *np) { } #endif /* defined(CONFIG_GPIOLIB) */ +/*********************************************************************** + * Timer API + */ + +/** + * mpc52xx_gpt_from_irq - Return the GPT device associated with an IRQ number + * @irq: irq of timer. + */ +struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq) +{ + struct mpc52xx_gpt_priv *gpt; + struct list_head *pos; + + /* Iterate over the list of timers looking for a matching device */ + mutex_lock(&mpc52xx_gpt_list_mutex); + list_for_each(pos, &mpc52xx_gpt_list) { + gpt = container_of(pos, struct mpc52xx_gpt_priv, list); + if (gpt->irqhost && irq == irq_linear_revmap(gpt->irqhost, 0)) { + mutex_unlock(&mpc52xx_gpt_list_mutex); + return gpt; + } + } + mutex_unlock(&mpc52xx_gpt_list_mutex); + + return NULL; +} +EXPORT_SYMBOL(mpc52xx_gpt_from_irq); + +static int mpc52xx_gpt_do_start(struct mpc52xx_gpt_priv *gpt, u64 period, + int continuous, int as_wdt) +{ + u32 clear, set; + u64 clocks; + u32 prescale; + unsigned long flags; + + clear = MPC52xx_GPT_MODE_MS_MASK | MPC52xx_GPT_MODE_CONTINUOUS; + set = MPC52xx_GPT_MODE_MS_GPIO | MPC52xx_GPT_MODE_COUNTER_ENABLE; + if (as_wdt) { + clear |= MPC52xx_GPT_MODE_IRQ_EN; + set |= MPC52xx_GPT_MODE_WDT_EN; + } else if (continuous) + set |= MPC52xx_GPT_MODE_CONTINUOUS; + + /* Determine the number of clocks in the requested period. 64 bit + * arithmatic is done here to preserve the precision until the value + * is scaled back down into the u32 range. Period is in 'ns', bus + * frequency is in Hz. */ + clocks = period * (u64)gpt->ipb_freq; + do_div(clocks, 1000000000); /* Scale it down to ns range */ + + /* This device cannot handle a clock count greater than 32 bits */ + if (clocks > 0xffffffff) + return -EINVAL; + + /* Calculate the prescaler and count values from the clocks value. + * 'clocks' is the number of clock ticks in the period. The timer + * has 16 bit precision and a 16 bit prescaler. Prescaler is + * calculated by integer dividing the clocks by 0x10000 (shifting + * down 16 bits) to obtain the smallest possible divisor for clocks + * to get a 16 bit count value. + * + * Note: the prescale register is '1' based, not '0' based. ie. a + * value of '1' means divide the clock by one. 0xffff divides the + * clock by 0xffff. '0x0000' does not divide by zero, but wraps + * around and divides by 0x10000. That is why prescale must be + * a u32 variable, not a u16, for this calculation. */ + prescale = (clocks >> 16) + 1; + do_div(clocks, prescale); + if (clocks > 0xffff) { + pr_err("calculation error; prescale:%x clocks:%llx\n", + prescale, clocks); + return -EINVAL; + } + + /* Set and enable the timer, reject an attempt to use a wdt as gpt */ + spin_lock_irqsave(&gpt->lock, flags); + if (as_wdt) + gpt->wdt_mode |= MPC52xx_GPT_IS_WDT; + else if ((gpt->wdt_mode & MPC52xx_GPT_IS_WDT) != 0) { + spin_unlock_irqrestore(&gpt->lock, flags); + return -EBUSY; + } + out_be32(&gpt->regs->count, prescale << 16 | clocks); + clrsetbits_be32(&gpt->regs->mode, clear, set); + spin_unlock_irqrestore(&gpt->lock, flags); + + return 0; +} + +/** + * mpc52xx_gpt_start_timer - Set and enable the GPT timer + * @gpt: Pointer to gpt private data structure + * @period: period of timer in ns; max. ~130s @ 33MHz IPB clock + * @continuous: set to 1 to make timer continuous free running + * + * An interrupt will be generated every time the timer fires + */ +int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period, + int continuous) +{ + return mpc52xx_gpt_do_start(gpt, period, continuous, 0); +} +EXPORT_SYMBOL(mpc52xx_gpt_start_timer); + +/** + * mpc52xx_gpt_stop_timer - Stop a gpt + * @gpt: Pointer to gpt private data structure + * + * Returns an error if attempting to stop a wdt + */ +int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt) +{ + unsigned long flags; + + /* reject the operation if the timer is used as watchdog (gpt 0 only) */ + spin_lock_irqsave(&gpt->lock, flags); + if ((gpt->wdt_mode & MPC52xx_GPT_IS_WDT) != 0) { + spin_unlock_irqrestore(&gpt->lock, flags); + return -EBUSY; + } + + clrbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_COUNTER_ENABLE); + spin_unlock_irqrestore(&gpt->lock, flags); + return 0; +} +EXPORT_SYMBOL(mpc52xx_gpt_stop_timer); + +/** + * mpc52xx_gpt_timer_period - Read the timer period + * @gpt: Pointer to gpt private data structure + * + * Returns the timer period in ns + */ +u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt) +{ + u64 period; + u64 prescale; + unsigned long flags; + + spin_lock_irqsave(&gpt->lock, flags); + period = in_be32(&gpt->regs->count); + spin_unlock_irqrestore(&gpt->lock, flags); + + prescale = period >> 16; + period &= 0xffff; + if (prescale == 0) + prescale = 0x10000; + period = period * prescale * 1000000000ULL; + do_div(period, (u64)gpt->ipb_freq); + return period; +} +EXPORT_SYMBOL(mpc52xx_gpt_timer_period); + +#if defined(CONFIG_MPC5200_WDT) +/*********************************************************************** + * Watchdog API for gpt0 + */ + +#define WDT_IDENTITY "mpc52xx watchdog on GPT0" + +/* wdt_is_active stores wether or not the /dev/watchdog device is opened */ +static unsigned long wdt_is_active; + +/* wdt-capable gpt */ +static struct mpc52xx_gpt_priv *mpc52xx_gpt_wdt; + +/* low-level wdt functions */ +static inline void mpc52xx_gpt_wdt_ping(struct mpc52xx_gpt_priv *gpt_wdt) +{ + unsigned long flags; + + spin_lock_irqsave(&gpt_wdt->lock, flags); + out_8((u8 *) &gpt_wdt->regs->mode, MPC52xx_GPT_MODE_WDT_PING); + spin_unlock_irqrestore(&gpt_wdt->lock, flags); +} + +/* wdt misc device api */ +static ssize_t mpc52xx_wdt_write(struct file *file, const char __user *data, + size_t len, loff_t *ppos) +{ + struct mpc52xx_gpt_priv *gpt_wdt = file->private_data; + mpc52xx_gpt_wdt_ping(gpt_wdt); + return 0; +} + +static struct watchdog_info mpc5200_wdt_info = { + .options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, + .identity = WDT_IDENTITY, +}; + +static long mpc52xx_wdt_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct mpc52xx_gpt_priv *gpt_wdt = file->private_data; + int __user *data = (int __user *)arg; + int timeout; + u64 real_timeout; + int ret = 0; + + switch (cmd) { + case WDIOC_GETSUPPORT: + ret = copy_to_user(data, &mpc5200_wdt_info, + sizeof(mpc5200_wdt_info)); + if (ret) + ret = -EFAULT; + break; + + case WDIOC_GETSTATUS: + case WDIOC_GETBOOTSTATUS: + ret = put_user(0, data); + break; + + case WDIOC_KEEPALIVE: + mpc52xx_gpt_wdt_ping(gpt_wdt); + break; + + case WDIOC_SETTIMEOUT: + ret = get_user(timeout, data); + if (ret) + break; + real_timeout = (u64) timeout * 1000000000ULL; + ret = mpc52xx_gpt_do_start(gpt_wdt, real_timeout, 0, 1); + if (ret) + break; + /* fall through and return the timeout */ + + case WDIOC_GETTIMEOUT: + /* we need to round here as to avoid e.g. the following + * situation: + * - timeout requested is 1 second; + * - real timeout @33MHz is 999997090ns + * - the int divide by 10^9 will return 0. + */ + real_timeout = + mpc52xx_gpt_timer_period(gpt_wdt) + 500000000ULL; + do_div(real_timeout, 1000000000ULL); + timeout = (int) real_timeout; + ret = put_user(timeout, data); + break; + + default: + ret = -ENOTTY; + } + return ret; +} + +static int mpc52xx_wdt_open(struct inode *inode, struct file *file) +{ + int ret; + + /* sanity check */ + if (!mpc52xx_gpt_wdt) + return -ENODEV; + + /* /dev/watchdog can only be opened once */ + if (test_and_set_bit(0, &wdt_is_active)) + return -EBUSY; + + /* Set and activate the watchdog with 30 seconds timeout */ + ret = mpc52xx_gpt_do_start(mpc52xx_gpt_wdt, 30ULL * 1000000000ULL, + 0, 1); + if (ret) { + clear_bit(0, &wdt_is_active); + return ret; + } + + file->private_data = mpc52xx_gpt_wdt; + return nonseekable_open(inode, file); +} + +static int mpc52xx_wdt_release(struct inode *inode, struct file *file) +{ + /* note: releasing the wdt in NOWAYOUT-mode does not stop it */ +#if !defined(CONFIG_WATCHDOG_NOWAYOUT) + struct mpc52xx_gpt_priv *gpt_wdt = file->private_data; + unsigned long flags; + + spin_lock_irqsave(&gpt_wdt->lock, flags); + clrbits32(&gpt_wdt->regs->mode, + MPC52xx_GPT_MODE_COUNTER_ENABLE | MPC52xx_GPT_MODE_WDT_EN); + gpt_wdt->wdt_mode &= ~MPC52xx_GPT_IS_WDT; + spin_unlock_irqrestore(&gpt_wdt->lock, flags); +#endif + clear_bit(0, &wdt_is_active); + return 0; +} + + +static const struct file_operations mpc52xx_wdt_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .write = mpc52xx_wdt_write, + .unlocked_ioctl = mpc52xx_wdt_ioctl, + .open = mpc52xx_wdt_open, + .release = mpc52xx_wdt_release, +}; + +static struct miscdevice mpc52xx_wdt_miscdev = { + .minor = WATCHDOG_MINOR, + .name = "watchdog", + .fops = &mpc52xx_wdt_fops, +}; + +static int __devinit mpc52xx_gpt_wdt_init(void) +{ + int err; + + /* try to register the watchdog misc device */ + err = misc_register(&mpc52xx_wdt_miscdev); + if (err) + pr_err("%s: cannot register watchdog device\n", WDT_IDENTITY); + else + pr_info("%s: watchdog device registered\n", WDT_IDENTITY); + return err; +} + +static int mpc52xx_gpt_wdt_setup(struct mpc52xx_gpt_priv *gpt, + const u32 *period) +{ + u64 real_timeout; + + /* remember the gpt for the wdt operation */ + mpc52xx_gpt_wdt = gpt; + + /* configure the wdt if the device tree contained a timeout */ + if (!period || *period == 0) + return 0; + + real_timeout = (u64) *period * 1000000000ULL; + if (mpc52xx_gpt_do_start(gpt, real_timeout, 0, 1)) + dev_warn(gpt->dev, "starting as wdt failed\n"); + else + dev_info(gpt->dev, "watchdog set to %us timeout\n", *period); + return 0; +} + +#else + +static int __devinit mpc52xx_gpt_wdt_init(void) +{ + return 0; +} + +#define mpc52xx_gpt_wdt_setup(x, y) (0) + +#endif /* CONFIG_MPC5200_WDT */ + /* --------------------------------------------------------------------- * of_platform bus binding code */ @@ -349,6 +729,7 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, spin_lock_init(&gpt->lock); gpt->dev = &ofdev->dev; + gpt->ipb_freq = mpc5xxx_get_bus_frequency(ofdev->node); gpt->regs = of_iomap(ofdev->node, 0); if (!gpt->regs) { kfree(gpt); @@ -360,6 +741,26 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev, mpc52xx_gpt_gpio_setup(gpt, ofdev->node); mpc52xx_gpt_irq_setup(gpt, ofdev->node); + mutex_lock(&mpc52xx_gpt_list_mutex); + list_add(&gpt->list, &mpc52xx_gpt_list); + mutex_unlock(&mpc52xx_gpt_list_mutex); + + /* check if this device could be a watchdog */ + if (of_get_property(ofdev->node, "fsl,has-wdt", NULL) || + of_get_property(ofdev->node, "has-wdt", NULL)) { + const u32 *on_boot_wdt; + + gpt->wdt_mode = MPC52xx_GPT_CAN_WDT; + on_boot_wdt = of_get_property(ofdev->node, "fsl,wdt-on-boot", + NULL); + if (on_boot_wdt) { + dev_info(gpt->dev, "used as watchdog\n"); + gpt->wdt_mode |= MPC52xx_GPT_IS_WDT; + } else + dev_info(gpt->dev, "can function as watchdog\n"); + mpc52xx_gpt_wdt_setup(gpt, on_boot_wdt); + } + return 0; } @@ -394,3 +795,4 @@ static int __init mpc52xx_gpt_init(void) /* Make sure GPIOs and IRQs get set up before anyone tries to use them */ subsys_initcall(mpc52xx_gpt_init); +device_initcall(mpc52xx_gpt_wdt_init); diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c new file mode 100644 index 00000000000..929d017535a --- /dev/null +++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c @@ -0,0 +1,560 @@ +/* + * LocalPlus Bus FIFO driver for the Freescale MPC52xx. + * + * Copyright (C) 2009 Secret Lab Technologies Ltd. + * + * This file is released under the GPLv2 + * + * Todo: + * - Add support for multiple requests to be queued. + */ + +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/spinlock.h> +#include <asm/io.h> +#include <asm/prom.h> +#include <asm/mpc52xx.h> +#include <asm/time.h> + +#include <sysdev/bestcomm/bestcomm.h> +#include <sysdev/bestcomm/bestcomm_priv.h> +#include <sysdev/bestcomm/gen_bd.h> + +MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>"); +MODULE_DESCRIPTION("MPC5200 LocalPlus FIFO device driver"); +MODULE_LICENSE("GPL"); + +#define LPBFIFO_REG_PACKET_SIZE (0x00) +#define LPBFIFO_REG_START_ADDRESS (0x04) +#define LPBFIFO_REG_CONTROL (0x08) +#define LPBFIFO_REG_ENABLE (0x0C) +#define LPBFIFO_REG_BYTES_DONE_STATUS (0x14) +#define LPBFIFO_REG_FIFO_DATA (0x40) +#define LPBFIFO_REG_FIFO_STATUS (0x44) +#define LPBFIFO_REG_FIFO_CONTROL (0x48) +#define LPBFIFO_REG_FIFO_ALARM (0x4C) + +struct mpc52xx_lpbfifo { + struct device *dev; + phys_addr_t regs_phys; + void __iomem *regs; + int irq; + spinlock_t lock; + + struct bcom_task *bcom_tx_task; + struct bcom_task *bcom_rx_task; + struct bcom_task *bcom_cur_task; + + /* Current state data */ + struct mpc52xx_lpbfifo_request *req; + int dma_irqs_enabled; +}; + +/* The MPC5200 has only one fifo, so only need one instance structure */ +static struct mpc52xx_lpbfifo lpbfifo; + +/** + * mpc52xx_lpbfifo_kick - Trigger the next block of data to be transfered + */ +static void mpc52xx_lpbfifo_kick(struct mpc52xx_lpbfifo_request *req) +{ + size_t transfer_size = req->size - req->pos; + struct bcom_bd *bd; + void __iomem *reg; + u32 *data; + int i; + int bit_fields; + int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA); + int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE; + int poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA; + + /* Set and clear the reset bits; is good practice in User Manual */ + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000); + + /* set master enable bit */ + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000001); + if (!dma) { + /* While the FIFO can be setup for transfer sizes as large as + * 16M-1, the FIFO itself is only 512 bytes deep and it does + * not generate interrupts for FIFO full events (only transfer + * complete will raise an IRQ). Therefore when not using + * Bestcomm to drive the FIFO it needs to either be polled, or + * transfers need to constrained to the size of the fifo. + * + * This driver restricts the size of the transfer + */ + if (transfer_size > 512) + transfer_size = 512; + + /* Load the FIFO with data */ + if (write) { + reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA; + data = req->data + req->pos; + for (i = 0; i < transfer_size; i += 4) + out_be32(reg, *data++); + } + + /* Unmask both error and completion irqs */ + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000301); + } else { + /* Choose the correct direction + * + * Configure the watermarks so DMA will always complete correctly. + * It may be worth experimenting with the ALARM value to see if + * there is a performance impacit. However, if it is wrong there + * is a risk of DMA not transferring the last chunk of data + */ + if (write) { + out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1e4); + out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 7); + lpbfifo.bcom_cur_task = lpbfifo.bcom_tx_task; + } else { + out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1ff); + out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 0); + lpbfifo.bcom_cur_task = lpbfifo.bcom_rx_task; + + if (poll_dma) { + if (lpbfifo.dma_irqs_enabled) { + disable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task)); + lpbfifo.dma_irqs_enabled = 0; + } + } else { + if (!lpbfifo.dma_irqs_enabled) { + enable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task)); + lpbfifo.dma_irqs_enabled = 1; + } + } + } + + bd = bcom_prepare_next_buffer(lpbfifo.bcom_cur_task); + bd->status = transfer_size; + if (!write) { + /* + * In the DMA read case, the DMA doesn't complete, + * possibly due to incorrect watermarks in the ALARM + * and CONTROL regs. For now instead of trying to + * determine the right watermarks that will make this + * work, just increase the number of bytes the FIFO is + * expecting. + * + * When submitting another operation, the FIFO will get + * reset, so the condition of the FIFO waiting for a + * non-existent 4 bytes will get cleared. + */ + transfer_size += 4; /* BLECH! */ + } + bd->data[0] = req->data_phys + req->pos; + bcom_submit_next_buffer(lpbfifo.bcom_cur_task, NULL); + + /* error irq & master enabled bit */ + bit_fields = 0x00000201; + + /* Unmask irqs */ + if (write && (!poll_dma)) + bit_fields |= 0x00000100; /* completion irq too */ + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, bit_fields); + } + + /* Set transfer size, width, chip select and READ mode */ + out_be32(lpbfifo.regs + LPBFIFO_REG_START_ADDRESS, + req->offset + req->pos); + out_be32(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, transfer_size); + + bit_fields = req->cs << 24 | 0x000008; + if (!write) + bit_fields |= 0x010000; /* read mode */ + out_be32(lpbfifo.regs + LPBFIFO_REG_CONTROL, bit_fields); + + /* Kick it off */ + out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01); + if (dma) + bcom_enable(lpbfifo.bcom_cur_task); +} + +/** + * mpc52xx_lpbfifo_irq - IRQ handler for LPB FIFO + * + * On transmit, the dma completion irq triggers before the fifo completion + * triggers. Handle the dma completion here instead of the LPB FIFO Bestcomm + * task completion irq becuase everyting is not really done until the LPB FIFO + * completion irq triggers. + * + * In other words: + * For DMA, on receive, the "Fat Lady" is the bestcom completion irq. on + * transmit, the fifo completion irq is the "Fat Lady". The opera (or in this + * case the DMA/FIFO operation) is not finished until the "Fat Lady" sings. + * + * Reasons for entering this routine: + * 1) PIO mode rx and tx completion irq + * 2) DMA interrupt mode tx completion irq + * 3) DMA polled mode tx + * + * Exit conditions: + * 1) Transfer aborted + * 2) FIFO complete without DMA; more data to do + * 3) FIFO complete without DMA; all data transfered + * 4) FIFO complete using DMA + * + * Condition 1 can occur regardless of whether or not DMA is used. + * It requires executing the callback to report the error and exiting + * immediately. + * + * Condition 2 requires programming the FIFO with the next block of data + * + * Condition 3 requires executing the callback to report completion + * + * Condition 4 means the same as 3, except that we also retrieve the bcom + * buffer so DMA doesn't get clogged up. + * + * To make things trickier, the spinlock must be dropped before + * executing the callback, otherwise we could end up with a deadlock + * or nested spinlock condition. The out path is non-trivial, so + * extra fiddling is done to make sure all paths lead to the same + * outbound code. + */ +static irqreturn_t mpc52xx_lpbfifo_irq(int irq, void *dev_id) +{ + struct mpc52xx_lpbfifo_request *req; + u32 status = in_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS); + void __iomem *reg; + u32 *data; + int count, i; + int do_callback = 0; + u32 ts; + unsigned long flags; + int dma, write, poll_dma; + + spin_lock_irqsave(&lpbfifo.lock, flags); + ts = get_tbl(); + + req = lpbfifo.req; + if (!req) { + spin_unlock_irqrestore(&lpbfifo.lock, flags); + pr_err("bogus LPBFIFO IRQ\n"); + return IRQ_HANDLED; + } + + dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA); + write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE; + poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA; + + if (dma && !write) { + spin_unlock_irqrestore(&lpbfifo.lock, flags); + pr_err("bogus LPBFIFO IRQ (dma and not writting)\n"); + return IRQ_HANDLED; + } + + if ((status & 0x01) == 0) { + goto out; + } + + /* check abort bit */ + if (status & 0x10) { + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000); + do_callback = 1; + goto out; + } + + /* Read result from hardware */ + count = in_be32(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS); + count &= 0x00ffffff; + + if (!dma && !write) { + /* copy the data out of the FIFO */ + reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA; + data = req->data + req->pos; + for (i = 0; i < count; i += 4) + *data++ = in_be32(reg); + } + + /* Update transfer position and count */ + req->pos += count; + + /* Decide what to do next */ + if (req->size - req->pos) + mpc52xx_lpbfifo_kick(req); /* more work to do */ + else + do_callback = 1; + + out: + /* Clear the IRQ */ + out_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS, 0x01); + + if (dma && (status & 0x11)) { + /* + * Count the DMA as complete only when the FIFO completion + * status or abort bits are set. + * + * (status & 0x01) should always be the case except sometimes + * when using polled DMA. + * + * (status & 0x10) {transfer aborted}: This case needs more + * testing. + */ + bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL); + } + req->last_byte = ((u8 *)req->data)[req->size - 1]; + + /* When the do_callback flag is set; it means the transfer is finished + * so set the FIFO as idle */ + if (do_callback) + lpbfifo.req = NULL; + + if (irq != 0) /* don't increment on polled case */ + req->irq_count++; + + req->irq_ticks += get_tbl() - ts; + spin_unlock_irqrestore(&lpbfifo.lock, flags); + + /* Spinlock is released; it is now safe to call the callback */ + if (do_callback && req->callback) + req->callback(req); + + return IRQ_HANDLED; +} + +/** + * mpc52xx_lpbfifo_bcom_irq - IRQ handler for LPB FIFO Bestcomm task + * + * Only used when receiving data. + */ +static irqreturn_t mpc52xx_lpbfifo_bcom_irq(int irq, void *dev_id) +{ + struct mpc52xx_lpbfifo_request *req; + unsigned long flags; + u32 status; + u32 ts; + + spin_lock_irqsave(&lpbfifo.lock, flags); + ts = get_tbl(); + + req = lpbfifo.req; + if (!req || (req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA)) { + spin_unlock_irqrestore(&lpbfifo.lock, flags); + return IRQ_HANDLED; + } + + if (irq != 0) /* don't increment on polled case */ + req->irq_count++; + + if (!bcom_buffer_done(lpbfifo.bcom_cur_task)) { + spin_unlock_irqrestore(&lpbfifo.lock, flags); + + req->buffer_not_done_cnt++; + if ((req->buffer_not_done_cnt % 1000) == 0) + pr_err("transfer stalled\n"); + + return IRQ_HANDLED; + } + + bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL); + + req->last_byte = ((u8 *)req->data)[req->size - 1]; + + req->pos = status & 0x00ffffff; + + /* Mark the FIFO as idle */ + lpbfifo.req = NULL; + + /* Release the lock before calling out to the callback. */ + req->irq_ticks += get_tbl() - ts; + spin_unlock_irqrestore(&lpbfifo.lock, flags); + + if (req->callback) + req->callback(req); + + return IRQ_HANDLED; +} + +/** + * mpc52xx_lpbfifo_bcom_poll - Poll for DMA completion + */ +void mpc52xx_lpbfifo_poll(void) +{ + struct mpc52xx_lpbfifo_request *req = lpbfifo.req; + int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA); + int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE; + + /* + * For more information, see comments on the "Fat Lady" + */ + if (dma && write) + mpc52xx_lpbfifo_irq(0, NULL); + else + mpc52xx_lpbfifo_bcom_irq(0, NULL); +} +EXPORT_SYMBOL(mpc52xx_lpbfifo_poll); + +/** + * mpc52xx_lpbfifo_submit - Submit an LPB FIFO transfer request. + * @req: Pointer to request structure + */ +int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req) +{ + unsigned long flags; + + if (!lpbfifo.regs) + return -ENODEV; + + spin_lock_irqsave(&lpbfifo.lock, flags); + + /* If the req pointer is already set, then a transfer is in progress */ + if (lpbfifo.req) { + spin_unlock_irqrestore(&lpbfifo.lock, flags); + return -EBUSY; + } + + /* Setup the transfer */ + lpbfifo.req = req; + req->irq_count = 0; + req->irq_ticks = 0; + req->buffer_not_done_cnt = 0; + req->pos = 0; + + mpc52xx_lpbfifo_kick(req); + spin_unlock_irqrestore(&lpbfifo.lock, flags); + return 0; +} +EXPORT_SYMBOL(mpc52xx_lpbfifo_submit); + +void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req) +{ + unsigned long flags; + + spin_lock_irqsave(&lpbfifo.lock, flags); + if (lpbfifo.req == req) { + /* Put it into reset and clear the state */ + bcom_gen_bd_rx_reset(lpbfifo.bcom_rx_task); + bcom_gen_bd_tx_reset(lpbfifo.bcom_tx_task); + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000); + lpbfifo.req = NULL; + } + spin_unlock_irqrestore(&lpbfifo.lock, flags); +} +EXPORT_SYMBOL(mpc52xx_lpbfifo_abort); + +static int __devinit +mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match) +{ + struct resource res; + int rc = -ENOMEM; + + if (lpbfifo.dev != NULL) + return -ENOSPC; + + lpbfifo.irq = irq_of_parse_and_map(op->node, 0); + if (!lpbfifo.irq) + return -ENODEV; + + if (of_address_to_resource(op->node, 0, &res)) + return -ENODEV; + lpbfifo.regs_phys = res.start; + lpbfifo.regs = of_iomap(op->node, 0); + if (!lpbfifo.regs) + return -ENOMEM; + + spin_lock_init(&lpbfifo.lock); + + /* Put FIFO into reset */ + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000); + + /* Register the interrupt handler */ + rc = request_irq(lpbfifo.irq, mpc52xx_lpbfifo_irq, 0, + "mpc52xx-lpbfifo", &lpbfifo); + if (rc) + goto err_irq; + + /* Request the Bestcomm receive (fifo --> memory) task and IRQ */ + lpbfifo.bcom_rx_task = + bcom_gen_bd_rx_init(2, res.start + LPBFIFO_REG_FIFO_DATA, + BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC, + 16*1024*1024); + if (!lpbfifo.bcom_rx_task) + goto err_bcom_rx; + + rc = request_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), + mpc52xx_lpbfifo_bcom_irq, 0, + "mpc52xx-lpbfifo-rx", &lpbfifo); + if (rc) + goto err_bcom_rx_irq; + + /* Request the Bestcomm transmit (memory --> fifo) task and IRQ */ + lpbfifo.bcom_tx_task = + bcom_gen_bd_tx_init(2, res.start + LPBFIFO_REG_FIFO_DATA, + BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC); + if (!lpbfifo.bcom_tx_task) + goto err_bcom_tx; + + lpbfifo.dev = &op->dev; + return 0; + + err_bcom_tx: + free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo); + err_bcom_rx_irq: + bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task); + err_bcom_rx: + err_irq: + iounmap(lpbfifo.regs); + lpbfifo.regs = NULL; + + dev_err(&op->dev, "mpc52xx_lpbfifo_probe() failed\n"); + return -ENODEV; +} + + +static int __devexit mpc52xx_lpbfifo_remove(struct of_device *op) +{ + if (lpbfifo.dev != &op->dev) + return 0; + + /* Put FIFO in reset */ + out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000); + + /* Release the bestcomm transmit task */ + free_irq(bcom_get_task_irq(lpbfifo.bcom_tx_task), &lpbfifo); + bcom_gen_bd_tx_release(lpbfifo.bcom_tx_task); + + /* Release the bestcomm receive task */ + free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo); + bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task); + + free_irq(lpbfifo.irq, &lpbfifo); + iounmap(lpbfifo.regs); + lpbfifo.regs = NULL; + lpbfifo.dev = NULL; + + return 0; +} + +static struct of_device_id mpc52xx_lpbfifo_match[] __devinitconst = { + { .compatible = "fsl,mpc5200-lpbfifo", }, + {}, +}; + +static struct of_platform_driver mpc52xx_lpbfifo_driver = { + .owner = THIS_MODULE, + .name = "mpc52xx-lpbfifo", + .match_table = mpc52xx_lpbfifo_match, + .probe = mpc52xx_lpbfifo_probe, + .remove = __devexit_p(mpc52xx_lpbfifo_remove), +}; + +/*********************************************************************** + * Module init/exit + */ +static int __init mpc52xx_lpbfifo_init(void) +{ + pr_debug("Registering LocalPlus bus FIFO driver\n"); + return of_register_platform_driver(&mpc52xx_lpbfifo_driver); +} +module_init(mpc52xx_lpbfifo_init); + +static void __exit mpc52xx_lpbfifo_exit(void) +{ + pr_debug("Unregistering LocalPlus bus FIFO driver\n"); + of_unregister_platform_driver(&mpc52xx_lpbfifo_driver); +} +module_exit(mpc52xx_lpbfifo_exit); diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 4b1c422b814..0ff5174ae4f 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -8,7 +8,7 @@ endif obj-y := lpar.o hvCall.o nvram.o reconfig.o \ setup.o iommu.o ras.o \ - firmware.o power.o + firmware.o power.o dlpar.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_XICS) += xics.o obj-$(CONFIG_SCANLOG) += scanlog.o diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c new file mode 100644 index 00000000000..fd2f0afeb4d --- /dev/null +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -0,0 +1,558 @@ +/* + * Support for dynamic reconfiguration for PCI, Memory, and CPU + * Hotplug and Dynamic Logical Partitioning on RPA platforms. + * + * Copyright (C) 2009 Nathan Fontenot + * Copyright (C) 2009 IBM Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/kref.h> +#include <linux/notifier.h> +#include <linux/proc_fs.h> +#include <linux/spinlock.h> +#include <linux/cpu.h> +#include "offline_states.h" + +#include <asm/prom.h> +#include <asm/machdep.h> +#include <asm/uaccess.h> +#include <asm/rtas.h> +#include <asm/pSeries_reconfig.h> + +struct cc_workarea { + u32 drc_index; + u32 zero; + u32 name_offset; + u32 prop_length; + u32 prop_offset; +}; + +static void dlpar_free_cc_property(struct property *prop) +{ + kfree(prop->name); + kfree(prop->value); + kfree(prop); +} + +static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa) +{ + struct property *prop; + char *name; + char *value; + + prop = kzalloc(sizeof(*prop), GFP_KERNEL); + if (!prop) + return NULL; + + name = (char *)ccwa + ccwa->name_offset; + prop->name = kstrdup(name, GFP_KERNEL); + + prop->length = ccwa->prop_length; + value = (char *)ccwa + ccwa->prop_offset; + prop->value = kzalloc(prop->length, GFP_KERNEL); + if (!prop->value) { + dlpar_free_cc_property(prop); + return NULL; + } + + memcpy(prop->value, value, prop->length); + return prop; +} + +static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa) +{ + struct device_node *dn; + char *name; + + dn = kzalloc(sizeof(*dn), GFP_KERNEL); + if (!dn) + return NULL; + + /* The configure connector reported name does not contain a + * preceeding '/', so we allocate a buffer large enough to + * prepend this to the full_name. + */ + name = (char *)ccwa + ccwa->name_offset; + dn->full_name = kmalloc(strlen(name) + 2, GFP_KERNEL); + if (!dn->full_name) { + kfree(dn); + return NULL; + } + + sprintf(dn->full_name, "/%s", name); + return dn; +} + +static void dlpar_free_one_cc_node(struct device_node *dn) +{ + struct property *prop; + + while (dn->properties) { + prop = dn->properties; + dn->properties = prop->next; + dlpar_free_cc_property(prop); + } + + kfree(dn->full_name); + kfree(dn); +} + +static void dlpar_free_cc_nodes(struct device_node *dn) +{ + if (dn->child) + dlpar_free_cc_nodes(dn->child); + + if (dn->sibling) + dlpar_free_cc_nodes(dn->sibling); + + dlpar_free_one_cc_node(dn); +} + +#define NEXT_SIBLING 1 +#define NEXT_CHILD 2 +#define NEXT_PROPERTY 3 +#define PREV_PARENT 4 +#define MORE_MEMORY 5 +#define CALL_AGAIN -2 +#define ERR_CFG_USE -9003 + +struct device_node *dlpar_configure_connector(u32 drc_index) +{ + struct device_node *dn; + struct device_node *first_dn = NULL; + struct device_node *last_dn = NULL; + struct property *property; + struct property *last_property = NULL; + struct cc_workarea *ccwa; + int cc_token; + int rc; + + cc_token = rtas_token("ibm,configure-connector"); + if (cc_token == RTAS_UNKNOWN_SERVICE) + return NULL; + + spin_lock(&rtas_data_buf_lock); + ccwa = (struct cc_workarea *)&rtas_data_buf[0]; + ccwa->drc_index = drc_index; + ccwa->zero = 0; + + rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL); + while (rc) { + switch (rc) { + case NEXT_SIBLING: + dn = dlpar_parse_cc_node(ccwa); + if (!dn) + goto cc_error; + + dn->parent = last_dn->parent; + last_dn->sibling = dn; + last_dn = dn; + break; + + case NEXT_CHILD: + dn = dlpar_parse_cc_node(ccwa); + if (!dn) + goto cc_error; + + if (!first_dn) + first_dn = dn; + else { + dn->parent = last_dn; + if (last_dn) + last_dn->child = dn; + } + + last_dn = dn; + break; + + case NEXT_PROPERTY: + property = dlpar_parse_cc_property(ccwa); + if (!property) + goto cc_error; + + if (!last_dn->properties) + last_dn->properties = property; + else + last_property->next = property; + + last_property = property; + break; + + case PREV_PARENT: + last_dn = last_dn->parent; + break; + + case CALL_AGAIN: + break; + + case MORE_MEMORY: + case ERR_CFG_USE: + default: + printk(KERN_ERR "Unexpected Error (%d) " + "returned from configure-connector\n", rc); + goto cc_error; + } + + rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL); + } + + spin_unlock(&rtas_data_buf_lock); + return first_dn; + +cc_error: + if (first_dn) + dlpar_free_cc_nodes(first_dn); + spin_unlock(&rtas_data_buf_lock); + return NULL; +} + +static struct device_node *derive_parent(const char *path) +{ + struct device_node *parent; + char *last_slash; + + last_slash = strrchr(path, '/'); + if (last_slash == path) { + parent = of_find_node_by_path("/"); + } else { + char *parent_path; + int parent_path_len = last_slash - path + 1; + parent_path = kmalloc(parent_path_len, GFP_KERNEL); + if (!parent_path) + return NULL; + + strlcpy(parent_path, path, parent_path_len); + parent = of_find_node_by_path(parent_path); + kfree(parent_path); + } + + return parent; +} + +int dlpar_attach_node(struct device_node *dn) +{ + struct proc_dir_entry *ent; + int rc; + + of_node_set_flag(dn, OF_DYNAMIC); + kref_init(&dn->kref); + dn->parent = derive_parent(dn->full_name); + if (!dn->parent) + return -ENOMEM; + + rc = blocking_notifier_call_chain(&pSeries_reconfig_chain, + PSERIES_RECONFIG_ADD, dn); + if (rc == NOTIFY_BAD) { + printk(KERN_ERR "Failed to add device node %s\n", + dn->full_name); + return -ENOMEM; /* For now, safe to assume kmalloc failure */ + } + + of_attach_node(dn); + +#ifdef CONFIG_PROC_DEVICETREE + ent = proc_mkdir(strrchr(dn->full_name, '/') + 1, dn->parent->pde); + if (ent) + proc_device_tree_add_node(dn, ent); +#endif + + of_node_put(dn->parent); + return 0; +} + +int dlpar_detach_node(struct device_node *dn) +{ + struct device_node *parent = dn->parent; + struct property *prop = dn->properties; + +#ifdef CONFIG_PROC_DEVICETREE + while (prop) { + remove_proc_entry(prop->name, dn->pde); + prop = prop->next; + } + + if (dn->pde) + remove_proc_entry(dn->pde->name, parent->pde); +#endif + + blocking_notifier_call_chain(&pSeries_reconfig_chain, + PSERIES_RECONFIG_REMOVE, dn); + of_detach_node(dn); + of_node_put(dn); /* Must decrement the refcount */ + + return 0; +} + +int online_node_cpus(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const u32 *intserv; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != intserv[i]) + continue; + BUG_ON(get_cpu_current_state(cpu) + != CPU_STATE_OFFLINE); + cpu_maps_update_done(); + rc = cpu_up(cpu); + if (rc) + goto out; + cpu_maps_update_begin(); + + break; + } + if (cpu == num_possible_cpus()) + printk(KERN_WARNING "Could not find cpu to online " + "with physical id 0x%x\n", intserv[i]); + } + cpu_maps_update_done(); + +out: + return rc; + +} + +int offline_node_cpus(struct device_node *dn) +{ + int rc = 0; + unsigned int cpu; + int len, nthreads, i; + const u32 *intserv; + + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); + if (!intserv) + return -EINVAL; + + nthreads = len / sizeof(u32); + + cpu_maps_update_begin(); + for (i = 0; i < nthreads; i++) { + for_each_present_cpu(cpu) { + if (get_hard_smp_processor_id(cpu) != intserv[i]) + continue; + + if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) + break; + + if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { + cpu_maps_update_done(); + rc = cpu_down(cpu); + if (rc) + goto out; + cpu_maps_update_begin(); + break; + + } + + /* + * The cpu is in CPU_STATE_INACTIVE. + * Upgrade it's state to CPU_STATE_OFFLINE. + */ + set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); + BUG_ON(plpar_hcall_norets(H_PROD, intserv[i]) + != H_SUCCESS); + __cpu_die(cpu); + break; + } + if (cpu == num_possible_cpus()) + printk(KERN_WARNING "Could not find cpu to offline " + "with physical id 0x%x\n", intserv[i]); + } + cpu_maps_update_done(); + +out: + return rc; + +} + +#define DR_ENTITY_SENSE 9003 +#define DR_ENTITY_PRESENT 1 +#define DR_ENTITY_UNUSABLE 2 +#define ALLOCATION_STATE 9003 +#define ALLOC_UNUSABLE 0 +#define ALLOC_USABLE 1 +#define ISOLATION_STATE 9001 +#define ISOLATE 0 +#define UNISOLATE 1 + +int dlpar_acquire_drc(u32 drc_index) +{ + int dr_status, rc; + + rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status, + DR_ENTITY_SENSE, drc_index); + if (rc || dr_status != DR_ENTITY_UNUSABLE) + return -1; + + rc = rtas_set_indicator(ALLOCATION_STATE, drc_index, ALLOC_USABLE); + if (rc) + return rc; + + rc = rtas_set_indicator(ISOLATION_STATE, drc_index, UNISOLATE); + if (rc) { + rtas_set_indicator(ALLOCATION_STATE, drc_index, ALLOC_UNUSABLE); + return rc; + } + + return 0; +} + +int dlpar_release_drc(u32 drc_index) +{ + int dr_status, rc; + + rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status, + DR_ENTITY_SENSE, drc_index); + if (rc || dr_status != DR_ENTITY_PRESENT) + return -1; + + rc = rtas_set_indicator(ISOLATION_STATE, drc_index, ISOLATE); + if (rc) + return rc; + + rc = rtas_set_indicator(ALLOCATION_STATE, drc_index, ALLOC_UNUSABLE); + if (rc) { + rtas_set_indicator(ISOLATION_STATE, drc_index, UNISOLATE); + return rc; + } + + return 0; +} + +#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE + +static DEFINE_MUTEX(pseries_cpu_hotplug_mutex); + +void cpu_hotplug_driver_lock() +{ + mutex_lock(&pseries_cpu_hotplug_mutex); +} + +void cpu_hotplug_driver_unlock() +{ + mutex_unlock(&pseries_cpu_hotplug_mutex); +} + +static ssize_t dlpar_cpu_probe(const char *buf, size_t count) +{ + struct device_node *dn; + unsigned long drc_index; + char *cpu_name; + int rc; + + cpu_hotplug_driver_lock(); + rc = strict_strtoul(buf, 0, &drc_index); + if (rc) { + rc = -EINVAL; + goto out; + } + + dn = dlpar_configure_connector(drc_index); + if (!dn) { + rc = -EINVAL; + goto out; + } + + /* configure-connector reports cpus as living in the base + * directory of the device tree. CPUs actually live in the + * cpus directory so we need to fixup the full_name. + */ + cpu_name = kzalloc(strlen(dn->full_name) + strlen("/cpus") + 1, + GFP_KERNEL); + if (!cpu_name) { + dlpar_free_cc_nodes(dn); + rc = -ENOMEM; + goto out; + } + + sprintf(cpu_name, "/cpus%s", dn->full_name); + kfree(dn->full_name); + dn->full_name = cpu_name; + + rc = dlpar_acquire_drc(drc_index); + if (rc) { + dlpar_free_cc_nodes(dn); + rc = -EINVAL; + goto out; + } + + rc = dlpar_attach_node(dn); + if (rc) { + dlpar_release_drc(drc_index); + dlpar_free_cc_nodes(dn); + } + + rc = online_node_cpus(dn); +out: + cpu_hotplug_driver_unlock(); + + return rc ? rc : count; +} + +static ssize_t dlpar_cpu_release(const char *buf, size_t count) +{ + struct device_node *dn; + const u32 *drc_index; + int rc; + + dn = of_find_node_by_path(buf); + if (!dn) + return -EINVAL; + + drc_index = of_get_property(dn, "ibm,my-drc-index", NULL); + if (!drc_index) { + of_node_put(dn); + return -EINVAL; + } + + cpu_hotplug_driver_lock(); + rc = offline_node_cpus(dn); + if (rc) { + of_node_put(dn); + rc = -EINVAL; + goto out; + } + + rc = dlpar_release_drc(*drc_index); + if (rc) { + of_node_put(dn); + goto out; + } + + rc = dlpar_detach_node(dn); + if (rc) { + dlpar_acquire_drc(*drc_index); + goto out; + } + + of_node_put(dn); +out: + cpu_hotplug_driver_unlock(); + return rc ? rc : count; +} + +static int __init pseries_dlpar_init(void) +{ + ppc_md.cpu_probe = dlpar_cpu_probe; + ppc_md.cpu_release = dlpar_cpu_release; + + return 0; +} +machine_device_initcall(pseries, pseries_dlpar_init); + +#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 5182d2b992c..a2305d29bbb 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -96,7 +96,7 @@ static struct device_node *derive_parent(const char *path) return parent; } -static BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain); +BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain); int pSeries_reconfig_notifier_register(struct notifier_block *nb) { |