diff options
85 files changed, 682 insertions, 503 deletions
diff --git a/arch/frv/kernel/semaphore.c b/arch/frv/kernel/semaphore.c index 5cba9c1f2b3d..7971d680ae29 100644 --- a/arch/frv/kernel/semaphore.c +++ b/arch/frv/kernel/semaphore.c @@ -20,7 +20,7 @@ struct sem_waiter { struct task_struct *task; }; -#if SEM_DEBUG +#if SEMAPHORE_DEBUG void semtrace(struct semaphore *sem, const char *str) { if (sem->debug) diff --git a/arch/frv/mb93090-mb00/pci-irq.c b/arch/frv/mb93090-mb00/pci-irq.c index af981bda015c..24622d89b1ca 100644 --- a/arch/frv/mb93090-mb00/pci-irq.c +++ b/arch/frv/mb93090-mb00/pci-irq.c @@ -60,7 +60,7 @@ void __init pcibios_fixup_irqs(void) } } -void __init pcibios_penalize_isa_irq(int irq, int active) +void __init pcibios_penalize_isa_irq(int irq) { } diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c index 79433159b5f0..765088ea8a50 100644 --- a/arch/frv/mm/init.c +++ b/arch/frv/mm/init.c @@ -108,7 +108,7 @@ void __init paging_init(void) memset((void *) empty_zero_page, 0, PAGE_SIZE); -#if CONFIG_HIGHMEM +#ifdef CONFIG_HIGHMEM if (num_physpages - num_mappedpages) { pgd_t *pge; pud_t *pue; diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c index 2c67dfe5a6b3..f76dd03ddd99 100644 --- a/arch/frv/mm/pgalloc.c +++ b/arch/frv/mm/pgalloc.c @@ -85,7 +85,7 @@ static inline void pgd_list_add(pgd_t *pgd) struct page *page = virt_to_page(pgd); page->index = (unsigned long) pgd_list; if (pgd_list) - pgd_list->private = (unsigned long) &page->index; + set_page_private(pgd_list, (unsigned long) &page->index); pgd_list = page; set_page_private(page, (unsigned long)&pgd_list); } @@ -94,10 +94,10 @@ static inline void pgd_list_del(pgd_t *pgd) { struct page *next, **pprev, *page = virt_to_page(pgd); next = (struct page *) page->index; - pprev = (struct page **)page_private(page); + pprev = (struct page **) page_private(page); *pprev = next; if (next) - next->private = (unsigned long) pprev; + set_page_private(next, (unsigned long) pprev); } void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused) diff --git a/arch/m32r/kernel/io_mappi3.c b/arch/m32r/kernel/io_mappi3.c index 6716ffea769a..f80321a58764 100644 --- a/arch/m32r/kernel/io_mappi3.c +++ b/arch/m32r/kernel/io_mappi3.c @@ -36,12 +36,13 @@ static inline void *_port2addr(unsigned long port) return (void *)(port + NONCACHE_OFFSET); } -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) +#if defined(CONFIG_IDE) static inline void *__port2addr_ata(unsigned long port) { static int dummy_reg; switch (port) { + /* IDE0 CF */ case 0x1f0: return (void *)0xb4002000; case 0x1f1: return (void *)0xb4012800; case 0x1f2: return (void *)0xb4012002; @@ -51,6 +52,17 @@ static inline void *__port2addr_ata(unsigned long port) case 0x1f6: return (void *)0xb4012006; case 0x1f7: return (void *)0xb4012806; case 0x3f6: return (void *)0xb401200e; + /* IDE1 IDE */ + case 0x170: return (void *)0xb4810000; /* Data 16bit */ + case 0x171: return (void *)0xb4810002; /* Features / Error */ + case 0x172: return (void *)0xb4810004; /* Sector count */ + case 0x173: return (void *)0xb4810006; /* Sector number */ + case 0x174: return (void *)0xb4810008; /* Cylinder low */ + case 0x175: return (void *)0xb481000a; /* Cylinder high */ + case 0x176: return (void *)0xb481000c; /* Device head */ + case 0x177: return (void *)0xb481000e; /* Command */ + case 0x376: return (void *)0xb480800c; /* Device control / Alt status */ + default: return (void *)&dummy_reg; } } @@ -108,8 +120,9 @@ unsigned char _inb(unsigned long port) { if (port >= LAN_IOSTART && port < LAN_IOEND) return _ne_inb(PORT2ADDR_NE(port)); -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - else if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + else if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ return *(volatile unsigned char *)__port2addr_ata(port); } #endif @@ -127,8 +140,9 @@ unsigned short _inw(unsigned long port) { if (port >= LAN_IOSTART && port < LAN_IOEND) return _ne_inw(PORT2ADDR_NE(port)); -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - else if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + else if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ return *(volatile unsigned short *)__port2addr_ata(port); } #endif @@ -185,8 +199,9 @@ void _outb(unsigned char b, unsigned long port) if (port >= LAN_IOSTART && port < LAN_IOEND) _ne_outb(b, PORT2ADDR_NE(port)); else -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ *(volatile unsigned char *)__port2addr_ata(port) = b; } else #endif @@ -203,8 +218,9 @@ void _outw(unsigned short w, unsigned long port) if (port >= LAN_IOSTART && port < LAN_IOEND) _ne_outw(w, PORT2ADDR_NE(port)); else -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ *(volatile unsigned short *)__port2addr_ata(port) = w; } else #endif @@ -253,8 +269,9 @@ void _insb(unsigned int port, void * addr, unsigned long count) { if (port >= LAN_IOSTART && port < LAN_IOEND) _ne_insb(PORT2ADDR_NE(port), addr, count); -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - else if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + else if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ unsigned char *buf = addr; unsigned char *portp = __port2addr_ata(port); while (count--) @@ -289,8 +306,9 @@ void _insw(unsigned int port, void * addr, unsigned long count) pcc_ioread_word(9, port, (void *)addr, sizeof(unsigned short), count, 1); #endif -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - } else if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + } else if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ portp = __port2addr_ata(port); while (count--) *buf++ = *(volatile unsigned short *)portp; @@ -321,8 +339,9 @@ void _outsb(unsigned int port, const void * addr, unsigned long count) portp = PORT2ADDR_NE(port); while (count--) _ne_outb(*buf++, portp); -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - } else if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + } else if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ portp = __port2addr_ata(port); while (count--) *(volatile unsigned char *)portp = *buf++; @@ -348,8 +367,9 @@ void _outsw(unsigned int port, const void * addr, unsigned long count) portp = PORT2ADDR_NE(port); while (count--) *(volatile unsigned short *)portp = *buf++; -#if defined(CONFIG_IDE) && !defined(CONFIG_M32R_CFC) - } else if ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) { +#if defined(CONFIG_IDE) + } else if ( ((port >= 0x170 && port <=0x177) || port == 0x376) || + ((port >= 0x1f0 && port <=0x1f7) || port == 0x3f6) ){ portp = __port2addr_ata(port); while (count--) *(volatile unsigned short *)portp = *buf++; diff --git a/arch/m32r/kernel/setup_mappi3.c b/arch/m32r/kernel/setup_mappi3.c index 9c79341a7b45..f6ecdf7f555c 100644 --- a/arch/m32r/kernel/setup_mappi3.c +++ b/arch/m32r/kernel/setup_mappi3.c @@ -151,7 +151,7 @@ void __init init_IRQ(void) disable_mappi3_irq(M32R_IRQ_INT1); #endif /* CONFIG_USB */ - /* ICUCR40: CFC IREQ */ + /* CFC IREQ */ irq_desc[PLD_IRQ_CFIREQ].status = IRQ_DISABLED; irq_desc[PLD_IRQ_CFIREQ].handler = &mappi3_irq_type; irq_desc[PLD_IRQ_CFIREQ].action = 0; @@ -160,7 +160,7 @@ void __init init_IRQ(void) disable_mappi3_irq(PLD_IRQ_CFIREQ); #if defined(CONFIG_M32R_CFC) - /* ICUCR41: CFC Insert */ + /* ICUCR41: CFC Insert & eject */ irq_desc[PLD_IRQ_CFC_INSERT].status = IRQ_DISABLED; irq_desc[PLD_IRQ_CFC_INSERT].handler = &mappi3_irq_type; irq_desc[PLD_IRQ_CFC_INSERT].action = 0; @@ -168,14 +168,16 @@ void __init init_IRQ(void) icu_data[PLD_IRQ_CFC_INSERT].icucr = M32R_ICUCR_IEN|M32R_ICUCR_ISMOD00; disable_mappi3_irq(PLD_IRQ_CFC_INSERT); - /* ICUCR42: CFC Eject */ - irq_desc[PLD_IRQ_CFC_EJECT].status = IRQ_DISABLED; - irq_desc[PLD_IRQ_CFC_EJECT].handler = &mappi3_irq_type; - irq_desc[PLD_IRQ_CFC_EJECT].action = 0; - irq_desc[PLD_IRQ_CFC_EJECT].depth = 1; /* disable nested irq */ - icu_data[PLD_IRQ_CFC_EJECT].icucr = M32R_ICUCR_IEN|M32R_ICUCR_ISMOD10; - disable_mappi3_irq(PLD_IRQ_CFC_EJECT); #endif /* CONFIG_M32R_CFC */ + + /* IDE IREQ */ + irq_desc[PLD_IRQ_IDEIREQ].status = IRQ_DISABLED; + irq_desc[PLD_IRQ_IDEIREQ].handler = &mappi3_irq_type; + irq_desc[PLD_IRQ_IDEIREQ].action = 0; + irq_desc[PLD_IRQ_IDEIREQ].depth = 1; /* disable nested irq */ + icu_data[PLD_IRQ_IDEIREQ].icucr = M32R_ICUCR_IEN|M32R_ICUCR_ISMOD10; + disable_mappi3_irq(PLD_IRQ_IDEIREQ); + } #if defined(CONFIG_SMC91X) diff --git a/arch/m32r/kernel/sys_m32r.c b/arch/m32r/kernel/sys_m32r.c index e0500e12c5fb..fe55b28d3725 100644 --- a/arch/m32r/kernel/sys_m32r.c +++ b/arch/m32r/kernel/sys_m32r.c @@ -41,7 +41,8 @@ asmlinkage int sys_tas(int *addr) return -EFAULT; local_irq_save(flags); oldval = *addr; - *addr = 1; + if (!oldval) + *addr = 1; local_irq_restore(flags); return oldval; } @@ -59,7 +60,8 @@ asmlinkage int sys_tas(int *addr) _raw_spin_lock(&tas_lock); oldval = *addr; - *addr = 1; + if (!oldval) + *addr = 1; _raw_spin_unlock(&tas_lock); return oldval; diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 98f67c78d1bd..a13eb575f834 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -61,15 +61,17 @@ endif LDFLAGS_vmlinux := -Bstatic # The -Iarch/$(ARCH)/include is temporary while we are merging -CPPFLAGS += -Iarch/$(ARCH) -Iarch/$(ARCH)/include -AFLAGS += -Iarch/$(ARCH) -CFLAGS += -Iarch/$(ARCH) -msoft-float -pipe +CPPFLAGS-$(CONFIG_PPC32) := -Iarch/$(ARCH) -Iarch/$(ARCH)/include +AFLAGS-$(CONFIG_PPC32) := -Iarch/$(ARCH) CFLAGS-$(CONFIG_PPC64) := -mminimal-toc -mtraceback=none -mcall-aixdesc -CFLAGS-$(CONFIG_PPC32) := -ffixed-r2 -mmultiple -CFLAGS += $(CFLAGS-y) +CFLAGS-$(CONFIG_PPC32) := -Iarch/$(ARCH) -ffixed-r2 -mmultiple +CPPFLAGS += $(CPPFLAGS-y) +AFLAGS += $(AFLAGS-y) +CFLAGS += -msoft-float -pipe $(CFLAGS-y) CPP = $(CC) -E $(CFLAGS) # Temporary hack until we have migrated to asm-powerpc -LINUXINCLUDE += -Iarch/$(ARCH)/include +LINUXINCLUDE-$(CONFIG_PPC32) := -Iarch/$(ARCH)/include +LINUXINCLUDE += $(LINUXINCLUDE-y) CHECKFLAGS += -m$(SZ) -D__powerpc__ -D__powerpc$(SZ)__ @@ -173,11 +175,13 @@ archclean: archprepare: checkbin +ifeq ($(CONFIG_PPC32),y) # Temporary hack until we have migrated to asm-powerpc include/asm: arch/$(ARCH)/include/asm arch/$(ARCH)/include/asm: FORCE $(Q)if [ ! -d arch/$(ARCH)/include ]; then mkdir -p arch/$(ARCH)/include; fi $(Q)ln -fsn $(srctree)/include/asm-$(OLDARCH) arch/$(ARCH)/include/asm +endif # Use the file '.tmp_gas_check' for binutils tests, as gas won't output # to stdout and these checks are run even on install targets. diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index b44b36e0c293..f0c47dab0903 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -145,8 +145,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma) struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE); struct page *upg = (vma && vma->vm_mm) ? - follow_page(vma->vm_mm, vma->vm_start + - i*PAGE_SIZE, 0) + follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0) : NULL; dump_one_vdso_page(pg, upg); } @@ -157,8 +156,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma) struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE); struct page *upg = (vma && vma->vm_mm) ? - follow_page(vma->vm_mm, vma->vm_start + - i*PAGE_SIZE, 0) + follow_page(vma, vma->vm_start + i*PAGE_SIZE, 0) : NULL; dump_one_vdso_page(pg, upg); } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index f867bba893ca..6bc9dbad7dea 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -295,7 +295,7 @@ int prepare_hugepage_range(unsigned long addr, unsigned long len) if (addr < 0x100000000UL) err = open_low_hpage_areas(current->mm, LOW_ESID_MASK(addr, len)); - if ((addr + len) >= 0x100000000UL) + if ((addr + len) > 0x100000000UL) err = open_high_hpage_areas(current->mm, HTLB_AREA_MASK(addr, len)); if (err) { diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c index bf081b345820..2b54eeb2c899 100644 --- a/arch/powerpc/platforms/iseries/iommu.c +++ b/arch/powerpc/platforms/iseries/iommu.c @@ -3,7 +3,7 @@ * * Rewrite, cleanup: * - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * Dynamic DMA mapping support, iSeries-specific parts. * diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 97ba5214417f..c78f2b290a73 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -5,7 +5,7 @@ * * Rewrite, cleanup: * - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * Dynamic DMA mapping support, pSeries-specific parts, both SMP and LPAR. * diff --git a/arch/powerpc/sysdev/dart.h b/arch/powerpc/sysdev/dart.h index ea8f0d9eed8a..33ed9ed7fc1e 100644 --- a/arch/powerpc/sysdev/dart.h +++ b/arch/powerpc/sysdev/dart.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/arch/powerpc/sysdev/u3_iommu.c b/arch/powerpc/sysdev/u3_iommu.c index f32baf7f4693..5c1a26a6d00c 100644 --- a/arch/powerpc/sysdev/u3_iommu.c +++ b/arch/powerpc/sysdev/u3_iommu.c @@ -1,11 +1,11 @@ /* * arch/powerpc/sysdev/u3_iommu.c * - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * Based on pSeries_iommu.c: * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * Dynamic DMA mapping support, Apple U3 & IBM CPC925 "DART" iommu. * diff --git a/arch/sparc/mm/generic.c b/arch/sparc/mm/generic.c index 0410bae681f8..2cb0728cee05 100644 --- a/arch/sparc/mm/generic.c +++ b/arch/sparc/mm/generic.c @@ -32,9 +32,7 @@ static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigne if (end > PMD_SIZE) end = PMD_SIZE; do { - pte_t oldpage = *pte; - pte_clear(mm, address, pte); - set_pte(pte, mk_pte_io(offset, prot, space)); + set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space)); address += PAGE_SIZE; offset += PAGE_SIZE; pte++; @@ -63,7 +61,7 @@ static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned } int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, - unsigned long pfn, unsigned long size, pgprot_t prot) + unsigned long pfn, unsigned long size, pgprot_t prot) { int error = 0; pgd_t * dir; @@ -74,7 +72,9 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; /* See comment in mm/memory.c remap_pfn_range */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_UNPAGED; + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + vma->vm_pgoff = (offset >> PAGE_SHIFT) | + ((unsigned long)space << 28UL); prot = __pgprot(pg_iobits); offset -= from; diff --git a/arch/sparc64/mm/generic.c b/arch/sparc64/mm/generic.c index 8fd4cb1f050a..d9396c1721cd 100644 --- a/arch/sparc64/mm/generic.c +++ b/arch/sparc64/mm/generic.c @@ -15,6 +15,15 @@ #include <asm/page.h> #include <asm/tlbflush.h> +static inline pte_t mk_pte_io(unsigned long page, pgprot_t prot, int space) +{ + pte_t pte; + pte_val(pte) = (((page) | pgprot_val(prot) | _PAGE_E) & + ~(unsigned long)_PAGE_CACHE); + pte_val(pte) |= (((unsigned long)space) << 32); + return pte; +} + /* Remap IO memory, the same way as remap_pfn_range(), but use * the obio memory space. * @@ -126,9 +135,13 @@ int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, struct mm_struct *mm = vma->vm_mm; int space = GET_IOSPACE(pfn); unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; + unsigned long phys_base; + + phys_base = offset | (((unsigned long) space) << 32UL); /* See comment in mm/memory.c remap_pfn_range */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_UNPAGED; + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + vma->vm_pgoff = phys_base >> PAGE_SHIFT; prot = __pgprot(pg_iobits); offset -= from; diff --git a/drivers/char/drm/drm_lock.c b/drivers/char/drm/drm_lock.c index b276ae8a6633..b48a595d54ec 100644 --- a/drivers/char/drm/drm_lock.c +++ b/drivers/char/drm/drm_lock.c @@ -104,6 +104,10 @@ int drm_lock(struct inode *inode, struct file *filp, __set_current_state(TASK_RUNNING); remove_wait_queue(&dev->lock.lock_queue, &entry); + DRM_DEBUG("%d %s\n", lock.context, ret ? "interrupted" : "has lock"); + if (ret) + return ret; + sigemptyset(&dev->sigmask); sigaddset(&dev->sigmask, SIGSTOP); sigaddset(&dev->sigmask, SIGTSTP); @@ -116,8 +120,12 @@ int drm_lock(struct inode *inode, struct file *filp, if (dev->driver->dma_ready && (lock.flags & _DRM_LOCK_READY)) dev->driver->dma_ready(dev); - if (dev->driver->dma_quiescent && (lock.flags & _DRM_LOCK_QUIESCENT)) - return dev->driver->dma_quiescent(dev); + if (dev->driver->dma_quiescent && (lock.flags & _DRM_LOCK_QUIESCENT)) { + if (dev->driver->dma_quiescent(dev)) { + DRM_DEBUG("%d waiting for DMA quiescent\n", lock.context); + return DRM_ERR(EBUSY); + } + } /* dev->driver->kernel_context_switch isn't used by any of the x86 * drivers but is used by the Sparc driver. @@ -128,9 +136,7 @@ int drm_lock(struct inode *inode, struct file *filp, dev->driver->kernel_context_switch(dev, dev->last_context, lock.context); } - DRM_DEBUG("%d %s\n", lock.context, ret ? "interrupted" : "has lock"); - - return ret; + return 0; } /** diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 29c3b631445a..91dd669273e0 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -591,7 +591,7 @@ static inline size_t read_zero_pagealigned(char __user * buf, size_t size) if (vma->vm_start > addr || (vma->vm_flags & VM_WRITE) == 0) goto out_up; - if (vma->vm_flags & (VM_SHARED | VM_HUGETLB | VM_UNPAGED)) + if (vma->vm_flags & (VM_SHARED | VM_HUGETLB)) break; count = vma->vm_end - addr; if (count > size) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 1c0f62d0f938..815902c2c856 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1113,21 +1113,13 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, { int retval = -EINVAL; - /* - * If we are already in context of hotplug thread, we dont need to - * acquire the hotplug lock. Otherwise acquire cpucontrol to prevent - * hotplug from removing this cpu that we are working on. - */ - if (!current_in_cpu_hotplug()) - lock_cpu_hotplug(); - + lock_cpu_hotplug(); dprintk("target for CPU %u: %u kHz, relation %u\n", policy->cpu, target_freq, relation); if (cpu_online(policy->cpu) && cpufreq_driver->target) retval = cpufreq_driver->target(policy, target_freq, relation); - if (!current_in_cpu_hotplug()) - unlock_cpu_hotplug(); + unlock_cpu_hotplug(); return retval; } diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 41d6b4017acb..d393b504bf26 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -355,9 +355,9 @@ error4: spin_unlock_irqrestore(&port_priv->reg_lock, flags); kfree(reg_req); error3: - kfree(mad_agent_priv); -error2: ib_dereg_mr(mad_agent_priv->agent.mr); +error2: + kfree(mad_agent_priv); error1: return ret; } diff --git a/drivers/md/md.c b/drivers/md/md.c index 78c7418478d6..cd12fca73b0d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1028,7 +1028,6 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) mddev->size = le64_to_cpu(sb->size)/2; mddev->events = le64_to_cpu(sb->events); mddev->bitmap_offset = 0; - mddev->default_bitmap_offset = 0; mddev->default_bitmap_offset = 1024; mddev->recovery_cp = le64_to_cpu(sb->resync_offset); @@ -2932,6 +2931,9 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) mddev->sb_dirty = 1; + mddev->default_bitmap_offset = MD_SB_BYTES >> 9; + mddev->bitmap_offset = 0; + /* * Generate a 128 bit UUID */ diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 2da9d3ba902d..3066c587b539 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -953,9 +953,6 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) int mirror = 0; mirror_info_t *p; - if (rdev->saved_raid_disk >= 0 && - conf->mirrors[rdev->saved_raid_disk].rdev == NULL) - mirror = rdev->saved_raid_disk; for (mirror=0; mirror < mddev->raid_disks; mirror++) if ( !(p=conf->mirrors+mirror)->rdev) { @@ -972,7 +969,10 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) p->head_position = 0; rdev->raid_disk = mirror; found = 1; - if (rdev->saved_raid_disk != mirror) + /* As all devices are equivalent, we don't need a full recovery + * if this was recently any drive of the array + */ + if (rdev->saved_raid_disk < 0) conf->fullsync = 1; rcu_assign_pointer(p->rdev, rdev); break; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 867f06ae33d9..713dc9c2c730 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -552,7 +552,11 @@ static int read_balance(conf_t *conf, r10bio_t *r10_bio) !test_bit(In_sync, &rdev->flags)) continue; - if (!atomic_read(&rdev->nr_pending)) { + /* This optimisation is debatable, and completely destroys + * sequential read speed for 'far copies' arrays. So only + * keep it for 'near' arrays, and review those later. + */ + if (conf->near_copies > 1 && !atomic_read(&rdev->nr_pending)) { disk = ndisk; slot = nslot; break; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e2a40283e323..36d5f8ac8265 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -1704,7 +1704,9 @@ static void raid5d (mddev_t *mddev) if (conf->seq_flush - conf->seq_write > 0) { int seq = conf->seq_flush; + spin_unlock_irq(&conf->device_lock); bitmap_unplug(mddev->bitmap); + spin_lock_irq(&conf->device_lock); conf->seq_write = seq; activate_bit_delay(conf); } diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c index eae5a35629c5..0000d162d198 100644 --- a/drivers/md/raid6main.c +++ b/drivers/md/raid6main.c @@ -1702,6 +1702,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i int data_disks = raid_disks - 2; sector_t max_sector = mddev->size << 1; int sync_blocks; + int still_degraded = 0; + int i; if (sector_nr >= max_sector) { /* just being told to finish up .. nothing much to do */ @@ -1710,7 +1712,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i if (mddev->curr_resync < max_sector) /* aborted */ bitmap_end_sync(mddev->bitmap, mddev->curr_resync, &sync_blocks, 1); - else /* compelted sync */ + else /* completed sync */ conf->fullsync = 0; bitmap_close_sync(mddev->bitmap); @@ -1748,7 +1750,16 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i */ schedule_timeout_uninterruptible(1); } - bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 0); + /* Need to check if array will still be degraded after recovery/resync + * We don't need to check the 'failed' flag as when that gets set, + * recovery aborts. + */ + for (i=0; i<mddev->raid_disks; i++) + if (conf->disks[i].rdev == NULL) + still_degraded = 1; + + bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded); + spin_lock(&sh->lock); set_bit(STRIPE_SYNCING, &sh->state); clear_bit(STRIPE_INSYNC, &sh->state); @@ -1784,7 +1795,9 @@ static void raid6d (mddev_t *mddev) if (conf->seq_flush - conf->seq_write > 0) { int seq = conf->seq_flush; + spin_unlock_irq(&conf->device_lock); bitmap_unplug(mddev->bitmap); + spin_lock_irq(&conf->device_lock); conf->seq_write = seq; activate_bit_delay(conf); } @@ -2145,9 +2158,15 @@ static int raid6_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) /* no point adding a device */ return 0; /* - * find the disk ... + * find the disk ... but prefer rdev->saved_raid_disk + * if possible. */ - for (disk=0; disk < mddev->raid_disks; disk++) + if (rdev->saved_raid_disk >= 0 && + conf->disks[rdev->saved_raid_disk].rdev == NULL) + disk = rdev->saved_raid_disk; + else + disk = 0; + for ( ; disk < mddev->raid_disks; disk++) if ((p=conf->disks + disk)->rdev == NULL) { clear_bit(In_sync, &rdev->flags); rdev->raid_disk = disk; diff --git a/drivers/media/video/Kconfig b/drivers/media/video/Kconfig index 1a3b3c7e5e99..ecb9a31dd003 100644 --- a/drivers/media/video/Kconfig +++ b/drivers/media/video/Kconfig @@ -26,7 +26,7 @@ config VIDEO_BT848 module will be called bttv. config VIDEO_BT848_DVB - tristate "DVB/ATSC Support for bt878 based TV cards" + bool "DVB/ATSC Support for bt878 based TV cards" depends on VIDEO_BT848 && DVB_CORE select DVB_BT8XX ---help--- diff --git a/drivers/media/video/cx88/Kconfig b/drivers/media/video/cx88/Kconfig index 41818b6205b3..85ba4106dc79 100644 --- a/drivers/media/video/cx88/Kconfig +++ b/drivers/media/video/cx88/Kconfig @@ -46,8 +46,8 @@ config VIDEO_CX88_DVB_ALL_FRONTENDS If you are unsure, choose Y. config VIDEO_CX88_DVB_MT352 - tristate "Zarlink MT352 DVB-T Support" - default m + bool "Zarlink MT352 DVB-T Support" + default y depends on VIDEO_CX88_DVB && !VIDEO_CX88_DVB_ALL_FRONTENDS select DVB_MT352 ---help--- @@ -55,8 +55,8 @@ config VIDEO_CX88_DVB_MT352 Connexant 2388x chip and the MT352 demodulator. config VIDEO_CX88_DVB_OR51132 - tristate "OR51132 ATSC Support" - default m + bool "OR51132 ATSC Support" + default y depends on VIDEO_CX88_DVB && !VIDEO_CX88_DVB_ALL_FRONTENDS select DVB_OR51132 ---help--- @@ -64,8 +64,8 @@ config VIDEO_CX88_DVB_OR51132 Connexant 2388x chip and the OR51132 demodulator. config VIDEO_CX88_DVB_CX22702 - tristate "Conexant CX22702 DVB-T Support" - default m + bool "Conexant CX22702 DVB-T Support" + default y depends on VIDEO_CX88_DVB && !VIDEO_CX88_DVB_ALL_FRONTENDS select DVB_CX22702 ---help--- @@ -73,8 +73,8 @@ config VIDEO_CX88_DVB_CX22702 Connexant 2388x chip and the CX22702 demodulator. config VIDEO_CX88_DVB_LGDT330X - tristate "LG Electronics DT3302/DT3303 ATSC Support" - default m + bool "LG Electronics DT3302/DT3303 ATSC Support" + default y depends on VIDEO_CX88_DVB && !VIDEO_CX88_DVB_ALL_FRONTENDS select DVB_LGDT330X ---help--- @@ -82,8 +82,8 @@ config VIDEO_CX88_DVB_LGDT330X Connexant 2388x chip and the LGDT3302/LGDT3303 demodulator. config VIDEO_CX88_DVB_NXT200X - tristate "NXT2002/NXT2004 ATSC Support" - default m + bool "NXT2002/NXT2004 ATSC Support" + default y depends on VIDEO_CX88_DVB && !VIDEO_CX88_DVB_ALL_FRONTENDS select DVB_NXT200X ---help--- diff --git a/drivers/media/video/cx88/Makefile b/drivers/media/video/cx88/Makefile index 0df40b773454..54401b02b7ce 100644 --- a/drivers/media/video/cx88/Makefile +++ b/drivers/media/video/cx88/Makefile @@ -9,21 +9,12 @@ obj-$(CONFIG_VIDEO_CX88_DVB) += cx88-dvb.o EXTRA_CFLAGS += -I$(src)/.. EXTRA_CFLAGS += -I$(srctree)/drivers/media/dvb/dvb-core EXTRA_CFLAGS += -I$(srctree)/drivers/media/dvb/frontends -ifneq ($(CONFIG_VIDEO_BUF_DVB),n) - EXTRA_CFLAGS += -DHAVE_VIDEO_BUF_DVB=1 -endif -ifneq ($(CONFIG_DVB_CX22702),n) - EXTRA_CFLAGS += -DHAVE_CX22702=1 -endif -ifneq ($(CONFIG_DVB_OR51132),n) - EXTRA_CFLAGS += -DHAVE_OR51132=1 -endif -ifneq ($(CONFIG_DVB_LGDT330X),n) - EXTRA_CFLAGS += -DHAVE_LGDT330X=1 -endif -ifneq ($(CONFIG_DVB_MT352),n) - EXTRA_CFLAGS += -DHAVE_MT352=1 -endif -ifneq ($(CONFIG_DVB_NXT200X),n) - EXTRA_CFLAGS += -DHAVE_NXT200X=1 -endif + +extra-cflags-$(CONFIG_VIDEO_BUF_DVB) += -DHAVE_VIDEO_BUF_DVB=1 +extra-cflags-$(CONFIG_DVB_CX22702) += -DHAVE_CX22702=1 +extra-cflags-$(CONFIG_DVB_OR51132) += -DHAVE_OR51132=1 +extra-cflags-$(CONFIG_DVB_LGDT330X) += -DHAVE_LGDT330X=1 +extra-cflags-$(CONFIG_DVB_MT352) += -DHAVE_MT352=1 +extra-cflags-$(CONFIG_DVB_NXT200X) += -DHAVE_NXT200X=1 + +EXTRA_CFLAGS += $(extra-cflags-y) $(extra-cflags-m) diff --git a/drivers/media/video/saa7134/Kconfig b/drivers/media/video/saa7134/Kconfig index 7bdeabe638ca..c512c4411b38 100644 --- a/drivers/media/video/saa7134/Kconfig +++ b/drivers/media/video/saa7134/Kconfig @@ -42,8 +42,8 @@ config VIDEO_SAA7134_DVB_ALL_FRONTENDS If you are unsure, choose Y. config VIDEO_SAA7134_DVB_MT352 - tristate "Zarlink MT352 DVB-T Support" - default m + bool "Zarlink MT352 DVB-T Support" + default y depends on VIDEO_SAA7134_DVB && !VIDEO_SAA7134_DVB_ALL_FRONTENDS select DVB_MT352 ---help--- @@ -51,8 +51,8 @@ config VIDEO_SAA7134_DVB_MT352 Philips saa7134 chip and the MT352 demodulator. config VIDEO_SAA7134_DVB_TDA1004X - tristate "Phillips TDA10045H/TDA10046H DVB-T Support" - default m + bool "Phillips TDA10045H/TDA10046H DVB-T Support" + default y depends on VIDEO_SAA7134_DVB && !VIDEO_SAA7134_DVB_ALL_FRONTENDS select DVB_TDA1004X ---help--- @@ -60,8 +60,8 @@ config VIDEO_SAA7134_DVB_TDA1004X Philips saa7134 chip and the TDA10045H/TDA10046H demodulator. config VIDEO_SAA7134_DVB_NXT200X - tristate "NXT2002/NXT2004 ATSC Support" - default m + bool "NXT2002/NXT2004 ATSC Support" + default y depends on VIDEO_SAA7134_DVB && !VIDEO_SAA7134_DVB_ALL_FRONTENDS select DVB_NXT200X ---help--- diff --git a/drivers/media/video/saa7134/Makefile b/drivers/media/video/saa7134/Makefile index 4226b61cc613..134f83a96218 100644 --- a/drivers/media/video/saa7134/Makefile +++ b/drivers/media/video/saa7134/Makefile @@ -11,15 +11,10 @@ obj-$(CONFIG_VIDEO_SAA7134_DVB) += saa7134-dvb.o EXTRA_CFLAGS += -I$(src)/.. EXTRA_CFLAGS += -I$(srctree)/drivers/media/dvb/dvb-core EXTRA_CFLAGS += -I$(srctree)/drivers/media/dvb/frontends -ifneq ($(CONFIG_VIDEO_BUF_DVB),n) - EXTRA_CFLAGS += -DHAVE_VIDEO_BUF_DVB=1 -endif -ifneq ($(CONFIG_DVB_MT352),n) - EXTRA_CFLAGS += -DHAVE_MT352=1 -endif -ifneq ($(CONFIG_DVB_TDA1004X),n) - EXTRA_CFLAGS += -DHAVE_TDA1004X=1 -endif -ifneq ($(CONFIG_DVB_NXT200X),n) - EXTRA_CFLAGS += -DHAVE_NXT200X=1 -endif + +extra-cflags-$(CONFIG_VIDEO_BUF_DVB) += -DHAVE_VIDEO_BUF_DVB=1 +extra-cflags-$(CONFIG_DVB_MT352) += -DHAVE_MT352=1 +extra-cflags-$(CONFIG_DVB_TDA1004X) += -DHAVE_TDA1004X=1 +extra-cflags-$(CONFIG_DVB_NXT200X) += -DHAVE_NXT200X=1 + +EXTRA_CFLAGS += $(extra-cflags-y) $(extra-cflags-m) diff --git a/drivers/message/i2o/pci.c b/drivers/message/i2o/pci.c index 66c03e882570..81ef306cb124 100644 --- a/drivers/message/i2o/pci.c +++ b/drivers/message/i2o/pci.c @@ -421,8 +421,8 @@ static int __devinit i2o_pci_probe(struct pci_dev *pdev, i2o_pci_free(c); free_controller: - i2o_iop_free(c); put_device(c->device.parent); + i2o_iop_free(c); disable: pci_disable_device(pdev); diff --git a/drivers/pcmcia/m32r_cfc.c b/drivers/pcmcia/m32r_cfc.c index 2c22b4b3619d..078579ae6359 100644 --- a/drivers/pcmcia/m32r_cfc.c +++ b/drivers/pcmcia/m32r_cfc.c @@ -355,9 +355,10 @@ static void add_pcc_socket(ulong base, int irq, ulong mapaddr, kio_addr_t ioaddr #ifndef CONFIG_PLAT_USRV /* insert interrupt */ request_irq(irq, pcc_interrupt, 0, "m32r_cfc", pcc_interrupt); +#ifndef CONFIG_PLAT_MAPPI3 /* eject interrupt */ request_irq(irq+1, pcc_interrupt, 0, "m32r_cfc", pcc_interrupt); - +#endif debug(3, "m32r_cfc: enable CFMSK, RDYSEL\n"); pcc_set(pcc_sockets, (unsigned int)PLD_CFIMASK, 0x01); #endif /* CONFIG_PLAT_USRV */ diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index c28e3aea1c3c..418fc7b896ac 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -816,7 +816,7 @@ static int adpt_hba_reset(adpt_hba* pHba) static void adpt_i2o_sys_shutdown(void) { adpt_hba *pHba, *pNext; - struct adpt_i2o_post_wait_data *p1, *p2; + struct adpt_i2o_post_wait_data *p1, *old; printk(KERN_INFO"Shutting down Adaptec I2O controllers.\n"); printk(KERN_INFO" This could take a few minutes if there are many devices attached\n"); @@ -830,13 +830,14 @@ static void adpt_i2o_sys_shutdown(void) } /* Remove any timedout entries from the wait queue. */ - p2 = NULL; // spin_lock_irqsave(&adpt_post_wait_lock, flags); /* Nothing should be outstanding at this point so just * free them */ - for(p1 = adpt_post_wait_queue; p1; p2 = p1, p1 = p2->next) { - kfree(p1); + for(p1 = adpt_post_wait_queue; p1;) { + old = p1; + p1 = p1->next; + kfree(old); } // spin_unlock_irqrestore(&adpt_post_wait_lock, flags); adpt_post_wait_queue = NULL; diff --git a/drivers/video/console/fbcon_ccw.c b/drivers/video/console/fbcon_ccw.c index 3afd1eeb1ade..4952b66ae206 100644 --- a/drivers/video/console/fbcon_ccw.c +++ b/drivers/video/console/fbcon_ccw.c @@ -34,7 +34,7 @@ static inline void ccw_update_attr(u8 *dst, u8 *src, int attribute, msk <<= (8 - mod); if (offset > mod) - set_bit(FBCON_BIT(7), (void *)&msk1); + msk1 |= 0x01; for (i = 0; i < vc->vc_font.width; i++) { for (j = 0; j < width; j++) { diff --git a/drivers/video/console/fbcon_rotate.h b/drivers/video/console/fbcon_rotate.h index e504fbf5c604..1b8f92fdc6a8 100644 --- a/drivers/video/console/fbcon_rotate.h +++ b/drivers/video/console/fbcon_rotate.h @@ -21,21 +21,13 @@ (s == SCROLL_REDRAW || s == SCROLL_MOVE || !(i)->fix.xpanstep) ? \ (i)->var.xres : (i)->var.xres_virtual; }) -/* - * The bitmap is always big endian - */ -#if defined(__LITTLE_ENDIAN) -#define FBCON_BIT(b) (7 - (b)) -#else -#define FBCON_BIT(b) (b) -#endif static inline int pattern_test_bit(u32 x, u32 y, u32 pitch, const char *pat) { u32 tmp = (y * pitch) + x, index = tmp / 8, bit = tmp % 8; pat +=index; - return (test_bit(FBCON_BIT(bit), (void *)pat)); + return (*pat) & (0x80 >> bit); } static inline void pattern_set_bit(u32 x, u32 y, u32 pitch, char *pat) @@ -43,7 +35,8 @@ static inline void pattern_set_bit(u32 x, u32 y, u32 pitch, char *pat) u32 tmp = (y * pitch) + x, index = tmp / 8, bit = tmp % 8; pat += index; - set_bit(FBCON_BIT(bit), (void *)pat); + + (*pat) |= 0x80 >> bit; } static inline void rotate_ud(const char *in, char *out, u32 width, u32 height) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index be7288184fa9..0ea965c3bb7d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -427,6 +427,8 @@ v9fs_create(struct inode *dir, v9fs_mistat2inode(fcall->params.rstat.stat, file_inode, sb); kfree(fcall); + fcall = NULL; + file_dentry->d_op = &v9fs_dentry_operations; d_instantiate(file_dentry, file_inode); if (perm & V9FS_DMDIR) { diff --git a/fs/dquot.c b/fs/dquot.c index 05b60283c9c2..2a62b3dc20ec 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -1513,10 +1513,16 @@ int vfs_quota_on_mount(struct super_block *sb, char *qf_name, if (IS_ERR(dentry)) return PTR_ERR(dentry); + if (!dentry->d_inode) { + error = -ENOENT; + goto out; + } + error = security_quota_on(dentry); if (!error) error = vfs_quota_on_inode(dentry->d_inode, type, format_id); +out: dput(dentry); return error; } diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c index 1be78b4b4de9..6104ad310507 100644 --- a/fs/ext3/resize.c +++ b/fs/ext3/resize.c @@ -767,6 +767,7 @@ int ext3_group_add(struct super_block *sb, struct ext3_new_group_data *input) if (input->group != EXT3_SB(sb)->s_groups_count) { ext3_warning(sb, __FUNCTION__, "multiple resizers run on filesystem!\n"); + err = -EBUSY; goto exit_journal; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index c045cc70c749..51f5da652771 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -74,6 +74,24 @@ static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd) return 1; } +static int dir_alias(struct inode *inode) +{ + if (S_ISDIR(inode->i_mode)) { + /* Don't allow creating an alias to a directory */ + struct dentry *alias = d_find_alias(inode); + if (alias) { + dput(alias); + return 1; + } + } + return 0; +} + +static inline int invalid_nodeid(u64 nodeid) +{ + return !nodeid || nodeid == FUSE_ROOT_ID; +} + static struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, }; @@ -97,7 +115,7 @@ static int fuse_lookup_iget(struct inode *dir, struct dentry *entry, fuse_lookup_init(req, dir, entry, &outarg); request_send(fc, req); err = req->out.h.error; - if (!err && (!outarg.nodeid || outarg.nodeid == FUSE_ROOT_ID)) + if (!err && invalid_nodeid(outarg.nodeid)) err = -EIO; if (!err) { inode = fuse_iget(dir->i_sb, outarg.nodeid, outarg.generation, @@ -193,7 +211,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, int mode, } err = -EIO; - if (!S_ISREG(outentry.attr.mode)) + if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid)) goto out_free_ff; inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation, @@ -250,7 +268,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, fuse_put_request(fc, req); return err; } - if (!outarg.nodeid || outarg.nodeid == FUSE_ROOT_ID) { + if (invalid_nodeid(outarg.nodeid)) { fuse_put_request(fc, req); return -EIO; } @@ -263,7 +281,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_req *req, fuse_put_request(fc, req); /* Don't allow userspace to do really stupid things... */ - if ((inode->i_mode ^ mode) & S_IFMT) { + if (((inode->i_mode ^ mode) & S_IFMT) || dir_alias(inode)) { iput(inode); return -EIO; } @@ -874,14 +892,9 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry, err = fuse_lookup_iget(dir, entry, &inode); if (err) return ERR_PTR(err); - if (inode && S_ISDIR(inode->i_mode)) { - /* Don't allow creating an alias to a directory */ - struct dentry *alias = d_find_alias(inode); - if (alias) { - dput(alias); - iput(inode); - return ERR_PTR(-EIO); - } + if (inode && dir_alias(inode)) { + iput(inode); + return ERR_PTR(-EIO); } d_add(entry, inode); return NULL; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6391d8964214..aaab1a5ac461 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -643,14 +643,11 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt) /* * Invalidate the local caches */ -void -nfs_zap_caches(struct inode *inode) +static void nfs_zap_caches_locked(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); int mode = inode->i_mode; - spin_lock(&inode->i_lock); - NFS_ATTRTIMEO(inode) = NFS_MINATTRTIMEO(inode); NFS_ATTRTIMEO_UPDATE(inode) = jiffies; @@ -659,7 +656,12 @@ nfs_zap_caches(struct inode *inode) nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE; else nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE; +} +void nfs_zap_caches(struct inode *inode) +{ + spin_lock(&inode->i_lock); + nfs_zap_caches_locked(inode); spin_unlock(&inode->i_lock); } @@ -676,16 +678,13 @@ static void nfs_zap_acl_cache(struct inode *inode) } /* - * Invalidate, but do not unhash, the inode + * Invalidate, but do not unhash, the inode. + * NB: must be called with inode->i_lock held! */ -static void -nfs_invalidate_inode(struct inode *inode) +static void nfs_invalidate_inode(struct inode *inode) { - umode_t save_mode = inode->i_mode; - - make_bad_inode(inode); - inode->i_mode = save_mode; - nfs_zap_caches(inode); + set_bit(NFS_INO_STALE, &NFS_FLAGS(inode)); + nfs_zap_caches_locked(inode); } struct nfs_find_desc { @@ -1528,14 +1527,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr, unsign printk(KERN_DEBUG "%s: inode %ld mode changed, %07o to %07o\n", __FUNCTION__, inode->i_ino, inode->i_mode, fattr->mode); #endif + out_err: /* * No need to worry about unhashing the dentry, as the * lookup validation will know that the inode is bad. * (But we fall through to invalidate the caches.) */ nfs_invalidate_inode(inode); - out_err: - set_bit(NFS_INO_STALE, &NFS_FLAGS(inode)); return -ESTALE; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 21482b2518f6..60e0dd800cc3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3071,15 +3071,15 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock struct nfs4_client *clp = state->owner->so_client; int status; - down_read(&clp->cl_sem); /* Is this a delegated open? */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags)) { + if (NFS_I(state->inode)->delegation_state != 0) { /* Yes: cache locks! */ status = do_vfs_lock(request->fl_file, request); /* ...but avoid races with delegation recall... */ if (status < 0 || test_bit(NFS_DELEGATED_STATE, &state->flags)) - goto out; + return status; } + down_read(&clp->cl_sem); status = nfs4_set_lock_state(state, request); if (status != 0) goto out; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0675f3215e0a..5ef4c57618fe 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -644,12 +644,15 @@ void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t f struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter) { + struct rpc_sequence *sequence = counter->sequence; struct nfs_seqid *new; new = kmalloc(sizeof(*new), GFP_KERNEL); if (new != NULL) { new->sequence = counter; - INIT_LIST_HEAD(&new->list); + spin_lock(&sequence->lock); + list_add_tail(&new->list, &sequence->list); + spin_unlock(&sequence->lock); } return new; } @@ -658,12 +661,10 @@ void nfs_free_seqid(struct nfs_seqid *seqid) { struct rpc_sequence *sequence = seqid->sequence->sequence; - if (!list_empty(&seqid->list)) { - spin_lock(&sequence->lock); - list_del(&seqid->list); - spin_unlock(&sequence->lock); - } - rpc_wake_up_next(&sequence->wait); + spin_lock(&sequence->lock); + list_del(&seqid->list); + spin_unlock(&sequence->lock); + rpc_wake_up(&sequence->wait); kfree(seqid); } @@ -722,11 +723,10 @@ int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task) if (sequence->list.next == &seqid->list) goto out; spin_lock(&sequence->lock); - if (!list_empty(&sequence->list)) { + if (sequence->list.next != &seqid->list) { rpc_sleep_on(&sequence->wait, task, NULL, NULL); status = -EAGAIN; - } else - list_add(&seqid->list, &sequence->list); + } spin_unlock(&sequence->lock); out: return status; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 9ab97cef0daa..50bd5a8f0446 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -402,12 +402,11 @@ struct numa_maps { /* * Calculate numa node maps for a vma */ -static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma) +static struct numa_maps *get_numa_maps(struct vm_area_struct *vma) { + int i; struct page *page; unsigned long vaddr; - struct mm_struct *mm = vma->vm_mm; - int i; struct numa_maps *md = kmalloc(sizeof(struct numa_maps), GFP_KERNEL); if (!md) @@ -420,7 +419,7 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma) md->node[i] =0; for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) { - page = follow_page(mm, vaddr, 0); + page = follow_page(vma, vaddr, 0); if (page) { int count = page_mapcount(page); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 5f82352b97e1..0a044ad98885 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2194,7 +2194,7 @@ static int map_block_for_writepage(struct inode *inode, INITIALIZE_PATH(path); int pos_in_item; int jbegin_count = JOURNAL_PER_BALANCE_CNT; - loff_t byte_offset = (block << inode->i_sb->s_blocksize_bits) + 1; + loff_t byte_offset = ((loff_t)block << inode->i_sb->s_blocksize_bits)+1; int retval; int use_get_block = 0; int bytes_copied = 0; diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index c6108971b4e6..94d3cdfbf9b8 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -941,13 +941,12 @@ __linvfs_get_block( int retpbbm = 1; int error; - if (blocks) { - offset = blocks << inode->i_blkbits; /* 64 bit goodness */ - size = (ssize_t) min_t(xfs_off_t, offset, LONG_MAX); - } else { - size = 1 << inode->i_blkbits; - } offset = (xfs_off_t)iblock << inode->i_blkbits; + if (blocks) + size = (ssize_t) min_t(xfs_off_t, LONG_MAX, + (xfs_off_t)blocks << inode->i_blkbits); + else + size = 1 << inode->i_blkbits; VOP_BMAP(vp, offset, size, create ? flags : BMAPI_READ, &iomap, &retpbbm, error); @@ -1007,7 +1006,7 @@ __linvfs_get_block( ASSERT(iomap.iomap_bsize - iomap.iomap_delta > 0); offset = min_t(xfs_off_t, iomap.iomap_bsize - iomap.iomap_delta, - blocks << inode->i_blkbits); + (xfs_off_t)blocks << inode->i_blkbits); bh_result->b_size = (u32) min_t(xfs_off_t, UINT_MAX, offset); } diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 35e557b00db2..1c7421840c18 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -310,7 +310,8 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) * Fix up the start offset of the attribute fork */ totsize -= size; - if (totsize == sizeof(xfs_attr_sf_hdr_t) && !args->addname) { + if (totsize == sizeof(xfs_attr_sf_hdr_t) && !args->addname && + !(mp->m_flags & XFS_MOUNT_COMPAT_ATTR)) { /* * Last attribute now removed, revert to original * inode format making all literal area available @@ -328,7 +329,8 @@ xfs_attr_shortform_remove(xfs_da_args_t *args) xfs_idata_realloc(dp, -size, XFS_ATTR_FORK); dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize); ASSERT(dp->i_d.di_forkoff); - ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || args->addname); + ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) || args->addname || + (mp->m_flags & XFS_MOUNT_COMPAT_ATTR)); dp->i_afp->if_ext_max = XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t); dp->i_df.if_ext_max = @@ -737,7 +739,8 @@ xfs_attr_shortform_allfit(xfs_dabuf_t *bp, xfs_inode_t *dp) + name_loc->namelen + INT_GET(name_loc->valuelen, ARCH_CONVERT); } - if (bytes == sizeof(struct xfs_attr_sf_hdr)) + if (!(dp->i_mount->m_flags & XFS_MOUNT_COMPAT_ATTR) && + (bytes == sizeof(struct xfs_attr_sf_hdr))) return(-1); return(xfs_attr_shortform_bytesfit(dp, bytes)); } @@ -775,6 +778,8 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff) goto out; if (forkoff == -1) { + ASSERT(!(dp->i_mount->m_flags & XFS_MOUNT_COMPAT_ATTR)); + /* * Last attribute was removed, revert to original * inode format making all literal area available diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 7ceabd0e2d9d..d1236d6f4045 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -550,7 +550,7 @@ xfs_fs_goingdown( struct vfs *vfsp = XFS_MTOVFS(mp); struct super_block *sb = freeze_bdev(vfsp->vfs_super->s_bdev); - if (sb) { + if (sb && !IS_ERR(sb)) { xfs_force_shutdown(mp, XFS_FORCE_UMOUNT); thaw_bdev(sb->s_bdev, sb); } diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index fcd6d63bb68b..3ce204a524b0 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -69,7 +69,7 @@ typedef struct xfs_iomap { xfs_buftarg_t *iomap_target; xfs_off_t iomap_offset; /* offset of mapping, bytes */ xfs_off_t iomap_bsize; /* size of mapping, bytes */ - size_t iomap_delta; /* offset into mapping, bytes */ + xfs_off_t iomap_delta; /* offset into mapping, bytes */ iomap_flags_t iomap_flags; } xfs_iomap_t; diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 8f285149681f..4518b188ade6 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -494,10 +494,8 @@ typedef struct log { #define XLOG_FORCED_SHUTDOWN(log) ((log)->l_flags & XLOG_IO_ERROR) -#define XLOG_GRANT_SUB_SPACE(log,bytes,type) \ - xlog_grant_sub_space(log,bytes,type) -static inline void xlog_grant_sub_space(struct log *log, int bytes, int type) -{ +#define XLOG_GRANT_SUB_SPACE(log,bytes,type) \ + { \ if (type == 'w') { \ (log)->l_grant_write_bytes -= (bytes); \ if ((log)->l_grant_write_bytes < 0) { \ @@ -511,13 +509,9 @@ static inline void xlog_grant_sub_space(struct log *log, int bytes, int type) (log)->l_grant_reserve_cycle--; \ } \ } \ -} - -#define XLOG_GRANT_ADD_SPACE(log,bytes,type) \ - xlog_grant_add_space(log,bytes,type) -static inline void -xlog_grant_add_space(struct log *log, int bytes, int type) -{ + } +#define XLOG_GRANT_ADD_SPACE(log,bytes,type) \ + { \ if (type == 'w') { \ (log)->l_grant_write_bytes += (bytes); \ if ((log)->l_grant_write_bytes > (log)->l_logsize) { \ @@ -531,12 +525,9 @@ xlog_grant_add_space(struct log *log, int bytes, int type) (log)->l_grant_reserve_cycle++; \ } \ } \ -} - -#define XLOG_INS_TICKETQ(q, tic) xlog_ins_ticketq(q, tic) -static inline void -xlog_ins_ticketq(struct xlog_ticket *q, struct xlog_ticket *tic) -{ \ + } +#define XLOG_INS_TICKETQ(q, tic) \ + { \ if (q) { \ (tic)->t_next = (q); \ (tic)->t_prev = (q)->t_prev; \ @@ -547,12 +538,9 @@ xlog_ins_ticketq(struct xlog_ticket *q, struct xlog_ticket *tic) (q) = (tic); \ } \ (tic)->t_flags |= XLOG_TIC_IN_Q; \ -} - -#define XLOG_DEL_TICKETQ(q, tic) xlog_del_ticketq(q, tic) -static inline void -xlog_del_ticketq(struct xlog_ticket *q, struct xlog_ticket *tic) -{ \ + } +#define XLOG_DEL_TICKETQ(q, tic) \ + { \ if ((tic) == (tic)->t_next) { \ (q) = NULL; \ } else { \ @@ -562,7 +550,7 @@ xlog_del_ticketq(struct xlog_ticket *q, struct xlog_ticket *tic) } \ (tic)->t_next = (tic)->t_prev = NULL; \ (tic)->t_flags &= ~XLOG_TIC_IN_Q; \ -} + } /* common routines */ extern xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 7c1f74531463..e03fa2a3d5ed 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -3958,8 +3958,9 @@ xfs_finish_reclaim_all(xfs_mount_t *mp, int noblock) } } XFS_MOUNT_IUNLOCK(mp); - xfs_finish_reclaim(ip, noblock, - XFS_IFLUSH_DELWRI_ELSE_ASYNC); + if (xfs_finish_reclaim(ip, noblock, + XFS_IFLUSH_DELWRI_ELSE_ASYNC)) + delay(1); purged = 1; break; } diff --git a/include/asm-frv/hardirq.h b/include/asm-frv/hardirq.h index 5248ca054909..685123981e8b 100644 --- a/include/asm-frv/hardirq.h +++ b/include/asm-frv/hardirq.h @@ -14,6 +14,7 @@ #include <linux/config.h> #include <linux/threads.h> +#include <linux/irq.h> typedef struct { unsigned int __softirq_pending; diff --git a/include/asm-frv/ide.h b/include/asm-frv/ide.h index f9caecf7e3c0..ae031eaa3dd2 100644 --- a/include/asm-frv/ide.h +++ b/include/asm-frv/ide.h @@ -33,10 +33,10 @@ /* * some bits needed for parts of the IDE subsystem to compile */ -#define __ide_mm_insw(port, addr, n) insw(port, addr, n) -#define __ide_mm_insl(port, addr, n) insl(port, addr, n) -#define __ide_mm_outsw(port, addr, n) outsw(port, addr, n) -#define __ide_mm_outsl(port, addr, n) outsl(port, addr, n) +#define __ide_mm_insw(port, addr, n) insw((unsigned long) (port), addr, n) +#define __ide_mm_insl(port, addr, n) insl((unsigned long) (port), addr, n) +#define __ide_mm_outsw(port, addr, n) outsw((unsigned long) (port), addr, n) +#define __ide_mm_outsl(port, addr, n) outsl((unsigned long) (port), addr, n) #endif /* __KERNEL__ */ diff --git a/include/asm-frv/page.h b/include/asm-frv/page.h index 4feba567e7fd..b8221b611b5c 100644 --- a/include/asm-frv/page.h +++ b/include/asm-frv/page.h @@ -47,8 +47,8 @@ typedef struct { unsigned long pgprot; } pgprot_t; #define devmem_is_allowed(pfn) 1 -#define __pa(vaddr) virt_to_phys((void *) vaddr) -#define __va(paddr) phys_to_virt((unsigned long) paddr) +#define __pa(vaddr) virt_to_phys((void *) (unsigned long) (vaddr)) +#define __va(paddr) phys_to_virt((unsigned long) (paddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) diff --git a/include/asm-frv/semaphore.h b/include/asm-frv/semaphore.h index b18396288df1..907c5c3643cc 100644 --- a/include/asm-frv/semaphore.h +++ b/include/asm-frv/semaphore.h @@ -20,7 +20,7 @@ #include <linux/spinlock.h> #include <linux/rwsem.h> -#define SEMAPHORE_DEBUG WAITQUEUE_DEBUG +#define SEMAPHORE_DEBUG 0 /* * the semaphore definition diff --git a/include/asm-frv/thread_info.h b/include/asm-frv/thread_info.h index c8cba7836f0d..60f6b2aee76d 100644 --- a/include/asm-frv/thread_info.h +++ b/include/asm-frv/thread_info.h @@ -58,7 +58,7 @@ struct thread_info { #endif -#define PREEMPT_ACTIVE 0x4000000 +#define PREEMPT_ACTIVE 0x10000000 /* * macros/functions for gaining access to the thread information structure diff --git a/include/asm-m32r/atomic.h b/include/asm-m32r/atomic.h index bfff69a49936..ef1fb8ea4726 100644 --- a/include/asm-m32r/atomic.h +++ b/include/asm-m32r/atomic.h @@ -242,6 +242,27 @@ static __inline__ int atomic_dec_return(atomic_t *v) */ #define atomic_add_negative(i,v) (atomic_add_return((i), (v)) < 0) +#define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n))) + +/** + * atomic_add_unless - add unless the number is a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as it was not @u. + * Returns non-zero if @v was not @u, and zero otherwise. + */ +#define atomic_add_unless(v, a, u) \ +({ \ + int c, old; \ + c = atomic_read(v); \ + while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \ + c = old; \ + c != (u); \ +}) +#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) + static __inline__ void atomic_clear_mask(unsigned long mask, atomic_t *addr) { unsigned long flags; diff --git a/include/asm-m32r/ide.h b/include/asm-m32r/ide.h index 194393bd8beb..f7aa96970d18 100644 --- a/include/asm-m32r/ide.h +++ b/include/asm-m32r/ide.h @@ -25,18 +25,21 @@ # endif #endif -#if defined(CONFIG_PLAT_M32700UT) -#include <asm/irq.h> -#include <asm/m32700ut/m32700ut_pld.h> -#endif +#include <asm/m32r.h> + #define IDE_ARCH_OBSOLETE_DEFAULTS static __inline__ int ide_default_irq(unsigned long base) { switch (base) { -#if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_MAPPI2) || defined(CONFIG_PLAT_MAPPI3) +#if defined(CONFIG_PLAT_M32700UT) || defined(CONFIG_PLAT_MAPPI2) + case 0x1f0: return PLD_IRQ_CFIREQ; + default: + return 0; +#elif defined(CONFIG_PLAT_MAPPI3) case 0x1f0: return PLD_IRQ_CFIREQ; + case 0x170: return PLD_IRQ_IDEIREQ; default: return 0; #else diff --git a/include/asm-m32r/mappi3/mappi3_pld.h b/include/asm-m32r/mappi3/mappi3_pld.h index 3f1551f7f01f..1d3c25d61bcb 100644 --- a/include/asm-m32r/mappi3/mappi3_pld.h +++ b/include/asm-m32r/mappi3/mappi3_pld.h @@ -59,7 +59,7 @@ #define M32R_IRQ_I2C (28) /* I2C-BUS */ #define PLD_IRQ_CFIREQ (6) /* INT5 CFC Card Interrupt */ #define PLD_IRQ_CFC_INSERT (7) /* INT6 CFC Card Insert */ -#define PLD_IRQ_CFC_EJECT (8) /* INT7 CFC Card Eject */ +#define PLD_IRQ_IDEIREQ (8) /* INT7 IDE Interrupt */ #define PLD_IRQ_MMCCARD (43) /* MMC Card Insert */ #define PLD_IRQ_MMCIRQ (44) /* MMC Transfer Done */ diff --git a/include/asm-m32r/system.h b/include/asm-m32r/system.h index 73348c3f858b..5eee832b73a0 100644 --- a/include/asm-m32r/system.h +++ b/include/asm-m32r/system.h @@ -11,6 +11,7 @@ */ #include <linux/config.h> +#include <asm/assembler.h> #ifdef __KERNEL__ @@ -132,8 +133,6 @@ static inline void local_irq_disable(void) !(flags & 0x40); \ }) -#endif /* __KERNEL__ */ - #define nop() __asm__ __volatile__ ("nop" : : ) #define xchg(ptr,x) \ @@ -213,6 +212,67 @@ static __inline__ unsigned long __xchg(unsigned long x, volatile void * ptr, return (tmp); } +#define __HAVE_ARCH_CMPXCHG 1 + +static __inline__ unsigned long +__cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new) +{ + unsigned long flags; + unsigned int retval; + + local_irq_save(flags); + __asm__ __volatile__ ( + DCACHE_CLEAR("%0", "r4", "%1") + M32R_LOCK" %0, @%1; \n" + " bne %0, %2, 1f; \n" + M32R_UNLOCK" %3, @%1; \n" + " bra 2f; \n" + " .fillinsn \n" + "1:" + M32R_UNLOCK" %2, @%1; \n" + " .fillinsn \n" + "2:" + : "=&r" (retval) + : "r" (p), "r" (old), "r" (new) + : "cbit", "memory" +#ifdef CONFIG_CHIP_M32700_TS1 + , "r4" +#endif /* CONFIG_CHIP_M32700_TS1 */ + ); + local_irq_restore(flags); + + return retval; +} + +/* This function doesn't exist, so you'll get a linker error + if something tries to do an invalid cmpxchg(). */ +extern void __cmpxchg_called_with_bad_pointer(void); + +static __inline__ unsigned long +__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size) +{ + switch (size) { + case 4: + return __cmpxchg_u32(ptr, old, new); +#if 0 /* we don't have __cmpxchg_u64 */ + case 8: + return __cmpxchg_u64(ptr, old, new); +#endif /* 0 */ + } + __cmpxchg_called_with_bad_pointer(); + return old; +} + +#define cmpxchg(ptr,o,n) \ + ({ \ + __typeof__(*(ptr)) _o_ = (o); \ + __typeof__(*(ptr)) _n_ = (n); \ + (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_, \ + (unsigned long)_n_, sizeof(*(ptr))); \ + }) + +#endif /* __KERNEL__ */ + /* * Memory barrier. * diff --git a/include/asm-powerpc/iommu.h b/include/asm-powerpc/iommu.h index 6a35e6570ccd..f89f06050893 100644 --- a/include/asm-powerpc/iommu.h +++ b/include/asm-powerpc/iommu.h @@ -1,7 +1,7 @@ /* * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation * Rewrite, cleanup: - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/include/asm-powerpc/page_64.h b/include/asm-powerpc/page_64.h index 58a3dd9a79ec..6642c0125001 100644 --- a/include/asm-powerpc/page_64.h +++ b/include/asm-powerpc/page_64.h @@ -103,8 +103,9 @@ extern unsigned int HPAGE_SHIFT; #define HTLB_AREA_SIZE (1UL << HTLB_AREA_SHIFT) #define GET_HTLB_AREA(x) ((x) >> HTLB_AREA_SHIFT) -#define LOW_ESID_MASK(addr, len) (((1U << (GET_ESID(addr+len-1)+1)) \ - - (1U << GET_ESID(addr))) & 0xffff) +#define LOW_ESID_MASK(addr, len) \ + (((1U << (GET_ESID(min((addr)+(len)-1, 0x100000000UL))+1)) \ + - (1U << GET_ESID(min((addr), 0x100000000UL)))) & 0xffff) #define HTLB_AREA_MASK(addr, len) (((1U << (GET_HTLB_AREA(addr+len-1)+1)) \ - (1U << GET_HTLB_AREA(addr))) & 0xffff) @@ -113,17 +114,21 @@ extern unsigned int HPAGE_SHIFT; #define ARCH_HAS_SETCLEAR_HUGE_PTE #define touches_hugepage_low_range(mm, addr, len) \ - (LOW_ESID_MASK((addr), (len)) & (mm)->context.low_htlb_areas) + (((addr) < 0x100000000UL) \ + && (LOW_ESID_MASK((addr), (len)) & (mm)->context.low_htlb_areas)) #define touches_hugepage_high_range(mm, addr, len) \ - (HTLB_AREA_MASK((addr), (len)) & (mm)->context.high_htlb_areas) + ((((addr) + (len)) > 0x100000000UL) \ + && (HTLB_AREA_MASK((addr), (len)) & (mm)->context.high_htlb_areas)) #define __within_hugepage_low_range(addr, len, segmask) \ - ((LOW_ESID_MASK((addr), (len)) | (segmask)) == (segmask)) + ( (((addr)+(len)) <= 0x100000000UL) \ + && ((LOW_ESID_MASK((addr), (len)) | (segmask)) == (segmask))) #define within_hugepage_low_range(addr, len) \ __within_hugepage_low_range((addr), (len), \ current->mm->context.low_htlb_areas) #define __within_hugepage_high_range(addr, len, zonemask) \ - ((HTLB_AREA_MASK((addr), (len)) | (zonemask)) == (zonemask)) + ( ((addr) >= 0x100000000UL) \ + && ((HTLB_AREA_MASK((addr), (len)) | (zonemask)) == (zonemask))) #define within_hugepage_high_range(addr, len) \ __within_hugepage_high_range((addr), (len), \ current->mm->context.high_htlb_areas) diff --git a/include/asm-powerpc/tce.h b/include/asm-powerpc/tce.h index d099d5200f9b..980a094fd5a7 100644 --- a/include/asm-powerpc/tce.h +++ b/include/asm-powerpc/tce.h @@ -1,7 +1,7 @@ /* * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation * Rewrite, cleanup: - * Copyright (C) 2004 Olof Johansson <olof@austin.ibm.com>, IBM Corporation + * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/include/asm-sparc64/pgtable.h b/include/asm-sparc64/pgtable.h index 9a02879b235d..f0a9b44d3eb5 100644 --- a/include/asm-sparc64/pgtable.h +++ b/include/asm-sparc64/pgtable.h @@ -348,16 +348,6 @@ extern unsigned long find_ecache_flush_span(unsigned long size); struct vm_area_struct; extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t); -/* Make a non-present pseudo-TTE. */ -static inline pte_t mk_pte_io(unsigned long page, pgprot_t prot, int space) -{ - pte_t pte; - pte_val(pte) = (((page) | pgprot_val(prot) | _PAGE_E) & - ~(unsigned long)_PAGE_CACHE); - pte_val(pte) |= (((unsigned long)space) << 32); - return pte; -} - /* Encode and de-code a swap entry */ #define __swp_type(entry) (((entry).val >> PAGE_SHIFT) & 0xffUL) #define __swp_offset(entry) ((entry).val >> (PAGE_SHIFT + 8UL)) diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 43c44530ef9d..0ed1d4853c69 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -65,10 +65,9 @@ extern struct sysdev_class cpu_sysdev_class; #ifdef CONFIG_HOTPLUG_CPU /* Stop CPUs going up and down. */ -extern struct semaphore cpucontrol; -#define lock_cpu_hotplug() down(&cpucontrol) -#define unlock_cpu_hotplug() up(&cpucontrol) -#define lock_cpu_hotplug_interruptible() down_interruptible(&cpucontrol) +extern void lock_cpu_hotplug(void); +extern void unlock_cpu_hotplug(void); +extern int lock_cpu_hotplug_interruptible(void); #define hotcpu_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ { .notifier_call = fn, .priority = pri }; \ diff --git a/include/linux/memory.h b/include/linux/memory.h index 9a424383e6c6..dc4081b6f161 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -85,7 +85,6 @@ struct notifier_block; extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -extern struct sysdev_class memory_sysdev_class; #endif /* CONFIG_MEMORY_HOTPLUG */ #define hotplug_memory_notifier(fn, pri) { \ diff --git a/include/linux/mm.h b/include/linux/mm.h index f0cdfd18db55..6a75a7a78bf1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -145,7 +145,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_GROWSUP 0x00000200 #define VM_SHM 0x00000000 /* Means nothing: delete it later */ -#define VM_UNPAGED 0x00000400 /* Pages managed without map count */ +#define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_EXECUTABLE 0x00001000 @@ -664,6 +664,7 @@ struct zap_details { unsigned long truncate_count; /* Compare vm_truncate_count */ }; +struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); unsigned long unmap_vmas(struct mmu_gather **tlb, @@ -953,7 +954,7 @@ unsigned long vmalloc_to_pfn(void *addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); -struct page *follow_page(struct mm_struct *, unsigned long address, +struct page *follow_page(struct vm_area_struct *, unsigned long address, unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 35b30e6c8cf8..33261f1d2239 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -89,7 +89,7 @@ static inline void page_dup_rmap(struct page *page) /* * Called from mm/vmscan.c to handle paging out */ -int page_referenced(struct page *, int is_locked, int ignore_token); +int page_referenced(struct page *, int is_locked); int try_to_unmap(struct page *); /* @@ -109,7 +109,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); #define anon_vma_prepare(vma) (0) #define anon_vma_link(vma) do {} while (0) -#define page_referenced(page,l,i) TestClearPageReferenced(page) +#define page_referenced(page,l) TestClearPageReferenced(page) #define try_to_unmap(page) SWAP_FAIL #endif /* CONFIG_MMU */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 2038bd27b041..b0ad6f30679e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -908,7 +908,6 @@ do { if (atomic_dec_and_test(&(tsk)->usage)) __put_task_struct(tsk); } while(0) #define PF_SYNCWRITE 0x00200000 /* I am doing a sync write */ #define PF_BORROWED_MM 0x00400000 /* I am a kthread doing use_mm */ #define PF_RANDOMIZE 0x00800000 /* randomize virtual address space */ -#define PF_HOTPLUG_CPU 0x01000000 /* Currently performing CPU hotplug */ /* * Only the _current_ task can read/write to tsk->flags, but other diff --git a/include/linux/swap.h b/include/linux/swap.h index 20c975642cab..508668f840b6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -239,6 +239,11 @@ static inline void put_swap_token(struct mm_struct *mm) __put_swap_token(mm); } +static inline void disable_swap_token(void) +{ + put_swap_token(swap_token_mm); +} + #else /* CONFIG_SWAP */ #define total_swap_pages 0 @@ -283,6 +288,7 @@ static inline swp_entry_t get_swap_page(void) #define put_swap_token(x) do { } while(0) #define grab_swap_token() do { } while(0) #define has_swap_token(x) 0 +#define disable_swap_token() do { } while(0) #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ diff --git a/kernel/cpu.c b/kernel/cpu.c index d61ba88f34e5..e882c6babf41 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -16,47 +16,76 @@ #include <asm/semaphore.h> /* This protects CPUs going up and down... */ -DECLARE_MUTEX(cpucontrol); -EXPORT_SYMBOL_GPL(cpucontrol); +static DECLARE_MUTEX(cpucontrol); static struct notifier_block *cpu_chain; -/* - * Used to check by callers if they need to acquire the cpucontrol - * or not to protect a cpu from being removed. Its sometimes required to - * call these functions both for normal operations, and in response to - * a cpu being added/removed. If the context of the call is in the same - * thread context as a CPU hotplug thread, we dont need to take the lock - * since its already protected - * check drivers/cpufreq/cpufreq.c for its usage - Ashok Raj - */ +#ifdef CONFIG_HOTPLUG_CPU +static struct task_struct *lock_cpu_hotplug_owner; +static int lock_cpu_hotplug_depth; -int current_in_cpu_hotplug(void) +static int __lock_cpu_hotplug(int interruptible) { - return (current->flags & PF_HOTPLUG_CPU); + int ret = 0; + + if (lock_cpu_hotplug_owner != current) { + if (interruptible) + ret = down_interruptible(&cpucontrol); + else + down(&cpucontrol); + } + + /* + * Set only if we succeed in locking + */ + if (!ret) { + lock_cpu_hotplug_depth++; + lock_cpu_hotplug_owner = current; + } + + return ret; } -EXPORT_SYMBOL_GPL(current_in_cpu_hotplug); +void lock_cpu_hotplug(void) +{ + __lock_cpu_hotplug(0); +} +EXPORT_SYMBOL_GPL(lock_cpu_hotplug); +void unlock_cpu_hotplug(void) +{ + if (--lock_cpu_hotplug_depth == 0) { + lock_cpu_hotplug_owner = NULL; + up(&cpucontrol); + } +} +EXPORT_SYMBOL_GPL(unlock_cpu_hotplug); + +int lock_cpu_hotplug_interruptible(void) +{ + return __lock_cpu_hotplug(1); +} +EXPORT_SYMBOL_GPL(lock_cpu_hotplug_interruptible); +#endif /* CONFIG_HOTPLUG_CPU */ /* Need to know about CPUs going up/down? */ int register_cpu_notifier(struct notifier_block *nb) { int ret; - if ((ret = down_interruptible(&cpucontrol)) != 0) + if ((ret = lock_cpu_hotplug_interruptible()) != 0) return ret; ret = notifier_chain_register(&cpu_chain, nb); - up(&cpucontrol); + unlock_cpu_hotplug(); return ret; } EXPORT_SYMBOL(register_cpu_notifier); void unregister_cpu_notifier(struct notifier_block *nb) { - down(&cpucontrol); + lock_cpu_hotplug(); notifier_chain_unregister(&cpu_chain, nb); - up(&cpucontrol); + unlock_cpu_hotplug(); } EXPORT_SYMBOL(unregister_cpu_notifier); @@ -112,13 +141,6 @@ int cpu_down(unsigned int cpu) goto out; } - /* - * Leave a trace in current->flags indicating we are already in - * process of performing CPU hotplug. Callers can check if cpucontrol - * is already acquired by current thread, and if so not cause - * a dead lock by not acquiring the lock - */ - current->flags |= PF_HOTPLUG_CPU; err = notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE, (void *)(long)cpu); if (err == NOTIFY_BAD) { @@ -171,7 +193,6 @@ out_thread: out_allowed: set_cpus_allowed(current, old_allowed); out: - current->flags &= ~PF_HOTPLUG_CPU; unlock_cpu_hotplug(); return err; } @@ -182,7 +203,7 @@ int __devinit cpu_up(unsigned int cpu) int ret; void *hcpu = (void *)(long)cpu; - if ((ret = down_interruptible(&cpucontrol)) != 0) + if ((ret = lock_cpu_hotplug_interruptible()) != 0) return ret; if (cpu_online(cpu) || !cpu_present(cpu)) { @@ -190,11 +211,6 @@ int __devinit cpu_up(unsigned int cpu) goto out; } - /* - * Leave a trace in current->flags indicating we are already in - * process of performing CPU hotplug. - */ - current->flags |= PF_HOTPLUG_CPU; ret = notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu); if (ret == NOTIFY_BAD) { printk("%s: attempt to bring up CPU %u failed\n", @@ -217,7 +233,6 @@ out_notify: if (ret != 0) notifier_call_chain(&cpu_chain, CPU_UP_CANCELED, hcpu); out: - current->flags &= ~PF_HOTPLUG_CPU; - up(&cpucontrol); + unlock_cpu_hotplug(); return ret; } diff --git a/kernel/fork.c b/kernel/fork.c index 1c1cf8dc396b..fb8572a42297 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1124,8 +1124,6 @@ static task_t *copy_process(unsigned long clone_flags, if (unlikely(p->ptrace & PT_PTRACED)) __ptrace_link(p, current->parent); - cpuset_fork(p); - attach_pid(p, PIDTYPE_PID, p->pid); attach_pid(p, PIDTYPE_TGID, p->tgid); if (thread_group_leader(p)) { @@ -1135,13 +1133,14 @@ static task_t *copy_process(unsigned long clone_flags, __get_cpu_var(process_counts)++; } - proc_fork_connector(p); if (!current->signal->tty && p->signal->tty) p->signal->tty = NULL; nr_threads++; total_forks++; write_unlock_irq(&tasklist_lock); + proc_fork_connector(p); + cpuset_fork(p); retval = 0; fork_out: diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 84af54c39e1b..cae4f5728997 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -36,7 +36,7 @@ timespec_to_sample(clockid_t which_clock, const struct timespec *tp) union cpu_time_count ret; ret.sched = 0; /* high half always zero when .cpu used */ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - ret.sched = tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; + ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; } else { ret.cpu = timespec_to_cputime(tp); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 42df83d7fad2..2bd5aee1c736 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -102,7 +102,7 @@ int fastcall queue_work(struct workqueue_struct *wq, struct work_struct *work) if (!test_and_set_bit(0, &work->pending)) { if (unlikely(is_single_threaded(wq))) - cpu = 0; + cpu = any_online_cpu(cpu_online_map); BUG_ON(!list_empty(&work->entry)); __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work); ret = 1; @@ -118,7 +118,7 @@ static void delayed_work_timer_fn(unsigned long __data) int cpu = smp_processor_id(); if (unlikely(is_single_threaded(wq))) - cpu = 0; + cpu = any_online_cpu(cpu_online_map); __queue_work(per_cpu_ptr(wq->cpu_wq, cpu), work); } @@ -266,8 +266,8 @@ void fastcall flush_workqueue(struct workqueue_struct *wq) might_sleep(); if (is_single_threaded(wq)) { - /* Always use cpu 0's area. */ - flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, 0)); + /* Always use first cpu's area. */ + flush_cpu_workqueue(per_cpu_ptr(wq->cpu_wq, any_online_cpu(cpu_online_map))); } else { int cpu; @@ -320,7 +320,7 @@ struct workqueue_struct *__create_workqueue(const char *name, lock_cpu_hotplug(); if (singlethread) { INIT_LIST_HEAD(&wq->list); - p = create_workqueue_thread(wq, 0); + p = create_workqueue_thread(wq, any_online_cpu(cpu_online_map)); if (!p) destroy = 1; else @@ -374,7 +374,7 @@ void destroy_workqueue(struct workqueue_struct *wq) /* We don't need the distraction of CPUs appearing and vanishing. */ lock_cpu_hotplug(); if (is_single_threaded(wq)) - cleanup_workqueue_thread(wq, 0); + cleanup_workqueue_thread(wq, any_online_cpu(cpu_online_map)); else { for_each_online_cpu(cpu) cleanup_workqueue_thread(wq, cpu); diff --git a/lib/genalloc.c b/lib/genalloc.c index d6d30d2e7166..9ce0a6a3b85a 100644 --- a/lib/genalloc.c +++ b/lib/genalloc.c @@ -95,12 +95,10 @@ unsigned long gen_pool_alloc(struct gen_pool *poolp, int size) if (size > max_chunk_size) return 0; - i = 0; - size = max(size, 1 << ALLOC_MIN_SHIFT); - s = roundup_pow_of_two(size); - - j = i; + i = fls(size - 1); + s = 1 << i; + j = i -= ALLOC_MIN_SHIFT; spin_lock_irqsave(&poolp->lock, flags); while (!h[j].next) { @@ -153,10 +151,10 @@ void gen_pool_free(struct gen_pool *poolp, unsigned long ptr, int size) if (size > max_chunk_size) return; - i = 0; - size = max(size, 1 << ALLOC_MIN_SHIFT); - s = roundup_pow_of_two(size); + i = fls(size - 1); + s = 1 << i; + i -= ALLOC_MIN_SHIFT; a = ptr; diff --git a/mm/fremap.c b/mm/fremap.c index 007cbad9331e..f851775e09c2 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -27,24 +27,20 @@ static int zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page = NULL; if (pte_present(pte)) { - unsigned long pfn = pte_pfn(pte); - flush_cache_page(vma, addr, pfn); + flush_cache_page(vma, addr, pte_pfn(pte)); pte = ptep_clear_flush(vma, addr, ptep); - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, pte, addr); - goto out; + page = vm_normal_page(vma, addr, pte); + if (page) { + if (pte_dirty(pte)) + set_page_dirty(page); + page_remove_rmap(page); + page_cache_release(page); } - page = pfn_to_page(pfn); - if (pte_dirty(pte)) - set_page_dirty(page); - page_remove_rmap(page); - page_cache_release(page); } else { if (!pte_file(pte)) free_swap_and_cache(pte_to_swp_entry(pte)); pte_clear(mm, addr, ptep); } -out: return !!page; } @@ -65,8 +61,6 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_t pte_val; spinlock_t *ptl; - BUG_ON(vma->vm_flags & VM_UNPAGED); - pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (!pud) @@ -122,8 +116,6 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, pte_t pte_val; spinlock_t *ptl; - BUG_ON(vma->vm_flags & VM_UNPAGED); - pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (!pud) diff --git a/mm/madvise.c b/mm/madvise.c index 328a3bcce527..2b7cf0400a21 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -126,7 +126,7 @@ static long madvise_dontneed(struct vm_area_struct * vma, unsigned long start, unsigned long end) { *prev = vma; - if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_UNPAGED)) + if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) return -EINVAL; if (unlikely(vma->vm_flags & VM_NONLINEAR)) { diff --git a/mm/memory.c b/mm/memory.c index d1f46f4e4c8a..9ab206b829a2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -333,9 +333,9 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) } /* - * This function is called to print an error when a pte in a - * !VM_UNPAGED region is found pointing to an invalid pfn (which - * is an error. + * This function is called to print an error when a bad pte + * is found. For example, we might have a PFN-mapped pte in + * a region that doesn't allow it. * * The calling function must still handle the error. */ @@ -350,19 +350,56 @@ void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr) } /* - * page_is_anon applies strict checks for an anonymous page belonging to - * this vma at this address. It is used on VM_UNPAGED vmas, which are - * usually populated with shared originals (which must not be counted), - * but occasionally contain private COWed copies (when !VM_SHARED, or - * perhaps via ptrace when VM_SHARED). An mmap of /dev/mem might window - * free pages, pages from other processes, or from other parts of this: - * it's tricky, but try not to be deceived by foreign anonymous pages. + * This function gets the "struct page" associated with a pte. + * + * NOTE! Some mappings do not have "struct pages". A raw PFN mapping + * will have each page table entry just pointing to a raw page frame + * number, and as far as the VM layer is concerned, those do not have + * pages associated with them - even if the PFN might point to memory + * that otherwise is perfectly fine and has a "struct page". + * + * The way we recognize those mappings is through the rules set up + * by "remap_pfn_range()": the vma will have the VM_PFNMAP bit set, + * and the vm_pgoff will point to the first PFN mapped: thus every + * page that is a raw mapping will always honor the rule + * + * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) + * + * and if that isn't true, the page has been COW'ed (in which case it + * _does_ have a "struct page" associated with it even if it is in a + * VM_PFNMAP range). */ -static inline int page_is_anon(struct page *page, - struct vm_area_struct *vma, unsigned long addr) +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - return page && PageAnon(page) && page_mapped(page) && - page_address_in_vma(page, vma) == addr; + unsigned long pfn = pte_pfn(pte); + + if (vma->vm_flags & VM_PFNMAP) { + unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + } + + /* + * Add some anal sanity checks for now. Eventually, + * we should just do "return pfn_to_page(pfn)", but + * in the meantime we check that we get a valid pfn, + * and that the resulting page looks ok. + * + * Remove this test eventually! + */ + if (unlikely(!pfn_valid(pfn))) { + print_bad_pte(vma, pte, addr); + return NULL; + } + + /* + * NOTE! We still have PageReserved() pages in the page + * tables. + * + * The PAGE_ZERO() pages and various VDSO mappings can + * cause them to exist. + */ + return pfn_to_page(pfn); } /* @@ -379,7 +416,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; - unsigned long pfn; /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { @@ -397,22 +433,6 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_set_pte; } - pfn = pte_pfn(pte); - page = pfn_valid(pfn)? pfn_to_page(pfn): NULL; - - if (unlikely(vm_flags & VM_UNPAGED)) - if (!page_is_anon(page, vma, addr)) - goto out_set_pte; - - /* - * If the pte points outside of valid memory but - * the region is not VM_UNPAGED, we have a problem. - */ - if (unlikely(!page)) { - print_bad_pte(vma, pte, addr); - goto out_set_pte; /* try to do something sane */ - } - /* * If it's a COW mapping, write protect it both * in the parent and the child @@ -429,9 +449,13 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (vm_flags & VM_SHARED) pte = pte_mkclean(pte); pte = pte_mkold(pte); - get_page(page); - page_dup_rmap(page); - rss[!!PageAnon(page)]++; + + page = vm_normal_page(vma, addr, pte); + if (page) { + get_page(page); + page_dup_rmap(page); + rss[!!PageAnon(page)]++; + } out_set_pte: set_pte_at(dst_mm, addr, dst_pte, pte); @@ -543,7 +567,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_UNPAGED))) { + if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP))) { if (!vma->anon_vma) return 0; } @@ -584,19 +608,10 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, } if (pte_present(ptent)) { struct page *page; - unsigned long pfn; (*zap_work) -= PAGE_SIZE; - pfn = pte_pfn(ptent); - page = pfn_valid(pfn)? pfn_to_page(pfn): NULL; - - if (unlikely(vma->vm_flags & VM_UNPAGED)) { - if (!page_is_anon(page, vma, addr)) - page = NULL; - } else if (unlikely(!page)) - print_bad_pte(vma, ptent, addr); - + page = vm_normal_page(vma, addr, ptent); if (unlikely(details) && page) { /* * unmap_shared_mapping_pages() wants to @@ -852,7 +867,7 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, /* * Do a quick page-table lookup for a single page. */ -struct page *follow_page(struct mm_struct *mm, unsigned long address, +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int flags) { pgd_t *pgd; @@ -860,8 +875,8 @@ struct page *follow_page(struct mm_struct *mm, unsigned long address, pmd_t *pmd; pte_t *ptep, pte; spinlock_t *ptl; - unsigned long pfn; struct page *page; + struct mm_struct *mm = vma->vm_mm; page = follow_huge_addr(mm, address, flags & FOLL_WRITE); if (!IS_ERR(page)) { @@ -897,11 +912,10 @@ struct page *follow_page(struct mm_struct *mm, unsigned long address, goto unlock; if ((flags & FOLL_WRITE) && !pte_write(pte)) goto unlock; - pfn = pte_pfn(pte); - if (!pfn_valid(pfn)) + page = vm_normal_page(vma, address, pte); + if (unlikely(!page)) goto unlock; - page = pfn_to_page(pfn); if (flags & FOLL_GET) get_page(page); if (flags & FOLL_TOUCH) { @@ -974,8 +988,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, return i ? : -EFAULT; } if (pages) { - pages[i] = pte_page(*pte); - get_page(pages[i]); + struct page *page = vm_normal_page(vma, start, *pte); + pages[i] = page; + if (page) + get_page(page); } pte_unmap(pte); if (vmas) @@ -1010,7 +1026,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, foll_flags |= FOLL_WRITE; cond_resched(); - while (!(page = follow_page(mm, start, foll_flags))) { + while (!(page = follow_page(vma, start, foll_flags))) { int ret; ret = __handle_mm_fault(mm, vma, start, foll_flags & FOLL_WRITE); @@ -1214,11 +1230,12 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * in 2.6 the LRU scan won't even find its pages, so this * flag means no more than count its pages in reserved_vm, * and omit it from core dump, even when VM_IO turned off. - * VM_UNPAGED tells the core MM not to "manage" these pages - * (e.g. refcount, mapcount, try to swap them out): in - * particular, zap_pte_range does not try to free them. + * VM_PFNMAP tells the core MM that the base pages are just + * raw PFN mappings, and do not have a "struct page" associated + * with them. */ - vma->vm_flags |= VM_IO | VM_RESERVED | VM_UNPAGED; + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + vma->vm_pgoff = pfn; BUG_ON(addr >= end); pfn -= addr >> PAGE_SHIFT; @@ -1273,6 +1290,26 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } +static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va) +{ + /* + * If the source page was a PFN mapping, we don't have + * a "struct page" for it. We do a best-effort copy by + * just copying from the original user address. If that + * fails, we just zero-fill it. Live with it. + */ + if (unlikely(!src)) { + void *kaddr = kmap_atomic(dst, KM_USER0); + unsigned long left = __copy_from_user_inatomic(kaddr, (void __user *)va, PAGE_SIZE); + if (left) + memset(kaddr, 0, PAGE_SIZE); + kunmap_atomic(kaddr, KM_USER0); + return; + + } + copy_user_highpage(dst, src, va); +} + /* * This routine handles present pages, when users try to write * to a shared page. It is done by copying the page to a new address @@ -1296,28 +1333,13 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, spinlock_t *ptl, pte_t orig_pte) { struct page *old_page, *src_page, *new_page; - unsigned long pfn = pte_pfn(orig_pte); pte_t entry; int ret = VM_FAULT_MINOR; - if (unlikely(!pfn_valid(pfn))) { - /* - * Page table corrupted: show pte and kill process. - * Or it's an attempt to COW an out-of-map VM_UNPAGED - * entry, which copy_user_highpage does not support. - */ - print_bad_pte(vma, orig_pte, address); - ret = VM_FAULT_OOM; - goto unlock; - } - old_page = pfn_to_page(pfn); + old_page = vm_normal_page(vma, address, orig_pte); src_page = old_page; - - if (unlikely(vma->vm_flags & VM_UNPAGED)) - if (!page_is_anon(old_page, vma, address)) { - old_page = NULL; - goto gotten; - } + if (!old_page) + goto gotten; if (PageAnon(old_page) && !TestSetPageLocked(old_page)) { int reuse = can_share_swap_page(old_page); @@ -1351,7 +1373,7 @@ gotten: new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); if (!new_page) goto oom; - copy_user_highpage(new_page, src_page, address); + cow_user_page(new_page, src_page, address); } /* @@ -1812,16 +1834,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, spinlock_t *ptl; pte_t entry; - /* - * A VM_UNPAGED vma will normally be filled with present ptes - * by remap_pfn_range, and never arrive here; but it might have - * holes, or if !VM_DONTEXPAND, mremap might have expanded it. - * It's weird enough handling anon pages in unpaged vmas, we do - * not want to worry about ZERO_PAGEs too (it may or may not - * matter if their counts wrap): just give them anon pages. - */ - - if (write_access || (vma->vm_flags & VM_UNPAGED)) { + if (write_access) { /* Allocate our own private page. */ pte_unmap(page_table); @@ -1896,8 +1909,6 @@ static int do_no_page(struct mm_struct *mm, struct vm_area_struct *vma, int anon = 0; pte_unmap(page_table); - BUG_ON(vma->vm_flags & VM_UNPAGED); - if (vma->vm_file) { mapping = vma->vm_file->f_mapping; sequence = mapping->truncate_count; @@ -1930,7 +1941,7 @@ retry: page = alloc_page_vma(GFP_HIGHUSER, vma, address); if (!page) goto oom; - copy_user_highpage(page, new_page, address); + cow_user_page(page, new_page, address); page_cache_release(new_page); new_page = page; anon = 1; @@ -2149,6 +2160,12 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) spin_unlock(&mm->page_table_lock); return 0; } +#else +/* Workaround for gcc 2.96 */ +int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + return 0; +} #endif /* __PAGETABLE_PUD_FOLDED */ #ifndef __PAGETABLE_PMD_FOLDED @@ -2177,6 +2194,12 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) spin_unlock(&mm->page_table_lock); return 0; } +#else +/* Workaround for gcc 2.96 */ +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) +{ + return 0; +} #endif /* __PAGETABLE_PMD_FOLDED */ int make_pages_present(unsigned long addr, unsigned long end) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 5609a31bdf22..bec88c81244e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -189,17 +189,15 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { - unsigned long pfn; + struct page *page; unsigned int nid; if (!pte_present(*pte)) continue; - pfn = pte_pfn(*pte); - if (!pfn_valid(pfn)) { - print_bad_pte(vma, *pte, addr); + page = vm_normal_page(vma, addr, *pte); + if (!page) continue; - } - nid = pfn_to_nid(pfn); + nid = page_to_nid(page); if (!node_isset(nid, *nodes)) break; } while (pte++, addr += PAGE_SIZE, addr != end); @@ -269,8 +267,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, first = find_vma(mm, start); if (!first) return ERR_PTR(-EFAULT); - if (first->vm_flags & VM_UNPAGED) - return ERR_PTR(-EACCES); prev = NULL; for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) { if (!vma->vm_next && vma->vm_end < end) diff --git a/mm/msync.c b/mm/msync.c index b3f4caf3010b..1b5b6f662dcf 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -27,7 +27,6 @@ static void msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd, again: pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { - unsigned long pfn; struct page *page; if (progress >= 64) { @@ -40,13 +39,9 @@ again: continue; if (!pte_maybe_dirty(*pte)) continue; - pfn = pte_pfn(*pte); - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, *pte, addr); + page = vm_normal_page(vma, addr, *pte); + if (!page) continue; - } - page = pfn_to_page(pfn); - if (ptep_clear_flush_dirty(vma, addr, pte) || page_test_and_clear_dirty(page)) set_page_dirty(page); @@ -97,9 +92,8 @@ static void msync_page_range(struct vm_area_struct *vma, /* For hugepages we can't go walking the page table normally, * but that's ok, hugetlbfs is memory based, so we don't need * to do anything more on an msync(). - * Can't do anything with VM_UNPAGED regions either. */ - if (vma->vm_flags & (VM_HUGETLB|VM_UNPAGED)) + if (vma->vm_flags & VM_HUGETLB) return; BUG_ON(addr >= end); diff --git a/mm/nommu.c b/mm/nommu.c index 6deb6ab3d6ad..c1196812876b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1045,7 +1045,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) EXPORT_SYMBOL(find_vma); -struct page *follow_page(struct mm_struct *mm, unsigned long address, +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags) { return NULL; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1731236dec35..b257720edfc8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -773,9 +773,12 @@ again: } #define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */ -#define ALLOC_HARDER 0x02 /* try to alloc harder */ -#define ALLOC_HIGH 0x04 /* __GFP_HIGH set */ -#define ALLOC_CPUSET 0x08 /* check for correct cpuset */ +#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */ +#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */ +#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */ +#define ALLOC_HARDER 0x10 /* try to alloc harder */ +#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ +#define ALLOC_CPUSET 0x40 /* check for correct cpuset */ /* * Return 1 if free pages are above 'mark'. This takes into account the order @@ -830,7 +833,14 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, continue; if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { - if (!zone_watermark_ok(*z, order, (*z)->pages_low, + unsigned long mark; + if (alloc_flags & ALLOC_WMARK_MIN) + mark = (*z)->pages_min; + else if (alloc_flags & ALLOC_WMARK_LOW) + mark = (*z)->pages_low; + else + mark = (*z)->pages_high; + if (!zone_watermark_ok(*z, order, mark, classzone_idx, alloc_flags)) continue; } @@ -871,7 +881,7 @@ restart: } page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order, - zonelist, ALLOC_CPUSET); + zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET); if (page) goto got_pg; @@ -888,7 +898,7 @@ restart: * cannot run direct reclaim, or if the caller has realtime scheduling * policy. */ - alloc_flags = 0; + alloc_flags = ALLOC_WMARK_MIN; if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait) alloc_flags |= ALLOC_HARDER; if (gfp_mask & __GFP_HIGH) @@ -959,7 +969,7 @@ rebalance: * under heavy pressure. */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order, - zonelist, ALLOC_CPUSET); + zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET); if (page) goto got_pg; diff --git a/mm/rmap.c b/mm/rmap.c index 2e034a0b89ab..491ac350048f 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -226,8 +226,6 @@ vma_address(struct page *page, struct vm_area_struct *vma) /* * At what user virtual address is page expected in vma? checking that the * page matches the vma: currently only used on anon pages, by unuse_vma; - * and by extraordinary checks on anon pages in VM_UNPAGED vmas, taking - * care that an mmap of /dev/mem might window free and foreign pages. */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { @@ -292,7 +290,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm, * repeatedly from either page_referenced_anon or page_referenced_file. */ static int page_referenced_one(struct page *page, - struct vm_area_struct *vma, unsigned int *mapcount, int ignore_token) + struct vm_area_struct *vma, unsigned int *mapcount) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -313,7 +311,7 @@ static int page_referenced_one(struct page *page, /* Pretend the page is referenced if the task has the swap token and is in the middle of a page fault. */ - if (mm != current->mm && !ignore_token && has_swap_token(mm) && + if (mm != current->mm && has_swap_token(mm) && rwsem_is_locked(&mm->mmap_sem)) referenced++; @@ -323,7 +321,7 @@ out: return referenced; } -static int page_referenced_anon(struct page *page, int ignore_token) +static int page_referenced_anon(struct page *page) { unsigned int mapcount; struct anon_vma *anon_vma; @@ -336,8 +334,7 @@ static int page_referenced_anon(struct page *page, int ignore_token) mapcount = page_mapcount(page); list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { - referenced += page_referenced_one(page, vma, &mapcount, - ignore_token); + referenced += page_referenced_one(page, vma, &mapcount); if (!mapcount) break; } @@ -356,7 +353,7 @@ static int page_referenced_anon(struct page *page, int ignore_token) * * This function is only called from page_referenced for object-based pages. */ -static int page_referenced_file(struct page *page, int ignore_token) +static int page_referenced_file(struct page *page) { unsigned int mapcount; struct address_space *mapping = page->mapping; @@ -394,8 +391,7 @@ static int page_referenced_file(struct page *page, int ignore_token) referenced++; break; } - referenced += page_referenced_one(page, vma, &mapcount, - ignore_token); + referenced += page_referenced_one(page, vma, &mapcount); if (!mapcount) break; } @@ -412,13 +408,10 @@ static int page_referenced_file(struct page *page, int ignore_token) * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ -int page_referenced(struct page *page, int is_locked, int ignore_token) +int page_referenced(struct page *page, int is_locked) { int referenced = 0; - if (!swap_token_default_timeout) - ignore_token = 1; - if (page_test_and_clear_young(page)) referenced++; @@ -427,15 +420,14 @@ int page_referenced(struct page *page, int is_locked, int ignore_token) if (page_mapped(page) && page->mapping) { if (PageAnon(page)) - referenced += page_referenced_anon(page, ignore_token); + referenced += page_referenced_anon(page); else if (is_locked) - referenced += page_referenced_file(page, ignore_token); + referenced += page_referenced_file(page); else if (TestSetPageLocked(page)) referenced++; else { if (page->mapping) - referenced += page_referenced_file(page, - ignore_token); + referenced += page_referenced_file(page); unlock_page(page); } } @@ -614,7 +606,6 @@ static void try_to_unmap_cluster(unsigned long cursor, struct page *page; unsigned long address; unsigned long end; - unsigned long pfn; address = (vma->vm_start + cursor) & CLUSTER_MASK; end = address + CLUSTER_SIZE; @@ -643,15 +634,8 @@ static void try_to_unmap_cluster(unsigned long cursor, for (; address < end; pte++, address += PAGE_SIZE) { if (!pte_present(*pte)) continue; - - pfn = pte_pfn(*pte); - if (unlikely(!pfn_valid(pfn))) { - print_bad_pte(vma, *pte, address); - continue; - } - - page = pfn_to_page(pfn); - BUG_ON(PageAnon(page)); + page = vm_normal_page(vma, address, *pte); + BUG_ON(!page || PageAnon(page)); if (ptep_clear_flush_young(vma, address, pte)) continue; diff --git a/mm/thrash.c b/mm/thrash.c index eff3c18c33a1..f4c560b4a2b7 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -57,14 +57,17 @@ void grab_swap_token(void) /* We have the token. Let others know we still need it. */ if (has_swap_token(current->mm)) { current->mm->recent_pagein = 1; + if (unlikely(!swap_token_default_timeout)) + disable_swap_token(); return; } if (time_after(jiffies, swap_token_check)) { - /* Can't get swapout protection if we exceed our RSS limit. */ - // if (current->mm->rss > current->mm->rlimit_rss) - // return; + if (!swap_token_default_timeout) { + swap_token_check = jiffies + SWAP_TOKEN_CHECK_INTERVAL; + return; + } /* ... or if we recently held the token. */ if (time_before(jiffies, current->mm->swap_token_time)) @@ -95,6 +98,7 @@ void __put_swap_token(struct mm_struct *mm) { spin_lock(&swap_token_lock); if (likely(mm == swap_token_mm)) { + mm->swap_token_time = jiffies + SWAP_TOKEN_CHECK_INTERVAL; swap_token_mm = &init_mm; swap_token_check = jiffies; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 28130541270f..b0cd81c32de6 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -201,13 +201,25 @@ static int shrink_slab(unsigned long scanned, gfp_t gfp_mask, list_for_each_entry(shrinker, &shrinker_list, list) { unsigned long long delta; unsigned long total_scan; + unsigned long max_pass = (*shrinker->shrinker)(0, gfp_mask); delta = (4 * scanned) / shrinker->seeks; - delta *= (*shrinker->shrinker)(0, gfp_mask); + delta *= max_pass; do_div(delta, lru_pages + 1); shrinker->nr += delta; - if (shrinker->nr < 0) - shrinker->nr = LONG_MAX; /* It wrapped! */ + if (shrinker->nr < 0) { + printk(KERN_ERR "%s: nr=%ld\n", + __FUNCTION__, shrinker->nr); + shrinker->nr = max_pass; + } + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (shrinker->nr > max_pass * 2) + shrinker->nr = max_pass * 2; total_scan = shrinker->nr; shrinker->nr = 0; @@ -407,7 +419,7 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc) if (PageWriteback(page)) goto keep_locked; - referenced = page_referenced(page, 1, sc->priority <= 0); + referenced = page_referenced(page, 1); /* In active use or really unfreeable? Activate it. */ if (referenced && page_mapping_inuse(page)) goto activate_locked; @@ -756,7 +768,7 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc) if (page_mapped(page)) { if (!reclaim_mapped || (total_swap_pages == 0 && PageAnon(page)) || - page_referenced(page, 0, sc->priority <= 0)) { + page_referenced(page, 0)) { list_add(&page->lru, &l_active); continue; } @@ -960,6 +972,8 @@ int try_to_free_pages(struct zone **zones, gfp_t gfp_mask) sc.nr_reclaimed = 0; sc.priority = priority; sc.swap_cluster_max = SWAP_CLUSTER_MAX; + if (!priority) + disable_swap_token(); shrink_caches(zones, &sc); shrink_slab(sc.nr_scanned, gfp_mask, lru_pages); if (reclaim_state) { @@ -1056,6 +1070,10 @@ loop_again: int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ unsigned long lru_pages = 0; + /* The swap token gets in the way of swapout... */ + if (!priority) + disable_swap_token(); + all_zones_ok = 1; if (nr_pages == 0) { @@ -1360,6 +1378,7 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) sc.nr_reclaimed = 0; /* scan at the highest priority */ sc.priority = 0; + disable_swap_token(); if (nr_pages > SWAP_CLUSTER_MAX) sc.swap_cluster_max = nr_pages; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 81e00a6c19de..e3b242daf53c 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -39,23 +39,27 @@ static kmem_cache_t *rpc_inode_cachep __read_mostly; #define RPC_UPCALL_TIMEOUT (30*HZ) static void -__rpc_purge_upcall(struct inode *inode, int err) +__rpc_purge_list(struct rpc_inode *rpci, struct list_head *head, int err) { - struct rpc_inode *rpci = RPC_I(inode); struct rpc_pipe_msg *msg; + void (*destroy_msg)(struct rpc_pipe_msg *); - while (!list_empty(&rpci->pipe)) { - msg = list_entry(rpci->pipe.next, struct rpc_pipe_msg, list); + destroy_msg = rpci->ops->destroy_msg; + while (!list_empty(head)) { + msg = list_entry(head->next, struct rpc_pipe_msg, list); list_del_init(&msg->list); msg->errno = err; - rpci->ops->destroy_msg(msg); - } - while (!list_empty(&rpci->in_upcall)) { - msg = list_entry(rpci->pipe.next, struct rpc_pipe_msg, list); - list_del_init(&msg->list); - msg->errno = err; - rpci->ops->destroy_msg(msg); + destroy_msg(msg); } +} + +static void +__rpc_purge_upcall(struct inode *inode, int err) +{ + struct rpc_inode *rpci = RPC_I(inode); + + __rpc_purge_list(rpci, &rpci->pipe, err); + __rpc_purge_list(rpci, &rpci->in_upcall, err); rpci->pipelen = 0; wake_up(&rpci->waitq); } |