diff options
| author | Tejun Heo | 2011-11-28 09:46:22 -0800 |
|---|---|---|
| committer | Tejun Heo | 2011-11-28 09:46:22 -0800 |
| commit | d4bbf7e7759afc172e2bfbc5c416324590049cdd (patch) | |
| tree | 7eab5ee5481cd3dcf1162329fec827177640018a /arch/sparc | |
| parent | a150439c4a97db379f0ed6faa46fbbb6e7bf3cb2 (diff) | |
| parent | 401d0069cb344f401bc9d264c31db55876ff78c0 (diff) | |
Merge branch 'master' into x86/memblock
Conflicts & resolutions:
* arch/x86/xen/setup.c
dc91c728fd "xen: allow extra memory to be in multiple regions"
24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."
conflicted on xen_add_extra_mem() updates. The resolution is
trivial as the latter just want to replace
memblock_x86_reserve_range() with memblock_reserve().
* drivers/pci/intel-iommu.c
166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."
conflicted as the former moved the file under drivers/iommu/.
Resolved by applying the chnages from the latter on the moved
file.
* mm/Kconfig
6661672053a "memblock: add NO_BOOTMEM config symbol"
c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"
conflicted trivially. Both added config options. Just
letting both add their own options resolves the conflict.
* mm/memblock.c
d1f0ece6cdc "mm/memblock.c: small function definition fixes"
ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"
confliected. The former updates function removed by the
latter. Resolution is trivial.
Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'arch/sparc')
132 files changed, 2000 insertions, 1833 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 253986bd6bb6..f92602e86607 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -41,6 +41,7 @@ config SPARC64 select HAVE_FUNCTION_TRACE_MCOUNT_TEST select HAVE_KRETPROBES select HAVE_KPROBES + select HAVE_RCU_TABLE_FREE if SMP select HAVE_MEMBLOCK select HAVE_SYSCALL_WRAPPERS select HAVE_DYNAMIC_FTRACE @@ -53,6 +54,8 @@ config SPARC64 select HAVE_PERF_EVENTS select PERF_USE_VMALLOC select IRQ_PREFLOW_FASTEOI + select ARCH_HAVE_NMI_SAFE_CMPXCHG + select HAVE_C_RECORDMCOUNT config ARCH_DEFCONFIG string @@ -81,10 +84,6 @@ config IOMMU_HELPER bool default y if SPARC64 -config QUICKLIST - bool - default y if SPARC64 - config STACKTRACE_SUPPORT bool default y if SPARC64 @@ -561,12 +560,7 @@ config SUN_OPENPROMFS Only choose N if you know in advance that you will not need to modify OpenPROM settings on the running system. -# Makefile helpers -config SPARC32_PCI - bool - default y - depends on SPARC32 && PCI - +# Makefile helper config SPARC64_PCI bool default y diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 3c93f08ce187..2c2e38821f60 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -16,3 +16,8 @@ header-y += traps.h header-y += uctx.h header-y += utrap.h header-y += watchdog.h + +generic-y += div64.h +generic-y += local64.h +generic-y += irq_regs.h +generic-y += local.h diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h index 7ae128b19d3f..5c3c8b69884d 100644 --- a/arch/sparc/include/asm/atomic_32.h +++ b/arch/sparc/include/asm/atomic_32.h @@ -22,7 +22,7 @@ extern int __atomic_add_return(int, atomic_t *); extern int atomic_cmpxchg(atomic_t *, int, int); #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -extern int atomic_add_unless(atomic_t *, int, int); +extern int __atomic_add_unless(atomic_t *, int, int); extern void atomic_set(atomic_t *, int); #define atomic_read(v) (*(volatile int *)&(v)->counter) @@ -52,7 +52,6 @@ extern void atomic_set(atomic_t *, int); #define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) #define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) /* This is the old 24-bit implementation. It's still used internally * by some sparc-specific code, notably the semaphore implementation. @@ -161,5 +160,4 @@ static inline int __atomic24_sub(int i, atomic24_t *v) #endif /* !(__KERNEL__) */ -#include <asm-generic/atomic-long.h> #endif /* !(__ARCH_SPARC_ATOMIC__) */ diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h index bdb2ff880bdd..9f421df46aec 100644 --- a/arch/sparc/include/asm/atomic_64.h +++ b/arch/sparc/include/asm/atomic_64.h @@ -70,7 +70,7 @@ extern long atomic64_sub_ret(long, atomic64_t *); #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n))) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) -static inline int atomic_add_unless(atomic_t *v, int a, int u) +static inline int __atomic_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); @@ -82,10 +82,9 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u) break; c = old; } - return c != (u); + return c; } -#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) #define atomic64_cmpxchg(v, o, n) \ ((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n))) @@ -114,5 +113,4 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u) #define smp_mb__before_atomic_inc() barrier() #define smp_mb__after_atomic_inc() barrier() -#include <asm-generic/atomic-long.h> #endif /* !(__ARCH_SPARC64_ATOMIC__) */ diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h index 38e9aa1b2cea..29011cc0e4be 100644 --- a/arch/sparc/include/asm/bitops_64.h +++ b/arch/sparc/include/asm/bitops_64.h @@ -26,61 +26,28 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr); #define smp_mb__before_clear_bit() barrier() #define smp_mb__after_clear_bit() barrier() -#include <asm-generic/bitops/ffz.h> -#include <asm-generic/bitops/__ffs.h> #include <asm-generic/bitops/fls.h> #include <asm-generic/bitops/__fls.h> #include <asm-generic/bitops/fls64.h> #ifdef __KERNEL__ +extern int ffs(int x); +extern unsigned long __ffs(unsigned long); + +#include <asm-generic/bitops/ffz.h> #include <asm-generic/bitops/sched.h> -#include <asm-generic/bitops/ffs.h> /* * hweightN: returns the hamming weight (i.e. the number * of bits set) of a N-bit word */ -#ifdef ULTRA_HAS_POPULATION_COUNT - -static inline unsigned int __arch_hweight64(unsigned long w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w)); - return res; -} - -static inline unsigned int __arch_hweight32(unsigned int w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffffffff)); - return res; -} +extern unsigned long __arch_hweight64(__u64 w); +extern unsigned int __arch_hweight32(unsigned int w); +extern unsigned int __arch_hweight16(unsigned int w); +extern unsigned int __arch_hweight8(unsigned int w); -static inline unsigned int __arch_hweight16(unsigned int w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xffff)); - return res; -} - -static inline unsigned int __arch_hweight8(unsigned int w) -{ - unsigned int res; - - __asm__ ("popc %1,%0" : "=r" (res) : "r" (w & 0xff)); - return res; -} - -#else - -#include <asm-generic/bitops/arch_hweight.h> - -#endif #include <asm-generic/bitops/const_hweight.h> #include <asm-generic/bitops/lock.h> #endif /* __KERNEL__ */ @@ -91,10 +58,7 @@ static inline unsigned int __arch_hweight8(unsigned int w) #include <asm-generic/bitops/le.h> -#define ext2_set_bit_atomic(lock,nr,addr) \ - test_and_set_bit((nr) ^ 0x38,(unsigned long *)(addr)) -#define ext2_clear_bit_atomic(lock,nr,addr) \ - test_and_clear_bit((nr) ^ 0x38,(unsigned long *)(addr)) +#include <asm-generic/bitops/ext2-atomic-setbit.h> #endif /* __KERNEL__ */ diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h index 6f57325bb883..b8be20d42a0a 100644 --- a/arch/sparc/include/asm/compat.h +++ b/arch/sparc/include/asm/compat.h @@ -134,7 +134,8 @@ struct compat_statfs { compat_fsid_t f_fsid; int f_namelen; /* SunOS ignores this field. */ int f_frsize; - int f_spare[5]; + int f_flags; + int f_spare[4]; }; #define COMPAT_RLIM_INFINITY 0x7fffffff diff --git a/arch/sparc/include/asm/div64.h b/arch/sparc/include/asm/div64.h deleted file mode 100644 index 6cd978cefb28..000000000000 --- a/arch/sparc/include/asm/div64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/div64.h> diff --git a/arch/sparc/include/asm/elf_64.h b/arch/sparc/include/asm/elf_64.h index e67880381b84..7df8b7f544d4 100644 --- a/arch/sparc/include/asm/elf_64.h +++ b/arch/sparc/include/asm/elf_64.h @@ -59,15 +59,33 @@ #define R_SPARC_6 45 /* Bits present in AT_HWCAP, primarily for Sparc32. */ - -#define HWCAP_SPARC_FLUSH 1 /* CPU supports flush instruction. */ -#define HWCAP_SPARC_STBAR 2 -#define HWCAP_SPARC_SWAP 4 -#define HWCAP_SPARC_MULDIV 8 -#define HWCAP_SPARC_V9 16 -#define HWCAP_SPARC_ULTRA3 32 -#define HWCAP_SPARC_BLKINIT 64 -#define HWCAP_SPARC_N2 128 +#define HWCAP_SPARC_FLUSH 0x00000001 +#define HWCAP_SPARC_STBAR 0x00000002 +#define HWCAP_SPARC_SWAP 0x00000004 +#define HWCAP_SPARC_MULDIV 0x00000008 +#define HWCAP_SPARC_V9 0x00000010 +#define HWCAP_SPARC_ULTRA3 0x00000020 +#define HWCAP_SPARC_BLKINIT 0x00000040 +#define HWCAP_SPARC_N2 0x00000080 + +/* Solaris compatible AT_HWCAP bits. */ +#define AV_SPARC_MUL32 0x00000100 /* 32x32 multiply is efficient */ +#define AV_SPARC_DIV32 0x00000200 /* 32x32 divide is efficient */ +#define AV_SPARC_FSMULD 0x00000400 /* 'fsmuld' is efficient */ +#define AV_SPARC_V8PLUS 0x00000800 /* v9 insn available to 32bit */ +#define AV_SPARC_POPC 0x00001000 /* 'popc' is efficient */ +#define AV_SPARC_VIS 0x00002000 /* VIS insns available */ +#define AV_SPARC_VIS2 0x00004000 /* VIS2 insns available */ +#define AV_SPARC_ASI_BLK_INIT 0x00008000 /* block init ASIs available */ +#define AV_SPARC_FMAF 0x00010000 /* fused multiply-add */ +#define AV_SPARC_VIS3 0x00020000 /* VIS3 insns available */ +#define AV_SPARC_HPC 0x00040000 /* HPC insns available */ +#define AV_SPARC_RANDOM 0x00080000 /* 'random' insn available */ +#define AV_SPARC_TRANS 0x00100000 /* transaction insns available */ +#define AV_SPARC_FJFMAU 0x00200000 /* unfused multiply-add */ +#define AV_SPARC_IMA 0x00400000 /* integer multiply-add */ +#define AV_SPARC_ASI_CACHE_SPARING \ + 0x00800000 /* cache sparing ASIs available */ #define CORE_DUMP_USE_REGSET @@ -162,31 +180,8 @@ typedef struct { #define ELF_ET_DYN_BASE 0x0000010000000000UL #define COMPAT_ELF_ET_DYN_BASE 0x0000000070000000UL - -/* This yields a mask that user programs can use to figure out what - instruction set this cpu supports. */ - -/* On Ultra, we support all of the v8 capabilities. */ -static inline unsigned int sparc64_elf_hwcap(void) -{ - unsigned int cap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | - HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV | - HWCAP_SPARC_V9); - - if (tlb_type == cheetah || tlb_type == cheetah_plus) - cap |= HWCAP_SPARC_ULTRA3; - else if (tlb_type == hypervisor) { - if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || - sun4v_chip_type == SUN4V_CHIP_NIAGARA2) - cap |= HWCAP_SPARC_BLKINIT; - if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2) - cap |= HWCAP_SPARC_N2; - } - - return cap; -} - -#define ELF_HWCAP sparc64_elf_hwcap(); +extern unsigned long sparc64_elf_hwcap; +#define ELF_HWCAP sparc64_elf_hwcap /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h index 75686409be24..015a761eaa32 100644 --- a/arch/sparc/include/asm/hypervisor.h +++ b/arch/sparc/include/asm/hypervisor.h @@ -2927,6 +2927,13 @@ extern unsigned long sun4v_ncs_request(unsigned long request, #define HV_FAST_FIRE_GET_PERFREG 0x120 #define HV_FAST_FIRE_SET_PERFREG 0x121 +#define HV_FAST_REBOOT_DATA_SET 0x172 + +#ifndef __ASSEMBLY__ +extern unsigned long sun4v_reboot_data_set(unsigned long ra, + unsigned long len); +#endif + /* Function numbers for HV_CORE_TRAP. */ #define HV_CORE_SET_VER 0x00 #define HV_CORE_PUTCHAR 0x01 @@ -2940,16 +2947,23 @@ extern unsigned long sun4v_ncs_request(unsigned long request, #define HV_GRP_CORE 0x0001 #define HV_GRP_INTR 0x0002 #define HV_GRP_SOFT_STATE 0x0003 +#define HV_GRP_TM 0x0080 #define HV_GRP_PCI 0x0100 #define HV_GRP_LDOM 0x0101 #define HV_GRP_SVC_CHAN 0x0102 #define HV_GRP_NCS 0x0103 #define HV_GRP_RNG 0x0104 +#define HV_GRP_PBOOT 0x0105 +#define HV_GRP_TPM 0x0107 +#define HV_GRP_SDIO 0x0108 +#define HV_GRP_SDIO_ERR 0x0109 +#define HV_GRP_REBOOT_DATA 0x0110 #define HV_GRP_NIAG_PERF 0x0200 #define HV_GRP_FIRE_PERF 0x0201 #define HV_GRP_N2_CPU 0x0202 #define HV_GRP_NIU 0x0204 #define HV_GRP_VF_CPU 0x0205 +#define HV_GRP_KT_CPU 0x0209 #define HV_GRP_DIAG 0x0300 #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/irq_regs.h b/arch/sparc/include/asm/irq_regs.h deleted file mode 100644 index 3dd9c0b70270..000000000000 --- a/arch/sparc/include/asm/irq_regs.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/irq_regs.h> diff --git a/arch/sparc/include/asm/irqflags_32.h b/arch/sparc/include/asm/irqflags_32.h index d4d0711de0f9..14848909e0de 100644 --- a/arch/sparc/include/asm/irqflags_32.h +++ b/arch/sparc/include/asm/irqflags_32.h @@ -18,7 +18,7 @@ extern void arch_local_irq_restore(unsigned long); extern unsigned long arch_local_irq_save(void); extern void arch_local_irq_enable(void); -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { unsigned long flags; @@ -26,17 +26,17 @@ static inline unsigned long arch_local_save_flags(void) return flags; } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { arch_local_irq_save(); } -static inline bool arch_irqs_disabled_flags(unsigned long flags) +static inline notrace bool arch_irqs_disabled_flags(unsigned long flags) { return (flags & PSR_PIL) != 0; } -static inline bool arch_irqs_disabled(void) +static inline notrace bool arch_irqs_disabled(void) { return arch_irqs_disabled_flags(arch_local_save_flags()); } diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h index aab969c82c2b..23cd27f6beb4 100644 --- a/arch/sparc/include/asm/irqflags_64.h +++ b/arch/sparc/include/asm/irqflags_64.h @@ -14,7 +14,7 @@ #ifndef __ASSEMBLY__ -static inline unsigned long arch_local_save_flags(void) +static inline notrace unsigned long arch_local_save_flags(void) { unsigned long flags; @@ -26,7 +26,7 @@ static inline unsigned long arch_local_save_flags(void) return flags; } -static inline void arch_local_irq_restore(unsigned long flags) +static inline notrace void arch_local_irq_restore(unsigned long flags) { __asm__ __volatile__( "wrpr %0, %%pil" @@ -36,7 +36,7 @@ static inline void arch_local_irq_restore(unsigned long flags) ); } -static inline void arch_local_irq_disable(void) +static inline notrace void arch_local_irq_disable(void) { __asm__ __volatile__( "wrpr %0, %%pil" @@ -46,7 +46,7 @@ static inline void arch_local_irq_disable(void) ); } -static inline void arch_local_irq_enable(void) +static inline notrace void arch_local_irq_enable(void) { __asm__ __volatile__( "wrpr 0, %%pil" @@ -56,17 +56,17 @@ static inline void arch_local_irq_enable(void) ); } -static inline int arch_irqs_disabled_flags(unsigned long flags) +static inline notrace int arch_irqs_disabled_flags(unsigned long flags) { return (flags > 0); } -static inline int arch_irqs_disabled(void) +static inline notrace int arch_irqs_disabled(void) { return arch_irqs_disabled_flags(arch_local_save_flags()); } -static inline unsigned long arch_local_irq_save(void) +static inline notrace unsigned long arch_local_irq_save(void) { unsigned long flags, tmp; diff --git a/arch/sparc/include/asm/leon_pci.h b/arch/sparc/include/asm/leon_pci.h index 42b4b31a82fe..f48527ebdd8f 100644 --- a/arch/sparc/include/asm/leon_pci.h +++ b/arch/sparc/include/asm/leon_pci.h @@ -12,7 +12,7 @@ struct leon_pci_info { struct pci_ops *ops; struct resource io_space; struct resource mem_space; - int (*map_irq)(struct pci_dev *dev, u8 slot, u8 pin); + int (*map_irq)(const struct pci_dev *dev, u8 slot, u8 pin); }; extern void leon_pci_init(struct platform_device *ofdev, diff --git a/arch/sparc/include/asm/local.h b/arch/sparc/include/asm/local.h deleted file mode 100644 index bc80815a435c..000000000000 --- a/arch/sparc/include/asm/local.h +++ /dev/null @@ -1,6 +0,0 @@ -#ifndef _SPARC_LOCAL_H -#define _SPARC_LOCAL_H - -#include <asm-generic/local.h> - -#endif diff --git a/arch/sparc/include/asm/local64.h b/arch/sparc/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/sparc/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h index 862e3ce92b15..02939abd356c 100644 --- a/arch/sparc/include/asm/pci_32.h +++ b/arch/sparc/include/asm/pci_32.h @@ -42,9 +42,6 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev, } #endif -struct device_node; -extern struct device_node *pci_device_to_OF_node(struct pci_dev *pdev); - #endif /* __KERNEL__ */ #ifndef CONFIG_LEON_PCI diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h index 948b686ec089..2614d96141c9 100644 --- a/arch/sparc/include/asm/pci_64.h +++ b/arch/sparc/include/asm/pci_64.h @@ -91,9 +91,6 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) return PCI_IRQ_NONE; } -struct device_node; -extern struct device_node *pci_device_to_OF_node(struct pci_dev *pdev); - #define HAVE_ARCH_PCI_RESOURCE_TO_USER extern void pci_resource_to_user(const struct pci_dev *dev, int bar, const struct resource *rsrc, diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index 4e5e0878144f..40b2d7a7023d 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -5,7 +5,6 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/slab.h> -#include <linux/quicklist.h> #include <asm/spitfire.h> #include <asm/cpudata.h> @@ -14,71 +13,114 @@ /* Page table allocation/freeing. */ +extern struct kmem_cache *pgtable_cache; + static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return quicklist_alloc(0, GFP_KERNEL, NULL); + return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - quicklist_free(0, NULL, pgd); + kmem_cache_free(pgtable_cache, pgd); } #define pud_populate(MM, PUD, PMD) pud_set(PUD, PMD) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return quicklist_alloc(0, GFP_KERNEL, NULL); + return kmem_cache_alloc(pgtable_cache, + GFP_KERNEL|__GFP_REPEAT); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { - quicklist_free(0, NULL, pmd); + kmem_cache_free(pgtable_cache, pmd); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return quicklist_alloc(0, GFP_KERNEL, NULL); + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *page; - void *pg; + pte_t *pte; - pg = quicklist_alloc(0, GFP_KERNEL, NULL); - if (!pg) + pte = pte_alloc_one_kernel(mm, address); + if (!pte) return NULL; - page = virt_to_page(pg); + page = virt_to_page(pte); pgtable_page_ctor(page); return page; } static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - quicklist_free(0, NULL, pte); + free_page((unsigned long)pte); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { pgtable_page_dtor(ptepage); - quicklist_free_page(0, NULL, ptepage); + __free_page(ptepage); } - #define pmd_populate_kernel(MM, PMD, PTE) pmd_set(PMD, PTE) #define pmd_populate(MM,PMD,PTE_PAGE) \ pmd_populate_kernel(MM,PMD,page_address(PTE_PAGE)) #define pmd_pgtable(pmd) pmd_page(pmd) -static inline void check_pgt_cache(void) +#define check_pgt_cache() do { } while (0) + +static inline void pgtable_free(void *table, bool is_page) +{ + if (is_page) + free_page((unsigned long)table); + else + kmem_cache_free(pgtable_cache, table); +} + +#ifdef CONFIG_SMP + +struct mmu_gather; +extern void tlb_remove_table(struct mmu_gather *, void *); + +static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page) +{ + unsigned long pgf = (unsigned long)table; + if (is_page) + pgf |= 0x1UL; + tlb_remove_table(tlb, (void *)pgf); +} + +static inline void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~0x1UL); + bool is_page = false; + + if ((unsigned long)_table & 0x1UL) + is_page = true; + pgtable_free(table, is_page); +} +#else /* CONFIG_SMP */ +static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, bool is_page) { - quicklist_trim(0, NULL, 25, 16); + pgtable_free(table, is_page); +} +#endif /* !CONFIG_SMP */ + +static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage, + unsigned long address) +{ + pgtable_page_dtor(ptepage); + pgtable_free_tlb(tlb, page_address(ptepage), true); } -#define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, pte) -#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) +#define __pmd_free_tlb(tlb, pmd, addr) \ + pgtable_free_tlb(tlb, pmd, false) #endif /* _SPARC64_PGALLOC_H */ diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index 5b31a8e89823..a790cc657476 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -431,10 +431,6 @@ extern unsigned long *sparc_valid_addr_bitmap; #define kern_addr_valid(addr) \ (test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap)) -extern int io_remap_pfn_range(struct vm_area_struct *vma, - unsigned long from, unsigned long pfn, - unsigned long size, pgprot_t prot); - /* * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in * its high 4 bits. These macros/functions put it there or get it from there. @@ -443,6 +439,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, #define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4)) #define GET_PFN(pfn) (pfn & 0x0fffffffUL) +extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long, + unsigned long, pgprot_t); + +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long long offset, space, phys_base; + + offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT; + space = GET_IOSPACE(pfn); + phys_base = offset | (space << 32ULL); + + return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); +} + #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ ({ \ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 1e03c5a6b4f7..38ebb2c60137 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -95,6 +95,10 @@ /* PTE bits which are the same in SUN4U and SUN4V format. */ #define _PAGE_VALID _AC(0x8000000000000000,UL) /* Valid TTE */ #define _PAGE_R _AC(0x8000000000000000,UL) /* Keep ref bit uptodate*/ +#define _PAGE_SPECIAL _AC(0x0200000000000000,UL) /* Special page */ + +/* Advertise support for _PAGE_SPECIAL */ +#define __HAVE_ARCH_PTE_SPECIAL /* SUN4U pte bits... */ #define _PAGE_SZ4MB_4U _AC(0x6000000000000000,UL) /* 4MB Page */ @@ -104,6 +108,7 @@ #define _PAGE_NFO_4U _AC(0x1000000000000000,UL) /* No Fault Only */ #define _PAGE_IE_4U _AC(0x0800000000000000,UL) /* Invert Endianness */ #define _PAGE_SOFT2_4U _AC(0x07FC000000000000,UL) /* Software bits, set 2 */ +#define _PAGE_SPECIAL_4U _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_RES1_4U _AC(0x0002000000000000,UL) /* Reserved */ #define _PAGE_SZ32MB_4U _AC(0x0001000000000000,UL) /* (Panther) 32MB page */ #define _PAGE_SZ256MB_4U _AC(0x2001000000000000,UL) /* (Panther) 256MB page */ @@ -133,6 +138,7 @@ #define _PAGE_ACCESSED_4V _AC(0x1000000000000000,UL) /* Accessed (ref'd) */ #define _PAGE_READ_4V _AC(0x0800000000000000,UL) /* Readable SW Bit */ #define _PAGE_WRITE_4V _AC(0x0400000000000000,UL) /* Writable SW Bit */ +#define _PAGE_SPECIAL_4V _AC(0x0200000000000000,UL) /* Special page */ #define _PAGE_PADDR_4V _AC(0x00FFFFFFFFFFE000,UL) /* paddr[55:13] */ #define _PAGE_IE_4V _AC(0x0000000000001000,UL) /* Invert Endianness */ #define _PAGE_E_4V _AC(0x0000000000000800,UL) /* side-Effect */ @@ -302,10 +308,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t prot) : "=r" (mask), "=r" (tmp) : "i" (_PAGE_PADDR_4U | _PAGE_MODIFIED_4U | _PAGE_ACCESSED_4U | _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_E_4U | _PAGE_PRESENT_4U | - _PAGE_SZBITS_4U), + _PAGE_SZBITS_4U | _PAGE_SPECIAL), "i" (_PAGE_PADDR_4V | _PAGE_MODIFIED_4V | _PAGE_ACCESSED_4V | _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_E_4V | _PAGE_PRESENT_4V | - _PAGE_SZBITS_4V)); + _PAGE_SZBITS_4V | _PAGE_SPECIAL)); return __pte((pte_val(pte) & mask) | (pgprot_val(prot) & ~mask)); } @@ -502,6 +508,7 @@ static inline pte_t pte_mkyoung(pte_t pte) static inline pte_t pte_mkspecial(pte_t pte) { + pte_val(pte) |= _PAGE_SPECIAL; return pte; } @@ -607,9 +614,9 @@ static inline unsigned long pte_present(pte_t pte) return val; } -static inline int pte_special(pte_t pte) +static inline unsigned long pte_special(pte_t pte) { - return 0; + return pte_val(pte) & _PAGE_SPECIAL; } #define pmd_set(pmdp, ptep) \ @@ -750,10 +757,6 @@ static inline bool kern_addr_valid(unsigned long addr) extern int page_in_phys_avail(unsigned long paddr); -extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, - unsigned long size, pgprot_t prot); - /* * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in * its high 4 bits. These macros/functions put it there or get it from there. @@ -762,6 +765,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, #define GET_IOSPACE(pfn) (pfn >> (BITS_PER_LONG - 4)) #define GET_PFN(pfn) (pfn & 0x0fffffffffffffffUL) +extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long, + unsigned long, pgprot_t); + +static inline int io_remap_pfn_range(struct vm_area_struct *vma, + unsigned long from, unsigned long pfn, + unsigned long size, pgprot_t prot) +{ + unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; + int space = GET_IOSPACE(pfn); + unsigned long phys_base; + + phys_base = offset | (((unsigned long) space) << 32UL); + + return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot); +} + #include <asm-generic/pgtable.h> /* We provide our own get_unmapped_area to cope with VA holes and diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h index 1407c07bdade..f6ae2b2b6870 100644 --- a/arch/sparc/include/asm/pgtsrmmu.h +++ b/arch/sparc/include/asm/pgtsrmmu.h @@ -280,7 +280,7 @@ static inline unsigned long srmmu_hwprobe(unsigned long vaddr) return retval; } #else -#define srmmu_hwprobe(addr) (srmmu_swprobe(addr, 0) & SRMMU_PTE_PMASK) +#define srmmu_hwprobe(addr) srmmu_swprobe(addr, 0) #endif static inline int diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h index 56bbaadef646..edd3d3cde460 100644 --- a/arch/sparc/include/asm/prom.h +++ b/arch/sparc/include/asm/prom.h @@ -21,7 +21,7 @@ #include <linux/of_pdt.h> #include <linux/proc_fs.h> #include <linux/mutex.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 2 #define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index c7ad3fe2b252..a0e1bcf843a1 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -205,6 +205,7 @@ do { current_thread_info()->syscall_noerror = 1; \ } while (0) #define user_mode(regs) (!((regs)->tstate & TSTATE_PRIV)) #define instruction_pointer(regs) ((regs)->tpc) +#define instruction_pointer_set(regs, val) ((regs)->tpc = (val)) #define user_stack_pointer(regs) ((regs)->u_regs[UREG_FP]) #define regs_return_value(regs) ((regs)->u_regs[UREG_I0]) #ifdef CONFIG_SMP @@ -212,7 +213,6 @@ extern unsigned long profile_pc(struct pt_regs *); #else #define profile_pc(regs) instruction_pointer(regs) #endif -extern void show_regs(struct pt_regs *); #endif /* (__KERNEL__) */ #else /* __ASSEMBLY__ */ @@ -256,7 +256,6 @@ static inline bool pt_regs_clear_syscall(struct pt_regs *regs) #define instruction_pointer(regs) ((regs)->pc) #define user_stack_pointer(regs) ((regs)->u_regs[UREG_FP]) unsigned long profile_pc(struct pt_regs *); -extern void show_regs(struct pt_regs *); #endif /* (__KERNEL__) */ #else /* (!__ASSEMBLY__) */ diff --git a/arch/sparc/include/asm/sigcontext.h b/arch/sparc/include/asm/sigcontext.h index a1607d180354..69914d748130 100644 --- a/arch/sparc/include/asm/sigcontext.h +++ b/arch/sparc/include/asm/sigcontext.h @@ -45,6 +45,19 @@ typedef struct { int si_mask; } __siginfo32_t; +#define __SIGC_MAXWIN 7 + +typedef struct { + unsigned long locals[8]; + unsigned long ins[8]; +} __siginfo_reg_window; + +typedef struct { + int wsaved; + __siginfo_reg_window reg_window[__SIGC_MAXWIN]; + unsigned long rwbuf_stkptrs[__SIGC_MAXWIN]; +} __siginfo_rwin_t; + #ifdef CONFIG_SPARC64 typedef struct { unsigned int si_float_regs [64]; @@ -73,6 +86,7 @@ struct sigcontext { unsigned long ss_size; } sigc_stack; unsigned long sigc_mask; + __siginfo_rwin_t * sigc_rwin_save; }; #else diff --git a/arch/sparc/include/asm/smp_32.h b/arch/sparc/include/asm/smp_32.h index 093f10843ff2..01c51c704341 100644 --- a/arch/sparc/include/asm/smp_32.h +++ b/arch/sparc/include/asm/smp_32.h @@ -22,7 +22,7 @@ #include <asm/ptrace.h> #include <asm/asi.h> -#include <asm/atomic.h> +#include <linux/atomic.h> /* * Private routines/data diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index 20bca8950710..29862a9e9065 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -27,7 +27,7 @@ */ #include <linux/bitops.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/percpu.h> DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h index 5f5b8bf3f50d..bcc98fc35281 100644 --- a/arch/sparc/include/asm/spinlock_32.h +++ b/arch/sparc/include/asm/spinlock_32.h @@ -131,6 +131,15 @@ static inline void arch_write_lock(arch_rwlock_t *rw) *(volatile __u32 *)&lp->lock = ~0U; } +static void inline arch_write_unlock(arch_rwlock_t *lock) +{ + __asm__ __volatile__( +" st %%g0, [%0]" + : /* no outputs */ + : "r" (lock) + : "memory"); +} + static inline int arch_write_trylock(arch_rwlock_t *rw) { unsigned int val; @@ -175,8 +184,6 @@ static inline int __arch_read_trylock(arch_rwlock_t *rw) res; \ }) -#define arch_write_unlock(rw) do { (rw)->lock = 0; } while(0) - #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) #define arch_read_lock_flags(rw, flags) arch_read_lock(rw) #define arch_write_lock_flags(rw, flags) arch_write_lock(rw) diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h index 073936a8b275..968917694978 100644 --- a/arch/sparc/include/asm/spinlock_64.h +++ b/arch/sparc/include/asm/spinlock_64.h @@ -210,14 +210,8 @@ static int inline arch_write_trylock(arch_rwlock_t *lock) return result; } -#define arch_read_lock(p) arch_read_lock(p) #define arch_read_lock_flags(p, f) arch_read_lock(p) -#define arch_read_trylock(p) arch_read_trylock(p) -#define arch_read_unlock(p) arch_read_unlock(p) -#define arch_write_lock(p) arch_write_lock(p) #define arch_write_lock_flags(p, f) arch_write_lock(p) -#define arch_write_unlock(p) arch_write_unlock(p) -#define arch_write_trylock(p) arch_write_trylock(p) #define arch_read_can_lock(rw) (!((rw)->lock & 0x80000000UL)) #define arch_write_can_lock(rw) (!(rw)->lock) diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index f0d0c40c44da..d06a26601753 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -42,6 +42,9 @@ #define SUN4V_CHIP_INVALID 0x00 #define SUN4V_CHIP_NIAGARA1 0x01 #define SUN4V_CHIP_NIAGARA2 0x02 +#define SUN4V_CHIP_NIAGARA3 0x03 +#define SUN4V_CHIP_NIAGARA4 0x04 +#define SUN4V_CHIP_NIAGARA5 0x05 #define SUN4V_CHIP_UNKNOWN 0xff #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/asm/termios.h b/arch/sparc/include/asm/termios.h index e8ba95399643..e2f46705a210 100644 --- a/arch/sparc/include/asm/termios.h +++ b/arch/sparc/include/asm/termios.h @@ -40,7 +40,6 @@ struct winsize { }; #ifdef __KERNEL__ -#include <linux/module.h> /* * c_cc characters in the termio structure. Oh, how I love being diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h index 83c571d8c8a7..1a8afd1ad04f 100644 --- a/arch/sparc/include/asm/tsb.h +++ b/arch/sparc/include/asm/tsb.h @@ -133,29 +133,6 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; sub TSB, 0x8, TSB; \ TSB_STORE(TSB, TAG); -#define KTSB_LOAD_QUAD(TSB, REG) \ - ldda [TSB] ASI_NUCLEUS_QUAD_LDD, REG; - -#define KTSB_STORE(ADDR, VAL) \ - stxa VAL, [ADDR] ASI_N; - -#define KTSB_LOCK_TAG(TSB, REG1, REG2) \ -99: lduwa [TSB] ASI_N, REG1; \ - sethi %hi(TSB_TAG_LOCK_HIGH), REG2;\ - andcc REG1, REG2, %g0; \ - bne,pn %icc, 99b; \ - nop; \ - casa [TSB] ASI_N, REG1, REG2;\ - cmp REG1, REG2; \ - bne,pn %icc, 99b; \ - nop; \ - -#define KTSB_WRITE(TSB, TTE, TAG) \ - add TSB, 0x8, TSB; \ - stxa TTE, [TSB] ASI_N; \ - sub TSB, 0x8, TSB; \ - stxa TAG, [TSB] ASI_N; - /* Do a kernel page table walk. Leaves physical PTE pointer in * REG1. Jumps to FAIL_LABEL on early page table walk termination. * VADDR will not be clobbered, but REG2 will. @@ -239,6 +216,8 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; (KERNEL_TSB_SIZE_BYTES / 16) #define KERNEL_TSB4M_NENTRIES 4096 +#define KTSB_PHYS_SHIFT 15 + /* Do a kernel TSB lookup at tl>0 on VADDR+TAG, branch to OK_LABEL * on TSB hit. REG1, REG2, REG3, and REG4 are used as temporaries * and the found TTE will be left in REG1. REG3 and REG4 must @@ -247,13 +226,22 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * VADDR and TAG will be preserved and not clobbered by this macro. */ #define KERN_TSB_LOOKUP_TL1(VADDR, TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ - sethi %hi(swapper_tsb), REG1; \ +661: sethi %hi(swapper_tsb), REG1; \ or REG1, %lo(swapper_tsb), REG1; \ + .section .swapper_tsb_phys_patch, "ax"; \ + .word 661b; \ + .previous; \ +661: nop; \ + .section .tsb_ldquad_phys_patch, "ax"; \ + .word 661b; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + .previous; \ srlx VADDR, PAGE_SHIFT, REG2; \ and REG2, (KERNEL_TSB_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ - KTSB_LOAD_QUAD(REG2, REG3); \ + TSB_LOAD_QUAD(REG2, REG3); \ cmp REG3, TAG; \ be,a,pt %xcc, OK_LABEL; \ mov REG4, REG1; @@ -263,12 +251,21 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end; * we can make use of that for the index computation. */ #define KERN_TSB4M_LOOKUP_TL1(TAG, REG1, REG2, REG3, REG4, OK_LABEL) \ - sethi %hi(swapper_4m_tsb), REG1; \ +661: sethi %hi(swapper_4m_tsb), REG1; \ or REG1, %lo(swapper_4m_tsb), REG1; \ + .section .swapper_4m_tsb_phys_patch, "ax"; \ + .word 661b; \ + .previous; \ +661: nop; \ + .section .tsb_ldquad_phys_patch, "ax"; \ + .word 661b; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + sllx REG1, KTSB_PHYS_SHIFT, REG1; \ + .previous; \ and TAG, (KERNEL_TSB4M_NENTRIES - 1), REG2; \ sllx REG2, 4, REG2; \ add REG1, REG2, REG2; \ - KTSB_LOAD_QUAD(REG2, REG3); \ + TSB_LOAD_QUAD(REG2, REG3); \ cmp REG3, TAG; \ be,a,pt %xcc, OK_LABEL; \ mov REG4, REG1; diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h index 6260d5deeabc..c7cb0af0eb59 100644 --- a/arch/sparc/include/asm/unistd.h +++ b/arch/sparc/include/asm/unistd.h @@ -406,8 +406,10 @@ #define __NR_syncfs 335 #define __NR_sendmmsg 336 #define __NR_setns 337 +#define __NR_process_vm_readv 338 +#define __NR_process_vm_writev 339 -#define NR_syscalls 338 +#define NR_syscalls 340 #ifdef __32bit_syscall_numbers__ /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants, diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h index bee4bf4be3af..ee8edc68423e 100644 --- a/arch/sparc/include/asm/xor_64.h +++ b/arch/sparc/include/asm/xor_64.h @@ -65,6 +65,9 @@ static struct xor_block_template xor_block_niagara = { #define XOR_SELECT_TEMPLATE(FASTEST) \ ((tlb_type == hypervisor && \ (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \ - sun4v_chip_type == SUN4V_CHIP_NIAGARA2)) ? \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || \ + sun4v_chip_type == SUN4V_CHIP_NIAGARA5)) ? \ &xor_block_niagara : \ &xor_block_VIS) diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index b90b4a1d070a..cb85458f89d2 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_SPARC32) += sun4m_irq.o sun4c_irq.o sun4d_irq.o obj-y += process_$(BITS).o obj-y += signal_$(BITS).o +obj-y += sigutil_$(BITS).o obj-$(CONFIG_SPARC32) += ioport.o obj-y += setup_$(BITS).o obj-y += idprom.o diff --git a/arch/sparc/kernel/apc.c b/arch/sparc/kernel/apc.c index caef9deb5866..812e10bbb0b3 100644 --- a/arch/sparc/kernel/apc.c +++ b/arch/sparc/kernel/apc.c @@ -13,6 +13,7 @@ #include <linux/pm.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/module.h> #include <asm/io.h> #include <asm/oplib.h> diff --git a/arch/sparc/kernel/auxio_32.c b/arch/sparc/kernel/auxio_32.c index acf5151f3c1d..f7ea8f032719 100644 --- a/arch/sparc/kernel/auxio_32.c +++ b/arch/sparc/kernel/auxio_32.c @@ -8,6 +8,7 @@ #include <linux/spinlock.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/export.h> #include <asm/oplib.h> #include <asm/io.h> #include <asm/auxio.h> diff --git a/arch/sparc/kernel/btext.c b/arch/sparc/kernel/btext.c index 89aa4eb20cf5..57073e56ba9e 100644 --- a/arch/sparc/kernel/btext.c +++ b/arch/sparc/kernel/btext.c @@ -6,7 +6,6 @@ #include <linux/kernel.h> #include <linux/string.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/console.h> #include <asm/btext.h> diff --git a/arch/sparc/kernel/central.c b/arch/sparc/kernel/central.c index 7eef3f741963..38d48a59879c 100644 --- a/arch/sparc/kernel/central.c +++ b/arch/sparc/kernel/central.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/init.h> #include <linux/of_device.h> diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index 138dbbc8dc84..2d1819641769 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -6,7 +6,7 @@ #include <linux/seq_file.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/smp.h> #include <linux/threads.h> @@ -396,6 +396,7 @@ static int show_cpuinfo(struct seq_file *m, void *__unused) , cpu_data(0).clock_tick #endif ); + cpucap_info(m); #ifdef CONFIG_SMP smp_bogo(m); #endif @@ -474,11 +475,30 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "niagara2"; break; + case SUN4V_CHIP_NIAGARA3: + sparc_cpu_type = "UltraSparc T3 (Niagara3)"; + sparc_fpu_type = "UltraSparc T3 integrated FPU"; + sparc_pmu_type = "niagara3"; + break; + + case SUN4V_CHIP_NIAGARA4: + sparc_cpu_type = "UltraSparc T4 (Niagara4)"; + sparc_fpu_type = "UltraSparc T4 integrated FPU"; + sparc_pmu_type = "niagara4"; + break; + + case SUN4V_CHIP_NIAGARA5: + sparc_cpu_type = "UltraSparc T5 (Niagara5)"; + sparc_fpu_type = "UltraSparc T5 integrated FPU"; + sparc_pmu_type = "niagara5"; + break; + default: printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n", prom_cpu_compatible); sparc_cpu_type = "Unknown SUN4V CPU"; sparc_fpu_type = "Unknown SUN4V FPU"; + sparc_pmu_type = "Unknown SUN4V PMU"; break; } } diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index d91fd782743a..e4de74c2c9b0 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -3,7 +3,7 @@ * Copyright (C) 2009 Hong H. Pham <hong.pham@windriver.com> */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/init.h> @@ -324,6 +324,9 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) switch (sun4v_chip_type) { case SUN4V_CHIP_NIAGARA1: case SUN4V_CHIP_NIAGARA2: + case SUN4V_CHIP_NIAGARA3: + case SUN4V_CHIP_NIAGARA4: + case SUN4V_CHIP_NIAGARA5: rover_inc_table = niagara_iterate_method; break; default: diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c index e1ba8ee21b9a..b667aa6f28f6 100644 --- a/arch/sparc/kernel/dma.c +++ b/arch/sparc/kernel/dma.c @@ -1,5 +1,4 @@ #include <linux/kernel.h> -#include <linux/module.h> #include <linux/dma-mapping.h> #include <linux/dma-debug.h> diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c index dd1342c0a3be..7429b47c3aca 100644 --- a/arch/sparc/kernel/ds.c +++ b/arch/sparc/kernel/ds.c @@ -15,12 +15,15 @@ #include <linux/reboot.h> #include <linux/cpu.h> +#include <asm/hypervisor.h> #include <asm/ldc.h> #include <asm/vio.h> #include <asm/mdesc.h> #include <asm/head.h> #include <asm/irq.h> +#include "kernel.h" + #define DRV_MODULE_NAME "ds" #define PFX DRV_MODULE_NAME ": " #define DRV_MODULE_VERSION "1.0" @@ -828,18 +831,32 @@ void ldom_set_var(const char *var, const char *value) } } +static char full_boot_str[256] __attribute__((aligned(32))); +static int reboot_data_supported; + void ldom_reboot(const char *boot_command) { /* Don't bother with any of this if the boot_command * is empty. */ if (boot_command && strlen(boot_command)) { - char full_boot_str[256]; + unsigned long len; strcpy(full_boot_str, "boot "); strcpy(full_boot_str + strlen("boot "), boot_command); + len = strlen(full_boot_str); - ldom_set_var("reboot-command", full_boot_str); + if (reboot_data_supported) { + unsigned long ra = kimage_addr_to_ra(full_boot_str); + unsigned long hv_ret; + + hv_ret = sun4v_reboot_data_set(ra, len); + if (hv_ret != HV_EOK) + pr_err("SUN4V: Unable to set reboot data " + "hv_ret=%lu\n", hv_ret); + } else { + ldom_set_var("reboot-command", full_boot_str); + } } sun4v_mach_sir(); } @@ -1237,6 +1254,16 @@ static struct vio_driver ds_driver = { static int __init ds_init(void) { + unsigned long hv_ret, major, minor; + + if (tlb_type == hypervisor) { + hv_ret = sun4v_get_version(HV_GRP_REBOOT_DATA, &major, &minor); + if (hv_ret == HV_EOK) { + pr_info("SUN4V: Reboot data supported (maj=%lu,min=%lu).\n", + major, minor); + reboot_data_supported = 1; + } + } kthread_run(ds_thread, NULL, "kldomd"); return vio_register_driver(&ds_driver); diff --git a/arch/sparc/kernel/ebus.c b/arch/sparc/kernel/ebus.c index 77dbf6d45faf..e306fb08ee5e 100644 --- a/arch/sparc/kernel/ebus.c +++ b/arch/sparc/kernel/ebus.c @@ -4,7 +4,7 @@ * Copyright (C) 1999 David S. Miller (davem@redhat.com) */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 9fe08a1ea6c6..f445e98463e6 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -293,7 +293,7 @@ maybe_smp4m_msg: WRITE_PAUSE wr %l4, PSR_ET, %psr WRITE_PAUSE - sll %o3, 28, %o2 ! shift for simpler checks below + srl %o3, 28, %o2 ! shift for simpler checks below maybe_smp4m_msg_check_single: andcc %o2, 0x1, %g0 beq,a maybe_smp4m_msg_check_mask diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h index d1f1361c4167..0c218e4c0881 100644 --- a/arch/sparc/kernel/entry.h +++ b/arch/sparc/kernel/entry.h @@ -42,7 +42,28 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr, extern void fpload(unsigned long *fpregs, unsigned long *fsr); #else /* CONFIG_SPARC32 */ + +#include <asm/trap_block.h> + +struct popc_3insn_patch_entry { + unsigned int addr; + unsigned int insns[3]; +}; +extern struct popc_3insn_patch_entry __popc_3insn_patch, + __popc_3insn_patch_end; + +struct popc_6insn_patch_entry { + unsigned int addr; + unsigned int insns[6]; +}; +extern struct popc_6insn_patch_entry __popc_6insn_patch, + __popc_6insn_patch_end; + extern void __init per_cpu_patch(void); +extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *, + struct sun4v_1insn_patch_entry *); +extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *, + struct sun4v_2insn_patch_entry *); extern void __init sun4v_patch(void); extern void __init boot_cpu_id_too_large(int cpu); extern unsigned int dcache_parity_tl1_occurred; diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index aa594c792d19..0d810c2f1d00 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -132,6 +132,8 @@ prom_sun4v_name: .asciz "sun4v" prom_niagara_prefix: .asciz "SUNW,UltraSPARC-T" +prom_sparc_prefix: + .asciz "SPARC-" .align 4 prom_root_compatible: .skip 64 @@ -382,6 +384,22 @@ sun4v_chip_type: 90: ldub [%g7], %g2 ldub [%g1], %g4 cmp %g2, %g4 + bne,pn %icc, 89f + add %g7, 1, %g7 + subcc %g3, 1, %g3 + bne,pt %xcc, 90b + add %g1, 1, %g1 + ba,pt %xcc, 91f + nop + +89: sethi %hi(prom_cpu_compatible), %g1 + or %g1, %lo(prom_cpu_compatible), %g1 + sethi %hi(prom_sparc_prefix), %g7 + or %g7, %lo(prom_sparc_prefix), %g7 + mov 6, %g3 +90: ldub [%g7], %g2 + ldub [%g1], %g4 + cmp %g2, %g4 bne,pn %icc, 4f add %g7, 1, %g7 subcc %g3, 1, %g3 @@ -390,6 +408,28 @@ sun4v_chip_type: sethi %hi(prom_cpu_compatible), %g1 or %g1, %lo(prom_cpu_compatible), %g1 + ldub [%g1 + 6], %g2 + cmp %g2, 'T' + be,pt %xcc, 70f + cmp %g2, 'M' + bne,pn %xcc, 4f + nop + +70: ldub [%g1 + 7], %g2 + cmp %g2, '3' + be,pt %xcc, 5f + mov SUN4V_CHIP_NIAGARA3, %g4 + cmp %g2, '4' + be,pt %xcc, 5f + mov SUN4V_CHIP_NIAGARA4, %g4 + cmp %g2, '5' + be,pt %xcc, 5f + mov SUN4V_CHIP_NIAGARA5, %g4 + ba,pt %xcc, 4f + nop + +91: sethi %hi(prom_cpu_compatible), %g1 + or %g1, %lo(prom_cpu_compatible), %g1 ldub [%g1 + 17], %g2 cmp %g2, '1' be,pt %xcc, 5f @@ -397,6 +437,7 @@ sun4v_chip_type: cmp %g2, '2' be,pt %xcc, 5f mov SUN4V_CHIP_NIAGARA2, %g4 + 4: mov SUN4V_CHIP_UNKNOWN, %g4 5: sethi %hi(sun4v_chip_type), %g2 @@ -514,6 +555,15 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_NIAGARA2 be,pt %xcc, niagara2_patch nop + cmp %g1, SUN4V_CHIP_NIAGARA3 + be,pt %xcc, niagara2_patch + nop + cmp %g1, SUN4V_CHIP_NIAGARA4 + be,pt %xcc, niagara2_patch + nop + cmp %g1, SUN4V_CHIP_NIAGARA5 + be,pt %xcc, niagara2_patch + nop call generic_patch_copyops nop @@ -528,7 +578,7 @@ niagara2_patch: nop call niagara_patch_bzero nop - call niagara2_patch_pageops + call niagara_patch_pageops nop ba,a,pt %xcc, 80f diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c index 7c60afb835b0..8593672838fd 100644 --- a/arch/sparc/kernel/hvapi.c +++ b/arch/sparc/kernel/hvapi.c @@ -3,7 +3,7 @@ * Copyright (C) 2007 David S. Miller <davem@davemloft.net> */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <asm/hypervisor.h> @@ -28,16 +28,23 @@ static struct api_info api_table[] = { { .group = HV_GRP_CORE, .flags = FLAG_PRE_API }, { .group = HV_GRP_INTR, }, { .group = HV_GRP_SOFT_STATE, }, + { .group = HV_GRP_TM, }, { .group = HV_GRP_PCI, .flags = FLAG_PRE_API }, { .group = HV_GRP_LDOM, }, { .group = HV_GRP_SVC_CHAN, .flags = FLAG_PRE_API }, { .group = HV_GRP_NCS, .flags = FLAG_PRE_API }, { .group = HV_GRP_RNG, }, + { .group = HV_GRP_PBOOT, }, + { .group = HV_GRP_TPM, }, + { .group = HV_GRP_SDIO, }, + { .group = HV_GRP_SDIO_ERR, }, + { .group = HV_GRP_REBOOT_DATA, }, { .group = HV_GRP_NIAG_PERF, .flags = FLAG_PRE_API }, { .group = HV_GRP_FIRE_PERF, }, { .group = HV_GRP_N2_CPU, }, { .group = HV_GRP_NIU, }, { .group = HV_GRP_VF_CPU, }, + { .group = HV_GRP_KT_CPU, }, { .group = HV_GRP_DIAG, .flags = FLAG_PRE_API }, }; diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S index 8a5f35ffb15e..58d60de4d65b 100644 --- a/arch/sparc/kernel/hvcalls.S +++ b/arch/sparc/kernel/hvcalls.S @@ -798,3 +798,10 @@ ENTRY(sun4v_niagara2_setperf) retl nop ENDPROC(sun4v_niagara2_setperf) + +ENTRY(sun4v_reboot_data_set) + mov HV_FAST_REBOOT_DATA_SET, %o5 + ta HV_FAST_TRAP + retl + nop +ENDPROC(sun4v_reboot_data_set) diff --git a/arch/sparc/kernel/idprom.c b/arch/sparc/kernel/idprom.c index 52a15fe2db19..9167db40720e 100644 --- a/arch/sparc/kernel/idprom.c +++ b/arch/sparc/kernel/idprom.c @@ -8,7 +8,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/oplib.h> #include <asm/idprom.h> diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 6f01e8c83197..4643d68713fa 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -5,7 +5,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/delay.h> #include <linux/device.h> diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c index 1c9c80a1a86a..d0479e2163fa 100644 --- a/arch/sparc/kernel/ioport.c +++ b/arch/sparc/kernel/ioport.c @@ -65,9 +65,6 @@ static inline void dma_make_coherent(unsigned long pa, unsigned long len) } #endif -static struct resource *_sparc_find_resource(struct resource *r, - unsigned long); - static void __iomem *_sparc_ioremap(struct resource *res, u32 bus, u32 pa, int sz); static void __iomem *_sparc_alloc_io(unsigned int busno, unsigned long phys, unsigned long size, char *name); @@ -143,7 +140,11 @@ void iounmap(volatile void __iomem *virtual) unsigned long vaddr = (unsigned long) virtual & PAGE_MASK; struct resource *res; - if ((res = _sparc_find_resource(&sparc_iomap, vaddr)) == NULL) { + /* + * XXX Too slow. Can have 8192 DVMA pages on sun4m in the worst case. + * This probably warrants some sort of hashing. + */ + if ((res = lookup_resource(&sparc_iomap, vaddr)) == NULL) { printk("free_io/iounmap: cannot free %lx\n", vaddr); return; } @@ -228,7 +229,7 @@ _sparc_ioremap(struct resource *res, u32 bus, u32 pa, int sz) } pa &= PAGE_MASK; - sparc_mapiorange(bus, pa, res->start, res->end - res->start + 1); + sparc_mapiorange(bus, pa, res->start, resource_size(res)); return (void __iomem *)(unsigned long)(res->start + offset); } @@ -240,7 +241,7 @@ static void _sparc_free_io(struct resource *res) { unsigned long plen; - plen = res->end - res->start + 1; + plen = resource_size(res); BUG_ON((plen & (PAGE_SIZE-1)) != 0); sparc_unmapiorange(res->start, plen); release_resource(res); @@ -319,7 +320,7 @@ static void sbus_free_coherent(struct device *dev, size_t n, void *p, struct resource *res; struct page *pgv; - if ((res = _sparc_find_resource(&_sparc_dvma, + if ((res = lookup_resource(&_sparc_dvma, (unsigned long)p)) == NULL) { printk("sbus_free_consistent: cannot free %p\n", p); return; @@ -331,9 +332,9 @@ static void sbus_free_coherent(struct device *dev, size_t n, void *p, } n = PAGE_ALIGN(n); - if ((res->end-res->start)+1 != n) { + if (resource_size(res) != n) { printk("sbus_free_consistent: region 0x%lx asked 0x%zx\n", - (long)((res->end-res->start)+1), n); + (long)resource_size(res), n); return; } @@ -492,7 +493,7 @@ static void pci32_free_coherent(struct device *dev, size_t n, void *p, { struct resource *res; - if ((res = _sparc_find_resource(&_sparc_dvma, + if ((res = lookup_resource(&_sparc_dvma, (unsigned long)p)) == NULL) { printk("pci_free_consistent: cannot free %p\n", p); return; @@ -504,9 +505,9 @@ static void pci32_free_coherent(struct device *dev, size_t n, void *p, } n = PAGE_ALIGN(n); - if ((res->end-res->start)+1 != n) { + if (resource_size(res) != n) { printk("pci_free_consistent: region 0x%lx asked 0x%lx\n", - (long)((res->end-res->start)+1), (long)n); + (long)resource_size(res), (long)n); return; } @@ -715,25 +716,6 @@ static const struct file_operations sparc_io_proc_fops = { }; #endif /* CONFIG_PROC_FS */ -/* - * This is a version of find_resource and it belongs to kernel/resource.c. - * Until we have agreement with Linus and Martin, it lingers here. - * - * XXX Too slow. Can have 8192 DVMA pages on sun4m in the worst case. - * This probably warrants some sort of hashing. - */ -static struct resource *_sparc_find_resource(struct resource *root, - unsigned long hit) -{ - struct resource *tmp; - - for (tmp = root->child; tmp != 0; tmp = tmp->sibling) { - if (tmp->start <= hit && tmp->end >= hit) - return tmp; - } - return NULL; -} - static void register_proc_sparc_ioport(void) { #ifdef CONFIG_PROC_FS diff --git a/arch/sparc/kernel/irq.h b/arch/sparc/kernel/irq.h index 100b9c204e78..42851122bbd9 100644 --- a/arch/sparc/kernel/irq.h +++ b/arch/sparc/kernel/irq.h @@ -88,7 +88,7 @@ BTFIXUPDEF_CALL(void, set_irq_udt, int) #define set_irq_udt(cpu) BTFIXUP_CALL(set_irq_udt)(cpu) /* All SUN4D IPIs are sent on this IRQ, may be shared with hard IRQs */ -#define SUN4D_IPI_IRQ 14 +#define SUN4D_IPI_IRQ 13 extern void sun4d_ipi_interrupt(void); diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c index 9b89d842913c..b2668afd1c34 100644 --- a/arch/sparc/kernel/irq_32.c +++ b/arch/sparc/kernel/irq_32.c @@ -13,6 +13,7 @@ #include <linux/kernel_stat.h> #include <linux/seq_file.h> +#include <linux/export.h> #include <asm/cacheflush.h> #include <asm/cpudata.h> diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 4e78862d12fd..d45b710ea7e4 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -5,7 +5,6 @@ * Copyright (C) 1998 Jakub Jelinek (jj@ultra.linux.cz) */ -#include <linux/module.h> #include <linux/sched.h> #include <linux/linkage.h> #include <linux/ptrace.h> @@ -26,7 +25,7 @@ #include <asm/ptrace.h> #include <asm/processor.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/system.h> #include <asm/irq.h> #include <asm/io.h> diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c index ea2dafc93d78..971fd435a281 100644 --- a/arch/sparc/kernel/jump_label.c +++ b/arch/sparc/kernel/jump_label.c @@ -36,12 +36,4 @@ void arch_jump_label_transform(struct jump_entry *entry, put_online_cpus(); } -void arch_jump_label_text_poke_early(jump_label_t addr) -{ - u32 *insn_p = (u32 *) (unsigned long) addr; - - *insn_p = 0x01000000; - flushi(insn_p); -} - #endif diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h index 6f6544cfa0ef..fd6c36b1df74 100644 --- a/arch/sparc/kernel/kernel.h +++ b/arch/sparc/kernel/kernel.h @@ -4,12 +4,27 @@ #include <linux/interrupt.h> #include <asm/traps.h> +#include <asm/head.h> +#include <asm/io.h> /* cpu.c */ extern const char *sparc_pmu_type; extern unsigned int fsr_storage; extern int ncpus_probed; +#ifdef CONFIG_SPARC64 +/* setup_64.c */ +struct seq_file; +extern void cpucap_info(struct seq_file *); + +static inline unsigned long kimage_addr_to_ra(const char *p) +{ + unsigned long val = (unsigned long) p; + + return kern_base + (val - KERNBASE); +} +#endif + #ifdef CONFIG_SPARC32 /* cpu.c */ extern void cpu_probe(void); diff --git a/arch/sparc/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S index 1d361477d7d6..79f310364849 100644 --- a/arch/sparc/kernel/ktlb.S +++ b/arch/sparc/kernel/ktlb.S @@ -47,16 +47,16 @@ kvmap_itlb_tsb_miss: kvmap_itlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_itlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) /* Load and check PTE. */ ldxa [%g5] ASI_PHYS_USE_EC, %g5 mov 1, %g7 sllx %g7, TSB_TAG_INVALID_BIT, %g7 brgez,a,pn %g5, kvmap_itlb_longpath - KTSB_STORE(%g1, %g7) + TSB_STORE(%g1, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ @@ -102,9 +102,9 @@ kvmap_itlb_longpath: kvmap_itlb_obp: OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_itlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) ba,pt %xcc, kvmap_itlb_load nop @@ -112,17 +112,17 @@ kvmap_itlb_obp: kvmap_dtlb_obp: OBP_TRANS_LOOKUP(%g4, %g5, %g2, %g3, kvmap_dtlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) ba,pt %xcc, kvmap_dtlb_load nop .align 32 kvmap_dtlb_tsb4m_load: - KTSB_LOCK_TAG(%g1, %g2, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_LOCK_TAG(%g1, %g2, %g7) + TSB_WRITE(%g1, %g5, %g6) ba,pt %xcc, kvmap_dtlb_load nop @@ -222,16 +222,16 @@ kvmap_linear_patch: kvmap_dtlb_vmalloc_addr: KERN_PGTABLE_WALK(%g4, %g5, %g2, kvmap_dtlb_longpath) - KTSB_LOCK_TAG(%g1, %g2, %g7) + TSB_LOCK_TAG(%g1, %g2, %g7) /* Load and check PTE. */ ldxa [%g5] ASI_PHYS_USE_EC, %g5 mov 1, %g7 sllx %g7, TSB_TAG_INVALID_BIT, %g7 brgez,a,pn %g5, kvmap_dtlb_longpath - KTSB_STORE(%g1, %g7) + TSB_STORE(%g1, %g7) - KTSB_WRITE(%g1, %g5, %g6) + TSB_WRITE(%g1, %g5, %g6) /* fallthrough to TLB load */ diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c index 732b0bce6001..435e406fdec3 100644 --- a/arch/sparc/kernel/ldc.c +++ b/arch/sparc/kernel/ldc.c @@ -4,7 +4,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/delay.h> diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c index d17255a2bbac..a19c8a063683 100644 --- a/arch/sparc/kernel/leon_kernel.c +++ b/arch/sparc/kernel/leon_kernel.c @@ -4,7 +4,6 @@ */ #include <linux/kernel.h> -#include <linux/module.h> #include <linux/errno.h> #include <linux/mutex.h> #include <linux/of.h> diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c index a8a9a275037d..f1cf6ef011a7 100644 --- a/arch/sparc/kernel/leon_pci.c +++ b/arch/sparc/kernel/leon_pci.c @@ -9,6 +9,7 @@ #include <linux/of_device.h> #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/export.h> #include <asm/leon.h> #include <asm/leon_pci.h> diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c index 44dc093ee33a..b1bc38853a3d 100644 --- a/arch/sparc/kernel/leon_pci_grpci2.c +++ b/arch/sparc/kernel/leon_pci_grpci2.c @@ -9,7 +9,7 @@ #include <linux/kernel.h> #include <linux/pci.h> #include <linux/delay.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/io.h> #include <asm/leon.h> #include <asm/vaddrs.h> @@ -215,7 +215,7 @@ struct grpci2_priv { DEFINE_SPINLOCK(grpci2_dev_lock); struct grpci2_priv *grpci2priv; -int grpci2_map_irq(struct pci_dev *dev, u8 slot, u8 pin) +int grpci2_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { struct grpci2_priv *priv = dev->bus->sysdata; int irq_group; diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c index fe8fb44c609c..1210fde18740 100644 --- a/arch/sparc/kernel/leon_smp.c +++ b/arch/sparc/kernel/leon_smp.c @@ -28,7 +28,7 @@ #include <asm/tlbflush.h> #include <asm/ptrace.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/irq_regs.h> #include <asm/traps.h> diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 42f28c7420e1..6dc796280589 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -11,11 +11,13 @@ #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/bootmem.h> +#include <linux/export.h> #include <asm/cpudata.h> #include <asm/hypervisor.h> #include <asm/mdesc.h> #include <asm/prom.h> +#include <asm/uaccess.h> #include <asm/oplib.h> #include <asm/smp.h> @@ -508,6 +510,8 @@ const char *mdesc_node_name(struct mdesc_handle *hp, u64 node) } EXPORT_SYMBOL(mdesc_node_name); +static u64 max_cpus = 64; + static void __init report_platform_properties(void) { struct mdesc_handle *hp = mdesc_grab(); @@ -543,8 +547,10 @@ static void __init report_platform_properties(void) if (v) printk("PLATFORM: watchdog-max-timeout [%llu ms]\n", *v); v = mdesc_get_property(hp, pn, "max-cpus", NULL); - if (v) - printk("PLATFORM: max-cpus [%llu]\n", *v); + if (v) { + max_cpus = *v; + printk("PLATFORM: max-cpus [%llu]\n", max_cpus); + } #ifdef CONFIG_SMP { @@ -715,7 +721,7 @@ static void __cpuinit set_proc_ids(struct mdesc_handle *hp) } static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask, - unsigned char def) + unsigned long def, unsigned long max) { u64 val; @@ -726,6 +732,9 @@ static void __cpuinit get_one_mondo_bits(const u64 *p, unsigned int *mask, if (!val || val >= 64) goto use_default; + if (val > max) + val = max; + *mask = ((1U << val) * 64U) - 1U; return; @@ -736,19 +745,28 @@ use_default: static void __cpuinit get_mondo_data(struct mdesc_handle *hp, u64 mp, struct trap_per_cpu *tb) { + static int printed; const u64 *val; val = mdesc_get_property(hp, mp, "q-cpu-mondo-#bits", NULL); - get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7); + get_one_mondo_bits(val, &tb->cpu_mondo_qmask, 7, ilog2(max_cpus * 2)); val = mdesc_get_property(hp, mp, "q-dev-mondo-#bits", NULL); - get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7); + get_one_mondo_bits(val, &tb->dev_mondo_qmask, 7, 8); val = mdesc_get_property(hp, mp, "q-resumable-#bits", NULL); - get_one_mondo_bits(val, &tb->resum_qmask, 6); + get_one_mondo_bits(val, &tb->resum_qmask, 6, 7); val = mdesc_get_property(hp, mp, "q-nonresumable-#bits", NULL); - get_one_mondo_bits(val, &tb->nonresum_qmask, 2); + get_one_mondo_bits(val, &tb->nonresum_qmask, 2, 2); + if (!printed++) { + pr_info("SUN4V: Mondo queue sizes " + "[cpu(%u) dev(%u) r(%u) nr(%u)]\n", + tb->cpu_mondo_qmask + 1, + tb->dev_mondo_qmask + 1, + tb->resum_qmask + 1, + tb->nonresum_qmask + 1); + } } static void * __cpuinit mdesc_iterate_over_cpus(void *(*func)(struct mdesc_handle *, u64, int, void *), void *arg, cpumask_t *mask) diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index 99ba5baa9497..e5519870c3d9 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -17,6 +17,8 @@ #include <asm/processor.h> #include <asm/spitfire.h> +#include "entry.h" + #ifdef CONFIG_SPARC64 #include <linux/jump_label.h> @@ -68,12 +70,6 @@ void *module_alloc(unsigned long size) return ret; } -/* Free memory returned from module_core_alloc/module_init_alloc */ -void module_free(struct module *mod, void *module_region) -{ - vfree(module_region); -} - /* Make generic code ignore STT_REGISTER dummy undefined symbols. */ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, @@ -107,17 +103,6 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, return 0; } -int apply_relocate(Elf_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - printk(KERN_ERR "module %s: non-ADD RELOCATION unsupported\n", - me->name); - return -ENOEXEC; -} - int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, unsigned int symindex, @@ -220,6 +205,29 @@ int apply_relocate_add(Elf_Shdr *sechdrs, } #ifdef CONFIG_SPARC64 +static void do_patch_sections(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs) +{ + const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL; + char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { + if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name)) + sun4v_1insn = s; + if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name)) + sun4v_2insn = s; + } + + if (sun4v_1insn && tlb_type == hypervisor) { + void *p = (void *) sun4v_1insn->sh_addr; + sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size); + } + if (sun4v_2insn && tlb_type == hypervisor) { + void *p = (void *) sun4v_2insn->sh_addr; + sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size); + } +} + int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) @@ -227,6 +235,8 @@ int module_finalize(const Elf_Ehdr *hdr, /* make jump label nops */ jump_label_apply_nops(me); + do_patch_sections(hdr, sechdrs); + /* Cheetah's I-cache is fully coherent. */ if (tlb_type == spitfire) { unsigned long va; @@ -239,15 +249,4 @@ int module_finalize(const Elf_Ehdr *hdr, return 0; } -#else -int module_finalize(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - struct module *me) -{ - return 0; -} #endif /* CONFIG_SPARC64 */ - -void module_arch_cleanup(struct module *mod) -{ -} diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c index 300f810142f5..c76fe0b5bd94 100644 --- a/arch/sparc/kernel/nmi.c +++ b/arch/sparc/kernel/nmi.c @@ -10,7 +10,7 @@ #include <linux/init.h> #include <linux/percpu.h> #include <linux/nmi.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/kprobes.h> #include <linux/kernel_stat.h> #include <linux/reboot.h> diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index a312af40ea84..4ee8ce0d5d8d 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -2,7 +2,6 @@ #include <linux/kernel.h> #include <linux/of.h> #include <linux/init.h> -#include <linux/module.h> #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/errno.h> diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 3bb2eace58cf..7a3be6f6737a 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -2,13 +2,14 @@ #include <linux/kernel.h> #include <linux/of.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/irq.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <asm/spitfire.h> #include "of_device_common.h" diff --git a/arch/sparc/kernel/of_device_common.c b/arch/sparc/kernel/of_device_common.c index cb15bbf8a201..de199bf0cb05 100644 --- a/arch/sparc/kernel/of_device_common.c +++ b/arch/sparc/kernel/of_device_common.c @@ -2,7 +2,7 @@ #include <linux/kernel.h> #include <linux/of.h> #include <linux/init.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mod_devicetable.h> #include <linux/errno.h> #include <linux/irq.h> diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 713dc91020a6..31111e35281e 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -8,7 +8,7 @@ * with minor modifications, see there for credits. */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sched.h> @@ -230,7 +230,8 @@ static void pci_parse_of_addrs(struct platform_device *op, res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2]; } else if (i == dev->rom_base_reg) { res = &dev->resource[PCI_ROM_RESOURCE]; - flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE; + flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE + | IORESOURCE_SIZEALIGN; } else { printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i); continue; @@ -284,7 +285,7 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, dev->sysdata = node; dev->dev.parent = bus->bridge; dev->dev.bus = &pci_bus_type; - dev->dev.of_node = node; + dev->dev.of_node = of_node_get(node); dev->devfn = devfn; dev->multifunction = 0; /* maybe a lie? */ set_pcie_port_type(dev); @@ -820,11 +821,9 @@ static int __pci_mmap_make_offset_bus(struct pci_dev *pdev, struct vm_area_struc unsigned long space_size, user_offset, user_size; if (mmap_state == pci_mmap_io) { - space_size = (pbm->io_space.end - - pbm->io_space.start) + 1; + space_size = resource_size(&pbm->io_space); } else { - space_size = (pbm->mem_space.end - - pbm->mem_space.start) + 1; + space_size = resource_size(&pbm->mem_space); } /* Make sure the request is in range. */ @@ -1021,12 +1020,6 @@ void arch_teardown_msi_irq(unsigned int irq) } #endif /* !(CONFIG_PCI_MSI) */ -struct device_node *pci_device_to_OF_node(struct pci_dev *pdev) -{ - return pdev->dev.of_node; -} -EXPORT_SYMBOL(pci_device_to_OF_node); - static void ali_sound_dma_hack(struct pci_dev *pdev, int set_bit) { struct pci_dev *ali_isa_bridge; diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c index d29a32fcc5e4..188f935276fd 100644 --- a/arch/sparc/kernel/pci_fire.c +++ b/arch/sparc/kernel/pci_fire.c @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/init.h> #include <linux/msi.h> +#include <linux/export.h> #include <linux/irq.h> #include <linux/of_device.h> diff --git a/arch/sparc/kernel/pci_psycho.c b/arch/sparc/kernel/pci_psycho.c index 86ae08d9b6ee..f4d29e15ce71 100644 --- a/arch/sparc/kernel/pci_psycho.c +++ b/arch/sparc/kernel/pci_psycho.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/pci.h> #include <linux/init.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/of_device.h> diff --git a/arch/sparc/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c index d1840dbdaa2f..3efaa4644d60 100644 --- a/arch/sparc/kernel/pci_sabre.c +++ b/arch/sparc/kernel/pci_sabre.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/pci.h> #include <linux/init.h> +#include <linux/export.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/of_device.h> diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index f030b02edddd..13d4aa20b5a5 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -8,6 +8,7 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/export.h> #include <linux/interrupt.h> #include <linux/of_device.h> diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index b01a06e9ae4e..b272cda35a01 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -12,6 +12,7 @@ #include <linux/percpu.h> #include <linux/irq.h> #include <linux/msi.h> +#include <linux/export.h> #include <linux/log2.h> #include <linux/of_device.h> diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index 948601a066ff..fcc148effaac 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -25,6 +25,7 @@ #include <linux/time.h> #include <linux/timex.h> #include <linux/interrupt.h> +#include <linux/export.h> #include <asm/irq.h> #include <asm/oplib.h> @@ -352,8 +353,8 @@ int __init pcic_probe(void) strcpy(pbm->prom_name, namebuf); { - extern volatile int t_nmi[1]; - extern int pcic_nmi_trap_patch[1]; + extern volatile int t_nmi[4]; + extern int pcic_nmi_trap_patch[4]; t_nmi[0] = pcic_nmi_trap_patch[0]; t_nmi[1] = pcic_nmi_trap_patch[1]; @@ -885,14 +886,6 @@ int pcibios_assign_resource(struct pci_dev *pdev, int resource) return -ENXIO; } -struct device_node *pci_device_to_OF_node(struct pci_dev *pdev) -{ - struct pcidev_cookie *pc = pdev->sysdata; - - return pc->prom_node; -} -EXPORT_SYMBOL(pci_device_to_OF_node); - /* * This probably belongs here rather than ioport.c because * we do not want this crud linked into SBus kernels. diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c index 8ac23e660080..a24072a49270 100644 --- a/arch/sparc/kernel/pcr.c +++ b/arch/sparc/kernel/pcr.c @@ -3,7 +3,7 @@ * Copyright (C) 2009 David S. Miller (davem@davemloft.net) */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/irq.h> @@ -13,6 +13,7 @@ #include <asm/pil.h> #include <asm/pcr.h> #include <asm/nmi.h> +#include <asm/spitfire.h> /* This code is shared between various users of the performance * counters. Users will be oprofile, pseudo-NMI watchdog, and the @@ -80,8 +81,11 @@ static void n2_pcr_write(u64 val) { unsigned long ret; - ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val); - if (ret != HV_EOK) + if (val & PCR_N2_HTRACE) { + ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val); + if (ret != HV_EOK) + write_pcr(val); + } else write_pcr(val); } @@ -106,6 +110,10 @@ static int __init register_perf_hsvc(void) perf_hsvc_group = HV_GRP_N2_CPU; break; + case SUN4V_CHIP_NIAGARA3: + perf_hsvc_group = HV_GRP_KT_CPU; + break; + default: return -ENODEV; } diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 2cb0e1c001e2..614da624330c 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -22,7 +22,7 @@ #include <asm/stacktrace.h> #include <asm/cpudata.h> #include <asm/uaccess.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/nmi.h> #include <asm/pcr.h> @@ -246,6 +246,20 @@ static const cache_map_t ultra3_cache_map = { [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, }, }, +[C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { CACHE_OP_UNSUPPORTED }, + [C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED }, + [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED }, + [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, +}, }; static const struct sparc_pmu ultra3_pmu = { @@ -361,6 +375,20 @@ static const cache_map_t niagara1_cache_map = { [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, }, }, +[C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { CACHE_OP_UNSUPPORTED }, + [C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED }, + [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED }, + [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, +}, }; static const struct sparc_pmu niagara1_pmu = { @@ -473,6 +501,20 @@ static const cache_map_t niagara2_cache_map = { [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, }, }, +[C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = { CACHE_OP_UNSUPPORTED }, + [C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED }, + [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED }, + [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED }, + }, +}, }; static const struct sparc_pmu niagara2_pmu = { @@ -1277,7 +1319,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self, if (!sparc_perf_event_set_period(event, hwc, idx)) continue; - if (perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) sparc_pmu_stop(event, 0); } @@ -1301,7 +1343,8 @@ static bool __init supported_pmu(void) sparc_pmu = &niagara1_pmu; return true; } - if (!strcmp(sparc_pmu_type, "niagara2")) { + if (!strcmp(sparc_pmu_type, "niagara2") || + !strcmp(sparc_pmu_type, "niagara3")) { sparc_pmu = &niagara2_pmu; return true; } diff --git a/arch/sparc/kernel/pmc.c b/arch/sparc/kernel/pmc.c index 6a585d393580..0e3202239ff5 100644 --- a/arch/sparc/kernel/pmc.c +++ b/arch/sparc/kernel/pmc.c @@ -11,6 +11,7 @@ #include <linux/pm.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/module.h> #include <asm/io.h> #include <asm/oplib.h> diff --git a/arch/sparc/kernel/power.c b/arch/sparc/kernel/power.c index cb4c0f57c024..0d39075063b2 100644 --- a/arch/sparc/kernel/power.c +++ b/arch/sparc/kernel/power.c @@ -4,7 +4,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/reboot.h> diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index c8cc461ff75f..f793742eec2b 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -380,8 +380,7 @@ void flush_thread(void) #endif } - /* Now, this task is no longer a kernel thread. */ - current->thread.current_ds = USER_DS; + /* This task is no longer a kernel thread. */ if (current->thread.flags & SPARC_FLAG_KTHREAD) { current->thread.flags &= ~SPARC_FLAG_KTHREAD; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index c158a95ec664..3739a06a76cb 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -12,7 +12,7 @@ #include <stdarg.h> #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/mm.h> @@ -368,9 +368,6 @@ void flush_thread(void) /* Clear FPU register state. */ t->fpsaved[0] = 0; - - if (get_thread_current_ds() != ASI_AIUS) - set_fs(USER_DS); } /* It's a bit more tricky when 64-bit tasks are involved... */ diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index 5ce3d15a99b0..b51cbb9e87dc 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -20,7 +20,6 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/bootmem.h> -#include <linux/module.h> #include <asm/prom.h> #include <asm/oplib.h> diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index 86597d9867fd..340c5b976d28 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -19,7 +19,6 @@ #include <linux/types.h> #include <linux/string.h> #include <linux/mm.h> -#include <linux/module.h> #include <linux/memblock.h> #include <linux/of.h> diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c index ed25834328f4..46614807a57f 100644 --- a/arch/sparc/kernel/prom_common.c +++ b/arch/sparc/kernel/prom_common.c @@ -15,7 +15,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/errno.h> #include <linux/mutex.h> #include <linux/slab.h> diff --git a/arch/sparc/kernel/reboot.c b/arch/sparc/kernel/reboot.c index ef89d3d69748..006a42dd2007 100644 --- a/arch/sparc/kernel/reboot.c +++ b/arch/sparc/kernel/reboot.c @@ -4,7 +4,7 @@ */ #include <linux/kernel.h> #include <linux/reboot.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/pm.h> #include <asm/system.h> diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index a161b9c77f05..1271b3a27d4e 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/slab.h> +#include <linux/export.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/of.h> diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index d26e1f6c717a..fe1e3fc31bc5 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -31,6 +31,7 @@ #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/kdebug.h> +#include <linux/export.h> #include <asm/system.h> #include <asm/io.h> @@ -137,7 +138,7 @@ static void __init process_switch(char c) prom_halt(); break; case 'p': - /* Just ignore, this behavior is now the default. */ + prom_early_console.flags &= ~CON_BOOT; break; default: printk("Unknown boot switch (-%c)\n", c); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index c4dd0999da86..a854a1c240ff 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -29,6 +29,7 @@ #include <linux/interrupt.h> #include <linux/cpu.h> #include <linux/initrd.h> +#include <linux/module.h> #include <asm/system.h> #include <asm/io.h> @@ -46,6 +47,8 @@ #include <asm/mmu.h> #include <asm/ns87303.h> #include <asm/btext.h> +#include <asm/elf.h> +#include <asm/mdesc.h> #ifdef CONFIG_IP_PNP #include <net/ipconfig.h> @@ -103,7 +106,7 @@ static void __init process_switch(char c) prom_halt(); break; case 'p': - /* Just ignore, this behavior is now the default. */ + prom_early_console.flags &= ~CON_BOOT; break; case 'P': /* Force UltraSPARC-III P-Cache on. */ @@ -231,44 +234,88 @@ void __init per_cpu_patch(void) } } -void __init sun4v_patch(void) +void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start, + struct sun4v_1insn_patch_entry *end) { - extern void sun4v_hvapi_init(void); - struct sun4v_1insn_patch_entry *p1; - struct sun4v_2insn_patch_entry *p2; - - if (tlb_type != hypervisor) - return; + while (start < end) { + unsigned long addr = start->addr; - p1 = &__sun4v_1insn_patch; - while (p1 < &__sun4v_1insn_patch_end) { - unsigned long addr = p1->addr; - - *(unsigned int *) (addr + 0) = p1->insn; + *(unsigned int *) (addr + 0) = start->insn; wmb(); __asm__ __volatile__("flush %0" : : "r" (addr + 0)); - p1++; + start++; } +} - p2 = &__sun4v_2insn_patch; - while (p2 < &__sun4v_2insn_patch_end) { - unsigned long addr = p2->addr; +void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start, + struct sun4v_2insn_patch_entry *end) +{ + while (start < end) { + unsigned long addr = start->addr; - *(unsigned int *) (addr + 0) = p2->insns[0]; + *(unsigned int *) (addr + 0) = start->insns[0]; wmb(); __asm__ __volatile__("flush %0" : : "r" (addr + 0)); - *(unsigned int *) (addr + 4) = p2->insns[1]; + *(unsigned int *) (addr + 4) = start->insns[1]; wmb(); __asm__ __volatile__("flush %0" : : "r" (addr + 4)); - p2++; + start++; } +} + +void __init sun4v_patch(void) +{ + extern void sun4v_hvapi_init(void); + + if (tlb_type != hypervisor) + return; + + sun4v_patch_1insn_range(&__sun4v_1insn_patch, + &__sun4v_1insn_patch_end); + + sun4v_patch_2insn_range(&__sun4v_2insn_patch, + &__sun4v_2insn_patch_end); sun4v_hvapi_init(); } +static void __init popc_patch(void) +{ + struct popc_3insn_patch_entry *p3; + struct popc_6insn_patch_entry *p6; + + p3 = &__popc_3insn_patch; + while (p3 < &__popc_3insn_patch_end) { + unsigned long i, addr = p3->addr; + + for (i = 0; i < 3; i++) { + *(unsigned int *) (addr + (i * 4)) = p3->insns[i]; + wmb(); + __asm__ __volatile__("flush %0" + : : "r" (addr + (i * 4))); + } + + p3++; + } + + p6 = &__popc_6insn_patch; + while (p6 < &__popc_6insn_patch_end) { + unsigned long i, addr = p6->addr; + + for (i = 0; i < 6; i++) { + *(unsigned int *) (addr + (i * 4)) = p6->insns[i]; + wmb(); + __asm__ __volatile__("flush %0" + : : "r" (addr + (i * 4))); + } + + p6++; + } +} + #ifdef CONFIG_SMP void __init boot_cpu_id_too_large(int cpu) { @@ -278,6 +325,168 @@ void __init boot_cpu_id_too_large(int cpu) } #endif +/* On Ultra, we support all of the v8 capabilities. */ +unsigned long sparc64_elf_hwcap = (HWCAP_SPARC_FLUSH | HWCAP_SPARC_STBAR | + HWCAP_SPARC_SWAP | HWCAP_SPARC_MULDIV | + HWCAP_SPARC_V9); +EXPORT_SYMBOL(sparc64_elf_hwcap); + +static const char *hwcaps[] = { + "flush", "stbar", "swap", "muldiv", "v9", + "ultra3", "blkinit", "n2", + + /* These strings are as they appear in the machine description + * 'hwcap-list' property for cpu nodes. + */ + "mul32", "div32", "fsmuld", "v8plus", "popc", "vis", "vis2", + "ASIBlkInit", "fmaf", "vis3", "hpc", "random", "trans", "fjfmau", + "ima", "cspare", +}; + +void cpucap_info(struct seq_file *m) +{ + unsigned long caps = sparc64_elf_hwcap; + int i, printed = 0; + + seq_puts(m, "cpucaps\t\t: "); + for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { + unsigned long bit = 1UL << i; + if (caps & bit) { + seq_printf(m, "%s%s", + printed ? "," : "", hwcaps[i]); + printed++; + } + } + seq_putc(m, '\n'); +} + +static void __init report_hwcaps(unsigned long caps) +{ + int i, printed = 0; + + printk(KERN_INFO "CPU CAPS: ["); + for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { + unsigned long bit = 1UL << i; + if (caps & bit) { + printk(KERN_CONT "%s%s", + printed ? "," : "", hwcaps[i]); + if (++printed == 8) { + printk(KERN_CONT "]\n"); + printk(KERN_INFO "CPU CAPS: ["); + printed = 0; + } + } + } + printk(KERN_CONT "]\n"); +} + +static unsigned long __init mdesc_cpu_hwcap_list(void) +{ + struct mdesc_handle *hp; + unsigned long caps = 0; + const char *prop; + int len; + u64 pn; + + hp = mdesc_grab(); + if (!hp) + return 0; + + pn = mdesc_node_by_name(hp, MDESC_NODE_NULL, "cpu"); + if (pn == MDESC_NODE_NULL) + goto out; + + prop = mdesc_get_property(hp, pn, "hwcap-list", &len); + if (!prop) + goto out; + + while (len) { + int i, plen; + + for (i = 0; i < ARRAY_SIZE(hwcaps); i++) { + unsigned long bit = 1UL << i; + + if (!strcmp(prop, hwcaps[i])) { + caps |= bit; + break; + } + } + + plen = strlen(prop) + 1; + prop += plen; + len -= plen; + } + +out: + mdesc_release(hp); + return caps; +} + +/* This yields a mask that user programs can use to figure out what + * instruction set this cpu supports. + */ +static void __init init_sparc64_elf_hwcap(void) +{ + unsigned long cap = sparc64_elf_hwcap; + unsigned long mdesc_caps; + + if (tlb_type == cheetah || tlb_type == cheetah_plus) + cap |= HWCAP_SPARC_ULTRA3; + else if (tlb_type == hypervisor) { + if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) + cap |= HWCAP_SPARC_BLKINIT; + if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) + cap |= HWCAP_SPARC_N2; + } + + cap |= (AV_SPARC_MUL32 | AV_SPARC_DIV32 | AV_SPARC_V8PLUS); + + mdesc_caps = mdesc_cpu_hwcap_list(); + if (!mdesc_caps) { + if (tlb_type == spitfire) + cap |= AV_SPARC_VIS; + if (tlb_type == cheetah || tlb_type == cheetah_plus) + cap |= AV_SPARC_VIS | AV_SPARC_VIS2; + if (tlb_type == cheetah_plus) { + unsigned long impl, ver; + + __asm__ __volatile__("rdpr %%ver, %0" : "=r" (ver)); + impl = ((ver >> 32) & 0xffff); + if (impl == PANTHER_IMPL) + cap |= AV_SPARC_POPC; + } + if (tlb_type == hypervisor) { + if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1) + cap |= AV_SPARC_ASI_BLK_INIT; + if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) + cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | + AV_SPARC_ASI_BLK_INIT | + AV_SPARC_POPC); + if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || + sun4v_chip_type == SUN4V_CHIP_NIAGARA5) + cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | + AV_SPARC_FMAF); + } + } + sparc64_elf_hwcap = cap | mdesc_caps; + + report_hwcaps(sparc64_elf_hwcap); + + if (sparc64_elf_hwcap & AV_SPARC_POPC) + popc_patch(); +} + void __init setup_arch(char **cmdline_p) { /* Initialize PROM console and command line. */ @@ -337,6 +546,7 @@ void __init setup_arch(char **cmdline_p) init_cur_cpu_trap(current_thread_info()); paging_init(); + init_sparc64_elf_hwcap(); } extern int stop_a_enabled; diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 75fad425e249..023b8860dc97 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -29,6 +29,8 @@ #include <asm/visasm.h> #include <asm/compat_signal.h> +#include "sigutil.h" + #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) /* This magic should be in g_upper[0] for all upper parts @@ -44,14 +46,14 @@ typedef struct { struct signal_frame32 { struct sparc_stackf32 ss; __siginfo32_t info; - /* __siginfo_fpu32_t * */ u32 fpu_save; + /* __siginfo_fpu_t * */ u32 fpu_save; unsigned int insns[2]; unsigned int extramask[_COMPAT_NSIG_WORDS - 1]; unsigned int extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */ /* Only valid if (info.si_regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */ siginfo_extra_v8plus_t v8plus; - __siginfo_fpu_t fpu_state; -}; + /* __siginfo_rwin_t * */u32 rwin_save; +} __attribute__((aligned(8))); typedef struct compat_siginfo{ int si_signo; @@ -110,18 +112,14 @@ struct rt_signal_frame32 { compat_siginfo_t info; struct pt_regs32 regs; compat_sigset_t mask; - /* __siginfo_fpu32_t * */ u32 fpu_save; + /* __siginfo_fpu_t * */ u32 fpu_save; unsigned int insns[2]; stack_t32 stack; unsigned int extra_size; /* Should be sizeof(siginfo_extra_v8plus_t) */ /* Only valid if (regs.psr & (PSR_VERS|PSR_IMPL)) == PSR_V8PLUS */ siginfo_extra_v8plus_t v8plus; - __siginfo_fpu_t fpu_state; -}; - -/* Align macros */ -#define SF_ALIGNEDSZ (((sizeof(struct signal_frame32) + 15) & (~15))) -#define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame32) + 15) & (~15))) + /* __siginfo_rwin_t * */u32 rwin_save; +} __attribute__((aligned(8))); int copy_siginfo_to_user32(compat_siginfo_t __user *to, siginfo_t *from) { @@ -192,30 +190,13 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return 0; } -static int restore_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err; - - err = __get_user(fprs, &fpu->si_fprs); - fprs_write(0); - regs->tstate &= ~TSTATE_PEF; - if (fprs & FPRS_DL) - err |= copy_from_user(fpregs, &fpu->si_float_regs[0], (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], (sizeof(unsigned int) * 32)); - err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr); - current_thread_info()->fpsaved[0] |= fprs; - return err; -} - void do_sigreturn32(struct pt_regs *regs) { struct signal_frame32 __user *sf; + compat_uptr_t fpu_save; + compat_uptr_t rwin_save; unsigned int psr; - unsigned pc, npc, fpu_save; + unsigned pc, npc; sigset_t set; unsigned seta[_COMPAT_NSIG_WORDS]; int err, i; @@ -273,8 +254,13 @@ void do_sigreturn32(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) - err |= restore_fpu_state32(regs, &sf->fpu_state); + if (!err && fpu_save) + err |= restore_fpu_state(regs, compat_ptr(fpu_save)); + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(compat_ptr(rwin_save))) + goto segv; + } err |= __get_user(seta[0], &sf->info.si_mask); err |= copy_from_user(seta+1, &sf->extramask, (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int)); @@ -287,10 +273,7 @@ void do_sigreturn32(struct pt_regs *regs) case 1: set.sig[0] = seta[0] + (((long)seta[1]) << 32); } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: @@ -300,7 +283,9 @@ segv: asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) { struct rt_signal_frame32 __user *sf; - unsigned int psr, pc, npc, fpu_save, u_ss_sp; + unsigned int psr, pc, npc, u_ss_sp; + compat_uptr_t fpu_save; + compat_uptr_t rwin_save; mm_segment_t old_fs; sigset_t set; compat_sigset_t seta; @@ -359,8 +344,8 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) - err |= restore_fpu_state32(regs, &sf->fpu_state); + if (!err && fpu_save) + err |= restore_fpu_state(regs, compat_ptr(fpu_save)); err |= copy_from_user(&seta, &sf->mask, sizeof(compat_sigset_t)); err |= __get_user(u_ss_sp, &sf->stack.ss_sp); st.ss_sp = compat_ptr(u_ss_sp); @@ -376,6 +361,12 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) do_sigaltstack((stack_t __user *) &st, NULL, (unsigned long)sf); set_fs(old_fs); + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(compat_ptr(rwin_save))) + goto segv; + } + switch (_NSIG_WORDS) { case 4: set.sig[3] = seta.sig[6] + (((long)seta.sig[7]) << 32); case 3: set.sig[2] = seta.sig[4] + (((long)seta.sig[5]) << 32); @@ -383,10 +374,7 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) case 1: set.sig[0] = seta.sig[0] + (((long)seta.sig[1]) << 32); } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -433,26 +421,6 @@ static void __user *get_sigframe(struct sigaction *sa, struct pt_regs *regs, uns return (void __user *) sp; } -static int save_fpu_state32(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err = 0; - - fprs = current_thread_info()->fpsaved[0]; - if (fprs & FPRS_DL) - err |= copy_to_user(&fpu->si_float_regs[0], fpregs, - (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16, - (sizeof(unsigned int) * 32)); - err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr); - err |= __put_user(fprs, &fpu->si_fprs); - - return err; -} - /* The I-cache flush instruction only works in the primary ASI, which * right now is the nucleus, aka. kernel space. * @@ -515,18 +483,23 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset) { struct signal_frame32 __user *sf; + int i, err, wsaved; + void __user *tail; int sigframe_size; u32 psr; - int i, err; unsigned int seta[_COMPAT_NSIG_WORDS]; /* 1. Make sure everything is clean */ synchronize_user_stack(); save_and_clear_fpu(); - sigframe_size = SF_ALIGNEDSZ; - if (!(current_thread_info()->fpsaved[0] & FPRS_FEF)) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = get_thread_wsaved(); + + sigframe_size = sizeof(*sf); + if (current_thread_info()->fpsaved[0] & FPRS_FEF) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct signal_frame32 __user *) get_sigframe(&ka->sa, regs, sigframe_size); @@ -534,8 +507,7 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (invalid_frame_pointer(sf, sigframe_size)) goto sigill; - if (get_thread_wsaved() != 0) - goto sigill; + tail = (sf + 1); /* 2. Save the current process state */ if (test_thread_flag(TIF_32BIT)) { @@ -560,11 +532,22 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, &sf->v8plus.asi); if (psr & PSR_EF) { - err |= save_fpu_state32(regs, &sf->fpu_state); - err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user((u64)fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user((u64)rwp, &sf->rwin_save); + set_thread_wsaved(0); + } else { + err |= __put_user(0, &sf->rwin_save); + } switch (_NSIG_WORDS) { case 4: seta[7] = (oldset->sig[3] >> 32); @@ -580,10 +563,21 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, err |= __copy_to_user(sf->extramask, seta + 1, (_COMPAT_NSIG_WORDS - 1) * sizeof(unsigned int)); - err |= copy_in_user((u32 __user *)sf, - (u32 __user *)(regs->u_regs[UREG_FP]), - sizeof(struct reg_window32)); - + if (!wsaved) { + err |= copy_in_user((u32 __user *)sf, + (u32 __user *)(regs->u_regs[UREG_FP]), + sizeof(struct reg_window32)); + } else { + struct reg_window *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + for (i = 0; i < 8; i++) + err |= __put_user(rp->locals[i], &sf->ss.locals[i]); + for (i = 0; i < 6; i++) + err |= __put_user(rp->ins[i], &sf->ss.ins[i]); + err |= __put_user(rp->ins[6], &sf->ss.fp); + err |= __put_user(rp->ins[7], &sf->ss.callers_pc); + } if (err) goto sigsegv; @@ -613,7 +607,6 @@ static int setup_frame32(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(0x91d02010, &sf->insns[1]); /*t 0x10*/ if (err) goto sigsegv; - flush_signal_insns(address); } return 0; @@ -632,18 +625,23 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, siginfo_t *info) { struct rt_signal_frame32 __user *sf; + int i, err, wsaved; + void __user *tail; int sigframe_size; u32 psr; - int i, err; compat_sigset_t seta; /* 1. Make sure everything is clean */ synchronize_user_stack(); save_and_clear_fpu(); - sigframe_size = RT_ALIGNEDSZ; - if (!(current_thread_info()->fpsaved[0] & FPRS_FEF)) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = get_thread_wsaved(); + + sigframe_size = sizeof(*sf); + if (current_thread_info()->fpsaved[0] & FPRS_FEF) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct rt_signal_frame32 __user *) get_sigframe(&ka->sa, regs, sigframe_size); @@ -651,8 +649,7 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, if (invalid_frame_pointer(sf, sigframe_size)) goto sigill; - if (get_thread_wsaved() != 0) - goto sigill; + tail = (sf + 1); /* 2. Save the current process state */ if (test_thread_flag(TIF_32BIT)) { @@ -677,11 +674,22 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, &sf->v8plus.asi); if (psr & PSR_EF) { - err |= save_fpu_state32(regs, &sf->fpu_state); - err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user((u64)fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user((u64)rwp, &sf->rwin_save); + set_thread_wsaved(0); + } else { + err |= __put_user(0, &sf->rwin_save); + } /* Update the siginfo structure. */ err |= copy_siginfo_to_user32(&sf->info, info); @@ -703,9 +711,21 @@ static int setup_rt_frame32(struct k_sigaction *ka, struct pt_regs *regs, } err |= __copy_to_user(&sf->mask, &seta, sizeof(compat_sigset_t)); - err |= copy_in_user((u32 __user *)sf, - (u32 __user *)(regs->u_regs[UREG_FP]), - sizeof(struct reg_window32)); + if (!wsaved) { + err |= copy_in_user((u32 __user *)sf, + (u32 __user *)(regs->u_regs[UREG_FP]), + sizeof(struct reg_window32)); + } else { + struct reg_window *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + for (i = 0; i < 8; i++) + err |= __put_user(rp->locals[i], &sf->ss.locals[i]); + for (i = 0; i < 6; i++) + err |= __put_user(rp->ins[i], &sf->ss.ins[i]); + err |= __put_user(rp->ins[6], &sf->ss.fp); + err |= __put_user(rp->ins[7], &sf->ss.callers_pc); + } if (err) goto sigsegv; @@ -756,6 +776,7 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; if (ka->sa.sa_flags & SA_SIGINFO) @@ -766,12 +787,10 @@ static inline int handle_signal32(unsigned long signr, struct k_sigaction *ka, if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked,signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -803,21 +822,23 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void do_signal32(sigset_t *oldset, struct pt_regs * regs, - int restart_syscall, unsigned long orig_i0) +void do_signal32(sigset_t *oldset, struct pt_regs * regs) { struct k_sigaction ka; + unsigned long orig_i0; + int restart_syscall; siginfo_t info; int signr; signr = get_signal_to_deliver(&info, &ka, regs, NULL); - /* If the debugger messes with the program counter, it clears - * the "in syscall" bit, directing us to not perform a syscall - * restart. - */ - if (restart_syscall && !pt_regs_is_syscall(regs)) - restart_syscall = 0; + restart_syscall = 0; + orig_i0 = 0; + if (pt_regs_is_syscall(regs) && + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { + restart_syscall = 1; + orig_i0 = regs->u_regs[UREG_G6]; + } if (signr > 0) { if (restart_syscall) @@ -855,7 +876,7 @@ void do_signal32(sigset_t *oldset, struct pt_regs * regs, */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 5e5c5fd03783..d54c6e53aba0 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -26,6 +26,8 @@ #include <asm/pgtable.h> #include <asm/cacheflush.h> /* flush_sig_insns */ +#include "sigutil.h" + #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) extern void fpsave(unsigned long *fpregs, unsigned long *fsr, @@ -39,8 +41,8 @@ struct signal_frame { unsigned long insns[2] __attribute__ ((aligned (8))); unsigned int extramask[_NSIG_WORDS - 1]; unsigned int extra_size; /* Should be 0 */ - __siginfo_fpu_t fpu_state; -}; + __siginfo_rwin_t __user *rwin_save; +} __attribute__((aligned(8))); struct rt_signal_frame { struct sparc_stackf ss; @@ -51,8 +53,8 @@ struct rt_signal_frame { unsigned int insns[2]; stack_t stack; unsigned int extra_size; /* Should be 0 */ - __siginfo_fpu_t fpu_state; -}; + __siginfo_rwin_t __user *rwin_save; +} __attribute__((aligned(8))); /* Align macros */ #define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7))) @@ -60,12 +62,13 @@ struct rt_signal_frame { static int _sigpause_common(old_sigset_t set) { - set &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, set); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + set &= _BLOCKABLE; + siginitset(&blocked, set); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -79,43 +82,13 @@ asmlinkage int sys_sigsuspend(old_sigset_t set) return _sigpause_common(set); } -static inline int -restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - int err; -#ifdef CONFIG_SMP - if (test_tsk_thread_flag(current, TIF_USEDFPU)) - regs->psr &= ~PSR_EF; -#else - if (current == last_task_used_math) { - last_task_used_math = NULL; - regs->psr &= ~PSR_EF; - } -#endif - set_used_math(); - clear_tsk_thread_flag(current, TIF_USEDFPU); - - if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu))) - return -EFAULT; - - err = __copy_from_user(¤t->thread.float_regs[0], &fpu->si_float_regs[0], - (sizeof(unsigned long) * 32)); - err |= __get_user(current->thread.fsr, &fpu->si_fsr); - err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth); - if (current->thread.fpqdepth != 0) - err |= __copy_from_user(¤t->thread.fpqueue[0], - &fpu->si_fpqueue[0], - ((sizeof(unsigned long) + - (sizeof(unsigned long *)))*16)); - return err; -} - asmlinkage void do_sigreturn(struct pt_regs *regs) { struct signal_frame __user *sf; unsigned long up_psr, pc, npc; sigset_t set; __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; int err; /* Always make any pending restarted system calls return -EINTR */ @@ -150,9 +123,11 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) err |= restore_fpu_state(regs, fpu_save); + err |= __get_user(rwin_save, &sf->rwin_save); + if (rwin_save) + err |= restore_rwin_state(rwin_save); /* This is pretty much atomic, no amount locking would prevent * the races which exist anyways. @@ -165,10 +140,7 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) goto segv_and_exit; sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv_and_exit: @@ -180,6 +152,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) struct rt_signal_frame __user *sf; unsigned int psr, pc, npc; __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; mm_segment_t old_fs; sigset_t set; stack_t st; @@ -207,8 +180,7 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); err |= __get_user(fpu_save, &sf->fpu_save); - - if (fpu_save) + if (!err && fpu_save) err |= restore_fpu_state(regs, fpu_save); err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t)); @@ -228,11 +200,14 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) do_sigaltstack((const stack_t __user *) &st, NULL, (unsigned long)sf); set_fs(old_fs); + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(rwin_save)) + goto segv; + } + sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); @@ -280,53 +255,23 @@ static inline void __user *get_sigframe(struct sigaction *sa, struct pt_regs *re return (void __user *) sp; } -static inline int -save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - int err = 0; -#ifdef CONFIG_SMP - if (test_tsk_thread_flag(current, TIF_USEDFPU)) { - put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); - regs->psr &= ~(PSR_EF); - clear_tsk_thread_flag(current, TIF_USEDFPU); - } -#else - if (current == last_task_used_math) { - put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); - last_task_used_math = NULL; - regs->psr &= ~(PSR_EF); - } -#endif - err |= __copy_to_user(&fpu->si_float_regs[0], - ¤t->thread.float_regs[0], - (sizeof(unsigned long) * 32)); - err |= __put_user(current->thread.fsr, &fpu->si_fsr); - err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth); - if (current->thread.fpqdepth != 0) - err |= __copy_to_user(&fpu->si_fpqueue[0], - ¤t->thread.fpqueue[0], - ((sizeof(unsigned long) + - (sizeof(unsigned long *)))*16)); - clear_used_math(); - return err; -} - static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset) { struct signal_frame __user *sf; - int sigframe_size, err; + int sigframe_size, err, wsaved; + void __user *tail; /* 1. Make sure everything is clean */ synchronize_user_stack(); - sigframe_size = SF_ALIGNEDSZ; - if (!used_math()) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = current_thread_info()->w_saved; + + sigframe_size = sizeof(*sf); + if (used_math()) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct signal_frame __user *) get_sigframe(&ka->sa, regs, sigframe_size); @@ -334,8 +279,7 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, if (invalid_frame_pointer(sf, sigframe_size)) goto sigill_and_return; - if (current_thread_info()->w_saved != 0) - goto sigill_and_return; + tail = sf + 1; /* 2. Save the current process state */ err = __copy_to_user(&sf->info.si_regs, regs, sizeof(struct pt_regs)); @@ -343,17 +287,34 @@ static int setup_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(0, &sf->extra_size); if (used_math()) { - err |= save_fpu_state(regs, &sf->fpu_state); - err |= __put_user(&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user(fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user(rwp, &sf->rwin_save); + } else { + err |= __put_user(0, &sf->rwin_save); + } err |= __put_user(oldset->sig[0], &sf->info.si_mask); err |= __copy_to_user(sf->extramask, &oldset->sig[1], (_NSIG_WORDS - 1) * sizeof(unsigned int)); - err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], - sizeof(struct reg_window32)); + if (!wsaved) { + err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], + sizeof(struct reg_window32)); + } else { + struct reg_window32 *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + err |= __copy_to_user(sf, rp, sizeof(struct reg_window32)); + } if (err) goto sigsegv; @@ -399,21 +360,24 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset, siginfo_t *info) { struct rt_signal_frame __user *sf; - int sigframe_size; + int sigframe_size, wsaved; + void __user *tail; unsigned int psr; int err; synchronize_user_stack(); - sigframe_size = RT_ALIGNEDSZ; - if (!used_math()) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = current_thread_info()->w_saved; + sigframe_size = sizeof(*sf); + if (used_math()) + sigframe_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sigframe_size += sizeof(__siginfo_rwin_t); sf = (struct rt_signal_frame __user *) get_sigframe(&ka->sa, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) goto sigill; - if (current_thread_info()->w_saved != 0) - goto sigill; + tail = sf + 1; err = __put_user(regs->pc, &sf->regs.pc); err |= __put_user(regs->npc, &sf->regs.npc); err |= __put_user(regs->y, &sf->regs.y); @@ -425,11 +389,21 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(0, &sf->extra_size); if (psr & PSR_EF) { - err |= save_fpu_state(regs, &sf->fpu_state); - err |= __put_user(&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t *fp = tail; + tail += sizeof(*fp); + err |= save_fpu_state(regs, fp); + err |= __put_user(fp, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t *rwp = tail; + tail += sizeof(*rwp); + err |= save_rwin_state(wsaved, rwp); + err |= __put_user(rwp, &sf->rwin_save); + } else { + err |= __put_user(0, &sf->rwin_save); + } err |= __copy_to_user(&sf->mask, &oldset->sig[0], sizeof(sigset_t)); /* Setup sigaltstack */ @@ -437,8 +411,15 @@ static int setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= __put_user(sas_ss_flags(regs->u_regs[UREG_FP]), &sf->stack.ss_flags); err |= __put_user(current->sas_ss_size, &sf->stack.ss_size); - err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], - sizeof(struct reg_window32)); + if (!wsaved) { + err |= __copy_to_user(sf, (char *) regs->u_regs[UREG_FP], + sizeof(struct reg_window32)); + } else { + struct reg_window32 *rp; + + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + err |= __copy_to_user(sf, rp, sizeof(struct reg_window32)); + } err |= copy_siginfo_to_user(&sf->info, info); @@ -484,6 +465,7 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; if (ka->sa.sa_flags & SA_SIGINFO) @@ -494,12 +476,10 @@ handle_signal(unsigned long signr, struct k_sigaction *ka, if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked, signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -539,10 +519,26 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) siginfo_t info; int signr; + /* It's a lot of work and synchronization to add a new ptrace + * register for GDB to save and restore in order to get + * orig_i0 correct for syscall restarts when debugging. + * + * Although it should be the case that most of the global + * registers are volatile across a system call, glibc already + * depends upon that fact that we preserve them. So we can't + * just use any global register to save away the orig_i0 value. + * + * In particular %g2, %g3, %g4, and %g5 are all assumed to be + * preserved across a system call trap by various pieces of + * code in glibc. + * + * %g7 is used as the "thread register". %g6 is not used in + * any fixed manner. %g6 is used as a scratch register and + * a compiler temporary, but it's value is never used across + * a system call. Therefore %g6 is usable for orig_i0 storage. + */ if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) - restart_syscall = 1; - else - restart_syscall = 0; + regs->u_regs[UREG_G6] = orig_i0; if (test_thread_flag(TIF_RESTORE_SIGMASK)) oldset = ¤t->saved_sigmask; @@ -555,8 +551,12 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) * the software "in syscall" bit, directing us to not perform * a syscall restart. */ - if (restart_syscall && !pt_regs_is_syscall(regs)) - restart_syscall = 0; + restart_syscall = 0; + if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) { + restart_syscall = 1; + orig_i0 = regs->u_regs[UREG_G6]; + } + if (signr > 0) { if (restart_syscall) @@ -595,7 +595,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) */ if (test_thread_flag(TIF_RESTORE_SIGMASK)) { clear_thread_flag(TIF_RESTORE_SIGMASK); - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index 006fe4515886..f0836cd0e2f2 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -34,6 +34,7 @@ #include "entry.h" #include "systbls.h" +#include "sigutil.h" #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) @@ -69,10 +70,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) goto do_sigsegv; } sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); } if (test_thread_flag(TIF_32BIT)) { pc &= 0xffffffff; @@ -236,17 +234,18 @@ struct rt_signal_frame { __siginfo_fpu_t __user *fpu_save; stack_t stack; sigset_t mask; - __siginfo_fpu_t fpu_state; + __siginfo_rwin_t *rwin_save; }; static long _sigpause_common(old_sigset_t set) { - set &= _BLOCKABLE; - spin_lock_irq(¤t->sighand->siglock); + sigset_t blocked; + current->saved_sigmask = current->blocked; - siginitset(¤t->blocked, set); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + + set &= _BLOCKABLE; + siginitset(&blocked, set); + set_current_blocked(&blocked); current->state = TASK_INTERRUPTIBLE; schedule(); @@ -266,33 +265,12 @@ asmlinkage long sys_sigsuspend(old_sigset_t set) return _sigpause_common(set); } -static inline int -restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err; - - err = __get_user(fprs, &fpu->si_fprs); - fprs_write(0); - regs->tstate &= ~TSTATE_PEF; - if (fprs & FPRS_DL) - err |= copy_from_user(fpregs, &fpu->si_float_regs[0], - (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], - (sizeof(unsigned int) * 32)); - err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr); - current_thread_info()->fpsaved[0] |= fprs; - return err; -} - void do_rt_sigreturn(struct pt_regs *regs) { struct rt_signal_frame __user *sf; unsigned long tpc, tnpc, tstate; __siginfo_fpu_t __user *fpu_save; + __siginfo_rwin_t __user *rwin_save; sigset_t set; int err; @@ -325,8 +303,8 @@ void do_rt_sigreturn(struct pt_regs *regs) regs->tstate |= (tstate & (TSTATE_ASI | TSTATE_ICC | TSTATE_XCC)); err |= __get_user(fpu_save, &sf->fpu_save); - if (fpu_save) - err |= restore_fpu_state(regs, &sf->fpu_state); + if (!err && fpu_save) + err |= restore_fpu_state(regs, fpu_save); err |= __copy_from_user(&set, &sf->mask, sizeof(sigset_t)); err |= do_sigaltstack(&sf->stack, NULL, (unsigned long)sf); @@ -334,6 +312,12 @@ void do_rt_sigreturn(struct pt_regs *regs) if (err) goto segv; + err |= __get_user(rwin_save, &sf->rwin_save); + if (!err && rwin_save) { + if (restore_rwin_state(rwin_save)) + goto segv; + } + regs->tpc = tpc; regs->tnpc = tnpc; @@ -341,44 +325,20 @@ void do_rt_sigreturn(struct pt_regs *regs) pt_regs_clear_syscall(regs); sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(¤t->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + set_current_blocked(&set); return; segv: force_sig(SIGSEGV, current); } /* Checks if the fp is valid */ -static int invalid_frame_pointer(void __user *fp, int fplen) +static int invalid_frame_pointer(void __user *fp) { if (((unsigned long) fp) & 15) return 1; return 0; } -static inline int -save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) -{ - unsigned long *fpregs = current_thread_info()->fpregs; - unsigned long fprs; - int err = 0; - - fprs = current_thread_info()->fpsaved[0]; - if (fprs & FPRS_DL) - err |= copy_to_user(&fpu->si_float_regs[0], fpregs, - (sizeof(unsigned int) * 32)); - if (fprs & FPRS_DU) - err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16, - (sizeof(unsigned int) * 32)); - err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr); - err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr); - err |= __put_user(fprs, &fpu->si_fprs); - - return err; -} - static inline void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, unsigned long framesize) { unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; @@ -414,34 +374,48 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, int signo, sigset_t *oldset, siginfo_t *info) { struct rt_signal_frame __user *sf; - int sigframe_size, err; + int wsaved, err, sf_size; + void __user *tail; /* 1. Make sure everything is clean */ synchronize_user_stack(); save_and_clear_fpu(); - sigframe_size = sizeof(struct rt_signal_frame); - if (!(current_thread_info()->fpsaved[0] & FPRS_FEF)) - sigframe_size -= sizeof(__siginfo_fpu_t); + wsaved = get_thread_wsaved(); + sf_size = sizeof(struct rt_signal_frame); + if (current_thread_info()->fpsaved[0] & FPRS_FEF) + sf_size += sizeof(__siginfo_fpu_t); + if (wsaved) + sf_size += sizeof(__siginfo_rwin_t); sf = (struct rt_signal_frame __user *) - get_sigframe(ka, regs, sigframe_size); - - if (invalid_frame_pointer (sf, sigframe_size)) - goto sigill; + get_sigframe(ka, regs, sf_size); - if (get_thread_wsaved() != 0) + if (invalid_frame_pointer (sf)) goto sigill; + tail = (sf + 1); + /* 2. Save the current process state */ err = copy_to_user(&sf->regs, regs, sizeof (*regs)); if (current_thread_info()->fpsaved[0] & FPRS_FEF) { - err |= save_fpu_state(regs, &sf->fpu_state); - err |= __put_user((u64)&sf->fpu_state, &sf->fpu_save); + __siginfo_fpu_t __user *fpu_save = tail; + tail += sizeof(__siginfo_fpu_t); + err |= save_fpu_state(regs, fpu_save); + err |= __put_user((u64)fpu_save, &sf->fpu_save); } else { err |= __put_user(0, &sf->fpu_save); } + if (wsaved) { + __siginfo_rwin_t __user *rwin_save = tail; + tail += sizeof(__siginfo_rwin_t); + err |= save_rwin_state(wsaved, rwin_save); + err |= __put_user((u64)rwin_save, &sf->rwin_save); + set_thread_wsaved(0); + } else { + err |= __put_user(0, &sf->rwin_save); + } /* Setup sigaltstack */ err |= __put_user(current->sas_ss_sp, &sf->stack.ss_sp); @@ -450,10 +424,17 @@ setup_rt_frame(struct k_sigaction *ka, struct pt_regs *regs, err |= copy_to_user(&sf->mask, oldset, sizeof(sigset_t)); - err |= copy_in_user((u64 __user *)sf, - (u64 __user *)(regs->u_regs[UREG_FP]+STACK_BIAS), - sizeof(struct reg_window)); + if (!wsaved) { + err |= copy_in_user((u64 __user *)sf, + (u64 __user *)(regs->u_regs[UREG_FP] + + STACK_BIAS), + sizeof(struct reg_window)); + } else { + struct reg_window *rp; + rp = ¤t_thread_info()->reg_window[wsaved - 1]; + err |= copy_to_user(sf, rp, sizeof(struct reg_window)); + } if (info) err |= copy_siginfo_to_user(&sf->info, info); else { @@ -498,18 +479,17 @@ static inline int handle_signal(unsigned long signr, struct k_sigaction *ka, siginfo_t *info, sigset_t *oldset, struct pt_regs *regs) { + sigset_t blocked; int err; err = setup_rt_frame(ka, regs, signr, oldset, (ka->sa.sa_flags & SA_SIGINFO) ? info : NULL); if (err) return err; - spin_lock_irq(¤t->sighand->siglock); - sigorsets(¤t->blocked,¤t->blocked,&ka->sa.sa_mask); + sigorsets(&blocked, ¤t->blocked, &ka->sa.sa_mask); if (!(ka->sa.sa_flags & SA_NOMASK)) - sigaddset(¤t->blocked,signr); - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); + sigaddset(&blocked, signr); + set_current_blocked(&blocked); tracehook_signal_handler(signr, info, ka, regs, 0); @@ -549,11 +529,27 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) siginfo_t info; int signr; + /* It's a lot of work and synchronization to add a new ptrace + * register for GDB to save and restore in order to get + * orig_i0 correct for syscall restarts when debugging. + * + * Although it should be the case that most of the global + * registers are volatile across a system call, glibc already + * depends upon that fact that we preserve them. So we can't + * just use any global register to save away the orig_i0 value. + * + * In particular %g2, %g3, %g4, and %g5 are all assumed to be + * preserved across a system call trap by various pieces of + * code in glibc. + * + * %g7 is used as the "thread register". %g6 is not used in + * any fixed manner. %g6 is used as a scratch register and + * a compiler temporary, but it's value is never used across + * a system call. Therefore %g6 is usable for orig_i0 storage. + */ if (pt_regs_is_syscall(regs) && - (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { - restart_syscall = 1; - } else - restart_syscall = 0; + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) + regs->u_regs[UREG_G6] = orig_i0; if (current_thread_info()->status & TS_RESTORE_SIGMASK) oldset = ¤t->saved_sigmask; @@ -562,22 +558,20 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) { - extern void do_signal32(sigset_t *, struct pt_regs *, - int restart_syscall, - unsigned long orig_i0); - do_signal32(oldset, regs, restart_syscall, orig_i0); + extern void do_signal32(sigset_t *, struct pt_regs *); + do_signal32(oldset, regs); return; } #endif signr = get_signal_to_deliver(&info, &ka, regs, NULL); - /* If the debugger messes with the program counter, it clears - * the software "in syscall" bit, directing us to not perform - * a syscall restart. - */ - if (restart_syscall && !pt_regs_is_syscall(regs)) - restart_syscall = 0; + restart_syscall = 0; + if (pt_regs_is_syscall(regs) && + (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) { + restart_syscall = 1; + orig_i0 = regs->u_regs[UREG_G6]; + } if (signr > 0) { if (restart_syscall) @@ -615,7 +609,7 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0) */ if (current_thread_info()->status & TS_RESTORE_SIGMASK) { current_thread_info()->status &= ~TS_RESTORE_SIGMASK; - sigprocmask(SIG_SETMASK, ¤t->saved_sigmask, NULL); + set_current_blocked(¤t->saved_sigmask); } } diff --git a/arch/sparc/kernel/sigutil.h b/arch/sparc/kernel/sigutil.h new file mode 100644 index 000000000000..d223aa432bb6 --- /dev/null +++ b/arch/sparc/kernel/sigutil.h @@ -0,0 +1,9 @@ +#ifndef _SIGUTIL_H +#define _SIGUTIL_H + +int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu); +int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu); +int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin); +int restore_rwin_state(__siginfo_rwin_t __user *rp); + +#endif /* _SIGUTIL_H */ diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c new file mode 100644 index 000000000000..35c7897b009a --- /dev/null +++ b/arch/sparc/kernel/sigutil_32.c @@ -0,0 +1,120 @@ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/thread_info.h> +#include <linux/uaccess.h> +#include <linux/sched.h> + +#include <asm/sigcontext.h> +#include <asm/fpumacro.h> +#include <asm/ptrace.h> + +#include "sigutil.h" + +int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + int err = 0; +#ifdef CONFIG_SMP + if (test_tsk_thread_flag(current, TIF_USEDFPU)) { + put_psr(get_psr() | PSR_EF); + fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, + ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); + regs->psr &= ~(PSR_EF); + clear_tsk_thread_flag(current, TIF_USEDFPU); + } +#else + if (current == last_task_used_math) { + put_psr(get_psr() | PSR_EF); + fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, + ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); + last_task_used_math = NULL; + regs->psr &= ~(PSR_EF); + } +#endif + err |= __copy_to_user(&fpu->si_float_regs[0], + ¤t->thread.float_regs[0], + (sizeof(unsigned long) * 32)); + err |= __put_user(current->thread.fsr, &fpu->si_fsr); + err |= __put_user(current->thread.fpqdepth, &fpu->si_fpqdepth); + if (current->thread.fpqdepth != 0) + err |= __copy_to_user(&fpu->si_fpqueue[0], + ¤t->thread.fpqueue[0], + ((sizeof(unsigned long) + + (sizeof(unsigned long *)))*16)); + clear_used_math(); + return err; +} + +int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + int err; +#ifdef CONFIG_SMP + if (test_tsk_thread_flag(current, TIF_USEDFPU)) + regs->psr &= ~PSR_EF; +#else + if (current == last_task_used_math) { + last_task_used_math = NULL; + regs->psr &= ~PSR_EF; + } +#endif + set_used_math(); + clear_tsk_thread_flag(current, TIF_USEDFPU); + + if (!access_ok(VERIFY_READ, fpu, sizeof(*fpu))) + return -EFAULT; + + err = __copy_from_user(¤t->thread.float_regs[0], &fpu->si_float_regs[0], + (sizeof(unsigned long) * 32)); + err |= __get_user(current->thread.fsr, &fpu->si_fsr); + err |= __get_user(current->thread.fpqdepth, &fpu->si_fpqdepth); + if (current->thread.fpqdepth != 0) + err |= __copy_from_user(¤t->thread.fpqueue[0], + &fpu->si_fpqueue[0], + ((sizeof(unsigned long) + + (sizeof(unsigned long *)))*16)); + return err; +} + +int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin) +{ + int i, err = __put_user(wsaved, &rwin->wsaved); + + for (i = 0; i < wsaved; i++) { + struct reg_window32 *rp; + unsigned long fp; + + rp = ¤t_thread_info()->reg_window[i]; + fp = current_thread_info()->rwbuf_stkptrs[i]; + err |= copy_to_user(&rwin->reg_window[i], rp, + sizeof(struct reg_window32)); + err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]); + } + return err; +} + +int restore_rwin_state(__siginfo_rwin_t __user *rp) +{ + struct thread_info *t = current_thread_info(); + int i, wsaved, err; + + __get_user(wsaved, &rp->wsaved); + if (wsaved > NSWINS) + return -EFAULT; + + err = 0; + for (i = 0; i < wsaved; i++) { + err |= copy_from_user(&t->reg_window[i], + &rp->reg_window[i], + sizeof(struct reg_window32)); + err |= __get_user(t->rwbuf_stkptrs[i], + &rp->rwbuf_stkptrs[i]); + } + if (err) + return err; + + t->w_saved = wsaved; + synchronize_user_stack(); + if (t->w_saved) + return -EFAULT; + return 0; + +} diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c new file mode 100644 index 000000000000..b19570d41a39 --- /dev/null +++ b/arch/sparc/kernel/sigutil_64.c @@ -0,0 +1,94 @@ +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/thread_info.h> +#include <linux/uaccess.h> +#include <linux/errno.h> + +#include <asm/sigcontext.h> +#include <asm/fpumacro.h> +#include <asm/ptrace.h> + +#include "sigutil.h" + +int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + unsigned long *fpregs = current_thread_info()->fpregs; + unsigned long fprs; + int err = 0; + + fprs = current_thread_info()->fpsaved[0]; + if (fprs & FPRS_DL) + err |= copy_to_user(&fpu->si_float_regs[0], fpregs, + (sizeof(unsigned int) * 32)); + if (fprs & FPRS_DU) + err |= copy_to_user(&fpu->si_float_regs[32], fpregs+16, + (sizeof(unsigned int) * 32)); + err |= __put_user(current_thread_info()->xfsr[0], &fpu->si_fsr); + err |= __put_user(current_thread_info()->gsr[0], &fpu->si_gsr); + err |= __put_user(fprs, &fpu->si_fprs); + + return err; +} + +int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) +{ + unsigned long *fpregs = current_thread_info()->fpregs; + unsigned long fprs; + int err; + + err = __get_user(fprs, &fpu->si_fprs); + fprs_write(0); + regs->tstate &= ~TSTATE_PEF; + if (fprs & FPRS_DL) + err |= copy_from_user(fpregs, &fpu->si_float_regs[0], + (sizeof(unsigned int) * 32)); + if (fprs & FPRS_DU) + err |= copy_from_user(fpregs+16, &fpu->si_float_regs[32], + (sizeof(unsigned int) * 32)); + err |= __get_user(current_thread_info()->xfsr[0], &fpu->si_fsr); + err |= __get_user(current_thread_info()->gsr[0], &fpu->si_gsr); + current_thread_info()->fpsaved[0] |= fprs; + return err; +} + +int save_rwin_state(int wsaved, __siginfo_rwin_t __user *rwin) +{ + int i, err = __put_user(wsaved, &rwin->wsaved); + + for (i = 0; i < wsaved; i++) { + struct reg_window *rp = ¤t_thread_info()->reg_window[i]; + unsigned long fp = current_thread_info()->rwbuf_stkptrs[i]; + + err |= copy_to_user(&rwin->reg_window[i], rp, + sizeof(struct reg_window)); + err |= __put_user(fp, &rwin->rwbuf_stkptrs[i]); + } + return err; +} + +int restore_rwin_state(__siginfo_rwin_t __user *rp) +{ + struct thread_info *t = current_thread_info(); + int i, wsaved, err; + + __get_user(wsaved, &rp->wsaved); + if (wsaved > NSWINS) + return -EFAULT; + + err = 0; + for (i = 0; i < wsaved; i++) { + err |= copy_from_user(&t->reg_window[i], + &rp->reg_window[i], + sizeof(struct reg_window)); + err |= __get_user(t->rwbuf_stkptrs[i], + &rp->rwbuf_stkptrs[i]); + } + if (err) + return err; + + set_thread_wsaved(wsaved); + synchronize_user_stack(); + if (get_thread_wsaved()) + return -EFAULT; + return 0; +} diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 21b125341bf7..f671e7fd6ddc 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -22,7 +22,7 @@ #include <linux/delay.h> #include <asm/ptrace.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/irq.h> #include <asm/page.h> diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 99cb17251bb5..75607724d290 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -3,7 +3,7 @@ * Copyright (C) 1997, 2007, 2008 David S. Miller (davem@davemloft.net) */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> @@ -28,7 +28,7 @@ #include <asm/head.h> #include <asm/ptrace.h> -#include <asm/atomic.h> +#include <linux/atomic.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/cpudata.h> diff --git a/arch/sparc/kernel/sparc_ksyms_64.c b/arch/sparc/kernel/sparc_ksyms_64.c index 372ad59c4cba..12ff09824cd9 100644 --- a/arch/sparc/kernel/sparc_ksyms_64.c +++ b/arch/sparc/kernel/sparc_ksyms_64.c @@ -5,9 +5,10 @@ * Copyright (C) 1999 Jakub Jelinek (jj@ultra.linux.cz) */ -#include <linux/module.h> +#include <linux/export.h> #include <linux/pci.h> #include <linux/init.h> +#include <linux/bitops.h> #include <asm/system.h> #include <asm/cpudata.h> @@ -38,5 +39,15 @@ EXPORT_SYMBOL(sun4v_niagara_setperf); EXPORT_SYMBOL(sun4v_niagara2_getperf); EXPORT_SYMBOL(sun4v_niagara2_setperf); +/* from hweight.S */ +EXPORT_SYMBOL(__arch_hweight8); +EXPORT_SYMBOL(__arch_hweight16); +EXPORT_SYMBOL(__arch_hweight32); +EXPORT_SYMBOL(__arch_hweight64); + +/* from ffs_ffz.S */ +EXPORT_SYMBOL(ffs); +EXPORT_SYMBOL(__ffs); + /* Exporting a symbol from /init/main.c */ EXPORT_SYMBOL(saved_command_line); diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c index 8cdbe5946b43..c59af546f522 100644 --- a/arch/sparc/kernel/sstate.c +++ b/arch/sparc/kernel/sstate.c @@ -14,14 +14,9 @@ #include <asm/head.h> #include <asm/io.h> -static int hv_supports_soft_state; - -static unsigned long kimage_addr_to_ra(const char *p) -{ - unsigned long val = (unsigned long) p; +#include "kernel.h" - return kern_base + (val - KERNBASE); -} +static int hv_supports_soft_state; static void do_set_sstate(unsigned long state, const char *msg) { diff --git a/arch/sparc/kernel/stacktrace.c b/arch/sparc/kernel/stacktrace.c index 3e0815349630..e78386a0029f 100644 --- a/arch/sparc/kernel/stacktrace.c +++ b/arch/sparc/kernel/stacktrace.c @@ -2,7 +2,7 @@ #include <linux/stacktrace.h> #include <linux/thread_info.h> #include <linux/ftrace.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/ptrace.h> #include <asm/stacktrace.h> diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S index 44e5faf1ad5f..d97f3eb72e06 100644 --- a/arch/sparc/kernel/sys32.S +++ b/arch/sparc/kernel/sys32.S @@ -81,7 +81,6 @@ SIGN2(sys32_fadvise64, compat_sys_fadvise64, %o0, %o4) SIGN2(sys32_fadvise64_64, compat_sys_fadvise64_64, %o0, %o5) SIGN2(sys32_bdflush, sys_bdflush, %o0, %o1) SIGN1(sys32_mlockall, sys_mlockall, %o0) -SIGN1(sys32_nfsservctl, compat_sys_nfsservctl, %o0) SIGN1(sys32_clock_nanosleep, compat_sys_clock_nanosleep, %o1) SIGN1(sys32_timer_settime, compat_sys_timer_settime, %o1) SIGN1(sys32_io_submit, compat_sys_io_submit, %o1) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 170cd8e8eb2a..29c478ffed91 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -23,7 +23,6 @@ #include <linux/uio.h> #include <linux/nfs_fs.h> #include <linux/quota.h> -#include <linux/module.h> #include <linux/poll.h> #include <linux/personality.h> #include <linux/stat.h> diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 908b47a5ee24..441521ad8a3f 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -23,7 +23,7 @@ #include <linux/ipc.h> #include <linux/personality.h> #include <linux/random.h> -#include <linux/module.h> +#include <linux/export.h> #include <asm/uaccess.h> #include <asm/utrap.h> diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index 6e492d59f6b1..63402f9e9f51 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -67,7 +67,7 @@ sys_call_table: /*235*/ .long sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall /*240*/ .long sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler /*245*/ .long sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep -/*250*/ .long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl +/*250*/ .long sys_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_ni_syscall /*255*/ .long sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep /*260*/ .long sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun /*265*/ .long sys_timer_delete, sys_timer_create, sys_nis_syscall, sys_io_setup, sys_io_destroy @@ -84,4 +84,4 @@ sys_call_table: /*320*/ .long sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv /*325*/ .long sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init /*330*/ .long sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime -/*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns +/*335*/ .long sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index f566518483b5..db86b1a0e9a9 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -68,7 +68,7 @@ sys_call_table32: .word compat_sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys32_mlockall /*240*/ .word sys_munlockall, sys32_sched_setparam, sys32_sched_getparam, sys32_sched_setscheduler, sys32_sched_getscheduler .word sys_sched_yield, sys32_sched_get_priority_max, sys32_sched_get_priority_min, sys32_sched_rr_get_interval, compat_sys_nanosleep -/*250*/ .word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys32_nfsservctl +/*250*/ .word sys_mremap, compat_sys_sysctl, sys32_getsid, sys_fdatasync, sys_nis_syscall .word sys32_sync_file_range, compat_sys_clock_settime, compat_sys_clock_gettime, compat_sys_clock_getres, sys32_clock_nanosleep /*260*/ .word compat_sys_sched_getaffinity, compat_sys_sched_setaffinity, sys32_timer_settime, compat_sys_timer_gettime, sys_timer_getoverrun .word sys_timer_delete, compat_sys_timer_create, sys_ni_syscall, compat_sys_io_setup, sys_io_destroy @@ -85,7 +85,7 @@ sys_call_table32: /*320*/ .word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, compat_sys_preadv .word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo, sys_perf_event_open, compat_sys_recvmmsg, sys_fanotify_init /*330*/ .word sys32_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, compat_sys_open_by_handle_at, compat_sys_clock_adjtime - .word sys_syncfs, compat_sys_sendmmsg, sys_setns + .word sys_syncfs, compat_sys_sendmmsg, sys_setns, compat_sys_process_vm_readv, compat_sys_process_vm_writev #endif /* CONFIG_COMPAT */ @@ -145,7 +145,7 @@ sys_call_table: .word sys_fstatfs64, sys_llseek, sys_mlock, sys_munlock, sys_mlockall /*240*/ .word sys_munlockall, sys_sched_setparam, sys_sched_getparam, sys_sched_setscheduler, sys_sched_getscheduler .word sys_sched_yield, sys_sched_get_priority_max, sys_sched_get_priority_min, sys_sched_rr_get_interval, sys_nanosleep -/*250*/ .word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nfsservctl +/*250*/ .word sys_64_mremap, sys_sysctl, sys_getsid, sys_fdatasync, sys_nis_syscall .word sys_sync_file_range, sys_clock_settime, sys_clock_gettime, sys_clock_getres, sys_clock_nanosleep /*260*/ .word sys_sched_getaffinity, sys_sched_setaffinity, sys_timer_settime, sys_timer_gettime, sys_timer_getoverrun .word sys_timer_delete, sys_timer_create, sys_ni_syscall, sys_io_setup, sys_io_destroy @@ -162,4 +162,4 @@ sys_call_table: /*320*/ .word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv .word sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_event_open, sys_recvmmsg, sys_fanotify_init /*330*/ .word sys_fanotify_mark, sys_prlimit64, sys_name_to_handle_at, sys_open_by_handle_at, sys_clock_adjtime - .word sys_syncfs, sys_sendmmsg, sys_setns + .word sys_syncfs, sys_sendmmsg, sys_setns, sys_process_vm_readv, sys_process_vm_writev diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 1db6b18964d2..e861072b9c52 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -9,7 +9,7 @@ */ #include <linux/errno.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/param.h> diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index c0490c7bbde0..591f20ca9e48 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -14,6 +14,7 @@ #include <linux/signal.h> #include <linux/smp.h> #include <linux/kdebug.h> +#include <linux/export.h> #include <asm/delay.h> #include <asm/system.h> diff --git a/arch/sparc/kernel/unaligned_32.c b/arch/sparc/kernel/unaligned_32.c index 4491f4cb2695..4d043a1b2492 100644 --- a/arch/sparc/kernel/unaligned_32.c +++ b/arch/sparc/kernel/unaligned_32.c @@ -10,7 +10,6 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/mm.h> -#include <linux/module.h> #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/system.h> @@ -247,7 +246,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn) unsigned long addr = compute_effective_address(regs, insn); int err; - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); switch (dir) { case load: err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f), @@ -338,7 +337,7 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn) } addr = compute_effective_address(regs, insn); - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); switch(dir) { case load: err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f), diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c index b2b019ea8caa..76e4ac1a13e1 100644 --- a/arch/sparc/kernel/unaligned_64.c +++ b/arch/sparc/kernel/unaligned_64.c @@ -22,6 +22,7 @@ #include <linux/bitops.h> #include <linux/perf_event.h> #include <linux/ratelimit.h> +#include <linux/bitops.h> #include <asm/fpumacro.h> enum direction { @@ -317,7 +318,7 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn) addr = compute_effective_address(regs, insn, ((insn >> 25) & 0x1f)); - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, addr); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); switch (asi) { case ASI_NL: case ASI_AIUPL: @@ -373,18 +374,13 @@ asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn) } } -static char popc_helper[] = { -0, 1, 1, 2, 1, 2, 2, 3, -1, 2, 2, 3, 2, 3, 3, 4, -}; - int handle_popc(u32 insn, struct pt_regs *regs) { - u64 value; - int ret, i, rd = ((insn >> 25) & 0x1f); int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; + int ret, rd = ((insn >> 25) & 0x1f); + u64 value; - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); if (insn & 0x2000) { maybe_flush_windows(0, 0, rd, from_kernel); value = sign_extend_imm13(insn); @@ -392,10 +388,7 @@ int handle_popc(u32 insn, struct pt_regs *regs) maybe_flush_windows(0, insn & 0x1f, rd, from_kernel); value = fetch_reg(insn & 0x1f, regs); } - for (ret = 0, i = 0; i < 16; i++) { - ret += popc_helper[value & 0xf]; - value >>= 4; - } + ret = hweight64(value); if (rd < 16) { if (rd) regs->u_regs[rd] = ret; @@ -431,7 +424,7 @@ int handle_ldf_stq(u32 insn, struct pt_regs *regs) int asi = decode_asi(insn, regs); int flag = (freg < 32) ? FPRS_DL : FPRS_DU; - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); save_and_clear_fpu(); current_thread_info()->xfsr[0] &= ~0x1c000; @@ -554,7 +547,7 @@ void handle_ld_nf(u32 insn, struct pt_regs *regs) int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; unsigned long *reg; - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); maybe_flush_windows(0, 0, rd, from_kernel); reg = fetch_reg_addr(rd, regs); @@ -586,7 +579,7 @@ void handle_lddfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr if (tstate & TSTATE_PRIV) die_if_kernel("lddfmna from kernel", regs); - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, sfar); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, sfar); if (test_thread_flag(TIF_32BIT)) pc = (u32)pc; if (get_user(insn, (u32 __user *) pc) != -EFAULT) { @@ -647,7 +640,7 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr if (tstate & TSTATE_PRIV) die_if_kernel("stdfmna from kernel", regs); - perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, 0, regs, sfar); + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, sfar); if (test_thread_flag(TIF_32BIT)) pc = (u32)pc; if (get_user(insn, (u32 __user *) pc) != -EFAULT) { diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index 3cb1def9806c..f67e28ef598c 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/irq.h> +#include <linux/export.h> #include <linux/init.h> #include <asm/mdesc.h> diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c index 29348ea139c3..f8e7dd53e1c7 100644 --- a/arch/sparc/kernel/viohs.c +++ b/arch/sparc/kernel/viohs.c @@ -4,7 +4,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/string.h> #include <linux/delay.h> #include <linux/sched.h> diff --git a/arch/sparc/kernel/visemul.c b/arch/sparc/kernel/visemul.c index 36357717d691..73370674ccff 100644 --- a/arch/sparc/kernel/visemul.c +++ b/arch/sparc/kernel/visemul.c @@ -713,17 +713,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a > b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPGT32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a > b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -733,17 +733,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a <= b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPLE32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a <= b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -753,17 +753,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a != b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPNE32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a != b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; @@ -773,17 +773,17 @@ static void pcmp(struct pt_regs *regs, unsigned int insn, unsigned int opf) s16 b = (rs2 >> (i * 16)) & 0xffff; if (a == b) - rd_val |= 1 << i; + rd_val |= 8 >> i; } break; case FCMPEQ32_OPF: for (i = 0; i < 2; i++) { - s32 a = (rs1 >> (i * 32)) & 0xffff; - s32 b = (rs2 >> (i * 32)) & 0xffff; + s32 a = (rs1 >> (i * 32)) & 0xffffffff; + s32 b = (rs2 >> (i * 32)) & 0xffffffff; if (a == b) - rd_val |= 1 << i; + rd_val |= 2 >> i; } break; } @@ -802,7 +802,7 @@ int vis_emul(struct pt_regs *regs, unsigned int insn) BUG_ON(regs->tstate & TSTATE_PRIV); - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); if (test_thread_flag(TIF_32BIT)) pc = (u32)pc; diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index c0220759003e..0e1605697b49 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -107,7 +107,26 @@ SECTIONS *(.sun4v_2insn_patch) __sun4v_2insn_patch_end = .; } - + .swapper_tsb_phys_patch : { + __swapper_tsb_phys_patch = .; + *(.swapper_tsb_phys_patch) + __swapper_tsb_phys_patch_end = .; + } + .swapper_4m_tsb_phys_patch : { + __swapper_4m_tsb_phys_patch = .; + *(.swapper_4m_tsb_phys_patch) + __swapper_4m_tsb_phys_patch_end = .; + } + .popc_3insn_patch : { + __popc_3insn_patch = .; + *(.popc_3insn_patch) + __popc_3insn_patch_end = .; + } + .popc_6insn_patch : { + __popc_6insn_patch = .; + *(.popc_6insn_patch) + __popc_6insn_patch_end = .; + } PERCPU_SECTION(SMP_CACHE_BYTES) . = ALIGN(PAGE_SIZE); diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile index 7f01b8fce8bc..a3fc4375a150 100644 --- a/arch/sparc/lib/Makefile +++ b/arch/sparc/lib/Makefile @@ -31,13 +31,13 @@ lib-$(CONFIG_SPARC64) += NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o -lib-$(CONFIG_SPARC64) += NG2patch.o NG2page.o +lib-$(CONFIG_SPARC64) += NG2patch.o lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o -lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o +lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o hweight.o ffs.o obj-y += iomap.o obj-$(CONFIG_SPARC32) += atomic32.o diff --git a/arch/sparc/lib/NG2page.S b/arch/sparc/lib/NG2page.S deleted file mode 100644 index 73b6b7c72cbf..000000000000 --- a/arch/sparc/lib/NG2page.S +++ /dev/null @@ -1,61 +0,0 @@ -/* NG2page.S: Niagara-2 optimized clear and copy page. - * - * Copyright (C) 2007 (davem@davemloft.net) - */ - -#include <asm/asi.h> -#include <asm/page.h> -#include <asm/visasm.h> - - .text - .align 32 - - /* This is heavily simplified from the sun4u variants - * because Niagara-2 does not have any D-cache aliasing issues. - */ -NG2copy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */ - prefetch [%o1 + 0x00], #one_read - prefetch [%o1 + 0x40], #one_read - VISEntryHalf - set PAGE_SIZE, %g7 - sub %o0, %o1, %g3 -1: stxa %g0, [%o1 + %g3] ASI_BLK_INIT_QUAD_LDD_P - subcc %g7, 64, %g7 - ldda [%o1] ASI_BLK_P, %f0 - stda %f0, [%o1 + %g3] ASI_BLK_P - add %o1, 64, %o1 - bne,pt %xcc, 1b - prefetch [%o1 + 0x40], #one_read - membar #Sync - VISExitHalf - retl - nop - -#define BRANCH_ALWAYS 0x10680000 -#define NOP 0x01000000 -#define NG_DO_PATCH(OLD, NEW) \ - sethi %hi(NEW), %g1; \ - or %g1, %lo(NEW), %g1; \ - sethi %hi(OLD), %g2; \ - or %g2, %lo(OLD), %g2; \ - sub %g1, %g2, %g1; \ - sethi %hi(BRANCH_ALWAYS), %g3; \ - sll %g1, 11, %g1; \ - srl %g1, 11 + 2, %g1; \ - or %g3, %lo(BRANCH_ALWAYS), %g3; \ - or %g3, %g1, %g3; \ - stw %g3, [%g2]; \ - sethi %hi(NOP), %g3; \ - or %g3, %lo(NOP), %g3; \ - stw %g3, [%g2 + 0x4]; \ - flush %g2; - - .globl niagara2_patch_pageops - .type niagara2_patch_pageops,#function -niagara2_patch_pageops: - NG_DO_PATCH(copy_user_page, NG2copy_user_page) - NG_DO_PATCH(_clear_page, NGclear_page) - NG_DO_PATCH(clear_user_page, NGclear_user_page) - retl - nop - .size niagara2_patch_pageops,.-niagara2_patch_pageops diff --git a/arch/sparc/lib/NGpage.S b/arch/sparc/lib/NGpage.S index 428920de05ba..b9e790b9c6b8 100644 --- a/arch/sparc/lib/NGpage.S +++ b/arch/sparc/lib/NGpage.S @@ -16,55 +16,91 @@ */ NGcopy_user_page: /* %o0=dest, %o1=src, %o2=vaddr */ - prefetch [%o1 + 0x00], #one_read - mov 8, %g1 - mov 16, %g2 - mov 24, %g3 + save %sp, -192, %sp + rd %asi, %g3 + wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi set PAGE_SIZE, %g7 + prefetch [%i1 + 0x00], #one_read + prefetch [%i1 + 0x40], #one_read -1: ldda [%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2 - ldda [%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4 - prefetch [%o1 + 0x40], #one_read - add %o1, 32, %o1 - stxa %o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P - stxa %o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P - ldda [%o1 + %g0] ASI_BLK_INIT_QUAD_LDD_P, %o2 - stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P - stxa %o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P - ldda [%o1 + %g2] ASI_BLK_INIT_QUAD_LDD_P, %o4 - add %o1, 32, %o1 - add %o0, 32, %o0 - stxa %o2, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P - stxa %o3, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P - stxa %o4, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P - stxa %o5, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P - subcc %g7, 64, %g7 +1: prefetch [%i1 + 0x80], #one_read + prefetch [%i1 + 0xc0], #one_read + ldda [%i1 + 0x00] %asi, %o2 + ldda [%i1 + 0x10] %asi, %o4 + ldda [%i1 + 0x20] %asi, %l2 + ldda [%i1 + 0x30] %asi, %l4 + stxa %o2, [%i0 + 0x00] %asi + stxa %o3, [%i0 + 0x08] %asi + stxa %o4, [%i0 + 0x10] %asi + stxa %o5, [%i0 + 0x18] %asi + stxa %l2, [%i0 + 0x20] %asi + stxa %l3, [%i0 + 0x28] %asi + stxa %l4, [%i0 + 0x30] %asi + stxa %l5, [%i0 + 0x38] %asi + ldda [%i1 + 0x40] %asi, %o2 + ldda [%i1 + 0x50] %asi, %o4 + ldda [%i1 + 0x60] %asi, %l2 + ldda [%i1 + 0x70] %asi, %l4 + stxa %o2, [%i0 + 0x40] %asi + stxa %o3, [%i0 + 0x48] %asi + stxa %o4, [%i0 + 0x50] %asi + stxa %o5, [%i0 + 0x58] %asi + stxa %l2, [%i0 + 0x60] %asi + stxa %l3, [%i0 + 0x68] %asi + stxa %l4, [%i0 + 0x70] %asi + stxa %l5, [%i0 + 0x78] %asi + add %i1, 128, %i1 + subcc %g7, 128, %g7 bne,pt %xcc, 1b - add %o0, 32, %o0 + add %i0, 128, %i0 + wr %g3, 0x0, %asi membar #Sync - retl - nop + ret + restore - .globl NGclear_page, NGclear_user_page + .align 32 NGclear_page: /* %o0=dest */ NGclear_user_page: /* %o0=dest, %o1=vaddr */ - mov 8, %g1 - mov 16, %g2 - mov 24, %g3 + rd %asi, %g3 + wr %g0, ASI_BLK_INIT_QUAD_LDD_P, %asi set PAGE_SIZE, %g7 -1: stxa %g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P - stxa %g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P - stxa %g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P - stxa %g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P - add %o0, 32, %o0 - stxa %g0, [%o0 + %g0] ASI_BLK_INIT_QUAD_LDD_P - stxa %g0, [%o0 + %g1] ASI_BLK_INIT_QUAD_LDD_P - stxa %g0, [%o0 + %g2] ASI_BLK_INIT_QUAD_LDD_P - stxa %g0, [%o0 + %g3] ASI_BLK_INIT_QUAD_LDD_P - subcc %g7, 64, %g7 +1: stxa %g0, [%o0 + 0x00] %asi + stxa %g0, [%o0 + 0x08] %asi + stxa %g0, [%o0 + 0x10] %asi + stxa %g0, [%o0 + 0x18] %asi + stxa %g0, [%o0 + 0x20] %asi + stxa %g0, [%o0 + 0x28] %asi + stxa %g0, [%o0 + 0x30] %asi + stxa %g0, [%o0 + 0x38] %asi + stxa %g0, [%o0 + 0x40] %asi + stxa %g0, [%o0 + 0x48] %asi + stxa %g0, [%o0 + 0x50] %asi + stxa %g0, [%o0 + 0x58] %asi + stxa %g0, [%o0 + 0x60] %asi + stxa %g0, [%o0 + 0x68] %asi + stxa %g0, [%o0 + 0x70] %asi + stxa %g0, [%o0 + 0x78] %asi + stxa %g0, [%o0 + 0x80] %asi + stxa %g0, [%o0 + 0x88] %asi + stxa %g0, [%o0 + 0x90] %asi + stxa %g0, [%o0 + 0x98] %asi + stxa %g0, [%o0 + 0xa0] %asi + stxa %g0, [%o0 + 0xa8] %asi + stxa %g0, [%o0 + 0xb0] %asi + stxa %g0, [%o0 + 0xb8] %asi + stxa %g0, [%o0 + 0xc0] %asi + stxa %g0, [%o0 + 0xc8] %asi + stxa %g0, [%o0 + 0xd0] %asi + stxa %g0, [%o0 + 0xd8] %asi + stxa %g0, [%o0 + 0xe0] %asi + stxa %g0, [%o0 + 0xe8] %asi + stxa %g0, [%o0 + 0xf0] %asi + stxa %g0, [%o0 + 0xf8] %asi + subcc %g7, 256, %g7 bne,pt %xcc, 1b - add %o0, 32, %o0 + add %o0, 256, %o0 + wr %g3, 0x0, %asi membar #Sync retl nop diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index d3c7a12ad879..1d32b54089aa 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -7,7 +7,7 @@ * Based on asm-parisc/atomic.h Copyright (C) 2000 Philipp Rumpf */ -#include <asm/atomic.h> +#include <linux/atomic.h> #include <linux/spinlock.h> #include <linux/module.h> @@ -55,7 +55,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new) } EXPORT_SYMBOL(atomic_cmpxchg); -int atomic_add_unless(atomic_t *v, int a, int u) +int __atomic_add_unless(atomic_t *v, int a, int u) { int ret; unsigned long flags; @@ -65,9 +65,9 @@ int atomic_add_unless(atomic_t *v, int a, int u) if (ret != u) v->counter += a; spin_unlock_irqrestore(ATOMIC_HASH(v), flags); - return ret != u; + return ret; } -EXPORT_SYMBOL(atomic_add_unless); +EXPORT_SYMBOL(__atomic_add_unless); /* Atomic operations are already serializing */ void atomic_set(atomic_t *v, int i) diff --git a/arch/sparc/lib/ffs.S b/arch/sparc/lib/ffs.S new file mode 100644 index 000000000000..b39389f69899 --- /dev/null +++ b/arch/sparc/lib/ffs.S @@ -0,0 +1,84 @@ +#include <linux/linkage.h> + + .register %g2,#scratch + + .text + .align 32 + +ENTRY(ffs) + brnz,pt %o0, 1f + mov 1, %o1 + retl + clr %o0 + nop + nop +ENTRY(__ffs) + sllx %o0, 32, %g1 /* 1 */ + srlx %o0, 32, %g2 + + clr %o1 /* 2 */ + movrz %g1, %g2, %o0 + + movrz %g1, 32, %o1 /* 3 */ +1: clr %o2 + + sllx %o0, (64 - 16), %g1 /* 4 */ + srlx %o0, 16, %g2 + + movrz %g1, %g2, %o0 /* 5 */ + clr %o3 + + movrz %g1, 16, %o2 /* 6 */ + clr %o4 + + and %o0, 0xff, %g1 /* 7 */ + srlx %o0, 8, %g2 + + movrz %g1, %g2, %o0 /* 8 */ + clr %o5 + + movrz %g1, 8, %o3 /* 9 */ + add %o2, %o1, %o2 + + and %o0, 0xf, %g1 /* 10 */ + srlx %o0, 4, %g2 + + movrz %g1, %g2, %o0 /* 11 */ + add %o2, %o3, %o2 + + movrz %g1, 4, %o4 /* 12 */ + + and %o0, 0x3, %g1 /* 13 */ + srlx %o0, 2, %g2 + + movrz %g1, %g2, %o0 /* 14 */ + add %o2, %o4, %o2 + + movrz %g1, 2, %o5 /* 15 */ + + and %o0, 0x1, %g1 /* 16 */ + + add %o2, %o5, %o2 /* 17 */ + xor %g1, 0x1, %g1 + + retl /* 18 */ + add %o2, %g1, %o0 +ENDPROC(ffs) +ENDPROC(__ffs) + + .section .popc_6insn_patch, "ax" + .word ffs + brz,pn %o0, 98f + neg %o0, %g1 + xnor %o0, %g1, %o1 + popc %o1, %o0 +98: retl + nop + .word __ffs + neg %o0, %g1 + xnor %o0, %g1, %o1 + popc %o1, %o0 + retl + sub %o0, 1, %o0 + nop + .previous diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S new file mode 100644 index 000000000000..95414e0a6808 --- /dev/null +++ b/arch/sparc/lib/hweight.S @@ -0,0 +1,51 @@ +#include <linux/linkage.h> + + .text + .align 32 +ENTRY(__arch_hweight8) + ba,pt %xcc, __sw_hweight8 + nop + nop +ENDPROC(__arch_hweight8) + .section .popc_3insn_patch, "ax" + .word __arch_hweight8 + sllx %o0, 64-8, %g1 + retl + popc %g1, %o0 + .previous + +ENTRY(__arch_hweight16) + ba,pt %xcc, __sw_hweight16 + nop + nop +ENDPROC(__arch_hweight16) + .section .popc_3insn_patch, "ax" + .word __arch_hweight16 + sllx %o0, 64-16, %g1 + retl + popc %g1, %o0 + .previous + +ENTRY(__arch_hweight32) + ba,pt %xcc, __sw_hweight32 + nop + nop +ENDPROC(__arch_hweight32) + .section .popc_3insn_patch, "ax" + .word __arch_hweight32 + sllx %o0, 64-32, %g1 + retl + popc %g1, %o0 + .previous + +ENTRY(__arch_hweight64) + ba,pt %xcc, __sw_hweight64 + nop + nop +ENDPROC(__arch_hweight64) + .section .popc_3insn_patch, "ax" + .word __arch_hweight64 + retl + popc %o0, %o0 + nop + .previous diff --git a/arch/sparc/lib/memcpy.S b/arch/sparc/lib/memcpy.S index 34fe65751737..4d8c497517bd 100644 --- a/arch/sparc/lib/memcpy.S +++ b/arch/sparc/lib/memcpy.S @@ -7,40 +7,12 @@ * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz) */ -#ifdef __KERNEL__ - -#define FUNC(x) \ +#define FUNC(x) \ .globl x; \ .type x,@function; \ - .align 4; \ + .align 4; \ x: -#undef FASTER_REVERSE -#undef FASTER_NONALIGNED -#define FASTER_ALIGNED - -/* In kernel these functions don't return a value. - * One should use macros in asm/string.h for that purpose. - * We return 0, so that bugs are more apparent. - */ -#define SETUP_RETL -#define RETL_INSN clr %o0 - -#else - -/* libc */ - -#include "DEFS.h" - -#define FASTER_REVERSE -#define FASTER_NONALIGNED -#define FASTER_ALIGNED - -#define SETUP_RETL mov %o0, %g6 -#define RETL_INSN mov %g6, %o0 - -#endif - /* Both these macros have to start with exactly the same insn */ #define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \ ldd [%src + (offset) + 0x00], %t0; \ @@ -164,30 +136,6 @@ x: .text .align 4 -#ifdef FASTER_REVERSE - -70: /* rdword_align */ - - andcc %o1, 1, %g0 - be 4f - andcc %o1, 2, %g0 - - ldub [%o1 - 1], %g2 - sub %o1, 1, %o1 - stb %g2, [%o0 - 1] - sub %o2, 1, %o2 - be 3f - sub %o0, 1, %o0 -4: - lduh [%o1 - 2], %g2 - sub %o1, 2, %o1 - sth %g2, [%o0 - 2] - sub %o2, 2, %o2 - b 3f - sub %o0, 2, %o0 - -#endif /* FASTER_REVERSE */ - 0: retl nop ! Only bcopy returns here and it retuns void... @@ -198,7 +146,7 @@ FUNC(__memmove) #endif FUNC(memmove) cmp %o0, %o1 - SETUP_RETL + mov %o0, %g7 bleu 9f sub %o0, %o1, %o4 @@ -207,8 +155,6 @@ FUNC(memmove) bleu 0f andcc %o4, 3, %o5 -#ifndef FASTER_REVERSE - add %o1, %o2, %o1 add %o0, %o2, %o0 sub %o1, 1, %o1 @@ -224,295 +170,7 @@ FUNC(memmove) sub %o0, 1, %o0 retl - RETL_INSN - -#else /* FASTER_REVERSE */ - - add %o1, %o2, %o1 - add %o0, %o2, %o0 - bne 77f - cmp %o2, 15 - bleu 91f - andcc %o1, 3, %g0 - bne 70b -3: - andcc %o1, 4, %g0 - - be 2f - mov %o2, %g1 - - ld [%o1 - 4], %o4 - sub %g1, 4, %g1 - st %o4, [%o0 - 4] - sub %o1, 4, %o1 - sub %o0, 4, %o0 -2: - andcc %g1, 0xffffff80, %g7 - be 3f - andcc %o0, 4, %g0 - - be 74f + 4 -5: - RMOVE_BIGCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 - sub %o1, 128, %o1 - bne 5b - sub %o0, 128, %o0 -3: - andcc %g1, 0x70, %g7 - be 72f - andcc %g1, 8, %g0 - - sethi %hi(72f), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - sub %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(72f), %g0 - sub %o0, %g7, %o0 - -71: /* rmemcpy_table */ - RMOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x30, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x20, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5) - RMOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5) - -72: /* rmemcpy_table_end */ - - be 73f - andcc %g1, 4, %g0 - - ldd [%o1 - 0x08], %g2 - sub %o0, 8, %o0 - sub %o1, 8, %o1 - st %g2, [%o0] - st %g3, [%o0 + 0x04] - -73: /* rmemcpy_last7 */ - - be 1f - andcc %g1, 2, %g0 - - ld [%o1 - 4], %g2 - sub %o1, 4, %o1 - st %g2, [%o0 - 4] - sub %o0, 4, %o0 -1: - be 1f - andcc %g1, 1, %g0 - - lduh [%o1 - 2], %g2 - sub %o1, 2, %o1 - sth %g2, [%o0 - 2] - sub %o0, 2, %o0 -1: - be 1f - nop - - ldub [%o1 - 1], %g2 - stb %g2, [%o0 - 1] -1: - retl - RETL_INSN - -74: /* rldd_std */ - RMOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) - RMOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 - sub %o1, 128, %o1 - bne 74b - sub %o0, 128, %o0 - - andcc %g1, 0x70, %g7 - be 72b - andcc %g1, 8, %g0 - - sethi %hi(72b), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - sub %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(72b), %g0 - sub %o0, %g7, %o0 - -75: /* rshort_end */ - - and %o2, 0xe, %o3 -2: - sethi %hi(76f), %o5 - sll %o3, 3, %o4 - sub %o0, %o3, %o0 - sub %o5, %o4, %o5 - sub %o1, %o3, %o1 - jmpl %o5 + %lo(76f), %g0 - andcc %o2, 1, %g0 - - RMOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3) - RMOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3) - -76: /* rshort_table_end */ - - be 1f - nop - ldub [%o1 - 1], %g2 - stb %g2, [%o0 - 1] -1: - retl - RETL_INSN - -91: /* rshort_aligned_end */ - - bne 75b - andcc %o2, 8, %g0 - - be 1f - andcc %o2, 4, %g0 - - ld [%o1 - 0x08], %g2 - ld [%o1 - 0x04], %g3 - sub %o1, 8, %o1 - st %g2, [%o0 - 0x08] - st %g3, [%o0 - 0x04] - sub %o0, 8, %o0 -1: - b 73b - mov %o2, %g1 - -77: /* rnon_aligned */ - cmp %o2, 15 - bleu 75b - andcc %o0, 3, %g0 - be 64f - andcc %o0, 1, %g0 - be 63f - andcc %o0, 2, %g0 - ldub [%o1 - 1], %g5 - sub %o1, 1, %o1 - stb %g5, [%o0 - 1] - sub %o0, 1, %o0 - be 64f - sub %o2, 1, %o2 -63: - ldub [%o1 - 1], %g5 - sub %o1, 2, %o1 - stb %g5, [%o0 - 1] - sub %o0, 2, %o0 - ldub [%o1], %g5 - sub %o2, 2, %o2 - stb %g5, [%o0] -64: - and %o1, 3, %g2 - and %o1, -4, %o1 - and %o2, 0xc, %g3 - add %o1, 4, %o1 - cmp %g3, 4 - sll %g2, 3, %g4 - mov 32, %g2 - be 4f - sub %g2, %g4, %g7 - - blu 3f - cmp %g3, 8 - - be 2f - srl %o2, 2, %g3 - - ld [%o1 - 4], %o3 - add %o0, -8, %o0 - ld [%o1 - 8], %o4 - add %o1, -16, %o1 - b 7f - add %g3, 1, %g3 -2: - ld [%o1 - 4], %o4 - add %o0, -4, %o0 - ld [%o1 - 8], %g1 - add %o1, -12, %o1 - b 8f - add %g3, 2, %g3 -3: - ld [%o1 - 4], %o5 - add %o0, -12, %o0 - ld [%o1 - 8], %o3 - add %o1, -20, %o1 - b 6f - srl %o2, 2, %g3 -4: - ld [%o1 - 4], %g1 - srl %o2, 2, %g3 - ld [%o1 - 8], %o5 - add %o1, -24, %o1 - add %o0, -16, %o0 - add %g3, -1, %g3 - - ld [%o1 + 12], %o3 -5: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 12] -6: - ld [%o1 + 8], %o4 - sll %o3, %g4, %g2 - srl %o5, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 8] -7: - ld [%o1 + 4], %g1 - sll %o4, %g4, %g2 - srl %o3, %g7, %g5 - or %g2, %g5, %g2 - st %g2, [%o0 + 4] -8: - ld [%o1], %o5 - sll %g1, %g4, %g2 - srl %o4, %g7, %g5 - addcc %g3, -4, %g3 - or %g2, %g5, %g2 - add %o1, -16, %o1 - st %g2, [%o0] - add %o0, -16, %o0 - bne,a 5b - ld [%o1 + 12], %o3 - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - srl %g4, 3, %g3 - or %g2, %g5, %g2 - add %o1, %g3, %o1 - andcc %o2, 2, %g0 - st %g2, [%o0 + 12] - be 1f - andcc %o2, 1, %g0 - - ldub [%o1 + 15], %g5 - add %o1, -2, %o1 - stb %g5, [%o0 + 11] - add %o0, -2, %o0 - ldub [%o1 + 16], %g5 - stb %g5, [%o0 + 12] -1: - be 1f - nop - ldub [%o1 + 15], %g5 - stb %g5, [%o0 + 11] -1: - retl - RETL_INSN - -#endif /* FASTER_REVERSE */ + mov %g7, %o0 /* NOTE: This code is executed just for the cases, where %src (=%o1) & 3 is != 0. @@ -546,7 +204,7 @@ FUNC(memmove) FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ sub %o0, %o1, %o4 - SETUP_RETL + mov %o0, %g7 9: andcc %o4, 3, %o5 0: @@ -569,7 +227,7 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ add %o1, 4, %o1 add %o0, 4, %o0 2: - andcc %g1, 0xffffff80, %g7 + andcc %g1, 0xffffff80, %g0 be 3f andcc %o0, 4, %g0 @@ -579,22 +237,23 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 + sub %g1, 128, %g1 add %o1, 128, %o1 - bne 5b + cmp %g1, 128 + bge 5b add %o0, 128, %o0 3: - andcc %g1, 0x70, %g7 + andcc %g1, 0x70, %g4 be 80f andcc %g1, 8, %g0 sethi %hi(80f), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - add %o1, %g7, %o1 + srl %g4, 1, %o4 + add %g4, %o4, %o4 + add %o1, %g4, %o1 sub %o5, %o4, %o5 jmpl %o5 + %lo(80f), %g0 - add %o0, %g7, %o0 + add %o0, %g4, %o0 79: /* memcpy_table */ @@ -641,43 +300,28 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN + mov %g7, %o0 82: /* ldd_std */ MOVE_BIGALIGNCHUNK(o1, o0, 0x00, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5) MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5) - subcc %g7, 128, %g7 + subcc %g1, 128, %g1 add %o1, 128, %o1 - bne 82b + cmp %g1, 128 + bge 82b add %o0, 128, %o0 -#ifndef FASTER_ALIGNED - - andcc %g1, 0x70, %g7 - be 80b - andcc %g1, 8, %g0 - - sethi %hi(80b), %o5 - srl %g7, 1, %o4 - add %g7, %o4, %o4 - add %o1, %g7, %o1 - sub %o5, %o4, %o5 - jmpl %o5 + %lo(80b), %g0 - add %o0, %g7, %o0 - -#else /* FASTER_ALIGNED */ - - andcc %g1, 0x70, %g7 + andcc %g1, 0x70, %g4 be 84f andcc %g1, 8, %g0 sethi %hi(84f), %o5 - add %o1, %g7, %o1 - sub %o5, %g7, %o5 + add %o1, %g4, %o1 + sub %o5, %g4, %o5 jmpl %o5 + %lo(84f), %g0 - add %o0, %g7, %o0 + add %o0, %g4, %o0 83: /* amemcpy_table */ @@ -721,382 +365,132 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN - -#endif /* FASTER_ALIGNED */ + mov %g7, %o0 86: /* non_aligned */ cmp %o2, 6 bleu 88f + nop -#ifdef FASTER_NONALIGNED - - cmp %o2, 256 - bcc 87f - -#endif /* FASTER_NONALIGNED */ - - andcc %o0, 3, %g0 + save %sp, -96, %sp + andcc %i0, 3, %g0 be 61f - andcc %o0, 1, %g0 + andcc %i0, 1, %g0 be 60f - andcc %o0, 2, %g0 + andcc %i0, 2, %g0 - ldub [%o1], %g5 - add %o1, 1, %o1 - stb %g5, [%o0] - sub %o2, 1, %o2 + ldub [%i1], %g5 + add %i1, 1, %i1 + stb %g5, [%i0] + sub %i2, 1, %i2 bne 61f - add %o0, 1, %o0 + add %i0, 1, %i0 60: - ldub [%o1], %g3 - add %o1, 2, %o1 - stb %g3, [%o0] - sub %o2, 2, %o2 - ldub [%o1 - 1], %g3 - add %o0, 2, %o0 - stb %g3, [%o0 - 1] + ldub [%i1], %g3 + add %i1, 2, %i1 + stb %g3, [%i0] + sub %i2, 2, %i2 + ldub [%i1 - 1], %g3 + add %i0, 2, %i0 + stb %g3, [%i0 - 1] 61: - and %o1, 3, %g2 - and %o2, 0xc, %g3 - and %o1, -4, %o1 + and %i1, 3, %g2 + and %i2, 0xc, %g3 + and %i1, -4, %i1 cmp %g3, 4 sll %g2, 3, %g4 mov 32, %g2 be 4f - sub %g2, %g4, %g7 + sub %g2, %g4, %l0 blu 3f cmp %g3, 0x8 be 2f - srl %o2, 2, %g3 + srl %i2, 2, %g3 - ld [%o1], %o3 - add %o0, -8, %o0 - ld [%o1 + 4], %o4 + ld [%i1], %i3 + add %i0, -8, %i0 + ld [%i1 + 4], %i4 b 8f add %g3, 1, %g3 2: - ld [%o1], %o4 - add %o0, -12, %o0 - ld [%o1 + 4], %o5 + ld [%i1], %i4 + add %i0, -12, %i0 + ld [%i1 + 4], %i5 add %g3, 2, %g3 b 9f - add %o1, -4, %o1 + add %i1, -4, %i1 3: - ld [%o1], %g1 - add %o0, -4, %o0 - ld [%o1 + 4], %o3 - srl %o2, 2, %g3 + ld [%i1], %g1 + add %i0, -4, %i0 + ld [%i1 + 4], %i3 + srl %i2, 2, %g3 b 7f - add %o1, 4, %o1 + add %i1, 4, %i1 4: - ld [%o1], %o5 - cmp %o2, 7 - ld [%o1 + 4], %g1 - srl %o2, 2, %g3 + ld [%i1], %i5 + cmp %i2, 7 + ld [%i1 + 4], %g1 + srl %i2, 2, %g3 bleu 10f - add %o1, 8, %o1 + add %i1, 8, %i1 - ld [%o1], %o3 + ld [%i1], %i3 add %g3, -1, %g3 5: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 + sll %i5, %g4, %g2 + srl %g1, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0] + st %g2, [%i0] 7: - ld [%o1 + 4], %o4 + ld [%i1 + 4], %i4 sll %g1, %g4, %g2 - srl %o3, %g7, %g5 + srl %i3, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0 + 4] + st %g2, [%i0 + 4] 8: - ld [%o1 + 8], %o5 - sll %o3, %g4, %g2 - srl %o4, %g7, %g5 + ld [%i1 + 8], %i5 + sll %i3, %g4, %g2 + srl %i4, %l0, %g5 or %g2, %g5, %g2 - st %g2, [%o0 + 8] + st %g2, [%i0 + 8] 9: - ld [%o1 + 12], %g1 - sll %o4, %g4, %g2 - srl %o5, %g7, %g5 + ld [%i1 + 12], %g1 + sll %i4, %g4, %g2 + srl %i5, %l0, %g5 addcc %g3, -4, %g3 or %g2, %g5, %g2 - add %o1, 16, %o1 - st %g2, [%o0 + 12] - add %o0, 16, %o0 + add %i1, 16, %i1 + st %g2, [%i0 + 12] + add %i0, 16, %i0 bne,a 5b - ld [%o1], %o3 + ld [%i1], %i3 10: - sll %o5, %g4, %g2 - srl %g1, %g7, %g5 - srl %g7, 3, %g3 + sll %i5, %g4, %g2 + srl %g1, %l0, %g5 + srl %l0, 3, %g3 or %g2, %g5, %g2 - sub %o1, %g3, %o1 - andcc %o2, 2, %g0 - st %g2, [%o0] + sub %i1, %g3, %i1 + andcc %i2, 2, %g0 + st %g2, [%i0] be 1f - andcc %o2, 1, %g0 - - ldub [%o1], %g2 - add %o1, 2, %o1 - stb %g2, [%o0 + 4] - add %o0, 2, %o0 - ldub [%o1 - 1], %g2 - stb %g2, [%o0 + 3] + andcc %i2, 1, %g0 + + ldub [%i1], %g2 + add %i1, 2, %i1 + stb %g2, [%i0 + 4] + add %i0, 2, %i0 + ldub [%i1 - 1], %g2 + stb %g2, [%i0 + 3] 1: be 1f nop - ldub [%o1], %g2 - stb %g2, [%o0 + 4] -1: - retl - RETL_INSN - -#ifdef FASTER_NONALIGNED - -87: /* faster_nonaligned */ - - andcc %o1, 3, %g0 - be 3f - andcc %o1, 1, %g0 - - be 4f - andcc %o1, 2, %g0 - - ldub [%o1], %g2 - add %o1, 1, %o1 - stb %g2, [%o0] - sub %o2, 1, %o2 - bne 3f - add %o0, 1, %o0 -4: - lduh [%o1], %g2 - add %o1, 2, %o1 - srl %g2, 8, %g3 - sub %o2, 2, %o2 - stb %g3, [%o0] - add %o0, 2, %o0 - stb %g2, [%o0 - 1] -3: - andcc %o1, 4, %g0 - - bne 2f - cmp %o5, 1 - - ld [%o1], %o4 - srl %o4, 24, %g2 - stb %g2, [%o0] - srl %o4, 16, %g3 - stb %g3, [%o0 + 1] - srl %o4, 8, %g2 - stb %g2, [%o0 + 2] - sub %o2, 4, %o2 - stb %o4, [%o0 + 3] - add %o1, 4, %o1 - add %o0, 4, %o0 -2: - be 33f - cmp %o5, 2 - be 32f - sub %o2, 4, %o2 -31: - ld [%o1], %g2 - add %o1, 4, %o1 - srl %g2, 24, %g3 - and %o0, 7, %g5 - stb %g3, [%o0] - cmp %g5, 7 - sll %g2, 8, %g1 - add %o0, 4, %o0 - be 41f - and %o2, 0xffffffc0, %o3 - ld [%o0 - 7], %o4 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - st %o4, [%o0 - 7] - sth %g2, [%o0 - 3] - srl %g1, 8, %g4 - b 88f - stb %g4, [%o0 - 1] -32: - ld [%o1], %g2 - add %o1, 4, %o1 - srl %g2, 16, %g3 - and %o0, 7, %g5 - sth %g3, [%o0] - cmp %g5, 6 - sll %g2, 16, %g1 - add %o0, 4, %o0 - be 42f - and %o2, 0xffffffc0, %o3 - ld [%o0 - 6], %o4 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - st %o4, [%o0 - 6] - b 88f - sth %g2, [%o0 - 2] -33: - ld [%o1], %g2 - sub %o2, 4, %o2 - srl %g2, 24, %g3 - and %o0, 7, %g5 - stb %g3, [%o0] - cmp %g5, 5 - srl %g2, 8, %g4 - sll %g2, 24, %g1 - sth %g4, [%o0 + 1] - add %o1, 4, %o1 - be 43f - and %o2, 0xffffffc0, %o3 - - ld [%o0 - 1], %o4 - add %o0, 4, %o0 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - SMOVE_CHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 4b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 24, %g2 -4: - SMOVE_CHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, -1) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 24, %g2 -1: - st %o4, [%o0 - 5] - b 88f - stb %g2, [%o0 - 1] -41: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 41b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 8, 24, -3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 + ldub [%i1], %g2 + stb %g2, [%i0 + 4] 1: - sth %g2, [%o0 - 3] - srl %g1, 8, %g4 - b 88f - stb %g4, [%o0 - 1] -43: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 43b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 24, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 24, 8, 3) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 24, %g2 -1: - stb %g2, [%o0 + 3] - b 88f - add %o0, 4, %o0 -42: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x10, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x20, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - SMOVE_ALIGNCHUNK(o1, o0, 0x30, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 64, %o3 - add %o1, 64, %o1 - bne 42b - add %o0, 64, %o0 - - andcc %o2, 0x30, %o3 - be,a 1f - srl %g1, 16, %g2 -4: - SMOVE_ALIGNCHUNK(o1, o0, 0x00, g2, g3, g4, g5, o4, o5, g7, g1, 16, 16, -2) - subcc %o3, 16, %o3 - add %o1, 16, %o1 - bne 4b - add %o0, 16, %o0 - - srl %g1, 16, %g2 -1: - sth %g2, [%o0 - 2] - - /* Fall through */ - -#endif /* FASTER_NONALIGNED */ + ret + restore %g7, %g0, %o0 88: /* short_end */ @@ -1127,7 +521,7 @@ FUNC(memcpy) /* %o0=dst %o1=src %o2=len */ stb %g2, [%o0] 1: retl - RETL_INSN + mov %g7, %o0 90: /* short_aligned_end */ bne 88b diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c index a3fccde894ec..aa4d55b0bdf0 100644 --- a/arch/sparc/math-emu/math_32.c +++ b/arch/sparc/math-emu/math_32.c @@ -164,7 +164,7 @@ int do_mathemu(struct pt_regs *regs, struct task_struct *fpt) int retcode = 0; /* assume all succeed */ unsigned long insn; - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); #ifdef DEBUG_MATHEMU printk("In do_mathemu()... pc is %08lx\n", regs->pc); diff --git a/arch/sparc/math-emu/math_64.c b/arch/sparc/math-emu/math_64.c index 56d2c44747b8..e575bd2fe381 100644 --- a/arch/sparc/math-emu/math_64.c +++ b/arch/sparc/math-emu/math_64.c @@ -184,7 +184,7 @@ int do_mathemu(struct pt_regs *regs, struct fpustate *f) if (tstate & TSTATE_PRIV) die_if_kernel("unfinished/unimplemented FPop from kernel", regs); - perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, 0, regs, 0); + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); if (test_thread_flag(TIF_32BIT)) pc = (u32)pc; if (get_user(insn, (u32 __user *) pc) != -EFAULT) { diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile index 79836a7dd00c..301421c11291 100644 --- a/arch/sparc/mm/Makefile +++ b/arch/sparc/mm/Makefile @@ -4,11 +4,10 @@ asflags-y := -ansi ccflags-y := -Werror -obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o +obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += loadmmu.o -obj-y += generic_$(BITS).o obj-$(CONFIG_SPARC32) += extable.o btfixup.o srmmu.o iommu.o io-unit.o obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o obj-$(CONFIG_SPARC_LEON)+= leon_mm.o diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 7543ddbdadb2..8023fd7e77b5 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -20,7 +20,6 @@ #include <linux/smp.h> #include <linux/perf_event.h> #include <linux/interrupt.h> -#include <linux/module.h> #include <linux/kdebug.h> #include <asm/system.h> @@ -251,7 +250,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write, if (in_atomic() || !mm) goto no_context; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); down_read(&mm->mmap_sem); @@ -301,12 +300,10 @@ good_area: } if (fault & VM_FAULT_MAJOR) { current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, - regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); } else { current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, - regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } up_read(&mm->mmap_sem); return; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index f92ce56a8b22..504c0622f729 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -325,7 +325,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) if (in_atomic() || !mm) goto intr_or_no_mm; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (!down_read_trylock(&mm->mmap_sem)) { if ((regs->tstate & TSTATE_PRIV) && @@ -433,12 +433,10 @@ good_area: } if (fault & VM_FAULT_MAJOR) { current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, - regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); } else { current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, - regs, address); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); } up_read(&mm->mmap_sem); diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c deleted file mode 100644 index e6067b75f11c..000000000000 --- a/arch/sparc/mm/generic_32.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * generic.c: Generic Sparc mm routines that are not dependent upon - * MMU type but are Sparc specific. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - */ - -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/pagemap.h> - -#include <asm/pgalloc.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> - -/* Remap IO memory, the same way as remap_pfn_range(), but use - * the obio memory space. - * - * They use a pgprot that sets PAGE_IO and does not check the - * mem_map table as this is independent of normal memory. - */ -static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - do { - set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space)); - address += PAGE_SIZE; - offset += PAGE_SIZE; - pte++; - } while (address < end); -} - -static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - offset -= address; - do { - pte_t *pte = pte_alloc_map(mm, NULL, pmd, address); - if (!pte) - return -ENOMEM; - io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address < end); - return 0; -} - -int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, unsigned long size, pgprot_t prot) -{ - int error = 0; - pgd_t * dir; - unsigned long beg = from; - unsigned long end = from + size; - struct mm_struct *mm = vma->vm_mm; - int space = GET_IOSPACE(pfn); - unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; - - /* See comment in mm/memory.c remap_pfn_range */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; - vma->vm_pgoff = (offset >> PAGE_SHIFT) | - ((unsigned long)space << 28UL); - - offset -= from; - dir = pgd_offset(mm, from); - flush_cache_range(vma, beg, end); - - while (from < end) { - pmd_t *pmd = pmd_alloc(mm, dir, from); - error = -ENOMEM; - if (!pmd) - break; - error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space); - if (error) - break; - from = (from + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } - - flush_tlb_range(vma, beg, end); - return error; -} -EXPORT_SYMBOL(io_remap_pfn_range); diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c deleted file mode 100644 index 3cb00dfd4bd6..000000000000 --- a/arch/sparc/mm/generic_64.c +++ /dev/null @@ -1,164 +0,0 @@ -/* - * generic.c: Generic Sparc mm routines that are not dependent upon - * MMU type but are Sparc specific. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - */ - -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/pagemap.h> - -#include <asm/pgalloc.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/tlbflush.h> - -/* Remap IO memory, the same way as remap_pfn_range(), but use - * the obio memory space. - * - * They use a pgprot that sets PAGE_IO and does not check the - * mem_map table as this is independent of normal memory. - */ -static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, - unsigned long address, - unsigned long size, - unsigned long offset, pgprot_t prot, - int space) -{ - unsigned long end; - - /* clear hack bit that was used as a write_combine side-effect flag */ - offset &= ~0x1UL; - address &= ~PMD_MASK; - end = address + size; - if (end > PMD_SIZE) - end = PMD_SIZE; - do { - pte_t entry; - unsigned long curend = address + PAGE_SIZE; - - entry = mk_pte_io(offset, prot, space, PAGE_SIZE); - if (!(address & 0xffff)) { - if (PAGE_SIZE < (4 * 1024 * 1024) && - !(address & 0x3fffff) && - !(offset & 0x3ffffe) && - end >= address + 0x400000) { - entry = mk_pte_io(offset, prot, space, - 4 * 1024 * 1024); - curend = address + 0x400000; - offset += 0x400000; - } else if (PAGE_SIZE < (512 * 1024) && - !(address & 0x7ffff) && - !(offset & 0x7fffe) && - end >= address + 0x80000) { - entry = mk_pte_io(offset, prot, space, - 512 * 1024 * 1024); - curend = address + 0x80000; - offset += 0x80000; - } else if (PAGE_SIZE < (64 * 1024) && - !(offset & 0xfffe) && - end >= address + 0x10000) { - entry = mk_pte_io(offset, prot, space, - 64 * 1024); - curend = address + 0x10000; - offset += 0x10000; - } else - offset += PAGE_SIZE; - } else - offset += PAGE_SIZE; - - if (pte_write(entry)) - entry = pte_mkdirty(entry); - do { - BUG_ON(!pte_none(*pte)); - set_pte_at(mm, address, pte, entry); - address += PAGE_SIZE; - pte_val(entry) += PAGE_SIZE; - pte++; - } while (address < curend); - } while (address < end); -} - -static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PGDIR_MASK; - end = address + size; - if (end > PGDIR_SIZE) - end = PGDIR_SIZE; - offset -= address; - do { - pte_t *pte = pte_alloc_map(mm, NULL, pmd, address); - if (!pte) - return -ENOMEM; - io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space); - pte_unmap(pte); - address = (address + PMD_SIZE) & PMD_MASK; - pmd++; - } while (address < end); - return 0; -} - -static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size, - unsigned long offset, pgprot_t prot, int space) -{ - unsigned long end; - - address &= ~PUD_MASK; - end = address + size; - if (end > PUD_SIZE) - end = PUD_SIZE; - offset -= address; - do { - pmd_t *pmd = pmd_alloc(mm, pud, address); - if (!pud) - return -ENOMEM; - io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space); - address = (address + PUD_SIZE) & PUD_MASK; - pud++; - } while (address < end); - return 0; -} - -int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, unsigned long size, pgprot_t prot) -{ - int error = 0; - pgd_t * dir; - unsigned long beg = from; - unsigned long end = from + size; - struct mm_struct *mm = vma->vm_mm; - int space = GET_IOSPACE(pfn); - unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; - unsigned long phys_base; - - phys_base = offset | (((unsigned long) space) << 32UL); - - /* See comment in mm/memory.c remap_pfn_range */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; - vma->vm_pgoff = phys_base >> PAGE_SHIFT; - - offset -= from; - dir = pgd_offset(mm, from); - flush_cache_range(vma, beg, end); - - while (from < end) { - pud_t *pud = pud_alloc(mm, dir, from); - error = -ENOMEM; - if (!pud) - break; - error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space); - if (error) - break; - from = (from + PGDIR_SIZE) & PGDIR_MASK; - dir++; - } - - flush_tlb_range(vma, beg, end); - return error; -} -EXPORT_SYMBOL(io_remap_pfn_range); diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c new file mode 100644 index 000000000000..42c55df3aec3 --- /dev/null +++ b/arch/sparc/mm/gup.c @@ -0,0 +1,183 @@ +/* + * Lockless get_user_pages_fast for sparc, cribbed from powerpc + * + * Copyright (C) 2008 Nick Piggin + * Copyright (C) 2008 Novell Inc. + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/pagemap.h> +#include <linux/rwsem.h> +#include <asm/pgtable.h> + +/* + * The performance critical leaf functions are made noinline otherwise gcc + * inlines everything into a single function which results in too much + * register pressure. + */ +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask, result; + pte_t *ptep; + + if (tlb_type == hypervisor) { + result = _PAGE_PRESENT_4V|_PAGE_P_4V; + if (write) + result |= _PAGE_WRITE_4V; + } else { + result = _PAGE_PRESENT_4U|_PAGE_P_4U; + if (write) + result |= _PAGE_WRITE_4U; + } + mask = result | _PAGE_SPECIAL; + + ptep = pte_offset_kernel(&pmd, addr); + do { + struct page *page, *head; + pte_t pte = *ptep; + + if ((pte_val(pte) & mask) != result) + return 0; + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + /* The hugepage case is simplified on sparc64 because + * we encode the sub-page pfn offsets into the + * hugepage PTEs. We could optimize this in the future + * use page_cache_add_speculative() for the hugepage case. + */ + page = pte_page(pte); + head = compound_head(page); + if (!page_cache_get_speculative(head)) + return 0; + if (unlikely(pte_val(pte) != pte_val(*ptep))) { + put_page(head); + return 0; + } + if (head != page) + get_huge_page_tail(page); + + pages[*nr] = page; + (*nr)++; + } while (ptep++, addr += PAGE_SIZE, addr != end); + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = *pmdp; + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + return 0; + if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(&pgd, addr); + do { + pud_t pud = *pudp; + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + return 0; + } while (pudp++, addr = next, addr != end); + + return 1; +} + +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long addr, len, end; + unsigned long next; + pgd_t *pgdp; + int nr = 0; + + start &= PAGE_MASK; + addr = start; + len = (unsigned long) nr_pages << PAGE_SHIFT; + end = start + len; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables from being freed on sparc. + * + * So long as we atomically load page table pointers versus teardown, + * we can follow the address down to the the page and take a ref on it. + */ + local_irq_disable(); + + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + goto slow; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + goto slow; + } while (pgdp++, addr = next, addr != end); + + local_irq_enable(); + + VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); + return nr; + + { + int ret; + +slow: + local_irq_enable(); + + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + + return ret; + } +} diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c index 4730eac0747b..77140a02c86a 100644 --- a/arch/sparc/mm/highmem.c +++ b/arch/sparc/mm/highmem.c @@ -24,6 +24,7 @@ */ #include <linux/mm.h> #include <linux/highmem.h> +#include <linux/export.h> #include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index f4e97646ce23..07e14535375c 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -5,7 +5,6 @@ */ #include <linux/init.h> -#include <linux/module.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/hugetlb.h> diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 8415f614ce0c..8584a25a9f0d 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -511,6 +511,11 @@ static void __init read_obp_translations(void) for (i = 0; i < prom_trans_ents; i++) prom_trans[i].data &= ~0x0003fe0000000000UL; } + + /* Force execute bit on. */ + for (i = 0; i < prom_trans_ents; i++) + prom_trans[i].data |= (tlb_type == hypervisor ? + _PAGE_EXEC_4V : _PAGE_EXEC_4U); } static void __init hypervisor_tlb_lock(unsigned long vaddr, @@ -1597,6 +1602,44 @@ static void __init tsb_phys_patch(void) static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR]; extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; +static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa) +{ + pa >>= KTSB_PHYS_SHIFT; + + while (start < end) { + unsigned int *ia = (unsigned int *)(unsigned long)*start; + + ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10); + __asm__ __volatile__("flush %0" : : "r" (ia)); + + ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff); + __asm__ __volatile__("flush %0" : : "r" (ia + 1)); + + start++; + } +} + +static void ktsb_phys_patch(void) +{ + extern unsigned int __swapper_tsb_phys_patch; + extern unsigned int __swapper_tsb_phys_patch_end; + unsigned long ktsb_pa; + + ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE); + patch_one_ktsb_phys(&__swapper_tsb_phys_patch, + &__swapper_tsb_phys_patch_end, ktsb_pa); +#ifndef CONFIG_DEBUG_PAGEALLOC + { + extern unsigned int __swapper_4m_tsb_phys_patch; + extern unsigned int __swapper_4m_tsb_phys_patch_end; + ktsb_pa = (kern_base + + ((unsigned long)&swapper_4m_tsb[0] - KERNBASE)); + patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch, + &__swapper_4m_tsb_phys_patch_end, ktsb_pa); + } +#endif +} + static void __init sun4v_ktsb_init(void) { unsigned long ktsb_pa; @@ -1716,8 +1759,10 @@ void __init paging_init(void) sun4u_pgprot_init(); if (tlb_type == cheetah_plus || - tlb_type == hypervisor) + tlb_type == hypervisor) { tsb_phys_patch(); + ktsb_phys_patch(); + } if (tlb_type == hypervisor) { sun4v_patch_tlb_handlers(); diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c index c0e01297e64e..13c2169822a8 100644 --- a/arch/sparc/mm/leon_mm.c +++ b/arch/sparc/mm/leon_mm.c @@ -162,7 +162,7 @@ ready: printk(KERN_INFO "swprobe: padde %x\n", paddr_calc); if (paddr) *paddr = paddr_calc; - return paddrbase; + return pte; } void leon_flush_icache_all(void) @@ -226,7 +226,7 @@ void leon3_getCacheRegs(struct leon3_cacheregs *regs) * Leon2 and Leon3 differ in their way of telling cache information * */ -int leon_flush_needed(void) +int __init leon_flush_needed(void) { int flush_needed = -1; unsigned int ssize, sets; diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index a5f51b22fcbe..536412d8f416 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -236,6 +236,8 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign } } +struct kmem_cache *pgtable_cache __read_mostly; + static struct kmem_cache *tsb_caches[8] __read_mostly; static const char *tsb_cache_names[8] = { @@ -253,6 +255,15 @@ void __init pgtable_cache_init(void) { unsigned long i; + pgtable_cache = kmem_cache_create("pgtable_cache", + PAGE_SIZE, PAGE_SIZE, + 0, + _clear_page); + if (!pgtable_cache) { + prom_printf("pgtable_cache_init(): Could not create!\n"); + prom_halt(); + } + for (i = 0; i < 8; i++) { unsigned long size = 8192 << i; const char *name = tsb_cache_names[i]; |