diff options
Diffstat (limited to 'arch/parisc/kernel')
34 files changed, 1127 insertions, 753 deletions
diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile index 66ee3f12df5..ff87b4603e3 100644 --- a/arch/parisc/kernel/Makefile +++ b/arch/parisc/kernel/Makefile @@ -29,7 +29,9 @@ obj-$(CONFIG_PCI) += pci.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_64BIT) += binfmt_elf32.o sys_parisc32.o signal32.o obj-$(CONFIG_STACKTRACE)+= stacktrace.o +obj-$(CONFIG_AUDIT) += audit.o +obj64-$(CONFIG_AUDIT) += compat_audit.o # only supported for PCX-W/U in 64-bit mode at the moment -obj-$(CONFIG_64BIT) += perf.o perf_asm.o +obj-$(CONFIG_64BIT) += perf.o perf_asm.o $(obj64-y) obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o diff --git a/arch/parisc/kernel/audit.c b/arch/parisc/kernel/audit.c new file mode 100644 index 00000000000..eb64a6148c8 --- /dev/null +++ b/arch/parisc/kernel/audit.c @@ -0,0 +1,81 @@ +#include <linux/init.h> +#include <linux/types.h> +#include <linux/audit.h> +#include <asm/unistd.h> + +static unsigned dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +static unsigned read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +static unsigned write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +static unsigned chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +static unsigned signal_class[] = { +#include <asm-generic/audit_signal.h> +~0U +}; + +int audit_classify_arch(int arch) +{ +#ifdef CONFIG_COMPAT + if (arch == AUDIT_ARCH_PARISC) + return 1; +#endif + return 0; +} + +int audit_classify_syscall(int abi, unsigned syscall) +{ +#ifdef CONFIG_COMPAT + extern int parisc32_classify_syscall(unsigned); + if (abi == AUDIT_ARCH_PARISC) + return parisc32_classify_syscall(syscall); +#endif + switch (syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_execve: + return 5; + default: + return 0; + } +} + +static int __init audit_classes_init(void) +{ +#ifdef CONFIG_COMPAT + extern __u32 parisc32_dir_class[]; + extern __u32 parisc32_write_class[]; + extern __u32 parisc32_read_class[]; + extern __u32 parisc32_chattr_class[]; + extern __u32 parisc32_signal_class[]; + audit_register_class(AUDIT_CLASS_WRITE_32, parisc32_write_class); + audit_register_class(AUDIT_CLASS_READ_32, parisc32_read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE_32, parisc32_dir_class); + audit_register_class(AUDIT_CLASS_CHATTR_32, parisc32_chattr_class); + audit_register_class(AUDIT_CLASS_SIGNAL_32, parisc32_signal_class); +#endif + audit_register_class(AUDIT_CLASS_WRITE, write_class); + audit_register_class(AUDIT_CLASS_READ, read_class); + audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class); + audit_register_class(AUDIT_CLASS_CHATTR, chattr_class); + audit_register_class(AUDIT_CLASS_SIGNAL, signal_class); + return 0; +} + +__initcall(audit_classes_init); diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 4b12890642e..f6448c7c62b 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -71,18 +71,27 @@ flush_cache_all_local(void) } EXPORT_SYMBOL(flush_cache_all_local); +/* Virtual address of pfn. */ +#define pfn_va(pfn) __va(PFN_PHYS(pfn)) + void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - struct page *page = pte_page(*ptep); + unsigned long pfn = pte_pfn(*ptep); + struct page *page; - if (pfn_valid(page_to_pfn(page)) && page_mapping(page) && - test_bit(PG_dcache_dirty, &page->flags)) { + /* We don't have pte special. As a result, we can be called with + an invalid pfn and we don't need to flush the kernel dcache page. + This occurs with FireGL card in C8000. */ + if (!pfn_valid(pfn)) + return; - flush_kernel_dcache_page(page); + page = pfn_to_page(pfn); + if (page_mapping(page) && test_bit(PG_dcache_dirty, &page->flags)) { + flush_kernel_dcache_page_addr(pfn_va(pfn)); clear_bit(PG_dcache_dirty, &page->flags); } else if (parisc_requires_coherency()) - flush_kernel_dcache_page(page); + flush_kernel_dcache_page_addr(pfn_va(pfn)); } void @@ -314,7 +323,8 @@ void flush_dcache_page(struct page *page) * specifically accesses it, of course) */ flush_tlb_page(mpnt, addr); - if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { __flush_cache_page(mpnt, addr, page_to_phys(page)); if (old_addr) printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? (char *)mpnt->vm_file->f_path.dentry->d_name.name : "(null)"); @@ -379,41 +389,20 @@ void flush_kernel_dcache_page_addr(void *addr) } EXPORT_SYMBOL(flush_kernel_dcache_page_addr); -void clear_user_page(void *vto, unsigned long vaddr, struct page *page) -{ - clear_page_asm(vto); - if (!parisc_requires_coherency()) - flush_kernel_dcache_page_asm(vto); -} -EXPORT_SYMBOL(clear_user_page); - void copy_user_page(void *vto, void *vfrom, unsigned long vaddr, struct page *pg) { - /* Copy using kernel mapping. No coherency is needed - (all in kmap/kunmap) on machines that don't support - non-equivalent aliasing. However, the `from' page - needs to be flushed before it can be accessed through - the kernel mapping. */ + /* Copy using kernel mapping. No coherency is needed (all in + kunmap) for the `to' page. However, the `from' page needs to + be flushed through a mapping equivalent to the user mapping + before it can be accessed through the kernel mapping. */ preempt_disable(); flush_dcache_page_asm(__pa(vfrom), vaddr); preempt_enable(); copy_page_asm(vto, vfrom); - if (!parisc_requires_coherency()) - flush_kernel_dcache_page_asm(vto); } EXPORT_SYMBOL(copy_user_page); -#ifdef CONFIG_PA8X00 - -void kunmap_parisc(void *addr) -{ - if (parisc_requires_coherency()) - flush_kernel_dcache_page_addr(addr); -} -EXPORT_SYMBOL(kunmap_parisc); -#endif - void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) { unsigned long flags; @@ -421,14 +410,11 @@ void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) /* Note: purge_tlb_entries can be called at startup with no context. */ - /* Disable preemption while we play with %sr1. */ - preempt_disable(); - mtsp(mm->context, 1); purge_tlb_start(flags); + mtsp(mm->context, 1); pdtlb(addr); pitlb(addr); purge_tlb_end(flags); - preempt_enable(); } EXPORT_SYMBOL(purge_tlb_entries); @@ -443,8 +429,8 @@ void __flush_tlb_range(unsigned long sid, unsigned long start, else { unsigned long flags; - mtsp(sid, 1); purge_tlb_start(flags); + mtsp(sid, 1); if (split_tlb) { while (npages--) { pdtlb(start); @@ -498,44 +484,42 @@ static inline pte_t *get_ptep(pgd_t *pgd, unsigned long addr) void flush_cache_mm(struct mm_struct *mm) { + struct vm_area_struct *vma; + pgd_t *pgd; + /* Flushing the whole cache on each cpu takes forever on rp3440, etc. So, avoid it if the mm isn't too big. */ - if (mm_total_size(mm) < parisc_cache_flush_threshold) { - struct vm_area_struct *vma; - - if (mm->context == mfsp(3)) { - for (vma = mm->mmap; vma; vma = vma->vm_next) { - flush_user_dcache_range_asm(vma->vm_start, - vma->vm_end); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm( - vma->vm_start, vma->vm_end); - } - } else { - pgd_t *pgd = mm->pgd; - - for (vma = mm->mmap; vma; vma = vma->vm_next) { - unsigned long addr; - - for (addr = vma->vm_start; addr < vma->vm_end; - addr += PAGE_SIZE) { - pte_t *ptep = get_ptep(pgd, addr); - if (ptep != NULL) { - pte_t pte = *ptep; - __flush_cache_page(vma, addr, - page_to_phys(pte_page(pte))); - } - } - } + if (mm_total_size(mm) >= parisc_cache_flush_threshold) { + flush_cache_all(); + return; + } + + if (mm->context == mfsp(3)) { + for (vma = mm->mmap; vma; vma = vma->vm_next) { + flush_user_dcache_range_asm(vma->vm_start, vma->vm_end); + if ((vma->vm_flags & VM_EXEC) == 0) + continue; + flush_user_icache_range_asm(vma->vm_start, vma->vm_end); } return; } -#ifdef CONFIG_SMP - flush_cache_all(); -#else - flush_cache_all_local(); -#endif + pgd = mm->pgd; + for (vma = mm->mmap; vma; vma = vma->vm_next) { + unsigned long addr; + + for (addr = vma->vm_start; addr < vma->vm_end; + addr += PAGE_SIZE) { + unsigned long pfn; + pte_t *ptep = get_ptep(pgd, addr); + if (!ptep) + continue; + pfn = pte_pfn(*ptep); + if (!pfn_valid(pfn)) + continue; + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + } + } } void @@ -559,33 +543,32 @@ flush_user_icache_range(unsigned long start, unsigned long end) void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { + unsigned long addr; + pgd_t *pgd; + BUG_ON(!vma->vm_mm->context); - if ((end - start) < parisc_cache_flush_threshold) { - if (vma->vm_mm->context == mfsp(3)) { - flush_user_dcache_range_asm(start, end); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(start, end); - } else { - unsigned long addr; - pgd_t *pgd = vma->vm_mm->pgd; - - for (addr = start & PAGE_MASK; addr < end; - addr += PAGE_SIZE) { - pte_t *ptep = get_ptep(pgd, addr); - if (ptep != NULL) { - pte_t pte = *ptep; - flush_cache_page(vma, - addr, pte_pfn(pte)); - } - } - } - } else { -#ifdef CONFIG_SMP + if ((end - start) >= parisc_cache_flush_threshold) { flush_cache_all(); -#else - flush_cache_all_local(); -#endif + return; + } + + if (vma->vm_mm->context == mfsp(3)) { + flush_user_dcache_range_asm(start, end); + if (vma->vm_flags & VM_EXEC) + flush_user_icache_range_asm(start, end); + return; + } + + pgd = vma->vm_mm->pgd; + for (addr = start & PAGE_MASK; addr < end; addr += PAGE_SIZE) { + unsigned long pfn; + pte_t *ptep = get_ptep(pgd, addr); + if (!ptep) + continue; + pfn = pte_pfn(*ptep); + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); } } @@ -594,71 +577,8 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long { BUG_ON(!vma->vm_mm->context); - flush_tlb_page(vma, vmaddr); - __flush_cache_page(vma, vmaddr, page_to_phys(pfn_to_page(pfn))); - -} - -#ifdef CONFIG_PARISC_TMPALIAS - -void clear_user_highpage(struct page *page, unsigned long vaddr) -{ - void *vto; - unsigned long flags; - - /* Clear using TMPALIAS region. The page doesn't need to - be flushed but the kernel mapping needs to be purged. */ - - vto = kmap_atomic(page, KM_USER0); - - /* The PA-RISC 2.0 Architecture book states on page F-6: - "Before a write-capable translation is enabled, *all* - non-equivalently-aliased translations must be removed - from the page table and purged from the TLB. (Note - that the caches are not required to be flushed at this - time.) Before any non-equivalent aliased translation - is re-enabled, the virtual address range for the writeable - page (the entire page) must be flushed from the cache, - and the write-capable translation removed from the page - table and purged from the TLB." */ - - purge_kernel_dcache_page_asm((unsigned long)vto); - purge_tlb_start(flags); - pdtlb_kernel(vto); - purge_tlb_end(flags); - preempt_disable(); - clear_user_page_asm(vto, vaddr); - preempt_enable(); - - pagefault_enable(); /* kunmap_atomic(addr, KM_USER0); */ -} - -void copy_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - void *vfrom, *vto; - unsigned long flags; - - /* Copy using TMPALIAS region. This has the advantage - that the `from' page doesn't need to be flushed. However, - the `to' page must be flushed in copy_user_page_asm since - it can be used to bring in executable code. */ - - vfrom = kmap_atomic(from, KM_USER0); - vto = kmap_atomic(to, KM_USER1); - - purge_kernel_dcache_page_asm((unsigned long)vto); - purge_tlb_start(flags); - pdtlb_kernel(vto); - pdtlb_kernel(vfrom); - purge_tlb_end(flags); - preempt_disable(); - copy_user_page_asm(vto, vfrom, vaddr); - flush_dcache_page_asm(__pa(vto), vaddr); - preempt_enable(); - - pagefault_enable(); /* kunmap_atomic(addr, KM_USER1); */ - pagefault_enable(); /* kunmap_atomic(addr, KM_USER0); */ + if (pfn_valid(pfn)) { + flush_tlb_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + } } - -#endif /* CONFIG_PARISC_TMPALIAS */ diff --git a/arch/parisc/kernel/compat_audit.c b/arch/parisc/kernel/compat_audit.c new file mode 100644 index 00000000000..c74478f6bc7 --- /dev/null +++ b/arch/parisc/kernel/compat_audit.c @@ -0,0 +1,40 @@ +#include <asm/unistd.h> + +unsigned int parisc32_dir_class[] = { +#include <asm-generic/audit_dir_write.h> +~0U +}; + +unsigned int parisc32_chattr_class[] = { +#include <asm-generic/audit_change_attr.h> +~0U +}; + +unsigned int parisc32_write_class[] = { +#include <asm-generic/audit_write.h> +~0U +}; + +unsigned int parisc32_read_class[] = { +#include <asm-generic/audit_read.h> +~0U +}; + +unsigned int parisc32_signal_class[] = { +#include <asm-generic/audit_signal.h> +~0U +}; + +int parisc32_classify_syscall(unsigned syscall) +{ + switch (syscall) { + case __NR_open: + return 2; + case __NR_openat: + return 3; + case __NR_execve: + return 5; + default: + return 1; + } +} diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index 5709c5e59be..dba508fe168 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -282,18 +282,6 @@ find_pa_parent_type(const struct parisc_device *padev, int type) return NULL; } -#ifdef CONFIG_PCI -static inline int is_pci_dev(struct device *dev) -{ - return dev->bus == &pci_bus_type; -} -#else -static inline int is_pci_dev(struct device *dev) -{ - return 0; -} -#endif - /* * get_node_path fills in @path with the firmware path to the device. * Note that if @node is a parisc device, we don't fill in the 'mod' field. @@ -306,7 +294,7 @@ static void get_node_path(struct device *dev, struct hardware_path *path) int i = 5; memset(&path->bc, -1, 6); - if (is_pci_dev(dev)) { + if (dev_is_pci(dev)) { unsigned int devfn = to_pci_dev(dev)->devfn; path->mod = PCI_FUNC(devfn); path->bc[i--] = PCI_SLOT(devfn); @@ -314,7 +302,7 @@ static void get_node_path(struct device *dev, struct hardware_path *path) } while (dev != &root) { - if (is_pci_dev(dev)) { + if (dev_is_pci(dev)) { unsigned int devfn = to_pci_dev(dev)->devfn; path->bc[i--] = PCI_SLOT(devfn) | (PCI_FUNC(devfn)<< 5); } else if (dev->bus == &parisc_bus_type) { @@ -394,7 +382,7 @@ EXPORT_SYMBOL(print_pci_hwpath); static void setup_bus_id(struct parisc_device *padev) { struct hardware_path path; - char name[20]; + char name[28]; char *output = name; int i; @@ -695,7 +683,7 @@ static int check_parent(struct device * dev, void * data) if (dev->bus == &parisc_bus_type) { if (match_parisc_device(dev, d->index, d->modpath)) d->dev = dev; - } else if (is_pci_dev(dev)) { + } else if (dev_is_pci(dev)) { if (match_pci_device(dev, d->index, d->modpath)) d->dev = dev; } else if (dev->bus == NULL) { @@ -753,7 +741,7 @@ struct device *hwpath_to_device(struct hardware_path *modpath) if (!parent) return NULL; } - if (is_pci_dev(parent)) /* pci devices already parse MOD */ + if (dev_is_pci(parent)) /* pci devices already parse MOD */ return parent; else return parse_tree_node(parent, 6, modpath); @@ -772,7 +760,7 @@ void device_to_hwpath(struct device *dev, struct hardware_path *path) padev = to_parisc_device(dev); get_node_path(dev->parent, path); path->mod = padev->hw_path; - } else if (is_pci_dev(dev)) { + } else if (dev_is_pci(dev)) { get_node_path(dev, path); } } diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index f33201bf897..e8f07dd2840 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -65,15 +65,11 @@ rsm PSW_SM_I, %r0 /* barrier for "Relied upon Translation */ mtsp %r0, %sr4 mtsp %r0, %sr5 - mfsp %sr7, %r1 - or,= %r0,%r1,%r0 /* Only save sr7 in sr3 if sr7 != 0 */ - mtsp %r1, %sr3 + mtsp %r0, %sr6 tovirt_r1 %r29 load32 KERNEL_PSW, %r1 rsm PSW_SM_QUIET,%r0 /* second "heavy weight" ctl op */ - mtsp %r0, %sr6 - mtsp %r0, %sr7 mtctl %r0, %cr17 /* Clear IIASQ tail */ mtctl %r0, %cr17 /* Clear IIASQ head */ mtctl %r1, %ipsw @@ -119,17 +115,20 @@ /* we save the registers in the task struct */ + copy %r30, %r17 mfctl %cr30, %r1 + ldo THREAD_SZ_ALGN(%r1), %r30 + mtsp %r0,%sr7 + mtsp %r16,%sr3 tophys %r1,%r9 LDREG TI_TASK(%r9), %r1 /* thread_info -> task_struct */ tophys %r1,%r9 ldo TASK_REGS(%r9),%r9 - STREG %r30, PT_GR30(%r9) + STREG %r17,PT_GR30(%r9) STREG %r29,PT_GR29(%r9) STREG %r26,PT_GR26(%r9) + STREG %r16,PT_SR7(%r9) copy %r9,%r29 - mfctl %cr30, %r1 - ldo THREAD_SZ_ALGN(%r1), %r30 .endm .macro get_stack_use_r30 @@ -137,10 +136,12 @@ /* we put a struct pt_regs on the stack and save the registers there */ tophys %r30,%r9 - STREG %r30,PT_GR30(%r9) + copy %r30,%r1 ldo PT_SZ_ALGN(%r30),%r30 + STREG %r1,PT_GR30(%r9) STREG %r29,PT_GR29(%r9) STREG %r26,PT_GR26(%r9) + STREG %r16,PT_SR7(%r9) copy %r9,%r29 .endm @@ -400,7 +401,15 @@ #if PT_NLEVELS == 3 extru \va,31-ASM_PMD_SHIFT,ASM_BITS_PER_PMD,\index #else +# if defined(CONFIG_64BIT) + extrd,u \va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index + #else + # if PAGE_SIZE > 4096 + extru \va,31-ASM_PGDIR_SHIFT,32-ASM_PGDIR_SHIFT,\index + # else extru \va,31-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index + # endif +# endif #endif dep %r0,31,PAGE_SHIFT,\pmd /* clear offset */ copy %r0,\pte @@ -444,9 +453,41 @@ L2_ptep \pgd,\pte,\index,\va,\fault .endm + /* Acquire pa_dbit_lock lock. */ + .macro dbit_lock spc,tmp,tmp1 +#ifdef CONFIG_SMP + cmpib,COND(=),n 0,\spc,2f + load32 PA(pa_dbit_lock),\tmp +1: LDCW 0(\tmp),\tmp1 + cmpib,COND(=) 0,\tmp1,1b + nop +2: +#endif + .endm + + /* Release pa_dbit_lock lock without reloading lock address. */ + .macro dbit_unlock0 spc,tmp +#ifdef CONFIG_SMP + or,COND(=) %r0,\spc,%r0 + stw \spc,0(\tmp) +#endif + .endm + + /* Release pa_dbit_lock lock. */ + .macro dbit_unlock1 spc,tmp +#ifdef CONFIG_SMP + load32 PA(pa_dbit_lock),\tmp + dbit_unlock0 \spc,\tmp +#endif + .endm + /* Set the _PAGE_ACCESSED bit of the PTE. Be clever and * don't needlessly dirty the cache line if it was already set */ - .macro update_ptep ptep,pte,tmp,tmp1 + .macro update_ptep spc,ptep,pte,tmp,tmp1 +#ifdef CONFIG_SMP + or,COND(=) %r0,\spc,%r0 + LDREG 0(\ptep),\pte +#endif ldi _PAGE_ACCESSED,\tmp1 or \tmp1,\pte,\tmp and,COND(<>) \tmp1,\pte,%r0 @@ -455,7 +496,11 @@ /* Set the dirty bit (and accessed bit). No need to be * clever, this is only used from the dirty fault */ - .macro update_dirty ptep,pte,tmp + .macro update_dirty spc,ptep,pte,tmp +#ifdef CONFIG_SMP + or,COND(=) %r0,\spc,%r0 + LDREG 0(\ptep),\pte +#endif ldi _PAGE_ACCESSED|_PAGE_DIRTY,\tmp or \tmp,\pte,\pte STREG \pte,0(\ptep) @@ -615,7 +660,7 @@ .text - .align PAGE_SIZE + .align 4096 ENTRY(fault_vector_20) /* First vector is invalid (0) */ @@ -825,11 +870,6 @@ ENTRY(syscall_exit_rfi) STREG %r19,PT_SR7(%r16) intr_return: - /* NOTE: Need to enable interrupts incase we schedule. */ - ssm PSW_SM_I, %r0 - -intr_check_resched: - /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ @@ -856,6 +896,11 @@ intr_check_sig: LDREG PT_IASQ1(%r16), %r20 cmpib,COND(=),n 0,%r20,intr_restore /* backward */ + /* NOTE: We need to enable interrupts if we have to deliver + * signals. We used to do this earlier but it caused kernel + * stack overflows. */ + ssm PSW_SM_I, %r0 + copy %r0, %r25 /* long in_syscall = 0 */ #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ @@ -907,6 +952,10 @@ intr_do_resched: cmpib,COND(=) 0, %r20, intr_do_preempt nop + /* NOTE: We need to enable interrupts if we schedule. We used + * to do this earlier but it caused kernel stack overflows. */ + ssm PSW_SM_I, %r0 + #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif @@ -1099,11 +1148,13 @@ dtlb_miss_20w: L3_ptep ptp,pte,t0,va,dtlb_check_alias_20w - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1123,11 +1174,13 @@ nadtlb_miss_20w: L3_ptep ptp,pte,t0,va,nadtlb_check_alias_20w - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1149,7 +1202,8 @@ dtlb_miss_11: L2_ptep ptp,pte,t0,va,dtlb_check_alias_11 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1160,6 +1214,7 @@ dtlb_miss_11: idtlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1180,7 +1235,8 @@ nadtlb_miss_11: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_11 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1192,6 +1248,7 @@ nadtlb_miss_11: idtlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1212,13 +1269,15 @@ dtlb_miss_20: L2_ptep ptp,pte,t0,va,dtlb_check_alias_20 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1238,13 +1297,15 @@ nadtlb_miss_20: L2_ptep ptp,pte,t0,va,nadtlb_check_alias_20 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 idtlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1345,11 +1406,13 @@ itlb_miss_20w: L3_ptep ptp,pte,t0,va,itlb_fault - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1367,11 +1430,13 @@ naitlb_miss_20w: L3_ptep ptp,pte,t0,va,naitlb_check_alias_20w - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1393,7 +1458,8 @@ itlb_miss_11: L2_ptep ptp,pte,t0,va,itlb_fault - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1404,6 +1470,7 @@ itlb_miss_11: iitlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1415,7 +1482,8 @@ naitlb_miss_11: L2_ptep ptp,pte,t0,va,naitlb_check_alias_11 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb_11 spc,pte,prot @@ -1426,6 +1494,7 @@ naitlb_miss_11: iitlbp prot,(%sr1,va) mtsp t0, %sr1 /* Restore sr1 */ + dbit_unlock1 spc,t0 rfir nop @@ -1447,13 +1516,15 @@ itlb_miss_20: L2_ptep ptp,pte,t0,va,itlb_fault - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1465,13 +1536,15 @@ naitlb_miss_20: L2_ptep ptp,pte,t0,va,naitlb_check_alias_20 - update_ptep ptp,pte,t0,t1 + dbit_lock spc,t0,t1 + update_ptep spc,ptp,pte,t0,t1 make_insert_tlb spc,pte,prot f_extend pte,t0 iitlbt pte,prot + dbit_unlock1 spc,t0 rfir nop @@ -1495,29 +1568,13 @@ dbit_trap_20w: L3_ptep ptp,pte,t0,va,dbit_fault -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nolock_20w - load32 PA(pa_dbit_lock),t0 - -dbit_spin_20w: - LDCW 0(t0),t1 - cmpib,COND(=) 0,t1,dbit_spin_20w - nop - -dbit_nolock_20w: -#endif - update_dirty ptp,pte,t1 + dbit_lock spc,t0,t1 + update_dirty spc,ptp,pte,t1 make_insert_tlb spc,pte,prot idtlbt pte,prot -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nounlock_20w - ldi 1,t1 - stw t1,0(t0) - -dbit_nounlock_20w: -#endif + dbit_unlock0 spc,t0 rfir nop @@ -1531,18 +1588,8 @@ dbit_trap_11: L2_ptep ptp,pte,t0,va,dbit_fault -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nolock_11 - load32 PA(pa_dbit_lock),t0 - -dbit_spin_11: - LDCW 0(t0),t1 - cmpib,= 0,t1,dbit_spin_11 - nop - -dbit_nolock_11: -#endif - update_dirty ptp,pte,t1 + dbit_lock spc,t0,t1 + update_dirty spc,ptp,pte,t1 make_insert_tlb_11 spc,pte,prot @@ -1553,13 +1600,7 @@ dbit_nolock_11: idtlbp prot,(%sr1,va) mtsp t1, %sr1 /* Restore sr1 */ -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nounlock_11 - ldi 1,t1 - stw t1,0(t0) - -dbit_nounlock_11: -#endif + dbit_unlock0 spc,t0 rfir nop @@ -1571,32 +1612,15 @@ dbit_trap_20: L2_ptep ptp,pte,t0,va,dbit_fault -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nolock_20 - load32 PA(pa_dbit_lock),t0 - -dbit_spin_20: - LDCW 0(t0),t1 - cmpib,= 0,t1,dbit_spin_20 - nop - -dbit_nolock_20: -#endif - update_dirty ptp,pte,t1 + dbit_lock spc,t0,t1 + update_dirty spc,ptp,pte,t1 make_insert_tlb spc,pte,prot f_extend pte,t1 idtlbt pte,prot - -#ifdef CONFIG_SMP - cmpib,COND(=),n 0,spc,dbit_nounlock_20 - ldi 1,t1 - stw t1,0(t0) - -dbit_nounlock_20: -#endif + dbit_unlock0 spc,t0 rfir nop @@ -1694,7 +1718,8 @@ ENTRY(sys_\name\()_wrapper) ldo TASK_REGS(%r1),%r1 reg_save %r1 mfctl %cr27, %r28 - b sys_\name + ldil L%sys_\name, %r31 + be R%sys_\name(%sr4,%r31) STREG %r28, PT_CR27(%r1) ENDPROC(sys_\name\()_wrapper) .endm @@ -1997,6 +2022,47 @@ ftrace_stub: ENDPROC(return_to_handler) #endif /* CONFIG_FUNCTION_TRACER */ +#ifdef CONFIG_IRQSTACKS +/* void call_on_stack(unsigned long param1, void *func, + unsigned long new_stack) */ +ENTRY(call_on_stack) + copy %sp, %r1 + + /* Regarding the HPPA calling conventions for function pointers, + we assume the PIC register is not changed across call. For + CONFIG_64BIT, the argument pointer is left to point at the + argument region allocated for the call to call_on_stack. */ +# ifdef CONFIG_64BIT + /* Switch to new stack. We allocate two 128 byte frames. */ + ldo 256(%arg2), %sp + /* Save previous stack pointer and return pointer in frame marker */ + STREG %rp, -144(%sp) + /* Calls always use function descriptor */ + LDREG 16(%arg1), %arg1 + bve,l (%arg1), %rp + STREG %r1, -136(%sp) + LDREG -144(%sp), %rp + bve (%rp) + LDREG -136(%sp), %sp +# else + /* Switch to new stack. We allocate two 64 byte frames. */ + ldo 128(%arg2), %sp + /* Save previous stack pointer and return pointer in frame marker */ + STREG %r1, -68(%sp) + STREG %rp, -84(%sp) + /* Calls use function descriptor if PLABEL bit is set */ + bb,>=,n %arg1, 30, 1f + depwi 0,31,2, %arg1 + LDREG 0(%arg1), %arg1 +1: + be,l 0(%sr4,%arg1), %sr0, %r31 + copy %r31, %rp + LDREG -84(%sp), %rp + bv (%rp) + LDREG -68(%sp), %sp +# endif /* CONFIG_64BIT */ +ENDPROC(call_on_stack) +#endif /* CONFIG_IRQSTACKS */ get_register: /* diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index f65fa480c90..22395901d47 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -150,7 +150,7 @@ static void convert_to_wide(unsigned long *addr) } #ifdef CONFIG_64BIT -void __cpuinit set_firmware_width_unlocked(void) +void set_firmware_width_unlocked(void) { int ret; @@ -167,7 +167,7 @@ void __cpuinit set_firmware_width_unlocked(void) * This function must be called before any pdc_* function that uses the * convert_to_wide function. */ -void __cpuinit set_firmware_width(void) +void set_firmware_width(void) { unsigned long flags; spin_lock_irqsave(&pdc_lock, flags); @@ -175,11 +175,13 @@ void __cpuinit set_firmware_width(void) spin_unlock_irqrestore(&pdc_lock, flags); } #else -void __cpuinit set_firmware_width_unlocked(void) { +void set_firmware_width_unlocked(void) +{ return; } -void __cpuinit set_firmware_width(void) { +void set_firmware_width(void) +{ return; } #endif /*CONFIG_64BIT*/ @@ -301,7 +303,7 @@ int pdc_chassis_warn(unsigned long *warn) return retval; } -int __cpuinit pdc_coproc_cfg_unlocked(struct pdc_coproc_cfg *pdc_coproc_info) +int pdc_coproc_cfg_unlocked(struct pdc_coproc_cfg *pdc_coproc_info) { int ret; @@ -322,7 +324,7 @@ int __cpuinit pdc_coproc_cfg_unlocked(struct pdc_coproc_cfg *pdc_coproc_info) * This PDC call returns the presence and status of all the coprocessors * attached to the processor. */ -int __cpuinit pdc_coproc_cfg(struct pdc_coproc_cfg *pdc_coproc_info) +int pdc_coproc_cfg(struct pdc_coproc_cfg *pdc_coproc_info) { int ret; unsigned long flags; diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c index f7752f6af29..af3bc359dc7 100644 --- a/arch/parisc/kernel/hardware.c +++ b/arch/parisc/kernel/hardware.c @@ -36,6 +36,9 @@ * HP PARISC Hardware Database * Access to this database is only possible during bootup * so don't reference this table after starting the init process + * + * NOTE: Product names which are listed here and ends with a '?' + * are guessed. If you know the correct name, please let us know. */ static struct hp_hardware hp_hardware_list[] = { @@ -222,6 +225,7 @@ static struct hp_hardware hp_hardware_list[] = { {HPHW_NPROC,0x5DD,0x4,0x81,"Duet W2"}, {HPHW_NPROC,0x5DE,0x4,0x81,"Piccolo W+"}, {HPHW_NPROC,0x5DF,0x4,0x81,"Cantata W2"}, + {HPHW_NPROC,0x5DF,0x0,0x00,"Marcato W+ (rp5470)?"}, {HPHW_NPROC,0x5E0,0x4,0x91,"Cantata DC- W2"}, {HPHW_NPROC,0x5E1,0x4,0x91,"Crescendo DC- W2"}, {HPHW_NPROC,0x5E2,0x4,0x91,"Crescendo 650 W2"}, @@ -275,9 +279,11 @@ static struct hp_hardware hp_hardware_list[] = { {HPHW_NPROC,0x888,0x4,0x91,"Storm Peak Fast DC-"}, {HPHW_NPROC,0x889,0x4,0x91,"Storm Peak Fast"}, {HPHW_NPROC,0x88A,0x4,0x91,"Crestone Peak Slow"}, + {HPHW_NPROC,0x88B,0x4,0x91,"Crestone Peak Fast?"}, {HPHW_NPROC,0x88C,0x4,0x91,"Orca Mako+"}, {HPHW_NPROC,0x88D,0x4,0x91,"Rainier/Medel Mako+ Slow"}, {HPHW_NPROC,0x88E,0x4,0x91,"Rainier/Medel Mako+ Fast"}, + {HPHW_NPROC,0x892,0x4,0x91,"Mt. Hamilton Slow Mako+?"}, {HPHW_NPROC,0x894,0x4,0x91,"Mt. Hamilton Fast Mako+"}, {HPHW_NPROC,0x895,0x4,0x91,"Storm Peak Slow Mako+"}, {HPHW_NPROC,0x896,0x4,0x91,"Storm Peak Fast Mako+"}, @@ -1204,6 +1210,8 @@ static struct hp_hardware hp_hardware_list[] = { {HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, {HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, {HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, + {HPHW_FIO, 0x076, 0x000AD, 0x0, "Crestone Peak Core RS-232"}, + {HPHW_FIO, 0x077, 0x000AD, 0x0, "Crestone Peak Fast? Core RS-232"}, {HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, {HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, {HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, @@ -1365,7 +1373,7 @@ const char *parisc_hardware_description(struct parisc_device_id *id) /* Interpret hversion (ret[0]) from PDC_MODEL(4)/PDC_MODEL_INFO(0) */ -enum cpu_type __cpuinit +enum cpu_type parisc_get_cpu_type(unsigned long hversion) { struct hp_cpu_type_mask *ptr; diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index 37aabd772fb..d4dc588c0dc 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -41,9 +41,7 @@ END(boot_args) .import fault_vector_11,code /* IVA parisc 1.1 32 bit */ .import $global$ /* forward declaration */ #endif /*!CONFIG_64BIT*/ - .export _stext,data /* Kernel want it this way! */ -_stext: -ENTRY(stext) +ENTRY(parisc_kernel_start) .proc .callinfo @@ -195,6 +193,8 @@ common_stext: ldw MEM_PDC_HI(%r0),%r6 depd %r6, 31, 32, %r3 /* move to upper word */ + mfctl %cr30,%r6 /* PCX-W2 firmware bug */ + ldo PDC_PSW(%r0),%arg0 /* 21 */ ldo PDC_PSW_SET_DEFAULTS(%r0),%arg1 /* 2 */ ldo PDC_PSW_WIDE_BIT(%r0),%arg2 /* 2 */ @@ -203,6 +203,8 @@ common_stext: copy %r0,%arg3 stext_pdc_ret: + mtctl %r6,%cr30 /* restore task thread info */ + /* restore rfi target address*/ ldd TI_TASK-THREAD_SZ_ALGN(%sp), %r10 tophys_r1 %r10 @@ -343,7 +345,7 @@ smp_slave_stext: .procend #endif /* CONFIG_SMP */ -ENDPROC(stext) +ENDPROC(parisc_kernel_start) #ifndef CONFIG_64BIT .section .data..read_mostly diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index 5595a2f3118..e158b6fbf1b 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -55,13 +55,13 @@ * IODC requires 7K byte stack. That leaves 1K byte for os_hpmc. */ - .align PAGE_SIZE + .align 4096 hpmc_stack: .block 16384 #define HPMC_IODC_BUF_SIZE 0x8000 - .align PAGE_SIZE + .align 4096 hpmc_iodc_buf: .block HPMC_IODC_BUF_SIZE diff --git a/arch/parisc/kernel/inventory.c b/arch/parisc/kernel/inventory.c index 3295ef4a185..f0b6722fc70 100644 --- a/arch/parisc/kernel/inventory.c +++ b/arch/parisc/kernel/inventory.c @@ -211,6 +211,7 @@ pat_query_module(ulong pcell_loc, ulong mod_index) /* REVISIT: who is the consumer of this? not sure yet... */ dev->mod_info = pa_pdc_cell->mod_info; /* pass to PAT_GET_ENTITY() */ dev->pmod_loc = pa_pdc_cell->mod_location; + dev->mod0 = pa_pdc_cell->mod[0]; register_parisc_device(dev); /* advertise device */ diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 8094d3ed3b6..cfe056fe7f5 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -27,11 +27,11 @@ #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/seq_file.h> -#include <linux/spinlock.h> #include <linux/types.h> #include <asm/io.h> #include <asm/smp.h> +#include <asm/ldcw.h> #undef PARISC_IRQ_CR16_COUNTS @@ -117,7 +117,7 @@ int cpu_check_affinity(struct irq_data *d, const struct cpumask *dest) return -EINVAL; /* whatever mask they set, we just allow one CPU */ - cpu_dest = first_cpu(*dest); + cpu_dest = cpumask_first_and(dest, cpu_online_mask); return cpu_dest; } @@ -152,6 +152,49 @@ static struct irq_chip cpu_interrupt_type = { .irq_retrigger = NULL, }; +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +#define irq_stats(x) (&per_cpu(irq_stat, x)) + +/* + * /proc/interrupts printing for arch specific interrupts + */ +int arch_show_interrupts(struct seq_file *p, int prec) +{ + int j; + +#ifdef CONFIG_DEBUG_STACKOVERFLOW + seq_printf(p, "%*s: ", prec, "STK"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->kernel_stack_usage); + seq_puts(p, " Kernel stack usage\n"); +# ifdef CONFIG_IRQSTACKS + seq_printf(p, "%*s: ", prec, "IST"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_stack_usage); + seq_puts(p, " Interrupt stack usage\n"); +# endif +#endif +#ifdef CONFIG_SMP + seq_printf(p, "%*s: ", prec, "RES"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count); + seq_puts(p, " Rescheduling interrupts\n"); +#endif + seq_printf(p, "%*s: ", prec, "UAH"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_unaligned_count); + seq_puts(p, " Unaligned access handler traps\n"); + seq_printf(p, "%*s: ", prec, "FPA"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_fpassist_count); + seq_puts(p, " Floating point assist traps\n"); + seq_printf(p, "%*s: ", prec, "TLB"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count); + seq_puts(p, " TLB shootdowns\n"); + return 0; +} + int show_interrupts(struct seq_file *p, void *v) { int i = *(loff_t *) v, j; @@ -219,6 +262,9 @@ int show_interrupts(struct seq_file *p, void *v) raw_spin_unlock_irqrestore(&desc->lock, flags); } + if (i == NR_IRQS) + arch_show_interrupts(p, 3); + return 0; } @@ -330,6 +376,131 @@ static inline int eirr_to_irq(unsigned long eirr) return (BITS_PER_LONG - bit) + TIMER_IRQ; } +#ifdef CONFIG_IRQSTACKS +/* + * IRQ STACK - used for irq handler + */ +#define IRQ_STACK_SIZE (4096 << 2) /* 16k irq stack size */ + +union irq_stack_union { + unsigned long stack[IRQ_STACK_SIZE/sizeof(unsigned long)]; + volatile unsigned int slock[4]; + volatile unsigned int lock[1]; +}; + +DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = { + .slock = { 1,1,1,1 }, + }; +#endif + + +int sysctl_panic_on_stackoverflow = 1; + +static inline void stack_overflow_check(struct pt_regs *regs) +{ +#ifdef CONFIG_DEBUG_STACKOVERFLOW + #define STACK_MARGIN (256*6) + + /* Our stack starts directly behind the thread_info struct. */ + unsigned long stack_start = (unsigned long) current_thread_info(); + unsigned long sp = regs->gr[30]; + unsigned long stack_usage; + unsigned int *last_usage; + int cpu = smp_processor_id(); + + /* if sr7 != 0, we interrupted a userspace process which we do not want + * to check for stack overflow. We will only check the kernel stack. */ + if (regs->sr[7]) + return; + + /* calculate kernel stack usage */ + stack_usage = sp - stack_start; +#ifdef CONFIG_IRQSTACKS + if (likely(stack_usage <= THREAD_SIZE)) + goto check_kernel_stack; /* found kernel stack */ + + /* check irq stack usage */ + stack_start = (unsigned long) &per_cpu(irq_stack_union, cpu).stack; + stack_usage = sp - stack_start; + + last_usage = &per_cpu(irq_stat.irq_stack_usage, cpu); + if (unlikely(stack_usage > *last_usage)) + *last_usage = stack_usage; + + if (likely(stack_usage < (IRQ_STACK_SIZE - STACK_MARGIN))) + return; + + pr_emerg("stackcheck: %s will most likely overflow irq stack " + "(sp:%lx, stk bottom-top:%lx-%lx)\n", + current->comm, sp, stack_start, stack_start + IRQ_STACK_SIZE); + goto panic_check; + +check_kernel_stack: +#endif + + /* check kernel stack usage */ + last_usage = &per_cpu(irq_stat.kernel_stack_usage, cpu); + + if (unlikely(stack_usage > *last_usage)) + *last_usage = stack_usage; + + if (likely(stack_usage < (THREAD_SIZE - STACK_MARGIN))) + return; + + pr_emerg("stackcheck: %s will most likely overflow kernel stack " + "(sp:%lx, stk bottom-top:%lx-%lx)\n", + current->comm, sp, stack_start, stack_start + THREAD_SIZE); + +#ifdef CONFIG_IRQSTACKS +panic_check: +#endif + if (sysctl_panic_on_stackoverflow) + panic("low stack detected by irq handler - check messages\n"); +#endif +} + +#ifdef CONFIG_IRQSTACKS +/* in entry.S: */ +void call_on_stack(unsigned long p1, void *func, unsigned long new_stack); + +static void execute_on_irq_stack(void *func, unsigned long param1) +{ + union irq_stack_union *union_ptr; + unsigned long irq_stack; + volatile unsigned int *irq_stack_in_use; + + union_ptr = &per_cpu(irq_stack_union, smp_processor_id()); + irq_stack = (unsigned long) &union_ptr->stack; + irq_stack = ALIGN(irq_stack + sizeof(irq_stack_union.slock), + 64); /* align for stack frame usage */ + + /* We may be called recursive. If we are already using the irq stack, + * just continue to use it. Use spinlocks to serialize + * the irq stack usage. + */ + irq_stack_in_use = (volatile unsigned int *)__ldcw_align(union_ptr); + if (!__ldcw(irq_stack_in_use)) { + void (*direct_call)(unsigned long p1) = func; + + /* We are using the IRQ stack already. + * Do direct call on current stack. */ + direct_call(param1); + return; + } + + /* This is where we switch to the IRQ stack. */ + call_on_stack(param1, func, irq_stack); + + /* free up irq stack usage. */ + *irq_stack_in_use = 1; +} + +void do_softirq_own_stack(void) +{ + execute_on_irq_stack(__do_softirq, 0); +} +#endif /* CONFIG_IRQSTACKS */ + /* ONLY called from entry.S:intr_extint() */ void do_cpu_irq_mask(struct pt_regs *regs) { @@ -364,7 +535,13 @@ void do_cpu_irq_mask(struct pt_regs *regs) goto set_out; } #endif + stack_overflow_check(regs); + +#ifdef CONFIG_IRQSTACKS + execute_on_irq_stack(&generic_handle_irq, irq); +#else generic_handle_irq(irq); +#endif /* CONFIG_IRQSTACKS */ out: irq_exit(); @@ -420,6 +597,4 @@ void __init init_IRQ(void) cpu_eiem = EIEM_MASK(TIMER_IRQ); #endif set_eiem(cpu_eiem); /* EIEM : enable all external intr */ - } - diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index 2a625fb063e..50dfafc3f2c 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -219,7 +219,7 @@ void *module_alloc(unsigned long size) * init_data correctly */ return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_HIGHMEM, - PAGE_KERNEL_RWX, -1, + PAGE_KERNEL_RWX, NUMA_NO_NODE, __builtin_return_address(0)); } diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S index 312b48422a5..b743a80eaba 100644 --- a/arch/parisc/kernel/pacache.S +++ b/arch/parisc/kernel/pacache.S @@ -563,6 +563,15 @@ ENDPROC(copy_page_asm) * %r23 physical page (shifted for tlb insert) of "from" translation */ + /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ + #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) + .macro convert_phys_for_tlb_insert20 phys + extrd,u \phys, 56-PAGE_ADD_SHIFT, 32-PAGE_ADD_SHIFT, \phys +#if _PAGE_SIZE_ENCODING_DEFAULT + depdi _PAGE_SIZE_ENCODING_DEFAULT, 63, (63-58), \phys +#endif + .endm + /* * We can't do this since copy_user_page is used to bring in * file data that might have instructions. Since the data would @@ -589,22 +598,21 @@ ENTRY(copy_user_page_asm) sub %r25, %r1, %r23 ldil L%(TMPALIAS_MAP_START), %r28 - /* FIXME for different page sizes != 4k */ #ifdef CONFIG_64BIT #if (TMPALIAS_MAP_START >= 0x80000000) depdi 0, 31,32, %r28 /* clear any sign extension */ #endif - extrd,u %r26,56,32, %r26 /* convert phys addr to tlb insert format */ - extrd,u %r23,56,32, %r23 /* convert phys addr to tlb insert format */ + convert_phys_for_tlb_insert20 %r26 /* convert phys addr to tlb insert format */ + convert_phys_for_tlb_insert20 %r23 /* convert phys addr to tlb insert format */ depd %r24,63,22, %r28 /* Form aliased virtual address 'to' */ - depdi 0, 63,12, %r28 /* Clear any offset bits */ + depdi 0, 63,PAGE_SHIFT, %r28 /* Clear any offset bits */ copy %r28, %r29 depdi 1, 41,1, %r29 /* Form aliased virtual address 'from' */ #else extrw,u %r26, 24,25, %r26 /* convert phys addr to tlb insert format */ extrw,u %r23, 24,25, %r23 /* convert phys addr to tlb insert format */ depw %r24, 31,22, %r28 /* Form aliased virtual address 'to' */ - depwi 0, 31,12, %r28 /* Clear any offset bits */ + depwi 0, 31,PAGE_SHIFT, %r28 /* Clear any offset bits */ copy %r28, %r29 depwi 1, 9,1, %r29 /* Form aliased virtual address 'from' */ #endif @@ -747,15 +755,14 @@ ENTRY(clear_user_page_asm) #ifdef CONFIG_64BIT #if (TMPALIAS_MAP_START >= 0x80000000) depdi 0, 31,32, %r28 /* clear any sign extension */ - /* FIXME: page size dependend */ #endif - extrd,u %r26, 56,32, %r26 /* convert phys addr to tlb insert format */ + convert_phys_for_tlb_insert20 %r26 /* convert phys addr to tlb insert format */ depd %r25, 63,22, %r28 /* Form aliased virtual address 'to' */ - depdi 0, 63,12, %r28 /* Clear any offset bits */ + depdi 0, 63,PAGE_SHIFT, %r28 /* Clear any offset bits */ #else extrw,u %r26, 24,25, %r26 /* convert phys addr to tlb insert format */ depw %r25, 31,22, %r28 /* Form aliased virtual address 'to' */ - depwi 0, 31,12, %r28 /* Clear any offset bits */ + depwi 0, 31,PAGE_SHIFT, %r28 /* Clear any offset bits */ #endif /* Purge any old translation */ @@ -832,15 +839,14 @@ ENTRY(flush_dcache_page_asm) #ifdef CONFIG_64BIT #if (TMPALIAS_MAP_START >= 0x80000000) depdi 0, 31,32, %r28 /* clear any sign extension */ - /* FIXME: page size dependend */ #endif - extrd,u %r26, 56,32, %r26 /* convert phys addr to tlb insert format */ + convert_phys_for_tlb_insert20 %r26 /* convert phys addr to tlb insert format */ depd %r25, 63,22, %r28 /* Form aliased virtual address 'to' */ - depdi 0, 63,12, %r28 /* Clear any offset bits */ + depdi 0, 63,PAGE_SHIFT, %r28 /* Clear any offset bits */ #else extrw,u %r26, 24,25, %r26 /* convert phys addr to tlb insert format */ depw %r25, 31,22, %r28 /* Form aliased virtual address 'to' */ - depwi 0, 31,12, %r28 /* Clear any offset bits */ + depwi 0, 31,PAGE_SHIFT, %r28 /* Clear any offset bits */ #endif /* Purge any old translation */ @@ -854,7 +860,7 @@ ENTRY(flush_dcache_page_asm) #endif ldil L%dcache_stride, %r1 - ldw R%dcache_stride(%r1), %r1 + ldw R%dcache_stride(%r1), r31 #ifdef CONFIG_64BIT depdi,z 1, 63-PAGE_SHIFT,1, %r25 @@ -862,26 +868,26 @@ ENTRY(flush_dcache_page_asm) depwi,z 1, 31-PAGE_SHIFT,1, %r25 #endif add %r28, %r25, %r25 - sub %r25, %r1, %r25 - - -1: fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) - fdc,m %r1(%r28) + sub %r25, r31, %r25 + + +1: fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) + fdc,m r31(%r28) cmpb,COND(<<) %r28, %r25,1b - fdc,m %r1(%r28) + fdc,m r31(%r28) sync @@ -909,15 +915,14 @@ ENTRY(flush_icache_page_asm) #ifdef CONFIG_64BIT #if (TMPALIAS_MAP_START >= 0x80000000) depdi 0, 31,32, %r28 /* clear any sign extension */ - /* FIXME: page size dependend */ #endif - extrd,u %r26, 56,32, %r26 /* convert phys addr to tlb insert format */ + convert_phys_for_tlb_insert20 %r26 /* convert phys addr to tlb insert format */ depd %r25, 63,22, %r28 /* Form aliased virtual address 'to' */ - depdi 0, 63,12, %r28 /* Clear any offset bits */ + depdi 0, 63,PAGE_SHIFT, %r28 /* Clear any offset bits */ #else extrw,u %r26, 24,25, %r26 /* convert phys addr to tlb insert format */ depw %r25, 31,22, %r28 /* Form aliased virtual address 'to' */ - depwi 0, 31,12, %r28 /* Clear any offset bits */ + depwi 0, 31,PAGE_SHIFT, %r28 /* Clear any offset bits */ #endif /* Purge any old translation */ @@ -931,7 +936,7 @@ ENTRY(flush_icache_page_asm) #endif ldil L%icache_stride, %r1 - ldw R%icache_stride(%r1), %r1 + ldw R%icache_stride(%r1), %r31 #ifdef CONFIG_64BIT depdi,z 1, 63-PAGE_SHIFT,1, %r25 @@ -939,28 +944,28 @@ ENTRY(flush_icache_page_asm) depwi,z 1, 31-PAGE_SHIFT,1, %r25 #endif add %r28, %r25, %r25 - sub %r25, %r1, %r25 + sub %r25, %r31, %r25 /* fic only has the type 26 form on PA1.1, requiring an * explicit space specification, so use %sr4 */ -1: fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - fic,m %r1(%sr4,%r28) - cmpb,COND(<<) %r28, %r25,1b - fic,m %r1(%sr4,%r28) +1: fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + fic,m %r31(%sr4,%r28) + cmpb,COND(<<) %r28, %r25,1b + fic,m %r31(%sr4,%r28) sync diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 6795dc6c995..568b2c61ea0 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -120,11 +120,13 @@ extern void __ashrdi3(void); extern void __ashldi3(void); extern void __lshrdi3(void); extern void __muldi3(void); +extern void __ucmpdi2(void); EXPORT_SYMBOL(__ashrdi3); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__lshrdi3); EXPORT_SYMBOL(__muldi3); +EXPORT_SYMBOL(__ucmpdi2); asmlinkage void * __canonicalize_funcptr_for_compare(void *); EXPORT_SYMBOL(__canonicalize_funcptr_for_compare); diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c index 60309051875..64f2764a8ce 100644 --- a/arch/parisc/kernel/pci.c +++ b/arch/parisc/kernel/pci.c @@ -220,6 +220,33 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, } +int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine) +{ + unsigned long prot; + + /* + * I/O space can be accessed via normal processor loads and stores on + * this platform but for now we elect not to do this and portable + * drivers should not do this anyway. + */ + if (mmap_state == pci_mmap_io) + return -EINVAL; + + if (write_combine) + return -EINVAL; + + /* + * Ignore write-combine; for now only return uncached mappings. + */ + prot = pgprot_val(vma->vm_page_prot); + prot |= _PAGE_NO_CACHE; + vma->vm_page_prot = __pgprot(prot); + + return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, vma->vm_page_prot); +} + /* * A driver is enabling the device. We make sure that all the appropriate * bits are set to allow the device to operate as the driver is expecting. diff --git a/arch/parisc/kernel/pdc_chassis.c b/arch/parisc/kernel/pdc_chassis.c index d47ba1aa825..3e04242de5a 100644 --- a/arch/parisc/kernel/pdc_chassis.c +++ b/arch/parisc/kernel/pdc_chassis.c @@ -30,11 +30,13 @@ #endif #include <linux/init.h> +#include <linux/module.h> #include <linux/kernel.h> #include <linux/reboot.h> #include <linux/notifier.h> #include <linux/cache.h> #include <linux/proc_fs.h> +#include <linux/seq_file.h> #include <asm/pdc_chassis.h> #include <asm/processor.h> @@ -244,38 +246,38 @@ int pdc_chassis_send_status(int message) #ifdef CONFIG_PDC_CHASSIS_WARN #ifdef CONFIG_PROC_FS -static int pdc_chassis_warn_pread(char *page, char **start, off_t off, - int count, int *eof, void *data) +static int pdc_chassis_warn_show(struct seq_file *m, void *v) { - char *out = page; - int len, ret; unsigned long warn; u32 warnreg; - ret = pdc_chassis_warn(&warn); - if (ret != PDC_OK) + if (pdc_chassis_warn(&warn) != PDC_OK) return -EIO; warnreg = (warn & 0xFFFFFFFF); if ((warnreg >> 24) & 0xFF) - out += sprintf(out, "Chassis component failure! (eg fan or PSU): 0x%.2x\n", ((warnreg >> 24) & 0xFF)); - - out += sprintf(out, "Battery: %s\n", (warnreg & 0x04) ? "Low!" : "OK"); - out += sprintf(out, "Temp low: %s\n", (warnreg & 0x02) ? "Exceeded!" : "OK"); - out += sprintf(out, "Temp mid: %s\n", (warnreg & 0x01) ? "Exceeded!" : "OK"); - - len = out - page - off; - if (len < count) { - *eof = 1; - if (len <= 0) return 0; - } else { - len = count; - } - *start = page + off; - return len; + seq_printf(m, "Chassis component failure! (eg fan or PSU): 0x%.2x\n", + (warnreg >> 24) & 0xFF); + + seq_printf(m, "Battery: %s\n", (warnreg & 0x04) ? "Low!" : "OK"); + seq_printf(m, "Temp low: %s\n", (warnreg & 0x02) ? "Exceeded!" : "OK"); + seq_printf(m, "Temp mid: %s\n", (warnreg & 0x01) ? "Exceeded!" : "OK"); + return 0; +} + +static int pdc_chassis_warn_open(struct inode *inode, struct file *file) +{ + return single_open(file, pdc_chassis_warn_show, NULL); } +static const struct file_operations pdc_chassis_warn_fops = { + .open = pdc_chassis_warn_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int __init pdc_chassis_create_procfs(void) { unsigned long test; @@ -290,8 +292,7 @@ static int __init pdc_chassis_create_procfs(void) printk(KERN_INFO "Enabling PDC chassis warnings support v%s\n", PDC_CHASSIS_VER); - create_proc_read_entry("chassis", 0400, NULL, pdc_chassis_warn_pread, - NULL); + proc_create("chassis", 0400, NULL, &pdc_chassis_warn_fops); return 0; } diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index d13507246c5..0bbbf0d3f60 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -13,7 +13,7 @@ * Copyright (C) 2000 Grant Grundler <grundler with parisc-linux.org> * Copyright (C) 2001 Alan Modra <amodra at parisc-linux.org> * Copyright (C) 2001-2002 Ryan Bradetich <rbrad at parisc-linux.org> - * Copyright (C) 2001-2007 Helge Deller <deller at parisc-linux.org> + * Copyright (C) 2001-2014 Helge Deller <deller@gmx.de> * Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org> * * @@ -49,6 +49,7 @@ #include <linux/kallsyms.h> #include <linux/uaccess.h> #include <linux/rcupdate.h> +#include <linux/random.h> #include <asm/io.h> #include <asm/asm-offsets.h> @@ -59,28 +60,6 @@ #include <asm/unwind.h> #include <asm/sections.h> -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) -{ - set_thread_flag(TIF_POLLING_NRFLAG); - - /* endless idle loop with no priority at all */ - while (1) { - rcu_idle_enter(); - while (!need_resched()) - barrier(); - rcu_idle_exit(); - schedule_preempt_disabled(); - check_pgt_cache(); - } -} - - #define COMMAND_GLOBAL F_EXTEND(0xfffe0030) #define CMD_RESET 5 /* reset any module */ @@ -308,3 +287,21 @@ void *dereference_function_descriptor(void *ptr) return ptr; } #endif + +static inline unsigned long brk_rnd(void) +{ + /* 8MB for 32bit, 1GB for 64bit */ + if (is_32bit_task()) + return (get_random_int() & 0x7ffUL) << PAGE_SHIFT; + else + return (get_random_int() & 0x3ffffUL) << PAGE_SHIFT; +} + +unsigned long arch_randomize_brk(struct mm_struct *mm) +{ + unsigned long ret = PAGE_ALIGN(mm->brk + brk_rnd()); + + if (ret < mm->brk) + return mm->brk; + return ret; +} diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index c8fb61ed32f..b68d977ce30 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -73,7 +73,7 @@ extern int update_cr16_clocksource(void); /* from time.c */ * * FIXME: doesn't do much yet... */ -static void __cpuinit +static void init_percpu_prof(unsigned long cpunum) { struct cpuinfo_parisc *p; @@ -92,7 +92,7 @@ init_percpu_prof(unsigned long cpunum) * (return 1). If so, initialize the chip and tell other partners in crime * they have work to do. */ -static int __cpuinit processor_probe(struct parisc_device *dev) +static int processor_probe(struct parisc_device *dev) { unsigned long txn_addr; unsigned long cpuid; @@ -299,7 +299,7 @@ void __init collect_boot_cpu_data(void) * * o Enable CPU profiling hooks. */ -int __cpuinit init_per_cpu(int cpunum) +int init_per_cpu(int cpunum) { int ret; struct pdc_coproc_cfg coproc_cfg; @@ -371,10 +371,23 @@ show_cpuinfo (struct seq_file *m, void *v) seq_printf(m, "capabilities\t:"); if (boot_cpu_data.pdc.capabilities & PDC_MODEL_OS32) - seq_printf(m, " os32"); + seq_puts(m, " os32"); if (boot_cpu_data.pdc.capabilities & PDC_MODEL_OS64) - seq_printf(m, " os64"); - seq_printf(m, "\n"); + seq_puts(m, " os64"); + if (boot_cpu_data.pdc.capabilities & PDC_MODEL_IOPDIR_FDC) + seq_puts(m, " iopdir_fdc"); + switch (boot_cpu_data.pdc.capabilities & PDC_MODEL_NVA_MASK) { + case PDC_MODEL_NVA_SUPPORTED: + seq_puts(m, " nva_supported"); + break; + case PDC_MODEL_NVA_SLOW: + seq_puts(m, " nva_slow"); + break; + case PDC_MODEL_NVA_UNSUPPORTED: + seq_puts(m, " needs_equivalent_aliasing"); + break; + } + seq_printf(m, " (0x%02lx)\n", boot_cpu_data.pdc.capabilities); seq_printf(m, "model\t\t: %s\n" "model name\t: %s\n", diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 534abd4936e..e842ee233db 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/compat.h> #include <linux/signal.h> +#include <linux/audit.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -267,11 +268,28 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { + long ret = 0; + if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) - return -1L; - - return regs->gr[20]; + ret = -1L; + +#ifdef CONFIG_64BIT + if (!is_compat_task()) + audit_syscall_entry(AUDIT_ARCH_PARISC64, + regs->gr[20], + regs->gr[26], regs->gr[25], + regs->gr[24], regs->gr[23]); + else +#endif + audit_syscall_entry(AUDIT_ARCH_PARISC, + regs->gr[20] & 0xffffffff, + regs->gr[26] & 0xffffffff, + regs->gr[25] & 0xffffffff, + regs->gr[24] & 0xffffffff, + regs->gr[23] & 0xffffffff); + + return ret ? : regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) @@ -279,6 +297,8 @@ void do_syscall_trace_exit(struct pt_regs *regs) int stepping = test_thread_flag(TIF_SINGLESTEP) || test_thread_flag(TIF_BLOCKSTEP); + audit_syscall_exit(regs); + if (stepping || test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, stepping); } diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c index a3328c2616b..72a3c658ad7 100644 --- a/arch/parisc/kernel/setup.c +++ b/arch/parisc/kernel/setup.c @@ -69,7 +69,8 @@ void __init setup_cmdline(char **cmdline_p) /* called from hpux boot loader */ boot_command_line[0] = '\0'; } else { - strcpy(boot_command_line, (char *)__va(boot_args[1])); + strlcpy(boot_command_line, (char *)__va(boot_args[1]), + COMMAND_LINE_SIZE); #ifdef CONFIG_BLK_DEV_INITRD if (boot_args[2] != 0) /* did palo pass us a ramdisk? */ @@ -129,6 +130,8 @@ void __init setup_arch(char **cmdline_p) printk(KERN_INFO "The 32-bit Kernel has started...\n"); #endif + printk(KERN_INFO "Default page size is %dKB.\n", (int)(PAGE_SIZE / 1024)); + pdc_console_init(); #ifdef CONFIG_64BIT @@ -153,7 +156,7 @@ void __init setup_arch(char **cmdline_p) #endif #if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; /* we use take_over_console() later ! */ + conswitchp = &dummy_con; /* we use do_take_over_console() later ! */ #endif } @@ -315,8 +318,12 @@ static int __init parisc_init(void) pdc_stable_write(0x40, &osid, sizeof(osid)); processor_init(); - printk(KERN_INFO "CPU(s): %d x %s at %d.%06d MHz\n", - num_present_cpus(), +#ifdef CONFIG_SMP + pr_info("CPU(s): %d out of %d %s at %d.%06d MHz online\n", + num_online_cpus(), num_present_cpus(), +#else + pr_info("CPU(s): 1 x %s at %d.%06d MHz\n", +#endif boot_cpu_data.cpu_name, boot_cpu_data.cpu_hz / 1000000, boot_cpu_data.cpu_hz % 1000000 ); diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 940188d1942..1cba8f29bb4 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -56,13 +56,6 @@ #define A(__x) ((unsigned long)(__x)) /* - * Atomically swap in the new signal mask, and wait for a signal. - */ -#ifdef CONFIG_64BIT -#include "sys32.h" -#endif - -/* * Do a signal return - restore sigcontext. */ @@ -85,7 +78,7 @@ restore_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs) err |= __copy_from_user(regs->iaoq, sc->sc_iaoq, sizeof(regs->iaoq)); err |= __copy_from_user(regs->iasq, sc->sc_iasq, sizeof(regs->iasq)); err |= __get_user(regs->sar, &sc->sc_sar); - DBG(2,"restore_sigcontext: iaoq is 0x%#lx / 0x%#lx\n", + DBG(2,"restore_sigcontext: iaoq is %#lx / %#lx\n", regs->iaoq[0],regs->iaoq[1]); DBG(2,"restore_sigcontext: r28 is %ld\n", regs->gr[28]); return err; diff --git a/arch/parisc/kernel/signal32.c b/arch/parisc/kernel/signal32.c index 33eca1b0492..984abbee71c 100644 --- a/arch/parisc/kernel/signal32.c +++ b/arch/parisc/kernel/signal32.c @@ -34,7 +34,6 @@ #include <asm/uaccess.h> #include "signal32.h" -#include "sys32.h" #define DEBUG_COMPAT_SIG 0 #define DEBUG_COMPAT_SIG_LEVEL 2 @@ -320,7 +319,7 @@ copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from) } int -copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from) +copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from) { compat_uptr_t addr; compat_int_t val; diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h index 72ab41a51f3..af51d4ccee4 100644 --- a/arch/parisc/kernel/signal32.h +++ b/arch/parisc/kernel/signal32.h @@ -34,7 +34,7 @@ struct compat_ucontext { /* ELF32 signal handling */ -int copy_siginfo_to_user32 (compat_siginfo_t __user *to, siginfo_t *from); +int copy_siginfo_to_user32 (compat_siginfo_t __user *to, const siginfo_t *from); int copy_siginfo_from_user32 (siginfo_t *to, compat_siginfo_t __user *from); /* In a deft move of uber-hackery, we decide to carry the top half of all diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 6266730efd6..ceda229ea6c 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -62,9 +62,9 @@ static int smp_debug_lvl = 0; volatile struct task_struct *smp_init_current_idle_task; /* track which CPU is booting */ -static volatile int cpu_now_booting __cpuinitdata; +static volatile int cpu_now_booting; -static int parisc_max_cpus __cpuinitdata = 1; +static int parisc_max_cpus = 1; static DEFINE_PER_CPU(spinlock_t, ipi_lock); @@ -72,7 +72,6 @@ enum ipi_message_type { IPI_NOP=0, IPI_RESCHEDULE=1, IPI_CALL_FUNC, - IPI_CALL_FUNC_SINGLE, IPI_CPU_START, IPI_CPU_STOP, IPI_CPU_TEST @@ -126,11 +125,6 @@ ipi_interrupt(int irq, void *dev_id) unsigned long ops; unsigned long flags; - /* Count this now; we may make a call that never returns. */ - p->ipi_count++; - - mb(); /* Order interrupt and bit testing. */ - for (;;) { spinlock_t *lock = &per_cpu(ipi_lock, this_cpu); spin_lock_irqsave(lock, flags); @@ -155,6 +149,7 @@ ipi_interrupt(int irq, void *dev_id) case IPI_RESCHEDULE: smp_debug(100, KERN_DEBUG "CPU%d IPI_RESCHEDULE\n", this_cpu); + inc_irq_stat(irq_resched_count); scheduler_ipi(); break; @@ -163,11 +158,6 @@ ipi_interrupt(int irq, void *dev_id) generic_smp_call_function_interrupt(); break; - case IPI_CALL_FUNC_SINGLE: - smp_debug(100, KERN_DEBUG "CPU%d IPI_CALL_FUNC_SINGLE\n", this_cpu); - generic_smp_call_function_single_interrupt(); - break; - case IPI_CPU_START: smp_debug(100, KERN_DEBUG "CPU%d IPI_CPU_START\n", this_cpu); break; @@ -259,18 +249,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask) void arch_send_call_function_single_ipi(int cpu) { - send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE); -} - -/* - * Flush all other CPU's tlb and then mine. Do this with on_each_cpu() - * as we want to ensure all TLB's flushed before proceeding. - */ - -void -smp_flush_tlb_all(void) -{ - on_each_cpu(flush_tlb_all_local, NULL, 1); + send_IPI_single(cpu, IPI_CALL_FUNC); } /* @@ -329,7 +308,7 @@ void __init smp_callin(void) local_irq_enable(); /* Interrupts have been off until now */ - cpu_idle(); /* Wait for timer to schedule some work */ + cpu_startup_entry(CPUHP_ONLINE); /* NOTREACHED */ panic("smp_callin() AAAAaaaaahhhh....\n"); @@ -338,7 +317,7 @@ void __init smp_callin(void) /* * Bring one cpu online. */ -int __cpuinit smp_boot_one_cpu(int cpuid, struct task_struct *idle) +int smp_boot_one_cpu(int cpuid, struct task_struct *idle) { const struct cpuinfo_parisc *p = &per_cpu(cpu_data, cpuid); long timeout; @@ -434,7 +413,7 @@ void smp_cpus_done(unsigned int cpu_max) } -int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) +int __cpu_up(unsigned int cpu, struct task_struct *tidle) { if (cpu != 0 && cpu < parisc_max_cpus) smp_boot_one_cpu(cpu, tidle); diff --git a/arch/parisc/kernel/sys32.h b/arch/parisc/kernel/sys32.h deleted file mode 100644 index 60dd470f39f..00000000000 --- a/arch/parisc/kernel/sys32.h +++ /dev/null @@ -1,36 +0,0 @@ -/* - * Copyright (C) 2002 Richard Hirst <rhirst at parisc-linux.org> - * Copyright (C) 2003 James Bottomley <jejb at parisc-linux.org> - * Copyright (C) 2003 Randolph Chung <tausq with parisc-linux.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ -#ifndef _PARISC64_KERNEL_SYS32_H -#define _PARISC64_KERNEL_SYS32_H - -#include <linux/compat.h> - -/* Call a kernel syscall which will use kernel space instead of user - * space for its copy_to/from_user. - */ -#define KERNEL_SYSCALL(ret, syscall, args...) \ -{ \ - mm_segment_t old_fs = get_fs(); \ - set_fs(KERNEL_DS); \ - ret = syscall(args); \ - set_fs (old_fs); \ -} - -#endif diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 5dfd248e3f1..e1ffea2f9a0 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -5,6 +5,7 @@ * Copyright (C) 1999-2003 Matthew Wilcox <willy at parisc-linux.org> * Copyright (C) 2000-2003 Paul Bame <bame at parisc-linux.org> * Copyright (C) 2001 Thomas Bogendoerfer <tsbogend at parisc-linux.org> + * Copyright (C) 1999-2014 Helge Deller <deller@gmx.de> * * * This program is free software; you can redistribute it and/or modify @@ -23,6 +24,7 @@ */ #include <asm/uaccess.h> +#include <asm/elf.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/linkage.h> @@ -32,73 +34,230 @@ #include <linux/syscalls.h> #include <linux/utsname.h> #include <linux/personality.h> +#include <linux/random.h> -static unsigned long get_unshared_area(unsigned long addr, unsigned long len) +/* we construct an artificial offset for the mapping based on the physical + * address of the kernel mapping variable */ +#define GET_LAST_MMAP(filp) \ + (filp ? ((unsigned long) filp->f_mapping) >> 8 : 0UL) +#define SET_LAST_MMAP(filp, val) \ + { /* nothing */ } + +static int get_offset(unsigned int last_mmap) { - struct vm_unmapped_area_info info; + return (last_mmap & (SHM_COLOUR-1)) >> PAGE_SHIFT; +} - info.flags = 0; - info.length = len; - info.low_limit = PAGE_ALIGN(addr); - info.high_limit = TASK_SIZE; - info.align_mask = 0; - info.align_offset = 0; - return vm_unmapped_area(&info); +static unsigned long shared_align_offset(unsigned int last_mmap, + unsigned long pgoff) +{ + return (get_offset(last_mmap) + pgoff) << PAGE_SHIFT; +} + +static inline unsigned long COLOR_ALIGN(unsigned long addr, + unsigned int last_mmap, unsigned long pgoff) +{ + unsigned long base = (addr+SHM_COLOUR-1) & ~(SHM_COLOUR-1); + unsigned long off = (SHM_COLOUR-1) & + (shared_align_offset(last_mmap, pgoff) << PAGE_SHIFT); + + return base + off; } /* - * We need to know the offset to use. Old scheme was to look for - * existing mapping and use the same offset. New scheme is to use the - * address of the kernel data structure as the seed for the offset. - * We'll see how that works... - * - * The mapping is cacheline aligned, so there's no information in the bottom - * few bits of the address. We're looking for 10 bits (4MB / 4k), so let's - * drop the bottom 8 bits and use bits 8-17. + * Top of mmap area (just below the process stack). */ -static int get_offset(struct address_space *mapping) + +static unsigned long mmap_upper_limit(void) { - return (unsigned long) mapping >> 8; + unsigned long stack_base; + + /* Limit stack size - see setup_arg_pages() in fs/exec.c */ + stack_base = rlimit_max(RLIMIT_STACK); + if (stack_base > STACK_SIZE_MAX) + stack_base = STACK_SIZE_MAX; + + return PAGE_ALIGN(STACK_TOP - stack_base); } -static unsigned long get_shared_area(struct address_space *mapping, - unsigned long addr, unsigned long len, unsigned long pgoff) + +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) { + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long task_size = TASK_SIZE; + int do_color_align, last_mmap; struct vm_unmapped_area_info info; + if (len > task_size) + return -ENOMEM; + + do_color_align = 0; + if (filp || (flags & MAP_SHARED)) + do_color_align = 1; + last_mmap = GET_LAST_MMAP(filp); + + if (flags & MAP_FIXED) { + if ((flags & MAP_SHARED) && last_mmap && + (addr - shared_align_offset(last_mmap, pgoff)) + & (SHM_COLOUR - 1)) + return -EINVAL; + goto found_addr; + } + + if (addr) { + if (do_color_align && last_mmap) + addr = COLOR_ALIGN(addr, last_mmap, pgoff); + else + addr = PAGE_ALIGN(addr); + + vma = find_vma(mm, addr); + if (task_size - len >= addr && + (!vma || addr + len <= vma->vm_start)) + goto found_addr; + } + info.flags = 0; info.length = len; - info.low_limit = PAGE_ALIGN(addr); - info.high_limit = TASK_SIZE; - info.align_mask = PAGE_MASK & (SHMLBA - 1); - info.align_offset = (get_offset(mapping) + pgoff) << PAGE_SHIFT; - return vm_unmapped_area(&info); + info.low_limit = mm->mmap_legacy_base; + info.high_limit = mmap_upper_limit(); + info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; + info.align_offset = shared_align_offset(last_mmap, pgoff); + addr = vm_unmapped_area(&info); + +found_addr: + if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) + SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); + + return addr; } -unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, - unsigned long len, unsigned long pgoff, unsigned long flags) +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, + const unsigned long len, const unsigned long pgoff, + const unsigned long flags) { + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + unsigned long addr = addr0; + int do_color_align, last_mmap; + struct vm_unmapped_area_info info; + +#ifdef CONFIG_64BIT + /* This should only ever run for 32-bit processes. */ + BUG_ON(!test_thread_flag(TIF_32BIT)); +#endif + + /* requested length too big for entire address space */ if (len > TASK_SIZE) return -ENOMEM; + + do_color_align = 0; + if (filp || (flags & MAP_SHARED)) + do_color_align = 1; + last_mmap = GET_LAST_MMAP(filp); + if (flags & MAP_FIXED) { - if ((flags & MAP_SHARED) && - (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)) + if ((flags & MAP_SHARED) && last_mmap && + (addr - shared_align_offset(last_mmap, pgoff)) + & (SHM_COLOUR - 1)) return -EINVAL; - return addr; + goto found_addr; } - if (!addr) - addr = TASK_UNMAPPED_BASE; - if (filp) { - addr = get_shared_area(filp->f_mapping, addr, len, pgoff); - } else if(flags & MAP_SHARED) { - addr = get_shared_area(NULL, addr, len, pgoff); - } else { - addr = get_unshared_area(addr, len); + /* requesting a specific address */ + if (addr) { + if (do_color_align && last_mmap) + addr = COLOR_ALIGN(addr, last_mmap, pgoff); + else + addr = PAGE_ALIGN(addr); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && + (!vma || addr + len <= vma->vm_start)) + goto found_addr; } + + info.flags = VM_UNMAPPED_AREA_TOPDOWN; + info.length = len; + info.low_limit = PAGE_SIZE; + info.high_limit = mm->mmap_base; + info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0; + info.align_offset = shared_align_offset(last_mmap, pgoff); + addr = vm_unmapped_area(&info); + if (!(addr & ~PAGE_MASK)) + goto found_addr; + VM_BUG_ON(addr != -ENOMEM); + + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + return arch_get_unmapped_area(filp, addr0, len, pgoff, flags); + +found_addr: + if (do_color_align && !last_mmap && !(addr & ~PAGE_MASK)) + SET_LAST_MMAP(filp, addr - (pgoff << PAGE_SHIFT)); + return addr; } +static int mmap_is_legacy(void) +{ + if (current->personality & ADDR_COMPAT_LAYOUT) + return 1; + + /* parisc stack always grows up - so a unlimited stack should + * not be an indicator to use the legacy memory layout. + * if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) + * return 1; + */ + + return sysctl_legacy_va_layout; +} + +static unsigned long mmap_rnd(void) +{ + unsigned long rnd = 0; + + /* + * 8 bits of randomness in 32bit mmaps, 20 address space bits + * 28 bits of randomness in 64bit mmaps, 40 address space bits + */ + if (current->flags & PF_RANDOMIZE) { + if (is_32bit_task()) + rnd = get_random_int() % (1<<8); + else + rnd = get_random_int() % (1<<28); + } + return rnd << PAGE_SHIFT; +} + +static unsigned long mmap_legacy_base(void) +{ + return TASK_UNMAPPED_BASE + mmap_rnd(); +} + +/* + * This function, called very early during the creation of a new + * process VM image, sets up which VM layout function to use: + */ +void arch_pick_mmap_layout(struct mm_struct *mm) +{ + mm->mmap_legacy_base = mmap_legacy_base(); + mm->mmap_base = mmap_upper_limit(); + + if (mmap_is_legacy()) { + mm->mmap_base = mm->mmap_legacy_base; + mm->get_unmapped_area = arch_get_unmapped_area; + } else { + mm->get_unmapped_area = arch_get_unmapped_area_topdown; + } +} + + asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff) diff --git a/arch/parisc/kernel/sys_parisc32.c b/arch/parisc/kernel/sys_parisc32.c index 051c8b90231..93c1963d76f 100644 --- a/arch/parisc/kernel/sys_parisc32.c +++ b/arch/parisc/kernel/sys_parisc32.c @@ -4,6 +4,7 @@ * Copyright (C) 2000-2001 Hewlett Packard Company * Copyright (C) 2000 John Marvin * Copyright (C) 2001 Matthew Wilcox + * Copyright (C) 2014 Helge Deller <deller@gmx.de> * * These routines maintain argument size conversion between 32bit and 64bit * environment. Based heavily on sys_ia32.c and sys_sparc32.c. @@ -11,46 +12,8 @@ #include <linux/compat.h> #include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/file.h> -#include <linux/signal.h> -#include <linux/resource.h> -#include <linux/times.h> -#include <linux/time.h> -#include <linux/smp.h> -#include <linux/sem.h> -#include <linux/shm.h> -#include <linux/slab.h> -#include <linux/uio.h> -#include <linux/ncp_fs.h> -#include <linux/poll.h> -#include <linux/personality.h> -#include <linux/stat.h> -#include <linux/highmem.h> -#include <linux/highuid.h> -#include <linux/mman.h> -#include <linux/binfmts.h> -#include <linux/namei.h> -#include <linux/vfs.h> -#include <linux/ptrace.h> -#include <linux/swap.h> #include <linux/syscalls.h> -#include <asm/types.h> -#include <asm/uaccess.h> -#include <asm/mmu_context.h> - -#include "sys32.h" - -#undef DEBUG - -#ifdef DEBUG -#define DBG(x) printk x -#else -#define DBG(x) -#endif asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23, int r22, int r21, int r20) @@ -60,51 +23,11 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23, return -ENOSYS; } -/* Note: it is necessary to treat out_fd and in_fd as unsigned ints, with the - * corresponding cast to a signed int to insure that the proper conversion - * (sign extension) between the register representation of a signed int (msr in - * 32-bit mode) and the register representation of a signed int (msr in 64-bit - * mode) is performed. - */ -asmlinkage long sys32_sendfile(u32 out_fd, u32 in_fd, - compat_off_t __user *offset, compat_size_t count) -{ - return compat_sys_sendfile((int)out_fd, (int)in_fd, offset, count); -} - -asmlinkage long sys32_sendfile64(u32 out_fd, u32 in_fd, - compat_loff_t __user *offset, compat_size_t count) -{ - return sys_sendfile64((int)out_fd, (int)in_fd, - (loff_t __user *)offset, count); -} - -asmlinkage long sys32_semctl(int semid, int semnum, int cmd, union semun arg) -{ - union semun u; - - if (cmd == SETVAL) { - /* Ugh. arg is a union of int,ptr,ptr,ptr, so is 8 bytes. - * The int should be in the first 4, but our argument - * frobbing has left it in the last 4. - */ - u.val = *((int *)&arg + 1); - return sys_semctl (semid, semnum, cmd, u); - } - return sys_semctl (semid, semnum, cmd, arg); -} - -long sys32_lookup_dcookie(u32 cookie_high, u32 cookie_low, char __user *buf, - size_t len) -{ - return sys_lookup_dcookie((u64)cookie_high << 32 | cookie_low, - buf, len); -} - -asmlinkage long compat_sys_fanotify_mark(int fan_fd, int flags, u32 mask_hi, - u32 mask_lo, int fd, - const char __user *pathname) +asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags, + compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd, + const char __user * pathname) { - return sys_fanotify_mark(fan_fd, flags, ((u64)mask_hi << 32) | mask_lo, - fd, pathname); + return sys_fanotify_mark(fanotify_fd, flags, + ((__u64)mask1 << 32) | mask0, + dfd, pathname); } diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 5e055240f00..83878601103 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -1,12 +1,35 @@ /* * Linux/PA-RISC Project (http://www.parisc-linux.org/) * - * System call entry code Copyright (c) Matthew Wilcox 1999 <willy@bofh.ai> + * System call entry code / Linux gateway page + * Copyright (c) Matthew Wilcox 1999 <willy@bofh.ai> * Licensed under the GNU GPL. * thanks to Philipp Rumpf, Mike Shaver and various others * sorry about the wall, puffin.. */ +/* +How does the Linux gateway page on PA-RISC work? +------------------------------------------------ +The Linux gateway page on PA-RISC is "special". +It actually has PAGE_GATEWAY bits set (this is linux terminology; in parisc +terminology it's Execute, promote to PL0) in the page map. So anything +executing on this page executes with kernel level privilege (there's more to it +than that: to have this happen, you also have to use a branch with a ,gate +completer to activate the privilege promotion). The upshot is that everything +that runs on the gateway page runs at kernel privilege but with the current +user process address space (although you have access to kernel space via %sr2). +For the 0x100 syscall entry, we redo the space registers to point to the kernel +address space (preserving the user address space in %sr3), move to wide mode if +required, save the user registers and branch into the kernel syscall entry +point. For all the other functions, we execute at kernel privilege but don't +flip address spaces. The basic upshot of this is that these code snippets are +executed atomically (because the kernel can't be pre-empted) and they may +perform architecturally forbidden (to PL3) operations (like setting control +registers). +*/ + + #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/errno.h> @@ -15,6 +38,7 @@ #include <asm/thread_info.h> #include <asm/assembly.h> #include <asm/processor.h> +#include <asm/cache.h> #include <linux/linkage.h> @@ -565,10 +589,13 @@ cas_nocontend: # endif /* ENABLE_LWS_DEBUG */ + rsm PSW_SM_I, %r0 /* Disable interrupts */ + /* COW breaks can cause contention on UP systems */ LDCW 0(%sr2,%r20), %r28 /* Try to acquire the lock */ cmpb,<>,n %r0, %r28, cas_action /* Did we get it? */ cas_wouldblock: ldo 2(%r0), %r28 /* 2nd case */ + ssm PSW_SM_I, %r0 b lws_exit /* Contended... */ ldo -EAGAIN(%r0), %r21 /* Spin in userspace */ @@ -595,15 +622,17 @@ cas_action: stw %r1, 4(%sr2,%r20) #endif /* The load and store could fail */ -1: ldw 0(%sr3,%r26), %r28 +1: ldw,ma 0(%sr3,%r26), %r28 sub,<> %r28, %r25, %r0 -2: stw %r24, 0(%sr3,%r26) +2: stw,ma %r24, 0(%sr3,%r26) /* Free lock */ - stw %r20, 0(%sr2,%r20) + stw,ma %r20, 0(%sr2,%r20) #if ENABLE_LWS_DEBUG /* Clear thread register indicator */ stw %r0, 4(%sr2,%r20) #endif + /* Enable interrupts */ + ssm PSW_SM_I, %r0 /* Return to userspace, set no error */ b lws_exit copy %r0, %r21 @@ -615,6 +644,7 @@ cas_action: #if ENABLE_LWS_DEBUG stw %r0, 4(%sr2,%r20) #endif + ssm PSW_SM_I, %r0 b lws_exit ldo -EFAULT(%r0),%r21 /* set errno */ nop @@ -625,10 +655,8 @@ cas_action: /* Two exception table entries, one for the load, the other for the store. Either return -EFAULT. Each of the entries must be relocated. */ - .section __ex_table,"aw" - ASM_ULONG_INSN (1b - linux_gateway_page), (3b - linux_gateway_page) - ASM_ULONG_INSN (2b - linux_gateway_page), (3b - linux_gateway_page) - .previous + ASM_EXCEPTIONTABLE_ENTRY(1b-linux_gateway_page, 3b-linux_gateway_page) + ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page) /* Make sure nothing else is placed on this page */ @@ -643,7 +671,7 @@ ENTRY(end_linux_gateway_page) .section .rodata,"a" - .align PAGE_SIZE + .align 8 /* Light-weight-syscall table */ /* Start of lws table. */ ENTRY(lws_table) @@ -652,13 +680,13 @@ ENTRY(lws_table) END(lws_table) /* End of lws table */ - .align PAGE_SIZE + .align 8 ENTRY(sys_call_table) #include "syscall_table.S" END(sys_call_table) #ifdef CONFIG_64BIT - .align PAGE_SIZE + .align 8 ENTRY(sys_call_table64) #define SYSCALL_TABLE_64BIT #include "syscall_table.S" @@ -674,7 +702,7 @@ END(sys_call_table64) with ldcw. */ .section .data - .align PAGE_SIZE + .align L1_CACHE_BYTES ENTRY(lws_lock_start) /* lws locks */ .rept 16 diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S index f57dc137b8d..84c5d3a58fa 100644 --- a/arch/parisc/kernel/syscall_table.S +++ b/arch/parisc/kernel/syscall_table.S @@ -198,7 +198,7 @@ ENTRY_SAME(madvise) ENTRY_SAME(clone_wrapper) /* 120 */ ENTRY_SAME(setdomainname) - ENTRY_DIFF(sendfile) + ENTRY_COMP(sendfile) /* struct sockaddr... */ ENTRY_SAME(recvfrom) /* struct timex contains longs */ @@ -282,7 +282,7 @@ ENTRY_COMP(recvmsg) ENTRY_SAME(semop) /* 185 */ ENTRY_SAME(semget) - ENTRY_DIFF(semctl) + ENTRY_COMP(semctl) ENTRY_COMP(msgsnd) ENTRY_COMP(msgrcv) ENTRY_SAME(msgget) /* 190 */ @@ -304,7 +304,7 @@ ENTRY_SAME(gettid) ENTRY_OURS(readahead) ENTRY_SAME(tkill) - ENTRY_DIFF(sendfile64) + ENTRY_COMP(sendfile64) ENTRY_COMP(futex) /* 210 */ ENTRY_COMP(sched_setaffinity) ENTRY_COMP(sched_getaffinity) @@ -318,7 +318,7 @@ ENTRY_SAME(alloc_hugepages) /* 220 */ ENTRY_SAME(free_hugepages) ENTRY_SAME(exit_group) - ENTRY_DIFF(lookup_dcookie) + ENTRY_COMP(lookup_dcookie) ENTRY_SAME(epoll_create) ENTRY_SAME(epoll_ctl) /* 225 */ ENTRY_SAME(epoll_wait) @@ -392,7 +392,7 @@ ENTRY_COMP(vmsplice) ENTRY_COMP(move_pages) /* 295 */ ENTRY_SAME(getcpu) - ENTRY_SAME(epoll_pwait) + ENTRY_COMP(epoll_pwait) ENTRY_COMP(statfs64) ENTRY_COMP(fstatfs64) ENTRY_COMP(kexec_load) /* 300 */ @@ -418,7 +418,7 @@ ENTRY_SAME(accept4) /* 320 */ ENTRY_SAME(prlimit64) ENTRY_SAME(fanotify_init) - ENTRY_COMP(fanotify_mark) + ENTRY_DIFF(fanotify_mark) ENTRY_COMP(clock_adjtime) ENTRY_SAME(name_to_handle_at) /* 325 */ ENTRY_COMP(open_by_handle_at) @@ -429,6 +429,10 @@ ENTRY_COMP(process_vm_writev) ENTRY_SAME(kcmp) ENTRY_SAME(finit_module) + ENTRY_SAME(sched_setattr) + ENTRY_SAME(sched_getattr) /* 335 */ + ENTRY_COMP(utimes) + ENTRY_SAME(renameat2) /* Nothing yet */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index aeb8f8f2c07..47ee620d15d 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -25,6 +25,7 @@ #include <linux/interrupt.h> #include <linux/console.h> #include <linux/bug.h> +#include <linux/ratelimit.h> #include <asm/assembly.h> #include <asm/uaccess.h> @@ -42,9 +43,6 @@ #include "../math-emu/math-emu.h" /* for handle_fpe() */ -#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */ - /* dumped to the console via printk) */ - #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) DEFINE_SPINLOCK(pa_dbit_lock); #endif @@ -126,6 +124,8 @@ void show_regs(struct pt_regs *regs) user = user_mode(regs); level = user ? KERN_DEBUG : KERN_CRIT; + show_regs_print_info(level); + print_gr(level, regs); for (i = 0; i < 8; i += 4) @@ -158,13 +158,16 @@ void show_regs(struct pt_regs *regs) } } +static DEFINE_RATELIMIT_STATE(_hppa_rs, + DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); -void dump_stack(void) -{ - show_stack(NULL, NULL); +#define parisc_printk_ratelimited(critical, regs, fmt, ...) { \ + if ((critical || show_unhandled_signals) && __ratelimit(&_hppa_rs)) { \ + printk(fmt, ##__VA_ARGS__); \ + show_regs(regs); \ + } \ } -EXPORT_SYMBOL(dump_stack); static void do_show_stack(struct unwind_frame_info *info) { @@ -235,12 +238,10 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) if (err == 0) return; /* STFU */ - printk(KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n", + parisc_printk_ratelimited(1, regs, + KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n", current->comm, task_pid_nr(current), str, err, regs->iaoq[0]); -#ifdef PRINT_USER_FAULTS - /* XXX for debugging only */ - show_regs(regs); -#endif + return; } @@ -297,11 +298,6 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) do_exit(SIGSEGV); } -int syscall_ipi(int (*syscall) (struct pt_regs *), struct pt_regs *regs) -{ - return syscall(regs); -} - /* gdb uses break 4,8 */ #define GDB_BREAK_INSN 0x10004 static void handle_gdb_break(struct pt_regs *regs, int wot) @@ -332,14 +328,11 @@ static void handle_break(struct pt_regs *regs) (tt == BUG_TRAP_TYPE_NONE) ? 9 : 0); } -#ifdef PRINT_USER_FAULTS - if (unlikely(iir != GDB_BREAK_INSN)) { - printk(KERN_DEBUG "break %d,%d: pid=%d command='%s'\n", + if (unlikely(iir != GDB_BREAK_INSN)) + parisc_printk_ratelimited(0, regs, + KERN_DEBUG "break %d,%d: pid=%d command='%s'\n", iir & 31, (iir>>13) & ((1<<13)-1), task_pid_nr(current), current->comm); - show_regs(regs); - } -#endif /* send standard GDB signal */ handle_gdb_break(regs, TRAP_BRKPT); @@ -528,10 +521,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs) */ if (((unsigned long)regs->iaoq[0] & 3) && ((unsigned long)regs->iasq[0] != (unsigned long)regs->sr[7])) { - /* Kill the user process later */ - regs->iaoq[0] = 0 | 3; + /* Kill the user process later */ + regs->iaoq[0] = 0 | 3; regs->iaoq[1] = regs->iaoq[0] + 4; - regs->iasq[0] = regs->iasq[1] = regs->sr[7]; + regs->iasq[0] = regs->iasq[1] = regs->sr[7]; regs->gr[0] &= ~PSW_B; return; } @@ -547,8 +540,8 @@ void notrace handle_interruption(int code, struct pt_regs *regs) /* set up a new led state on systems shipped with a LED State panel */ pdc_chassis_send_status(PDC_CHASSIS_DIRECT_HPMC); - - parisc_terminate("High Priority Machine Check (HPMC)", + + parisc_terminate("High Priority Machine Check (HPMC)", regs, code, 0); /* NOT REACHED */ @@ -590,13 +583,13 @@ void notrace handle_interruption(int code, struct pt_regs *regs) /* Break instruction trap */ handle_break(regs); return; - + case 10: /* Privileged operation trap */ die_if_kernel("Privileged operation", regs, code); si.si_code = ILL_PRVOPC; goto give_sigill; - + case 11: /* Privileged register trap */ if ((regs->iir & 0xffdfffe0) == 0x034008a0) { @@ -640,7 +633,7 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if(user_mode(regs)){ si.si_signo = SIGFPE; /* Set to zero, and let the userspace app figure it out from - the insn pointed to by si_addr */ + the insn pointed to by si_addr */ si.si_code = 0; si.si_addr = (void __user *) regs->iaoq[0]; force_sig_info(SIGFPE, &si, current); @@ -652,9 +645,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs) case 14: /* Assist Exception Trap, i.e. floating point exception. */ die_if_kernel("Floating point exception", regs, 0); /* quiet */ + __inc_irq_stat(irq_fpassist_count); handle_fpe(regs); return; - + case 15: /* Data TLB miss fault/Data page fault */ /* Fall through */ @@ -666,15 +660,15 @@ void notrace handle_interruption(int code, struct pt_regs *regs) case 17: /* Non-access data TLB miss fault/Non-access data page fault */ /* FIXME: - Still need to add slow path emulation code here! - If the insn used a non-shadow register, then the tlb + Still need to add slow path emulation code here! + If the insn used a non-shadow register, then the tlb handlers could not have their side-effect (e.g. probe writing to a target register) emulated since rfir would erase the changes to said register. Instead we have to setup everything, call this function we are in, and emulate by hand. Technically we need to emulate: fdc,fdce,pdc,"fic,4f",prober,probeir,probew, probeiw - */ + */ fault_address = regs->ior; fault_space = regs->isr; break; @@ -768,11 +762,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs) default: if (user_mode(regs)) { -#ifdef PRINT_USER_FAULTS - printk(KERN_DEBUG "\nhandle_interruption() pid=%d command='%s'\n", - task_pid_nr(current), current->comm); - show_regs(regs); -#endif + parisc_printk_ratelimited(0, regs, KERN_DEBUG + "handle_interruption() pid=%d command='%s'\n", + task_pid_nr(current), current->comm); /* SIGBUS, for lack of a better one. */ si.si_signo = SIGBUS; si.si_code = BUS_OBJERR; @@ -789,16 +781,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if (user_mode(regs)) { if ((fault_space >> SPACEID_SHIFT) != (regs->sr[7] >> SPACEID_SHIFT)) { -#ifdef PRINT_USER_FAULTS - if (fault_space == 0) - printk(KERN_DEBUG "User Fault on Kernel Space "); - else - printk(KERN_DEBUG "User Fault (long pointer) (fault %d) ", - code); - printk(KERN_CONT "pid=%d command='%s'\n", - task_pid_nr(current), current->comm); - show_regs(regs); -#endif + parisc_printk_ratelimited(0, regs, KERN_DEBUG + "User fault %d on space 0x%08lx, pid=%d command='%s'\n", + code, fault_space, + task_pid_nr(current), current->comm); si.si_signo = SIGSEGV; si.si_errno = 0; si.si_code = SEGV_MAPERR; @@ -810,14 +796,14 @@ void notrace handle_interruption(int code, struct pt_regs *regs) else { /* - * The kernel should never fault on its own address space. + * The kernel should never fault on its own address space, + * unless pagefault_disable() was called before. */ - if (fault_space == 0) + if (fault_space == 0 && !in_atomic()) { pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); - } } diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 234e3682cf0..d7c0acb35ec 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -27,6 +27,7 @@ #include <linux/signal.h> #include <linux/ratelimit.h> #include <asm/uaccess.h> +#include <asm/hardirq.h> /* #define DEBUG_UNALIGNED 1 */ @@ -454,6 +455,8 @@ void handle_unaligned(struct pt_regs *regs) struct siginfo si; register int flop=0; /* true if this is a flop */ + __inc_irq_stat(irq_unaligned_count); + /* log a message with pacing */ if (user_mode(regs)) { if (current->thread.flags & PARISC_UAC_SIGBUS) { diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 76ed62ed785..ddd988b267a 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -168,7 +168,7 @@ void unwind_table_remove(struct unwind_table *table) } /* Called from setup_arch to import the kernel unwind info */ -int unwind_init(void) +int __init unwind_init(void) { long start, stop; register unsigned long gp __asm__ ("r27"); @@ -233,7 +233,6 @@ static void unwind_frame_regs(struct unwind_frame_info *info) e = find_unwind_entry(info->ip); if (e == NULL) { unsigned long sp; - extern char _stext[], _etext[]; dbg("Cannot find unwind entry for 0x%lx; forced unwinding\n", info->ip); @@ -281,8 +280,7 @@ static void unwind_frame_regs(struct unwind_frame_info *info) break; info->prev_ip = tmp; sp = info->prev_sp; - } while (info->prev_ip < (unsigned long)_stext || - info->prev_ip > (unsigned long)_etext); + } while (!kernel_text_address(info->prev_ip)); info->rp = 0; @@ -435,9 +433,8 @@ unsigned long return_address(unsigned int level) do { if (unwind_once(&info) < 0 || info.ip == 0) return 0; - if (!__kernel_text_address(info.ip)) { + if (!kernel_text_address(info.ip)) return 0; - } } while (info.ip && level--); return info.ip; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 64a999882e4..0dacc5ca555 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -6,24 +6,19 @@ * Copyright (C) 2000 Michael Ang <mang with subcarrier.org> * Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org> * Copyright (C) 2003 James Bottomley <jejb with parisc-linux.org> - * Copyright (C) 2006 Helge Deller <deller@gmx.de> - * - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * Copyright (C) 2006-2013 Helge Deller <deller@gmx.de> + */ + +/* + * Put page table entries (swapper_pg_dir) as the first thing in .bss. This + * will ensure that it has .bss alignment (PAGE_SIZE). */ +#define BSS_FIRST_SECTIONS *(.data..vm0.pmd) \ + *(.data..vm0.pgd) \ + *(.data..vm0.pte) + #include <asm-generic/vmlinux.lds.h> + /* needed for the processor specific cache alignment size */ #include <asm/cache.h> #include <asm/page.h> @@ -39,7 +34,7 @@ OUTPUT_FORMAT("elf64-hppa-linux") OUTPUT_ARCH(hppa:hppa2.0w) #endif -ENTRY(_stext) +ENTRY(parisc_kernel_start) #ifndef CONFIG_64BIT jiffies = jiffies_64 + 4; #else @@ -49,11 +44,29 @@ SECTIONS { . = KERNEL_BINARY_TEXT_START; + __init_begin = .; + HEAD_TEXT_SECTION + INIT_TEXT_SECTION(8) + + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(PAGE_SIZE) + /* we have to discard exit text and such at runtime, not link time */ + .exit.text : + { + EXIT_TEXT + } + .exit.data : + { + EXIT_DATA + } + PERCPU_SECTION(8) + . = ALIGN(PAGE_SIZE); + __init_end = .; + /* freed after init ends here */ + _text = .; /* Text and read-only data */ - .head ALIGN(16) : { - HEAD_TEXT - } = 0 - .text ALIGN(16) : { + _stext = .; + .text ALIGN(PAGE_SIZE) : { TEXT_TEXT SCHED_TEXT LOCK_TEXT @@ -68,21 +81,28 @@ SECTIONS *(.lock.text) /* out-of-line lock text */ *(.gnu.warning) } - /* End of text section */ + . = ALIGN(PAGE_SIZE); _etext = .; + /* End of text section */ /* Start of data section */ _sdata = .; - RODATA + RO_DATA_SECTION(8) - /* writeable */ - /* Make sure this is page aligned so - * that we can properly leave these - * as writable - */ - . = ALIGN(PAGE_SIZE); - data_start = .; +#ifdef CONFIG_64BIT + . = ALIGN(16); + /* Linkage tables */ + .opd : { + *(.opd) + } PROVIDE (__gp = .); + .plt : { + *(.plt) + } + .dlt : { + *(.dlt) + } +#endif /* unwind info */ .PARISC.unwind : { @@ -91,11 +111,19 @@ SECTIONS __stop___unwind = .; } - EXCEPTION_TABLE(16) + /* writeable */ + /* Make sure this is page aligned so + * that we can properly leave these + * as writable + */ + . = ALIGN(PAGE_SIZE); + data_start = .; + + EXCEPTION_TABLE(8) NOTES /* Data */ - RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) + RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, PAGE_SIZE) /* PA-RISC locks requires 16-byte alignment */ . = ALIGN(16); @@ -107,54 +135,8 @@ SECTIONS _edata = .; /* BSS */ - __bss_start = .; - /* page table entries need to be PAGE_SIZE aligned */ - . = ALIGN(PAGE_SIZE); - .data..vmpages : { - *(.data..vm0.pmd) - *(.data..vm0.pgd) - *(.data..vm0.pte) - } - .bss : { - *(.bss) - *(COMMON) - } - __bss_stop = .; - -#ifdef CONFIG_64BIT - . = ALIGN(16); - /* Linkage tables */ - .opd : { - *(.opd) - } PROVIDE (__gp = .); - .plt : { - *(.plt) - } - .dlt : { - *(.dlt) - } -#endif + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 8) - /* reserve space for interrupt stack by aligning __init* to 16k */ - . = ALIGN(16384); - __init_begin = .; - INIT_TEXT_SECTION(16384) - . = ALIGN(PAGE_SIZE); - INIT_DATA_SECTION(16) - /* we have to discard exit text and such at runtime, not link time */ - .exit.text : - { - EXIT_TEXT - } - .exit.data : - { - EXIT_DATA - } - - PERCPU_SECTION(L1_CACHE_BYTES) - . = ALIGN(PAGE_SIZE); - __init_end = .; - /* freed after init ends here */ _end = . ; STABS_DEBUG |