diff --git a/MAINTAINERS b/MAINTAINERS index abf7f7a17ae0..767fb610963e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1618,6 +1618,13 @@ M: vandrove@vc.cvut.cz L: linux-fbdev-devel@lists.sourceforge.net S: Maintained +MEGARAID SCSI DRIVERS +P: Neela Syam Kolli +M: Neela.Kolli@engenio.com +S: linux-scsi@vger.kernel.org +W: http://megaraid.lsilogic.com +S: Maintained + MEMORY TECHNOLOGY DEVICES P: David Woodhouse M: dwmw2@infradead.org diff --git a/Makefile b/Makefile index 504ba3ceb296..be33d758c0fe 100644 --- a/Makefile +++ b/Makefile @@ -660,8 +660,10 @@ quiet_cmd_sysmap = SYSMAP # Link of vmlinux # If CONFIG_KALLSYMS is set .version is already updated # Generate System.map and verify that the content is consistent - +# Use + in front of the vmlinux_version rule to silent warning with make -j2 +# First command is ':' to allow us to use + in front of the rule define rule_vmlinux__ + : $(if $(CONFIG_KALLSYMS),,+$(call cmd,vmlinux_version)) $(call cmd,vmlinux__) diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 08e58ecd44be..0d5db5279c5c 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -89,13 +89,6 @@ SECTIONS *(.got) /* Global offset table */ } - . = ALIGN(16); - __ex_table : { /* Exception table */ - __start___ex_table = .; - *(__ex_table) - __stop___ex_table = .; - } - RODATA _etext = .; /* End of text and rodata section */ @@ -137,6 +130,14 @@ SECTIONS . = ALIGN(32); *(.data.cacheline_aligned) + /* + * The exception fixup table (might need resorting at runtime) + */ + . = ALIGN(32); + __start___ex_table = .; + *(__ex_table) + __stop___ex_table = .; + /* * and the usual data section */ diff --git a/arch/arm/mach-l7200/core.c b/arch/arm/mach-l7200/core.c index 5fd8c9f97f9a..03ed742ae2be 100644 --- a/arch/arm/mach-l7200/core.c +++ b/arch/arm/mach-l7200/core.c @@ -7,11 +7,17 @@ */ #include #include +#include +#include +#include +#include #include #include +#include #include +#include /* * IRQ base register @@ -47,6 +53,12 @@ static void l7200_unmask_irq(unsigned int irq) { IRQ_ENABLE = 1 << irq; } + +static struct irqchip l7200_irq_chip = { + .ack = l7200_mask_irq, + .mask = l7200_mask_irq, + .unmask = l7200_unmask_irq +}; static void __init l7200_init_irq(void) { @@ -56,11 +68,9 @@ static void __init l7200_init_irq(void) FIQ_ENABLECLEAR = 0xffffffff; /* clear all fast interrupt enables */ for (irq = 0; irq < NR_IRQS; irq++) { - irq_desc[irq].valid = 1; - irq_desc[irq].probe_ok = 1; - irq_desc[irq].mask_ack = l7200_mask_irq; - irq_desc[irq].mask = l7200_mask_irq; - irq_desc[irq].unmask = l7200_unmask_irq; + set_irq_chip(irq, &l7200_irq_chip); + set_irq_flags(irq, IRQF_VALID); + set_irq_handler(irq, do_level_IRQ); } init_FIQ(); diff --git a/arch/arm/mach-pxa/corgi_lcd.c b/arch/arm/mach-pxa/corgi_lcd.c index c02ef7c0f7ef..850538fadece 100644 --- a/arch/arm/mach-pxa/corgi_lcd.c +++ b/arch/arm/mach-pxa/corgi_lcd.c @@ -467,6 +467,7 @@ void corgi_put_hsync(void) { if (get_hsync_time) symbol_put(w100fb_get_hsynclen); + get_hsync_time = NULL; } void corgi_wait_hsync(void) @@ -476,20 +477,37 @@ void corgi_wait_hsync(void) #endif #ifdef CONFIG_PXA_SHARP_Cxx00 +static struct device *spitz_pxafb_dev; + +static int is_pxafb_device(struct device * dev, void * data) +{ + struct platform_device *pdev = container_of(dev, struct platform_device, dev); + + return (strncmp(pdev->name, "pxa2xx-fb", 9) == 0); +} + unsigned long spitz_get_hsync_len(void) { + if (!spitz_pxafb_dev) { + spitz_pxafb_dev = bus_find_device(&platform_bus_type, NULL, NULL, is_pxafb_device); + if (!spitz_pxafb_dev) + return 0; + } if (!get_hsync_time) get_hsync_time = symbol_get(pxafb_get_hsync_time); if (!get_hsync_time) return 0; - return pxafb_get_hsync_time(&pxafb_device.dev); + return pxafb_get_hsync_time(spitz_pxafb_dev); } void spitz_put_hsync(void) { + put_device(spitz_pxafb_dev); if (get_hsync_time) symbol_put(pxafb_get_hsync_time); + spitz_pxafb_dev = NULL; + get_hsync_time = NULL; } void spitz_wait_hsync(void) diff --git a/arch/arm/mach-pxa/generic.c b/arch/arm/mach-pxa/generic.c index d0660a8c4b70..d327c127eddb 100644 --- a/arch/arm/mach-pxa/generic.c +++ b/arch/arm/mach-pxa/generic.c @@ -208,6 +208,11 @@ static struct platform_device pxafb_device = { .resource = pxafb_resources, }; +void __init set_pxa_fb_parent(struct device *parent_dev) +{ + pxafb_device.dev.parent = parent_dev; +} + static struct platform_device ffuart_device = { .name = "pxa2xx-uart", .id = 0, diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 568afe3d6e1a..d0ab428c2d7d 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -36,7 +36,6 @@ #include #include #include -#include #include #include #include @@ -304,7 +303,6 @@ static struct platform_device *devices[] __initdata = { &spitzkbd_device, &spitzts_device, &spitzbl_device, - &spitzbattery_device, }; static void __init common_init(void) @@ -328,7 +326,7 @@ static void __init common_init(void) platform_add_devices(devices, ARRAY_SIZE(devices)); pxa_set_mci_info(&spitz_mci_platform_data); - pxafb_device.dev.parent = &spitzssp_device.dev; + set_pxa_fb_parent(&spitzssp_device.dev); set_pxa_fb_info(&spitz_pxafb_info); } diff --git a/arch/arm/mach-s3c2410/Kconfig b/arch/arm/mach-s3c2410/Kconfig index 06807c6ee68a..c796bcdd6158 100644 --- a/arch/arm/mach-s3c2410/Kconfig +++ b/arch/arm/mach-s3c2410/Kconfig @@ -12,6 +12,7 @@ config MACH_ANUBIS config ARCH_BAST bool "Simtec Electronics BAST (EB2410ITX)" select CPU_S3C2410 + select ISA help Say Y here if you are using the Simtec Electronics EB2410ITX development board (also known as BAST) diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index a4576ac7e870..8b1f6eb76870 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -275,12 +275,14 @@ static void flush_tlb_all_ipi(void *info) *==========================================================================*/ void smp_flush_tlb_mm(struct mm_struct *mm) { - int cpu_id = smp_processor_id(); + int cpu_id; cpumask_t cpu_mask; - unsigned long *mmc = &mm->context[cpu_id]; + unsigned long *mmc; unsigned long flags; preempt_disable(); + cpu_id = smp_processor_id(); + mmc = &mm->context[cpu_id]; cpu_mask = mm->cpu_vm_mask; cpu_clear(cpu_id, cpu_mask); @@ -343,12 +345,14 @@ void smp_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, void smp_flush_tlb_page(struct vm_area_struct *vma, unsigned long va) { struct mm_struct *mm = vma->vm_mm; - int cpu_id = smp_processor_id(); + int cpu_id; cpumask_t cpu_mask; - unsigned long *mmc = &mm->context[cpu_id]; + unsigned long *mmc; unsigned long flags; preempt_disable(); + cpu_id = smp_processor_id(); + mmc = &mm->context[cpu_id]; cpu_mask = mm->cpu_vm_mask; cpu_clear(cpu_id, cpu_mask); diff --git a/arch/mips/pci/fixup-tb0226.c b/arch/mips/pci/fixup-tb0226.c index 61513d5d97da..b5d42b12de10 100644 --- a/arch/mips/pci/fixup-tb0226.c +++ b/arch/mips/pci/fixup-tb0226.c @@ -1,7 +1,7 @@ /* * fixup-tb0226.c, The TANBAC TB0226 specific PCI fixups. * - * Copyright (C) 2002-2004 Yoichi Yuasa + * Copyright (C) 2002-2005 Yoichi Yuasa * * 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 @@ -20,6 +20,7 @@ #include #include +#include #include int __init pcibios_map_irq(struct pci_dev *dev, u8 slot, u8 pin) @@ -29,42 +30,42 @@ int __init pcibios_map_irq(struct pci_dev *dev, u8 slot, u8 pin) switch (slot) { case 12: vr41xx_set_irq_trigger(GD82559_1_PIN, - TRIGGER_LEVEL, - SIGNAL_THROUGH); - vr41xx_set_irq_level(GD82559_1_PIN, LEVEL_LOW); + IRQ_TRIGGER_LEVEL, + IRQ_SIGNAL_THROUGH); + vr41xx_set_irq_level(GD82559_1_PIN, IRQ_LEVEL_LOW); irq = GD82559_1_IRQ; break; case 13: vr41xx_set_irq_trigger(GD82559_2_PIN, - TRIGGER_LEVEL, - SIGNAL_THROUGH); - vr41xx_set_irq_level(GD82559_2_PIN, LEVEL_LOW); + IRQ_TRIGGER_LEVEL, + IRQ_SIGNAL_THROUGH); + vr41xx_set_irq_level(GD82559_2_PIN, IRQ_LEVEL_LOW); irq = GD82559_2_IRQ; break; case 14: switch (pin) { case 1: vr41xx_set_irq_trigger(UPD720100_INTA_PIN, - TRIGGER_LEVEL, - SIGNAL_THROUGH); + IRQ_TRIGGER_LEVEL, + IRQ_SIGNAL_THROUGH); vr41xx_set_irq_level(UPD720100_INTA_PIN, - LEVEL_LOW); + IRQ_LEVEL_LOW); irq = UPD720100_INTA_IRQ; break; case 2: vr41xx_set_irq_trigger(UPD720100_INTB_PIN, - TRIGGER_LEVEL, - SIGNAL_THROUGH); + IRQ_TRIGGER_LEVEL, + IRQ_SIGNAL_THROUGH); vr41xx_set_irq_level(UPD720100_INTB_PIN, - LEVEL_LOW); + IRQ_LEVEL_LOW); irq = UPD720100_INTB_IRQ; break; case 3: vr41xx_set_irq_trigger(UPD720100_INTC_PIN, - TRIGGER_LEVEL, - SIGNAL_THROUGH); + IRQ_TRIGGER_LEVEL, + IRQ_SIGNAL_THROUGH); vr41xx_set_irq_level(UPD720100_INTC_PIN, - LEVEL_LOW); + IRQ_LEVEL_LOW); irq = UPD720100_INTC_IRQ; break; default: diff --git a/arch/ppc64/kernel/pmac_setup.c b/arch/ppc64/kernel/pmac_setup.c index 25755252067a..fa8121d53b89 100644 --- a/arch/ppc64/kernel/pmac_setup.c +++ b/arch/ppc64/kernel/pmac_setup.c @@ -115,7 +115,7 @@ static void __pmac pmac_show_cpuinfo(struct seq_file *m) /* find motherboard type */ seq_printf(m, "machine\t\t: "); - np = find_devices("device-tree"); + np = of_find_node_by_path("/"); if (np != NULL) { pp = (char *) get_property(np, "model", NULL); if (pp != NULL) @@ -133,6 +133,7 @@ static void __pmac pmac_show_cpuinfo(struct seq_file *m) } seq_printf(m, "\n"); } + of_node_put(np); } else seq_printf(m, "PowerMac\n"); diff --git a/arch/sparc64/kernel/pci_iommu.c b/arch/sparc64/kernel/pci_iommu.c index 425c60cfea19..a11910be1013 100644 --- a/arch/sparc64/kernel/pci_iommu.c +++ b/arch/sparc64/kernel/pci_iommu.c @@ -49,12 +49,6 @@ static void __iommu_flushall(struct pci_iommu *iommu) /* Ensure completion of previous PIO writes. */ (void) pci_iommu_read(iommu->write_complete_reg); - - /* Now update everyone's flush point. */ - for (entry = 0; entry < PBM_NCLUSTERS; entry++) { - iommu->alloc_info[entry].flush = - iommu->alloc_info[entry].next; - } } #define IOPTE_CONSISTENT(CTX) \ @@ -80,120 +74,117 @@ static void inline iopte_make_dummy(struct pci_iommu *iommu, iopte_t *iopte) iopte_val(*iopte) = val; } -void pci_iommu_table_init(struct pci_iommu *iommu, int tsbsize) +/* Based largely upon the ppc64 iommu allocator. */ +static long pci_arena_alloc(struct pci_iommu *iommu, unsigned long npages) { - int i; + struct pci_iommu_arena *arena = &iommu->arena; + unsigned long n, i, start, end, limit; + int pass; - tsbsize /= sizeof(iopte_t); + limit = arena->limit; + start = arena->hint; + pass = 0; - for (i = 0; i < tsbsize; i++) +again: + n = find_next_zero_bit(arena->map, limit, start); + end = n + npages; + if (unlikely(end >= limit)) { + if (likely(pass < 1)) { + limit = start; + start = 0; + __iommu_flushall(iommu); + pass++; + goto again; + } else { + /* Scanned the whole thing, give up. */ + return -1; + } + } + + for (i = n; i < end; i++) { + if (test_bit(i, arena->map)) { + start = i + 1; + goto again; + } + } + + for (i = n; i < end; i++) + __set_bit(i, arena->map); + + arena->hint = end; + + return n; +} + +static void pci_arena_free(struct pci_iommu_arena *arena, unsigned long base, unsigned long npages) +{ + unsigned long i; + + for (i = base; i < (base + npages); i++) + __clear_bit(i, arena->map); +} + +void pci_iommu_table_init(struct pci_iommu *iommu, int tsbsize, u32 dma_offset, u32 dma_addr_mask) +{ + unsigned long i, tsbbase, order, sz, num_tsb_entries; + + num_tsb_entries = tsbsize / sizeof(iopte_t); + + /* Setup initial software IOMMU state. */ + spin_lock_init(&iommu->lock); + iommu->ctx_lowest_free = 1; + iommu->page_table_map_base = dma_offset; + iommu->dma_addr_mask = dma_addr_mask; + + /* Allocate and initialize the free area map. */ + sz = num_tsb_entries / 8; + sz = (sz + 7UL) & ~7UL; + iommu->arena.map = kmalloc(sz, GFP_KERNEL); + if (!iommu->arena.map) { + prom_printf("PCI_IOMMU: Error, kmalloc(arena.map) failed.\n"); + prom_halt(); + } + memset(iommu->arena.map, 0, sz); + iommu->arena.limit = num_tsb_entries; + + /* Allocate and initialize the dummy page which we + * set inactive IO PTEs to point to. + */ + iommu->dummy_page = __get_free_pages(GFP_KERNEL, 0); + if (!iommu->dummy_page) { + prom_printf("PCI_IOMMU: Error, gfp(dummy_page) failed.\n"); + prom_halt(); + } + memset((void *)iommu->dummy_page, 0, PAGE_SIZE); + iommu->dummy_page_pa = (unsigned long) __pa(iommu->dummy_page); + + /* Now allocate and setup the IOMMU page table itself. */ + order = get_order(tsbsize); + tsbbase = __get_free_pages(GFP_KERNEL, order); + if (!tsbbase) { + prom_printf("PCI_IOMMU: Error, gfp(tsb) failed.\n"); + prom_halt(); + } + iommu->page_table = (iopte_t *)tsbbase; + + for (i = 0; i < num_tsb_entries; i++) iopte_make_dummy(iommu, &iommu->page_table[i]); } -static iopte_t *alloc_streaming_cluster(struct pci_iommu *iommu, unsigned long npages) +static inline iopte_t *alloc_npages(struct pci_iommu *iommu, unsigned long npages) { - iopte_t *iopte, *limit, *first; - unsigned long cnum, ent, flush_point; + long entry; - cnum = 0; - while ((1UL << cnum) < npages) - cnum++; - iopte = (iommu->page_table + - (cnum << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS))); + entry = pci_arena_alloc(iommu, npages); + if (unlikely(entry < 0)) + return NULL; - if (cnum == 0) - limit = (iommu->page_table + - iommu->lowest_consistent_map); - else - limit = (iopte + - (1 << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS))); - - iopte += ((ent = iommu->alloc_info[cnum].next) << cnum); - flush_point = iommu->alloc_info[cnum].flush; - - first = iopte; - for (;;) { - if (IOPTE_IS_DUMMY(iommu, iopte)) { - if ((iopte + (1 << cnum)) >= limit) - ent = 0; - else - ent = ent + 1; - iommu->alloc_info[cnum].next = ent; - if (ent == flush_point) - __iommu_flushall(iommu); - break; - } - iopte += (1 << cnum); - ent++; - if (iopte >= limit) { - iopte = (iommu->page_table + - (cnum << - (iommu->page_table_sz_bits - PBM_LOGCLUSTERS))); - ent = 0; - } - if (ent == flush_point) - __iommu_flushall(iommu); - if (iopte == first) - goto bad; - } - - /* I've got your streaming cluster right here buddy boy... */ - return iopte; - -bad: - printk(KERN_EMERG "pci_iommu: alloc_streaming_cluster of npages(%ld) failed!\n", - npages); - return NULL; + return iommu->page_table + entry; } -static void free_streaming_cluster(struct pci_iommu *iommu, dma_addr_t base, - unsigned long npages, unsigned long ctx) +static inline void free_npages(struct pci_iommu *iommu, dma_addr_t base, unsigned long npages) { - unsigned long cnum, ent; - - cnum = 0; - while ((1UL << cnum) < npages) - cnum++; - - ent = (base << (32 - IO_PAGE_SHIFT + PBM_LOGCLUSTERS - iommu->page_table_sz_bits)) - >> (32 + PBM_LOGCLUSTERS + cnum - iommu->page_table_sz_bits); - - /* If the global flush might not have caught this entry, - * adjust the flush point such that we will flush before - * ever trying to reuse it. - */ -#define between(X,Y,Z) (((Z) - (Y)) >= ((X) - (Y))) - if (between(ent, iommu->alloc_info[cnum].next, iommu->alloc_info[cnum].flush)) - iommu->alloc_info[cnum].flush = ent; -#undef between -} - -/* We allocate consistent mappings from the end of cluster zero. */ -static iopte_t *alloc_consistent_cluster(struct pci_iommu *iommu, unsigned long npages) -{ - iopte_t *iopte; - - iopte = iommu->page_table + (1 << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS)); - while (iopte > iommu->page_table) { - iopte--; - if (IOPTE_IS_DUMMY(iommu, iopte)) { - unsigned long tmp = npages; - - while (--tmp) { - iopte--; - if (!IOPTE_IS_DUMMY(iommu, iopte)) - break; - } - if (tmp == 0) { - u32 entry = (iopte - iommu->page_table); - - if (entry < iommu->lowest_consistent_map) - iommu->lowest_consistent_map = entry; - return iopte; - } - } - } - return NULL; + pci_arena_free(&iommu->arena, base >> IO_PAGE_SHIFT, npages); } static int iommu_alloc_ctx(struct pci_iommu *iommu) @@ -233,7 +224,7 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t size, dma_addr_t *dma_ad struct pcidev_cookie *pcp; struct pci_iommu *iommu; iopte_t *iopte; - unsigned long flags, order, first_page, ctx; + unsigned long flags, order, first_page; void *ret; int npages; @@ -251,9 +242,10 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t size, dma_addr_t *dma_ad iommu = pcp->pbm->iommu; spin_lock_irqsave(&iommu->lock, flags); - iopte = alloc_consistent_cluster(iommu, size >> IO_PAGE_SHIFT); - if (iopte == NULL) { - spin_unlock_irqrestore(&iommu->lock, flags); + iopte = alloc_npages(iommu, size >> IO_PAGE_SHIFT); + spin_unlock_irqrestore(&iommu->lock, flags); + + if (unlikely(iopte == NULL)) { free_pages(first_page, order); return NULL; } @@ -262,31 +254,15 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t size, dma_addr_t *dma_ad ((iopte - iommu->page_table) << IO_PAGE_SHIFT)); ret = (void *) first_page; npages = size >> IO_PAGE_SHIFT; - ctx = 0; - if (iommu->iommu_ctxflush) - ctx = iommu_alloc_ctx(iommu); first_page = __pa(first_page); while (npages--) { - iopte_val(*iopte) = (IOPTE_CONSISTENT(ctx) | + iopte_val(*iopte) = (IOPTE_CONSISTENT(0UL) | IOPTE_WRITE | (first_page & IOPTE_PAGE)); iopte++; first_page += IO_PAGE_SIZE; } - { - int i; - u32 daddr = *dma_addrp; - - npages = size >> IO_PAGE_SHIFT; - for (i = 0; i < npages; i++) { - pci_iommu_write(iommu->iommu_flush, daddr); - daddr += IO_PAGE_SIZE; - } - } - - spin_unlock_irqrestore(&iommu->lock, flags); - return ret; } @@ -296,7 +272,7 @@ void pci_free_consistent(struct pci_dev *pdev, size_t size, void *cpu, dma_addr_ struct pcidev_cookie *pcp; struct pci_iommu *iommu; iopte_t *iopte; - unsigned long flags, order, npages, i, ctx; + unsigned long flags, order, npages; npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT; pcp = pdev->sysdata; @@ -306,46 +282,7 @@ void pci_free_consistent(struct pci_dev *pdev, size_t size, void *cpu, dma_addr_ spin_lock_irqsave(&iommu->lock, flags); - if ((iopte - iommu->page_table) == - iommu->lowest_consistent_map) { - iopte_t *walk = iopte + npages; - iopte_t *limit; - - limit = (iommu->page_table + - (1 << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS))); - while (walk < limit) { - if (!IOPTE_IS_DUMMY(iommu, walk)) - break; - walk++; - } - iommu->lowest_consistent_map = - (walk - iommu->page_table); - } - - /* Data for consistent mappings cannot enter the streaming - * buffers, so we only need to update the TSB. We flush - * the IOMMU here as well to prevent conflicts with the - * streaming mapping deferred tlb flush scheme. - */ - - ctx = 0; - if (iommu->iommu_ctxflush) - ctx = (iopte_val(*iopte) & IOPTE_CONTEXT) >> 47UL; - - for (i = 0; i < npages; i++, iopte++) - iopte_make_dummy(iommu, iopte); - - if (iommu->iommu_ctxflush) { - pci_iommu_write(iommu->iommu_ctxflush, ctx); - } else { - for (i = 0; i < npages; i++) { - u32 daddr = dvma + (i << IO_PAGE_SHIFT); - - pci_iommu_write(iommu->iommu_flush, daddr); - } - } - - iommu_free_ctx(iommu, ctx); + free_npages(iommu, dvma, npages); spin_unlock_irqrestore(&iommu->lock, flags); @@ -372,25 +309,27 @@ dma_addr_t pci_map_single(struct pci_dev *pdev, void *ptr, size_t sz, int direct iommu = pcp->pbm->iommu; strbuf = &pcp->pbm->stc; - if (direction == PCI_DMA_NONE) - BUG(); + if (unlikely(direction == PCI_DMA_NONE)) + goto bad_no_ctx; oaddr = (unsigned long)ptr; npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK); npages >>= IO_PAGE_SHIFT; spin_lock_irqsave(&iommu->lock, flags); + base = alloc_npages(iommu, npages); + ctx = 0; + if (iommu->iommu_ctxflush) + ctx = iommu_alloc_ctx(iommu); + spin_unlock_irqrestore(&iommu->lock, flags); - base = alloc_streaming_cluster(iommu, npages); - if (base == NULL) + if (unlikely(!base)) goto bad; + bus_addr = (iommu->page_table_map_base + ((base - iommu->page_table) << IO_PAGE_SHIFT)); ret = bus_addr | (oaddr & ~IO_PAGE_MASK); base_paddr = __pa(oaddr & IO_PAGE_MASK); - ctx = 0; - if (iommu->iommu_ctxflush) - ctx = iommu_alloc_ctx(iommu); if (strbuf->strbuf_enabled) iopte_protection = IOPTE_STREAMING(ctx); else @@ -401,12 +340,13 @@ dma_addr_t pci_map_single(struct pci_dev *pdev, void *ptr, size_t sz, int direct for (i = 0; i < npages; i++, base++, base_paddr += IO_PAGE_SIZE) iopte_val(*base) = iopte_protection | base_paddr; - spin_unlock_irqrestore(&iommu->lock, flags); - return ret; bad: - spin_unlock_irqrestore(&iommu->lock, flags); + iommu_free_ctx(iommu, ctx); +bad_no_ctx: + if (printk_ratelimit()) + WARN_ON(1); return PCI_DMA_ERROR_CODE; } @@ -481,10 +421,13 @@ void pci_unmap_single(struct pci_dev *pdev, dma_addr_t bus_addr, size_t sz, int struct pci_iommu *iommu; struct pci_strbuf *strbuf; iopte_t *base; - unsigned long flags, npages, ctx; + unsigned long flags, npages, ctx, i; - if (direction == PCI_DMA_NONE) - BUG(); + if (unlikely(direction == PCI_DMA_NONE)) { + if (printk_ratelimit()) + WARN_ON(1); + return; + } pcp = pdev->sysdata; iommu = pcp->pbm->iommu; @@ -510,13 +453,14 @@ void pci_unmap_single(struct pci_dev *pdev, dma_addr_t bus_addr, size_t sz, int /* Step 1: Kick data out of streaming buffers if necessary. */ if (strbuf->strbuf_enabled) - pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction); + pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, + npages, direction); - /* Step 2: Clear out first TSB entry. */ - iopte_make_dummy(iommu, base); + /* Step 2: Clear out TSB entries. */ + for (i = 0; i < npages; i++) + iopte_make_dummy(iommu, base + i); - free_streaming_cluster(iommu, bus_addr - iommu->page_table_map_base, - npages, ctx); + free_npages(iommu, bus_addr - iommu->page_table_map_base, npages); iommu_free_ctx(iommu, ctx); @@ -621,6 +565,8 @@ int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, int pci_map_single(pdev, (page_address(sglist->page) + sglist->offset), sglist->length, direction); + if (unlikely(sglist->dma_address == PCI_DMA_ERROR_CODE)) + return 0; sglist->dma_length = sglist->length; return 1; } @@ -629,21 +575,29 @@ int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, int iommu = pcp->pbm->iommu; strbuf = &pcp->pbm->stc; - if (direction == PCI_DMA_NONE) - BUG(); + if (unlikely(direction == PCI_DMA_NONE)) + goto bad_no_ctx; /* Step 1: Prepare scatter list. */ npages = prepare_sg(sglist, nelems); - /* Step 2: Allocate a cluster. */ + /* Step 2: Allocate a cluster and context, if necessary. */ spin_lock_irqsave(&iommu->lock, flags); - base = alloc_streaming_cluster(iommu, npages); + base = alloc_npages(iommu, npages); + ctx = 0; + if (iommu->iommu_ctxflush) + ctx = iommu_alloc_ctx(iommu); + + spin_unlock_irqrestore(&iommu->lock, flags); + if (base == NULL) goto bad; - dma_base = iommu->page_table_map_base + ((base - iommu->page_table) << IO_PAGE_SHIFT); + + dma_base = iommu->page_table_map_base + + ((base - iommu->page_table) << IO_PAGE_SHIFT); /* Step 3: Normalize DMA addresses. */ used = nelems; @@ -656,30 +610,28 @@ int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, int } used = nelems - used; - /* Step 4: Choose a context if necessary. */ - ctx = 0; - if (iommu->iommu_ctxflush) - ctx = iommu_alloc_ctx(iommu); - - /* Step 5: Create the mappings. */ + /* Step 4: Create the mappings. */ if (strbuf->strbuf_enabled) iopte_protection = IOPTE_STREAMING(ctx); else iopte_protection = IOPTE_CONSISTENT(ctx); if (direction != PCI_DMA_TODEVICE) iopte_protection |= IOPTE_WRITE; - fill_sg (base, sglist, used, nelems, iopte_protection); + + fill_sg(base, sglist, used, nelems, iopte_protection); + #ifdef VERIFY_SG verify_sglist(sglist, nelems, base, npages); #endif - spin_unlock_irqrestore(&iommu->lock, flags); - return used; bad: - spin_unlock_irqrestore(&iommu->lock, flags); - return PCI_DMA_ERROR_CODE; + iommu_free_ctx(iommu, ctx); +bad_no_ctx: + if (printk_ratelimit()) + WARN_ON(1); + return 0; } /* Unmap a set of streaming mode DMA translations. */ @@ -692,8 +644,10 @@ void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, unsigned long flags, ctx, i, npages; u32 bus_addr; - if (direction == PCI_DMA_NONE) - BUG(); + if (unlikely(direction == PCI_DMA_NONE)) { + if (printk_ratelimit()) + WARN_ON(1); + } pcp = pdev->sysdata; iommu = pcp->pbm->iommu; @@ -705,7 +659,8 @@ void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, if (sglist[i].dma_length == 0) break; i--; - npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) - bus_addr) >> IO_PAGE_SHIFT; + npages = (IO_PAGE_ALIGN(sglist[i].dma_address + sglist[i].dma_length) - + bus_addr) >> IO_PAGE_SHIFT; base = iommu->page_table + ((bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT); @@ -726,11 +681,11 @@ void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sglist, int nelems, if (strbuf->strbuf_enabled) pci_strbuf_flush(strbuf, iommu, bus_addr, ctx, npages, direction); - /* Step 2: Clear out first TSB entry. */ - iopte_make_dummy(iommu, base); + /* Step 2: Clear out the TSB entries. */ + for (i = 0; i < npages; i++) + iopte_make_dummy(iommu, base + i); - free_streaming_cluster(iommu, bus_addr - iommu->page_table_map_base, - npages, ctx); + free_npages(iommu, bus_addr - iommu->page_table_map_base, npages); iommu_free_ctx(iommu, ctx); diff --git a/arch/sparc64/kernel/pci_psycho.c b/arch/sparc64/kernel/pci_psycho.c index 6ed1ef25e0ac..c03ed5f49d31 100644 --- a/arch/sparc64/kernel/pci_psycho.c +++ b/arch/sparc64/kernel/pci_psycho.c @@ -1207,13 +1207,9 @@ static void psycho_scan_bus(struct pci_controller_info *p) static void psycho_iommu_init(struct pci_controller_info *p) { struct pci_iommu *iommu = p->pbm_A.iommu; - unsigned long tsbbase, i; + unsigned long i; u64 control; - /* Setup initial software IOMMU state. */ - spin_lock_init(&iommu->lock); - iommu->ctx_lowest_free = 1; - /* Register addresses. */ iommu->iommu_control = p->pbm_A.controller_regs + PSYCHO_IOMMU_CONTROL; iommu->iommu_tsbbase = p->pbm_A.controller_regs + PSYCHO_IOMMU_TSBBASE; @@ -1240,40 +1236,10 @@ static void psycho_iommu_init(struct pci_controller_info *p) /* Leave diag mode enabled for full-flushing done * in pci_iommu.c */ + pci_iommu_table_init(iommu, IO_TSB_SIZE, 0xc0000000, 0xffffffff); - iommu->dummy_page = __get_free_pages(GFP_KERNEL, 0); - if (!iommu->dummy_page) { - prom_printf("PSYCHO_IOMMU: Error, gfp(dummy_page) failed.\n"); - prom_halt(); - } - memset((void *)iommu->dummy_page, 0, PAGE_SIZE); - iommu->dummy_page_pa = (unsigned long) __pa(iommu->dummy_page); - - /* Using assumed page size 8K with 128K entries we need 1MB iommu page - * table (128K ioptes * 8 bytes per iopte). This is - * page order 7 on UltraSparc. - */ - tsbbase = __get_free_pages(GFP_KERNEL, get_order(IO_TSB_SIZE)); - if (!tsbbase) { - prom_printf("PSYCHO_IOMMU: Error, gfp(tsb) failed.\n"); - prom_halt(); - } - iommu->page_table = (iopte_t *)tsbbase; - iommu->page_table_sz_bits = 17; - iommu->page_table_map_base = 0xc0000000; - iommu->dma_addr_mask = 0xffffffff; - pci_iommu_table_init(iommu, IO_TSB_SIZE); - - /* We start with no consistent mappings. */ - iommu->lowest_consistent_map = - 1 << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS); - - for (i = 0; i < PBM_NCLUSTERS; i++) { - iommu->alloc_info[i].flush = 0; - iommu->alloc_info[i].next = 0; - } - - psycho_write(p->pbm_A.controller_regs + PSYCHO_IOMMU_TSBBASE, __pa(tsbbase)); + psycho_write(p->pbm_A.controller_regs + PSYCHO_IOMMU_TSBBASE, + __pa(iommu->page_table)); control = psycho_read(p->pbm_A.controller_regs + PSYCHO_IOMMU_CONTROL); control &= ~(PSYCHO_IOMMU_CTRL_TSBSZ | PSYCHO_IOMMU_CTRL_TBWSZ); @@ -1281,7 +1247,7 @@ static void psycho_iommu_init(struct pci_controller_info *p) psycho_write(p->pbm_A.controller_regs + PSYCHO_IOMMU_CONTROL, control); /* If necessary, hook us up for starfire IRQ translations. */ - if(this_is_starfire) + if (this_is_starfire) p->starfire_cookie = starfire_hookup(p->pbm_A.portid); else p->starfire_cookie = NULL; diff --git a/arch/sparc64/kernel/pci_sabre.c b/arch/sparc64/kernel/pci_sabre.c index 0ee6bd5b9ac6..da8e1364194f 100644 --- a/arch/sparc64/kernel/pci_sabre.c +++ b/arch/sparc64/kernel/pci_sabre.c @@ -1267,13 +1267,9 @@ static void sabre_iommu_init(struct pci_controller_info *p, u32 dma_mask) { struct pci_iommu *iommu = p->pbm_A.iommu; - unsigned long tsbbase, i, order; + unsigned long i; u64 control; - /* Setup initial software IOMMU state. */ - spin_lock_init(&iommu->lock); - iommu->ctx_lowest_free = 1; - /* Register addresses. */ iommu->iommu_control = p->pbm_A.controller_regs + SABRE_IOMMU_CONTROL; iommu->iommu_tsbbase = p->pbm_A.controller_regs + SABRE_IOMMU_TSBBASE; @@ -1295,26 +1291,10 @@ static void sabre_iommu_init(struct pci_controller_info *p, /* Leave diag mode enabled for full-flushing done * in pci_iommu.c */ + pci_iommu_table_init(iommu, tsbsize * 1024 * 8, dvma_offset, dma_mask); - iommu->dummy_page = __get_free_pages(GFP_KERNEL, 0); - if (!iommu->dummy_page) { - prom_printf("PSYCHO_IOMMU: Error, gfp(dummy_page) failed.\n"); - prom_halt(); - } - memset((void *)iommu->dummy_page, 0, PAGE_SIZE); - iommu->dummy_page_pa = (unsigned long) __pa(iommu->dummy_page); - - tsbbase = __get_free_pages(GFP_KERNEL, order = get_order(tsbsize * 1024 * 8)); - if (!tsbbase) { - prom_printf("SABRE_IOMMU: Error, gfp(tsb) failed.\n"); - prom_halt(); - } - iommu->page_table = (iopte_t *)tsbbase; - iommu->page_table_map_base = dvma_offset; - iommu->dma_addr_mask = dma_mask; - pci_iommu_table_init(iommu, PAGE_SIZE << order); - - sabre_write(p->pbm_A.controller_regs + SABRE_IOMMU_TSBBASE, __pa(tsbbase)); + sabre_write(p->pbm_A.controller_regs + SABRE_IOMMU_TSBBASE, + __pa(iommu->page_table)); control = sabre_read(p->pbm_A.controller_regs + SABRE_IOMMU_CONTROL); control &= ~(SABRE_IOMMUCTRL_TSBSZ | SABRE_IOMMUCTRL_TBWSZ); @@ -1322,11 +1302,9 @@ static void sabre_iommu_init(struct pci_controller_info *p, switch(tsbsize) { case 64: control |= SABRE_IOMMU_TSBSZ_64K; - iommu->page_table_sz_bits = 16; break; case 128: control |= SABRE_IOMMU_TSBSZ_128K; - iommu->page_table_sz_bits = 17; break; default: prom_printf("iommu_init: Illegal TSB size %d\n", tsbsize); @@ -1334,15 +1312,6 @@ static void sabre_iommu_init(struct pci_controller_info *p, break; } sabre_write(p->pbm_A.controller_regs + SABRE_IOMMU_CONTROL, control); - - /* We start with no consistent mappings. */ - iommu->lowest_consistent_map = - 1 << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS); - - for (i = 0; i < PBM_NCLUSTERS; i++) { - iommu->alloc_info[i].flush = 0; - iommu->alloc_info[i].next = 0; - } } static void pbm_register_toplevel_resources(struct pci_controller_info *p, diff --git a/arch/sparc64/kernel/pci_schizo.c b/arch/sparc64/kernel/pci_schizo.c index cae5b61fe2f0..d8c4e0919b4e 100644 --- a/arch/sparc64/kernel/pci_schizo.c +++ b/arch/sparc64/kernel/pci_schizo.c @@ -1765,7 +1765,7 @@ static void schizo_pbm_strbuf_init(struct pci_pbm_info *pbm) static void schizo_pbm_iommu_init(struct pci_pbm_info *pbm) { struct pci_iommu *iommu = pbm->iommu; - unsigned long tsbbase, i, tagbase, database, order; + unsigned long i, tagbase, database; u32 vdma[2], dma_mask; u64 control; int err, tsbsize; @@ -1800,10 +1800,6 @@ static void schizo_pbm_iommu_init(struct pci_pbm_info *pbm) prom_halt(); }; - /* Setup initial software IOMMU state. */ - spin_lock_init(&iommu->lock); - iommu->ctx_lowest_free = 1; - /* Register addresses, SCHIZO has iommu ctx flushing. */ iommu->iommu_control = pbm->pbm_regs + SCHIZO_IOMMU_CONTROL; iommu->iommu_tsbbase = pbm->pbm_regs + SCHIZO_IOMMU_TSBBASE; @@ -1832,56 +1828,9 @@ static void schizo_pbm_iommu_init(struct pci_pbm_info *pbm) /* Leave diag mode enabled for full-flushing done * in pci_iommu.c */ + pci_iommu_table_init(iommu, tsbsize * 8 * 1024, vdma[0], dma_mask); - iommu->dummy_page = __get_free_pages(GFP_KERNEL, 0); - if (!iommu->dummy_page) { - prom_printf("PSYCHO_IOMMU: Error, gfp(dummy_page) failed.\n"); - prom_halt(); - } - memset((void *)iommu->dummy_page, 0, PAGE_SIZE); - iommu->dummy_page_pa = (unsigned long) __pa(iommu->dummy_page); - - /* Using assumed page size 8K with 128K entries we need 1MB iommu page - * table (128K ioptes * 8 bytes per iopte). This is - * page order 7 on UltraSparc. - */ - order = get_order(tsbsize * 8 * 1024); - tsbbase = __get_free_pages(GFP_KERNEL, order); - if (!tsbbase) { - prom_printf("%s: Error, gfp(tsb) failed.\n", pbm->name); - prom_halt(); - } - - iommu->page_table = (iopte_t *)tsbbase; - iommu->page_table_map_base = vdma[0]; - iommu->dma_addr_mask = dma_mask; - pci_iommu_table_init(iommu, PAGE_SIZE << order); - - switch (tsbsize) { - case 64: - iommu->page_table_sz_bits = 16; - break; - - case 128: - iommu->page_table_sz_bits = 17; - break; - - default: - prom_printf("iommu_init: Illegal TSB size %d\n", tsbsize); - prom_halt(); - break; - }; - - /* We start with no consistent mappings. */ - iommu->lowest_consistent_map = - 1 << (iommu->page_table_sz_bits - PBM_LOGCLUSTERS); - - for (i = 0; i < PBM_NCLUSTERS; i++) { - iommu->alloc_info[i].flush = 0; - iommu->alloc_info[i].next = 0; - } - - schizo_write(iommu->iommu_tsbbase, __pa(tsbbase)); + schizo_write(iommu->iommu_tsbbase, __pa(iommu->page_table)); control = schizo_read(iommu->iommu_control); control &= ~(SCHIZO_IOMMU_CTRL_TSBSZ | SCHIZO_IOMMU_CTRL_TBWSZ); diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c index 590df5a16f5a..b137fd63f5e1 100644 --- a/arch/sparc64/kernel/smp.c +++ b/arch/sparc64/kernel/smp.c @@ -1001,13 +1001,6 @@ void smp_penguin_jailcell(int irq, struct pt_regs *regs) preempt_enable(); } -extern unsigned long xcall_promstop; - -void smp_promstop_others(void) -{ - smp_cross_call(&xcall_promstop, 0, 0, 0); -} - #define prof_multiplier(__cpu) cpu_data(__cpu).multiplier #define prof_counter(__cpu) cpu_data(__cpu).counter diff --git a/arch/sparc64/mm/ultra.S b/arch/sparc64/mm/ultra.S index 058b8126c1a7..e4c9151fa116 100644 --- a/arch/sparc64/mm/ultra.S +++ b/arch/sparc64/mm/ultra.S @@ -453,22 +453,6 @@ xcall_flush_dcache_page_spitfire: /* %g1 == physical page address nop nop - .globl xcall_promstop -xcall_promstop: - rdpr %pstate, %g2 - wrpr %g2, PSTATE_IG | PSTATE_AG, %pstate - rdpr %pil, %g2 - wrpr %g0, 15, %pil - sethi %hi(109f), %g7 - b,pt %xcc, etrap_irq -109: or %g7, %lo(109b), %g7 - flushw - call prom_stopself - nop - /* We should not return, just spin if we do... */ -1: b,a,pt %xcc, 1b - nop - .data errata32_hwbug: diff --git a/arch/sparc64/prom/misc.c b/arch/sparc64/prom/misc.c index 9b895faf077b..87f5cfce23bb 100644 --- a/arch/sparc64/prom/misc.c +++ b/arch/sparc64/prom/misc.c @@ -68,19 +68,11 @@ void prom_cmdline(void) local_irq_restore(flags); } -#ifdef CONFIG_SMP -extern void smp_promstop_others(void); -#endif - /* Drop into the prom, but completely terminate the program. * No chance of continuing. */ void prom_halt(void) { -#ifdef CONFIG_SMP - smp_promstop_others(); - udelay(8000); -#endif again: p1275_cmd("exit", P1275_INOUT(0, 0)); goto again; /* PROM is out to get me -DaveM */ @@ -88,10 +80,6 @@ again: void prom_halt_power_off(void) { -#ifdef CONFIG_SMP - smp_promstop_others(); - udelay(8000); -#endif p1275_cmd("SUNW,power-off", P1275_INOUT(0, 0)); /* if nothing else helps, we just halt */ diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index bfa8b76de403..2dbb1b0f11d5 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -58,9 +58,8 @@ acpi_system_read_event(struct file *file, char __user * buffer, size_t count, return_VALUE(-EAGAIN); result = acpi_bus_receive_event(&event); - if (result) { - return_VALUE(-EIO); - } + if (result) + return_VALUE(result); chars_remaining = sprintf(str, "%s %s %08x %08x\n", event.device_class ? event. diff --git a/drivers/char/mbcs.c b/drivers/char/mbcs.c index 3fa64c631108..c268ee04b2aa 100644 --- a/drivers/char/mbcs.c +++ b/drivers/char/mbcs.c @@ -830,6 +830,9 @@ static int __init mbcs_init(void) { int rv; + if (!ia64_platform_is("sn2")) + return -ENODEV; + // Put driver into chrdevs[]. Get major number. rv = register_chrdev(mbcs_major, DEVICE_NAME, &mbcs_ops); if (rv < 0) { diff --git a/drivers/char/n_r3964.c b/drivers/char/n_r3964.c index 97d6dc24b800..853c98cee64f 100644 --- a/drivers/char/n_r3964.c +++ b/drivers/char/n_r3964.c @@ -695,7 +695,7 @@ static void receive_char(struct r3964_info *pInfo, const unsigned char c) { TRACE_PE("IDLE - got STX but no space in rx_queue!"); pInfo->state=R3964_WAIT_FOR_RX_BUF; - mod_timer(&pInfo->tmr, R3964_TO_NO_BUF); + mod_timer(&pInfo->tmr, jiffies + R3964_TO_NO_BUF); break; } start_receiving: @@ -705,7 +705,7 @@ start_receiving: pInfo->last_rx = 0; pInfo->flags &= ~R3964_ERROR; pInfo->state=R3964_RECEIVING; - mod_timer(&pInfo->tmr, R3964_TO_ZVZ); + mod_timer(&pInfo->tmr, jiffies + R3964_TO_ZVZ); pInfo->nRetry = 0; put_char(pInfo, DLE); flush(pInfo); @@ -732,7 +732,7 @@ start_receiving: if(pInfo->flags & R3964_BCC) { pInfo->state = R3964_WAIT_FOR_BCC; - mod_timer(&pInfo->tmr, R3964_TO_ZVZ); + mod_timer(&pInfo->tmr, jiffies + R3964_TO_ZVZ); } else { @@ -744,7 +744,7 @@ start_receiving: pInfo->last_rx = c; char_to_buf: pInfo->rx_buf[pInfo->rx_position++] = c; - mod_timer(&pInfo->tmr, R3964_TO_ZVZ); + mod_timer(&pInfo->tmr, jiffies + R3964_TO_ZVZ); } } /* else: overflow-msg? BUF_SIZE>MTU; should not happen? */ diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 444f7756fee6..571a68691a4a 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -93,7 +93,7 @@ config KEYBOARD_LKKBD config KEYBOARD_LOCOMO tristate "LoCoMo Keyboard Support" - depends on SHARP_LOCOMO + depends on SHARP_LOCOMO && INPUT_KEYBOARD help Say Y here if you are running Linux on a Sharp Zaurus Collie or Poodle based PDA diff --git a/drivers/input/keyboard/spitzkbd.c b/drivers/input/keyboard/spitzkbd.c index 1714045a182b..344f46005401 100644 --- a/drivers/input/keyboard/spitzkbd.c +++ b/drivers/input/keyboard/spitzkbd.c @@ -53,7 +53,7 @@ static unsigned char spitzkbd_keycode[NR_SCANCODES] = { KEY_LEFTCTRL, KEY_1, KEY_3, KEY_5, KEY_6, KEY_7, KEY_9, KEY_0, KEY_BACKSPACE, SPITZ_KEY_EXOK, SPITZ_KEY_EXCANCEL, 0, 0, 0, 0, 0, /* 1-16 */ 0, KEY_2, KEY_4, KEY_R, KEY_Y, KEY_8, KEY_I, KEY_O, KEY_P, SPITZ_KEY_EXJOGDOWN, SPITZ_KEY_EXJOGUP, 0, 0, 0, 0, 0, /* 17-32 */ KEY_TAB, KEY_Q, KEY_E, KEY_T, KEY_G, KEY_U, KEY_J, KEY_K, 0, 0, 0, 0, 0, 0, 0, 0, /* 33-48 */ - SPITZ_KEY_CALENDER, KEY_W, KEY_S, KEY_F, KEY_V, KEY_H, KEY_M, KEY_L, 0, 0, KEY_RIGHTSHIFT, 0, 0, 0, 0, 0, /* 49-64 */ + SPITZ_KEY_CALENDER, KEY_W, KEY_S, KEY_F, KEY_V, KEY_H, KEY_M, KEY_L, 0, KEY_RIGHTSHIFT, 0, 0, 0, 0, 0, 0, /* 49-64 */ SPITZ_KEY_ADDRESS, KEY_A, KEY_D, KEY_C, KEY_B, KEY_N, KEY_DOT, 0, KEY_ENTER, KEY_LEFTSHIFT, 0, 0, 0, 0, 0, 0, /* 65-80 */ SPITZ_KEY_MAIL, KEY_Z, KEY_X, KEY_MINUS, KEY_SPACE, KEY_COMMA, 0, KEY_UP, 0, 0, SPITZ_KEY_FN, 0, 0, 0, 0, 0, /* 81-96 */ KEY_SYSRQ, SPITZ_KEY_JAP1, SPITZ_KEY_JAP2, SPITZ_KEY_CANCEL, SPITZ_KEY_OK, SPITZ_KEY_MENU, KEY_LEFT, KEY_DOWN, KEY_RIGHT, 0, 0, 0, 0, 0, 0, 0 /* 97-112 */ diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c index d5c5b32045af..4015a91f4b6e 100644 --- a/drivers/input/misc/uinput.c +++ b/drivers/input/misc/uinput.c @@ -90,11 +90,11 @@ static inline int uinput_request_reserve_slot(struct uinput_device *udev, struct static void uinput_request_done(struct uinput_device *udev, struct uinput_request *request) { - complete(&request->done); - /* Mark slot as available */ udev->requests[request->id] = NULL; wake_up_interruptible(&udev->requests_waitq); + + complete(&request->done); } static int uinput_request_submit(struct input_dev *dev, struct uinput_request *request) diff --git a/drivers/media/radio/radio-cadet.c b/drivers/media/radio/radio-cadet.c index 022913da8c59..9b0406318f2d 100644 --- a/drivers/media/radio/radio-cadet.c +++ b/drivers/media/radio/radio-cadet.c @@ -543,7 +543,7 @@ static int cadet_probe(void) for(i=0;i<8;i++) { io=iovals[i]; - if(request_region(io,2, "cadet-probe")>=0) { + if (request_region(io, 2, "cadet-probe")) { cadet_setfreq(1410); if(cadet_getfreq()==1410) { release_region(io, 2); diff --git a/drivers/media/video/vpx3220.c b/drivers/media/video/vpx3220.c index 4437bdebe24f..137b58f2c666 100644 --- a/drivers/media/video/vpx3220.c +++ b/drivers/media/video/vpx3220.c @@ -203,7 +203,7 @@ static const unsigned short init_ntsc[] = { 0x8c, 640, /* Horizontal length */ 0x8d, 640, /* Number of pixels */ 0x8f, 0xc00, /* Disable window 2 */ - 0xf0, 0x173, /* 13.5 MHz transport, Forced + 0xf0, 0x73, /* 13.5 MHz transport, Forced * mode, latch windows */ 0xf2, 0x13, /* NTSC M, composite input */ 0xe7, 0x1e1, /* Enable vertical standard @@ -212,38 +212,36 @@ static const unsigned short init_ntsc[] = { static const unsigned short init_pal[] = { 0x88, 23, /* Window 1 vertical begin */ - 0x89, 288 + 16, /* Vertical lines in (16 lines + 0x89, 288, /* Vertical lines in (16 lines * skipped by the VFE) */ - 0x8a, 288 + 16, /* Vertical lines out (16 lines + 0x8a, 288, /* Vertical lines out (16 lines * skipped by the VFE) */ 0x8b, 16, /* Horizontal begin */ 0x8c, 768, /* Horizontal length */ 0x8d, 784, /* Number of pixels * Must be >= Horizontal begin + Horizontal length */ 0x8f, 0xc00, /* Disable window 2 */ - 0xf0, 0x177, /* 13.5 MHz transport, Forced + 0xf0, 0x77, /* 13.5 MHz transport, Forced * mode, latch windows */ 0xf2, 0x3d1, /* PAL B,G,H,I, composite input */ - 0xe7, 0x261, /* PAL/SECAM set to 288 + 16 lines - * change to 0x241 for 288 lines */ + 0xe7, 0x241, /* PAL/SECAM set to 288 lines */ }; static const unsigned short init_secam[] = { - 0x88, 23 - 16, /* Window 1 vertical begin */ - 0x89, 288 + 16, /* Vertical lines in (16 lines + 0x88, 23, /* Window 1 vertical begin */ + 0x89, 288, /* Vertical lines in (16 lines * skipped by the VFE) */ - 0x8a, 288 + 16, /* Vertical lines out (16 lines + 0x8a, 288, /* Vertical lines out (16 lines * skipped by the VFE) */ 0x8b, 16, /* Horizontal begin */ 0x8c, 768, /* Horizontal length */ 0x8d, 784, /* Number of pixels * Must be >= Horizontal begin + Horizontal length */ 0x8f, 0xc00, /* Disable window 2 */ - 0xf0, 0x177, /* 13.5 MHz transport, Forced + 0xf0, 0x77, /* 13.5 MHz transport, Forced * mode, latch windows */ 0xf2, 0x3d5, /* SECAM, composite input */ - 0xe7, 0x261, /* PAL/SECAM set to 288 + 16 lines - * change to 0x241 for 288 lines */ + 0xe7, 0x241, /* PAL/SECAM set to 288 lines */ }; static const unsigned char init_common[] = { @@ -410,6 +408,12 @@ vpx3220_command (struct i2c_client *client, case DECODER_SET_NORM: { int *iarg = arg, data; + int temp_input; + + /* Here we back up the input selection because it gets + overwritten when we fill the registers with the + choosen video norm */ + temp_input = vpx3220_fp_read(client, 0xf2); dprintk(1, KERN_DEBUG "%s: DECODER_SET_NORM %d\n", I2C_NAME(client), *iarg); @@ -449,6 +453,10 @@ vpx3220_command (struct i2c_client *client, } decoder->norm = *iarg; + + /* And here we set the backed up video input again */ + vpx3220_fp_write(client, 0xf2, temp_input | 0x0010); + udelay(10); } break; diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig index 00a07f32a81e..7187958e40ca 100644 --- a/drivers/net/wireless/Kconfig +++ b/drivers/net/wireless/Kconfig @@ -243,7 +243,7 @@ config IPW_DEBUG config AIRO tristate "Cisco/Aironet 34X/35X/4500/4800 ISA and PCI cards" - depends on NET_RADIO && ISA && (PCI || BROKEN) + depends on NET_RADIO && ISA_DMA_API && (PCI || BROKEN) ---help--- This is the standard Linux driver to support Cisco/Aironet ISA and PCI 802.11 wireless cards. diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 11ca44387cb0..a6a630a950d0 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -1233,7 +1233,7 @@ static void __init quirk_alder_ioapic(struct pci_dev *pdev) DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_EESSC, quirk_alder_ioapic ); #endif -#ifdef CONFIG_SCSI_SATA +#ifdef CONFIG_SCSI_SATA_INTEL_COMBINED static void __devinit quirk_intel_ide_combined(struct pci_dev *pdev) { u8 prog, comb, tmp; @@ -1310,7 +1310,7 @@ static void __devinit quirk_intel_ide_combined(struct pci_dev *pdev) request_region(0x170, 8, "libata"); /* port 1 */ } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_intel_ide_combined ); -#endif /* CONFIG_SCSI_SATA */ +#endif /* CONFIG_SCSI_SATA_INTEL_COMBINED */ int pcie_mch_quirk; diff --git a/drivers/pcmcia/soc_common.c b/drivers/pcmcia/soc_common.c index 888b70e6a484..9e7ccd8a4321 100644 --- a/drivers/pcmcia/soc_common.c +++ b/drivers/pcmcia/soc_common.c @@ -66,7 +66,7 @@ void soc_pcmcia_debug(struct soc_pcmcia_socket *skt, const char *func, if (pc_debug > lvl) { printk(KERN_DEBUG "skt%u: %s: ", skt->nr, func); va_start(args, fmt); - printk(fmt, args); + vprintk(fmt, args); va_end(args); } } @@ -321,8 +321,6 @@ soc_common_pcmcia_get_socket(struct pcmcia_socket *sock, socket_state_t *state) * less punt all of this work and let the kernel handle the details * of power configuration, reset, &c. We also record the value of * `state' in order to regurgitate it to the PCMCIA core later. - * - * Returns: 0 */ static int soc_common_pcmcia_set_socket(struct pcmcia_socket *sock, socket_state_t *state) @@ -407,7 +405,7 @@ soc_common_pcmcia_set_io_map(struct pcmcia_socket *sock, struct pccard_io_map *m * the map speed as requested, but override the address ranges * supplied by Card Services. * - * Returns: 0 on success, -1 on error + * Returns: 0 on success, -ERRNO on error */ static int soc_common_pcmcia_set_mem_map(struct pcmcia_socket *sock, struct pccard_mem_map *map) @@ -655,8 +653,8 @@ static void soc_pcmcia_cpufreq_unregister(void) } #else -#define soc_pcmcia_cpufreq_register() -#define soc_pcmcia_cpufreq_unregister() +static int soc_pcmcia_cpufreq_register(void) { return 0; } +static void soc_pcmcia_cpufreq_unregister(void) {} #endif int soc_common_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops, int first, int nr) @@ -738,7 +736,7 @@ int soc_common_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops goto out_err_5; } - if ( list_empty(&soc_pcmcia_sockets) ) + if (list_empty(&soc_pcmcia_sockets)) soc_pcmcia_cpufreq_register(); list_add(&skt->node, &soc_pcmcia_sockets); @@ -839,7 +837,7 @@ int soc_common_drv_pcmcia_remove(struct device *dev) release_resource(&skt->res_io); release_resource(&skt->res_skt); } - if ( list_empty(&soc_pcmcia_sockets) ) + if (list_empty(&soc_pcmcia_sockets)) soc_pcmcia_cpufreq_unregister(); up(&soc_pcmcia_sockets_lock); diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 20019b82b4a8..3ee9b8b33be0 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -553,6 +553,11 @@ config SCSI_SATA_VITESSE If unsure, say N. +config SCSI_SATA_INTEL_COMBINED + bool + depends on IDE=y && !BLK_DEV_IDE_SATA && (SCSI_SATA_AHCI || SCSI_ATA_PIIX) + default y + config SCSI_BUSLOGIC tristate "BusLogic SCSI support" depends on (PCI || ISA || MCA) && SCSI && ISA_DMA_API diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index de8490a92831..a1f9ceef0ac9 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -453,9 +453,9 @@ static int aac_eh_reset(struct scsi_cmnd* cmd) /* * We can exit If all the commands are complete */ + spin_unlock_irq(host->host_lock); if (active == 0) return SUCCESS; - spin_unlock_irq(host->host_lock); ssleep(1); spin_lock_irq(host->host_lock); } diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c index a917ab7475ac..1fd5fc6d0fe3 100644 --- a/drivers/scsi/qlogicpti.c +++ b/drivers/scsi/qlogicpti.c @@ -1119,6 +1119,36 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int host->sg_tablesize = QLOGICPTI_MAX_SG(num_free); } +static unsigned int scsi_rbuf_get(struct scsi_cmnd *cmd, unsigned char **buf_out) +{ + unsigned char *buf; + unsigned int buflen; + + if (cmd->use_sg) { + struct scatterlist *sg; + + sg = (struct scatterlist *) cmd->request_buffer; + buf = kmap_atomic(sg->page, KM_IRQ0) + sg->offset; + buflen = sg->length; + } else { + buf = cmd->request_buffer; + buflen = cmd->request_bufflen; + } + + *buf_out = buf; + return buflen; +} + +static void scsi_rbuf_put(struct scsi_cmnd *cmd, unsigned char *buf) +{ + if (cmd->use_sg) { + struct scatterlist *sg; + + sg = (struct scatterlist *) cmd->request_buffer; + kunmap_atomic(buf - sg->offset, KM_IRQ0); + } +} + /* * Until we scan the entire bus with inquiries, go throught this fella... */ @@ -1145,11 +1175,9 @@ static void ourdone(struct scsi_cmnd *Cmnd) int ok = host_byte(Cmnd->result) == DID_OK; if (Cmnd->cmnd[0] == 0x12 && ok) { unsigned char *iqd; + unsigned int iqd_len; - if (Cmnd->use_sg != 0) - BUG(); - - iqd = ((unsigned char *)Cmnd->buffer); + iqd_len = scsi_rbuf_get(Cmnd, &iqd); /* tags handled in midlayer */ /* enable sync mode? */ @@ -1163,6 +1191,9 @@ static void ourdone(struct scsi_cmnd *Cmnd) if (iqd[7] & 0x20) { qpti->dev_param[tgt].device_flags |= 0x20; } + + scsi_rbuf_put(Cmnd, iqd); + qpti->sbits |= (1 << tgt); } else if (!ok) { qpti->sbits |= (1 << tgt); diff --git a/drivers/serial/8250_pnp.c b/drivers/serial/8250_pnp.c index 6b321e82cafb..c2786fc41cc5 100644 --- a/drivers/serial/8250_pnp.c +++ b/drivers/serial/8250_pnp.c @@ -272,6 +272,8 @@ static const struct pnp_device_id pnp_dev_table[] = { { "SUP1421", 0 }, /* SupraExpress 33.6 Data/Fax PnP modem */ { "SUP1590", 0 }, + /* SupraExpress 336i Sp ASVD */ + { "SUP1620", 0 }, /* SupraExpress 33.6 Data/Fax PnP modem */ { "SUP1760", 0 }, /* Phoebe Micro */ diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c index 512266307866..430754ebac8a 100644 --- a/drivers/serial/sh-sci.c +++ b/drivers/serial/sh-sci.c @@ -967,7 +967,7 @@ static int sci_startup(struct uart_port *port) #endif sci_request_irq(s); - sci_start_tx(port, 1); + sci_start_tx(port); sci_start_rx(port, 1); return 0; diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c index 41bbae83fc71..e142056b0d2c 100644 --- a/drivers/usb/host/isp116x-hcd.c +++ b/drivers/usb/host/isp116x-hcd.c @@ -326,7 +326,8 @@ static void postproc_atl_queue(struct isp116x *isp116x) usb_settoggle(udev, ep->epnum, ep->nextpid == USB_PID_OUT, - PTD_GET_TOGGLE(ptd) ^ 1); + PTD_GET_TOGGLE(ptd)); + urb->actual_length += PTD_GET_COUNT(ptd); urb->status = cc_to_error[TD_DATAUNDERRUN]; spin_unlock(&urb->lock); continue; diff --git a/drivers/usb/input/hid-core.c b/drivers/usb/input/hid-core.c index a99865c689c5..41f92b924761 100644 --- a/drivers/usb/input/hid-core.c +++ b/drivers/usb/input/hid-core.c @@ -1702,10 +1702,7 @@ static struct hid_device *usb_hid_configure(struct usb_interface *intf) if ((endpoint->bmAttributes & 3) != 3) /* Not an interrupt endpoint */ continue; - /* handle potential highspeed HID correctly */ interval = endpoint->bInterval; - if (dev->speed == USB_SPEED_HIGH) - interval = 1 << (interval - 1); /* Change the polling interval of mice. */ if (hid->collection->usage == HID_GD_MOUSE && hid_mousepoll_interval > 0) diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c index ddde5fb13f6b..5f7d3193d355 100644 --- a/drivers/usb/serial/generic.c +++ b/drivers/usb/serial/generic.c @@ -223,7 +223,7 @@ int usb_serial_generic_write_room (struct usb_serial_port *port) dbg("%s - port %d", __FUNCTION__, port->number); if (serial->num_bulk_out) { - if (port->write_urb_busy) + if (!(port->write_urb_busy)) room = port->bulk_out_size; } diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index 6ef6f7760e47..809fee2140ac 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -565,7 +565,11 @@ static int vgacon_switch(struct vc_data *c) scr_memcpyw((u16 *) c->vc_origin, (u16 *) c->vc_screenbuf, c->vc_screenbuf_size > vga_vram_size ? vga_vram_size : c->vc_screenbuf_size); - vgacon_doresize(c, c->vc_cols, c->vc_rows); + if (!(vga_video_num_columns % 2) && + vga_video_num_columns <= ORIG_VIDEO_COLS && + vga_video_num_lines <= (ORIG_VIDEO_LINES * + vga_default_font_height) / c->vc_font.height) + vgacon_doresize(c, c->vc_cols, c->vc_rows); } return 0; /* Redrawing not needed */ @@ -1023,7 +1027,8 @@ static int vgacon_resize(struct vc_data *c, unsigned int width, if (width % 2 || width > ORIG_VIDEO_COLS || height > (ORIG_VIDEO_LINES * vga_default_font_height)/ c->vc_font.height) - return -EINVAL; + /* let svgatextmode tinker with video timings */ + return 0; if (CON_IS_VISIBLE(c) && !vga_is_gfx) /* who knows */ vgacon_doresize(c, width, height); diff --git a/drivers/video/sa1100fb.c b/drivers/video/sa1100fb.c index beeec7b51425..8000890e4271 100644 --- a/drivers/video/sa1100fb.c +++ b/drivers/video/sa1100fb.c @@ -592,6 +592,7 @@ sa1100fb_setcolreg(u_int regno, u_int red, u_int green, u_int blue, return ret; } +#ifdef CONFIG_CPU_FREQ /* * sa1100fb_display_dma_period() * Calculate the minimum period (in picoseconds) between two DMA @@ -606,6 +607,7 @@ static inline unsigned int sa1100fb_display_dma_period(struct fb_var_screeninfo */ return var->pixclock * 8 * 16 / var->bits_per_pixel; } +#endif /* * sa1100fb_check_var(): diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index 1b6b74c116a9..14016b1cd948 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -77,8 +77,7 @@ static void w1_master_release(struct device *dev) dev_dbg(dev, "%s: Releasing %s.\n", __func__, md->name); - if (md->nls && md->nls->sk_socket) - sock_release(md->nls->sk_socket); + dev_fini_netlink(md); memset(md, 0, sizeof(struct w1_master) + sizeof(struct w1_bus_master)); kfree(md); } diff --git a/fs/aio.c b/fs/aio.c index d6b1551342b7..9fe7216457d8 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -398,7 +398,7 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx) if (unlikely(!req)) return NULL; - req->ki_flags = 1 << KIF_LOCKED; + req->ki_flags = 0; req->ki_users = 2; req->ki_key = 0; req->ki_ctx = ctx; @@ -547,25 +547,6 @@ struct kioctx *lookup_ioctx(unsigned long ctx_id) return ioctx; } -static int lock_kiocb_action(void *param) -{ - schedule(); - return 0; -} - -static inline void lock_kiocb(struct kiocb *iocb) -{ - wait_on_bit_lock(&iocb->ki_flags, KIF_LOCKED, lock_kiocb_action, - TASK_UNINTERRUPTIBLE); -} - -static inline void unlock_kiocb(struct kiocb *iocb) -{ - kiocbClearLocked(iocb); - smp_mb__after_clear_bit(); - wake_up_bit(&iocb->ki_flags, KIF_LOCKED); -} - /* * use_mm * Makes the calling kernel thread take on the specified @@ -796,9 +777,7 @@ static int __aio_run_iocbs(struct kioctx *ctx) * Hold an extra reference while retrying i/o. */ iocb->ki_users++; /* grab extra reference */ - lock_kiocb(iocb); aio_run_iocb(iocb); - unlock_kiocb(iocb); if (__aio_put_req(ctx, iocb)) /* drop extra ref */ put_ioctx(ctx); } @@ -1542,7 +1521,6 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, spin_lock_irq(&ctx->ctx_lock); aio_run_iocb(req); - unlock_kiocb(req); if (!list_empty(&ctx->run_list)) { /* drain the run list */ while (__aio_run_iocbs(ctx)) @@ -1674,7 +1652,6 @@ asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, if (NULL != cancel) { struct io_event tmp; pr_debug("calling cancel\n"); - lock_kiocb(kiocb); memset(&tmp, 0, sizeof(tmp)); tmp.obj = (u64)(unsigned long)kiocb->ki_obj.user; tmp.data = kiocb->ki_user_data; @@ -1686,7 +1663,6 @@ asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, if (copy_to_user(result, &tmp, sizeof(tmp))) ret = -EFAULT; } - unlock_kiocb(kiocb); } else ret = -EINVAL; diff --git a/fs/exec.c b/fs/exec.c index a04a575ad433..d2208f7c87db 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -126,8 +126,7 @@ asmlinkage long sys_uselib(const char __user * library) struct nameidata nd; int error; - nd.intent.open.flags = FMODE_READ; - error = __user_walk(library, LOOKUP_FOLLOW|LOOKUP_OPEN, &nd); + error = __user_path_lookup_open(library, LOOKUP_FOLLOW, &nd, FMODE_READ); if (error) goto out; @@ -139,7 +138,7 @@ asmlinkage long sys_uselib(const char __user * library) if (error) goto exit; - file = dentry_open(nd.dentry, nd.mnt, O_RDONLY); + file = nameidata_to_filp(&nd, O_RDONLY); error = PTR_ERR(file); if (IS_ERR(file)) goto out; @@ -167,6 +166,7 @@ asmlinkage long sys_uselib(const char __user * library) out: return error; exit: + release_open_intent(&nd); path_release(&nd); goto out; } @@ -490,8 +490,7 @@ struct file *open_exec(const char *name) int err; struct file *file; - nd.intent.open.flags = FMODE_READ; - err = path_lookup(name, LOOKUP_FOLLOW|LOOKUP_OPEN, &nd); + err = path_lookup_open(name, LOOKUP_FOLLOW, &nd, FMODE_READ); file = ERR_PTR(err); if (!err) { @@ -504,7 +503,7 @@ struct file *open_exec(const char *name) err = -EACCES; file = ERR_PTR(err); if (!err) { - file = dentry_open(nd.dentry, nd.mnt, O_RDONLY); + file = nameidata_to_filp(&nd, O_RDONLY); if (!IS_ERR(file)) { err = deny_write_access(file); if (err) { @@ -516,6 +515,7 @@ out: return file; } } + release_open_intent(&nd); path_release(&nd); } goto out; diff --git a/fs/locks.c b/fs/locks.c index 7eb1d77b9204..a1e8b2248014 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -316,21 +316,22 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ start += l->l_start; - end = start + l->l_len - 1; - if (l->l_len < 0) { - end = start - 1; - start += l->l_len; - } - if (start < 0) return -EINVAL; - if (l->l_len > 0 && end < 0) - return -EOVERFLOW; - + fl->fl_end = OFFSET_MAX; + if (l->l_len > 0) { + end = start + l->l_len - 1; + fl->fl_end = end; + } else if (l->l_len < 0) { + end = start - 1; + fl->fl_end = end; + start += l->l_len; + if (start < 0) + return -EINVAL; + } fl->fl_start = start; /* we record the absolute position */ - fl->fl_end = end; - if (l->l_len == 0) - fl->fl_end = OFFSET_MAX; + if (fl->fl_end < fl->fl_start) + return -EOVERFLOW; fl->fl_owner = current->files; fl->fl_pid = current->tgid; @@ -362,14 +363,21 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, return -EINVAL; } - if (((start += l->l_start) < 0) || (l->l_len < 0)) + start += l->l_start; + if (start < 0) return -EINVAL; - fl->fl_end = start + l->l_len - 1; - if (l->l_len > 0 && fl->fl_end < 0) - return -EOVERFLOW; + fl->fl_end = OFFSET_MAX; + if (l->l_len > 0) { + fl->fl_end = start + l->l_len - 1; + } else if (l->l_len < 0) { + fl->fl_end = start - 1; + start += l->l_len; + if (start < 0) + return -EINVAL; + } fl->fl_start = start; /* we record the absolute position */ - if (l->l_len == 0) - fl->fl_end = OFFSET_MAX; + if (fl->fl_end < fl->fl_start) + return -EOVERFLOW; fl->fl_owner = current->files; fl->fl_pid = current->tgid; diff --git a/fs/namei.c b/fs/namei.c index aa62dbda93ac..aaaa81036234 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -317,6 +318,18 @@ void path_release_on_umount(struct nameidata *nd) mntput_no_expire(nd->mnt); } +/** + * release_open_intent - free up open intent resources + * @nd: pointer to nameidata + */ +void release_open_intent(struct nameidata *nd) +{ + if (nd->intent.open.file->f_dentry == NULL) + put_filp(nd->intent.open.file); + else + fput(nd->intent.open.file); +} + /* * Internal lookup() using the new generic dcache. * SMP-safe @@ -750,6 +763,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) struct qstr this; unsigned int c; + nd->flags |= LOOKUP_CONTINUE; err = exec_permission_lite(inode, nd); if (err == -EAGAIN) { err = permission(inode, MAY_EXEC, nd); @@ -802,7 +816,6 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) if (err < 0) break; } - nd->flags |= LOOKUP_CONTINUE; /* This does the actual lookups.. */ err = do_lookup(nd, &this, &next); if (err) @@ -1052,6 +1065,70 @@ out: return retval; } +static int __path_lookup_intent_open(const char *name, unsigned int lookup_flags, + struct nameidata *nd, int open_flags, int create_mode) +{ + struct file *filp = get_empty_filp(); + int err; + + if (filp == NULL) + return -ENFILE; + nd->intent.open.file = filp; + nd->intent.open.flags = open_flags; + nd->intent.open.create_mode = create_mode; + err = path_lookup(name, lookup_flags|LOOKUP_OPEN, nd); + if (IS_ERR(nd->intent.open.file)) { + if (err == 0) { + err = PTR_ERR(nd->intent.open.file); + path_release(nd); + } + } else if (err != 0) + release_open_intent(nd); + return err; +} + +/** + * path_lookup_open - lookup a file path with open intent + * @name: pointer to file name + * @lookup_flags: lookup intent flags + * @nd: pointer to nameidata + * @open_flags: open intent flags + */ +int path_lookup_open(const char *name, unsigned int lookup_flags, + struct nameidata *nd, int open_flags) +{ + return __path_lookup_intent_open(name, lookup_flags, nd, + open_flags, 0); +} + +/** + * path_lookup_create - lookup a file path with open + create intent + * @name: pointer to file name + * @lookup_flags: lookup intent flags + * @nd: pointer to nameidata + * @open_flags: open intent flags + * @create_mode: create intent flags + */ +int path_lookup_create(const char *name, unsigned int lookup_flags, + struct nameidata *nd, int open_flags, int create_mode) +{ + return __path_lookup_intent_open(name, lookup_flags|LOOKUP_CREATE, nd, + open_flags, create_mode); +} + +int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags, + struct nameidata *nd, int open_flags) +{ + char *tmp = getname(name); + int err = PTR_ERR(tmp); + + if (!IS_ERR(tmp)) { + err = __path_lookup_intent_open(tmp, lookup_flags, nd, open_flags, 0); + putname(tmp); + } + return err; +} + /* * Restricted form of lookup. Doesn't follow links, single-component only, * needs parent already locked. Doesn't follow mounts. @@ -1416,27 +1493,27 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) */ int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) { - int acc_mode, error = 0; + int acc_mode, error; struct path path; struct dentry *dir; int count = 0; acc_mode = ACC_MODE(flag); + /* O_TRUNC implies we need access checks for write permissions */ + if (flag & O_TRUNC) + acc_mode |= MAY_WRITE; + /* Allow the LSM permission hook to distinguish append access from general write access. */ if (flag & O_APPEND) acc_mode |= MAY_APPEND; - /* Fill in the open() intent data */ - nd->intent.open.flags = flag; - nd->intent.open.create_mode = mode; - /* * The simplest case - just a plain lookup. */ if (!(flag & O_CREAT)) { - error = path_lookup(pathname, lookup_flags(flag)|LOOKUP_OPEN, nd); + error = path_lookup_open(pathname, lookup_flags(flag), nd, flag); if (error) return error; goto ok; @@ -1445,7 +1522,7 @@ int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) /* * Create - we need to know the parent. */ - error = path_lookup(pathname, LOOKUP_PARENT|LOOKUP_OPEN|LOOKUP_CREATE, nd); + error = path_lookup_create(pathname, LOOKUP_PARENT, nd, flag, mode); if (error) return error; @@ -1520,6 +1597,8 @@ ok: exit_dput: dput_path(&path, nd); exit: + if (!IS_ERR(nd->intent.open.file)) + release_open_intent(nd); path_release(nd); return error; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index d7f7eb669d03..44135af9894c 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -85,6 +85,10 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct struct nfs_delegation *delegation; int status = 0; + /* Ensure we first revalidate the attributes and page cache! */ + if ((nfsi->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATTR))) + __nfs_revalidate_inode(NFS_SERVER(inode), inode); + delegation = nfs_alloc_delegation(); if (delegation == NULL) return -ENOMEM; @@ -138,7 +142,7 @@ static void nfs_msync_inode(struct inode *inode) /* * Basic procedure for returning a delegation to the server */ -int nfs_inode_return_delegation(struct inode *inode) +int __nfs_inode_return_delegation(struct inode *inode) { struct nfs4_client *clp = NFS_SERVER(inode)->nfs4_state; struct nfs_inode *nfsi = NFS_I(inode); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 3f6c45a29d6a..8017846b561f 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -25,7 +25,7 @@ struct nfs_delegation { int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); -int nfs_inode_return_delegation(struct inode *inode); +int __nfs_inode_return_delegation(struct inode *inode); int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid); struct inode *nfs_delegation_find_inode(struct nfs4_client *clp, const struct nfs_fh *fhandle); @@ -47,11 +47,25 @@ static inline int nfs_have_delegation(struct inode *inode, int flags) return 1; return 0; } + +static inline int nfs_inode_return_delegation(struct inode *inode) +{ + int err = 0; + + if (NFS_I(inode)->delegation != NULL) + err = __nfs_inode_return_delegation(inode); + return err; +} #else static inline int nfs_have_delegation(struct inode *inode, int flags) { return 0; } + +static inline int nfs_inode_return_delegation(struct inode *inode) +{ + return 0; +} #endif #endif diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index c70eabd6d179..eb50c19fc253 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -801,6 +801,7 @@ static int nfs_dentry_delete(struct dentry *dentry) */ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) { + nfs_inode_return_delegation(inode); if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { lock_kernel(); inode->i_nlink--; @@ -914,7 +915,6 @@ static int is_atomic_open(struct inode *dir, struct nameidata *nd) static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { struct dentry *res = NULL; - struct inode *inode = NULL; int error; /* Check that we are indeed trying to open this file */ @@ -928,8 +928,10 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry dentry->d_op = NFS_PROTO(dir)->dentry_ops; /* Let vfs_create() deal with O_EXCL */ - if (nd->intent.open.flags & O_EXCL) - goto no_entry; + if (nd->intent.open.flags & O_EXCL) { + d_add(dentry, NULL); + goto out; + } /* Open the file on the server */ lock_kernel(); @@ -943,32 +945,30 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry if (nd->intent.open.flags & O_CREAT) { nfs_begin_data_update(dir); - inode = nfs4_atomic_open(dir, dentry, nd); + res = nfs4_atomic_open(dir, dentry, nd); nfs_end_data_update(dir); } else - inode = nfs4_atomic_open(dir, dentry, nd); + res = nfs4_atomic_open(dir, dentry, nd); unlock_kernel(); - if (IS_ERR(inode)) { - error = PTR_ERR(inode); + if (IS_ERR(res)) { + error = PTR_ERR(res); switch (error) { /* Make a negative dentry */ case -ENOENT: - inode = NULL; - break; + res = NULL; + goto out; /* This turned out not to be a regular file */ + case -EISDIR: + case -ENOTDIR: + goto no_open; case -ELOOP: if (!(nd->intent.open.flags & O_NOFOLLOW)) goto no_open; - /* case -EISDIR: */ /* case -EINVAL: */ default: - res = ERR_PTR(error); goto out; } - } -no_entry: - res = d_add_unique(dentry, inode); - if (res != NULL) + } else if (res != NULL) dentry = res; nfs_renew_times(dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); @@ -1012,7 +1012,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) */ lock_kernel(); verifier = nfs_save_change_attribute(dir); - ret = nfs4_open_revalidate(dir, dentry, openflags); + ret = nfs4_open_revalidate(dir, dentry, openflags, nd); if (!ret) nfs_set_verifier(dentry, verifier); unlock_kernel(); @@ -1135,7 +1135,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode, lock_kernel(); nfs_begin_data_update(dir); - error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags); + error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, nd); nfs_end_data_update(dir); if (error != 0) goto out_err; @@ -1330,6 +1330,7 @@ static int nfs_safe_remove(struct dentry *dentry) nfs_begin_data_update(dir); if (inode != NULL) { + nfs_inode_return_delegation(inode); nfs_begin_data_update(inode); error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); /* The VFS may want to delete this inode */ @@ -1510,9 +1511,11 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, */ if (!new_inode) goto go_ahead; - if (S_ISDIR(new_inode->i_mode)) - goto out; - else if (atomic_read(&new_dentry->d_count) > 2) { + if (S_ISDIR(new_inode->i_mode)) { + error = -EISDIR; + if (!S_ISDIR(old_inode->i_mode)) + goto out; + } else if (atomic_read(&new_dentry->d_count) > 2) { int err; /* copy the target dentry's name */ dentry = d_alloc(new_dentry->d_parent, @@ -1548,6 +1551,7 @@ go_ahead: nfs_wb_all(old_inode); shrink_dcache_parent(old_dentry); } + nfs_inode_return_delegation(old_inode); if (new_inode) d_delete(new_dentry); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index f6b9eda925c5..572d8593486f 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -137,7 +137,8 @@ static int nfs_revalidate_file(struct inode *inode, struct file *filp) struct nfs_inode *nfsi = NFS_I(inode); int retval = 0; - if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) || nfs_attribute_timeout(inode)) + if ((nfsi->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATTR)) + || nfs_attribute_timeout(inode)) retval = __nfs_revalidate_inode(NFS_SERVER(inode), inode); nfs_revalidate_mapping(inode, filp->f_mapping); return 0; @@ -375,22 +376,31 @@ out_swapfile: static int do_getlk(struct file *filp, int cmd, struct file_lock *fl) { + struct file_lock *cfl; struct inode *inode = filp->f_mapping->host; int status = 0; lock_kernel(); - /* Use local locking if mounted with "-onolock" */ - if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)) - status = NFS_PROTO(inode)->lock(filp, cmd, fl); - else { - struct file_lock *cfl = posix_test_lock(filp, fl); - - fl->fl_type = F_UNLCK; - if (cfl != NULL) - memcpy(fl, cfl, sizeof(*fl)); + /* Try local locking first */ + cfl = posix_test_lock(filp, fl); + if (cfl != NULL) { + locks_copy_lock(fl, cfl); + goto out; } + + if (nfs_have_delegation(inode, FMODE_READ)) + goto out_noconflict; + + if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM) + goto out_noconflict; + + status = NFS_PROTO(inode)->lock(filp, cmd, fl); +out: unlock_kernel(); return status; +out_noconflict: + fl->fl_type = F_UNLCK; + goto out; } static int do_vfs_lock(struct file *file, struct file_lock *fl) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 358d8ef8c087..65d5ab45ddc5 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -853,6 +853,11 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) filemap_fdatawait(inode->i_mapping); nfs_wb_all(inode); } + /* + * Return any delegations if we're going to change ACLs + */ + if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) + nfs_inode_return_delegation(inode); error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr); if (error == 0) nfs_refresh_inode(inode, &fattr); @@ -909,12 +914,10 @@ static int nfs_wait_on_inode(struct inode *inode) sigset_t oldmask; int error; - atomic_inc(&inode->i_count); rpc_clnt_sigmask(clnt, &oldmask); error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING, nfs_wait_schedule, TASK_INTERRUPTIBLE); rpc_clnt_sigunmask(clnt, &oldmask); - iput(inode); return error; } @@ -1258,10 +1261,6 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) loff_t cur_size, new_isize; int data_unstable; - /* Do we hold a delegation? */ - if (nfs_have_delegation(inode, FMODE_READ)) - return 0; - spin_lock(&inode->i_lock); /* Are we in the process of updating data on the server? */ @@ -1382,7 +1381,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr, unsign nfsi->read_cache_jiffies = fattr->timestamp; /* Are we racing with known updates of the metadata on the server? */ - data_unstable = ! nfs_verify_change_attribute(inode, verifier); + data_unstable = ! (nfs_verify_change_attribute(inode, verifier) || + (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)); /* Check if our cached file size is stale */ new_isize = nfs_size_to_loff_t(fattr->size); @@ -1676,8 +1676,7 @@ static void nfs4_clear_inode(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); /* If we are holding a delegation, return it! */ - if (nfsi->delegation != NULL) - nfs_inode_return_delegation(inode); + nfs_inode_return_delegation(inode); /* First call standard NFS clear_inode() code */ nfs_clear_inode(inode); /* Now clear out any remaining state */ diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index edc95514046d..df80477c5af4 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -299,7 +299,7 @@ static int nfs3_proc_commit(struct nfs_write_data *cdata) */ static int nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags) + int flags, struct nameidata *nd) { struct nfs_fh fhandle; struct nfs_fattr fattr; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ec1a22d7b876..8a3788199052 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -92,26 +92,51 @@ struct nfs4_client { unsigned char cl_id_uniquifier; }; +/* + * struct rpc_sequence ensures that RPC calls are sent in the exact + * order that they appear on the list. + */ +struct rpc_sequence { + struct rpc_wait_queue wait; /* RPC call delay queue */ + spinlock_t lock; /* Protects the list */ + struct list_head list; /* Defines sequence of RPC calls */ +}; + +#define NFS_SEQID_CONFIRMED 1 +struct nfs_seqid_counter { + struct rpc_sequence *sequence; + int flags; + u32 counter; +}; + +struct nfs_seqid { + struct list_head list; + struct nfs_seqid_counter *sequence; + struct rpc_task *task; +}; + +static inline void nfs_confirm_seqid(struct nfs_seqid_counter *seqid, int status) +{ + if (seqid_mutating_err(-status)) + seqid->flags |= NFS_SEQID_CONFIRMED; +} + /* * NFS4 state_owners and lock_owners are simply labels for ordered * sequences of RPC calls. Their sole purpose is to provide once-only * semantics by allowing the server to identify replayed requests. - * - * The ->so_sema is held during all state_owner seqid-mutating operations: - * OPEN, OPEN_DOWNGRADE, and CLOSE. Its purpose is to properly serialize - * so_seqid. */ struct nfs4_state_owner { struct list_head so_list; /* per-clientid list of state_owners */ struct nfs4_client *so_client; u32 so_id; /* 32-bit identifier, unique */ - struct semaphore so_sema; - u32 so_seqid; /* protected by so_sema */ atomic_t so_count; struct rpc_cred *so_cred; /* Associated cred */ struct list_head so_states; struct list_head so_delegations; + struct nfs_seqid_counter so_seqid; + struct rpc_sequence so_sequence; }; /* @@ -132,7 +157,7 @@ struct nfs4_lock_state { fl_owner_t ls_owner; /* POSIX lock owner */ #define NFS_LOCK_INITIALIZED 1 int ls_flags; - u32 ls_seqid; + struct nfs_seqid_counter ls_seqid; u32 ls_id; nfs4_stateid ls_stateid; atomic_t ls_count; @@ -153,7 +178,6 @@ struct nfs4_state { struct inode *inode; /* Pointer to the inode */ unsigned long flags; /* Do we hold any locks? */ - struct semaphore lock_sema; /* Serializes file locking operations */ spinlock_t state_lock; /* Protects the lock_states list */ nfs4_stateid stateid; @@ -191,8 +215,8 @@ extern int nfs4_proc_setclientid_confirm(struct nfs4_client *); extern int nfs4_proc_async_renew(struct nfs4_client *); extern int nfs4_proc_renew(struct nfs4_client *); extern int nfs4_do_close(struct inode *inode, struct nfs4_state *state, mode_t mode); -extern struct inode *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *); -extern int nfs4_open_revalidate(struct inode *, struct dentry *, int); +extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *); +extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *); extern struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops; extern struct nfs4_state_recovery_ops nfs4_network_partition_recovery_ops; @@ -224,12 +248,17 @@ extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state extern void nfs4_put_open_state(struct nfs4_state *); extern void nfs4_close_state(struct nfs4_state *, mode_t); extern struct nfs4_state *nfs4_find_state(struct inode *, struct rpc_cred *, mode_t mode); -extern void nfs4_increment_seqid(int status, struct nfs4_state_owner *sp); extern void nfs4_schedule_state_recovery(struct nfs4_client *); +extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); -extern void nfs4_increment_lock_seqid(int status, struct nfs4_lock_state *ls); extern void nfs4_copy_stateid(nfs4_stateid *, struct nfs4_state *, fl_owner_t); +extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter); +extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task); +extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid); +extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid); +extern void nfs_free_seqid(struct nfs_seqid *seqid); + extern const nfs4_stateid zero_stateid; /* nfs4xdr.c */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 9701ca8c9428..ff378126ccd7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -47,6 +47,7 @@ #include #include #include +#include #include "nfs4_fs.h" #include "delegation.h" @@ -56,10 +57,11 @@ #define NFS4_POLL_RETRY_MIN (1*HZ) #define NFS4_POLL_RETRY_MAX (15*HZ) +static int _nfs4_proc_open_confirm(struct rpc_clnt *clnt, const struct nfs_fh *fh, struct nfs4_state_owner *sp, nfs4_stateid *stateid, struct nfs_seqid *seqid); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); -static int nfs4_async_handle_error(struct rpc_task *, struct nfs_server *); +static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *); static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry); -static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception); +static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception); extern u32 *nfs4_decode_dirent(u32 *p, struct nfs_entry *entry, int plus); extern struct rpc_procinfo nfs4_procedures[]; @@ -189,6 +191,21 @@ static void update_changeattr(struct inode *inode, struct nfs4_change_info *cinf nfsi->change_attr = cinfo->after; } +/* Helper for asynchronous RPC calls */ +static int nfs4_call_async(struct rpc_clnt *clnt, rpc_action tk_begin, + rpc_action tk_exit, void *calldata) +{ + struct rpc_task *task; + + if (!(task = rpc_new_task(clnt, tk_exit, RPC_TASK_ASYNC))) + return -ENOMEM; + + task->tk_calldata = calldata; + task->tk_action = tk_begin; + rpc_execute(task); + return 0; +} + static void update_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, int open_flags) { struct inode *inode = state->inode; @@ -209,7 +226,6 @@ static void update_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, /* * OPEN_RECLAIM: * reclaim state on the server after a reboot. - * Assumes caller is holding the sp->so_sem */ static int _nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *state) { @@ -218,7 +234,6 @@ static int _nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *st struct nfs_delegation *delegation = NFS_I(inode)->delegation; struct nfs_openargs o_arg = { .fh = NFS_FH(inode), - .seqid = sp->so_seqid, .id = sp->so_id, .open_flags = state->state, .clientid = server->nfs4_state->cl_clientid, @@ -245,8 +260,13 @@ static int _nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *st } o_arg.u.delegation_type = delegation->type; } + o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid); + if (o_arg.seqid == NULL) + return -ENOMEM; status = rpc_call_sync(server->client, &msg, RPC_TASK_NOINTR); - nfs4_increment_seqid(status, sp); + /* Confirm the sequence as being established */ + nfs_confirm_seqid(&sp->so_seqid, status); + nfs_increment_open_seqid(status, o_arg.seqid); if (status == 0) { memcpy(&state->stateid, &o_res.stateid, sizeof(state->stateid)); if (o_res.delegation_type != 0) { @@ -256,6 +276,7 @@ static int _nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *st nfs_async_inode_return_delegation(inode, &o_res.stateid); } } + nfs_free_seqid(o_arg.seqid); clear_bit(NFS_DELEGATED_STATE, &state->flags); /* Ensure we update the inode attributes */ NFS_CACHEINV(inode); @@ -302,23 +323,35 @@ static int _nfs4_open_delegation_recall(struct dentry *dentry, struct nfs4_state }; int status = 0; - down(&sp->so_sema); if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) goto out; if (state->state == 0) goto out; - arg.seqid = sp->so_seqid; + arg.seqid = nfs_alloc_seqid(&sp->so_seqid); + status = -ENOMEM; + if (arg.seqid == NULL) + goto out; arg.open_flags = state->state; memcpy(arg.u.delegation.data, state->stateid.data, sizeof(arg.u.delegation.data)); status = rpc_call_sync(server->client, &msg, RPC_TASK_NOINTR); - nfs4_increment_seqid(status, sp); + nfs_increment_open_seqid(status, arg.seqid); + if (status != 0) + goto out_free; + if(res.rflags & NFS4_OPEN_RESULT_CONFIRM) { + status = _nfs4_proc_open_confirm(server->client, NFS_FH(inode), + sp, &res.stateid, arg.seqid); + if (status != 0) + goto out_free; + } + nfs_confirm_seqid(&sp->so_seqid, 0); if (status >= 0) { memcpy(state->stateid.data, res.stateid.data, sizeof(state->stateid.data)); clear_bit(NFS_DELEGATED_STATE, &state->flags); } +out_free: + nfs_free_seqid(arg.seqid); out: - up(&sp->so_sema); dput(parent); return status; } @@ -345,11 +378,11 @@ int nfs4_open_delegation_recall(struct dentry *dentry, struct nfs4_state *state) return err; } -static inline int _nfs4_proc_open_confirm(struct rpc_clnt *clnt, const struct nfs_fh *fh, struct nfs4_state_owner *sp, nfs4_stateid *stateid) +static int _nfs4_proc_open_confirm(struct rpc_clnt *clnt, const struct nfs_fh *fh, struct nfs4_state_owner *sp, nfs4_stateid *stateid, struct nfs_seqid *seqid) { struct nfs_open_confirmargs arg = { .fh = fh, - .seqid = sp->so_seqid, + .seqid = seqid, .stateid = *stateid, }; struct nfs_open_confirmres res; @@ -362,7 +395,9 @@ static inline int _nfs4_proc_open_confirm(struct rpc_clnt *clnt, const struct nf int status; status = rpc_call_sync(clnt, &msg, RPC_TASK_NOINTR); - nfs4_increment_seqid(status, sp); + /* Confirm the sequence as being established */ + nfs_confirm_seqid(&sp->so_seqid, status); + nfs_increment_open_seqid(status, seqid); if (status >= 0) memcpy(stateid, &res.stateid, sizeof(*stateid)); return status; @@ -380,21 +415,37 @@ static int _nfs4_proc_open(struct inode *dir, struct nfs4_state_owner *sp, stru int status; /* Update sequence id. The caller must serialize! */ - o_arg->seqid = sp->so_seqid; o_arg->id = sp->so_id; o_arg->clientid = sp->so_client->cl_clientid; status = rpc_call_sync(server->client, &msg, RPC_TASK_NOINTR); - nfs4_increment_seqid(status, sp); + if (status == 0) { + /* OPEN on anything except a regular file is disallowed in NFSv4 */ + switch (o_res->f_attr->mode & S_IFMT) { + case S_IFREG: + break; + case S_IFLNK: + status = -ELOOP; + break; + case S_IFDIR: + status = -EISDIR; + break; + default: + status = -ENOTDIR; + } + } + + nfs_increment_open_seqid(status, o_arg->seqid); if (status != 0) goto out; update_changeattr(dir, &o_res->cinfo); if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { status = _nfs4_proc_open_confirm(server->client, &o_res->fh, - sp, &o_res->stateid); + sp, &o_res->stateid, o_arg->seqid); if (status != 0) goto out; } + nfs_confirm_seqid(&sp->so_seqid, 0); if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) status = server->rpc_ops->getattr(server, &o_res->fh, o_res->f_attr); out: @@ -465,6 +516,10 @@ static int _nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st set_bit(NFS_DELEGATED_STATE, &state->flags); goto out; } + o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid); + status = -ENOMEM; + if (o_arg.seqid == NULL) + goto out; status = _nfs4_proc_open(dir, sp, &o_arg, &o_res); if (status != 0) goto out_nodeleg; @@ -490,6 +545,7 @@ static int _nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st nfs_inode_reclaim_delegation(inode, sp->so_cred, &o_res); } out_nodeleg: + nfs_free_seqid(o_arg.seqid); clear_bit(NFS_DELEGATED_STATE, &state->flags); out: dput(parent); @@ -564,7 +620,6 @@ static int _nfs4_open_delegated(struct inode *inode, int flags, struct rpc_cred dprintk("%s: nfs4_get_state_owner failed!\n", __FUNCTION__); goto out_err; } - down(&sp->so_sema); state = nfs4_get_open_state(inode, sp); if (state == NULL) goto out_err; @@ -589,7 +644,6 @@ static int _nfs4_open_delegated(struct inode *inode, int flags, struct rpc_cred set_bit(NFS_DELEGATED_STATE, &state->flags); update_open_stateid(state, &delegation->stateid, open_flags); out_ok: - up(&sp->so_sema); nfs4_put_state_owner(sp); up_read(&nfsi->rwsem); up_read(&clp->cl_sem); @@ -600,11 +654,12 @@ out_err: if (sp != NULL) { if (state != NULL) nfs4_put_open_state(state); - up(&sp->so_sema); nfs4_put_state_owner(sp); } up_read(&nfsi->rwsem); up_read(&clp->cl_sem); + if (err != -EACCES) + nfs_inode_return_delegation(inode); return err; } @@ -665,8 +720,10 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, int flags, st } else o_arg.u.attrs = sattr; /* Serialization for the sequence id */ - down(&sp->so_sema); + o_arg.seqid = nfs_alloc_seqid(&sp->so_seqid); + if (o_arg.seqid == NULL) + return -ENOMEM; status = _nfs4_proc_open(dir, sp, &o_arg, &o_res); if (status != 0) goto out_err; @@ -681,7 +738,7 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, int flags, st update_open_stateid(state, &o_res.stateid, flags); if (o_res.delegation_type != 0) nfs_inode_set_delegation(inode, cred, &o_res); - up(&sp->so_sema); + nfs_free_seqid(o_arg.seqid); nfs4_put_state_owner(sp); up_read(&clp->cl_sem); *res = state; @@ -690,7 +747,7 @@ out_err: if (sp != NULL) { if (state != NULL) nfs4_put_open_state(state); - up(&sp->so_sema); + nfs_free_seqid(o_arg.seqid); nfs4_put_state_owner(sp); } /* Note: clp->cl_sem must be released before nfs4_put_open_state()! */ @@ -718,7 +775,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry, * It is actually a sign of a bug on the client or on the server. * * If we receive a BAD_SEQID error in the particular case of - * doing an OPEN, we assume that nfs4_increment_seqid() will + * doing an OPEN, we assume that nfs_increment_open_seqid() will * have unhashed the old state_owner for us, and that we can * therefore safely retry using a new one. We should still warn * the user though... @@ -728,6 +785,16 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry, exception.retry = 1; continue; } + /* + * BAD_STATEID on OPEN means that the server cancelled our + * state before it received the OPEN_CONFIRM. + * Recover by retrying the request as per the discussion + * on Page 181 of RFC3530. + */ + if (status == -NFS4ERR_BAD_STATEID) { + exception.retry = 1; + continue; + } res = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir), status, &exception)); } while (exception.retry); @@ -789,17 +856,27 @@ struct nfs4_closedata { struct nfs_closeres res; }; +static void nfs4_free_closedata(struct nfs4_closedata *calldata) +{ + struct nfs4_state *state = calldata->state; + struct nfs4_state_owner *sp = state->owner; + + nfs4_put_open_state(calldata->state); + nfs_free_seqid(calldata->arg.seqid); + nfs4_put_state_owner(sp); + kfree(calldata); +} + static void nfs4_close_done(struct rpc_task *task) { struct nfs4_closedata *calldata = (struct nfs4_closedata *)task->tk_calldata; struct nfs4_state *state = calldata->state; - struct nfs4_state_owner *sp = state->owner; struct nfs_server *server = NFS_SERVER(calldata->inode); /* hmm. we are done with the inode, and in the process of freeing * the state_owner. we keep this around to process errors */ - nfs4_increment_seqid(task->tk_status, sp); + nfs_increment_open_seqid(task->tk_status, calldata->arg.seqid); switch (task->tk_status) { case 0: memcpy(&state->stateid, &calldata->res.stateid, @@ -817,24 +894,46 @@ static void nfs4_close_done(struct rpc_task *task) } } state->state = calldata->arg.open_flags; - nfs4_put_open_state(state); - up(&sp->so_sema); - nfs4_put_state_owner(sp); - up_read(&server->nfs4_state->cl_sem); - kfree(calldata); + nfs4_free_closedata(calldata); } -static inline int nfs4_close_call(struct rpc_clnt *clnt, struct nfs4_closedata *calldata) +static void nfs4_close_begin(struct rpc_task *task) { + struct nfs4_closedata *calldata = (struct nfs4_closedata *)task->tk_calldata; + struct nfs4_state *state = calldata->state; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE], .rpc_argp = &calldata->arg, .rpc_resp = &calldata->res, - .rpc_cred = calldata->state->owner->so_cred, + .rpc_cred = state->owner->so_cred, }; - if (calldata->arg.open_flags != 0) + int mode = 0; + int status; + + status = nfs_wait_on_sequence(calldata->arg.seqid, task); + if (status != 0) + return; + /* Don't reorder reads */ + smp_rmb(); + /* Recalculate the new open mode in case someone reopened the file + * while we were waiting in line to be scheduled. + */ + if (state->nreaders != 0) + mode |= FMODE_READ; + if (state->nwriters != 0) + mode |= FMODE_WRITE; + if (test_bit(NFS_DELEGATED_STATE, &state->flags)) + state->state = mode; + if (mode == state->state) { + nfs4_free_closedata(calldata); + task->tk_exit = NULL; + rpc_exit(task, 0); + return; + } + if (mode != 0) msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE]; - return rpc_call_async(clnt, &msg, 0, nfs4_close_done, calldata); + calldata->arg.open_flags = mode; + rpc_call_setup(task, &msg, 0); } /* @@ -851,39 +950,52 @@ static inline int nfs4_close_call(struct rpc_clnt *clnt, struct nfs4_closedata * int nfs4_do_close(struct inode *inode, struct nfs4_state *state, mode_t mode) { struct nfs4_closedata *calldata; - int status; + int status = -ENOMEM; - /* Tell caller we're done */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags)) { - state->state = mode; - return 0; - } - calldata = (struct nfs4_closedata *)kmalloc(sizeof(*calldata), GFP_KERNEL); + calldata = kmalloc(sizeof(*calldata), GFP_KERNEL); if (calldata == NULL) - return -ENOMEM; + goto out; calldata->inode = inode; calldata->state = state; calldata->arg.fh = NFS_FH(inode); + calldata->arg.stateid = &state->stateid; /* Serialization for the sequence id */ - calldata->arg.seqid = state->owner->so_seqid; - calldata->arg.open_flags = mode; - memcpy(&calldata->arg.stateid, &state->stateid, - sizeof(calldata->arg.stateid)); - status = nfs4_close_call(NFS_SERVER(inode)->client, calldata); - /* - * Return -EINPROGRESS on success in order to indicate to the - * caller that an asynchronous RPC call has been launched, and - * that it will release the semaphores on completion. - */ - return (status == 0) ? -EINPROGRESS : status; + calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid); + if (calldata->arg.seqid == NULL) + goto out_free_calldata; + + status = nfs4_call_async(NFS_SERVER(inode)->client, nfs4_close_begin, + nfs4_close_done, calldata); + if (status == 0) + goto out; + + nfs_free_seqid(calldata->arg.seqid); +out_free_calldata: + kfree(calldata); +out: + return status; } -struct inode * +static void nfs4_intent_set_file(struct nameidata *nd, struct dentry *dentry, struct nfs4_state *state) +{ + struct file *filp; + + filp = lookup_instantiate_filp(nd, dentry, NULL); + if (!IS_ERR(filp)) { + struct nfs_open_context *ctx; + ctx = (struct nfs_open_context *)filp->private_data; + ctx->state = state; + } else + nfs4_close_state(state, nd->intent.open.flags); +} + +struct dentry * nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { struct iattr attr; struct rpc_cred *cred; struct nfs4_state *state; + struct dentry *res; if (nd->flags & LOOKUP_CREATE) { attr.ia_mode = nd->intent.open.create_mode; @@ -897,16 +1009,23 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd) cred = rpcauth_lookupcred(NFS_SERVER(dir)->client->cl_auth, 0); if (IS_ERR(cred)) - return (struct inode *)cred; + return (struct dentry *)cred; state = nfs4_do_open(dir, dentry, nd->intent.open.flags, &attr, cred); put_rpccred(cred); - if (IS_ERR(state)) - return (struct inode *)state; - return state->inode; + if (IS_ERR(state)) { + if (PTR_ERR(state) == -ENOENT) + d_add(dentry, NULL); + return (struct dentry *)state; + } + res = d_add_unique(dentry, state->inode); + if (res != NULL) + dentry = res; + nfs4_intent_set_file(nd, dentry, state); + return res; } int -nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags) +nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, struct nameidata *nd) { struct rpc_cred *cred; struct nfs4_state *state; @@ -919,18 +1038,30 @@ nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags) if (IS_ERR(state)) state = nfs4_do_open(dir, dentry, openflags, NULL, cred); put_rpccred(cred); - if (state == ERR_PTR(-ENOENT) && dentry->d_inode == 0) - return 1; - if (IS_ERR(state)) - return 0; + if (IS_ERR(state)) { + switch (PTR_ERR(state)) { + case -EPERM: + case -EACCES: + case -EDQUOT: + case -ENOSPC: + case -EROFS: + lookup_instantiate_filp(nd, (struct dentry *)state, NULL); + return 1; + case -ENOENT: + if (dentry->d_inode == NULL) + return 1; + } + goto out_drop; + } inode = state->inode; + iput(inode); if (inode == dentry->d_inode) { - iput(inode); + nfs4_intent_set_file(nd, dentry, state); return 1; } - d_drop(dentry); nfs4_close_state(state, openflags); - iput(inode); +out_drop: + d_drop(dentry); return 0; } @@ -1431,7 +1562,7 @@ static int nfs4_proc_commit(struct nfs_write_data *cdata) static int nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags) + int flags, struct nameidata *nd) { struct nfs4_state *state; struct rpc_cred *cred; @@ -1453,13 +1584,13 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, struct nfs_fattr fattr; status = nfs4_do_setattr(NFS_SERVER(dir), &fattr, NFS_FH(state->inode), sattr, state); - if (status == 0) { + if (status == 0) nfs_setattr_update_inode(state->inode, sattr); - goto out; - } - } else if (flags != 0) - goto out; - nfs4_close_state(state, flags); + } + if (status == 0 && nd != NULL && (nd->flags & LOOKUP_OPEN)) + nfs4_intent_set_file(nd, dentry, state); + else + nfs4_close_state(state, flags); out: return status; } @@ -2106,65 +2237,6 @@ nfs4_proc_renew(struct nfs4_client *clp) return 0; } -/* - * We will need to arrange for the VFS layer to provide an atomic open. - * Until then, this open method is prone to inefficiency and race conditions - * due to the lookup, potential create, and open VFS calls from sys_open() - * placed on the wire. - */ -static int -nfs4_proc_file_open(struct inode *inode, struct file *filp) -{ - struct dentry *dentry = filp->f_dentry; - struct nfs_open_context *ctx; - struct nfs4_state *state = NULL; - struct rpc_cred *cred; - int status = -ENOMEM; - - dprintk("nfs4_proc_file_open: starting on (%.*s/%.*s)\n", - (int)dentry->d_parent->d_name.len, - dentry->d_parent->d_name.name, - (int)dentry->d_name.len, dentry->d_name.name); - - - /* Find our open stateid */ - cred = rpcauth_lookupcred(NFS_SERVER(inode)->client->cl_auth, 0); - if (IS_ERR(cred)) - return PTR_ERR(cred); - ctx = alloc_nfs_open_context(dentry, cred); - put_rpccred(cred); - if (unlikely(ctx == NULL)) - return -ENOMEM; - status = -EIO; /* ERACE actually */ - state = nfs4_find_state(inode, cred, filp->f_mode); - if (unlikely(state == NULL)) - goto no_state; - ctx->state = state; - nfs4_close_state(state, filp->f_mode); - ctx->mode = filp->f_mode; - nfs_file_set_open_context(filp, ctx); - put_nfs_open_context(ctx); - if (filp->f_mode & FMODE_WRITE) - nfs_begin_data_update(inode); - return 0; -no_state: - printk(KERN_WARNING "NFS: v4 raced in function %s\n", __FUNCTION__); - put_nfs_open_context(ctx); - return status; -} - -/* - * Release our state - */ -static int -nfs4_proc_file_release(struct inode *inode, struct file *filp) -{ - if (filp->f_mode & FMODE_WRITE) - nfs_end_data_update(inode); - nfs_file_clear_open_context(filp); - return 0; -} - static inline int nfs4_server_supports_acls(struct nfs_server *server) { return (server->caps & NFS_CAP_ACLS) @@ -2345,6 +2417,7 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen if (!nfs4_server_supports_acls(server)) return -EOPNOTSUPP; + nfs_inode_return_delegation(inode); buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase); ret = rpc_call_sync(NFS_SERVER(inode)->client, &msg, 0); if (ret == 0) @@ -2353,7 +2426,7 @@ static int nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t buflen } static int -nfs4_async_handle_error(struct rpc_task *task, struct nfs_server *server) +nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server) { struct nfs4_client *clp = server->nfs4_state; @@ -2431,7 +2504,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) /* This is the error handling routine for processes that are allowed * to sleep. */ -int nfs4_handle_exception(struct nfs_server *server, int errorcode, struct nfs4_exception *exception) +int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception) { struct nfs4_client *clp = server->nfs4_state; int ret = errorcode; @@ -2632,7 +2705,6 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock down_read(&clp->cl_sem); nlo.clientid = clp->cl_clientid; - down(&state->lock_sema); status = nfs4_set_lock_state(state, request); if (status != 0) goto out; @@ -2659,7 +2731,6 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock status = 0; } out: - up(&state->lock_sema); up_read(&clp->cl_sem); return status; } @@ -2696,67 +2767,125 @@ static int do_vfs_lock(struct file *file, struct file_lock *fl) return res; } -static int _nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *request) +struct nfs4_unlockdata { + struct nfs_lockargs arg; + struct nfs_locku_opargs luargs; + struct nfs_lockres res; + struct nfs4_lock_state *lsp; + struct nfs_open_context *ctx; + atomic_t refcount; + struct completion completion; +}; + +static void nfs4_locku_release_calldata(struct nfs4_unlockdata *calldata) { - struct inode *inode = state->inode; - struct nfs_server *server = NFS_SERVER(inode); - struct nfs4_client *clp = server->nfs4_state; - struct nfs_lockargs arg = { - .fh = NFS_FH(inode), - .type = nfs4_lck_type(cmd, request), - .offset = request->fl_start, - .length = nfs4_lck_length(request), - }; - struct nfs_lockres res = { - .server = server, - }; + if (atomic_dec_and_test(&calldata->refcount)) { + nfs_free_seqid(calldata->luargs.seqid); + nfs4_put_lock_state(calldata->lsp); + put_nfs_open_context(calldata->ctx); + kfree(calldata); + } +} + +static void nfs4_locku_complete(struct nfs4_unlockdata *calldata) +{ + complete(&calldata->completion); + nfs4_locku_release_calldata(calldata); +} + +static void nfs4_locku_done(struct rpc_task *task) +{ + struct nfs4_unlockdata *calldata = (struct nfs4_unlockdata *)task->tk_calldata; + + nfs_increment_lock_seqid(task->tk_status, calldata->luargs.seqid); + switch (task->tk_status) { + case 0: + memcpy(calldata->lsp->ls_stateid.data, + calldata->res.u.stateid.data, + sizeof(calldata->lsp->ls_stateid.data)); + break; + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_EXPIRED: + nfs4_schedule_state_recovery(calldata->res.server->nfs4_state); + break; + default: + if (nfs4_async_handle_error(task, calldata->res.server) == -EAGAIN) { + rpc_restart_call(task); + return; + } + } + nfs4_locku_complete(calldata); +} + +static void nfs4_locku_begin(struct rpc_task *task) +{ + struct nfs4_unlockdata *calldata = (struct nfs4_unlockdata *)task->tk_calldata; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOCKU], - .rpc_argp = &arg, - .rpc_resp = &res, - .rpc_cred = state->owner->so_cred, + .rpc_argp = &calldata->arg, + .rpc_resp = &calldata->res, + .rpc_cred = calldata->lsp->ls_state->owner->so_cred, }; - struct nfs4_lock_state *lsp; - struct nfs_locku_opargs luargs; int status; - - down_read(&clp->cl_sem); - down(&state->lock_sema); - status = nfs4_set_lock_state(state, request); - if (status != 0) - goto out; - lsp = request->fl_u.nfs4_fl.owner; - /* We might have lost the locks! */ - if ((lsp->ls_flags & NFS_LOCK_INITIALIZED) == 0) - goto out; - luargs.seqid = lsp->ls_seqid; - memcpy(&luargs.stateid, &lsp->ls_stateid, sizeof(luargs.stateid)); - arg.u.locku = &luargs; - status = rpc_call_sync(server->client, &msg, RPC_TASK_NOINTR); - nfs4_increment_lock_seqid(status, lsp); - if (status == 0) - memcpy(&lsp->ls_stateid, &res.u.stateid, - sizeof(lsp->ls_stateid)); -out: - up(&state->lock_sema); - if (status == 0) - do_vfs_lock(request->fl_file, request); - up_read(&clp->cl_sem); - return status; + status = nfs_wait_on_sequence(calldata->luargs.seqid, task); + if (status != 0) + return; + if ((calldata->lsp->ls_flags & NFS_LOCK_INITIALIZED) == 0) { + nfs4_locku_complete(calldata); + task->tk_exit = NULL; + rpc_exit(task, 0); + return; + } + rpc_call_setup(task, &msg, 0); } static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *request) { - struct nfs4_exception exception = { }; - int err; + struct nfs4_unlockdata *calldata; + struct inode *inode = state->inode; + struct nfs_server *server = NFS_SERVER(inode); + struct nfs4_lock_state *lsp; + int status; - do { - err = nfs4_handle_exception(NFS_SERVER(state->inode), - _nfs4_proc_unlck(state, cmd, request), - &exception); - } while (exception.retry); - return err; + status = nfs4_set_lock_state(state, request); + if (status != 0) + return status; + lsp = request->fl_u.nfs4_fl.owner; + /* We might have lost the locks! */ + if ((lsp->ls_flags & NFS_LOCK_INITIALIZED) == 0) + return 0; + calldata = kmalloc(sizeof(*calldata), GFP_KERNEL); + if (calldata == NULL) + return -ENOMEM; + calldata->luargs.seqid = nfs_alloc_seqid(&lsp->ls_seqid); + if (calldata->luargs.seqid == NULL) { + kfree(calldata); + return -ENOMEM; + } + calldata->luargs.stateid = &lsp->ls_stateid; + calldata->arg.fh = NFS_FH(inode); + calldata->arg.type = nfs4_lck_type(cmd, request); + calldata->arg.offset = request->fl_start; + calldata->arg.length = nfs4_lck_length(request); + calldata->arg.u.locku = &calldata->luargs; + calldata->res.server = server; + calldata->lsp = lsp; + atomic_inc(&lsp->ls_count); + + /* Ensure we don't close file until we're done freeing locks! */ + calldata->ctx = get_nfs_open_context((struct nfs_open_context*)request->fl_file->private_data); + + atomic_set(&calldata->refcount, 2); + init_completion(&calldata->completion); + + status = nfs4_call_async(NFS_SERVER(inode)->client, nfs4_locku_begin, + nfs4_locku_done, calldata); + if (status == 0) + wait_for_completion_interruptible(&calldata->completion); + do_vfs_lock(request->fl_file, request); + nfs4_locku_release_calldata(calldata); + return status; } static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *request, int reclaim) @@ -2764,11 +2893,23 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *r struct inode *inode = state->inode; struct nfs_server *server = NFS_SERVER(inode); struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner; + struct nfs_lock_opargs largs = { + .lock_stateid = &lsp->ls_stateid, + .open_stateid = &state->stateid, + .lock_owner = { + .clientid = server->nfs4_state->cl_clientid, + .id = lsp->ls_id, + }, + .reclaim = reclaim, + }; struct nfs_lockargs arg = { .fh = NFS_FH(inode), .type = nfs4_lck_type(cmd, request), .offset = request->fl_start, .length = nfs4_lck_length(request), + .u = { + .lock = &largs, + }, }; struct nfs_lockres res = { .server = server, @@ -2779,53 +2920,39 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *r .rpc_resp = &res, .rpc_cred = state->owner->so_cred, }; - struct nfs_lock_opargs largs = { - .reclaim = reclaim, - .new_lock_owner = 0, - }; - int status; + int status = -ENOMEM; - if (!(lsp->ls_flags & NFS_LOCK_INITIALIZED)) { + largs.lock_seqid = nfs_alloc_seqid(&lsp->ls_seqid); + if (largs.lock_seqid == NULL) + return -ENOMEM; + if (!(lsp->ls_seqid.flags & NFS_SEQID_CONFIRMED)) { struct nfs4_state_owner *owner = state->owner; - struct nfs_open_to_lock otl = { - .lock_owner = { - .clientid = server->nfs4_state->cl_clientid, - }, - }; - otl.lock_seqid = lsp->ls_seqid; - otl.lock_owner.id = lsp->ls_id; - memcpy(&otl.open_stateid, &state->stateid, sizeof(otl.open_stateid)); - largs.u.open_lock = &otl; + largs.open_seqid = nfs_alloc_seqid(&owner->so_seqid); + if (largs.open_seqid == NULL) + goto out; largs.new_lock_owner = 1; - arg.u.lock = &largs; - down(&owner->so_sema); - otl.open_seqid = owner->so_seqid; status = rpc_call_sync(server->client, &msg, RPC_TASK_NOINTR); - /* increment open_owner seqid on success, and - * seqid mutating errors */ - nfs4_increment_seqid(status, owner); - up(&owner->so_sema); - if (status == 0) { - lsp->ls_flags |= NFS_LOCK_INITIALIZED; - lsp->ls_seqid++; + /* increment open seqid on success, and seqid mutating errors */ + if (largs.new_lock_owner != 0) { + nfs_increment_open_seqid(status, largs.open_seqid); + if (status == 0) + nfs_confirm_seqid(&lsp->ls_seqid, 0); } - } else { - struct nfs_exist_lock el = { - .seqid = lsp->ls_seqid, - }; - memcpy(&el.stateid, &lsp->ls_stateid, sizeof(el.stateid)); - largs.u.exist_lock = ⪙ - arg.u.lock = &largs; + nfs_free_seqid(largs.open_seqid); + } else status = rpc_call_sync(server->client, &msg, RPC_TASK_NOINTR); - /* increment seqid on success, and * seqid mutating errors*/ - nfs4_increment_lock_seqid(status, lsp); - } + /* increment lock seqid on success, and seqid mutating errors*/ + nfs_increment_lock_seqid(status, largs.lock_seqid); /* save the returned stateid. */ - if (status == 0) - memcpy(&lsp->ls_stateid, &res.u.stateid, sizeof(nfs4_stateid)); - else if (status == -NFS4ERR_DENIED) + if (status == 0) { + memcpy(lsp->ls_stateid.data, res.u.stateid.data, + sizeof(lsp->ls_stateid.data)); + lsp->ls_flags |= NFS_LOCK_INITIALIZED; + } else if (status == -NFS4ERR_DENIED) status = -EAGAIN; +out: + nfs_free_seqid(largs.lock_seqid); return status; } @@ -2865,11 +2992,9 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock int status; down_read(&clp->cl_sem); - down(&state->lock_sema); status = nfs4_set_lock_state(state, request); if (status == 0) status = _nfs4_do_setlk(state, cmd, request, 0); - up(&state->lock_sema); if (status == 0) { /* Note: we always want to sleep here! */ request->fl_flags |= FL_SLEEP; @@ -3024,8 +3149,8 @@ struct nfs_rpc_ops nfs_v4_clientops = { .read_setup = nfs4_proc_read_setup, .write_setup = nfs4_proc_write_setup, .commit_setup = nfs4_proc_commit_setup, - .file_open = nfs4_proc_file_open, - .file_release = nfs4_proc_file_release, + .file_open = nfs_open, + .file_release = nfs_release, .lock = nfs4_proc_lock, .clear_acl_cache = nfs4_zap_acl_attr, }; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index afe587d82f1e..23834c8fb740 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -264,13 +264,15 @@ nfs4_alloc_state_owner(void) { struct nfs4_state_owner *sp; - sp = kmalloc(sizeof(*sp),GFP_KERNEL); + sp = kzalloc(sizeof(*sp),GFP_KERNEL); if (!sp) return NULL; - init_MUTEX(&sp->so_sema); - sp->so_seqid = 0; /* arbitrary */ INIT_LIST_HEAD(&sp->so_states); INIT_LIST_HEAD(&sp->so_delegations); + rpc_init_wait_queue(&sp->so_sequence.wait, "Seqid_waitqueue"); + sp->so_seqid.sequence = &sp->so_sequence; + spin_lock_init(&sp->so_sequence.lock); + INIT_LIST_HEAD(&sp->so_sequence.list); atomic_set(&sp->so_count, 1); return sp; } @@ -359,7 +361,6 @@ nfs4_alloc_open_state(void) memset(state->stateid.data, 0, sizeof(state->stateid.data)); atomic_set(&state->count, 1); INIT_LIST_HEAD(&state->lock_states); - init_MUTEX(&state->lock_sema); spin_lock_init(&state->state_lock); return state; } @@ -441,7 +442,6 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner) state = __nfs4_find_state_byowner(inode, owner); if (state == NULL && new != NULL) { state = new; - /* Caller *must* be holding owner->so_sem */ /* Note: The reclaim code dictates that we add stateless * and read-only stateids to the end of the list */ list_add_tail(&state->open_states, &owner->so_states); @@ -461,7 +461,7 @@ out: /* * Beware! Caller must be holding exactly one - * reference to clp->cl_sem and owner->so_sema! + * reference to clp->cl_sem! */ void nfs4_put_open_state(struct nfs4_state *state) { @@ -481,19 +481,15 @@ void nfs4_put_open_state(struct nfs4_state *state) } /* - * Beware! Caller must be holding no references to clp->cl_sem! - * of owner->so_sema! + * Close the current file. */ void nfs4_close_state(struct nfs4_state *state, mode_t mode) { struct inode *inode = state->inode; struct nfs4_state_owner *owner = state->owner; - struct nfs4_client *clp = owner->so_client; int newstate; atomic_inc(&owner->so_count); - down_read(&clp->cl_sem); - down(&owner->so_sema); /* Protect against nfs4_find_state() */ spin_lock(&inode->i_lock); if (mode & FMODE_READ) @@ -515,14 +511,16 @@ void nfs4_close_state(struct nfs4_state *state, mode_t mode) newstate |= FMODE_WRITE; if (state->state == newstate) goto out; - if (nfs4_do_close(inode, state, newstate) == -EINPROGRESS) + if (test_bit(NFS_DELEGATED_STATE, &state->flags)) { + state->state = newstate; + goto out; + } + if (nfs4_do_close(inode, state, newstate) == 0) return; } out: nfs4_put_open_state(state); - up(&owner->so_sema); nfs4_put_state_owner(owner); - up_read(&clp->cl_sem); } /* @@ -546,19 +544,16 @@ __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner) * Return a compatible lock_state. If no initialized lock_state structure * exists, return an uninitialized one. * - * The caller must be holding state->lock_sema */ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner) { struct nfs4_lock_state *lsp; struct nfs4_client *clp = state->owner->so_client; - lsp = kmalloc(sizeof(*lsp), GFP_KERNEL); + lsp = kzalloc(sizeof(*lsp), GFP_KERNEL); if (lsp == NULL) return NULL; - lsp->ls_flags = 0; - lsp->ls_seqid = 0; /* arbitrary */ - memset(lsp->ls_stateid.data, 0, sizeof(lsp->ls_stateid.data)); + lsp->ls_seqid.sequence = &state->owner->so_sequence; atomic_set(&lsp->ls_count, 1); lsp->ls_owner = fl_owner; spin_lock(&clp->cl_lock); @@ -572,7 +567,7 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f * Return a compatible lock_state. If no initialized lock_state structure * exists, return an uninitialized one. * - * The caller must be holding state->lock_sema and clp->cl_sem + * The caller must be holding clp->cl_sem */ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner) { @@ -605,7 +600,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_ * Release reference to lock_state, and free it if we see that * it is no longer in use */ -static void nfs4_put_lock_state(struct nfs4_lock_state *lsp) +void nfs4_put_lock_state(struct nfs4_lock_state *lsp) { struct nfs4_state *state; @@ -673,29 +668,98 @@ void nfs4_copy_stateid(nfs4_stateid *dst, struct nfs4_state *state, fl_owner_t f nfs4_put_lock_state(lsp); } -/* -* Called with state->lock_sema and clp->cl_sem held. -*/ -void nfs4_increment_lock_seqid(int status, struct nfs4_lock_state *lsp) +struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter) { - if (status == NFS_OK || seqid_mutating_err(-status)) - lsp->ls_seqid++; + struct rpc_sequence *sequence = counter->sequence; + struct nfs_seqid *new; + + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (new != NULL) { + new->sequence = counter; + new->task = NULL; + spin_lock(&sequence->lock); + list_add_tail(&new->list, &sequence->list); + spin_unlock(&sequence->lock); + } + return new; +} + +void nfs_free_seqid(struct nfs_seqid *seqid) +{ + struct rpc_sequence *sequence = seqid->sequence->sequence; + struct rpc_task *next = NULL; + + spin_lock(&sequence->lock); + list_del(&seqid->list); + if (!list_empty(&sequence->list)) { + next = list_entry(sequence->list.next, struct nfs_seqid, list)->task; + if (next) + rpc_wake_up_task(next); + } + spin_unlock(&sequence->lock); + kfree(seqid); } /* -* Called with sp->so_sema and clp->cl_sem held. -* -* Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or -* failed with a seqid incrementing error - -* see comments nfs_fs.h:seqid_mutating_error() -*/ -void nfs4_increment_seqid(int status, struct nfs4_state_owner *sp) + * Increment the seqid if the OPEN/OPEN_DOWNGRADE/CLOSE succeeded, or + * failed with a seqid incrementing error - + * see comments nfs_fs.h:seqid_mutating_error() + */ +static inline void nfs_increment_seqid(int status, struct nfs_seqid *seqid) { - if (status == NFS_OK || seqid_mutating_err(-status)) - sp->so_seqid++; - /* If the server returns BAD_SEQID, unhash state_owner here */ - if (status == -NFS4ERR_BAD_SEQID) + switch (status) { + case 0: + break; + case -NFS4ERR_BAD_SEQID: + case -NFS4ERR_STALE_CLIENTID: + case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_BAD_STATEID: + case -NFS4ERR_BADXDR: + case -NFS4ERR_RESOURCE: + case -NFS4ERR_NOFILEHANDLE: + /* Non-seqid mutating errors */ + return; + }; + /* + * Note: no locking needed as we are guaranteed to be first + * on the sequence list + */ + seqid->sequence->counter++; +} + +void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid) +{ + if (status == -NFS4ERR_BAD_SEQID) { + struct nfs4_state_owner *sp = container_of(seqid->sequence, + struct nfs4_state_owner, so_seqid); nfs4_drop_state_owner(sp); + } + return nfs_increment_seqid(status, seqid); +} + +/* + * Increment the seqid if the LOCK/LOCKU succeeded, or + * failed with a seqid incrementing error - + * see comments nfs_fs.h:seqid_mutating_error() + */ +void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid) +{ + return nfs_increment_seqid(status, seqid); +} + +int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task) +{ + struct rpc_sequence *sequence = seqid->sequence->sequence; + int status = 0; + + spin_lock(&sequence->lock); + if (sequence->list.next != &seqid->list) { + seqid->task = task; + rpc_sleep_on(&sequence->wait, task, NULL, NULL); + status = -EAGAIN; + } + spin_unlock(&sequence->lock); + return status; } static int reclaimer(void *); @@ -791,8 +855,6 @@ static int nfs4_reclaim_open_state(struct nfs4_state_recovery_ops *ops, struct n if (state->state == 0) continue; status = ops->recover_open(sp, state); - list_for_each_entry(lock, &state->lock_states, ls_locks) - lock->ls_flags &= ~NFS_LOCK_INITIALIZED; if (status >= 0) { status = nfs4_reclaim_locks(ops, state); if (status < 0) @@ -831,6 +893,26 @@ out_err: return status; } +static void nfs4_state_mark_reclaim(struct nfs4_client *clp) +{ + struct nfs4_state_owner *sp; + struct nfs4_state *state; + struct nfs4_lock_state *lock; + + /* Reset all sequence ids to zero */ + list_for_each_entry(sp, &clp->cl_state_owners, so_list) { + sp->so_seqid.counter = 0; + sp->so_seqid.flags = 0; + list_for_each_entry(state, &sp->so_states, open_states) { + list_for_each_entry(lock, &state->lock_states, ls_locks) { + lock->ls_seqid.counter = 0; + lock->ls_seqid.flags = 0; + lock->ls_flags &= ~NFS_LOCK_INITIALIZED; + } + } + } +} + static int reclaimer(void *ptr) { struct reclaimer_args *args = (struct reclaimer_args *)ptr; @@ -864,6 +946,7 @@ restart_loop: default: ops = &nfs4_network_partition_recovery_ops; }; + nfs4_state_mark_reclaim(clp); status = __nfs4_init_client(clp); if (status) goto out_error; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 6c564ef9489e..c5c75235c5b8 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -602,10 +602,10 @@ static int encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg) { uint32_t *p; - RESERVE_SPACE(8+sizeof(arg->stateid.data)); + RESERVE_SPACE(8+sizeof(arg->stateid->data)); WRITE32(OP_CLOSE); - WRITE32(arg->seqid); - WRITEMEM(arg->stateid.data, sizeof(arg->stateid.data)); + WRITE32(arg->seqid->sequence->counter); + WRITEMEM(arg->stateid->data, sizeof(arg->stateid->data)); return 0; } @@ -729,22 +729,18 @@ static int encode_lock(struct xdr_stream *xdr, const struct nfs_lockargs *arg) WRITE64(arg->length); WRITE32(opargs->new_lock_owner); if (opargs->new_lock_owner){ - struct nfs_open_to_lock *ol = opargs->u.open_lock; - RESERVE_SPACE(40); - WRITE32(ol->open_seqid); - WRITEMEM(&ol->open_stateid, sizeof(ol->open_stateid)); - WRITE32(ol->lock_seqid); - WRITE64(ol->lock_owner.clientid); + WRITE32(opargs->open_seqid->sequence->counter); + WRITEMEM(opargs->open_stateid->data, sizeof(opargs->open_stateid->data)); + WRITE32(opargs->lock_seqid->sequence->counter); + WRITE64(opargs->lock_owner.clientid); WRITE32(4); - WRITE32(ol->lock_owner.id); + WRITE32(opargs->lock_owner.id); } else { - struct nfs_exist_lock *el = opargs->u.exist_lock; - RESERVE_SPACE(20); - WRITEMEM(&el->stateid, sizeof(el->stateid)); - WRITE32(el->seqid); + WRITEMEM(opargs->lock_stateid->data, sizeof(opargs->lock_stateid->data)); + WRITE32(opargs->lock_seqid->sequence->counter); } return 0; @@ -775,8 +771,8 @@ static int encode_locku(struct xdr_stream *xdr, const struct nfs_lockargs *arg) RESERVE_SPACE(44); WRITE32(OP_LOCKU); WRITE32(arg->type); - WRITE32(opargs->seqid); - WRITEMEM(&opargs->stateid, sizeof(opargs->stateid)); + WRITE32(opargs->seqid->sequence->counter); + WRITEMEM(opargs->stateid->data, sizeof(opargs->stateid->data)); WRITE64(arg->offset); WRITE64(arg->length); @@ -826,7 +822,7 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena */ RESERVE_SPACE(8); WRITE32(OP_OPEN); - WRITE32(arg->seqid); + WRITE32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->open_flags); RESERVE_SPACE(16); WRITE64(arg->clientid); @@ -941,7 +937,7 @@ static int encode_open_confirm(struct xdr_stream *xdr, const struct nfs_open_con RESERVE_SPACE(8+sizeof(arg->stateid.data)); WRITE32(OP_OPEN_CONFIRM); WRITEMEM(arg->stateid.data, sizeof(arg->stateid.data)); - WRITE32(arg->seqid); + WRITE32(arg->seqid->sequence->counter); return 0; } @@ -950,10 +946,10 @@ static int encode_open_downgrade(struct xdr_stream *xdr, const struct nfs_closea { uint32_t *p; - RESERVE_SPACE(8+sizeof(arg->stateid.data)); + RESERVE_SPACE(8+sizeof(arg->stateid->data)); WRITE32(OP_OPEN_DOWNGRADE); - WRITEMEM(arg->stateid.data, sizeof(arg->stateid.data)); - WRITE32(arg->seqid); + WRITEMEM(arg->stateid->data, sizeof(arg->stateid->data)); + WRITE32(arg->seqid->sequence->counter); encode_share_access(xdr, arg->open_flags); return 0; } @@ -1437,6 +1433,9 @@ static int nfs4_xdr_enc_open(struct rpc_rqst *req, uint32_t *p, struct nfs_opena }; int status; + status = nfs_wait_on_sequence(args->seqid, req->rq_task); + if (status != 0) + goto out; xdr_init_encode(&xdr, &req->rq_snd_buf, p); encode_compound_hdr(&xdr, &hdr); status = encode_putfh(&xdr, args->fh); @@ -1464,6 +1463,9 @@ static int nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, uint32_t *p, struct n }; int status; + status = nfs_wait_on_sequence(args->seqid, req->rq_task); + if (status != 0) + goto out; xdr_init_encode(&xdr, &req->rq_snd_buf, p); encode_compound_hdr(&xdr, &hdr); status = encode_putfh(&xdr, args->fh); @@ -1485,6 +1487,9 @@ static int nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, uint32_t *p, struct nf }; int status; + status = nfs_wait_on_sequence(args->seqid, req->rq_task); + if (status != 0) + goto out; xdr_init_encode(&xdr, &req->rq_snd_buf, p); encode_compound_hdr(&xdr, &hdr); status = encode_putfh(&xdr, args->fh); @@ -1525,8 +1530,15 @@ static int nfs4_xdr_enc_lock(struct rpc_rqst *req, uint32_t *p, struct nfs_locka struct compound_hdr hdr = { .nops = 2, }; + struct nfs_lock_opargs *opargs = args->u.lock; int status; + status = nfs_wait_on_sequence(opargs->lock_seqid, req->rq_task); + if (status != 0) + goto out; + /* Do we need to do an open_to_lock_owner? */ + if (opargs->lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED) + opargs->new_lock_owner = 0; xdr_init_encode(&xdr, &req->rq_snd_buf, p); encode_compound_hdr(&xdr, &hdr); status = encode_putfh(&xdr, args->fh); @@ -2890,8 +2902,8 @@ static int decode_lock(struct xdr_stream *xdr, struct nfs_lockres *res) status = decode_op_hdr(xdr, OP_LOCK); if (status == 0) { - READ_BUF(sizeof(nfs4_stateid)); - COPYMEM(&res->u.stateid, sizeof(res->u.stateid)); + READ_BUF(sizeof(res->u.stateid.data)); + COPYMEM(res->u.stateid.data, sizeof(res->u.stateid.data)); } else if (status == -NFS4ERR_DENIED) return decode_lock_denied(xdr, &res->u.denied); return status; @@ -2913,8 +2925,8 @@ static int decode_locku(struct xdr_stream *xdr, struct nfs_lockres *res) status = decode_op_hdr(xdr, OP_LOCKU); if (status == 0) { - READ_BUF(sizeof(nfs4_stateid)); - COPYMEM(&res->u.stateid, sizeof(res->u.stateid)); + READ_BUF(sizeof(res->u.stateid.data)); + COPYMEM(res->u.stateid.data, sizeof(res->u.stateid.data)); } return status; } diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index be23c3fb9260..8fef86523d7f 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -216,7 +216,7 @@ static int nfs_proc_write(struct nfs_write_data *wdata) static int nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags) + int flags, struct nameidata *nd) { struct nfs_fh fhandle; struct nfs_fattr fattr; diff --git a/fs/open.c b/fs/open.c index f0d90cf0495c..8d06ec911fd9 100644 --- a/fs/open.c +++ b/fs/open.c @@ -739,7 +739,8 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group) } static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, - int flags, struct file *f) + int flags, struct file *f, + int (*open)(struct inode *, struct file *)) { struct inode *inode; int error; @@ -761,11 +762,14 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, f->f_op = fops_get(inode->i_fop); file_move(f, &inode->i_sb->s_files); - if (f->f_op && f->f_op->open) { - error = f->f_op->open(inode,f); + if (!open && f->f_op) + open = f->f_op->open; + if (open) { + error = open(inode, f); if (error) goto cleanup_all; } + f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); @@ -814,28 +818,75 @@ struct file *filp_open(const char * filename, int flags, int mode) { int namei_flags, error; struct nameidata nd; - struct file *f; namei_flags = flags; if ((namei_flags+1) & O_ACCMODE) namei_flags++; - if (namei_flags & O_TRUNC) - namei_flags |= 2; - - error = -ENFILE; - f = get_empty_filp(); - if (f == NULL) - return ERR_PTR(error); error = open_namei(filename, namei_flags, mode, &nd); if (!error) - return __dentry_open(nd.dentry, nd.mnt, flags, f); + return nameidata_to_filp(&nd, flags); - put_filp(f); return ERR_PTR(error); } EXPORT_SYMBOL(filp_open); +/** + * lookup_instantiate_filp - instantiates the open intent filp + * @nd: pointer to nameidata + * @dentry: pointer to dentry + * @open: open callback + * + * Helper for filesystems that want to use lookup open intents and pass back + * a fully instantiated struct file to the caller. + * This function is meant to be called from within a filesystem's + * lookup method. + * Note that in case of error, nd->intent.open.file is destroyed, but the + * path information remains valid. + * If the open callback is set to NULL, then the standard f_op->open() + * filesystem callback is substituted. + */ +struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, + int (*open)(struct inode *, struct file *)) +{ + if (IS_ERR(nd->intent.open.file)) + goto out; + if (IS_ERR(dentry)) + goto out_err; + nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->mnt), + nd->intent.open.flags - 1, + nd->intent.open.file, + open); +out: + return nd->intent.open.file; +out_err: + release_open_intent(nd); + nd->intent.open.file = (struct file *)dentry; + goto out; +} +EXPORT_SYMBOL_GPL(lookup_instantiate_filp); + +/** + * nameidata_to_filp - convert a nameidata to an open filp. + * @nd: pointer to nameidata + * @flags: open flags + * + * Note that this function destroys the original nameidata + */ +struct file *nameidata_to_filp(struct nameidata *nd, int flags) +{ + struct file *filp; + + /* Pick up the filp from the open intent */ + filp = nd->intent.open.file; + /* Has the filesystem initialised the file for us? */ + if (filp->f_dentry == NULL) + filp = __dentry_open(nd->dentry, nd->mnt, flags, filp, NULL); + else + path_release(nd); + return filp; +} + struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags) { int error; @@ -846,7 +897,7 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags) if (f == NULL) return ERR_PTR(error); - return __dentry_open(dentry, mnt, flags, f); + return __dentry_open(dentry, mnt, flags, f, NULL); } EXPORT_SYMBOL(dentry_open); diff --git a/fs/proc/base.c b/fs/proc/base.c index 3b33f94020db..a170450aadb1 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -103,7 +103,9 @@ enum pid_directory_inos { PROC_TGID_NUMA_MAPS, PROC_TGID_MOUNTS, PROC_TGID_WCHAN, +#ifdef CONFIG_MMU PROC_TGID_SMAPS, +#endif #ifdef CONFIG_SCHEDSTATS PROC_TGID_SCHEDSTAT, #endif @@ -141,7 +143,9 @@ enum pid_directory_inos { PROC_TID_NUMA_MAPS, PROC_TID_MOUNTS, PROC_TID_WCHAN, +#ifdef CONFIG_MMU PROC_TID_SMAPS, +#endif #ifdef CONFIG_SCHEDSTATS PROC_TID_SCHEDSTAT, #endif @@ -195,7 +199,9 @@ static struct pid_entry tgid_base_stuff[] = { E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), +#ifdef CONFIG_MMU E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), +#endif #ifdef CONFIG_SECURITY E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), #endif @@ -235,7 +241,9 @@ static struct pid_entry tid_base_stuff[] = { E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), +#ifdef CONFIG_MMU E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), +#endif #ifdef CONFIG_SECURITY E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), #endif @@ -630,6 +638,7 @@ static struct file_operations proc_numa_maps_operations = { }; #endif +#ifdef CONFIG_MMU extern struct seq_operations proc_pid_smaps_op; static int smaps_open(struct inode *inode, struct file *file) { @@ -648,6 +657,7 @@ static struct file_operations proc_smaps_operations = { .llseek = seq_lseek, .release = seq_release, }; +#endif extern struct seq_operations mounts_op; static int mounts_open(struct inode *inode, struct file *file) @@ -1681,10 +1691,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir, case PROC_TGID_MOUNTS: inode->i_fop = &proc_mounts_operations; break; +#ifdef CONFIG_MMU case PROC_TID_SMAPS: case PROC_TGID_SMAPS: inode->i_fop = &proc_smaps_operations; break; +#endif #ifdef CONFIG_SECURITY case PROC_TID_ATTR: inode->i_nlink = 2; diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index f3bf016d5ee3..cff10ab1af63 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -91,6 +91,7 @@ static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos) next = _rb; break; } + pos--; } return next; diff --git a/include/asm-arm/arch-pxa/pxafb.h b/include/asm-arm/arch-pxa/pxafb.h index 21c0e16dce5f..aba9b30f4249 100644 --- a/include/asm-arm/arch-pxa/pxafb.h +++ b/include/asm-arm/arch-pxa/pxafb.h @@ -66,4 +66,5 @@ struct pxafb_mach_info { }; void set_pxa_fb_info(struct pxafb_mach_info *hard_pxa_fb_info); +void set_pxa_fb_parent(struct device *parent_dev); unsigned long pxafb_get_hsync_time(struct device *dev); diff --git a/include/asm-arm/arch-s3c2410/io.h b/include/asm-arm/arch-s3c2410/io.h index 418233a7ee6f..4bf272ed9add 100644 --- a/include/asm-arm/arch-s3c2410/io.h +++ b/include/asm-arm/arch-s3c2410/io.h @@ -9,7 +9,7 @@ * 06-Dec-1997 RMK Created. * 02-Sep-2003 BJD Modified for S3C2410 * 10-Mar-2005 LCVR Changed S3C2410_VA to S3C24XX_VA - * + * 13-Oct-2005 BJD Fixed problems with LDRH/STRH offset range */ #ifndef __ASM_ARM_ARCH_IO_H @@ -97,7 +97,7 @@ DECLARE_IO(int,l,"") else \ __asm__ __volatile__( \ "strb %0, [%1, #0] @ outbc" \ - : : "r" (value), "r" ((port))); \ + : : "r" (value), "r" ((port))); \ }) #define __inbc(port) \ @@ -110,35 +110,61 @@ DECLARE_IO(int,l,"") else \ __asm__ __volatile__( \ "ldrb %0, [%1, #0] @ inbc" \ - : "=r" (result) : "r" ((port))); \ + : "=r" (result) : "r" ((port))); \ result; \ }) #define __outwc(value,port) \ ({ \ unsigned long v = value; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "strh %0, [%1, %2] @ outwc" \ - : : "r" (v), "r" (PCIO_BASE), "Jr" ((port))); \ - else \ + if (__PORT_PCIO((port))) { \ + if ((port) < 256 && (port) > -256) \ + __asm__ __volatile__( \ + "strh %0, [%1, %2] @ outwc" \ + : : "r" (v), "r" (PCIO_BASE), "Jr" ((port))); \ + else if ((port) > 0) \ + __asm__ __volatile__( \ + "strh %0, [%1, %2] @ outwc" \ + : : "r" (v), \ + "r" (PCIO_BASE + ((port) & ~0xff)), \ + "Jr" (((port) & 0xff))); \ + else \ + __asm__ __volatile__( \ + "strh %0, [%1, #0] @ outwc" \ + : : "r" (v), \ + "r" (PCIO_BASE + (port))); \ + } else \ __asm__ __volatile__( \ "strh %0, [%1, #0] @ outwc" \ - : : "r" (v), "r" ((port))); \ + : : "r" (v), "r" ((port))); \ }) #define __inwc(port) \ ({ \ unsigned short result; \ - if (__PORT_PCIO((port))) \ - __asm__ __volatile__( \ - "ldrh %0, [%1, %2] @ inwc" \ - : "=r" (result) : "r" (PCIO_BASE), "Jr" ((port))); \ - else \ + if (__PORT_PCIO((port))) { \ + if ((port) < 256 && (port) > -256 ) \ + __asm__ __volatile__( \ + "ldrh %0, [%1, %2] @ inwc" \ + : "=r" (result) \ + : "r" (PCIO_BASE), \ + "Jr" ((port))); \ + else if ((port) > 0) \ + __asm__ __volatile__( \ + "ldrh %0, [%1, %2] @ inwc" \ + : "=r" (result) \ + : "r" (PCIO_BASE + ((port) & ~0xff)), \ + "Jr" (((port) & 0xff))); \ + else \ + __asm__ __volatile__( \ + "ldrh %0, [%1, #0] @ inwc" \ + : "=r" (result) \ + : "r" (PCIO_BASE + ((port)))); \ + } else \ __asm__ __volatile__( \ "ldrh %0, [%1, #0] @ inwc" \ - : "=r" (result) : "r" ((port))); \ - result; \ + : "=r" (result) : "r" ((port))); \ + result; \ }) #define __outlc(value,port) \ diff --git a/include/asm-sparc64/pbm.h b/include/asm-sparc64/pbm.h index 38bbbccb4068..dd35a2c7798a 100644 --- a/include/asm-sparc64/pbm.h +++ b/include/asm-sparc64/pbm.h @@ -27,23 +27,27 @@ * PCI bus. */ -#define PBM_LOGCLUSTERS 3 -#define PBM_NCLUSTERS (1 << PBM_LOGCLUSTERS) - struct pci_controller_info; /* This contains the software state necessary to drive a PCI * controller's IOMMU. */ +struct pci_iommu_arena { + unsigned long *map; + unsigned int hint; + unsigned int limit; +}; + struct pci_iommu { /* This protects the controller's IOMMU and all * streaming buffers underneath. */ spinlock_t lock; + struct pci_iommu_arena arena; + /* IOMMU page table, a linear array of ioptes. */ iopte_t *page_table; /* The page table itself. */ - int page_table_sz_bits; /* log2 of ow many pages does it map? */ /* Base PCI memory space address where IOMMU mappings * begin. @@ -62,12 +66,6 @@ struct pci_iommu { */ unsigned long write_complete_reg; - /* The lowest used consistent mapping entry. Since - * we allocate consistent maps out of cluster 0 this - * is relative to the beginning of closter 0. - */ - u32 lowest_consistent_map; - /* In order to deal with some buggy third-party PCI bridges that * do wrong prefetching, we never mark valid mappings as invalid. * Instead we point them at this dummy page. @@ -75,16 +73,6 @@ struct pci_iommu { unsigned long dummy_page; unsigned long dummy_page_pa; - /* If PBM_NCLUSTERS is ever decreased to 4 or lower, - * or if largest supported page_table_sz * 8K goes above - * 2GB, you must increase the size of the type of - * these counters. You have been duly warned. -DaveM - */ - struct { - u16 next; - u16 flush; - } alloc_info[PBM_NCLUSTERS]; - /* CTX allocation. */ unsigned long ctx_lowest_free; unsigned long ctx_bitmap[IOMMU_NUM_CTXS / (sizeof(unsigned long) * 8)]; @@ -102,7 +90,7 @@ struct pci_iommu { u32 dma_addr_mask; }; -extern void pci_iommu_table_init(struct pci_iommu *, int); +extern void pci_iommu_table_init(struct pci_iommu *iommu, int tsbsize, u32 dma_offset, u32 dma_addr_mask); /* This describes a PCI bus module's streaming buffer. */ struct pci_strbuf { diff --git a/include/linux/acct.h b/include/linux/acct.h index 1993a3691768..19f70462b3be 100644 --- a/include/linux/acct.h +++ b/include/linux/acct.h @@ -162,13 +162,13 @@ typedef struct acct acct_t; #ifdef __KERNEL__ /* * Yet another set of HZ to *HZ helper functions. - * See for the original. + * See for the original. */ static inline u32 jiffies_to_AHZ(unsigned long x) { #if (TICK_NSEC % (NSEC_PER_SEC / AHZ)) == 0 - return x / (HZ / USER_HZ); + return x / (HZ / AHZ); #else u64 tmp = (u64)x * TICK_NSEC; do_div(tmp, (NSEC_PER_SEC / AHZ)); diff --git a/include/linux/aio.h b/include/linux/aio.h index 60def658b246..0decf66117c1 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -24,7 +24,12 @@ struct kioctx; #define KIOCB_SYNC_KEY (~0U) /* ki_flags bits */ -#define KIF_LOCKED 0 +/* + * This may be used for cancel/retry serialization in the future, but + * for now it's unused and we probably don't want modules to even + * think they can use it. + */ +/* #define KIF_LOCKED 0 */ #define KIF_KICKED 1 #define KIF_CANCELLED 2 diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index fe9778301d07..9bdba8169b41 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -393,15 +393,13 @@ extern cpumask_t cpu_present_map; #define for_each_present_cpu(cpu) for_each_cpu_mask((cpu), cpu_present_map) /* Find the highest possible smp_processor_id() */ -static inline unsigned int highest_possible_processor_id(void) -{ - unsigned int cpu, highest = 0; - - for_each_cpu_mask(cpu, cpu_possible_map) - highest = cpu; - - return highest; -} +#define highest_possible_processor_id() \ +({ \ + unsigned int cpu, highest = 0; \ + for_each_cpu_mask(cpu, cpu_possible_map) \ + highest = cpu; \ + highest; \ +}) #endif /* __LINUX_CPUMASK_H */ diff --git a/include/linux/list.h b/include/linux/list.h index e6ec59682274..084971f333fe 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -442,12 +442,14 @@ static inline void list_splice_init(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_rcu(pos, head) \ - for (pos = (head)->next; prefetch(pos->next), pos != (head); \ - pos = rcu_dereference(pos->next)) + for (pos = (head)->next; \ + prefetch(rcu_dereference(pos)->next), pos != (head); \ + pos = pos->next) #define __list_for_each_rcu(pos, head) \ - for (pos = (head)->next; pos != (head); \ - pos = rcu_dereference(pos->next)) + for (pos = (head)->next; \ + rcu_dereference(pos) != (head); \ + pos = pos->next) /** * list_for_each_safe_rcu - iterate over an rcu-protected list safe @@ -461,8 +463,9 @@ static inline void list_splice_init(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_safe_rcu(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = rcu_dereference(n), n = pos->next) + for (pos = (head)->next; \ + n = rcu_dereference(pos)->next, pos != (head); \ + pos = n) /** * list_for_each_entry_rcu - iterate over rcu list of given type @@ -474,11 +477,11 @@ static inline void list_splice_init(struct list_head *list, * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ -#define list_for_each_entry_rcu(pos, head, member) \ - for (pos = list_entry((head)->next, typeof(*pos), member); \ - prefetch(pos->member.next), &pos->member != (head); \ - pos = rcu_dereference(list_entry(pos->member.next, \ - typeof(*pos), member))) +#define list_for_each_entry_rcu(pos, head, member) \ + for (pos = list_entry((head)->next, typeof(*pos), member); \ + prefetch(rcu_dereference(pos)->member.next), \ + &pos->member != (head); \ + pos = list_entry(pos->member.next, typeof(*pos), member)) /** @@ -492,8 +495,9 @@ static inline void list_splice_init(struct list_head *list, * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_continue_rcu(pos, head) \ - for ((pos) = (pos)->next; prefetch((pos)->next), (pos) != (head); \ - (pos) = rcu_dereference((pos)->next)) + for ((pos) = (pos)->next; \ + prefetch(rcu_dereference((pos))->next), (pos) != (head); \ + (pos) = (pos)->next) /* * Double linked lists with a single pointer list head. @@ -696,8 +700,9 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, pos = n) #define hlist_for_each_rcu(pos, head) \ - for ((pos) = (head)->first; pos && ({ prefetch((pos)->next); 1; }); \ - (pos) = rcu_dereference((pos)->next)) + for ((pos) = (head)->first; \ + rcu_dereference((pos)) && ({ prefetch((pos)->next); 1; }); \ + (pos) = (pos)->next) /** * hlist_for_each_entry - iterate over list of given type @@ -762,9 +767,9 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, */ #define hlist_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = (head)->first; \ - pos && ({ prefetch(pos->next); 1;}) && \ + rcu_dereference(pos) && ({ prefetch(pos->next); 1;}) && \ ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \ - pos = rcu_dereference(pos->next)) + pos = pos->next) #else #warning "don't include kernel headers in userspace" diff --git a/include/linux/namei.h b/include/linux/namei.h index 7db67b008cac..1c975d0d9e94 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -8,6 +8,7 @@ struct vfsmount; struct open_intent { int flags; int create_mode; + struct file *file; }; enum { MAX_NESTED_LINKS = 5 }; @@ -65,6 +66,13 @@ extern int FASTCALL(link_path_walk(const char *, struct nameidata *)); extern void path_release(struct nameidata *); extern void path_release_on_umount(struct nameidata *); +extern int __user_path_lookup_open(const char __user *, unsigned lookup_flags, struct nameidata *nd, int open_flags); +extern int path_lookup_open(const char *, unsigned lookup_flags, struct nameidata *, int open_flags); +extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, + int (*open)(struct inode *, struct file *)); +extern struct file *nameidata_to_filp(struct nameidata *nd, int flags); +extern void release_open_intent(struct nameidata *); + extern struct dentry * lookup_one_len(const char *, struct dentry *, int); extern struct dentry * lookup_hash(struct qstr *, struct dentry *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index a2bf6914ff1b..60086dac11d5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -96,12 +96,13 @@ struct nfs4_change_info { u64 after; }; +struct nfs_seqid; /* * Arguments to the open call. */ struct nfs_openargs { const struct nfs_fh * fh; - __u32 seqid; + struct nfs_seqid * seqid; int open_flags; __u64 clientid; __u32 id; @@ -136,7 +137,7 @@ struct nfs_openres { struct nfs_open_confirmargs { const struct nfs_fh * fh; nfs4_stateid stateid; - __u32 seqid; + struct nfs_seqid * seqid; }; struct nfs_open_confirmres { @@ -148,8 +149,8 @@ struct nfs_open_confirmres { */ struct nfs_closeargs { struct nfs_fh * fh; - nfs4_stateid stateid; - __u32 seqid; + nfs4_stateid * stateid; + struct nfs_seqid * seqid; int open_flags; }; @@ -164,30 +165,19 @@ struct nfs_lowner { u32 id; }; -struct nfs_open_to_lock { - __u32 open_seqid; - nfs4_stateid open_stateid; - __u32 lock_seqid; - struct nfs_lowner lock_owner; -}; - -struct nfs_exist_lock { - nfs4_stateid stateid; - __u32 seqid; -}; - struct nfs_lock_opargs { + struct nfs_seqid * lock_seqid; + nfs4_stateid * lock_stateid; + struct nfs_seqid * open_seqid; + nfs4_stateid * open_stateid; + struct nfs_lowner lock_owner; __u32 reclaim; __u32 new_lock_owner; - union { - struct nfs_open_to_lock *open_lock; - struct nfs_exist_lock *exist_lock; - } u; }; struct nfs_locku_opargs { - __u32 seqid; - nfs4_stateid stateid; + struct nfs_seqid * seqid; + nfs4_stateid * stateid; }; struct nfs_lockargs { @@ -722,7 +712,7 @@ struct nfs_rpc_ops { int (*write) (struct nfs_write_data *); int (*commit) (struct nfs_write_data *); int (*create) (struct inode *, struct dentry *, - struct iattr *, int); + struct iattr *, int, struct nameidata *); int (*remove) (struct inode *, struct qstr *); int (*unlink_setup) (struct rpc_message *, struct dentry *, struct qstr *); diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4e65eb44adfd..70191a5a148f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -94,6 +94,7 @@ struct rcu_data { long batch; /* Batch # for current RCU batch */ struct rcu_head *nxtlist; struct rcu_head **nxttail; + long count; /* # of queued items */ struct rcu_head *curlist; struct rcu_head **curtail; struct rcu_head *donelist; diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 99cad3ead81d..068e1fb0868b 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -211,6 +211,7 @@ int xprt_reserve_xprt(struct rpc_task *task); int xprt_reserve_xprt_cong(struct rpc_task *task); int xprt_prepare_transmit(struct rpc_task *task); void xprt_transmit(struct rpc_task *task); +void xprt_abort_transmit(struct rpc_task *task); int xprt_adjust_timeout(struct rpc_rqst *req); void xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index ad85d3f0dcc4..7a51a5597c33 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -424,6 +424,7 @@ static void cleanup_timers(struct list_head *head, cputime_t ptime = cputime_add(utime, stime); list_for_each_entry_safe(timer, next, head, entry) { + put_task_struct(timer->task); timer->task = NULL; list_del_init(&timer->entry); if (cputime_lt(timer->expires.cpu, ptime)) { @@ -436,6 +437,7 @@ static void cleanup_timers(struct list_head *head, ++head; list_for_each_entry_safe(timer, next, head, entry) { + put_task_struct(timer->task); timer->task = NULL; list_del_init(&timer->entry); if (cputime_lt(timer->expires.cpu, utime)) { @@ -448,6 +450,7 @@ static void cleanup_timers(struct list_head *head, ++head; list_for_each_entry_safe(timer, next, head, entry) { + put_task_struct(timer->task); timer->task = NULL; list_del_init(&timer->entry); if (timer->expires.sched < sched_time) { diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index bef3b6901b76..2559d4b8f23f 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -71,7 +71,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L }; /* Fake initialization required by compiler */ static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL}; -static int maxbatch = 10; +static int maxbatch = 10000; #ifndef __HAVE_ARCH_CMPXCHG /* @@ -109,6 +109,10 @@ void fastcall call_rcu(struct rcu_head *head, rdp = &__get_cpu_var(rcu_data); *rdp->nxttail = head; rdp->nxttail = &head->next; + + if (unlikely(++rdp->count > 10000)) + set_need_resched(); + local_irq_restore(flags); } @@ -140,6 +144,12 @@ void fastcall call_rcu_bh(struct rcu_head *head, rdp = &__get_cpu_var(rcu_bh_data); *rdp->nxttail = head; rdp->nxttail = &head->next; + rdp->count++; +/* + * Should we directly call rcu_do_batch() here ? + * if (unlikely(rdp->count > 10000)) + * rcu_do_batch(rdp); + */ local_irq_restore(flags); } @@ -157,6 +167,7 @@ static void rcu_do_batch(struct rcu_data *rdp) next = rdp->donelist = list->next; list->func(list); list = next; + rdp->count--; if (++count >= maxbatch) break; } diff --git a/kernel/time.c b/kernel/time.c index dd5ae1162a8f..40c2410ac99a 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -570,6 +570,7 @@ void getnstimeofday(struct timespec *tv) tv->tv_sec = x.tv_sec; tv->tv_nsec = x.tv_usec * NSEC_PER_USEC; } +EXPORT_SYMBOL_GPL(getnstimeofday); #endif #if (BITS_PER_LONG < 64) diff --git a/mm/vmscan.c b/mm/vmscan.c index 0ea71e887bb6..64f9570cff56 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -511,10 +511,11 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc) * PageDirty _after_ making sure that the page is freeable and * not in use by anybody. (pagecache + us == 2) */ - if (page_count(page) != 2 || PageDirty(page)) { - write_unlock_irq(&mapping->tree_lock); - goto keep_locked; - } + if (unlikely(page_count(page) != 2)) + goto cannot_free; + smp_rmb(); + if (unlikely(PageDirty(page))) + goto cannot_free; #ifdef CONFIG_SWAP if (PageSwapCache(page)) { @@ -538,6 +539,10 @@ free_it: __pagevec_release_nonlru(&freed_pvec); continue; +cannot_free: + write_unlock_irq(&mapping->tree_lock); + goto keep_locked; + activate_locked: SetPageActive(page); pgactivate++; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index b03e90649eb5..21deec25a12b 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -975,7 +975,6 @@ replace_table(struct ip6t_table *table, struct ip6t_entry *table_base; unsigned int i; - for (i = 0; i < num_possible_cpus(); i++) { for_each_cpu(i) { table_base = (void *)newinfo->entries diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 5a8f01d726e9..534274056329 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -678,13 +678,11 @@ call_allocate(struct rpc_task *task) static void call_encode(struct rpc_task *task) { - struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; struct xdr_buf *sndbuf = &req->rq_snd_buf; struct xdr_buf *rcvbuf = &req->rq_rcv_buf; unsigned int bufsiz; kxdrproc_t encode; - int status; u32 *p; dprintk("RPC: %4d call_encode (status %d)\n", @@ -712,12 +710,9 @@ call_encode(struct rpc_task *task) rpc_exit(task, -EIO); return; } - if (encode && (status = rpcauth_wrap_req(task, encode, req, p, - task->tk_msg.rpc_argp)) < 0) { - printk(KERN_WARNING "%s: can't encode arguments: %d\n", - clnt->cl_protname, -status); - rpc_exit(task, status); - } + if (encode != NULL) + task->tk_status = rpcauth_wrap_req(task, encode, req, p, + task->tk_msg.rpc_argp); } /* @@ -759,7 +754,8 @@ call_bind_status(struct rpc_task *task) case -EACCES: dprintk("RPC: %4d remote rpcbind: RPC program/version unavailable\n", task->tk_pid); - break; + rpc_delay(task, 3*HZ); + goto retry_bind; case -ETIMEDOUT: dprintk("RPC: %4d rpcbind request timed out\n", task->tk_pid); @@ -864,10 +860,12 @@ call_transmit(struct rpc_task *task) if (task->tk_status != 0) return; /* Encode here so that rpcsec_gss can use correct sequence number. */ - if (!task->tk_rqstp->rq_bytes_sent) + if (task->tk_rqstp->rq_bytes_sent == 0) { call_encode(task); - if (task->tk_status < 0) - return; + /* Did the encode result in an error condition? */ + if (task->tk_status != 0) + goto out_nosend; + } xprt_transmit(task); if (task->tk_status < 0) return; @@ -875,6 +873,10 @@ call_transmit(struct rpc_task *task) task->tk_action = NULL; rpc_wake_up_task(task); } + return; +out_nosend: + /* release socket write lock before attempting to handle error */ + xprt_abort_transmit(task); } /* diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 215be0d0ef6b..1ba55dc38b7a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -709,6 +709,14 @@ out_unlock: return err; } +void +xprt_abort_transmit(struct rpc_task *task) +{ + struct rpc_xprt *xprt = task->tk_xprt; + + xprt_release_write(xprt, task); +} + /** * xprt_transmit - send an RPC request on a transport * @task: controlling RPC task