diff options
83 files changed, 1070 insertions, 1059 deletions
diff --git a/Documentation/devicetree/bindings/clock/uniphier-clock.txt b/Documentation/devicetree/bindings/clock/uniphier-clock.txt index c7179d3..8121630 100644 --- a/Documentation/devicetree/bindings/clock/uniphier-clock.txt +++ b/Documentation/devicetree/bindings/clock/uniphier-clock.txt @@ -24,7 +24,7 @@ Example: reg = <0x61840000 0x4000>; clock { - compatible = "socionext,uniphier-ld20-clock"; + compatible = "socionext,uniphier-ld11-clock"; #clock-cells = <1>; }; @@ -43,8 +43,8 @@ Provided clocks: 21: USB3 ch1 PHY1 -Media I/O (MIO) clock ---------------------- +Media I/O (MIO) clock, SD clock +------------------------------- Required properties: - compatible: should be one of the following: @@ -52,10 +52,10 @@ Required properties: "socionext,uniphier-ld4-mio-clock" - for LD4 SoC. "socionext,uniphier-pro4-mio-clock" - for Pro4 SoC. "socionext,uniphier-sld8-mio-clock" - for sLD8 SoC. - "socionext,uniphier-pro5-mio-clock" - for Pro5 SoC. - "socionext,uniphier-pxs2-mio-clock" - for PXs2/LD6b SoC. + "socionext,uniphier-pro5-sd-clock" - for Pro5 SoC. + "socionext,uniphier-pxs2-sd-clock" - for PXs2/LD6b SoC. "socionext,uniphier-ld11-mio-clock" - for LD11 SoC. - "socionext,uniphier-ld20-mio-clock" - for LD20 SoC. + "socionext,uniphier-ld20-sd-clock" - for LD20 SoC. - #clock-cells: should be 1. Example: @@ -66,7 +66,7 @@ Example: reg = <0x59810000 0x800>; clock { - compatible = "socionext,uniphier-ld20-mio-clock"; + compatible = "socionext,uniphier-ld11-mio-clock"; #clock-cells = <1>; }; @@ -112,7 +112,7 @@ Example: reg = <0x59820000 0x200>; clock { - compatible = "socionext,uniphier-ld20-peri-clock"; + compatible = "socionext,uniphier-ld11-peri-clock"; #clock-cells = <1>; }; diff --git a/Documentation/gpio/board.txt b/Documentation/gpio/board.txt index 40884c4..a0f6189 100644 --- a/Documentation/gpio/board.txt +++ b/Documentation/gpio/board.txt @@ -6,7 +6,7 @@ Note that it only applies to the new descriptor-based interface. For a description of the deprecated integer-based GPIO interface please refer to gpio-legacy.txt (actually, there is no real mapping possible with the old interface; you just fetch an integer from somewhere and request the -corresponding GPIO. +corresponding GPIO). All platforms can enable the GPIO library, but if the platform strictly requires GPIO functionality to be present, it needs to select GPIOLIB from its @@ -162,6 +162,9 @@ The driver controlling "foo.0" will then be able to obtain its GPIOs as follows: Since the "led" GPIOs are mapped as active-high, this example will switch their signals to 1, i.e. enabling the LEDs. And for the "power" GPIO, which is mapped -as active-low, its actual signal will be 0 after this code. Contrary to the legacy -integer GPIO interface, the active-low property is handled during mapping and is -thus transparent to GPIO consumers. +as active-low, its actual signal will be 0 after this code. Contrary to the +legacy integer GPIO interface, the active-low property is handled during +mapping and is thus transparent to GPIO consumers. + +A set of functions such as gpiod_set_value() is available to work with +the new descriptor-oriented interface. diff --git a/MAINTAINERS b/MAINTAINERS index c447953..f30b8ea7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8100,6 +8100,7 @@ S: Maintained F: drivers/media/dvb-frontends/mn88473* MODULE SUPPORT +M: Jessica Yu <jeyu@redhat.com> M: Rusty Russell <rusty@rustcorp.com.au> S: Maintained F: include/linux/module.h diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 64053d9..836c562 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -12,9 +12,7 @@ #ifndef __ASSEMBLY__ -unsigned long return_address(int depth); - -#define ftrace_return_address(n) return_address(n) +#define ftrace_return_address(n) __builtin_return_address(n) void _mcount(void); void ftrace_caller(void); diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 0332317..602af69 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -192,7 +192,7 @@ struct task_struct; struct mm_struct; struct seq_file; -typedef int (*dump_trace_func_t)(void *data, unsigned long address); +typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable); void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task, unsigned long sp); diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h index 02613ba..3066031 100644 --- a/arch/s390/include/asm/unistd.h +++ b/arch/s390/include/asm/unistd.h @@ -9,6 +9,9 @@ #include <uapi/asm/unistd.h> #define __IGNORE_time +#define __IGNORE_pkey_mprotect +#define __IGNORE_pkey_alloc +#define __IGNORE_pkey_free #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_SYS_ALARM diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c index 43446fa..c74c592 100644 --- a/arch/s390/kernel/dis.c +++ b/arch/s390/kernel/dis.c @@ -2014,12 +2014,12 @@ void show_code(struct pt_regs *regs) *ptr++ = '\t'; ptr += print_insn(ptr, code + start, addr); start += opsize; - printk("%s", buffer); + pr_cont("%s", buffer); ptr = buffer; ptr += sprintf(ptr, "\n "); hops++; } - printk("\n"); + pr_cont("\n"); } void print_fn_code(unsigned char *code, unsigned long len) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 6693383..55d4fe1 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -38,10 +38,10 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, if (sp < low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; + if (func(data, sf->gprs[8], 0)) + return sp; /* Follow the backchain. */ while (1) { - if (func(data, sf->gprs[8])) - return sp; low = sp; sp = sf->back_chain; if (!sp) @@ -49,6 +49,8 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, if (sp <= low || sp > high - sizeof(*sf)) return sp; sf = (struct stack_frame *) sp; + if (func(data, sf->gprs[8], 1)) + return sp; } /* Zero backchain detected, check for interrupt frame. */ sp = (unsigned long) (sf + 1); @@ -56,7 +58,7 @@ __dump_trace(dump_trace_func_t func, void *data, unsigned long sp, return sp; regs = (struct pt_regs *) sp; if (!user_mode(regs)) { - if (func(data, regs->psw.addr)) + if (func(data, regs->psw.addr, 1)) return sp; } low = sp; @@ -85,33 +87,12 @@ void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task, } EXPORT_SYMBOL_GPL(dump_trace); -struct return_address_data { - unsigned long address; - int depth; -}; - -static int __return_address(void *data, unsigned long address) -{ - struct return_address_data *rd = data; - - if (rd->depth--) - return 0; - rd->address = address; - return 1; -} - -unsigned long return_address(int depth) -{ - struct return_address_data rd = { .depth = depth + 2 }; - - dump_trace(__return_address, &rd, NULL, current_stack_pointer()); - return rd.address; -} -EXPORT_SYMBOL_GPL(return_address); - -static int show_address(void *data, unsigned long address) +static int show_address(void *data, unsigned long address, int reliable) { - printk("([<%016lx>] %pSR)\n", address, (void *)address); + if (reliable) + printk(" [<%016lx>] %pSR \n", address, (void *)address); + else + printk("([<%016lx>] %pSR)\n", address, (void *)address); return 0; } @@ -138,14 +119,14 @@ void show_stack(struct task_struct *task, unsigned long *sp) else stack = (unsigned long *)task->thread.ksp; } + printk(KERN_DEFAULT "Stack:\n"); for (i = 0; i < 20; i++) { if (((addr_t) stack & (THREAD_SIZE-1)) == 0) break; - if ((i * sizeof(long) % 32) == 0) - printk("%s ", i == 0 ? "" : "\n"); - printk("%016lx ", *stack++); + if (i % 4 == 0) + printk(KERN_DEFAULT " "); + pr_cont("%016lx%c", *stack++, i % 4 == 3 ? '\n' : ' '); } - printk("\n"); show_trace(task, (unsigned long)sp); } @@ -163,13 +144,13 @@ void show_registers(struct pt_regs *regs) mode = user_mode(regs) ? "User" : "Krnl"; printk("%s PSW : %p %p", mode, (void *)regs->psw.mask, (void *)regs->psw.addr); if (!user_mode(regs)) - printk(" (%pSR)", (void *)regs->psw.addr); - printk("\n"); + pr_cont(" (%pSR)", (void *)regs->psw.addr); + pr_cont("\n"); printk(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x " "P:%x AS:%x CC:%x PM:%x", psw->r, psw->t, psw->i, psw->e, psw->key, psw->m, psw->w, psw->p, psw->as, psw->cc, psw->pm); - printk(" RI:%x EA:%x", psw->ri, psw->eaba); - printk("\n%s GPRS: %016lx %016lx %016lx %016lx\n", mode, + pr_cont(" RI:%x EA:%x\n", psw->ri, psw->eaba); + printk("%s GPRS: %016lx %016lx %016lx %016lx\n", mode, regs->gprs[0], regs->gprs[1], regs->gprs[2], regs->gprs[3]); printk(" %016lx %016lx %016lx %016lx\n", regs->gprs[4], regs->gprs[5], regs->gprs[6], regs->gprs[7]); @@ -205,14 +186,14 @@ void die(struct pt_regs *regs, const char *str) printk("%s: %04x ilc:%d [#%d] ", str, regs->int_code & 0xffff, regs->int_code >> 17, ++die_counter); #ifdef CONFIG_PREEMPT - printk("PREEMPT "); + pr_cont("PREEMPT "); #endif #ifdef CONFIG_SMP - printk("SMP "); + pr_cont("SMP "); #endif if (debug_pagealloc_enabled()) - printk("DEBUG_PAGEALLOC"); - printk("\n"); + pr_cont("DEBUG_PAGEALLOC"); + pr_cont("\n"); notify_die(DIE_OOPS, str, regs, 0, regs->int_code & 0xffff, SIGSEGV); print_modules(); show_regs(regs); diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index 17431f6..955a7b6 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -222,7 +222,7 @@ static int __init service_level_perf_register(void) } arch_initcall(service_level_perf_register); -static int __perf_callchain_kernel(void *data, unsigned long address) +static int __perf_callchain_kernel(void *data, unsigned long address, int reliable) { struct perf_callchain_entry_ctx *entry = data; diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 44f84b2..355db9d 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -27,12 +27,12 @@ static int __save_address(void *data, unsigned long address, int nosched) return 1; } -static int save_address(void *data, unsigned long address) +static int save_address(void *data, unsigned long address, int reliable) { return __save_address(data, address, 0); } -static int save_address_nosched(void *data, unsigned long address) +static int save_address_nosched(void *data, unsigned long address, int reliable) { return __save_address(data, address, 1); } diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index cd404aa..4a0c5bc 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -217,6 +217,7 @@ static __init int setup_hugepagesz(char *opt) } else if (MACHINE_HAS_EDAT2 && size == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); } else { + hugetlb_bad_size(); pr_err("hugepagesz= specifies an unsupported page size %s\n", string); return 0; diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index f56a39b..b3e9d18 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -151,36 +151,40 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) #ifdef CONFIG_MEMORY_HOTPLUG int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { - unsigned long normal_end_pfn = PFN_DOWN(memblock_end_of_DRAM()); - unsigned long dma_end_pfn = PFN_DOWN(MAX_DMA_ADDRESS); + unsigned long zone_start_pfn, zone_end_pfn, nr_pages; unsigned long start_pfn = PFN_DOWN(start); unsigned long size_pages = PFN_DOWN(size); - unsigned long nr_pages; - int rc, zone_enum; + pg_data_t *pgdat = NODE_DATA(nid); + struct zone *zone; + int rc, i; rc = vmem_add_mapping(start, size); if (rc) return rc; - while (size_pages > 0) { - if (start_pfn < dma_end_pfn) { - nr_pages = (start_pfn + size_pages > dma_end_pfn) ? - dma_end_pfn - start_pfn : size_pages; - zone_enum = ZONE_DMA; - } else if (start_pfn < normal_end_pfn) { - nr_pages = (start_pfn + size_pages > normal_end_pfn) ? - normal_end_pfn - start_pfn : size_pages; - zone_enum = ZONE_NORMAL; + for (i = 0; i < MAX_NR_ZONES; i++) { + zone = pgdat->node_zones + i; + if (zone_idx(zone) != ZONE_MOVABLE) { + /* Add range within existing zone limits, if possible */ + zone_start_pfn = zone->zone_start_pfn; + zone_end_pfn = zone->zone_start_pfn + + zone->spanned_pages; } else { - nr_pages = size_pages; - zone_enum = ZONE_MOVABLE; + /* Add remaining range to ZONE_MOVABLE */ + zone_start_pfn = start_pfn; + zone_end_pfn = start_pfn + size_pages; } - rc = __add_pages(nid, NODE_DATA(nid)->node_zones + zone_enum, - start_pfn, size_pages); + if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn) + continue; + nr_pages = (start_pfn + size_pages > zone_end_pfn) ? + zone_end_pfn - start_pfn : size_pages; + rc = __add_pages(nid, zone, start_pfn, nr_pages); if (rc) break; start_pfn += nr_pages; size_pages -= nr_pages; + if (!size_pages) + break; } if (rc) vmem_remove_mapping(start, size); diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 16f4c39..9a4de45 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -13,7 +13,7 @@ #include <linux/init.h> #include <asm/processor.h> -static int __s390_backtrace(void *data, unsigned long address) +static int __s390_backtrace(void *data, unsigned long address, int reliable) { unsigned int *depth = data; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c0fdd57..bdd8556 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1837,6 +1837,7 @@ static void __init init_hvm_pv_info(void) xen_domain_type = XEN_HVM_DOMAIN; } +#endif static int xen_cpu_up_prepare(unsigned int cpu) { @@ -1887,6 +1888,7 @@ static int xen_cpu_up_online(unsigned int cpu) return 0; } +#ifdef CONFIG_XEN_PVHVM #ifdef CONFIG_KEXEC_CORE static void xen_hvm_shutdown(void) { diff --git a/block/badblocks.c b/block/badblocks.c index 6610e28..6ebcef2 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -133,6 +133,26 @@ retry: } EXPORT_SYMBOL_GPL(badblocks_check); +static void badblocks_update_acked(struct badblocks *bb) +{ + u64 *p = bb->page; + int i; + bool unacked = false; + + if (!bb->unacked_exist) + return; + + for (i = 0; i < bb->count ; i++) { + if (!BB_ACK(p[i])) { + unacked = true; + break; + } + } + + if (!unacked) + bb->unacked_exist = 0; +} + /** * badblocks_set() - Add a range of bad blocks to the table. * @bb: the badblocks structure that holds all badblock information @@ -294,6 +314,8 @@ int badblocks_set(struct badblocks *bb, sector_t s, int sectors, bb->changed = 1; if (!acknowledged) bb->unacked_exist = 1; + else + badblocks_update_acked(bb); write_sequnlock_irqrestore(&bb->lock, flags); return rv; @@ -401,6 +423,7 @@ int badblocks_clear(struct badblocks *bb, sector_t s, int sectors) } } + badblocks_update_acked(bb); bb->changed = 1; out: write_sequnlock_irq(&bb->lock); diff --git a/block/blk-flush.c b/block/blk-flush.c index 6a14b68..3c882cb 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -343,6 +343,34 @@ static void flush_data_end_io(struct request *rq, int error) struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL); /* + * Updating q->in_flight[] here for making this tag usable + * early. Because in blk_queue_start_tag(), + * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and + * reserve tags for sync I/O. + * + * More importantly this way can avoid the following I/O + * deadlock: + * + * - suppose there are 40 fua requests comming to flush queue + * and queue depth is 31 + * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc + * tag for async I/O any more + * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT + * and flush_data_end_io() is called + * - the other rqs still can't go ahead if not updating + * q->in_flight[BLK_RW_ASYNC] here, meantime these rqs + * are held in flush data queue and make no progress of + * handling post flush rq + * - only after the post flush rq is handled, all these rqs + * can be completed + */ + + elv_completed_request(q, rq); + + /* for avoiding double accounting */ + rq->cmd_flags &= ~REQ_STARTED; + + /* * After populating an empty queue, kick it to avoid stall. Read * the comment in flush_end_io(). */ diff --git a/block/blk-mq.c b/block/blk-mq.c index ddc2eed..f3d27a6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1217,9 +1217,9 @@ static struct request *blk_mq_map_request(struct request_queue *q, blk_mq_set_alloc_data(&alloc_data, q, 0, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, op, op_flags); - hctx->queued++; - data->hctx = hctx; - data->ctx = ctx; + data->hctx = alloc_data.hctx; + data->ctx = alloc_data.ctx; + data->hctx->queued++; return rq; } diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index ba5f11c..9669fc7 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1418,31 +1418,34 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, * Message mode could be enforced. In this case assume that advantage * of multipe MSIs is negated and use single MSI mode instead. */ - nvec = pci_alloc_irq_vectors(pdev, n_ports, INT_MAX, - PCI_IRQ_MSIX | PCI_IRQ_MSI); - if (nvec > 0) { - if (!(readl(hpriv->mmio + HOST_CTL) & HOST_MRSM)) { - hpriv->get_irq_vector = ahci_get_irq_vector; - hpriv->flags |= AHCI_HFLAG_MULTI_MSI; - return nvec; + if (n_ports > 1) { + nvec = pci_alloc_irq_vectors(pdev, n_ports, INT_MAX, + PCI_IRQ_MSIX | PCI_IRQ_MSI); + if (nvec > 0) { + if (!(readl(hpriv->mmio + HOST_CTL) & HOST_MRSM)) { + hpriv->get_irq_vector = ahci_get_irq_vector; + hpriv->flags |= AHCI_HFLAG_MULTI_MSI; + return nvec; + } + + /* + * Fallback to single MSI mode if the controller + * enforced MRSM mode. + */ + printk(KERN_INFO + "ahci: MRSM is on, fallback to single MSI\n"); + pci_free_irq_vectors(pdev); } /* - * Fallback to single MSI mode if the controller enforced MRSM - * mode. + * -ENOSPC indicated we don't have enough vectors. Don't bother + * trying a single vectors for any other error: */ - printk(KERN_INFO "ahci: MRSM is on, fallback to single MSI\n"); - pci_free_irq_vectors(pdev); + if (nvec < 0 && nvec != -ENOSPC) + return nvec; } /* - * -ENOSPC indicated we don't have enough vectors. Don't bother trying - * a single vectors for any other error: - */ - if (nvec < 0 && nvec != -ENOSPC) - return nvec; - - /* * If the host is not capable of supporting per-port vectors, fall * back to single MSI before finally attempting single MSI-X. */ @@ -1617,7 +1620,7 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* legacy intx interrupts */ pci_intx(pdev, 1); } - hpriv->irq = pdev->irq; + hpriv->irq = pci_irq_vector(pdev, 0); if (!(hpriv->cap & HOST_CAP_SSS) || ahci_ignore_sss) host->flags |= ATA_HOST_PARALLEL_SCAN; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index ba405b5..19a16b2 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -164,7 +164,7 @@ static void sock_shutdown(struct nbd_device *nbd) spin_lock(&nbd->sock_lock); if (!nbd->sock) { - spin_unlock_irq(&nbd->sock_lock); + spin_unlock(&nbd->sock_lock); return; } diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 4827945..d2d2c89 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -84,14 +84,14 @@ static size_t rng_buffer_size(void) static void add_early_randomness(struct hwrng *rng) { - unsigned char bytes[16]; int bytes_read; + size_t size = min_t(size_t, 16, rng_buffer_size()); mutex_lock(&reading_mutex); - bytes_read = rng_get_data(rng, bytes, sizeof(bytes), 1); + bytes_read = rng_get_data(rng, rng_buffer, size, 1); mutex_unlock(&reading_mutex); if (bytes_read > 0) - add_device_randomness(bytes, bytes_read); + add_device_randomness(rng_buffer, bytes_read); } static inline void cleanup_rng(struct kref *kref) diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c index 190122e64..85a449c 100644 --- a/drivers/clk/at91/clk-programmable.c +++ b/drivers/clk/at91/clk-programmable.c @@ -203,7 +203,7 @@ at91_clk_register_programmable(struct regmap *regmap, ret = clk_hw_register(NULL, &prog->hw); if (ret) { kfree(prog); - hw = &prog->hw; + hw = ERR_PTR(ret); } return hw; diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index b68bf57..8c7763f 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -502,8 +502,12 @@ static long bcm2835_pll_rate_from_divisors(unsigned long parent_rate, static long bcm2835_pll_round_rate(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate) { + struct bcm2835_pll *pll = container_of(hw, struct bcm2835_pll, hw); + const struct bcm2835_pll_data *data = pll->data; u32 ndiv, fdiv; + rate = clamp(rate, data->min_rate, data->max_rate); + bcm2835_pll_choose_ndiv_and_fdiv(rate, *parent_rate, &ndiv, &fdiv); return bcm2835_pll_rate_from_divisors(*parent_rate, ndiv, fdiv, 1); @@ -608,13 +612,6 @@ static int bcm2835_pll_set_rate(struct clk_hw *hw, u32 ana[4]; int i; - if (rate < data->min_rate || rate > data->max_rate) { - dev_err(cprman->dev, "%s: rate out of spec: %lu vs (%lu, %lu)\n", - clk_hw_get_name(hw), rate, - data->min_rate, data->max_rate); - return -EINVAL; - } - if (rate > data->max_fb_rate) { use_fb_prediv = true; rate /= 2; diff --git a/drivers/clk/clk-max77686.c b/drivers/clk/clk-max77686.c index b637f59..eb953d3 100644 --- a/drivers/clk/clk-max77686.c +++ b/drivers/clk/clk-max77686.c @@ -216,6 +216,7 @@ static int max77686_clk_probe(struct platform_device *pdev) return -EINVAL; } + drv_data->num_clks = num_clks; drv_data->max_clk_data = devm_kcalloc(dev, num_clks, sizeof(*drv_data->max_clk_data), GFP_KERNEL); diff --git a/drivers/clk/hisilicon/clk-hi6220.c b/drivers/clk/hisilicon/clk-hi6220.c index fe364e6..c0e8e1f 100644 --- a/drivers/clk/hisilicon/clk-hi6220.c +++ b/drivers/clk/hisilicon/clk-hi6220.c @@ -195,7 +195,7 @@ static void __init hi6220_clk_sys_init(struct device_node *np) hi6220_clk_register_divider(hi6220_div_clks_sys, ARRAY_SIZE(hi6220_div_clks_sys), clk_data); } -CLK_OF_DECLARE(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init); +CLK_OF_DECLARE_DRIVER(hi6220_clk_sys, "hisilicon,hi6220-sysctrl", hi6220_clk_sys_init); /* clocks in media controller */ @@ -252,7 +252,7 @@ static void __init hi6220_clk_media_init(struct device_node *np) hi6220_clk_register_divider(hi6220_div_clks_media, ARRAY_SIZE(hi6220_div_clks_media), clk_data); } -CLK_OF_DECLARE(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init); +CLK_OF_DECLARE_DRIVER(hi6220_clk_media, "hisilicon,hi6220-mediactrl", hi6220_clk_media_init); /* clocks in pmctrl */ diff --git a/drivers/clk/mediatek/Kconfig b/drivers/clk/mediatek/Kconfig index 380c372..f042bd2 100644 --- a/drivers/clk/mediatek/Kconfig +++ b/drivers/clk/mediatek/Kconfig @@ -8,6 +8,7 @@ config COMMON_CLK_MEDIATEK config COMMON_CLK_MT8135 bool "Clock driver for Mediatek MT8135" + depends on ARCH_MEDIATEK || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK ---help--- @@ -15,6 +16,7 @@ config COMMON_CLK_MT8135 config COMMON_CLK_MT8173 bool "Clock driver for Mediatek MT8173" + depends on ARCH_MEDIATEK || COMPILE_TEST select COMMON_CLK_MEDIATEK default ARCH_MEDIATEK ---help--- diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c index 45905fc..cecb0fd 100644 --- a/drivers/clk/mvebu/armada-37xx-periph.c +++ b/drivers/clk/mvebu/armada-37xx-periph.c @@ -305,7 +305,7 @@ static const struct of_device_id armada_3700_periph_clock_of_match[] = { }; static int armada_3700_add_composite_clk(const struct clk_periph_data *data, void __iomem *reg, spinlock_t *lock, - struct device *dev, struct clk_hw *hw) + struct device *dev, struct clk_hw **hw) { const struct clk_ops *mux_ops = NULL, *gate_ops = NULL, *rate_ops = NULL; @@ -329,6 +329,7 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data, gate->lock = lock; gate_ops = gate_hw->init->ops; gate->reg = reg + (u64)gate->reg; + gate->flags = CLK_GATE_SET_TO_DISABLE; } if (data->rate_hw) { @@ -353,13 +354,13 @@ static int armada_3700_add_composite_clk(const struct clk_periph_data *data, } } - hw = clk_hw_register_composite(dev, data->name, data->parent_names, + *hw = clk_hw_register_composite(dev, data->name, data->parent_names, data->num_parents, mux_hw, mux_ops, rate_hw, rate_ops, gate_hw, gate_ops, CLK_IGNORE_UNUSED); - if (IS_ERR(hw)) - return PTR_ERR(hw); + if (IS_ERR(*hw)) + return PTR_ERR(*hw); return 0; } @@ -400,7 +401,7 @@ static int armada_3700_periph_clock_probe(struct platform_device *pdev) spin_lock_init(&driver_data->lock); for (i = 0; i < num_periph; i++) { - struct clk_hw *hw = driver_data->hw_data->hws[i]; + struct clk_hw **hw = &driver_data->hw_data->hws[i]; if (armada_3700_add_composite_clk(&data[i], reg, &driver_data->lock, dev, hw)) diff --git a/drivers/clk/samsung/clk-exynos-audss.c b/drivers/clk/samsung/clk-exynos-audss.c index 51d152f..17e68a7 100644 --- a/drivers/clk/samsung/clk-exynos-audss.c +++ b/drivers/clk/samsung/clk-exynos-audss.c @@ -106,6 +106,7 @@ static const struct of_device_id exynos_audss_clk_of_match[] = { }, { }, }; +MODULE_DEVICE_TABLE(of, exynos_audss_clk_of_match); static void exynos_audss_clk_teardown(void) { diff --git a/drivers/clk/uniphier/clk-uniphier-core.c b/drivers/clk/uniphier/clk-uniphier-core.c index 5ffb898..26c53f7 100644 --- a/drivers/clk/uniphier/clk-uniphier-core.c +++ b/drivers/clk/uniphier/clk-uniphier-core.c @@ -79,7 +79,7 @@ static int uniphier_clk_probe(struct platform_device *pdev) hw_data->num = clk_num; /* avoid returning NULL for unused idx */ - for (; clk_num >= 0; clk_num--) + while (--clk_num >= 0) hw_data->hws[clk_num] = ERR_PTR(-EINVAL); for (p = data; p->name; p++) { @@ -111,6 +111,10 @@ static int uniphier_clk_remove(struct platform_device *pdev) static const struct of_device_id uniphier_clk_match[] = { /* System clock */ { + .compatible = "socionext,uniphier-sld3-clock", + .data = uniphier_sld3_sys_clk_data, + }, + { .compatible = "socionext,uniphier-ld4-clock", .data = uniphier_ld4_sys_clk_data, }, @@ -138,7 +142,7 @@ static const struct of_device_id uniphier_clk_match[] = { .compatible = "socionext,uniphier-ld20-clock", .data = uniphier_ld20_sys_clk_data, }, - /* Media I/O clock */ + /* Media I/O clock, SD clock */ { .compatible = "socionext,uniphier-sld3-mio-clock", .data = uniphier_sld3_mio_clk_data, @@ -156,20 +160,20 @@ static const struct of_device_id uniphier_clk_match[] = { .data = uniphier_sld3_mio_clk_data, }, { - .compatible = "socionext,uniphier-pro5-mio-clock", - .data = uniphier_pro5_mio_clk_data, + .compatible = "socionext,uniphier-pro5-sd-clock", + .data = uniphier_pro5_sd_clk_data, }, { - .compatible = "socionext,uniphier-pxs2-mio-clock", - .data = uniphier_pro5_mio_clk_data, + .compatible = "socionext,uniphier-pxs2-sd-clock", + .data = uniphier_pro5_sd_clk_data, }, { .compatible = "socionext,uniphier-ld11-mio-clock", .data = uniphier_sld3_mio_clk_data, }, { - .compatible = "socionext,uniphier-ld20-mio-clock", - .data = uniphier_pro5_mio_clk_data, + .compatible = "socionext,uniphier-ld20-sd-clock", + .data = uniphier_pro5_sd_clk_data, }, /* Peripheral clock */ { diff --git a/drivers/clk/uniphier/clk-uniphier-mio.c b/drivers/clk/uniphier/clk-uniphier-mio.c index 6aa7ec7..218d20f 100644 --- a/drivers/clk/uniphier/clk-uniphier-mio.c +++ b/drivers/clk/uniphier/clk-uniphier-mio.c @@ -93,7 +93,7 @@ const struct uniphier_clk_data uniphier_sld3_mio_clk_data[] = { { /* sentinel */ } }; -const struct uniphier_clk_data uniphier_pro5_mio_clk_data[] = { +const struct uniphier_clk_data uniphier_pro5_sd_clk_data[] = { UNIPHIER_MIO_CLK_SD_FIXED, UNIPHIER_MIO_CLK_SD(0, 0), UNIPHIER_MIO_CLK_SD(1, 1), diff --git a/drivers/clk/uniphier/clk-uniphier-mux.c b/drivers/clk/uniphier/clk-uniphier-mux.c index 15a2f2c..2c243a8 100644 --- a/drivers/clk/uniphier/clk-uniphier-mux.c +++ b/drivers/clk/uniphier/clk-uniphier-mux.c @@ -42,7 +42,7 @@ static u8 uniphier_clk_mux_get_parent(struct clk_hw *hw) struct uniphier_clk_mux *mux = to_uniphier_clk_mux(hw); int num_parents = clk_hw_get_num_parents(hw); int ret; - u32 val; + unsigned int val; u8 i; ret = regmap_read(mux->regmap, mux->reg, &val); diff --git a/drivers/clk/uniphier/clk-uniphier.h b/drivers/clk/uniphier/clk-uniphier.h index 3ae1840..0244dba 100644 --- a/drivers/clk/uniphier/clk-uniphier.h +++ b/drivers/clk/uniphier/clk-uniphier.h @@ -115,7 +115,7 @@ extern const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_ld11_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_ld20_sys_clk_data[]; extern const struct uniphier_clk_data uniphier_sld3_mio_clk_data[]; -extern const struct uniphier_clk_data uniphier_pro5_mio_clk_data[]; +extern const struct uniphier_clk_data uniphier_pro5_sd_clk_data[]; extern const struct uniphier_clk_data uniphier_ld4_peri_clk_data[]; extern const struct uniphier_clk_data uniphier_pro4_peri_clk_data[]; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 26ee00f..d011cb8 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -284,7 +284,7 @@ config GPIO_MM_LANTIQ config GPIO_MOCKUP tristate "GPIO Testing Driver" - depends on GPIOLIB + depends on GPIOLIB && SYSFS select GPIO_SYSFS help This enables GPIO Testing driver, which provides a way to test GPIO diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c index 9457e20..dc37dbe 100644 --- a/drivers/gpio/gpio-ath79.c +++ b/drivers/gpio/gpio-ath79.c @@ -219,6 +219,7 @@ static const struct of_device_id ath79_gpio_of_match[] = { { .compatible = "qca,ar9340-gpio" }, {}, }; +MODULE_DEVICE_TABLE(of, ath79_gpio_of_match); static int ath79_gpio_probe(struct platform_device *pdev) { diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c index 425501c..793518a 100644 --- a/drivers/gpio/gpio-mpc8xxx.c +++ b/drivers/gpio/gpio-mpc8xxx.c @@ -239,7 +239,7 @@ static int mpc8xxx_gpio_irq_map(struct irq_domain *h, unsigned int irq, irq_hw_number_t hwirq) { irq_set_chip_data(irq, h->host_data); - irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_level_irq); + irq_set_chip_and_handler(irq, &mpc8xxx_irq_chip, handle_edge_irq); return 0; } diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c index b9daa0b..ee17248 100644 --- a/drivers/gpio/gpio-mxs.c +++ b/drivers/gpio/gpio-mxs.c @@ -308,8 +308,10 @@ static int mxs_gpio_probe(struct platform_device *pdev) writel(~0U, port->base + PINCTRL_IRQSTAT(port) + MXS_CLR); irq_base = irq_alloc_descs(-1, 0, 32, numa_node_id()); - if (irq_base < 0) - return irq_base; + if (irq_base < 0) { + err = irq_base; + goto out_iounmap; + } port->domain = irq_domain_add_legacy(np, 32, irq_base, 0, &irq_domain_simple_ops, NULL); @@ -349,6 +351,8 @@ out_irqdomain_remove: irq_domain_remove(port->domain); out_irqdesc_free: irq_free_descs(irq_base, 32); +out_iounmap: + iounmap(port->base); return err; } diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c index e7d422a..5b00427 100644 --- a/drivers/gpio/gpio-stmpe.c +++ b/drivers/gpio/gpio-stmpe.c @@ -409,7 +409,7 @@ static irqreturn_t stmpe_gpio_irq(int irq, void *dev) * 801/1801/1600, bits are cleared when read. * Edge detect register is not present on 801/1600/1801 */ - if (stmpe->partnum != STMPE801 || stmpe->partnum != STMPE1600 || + if (stmpe->partnum != STMPE801 && stmpe->partnum != STMPE1600 && stmpe->partnum != STMPE1801) { stmpe_reg_write(stmpe, statmsbreg + i, status[i]); stmpe_reg_write(stmpe, diff --git a/drivers/gpio/gpio-ts4800.c b/drivers/gpio/gpio-ts4800.c index 9925611..c2a80b4 100644 --- a/drivers/gpio/gpio-ts4800.c +++ b/drivers/gpio/gpio-ts4800.c @@ -66,6 +66,7 @@ static const struct of_device_id ts4800_gpio_of_match[] = { { .compatible = "technologic,ts4800-gpio", }, {}, }; +MODULE_DEVICE_TABLE(of, ts4800_gpio_of_match); static struct platform_driver ts4800_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 58ece20..72a4b32 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -653,14 +653,17 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { int idx, i; unsigned int irq_flags; + int ret = -ENOENT; for (i = 0, idx = 0; idx <= index; i++) { struct acpi_gpio_info info; struct gpio_desc *desc; desc = acpi_get_gpiod_by_index(adev, NULL, i, &info); - if (IS_ERR(desc)) + if (IS_ERR(desc)) { + ret = PTR_ERR(desc); break; + } if (info.gpioint && idx++ == index) { int irq = gpiod_to_irq(desc); @@ -679,7 +682,7 @@ int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) } } - return -ENOENT; + return ret; } EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index f0fc3a0..20e09b7 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -333,6 +333,13 @@ struct linehandle_state { u32 numdescs; }; +#define GPIOHANDLE_REQUEST_VALID_FLAGS \ + (GPIOHANDLE_REQUEST_INPUT | \ + GPIOHANDLE_REQUEST_OUTPUT | \ + GPIOHANDLE_REQUEST_ACTIVE_LOW | \ + GPIOHANDLE_REQUEST_OPEN_DRAIN | \ + GPIOHANDLE_REQUEST_OPEN_SOURCE) + static long linehandle_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) { @@ -344,6 +351,8 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd, if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) { int val; + memset(&ghd, 0, sizeof(ghd)); + /* TODO: check if descriptors are really input */ for (i = 0; i < lh->numdescs; i++) { val = gpiod_get_value_cansleep(lh->descs[i]); @@ -444,6 +453,17 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) u32 lflags = handlereq.flags; struct gpio_desc *desc; + if (offset >= gdev->ngpio) { + ret = -EINVAL; + goto out_free_descs; + } + + /* Return an error if a unknown flag is set */ + if (lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS) { + ret = -EINVAL; + goto out_free_descs; + } + desc = &gdev->descs[offset]; ret = gpiod_request(desc, lh->label); if (ret) @@ -536,6 +556,10 @@ struct lineevent_state { struct mutex read_lock; }; +#define GPIOEVENT_REQUEST_VALID_FLAGS \ + (GPIOEVENT_REQUEST_RISING_EDGE | \ + GPIOEVENT_REQUEST_FALLING_EDGE) + static unsigned int lineevent_poll(struct file *filep, struct poll_table_struct *wait) { @@ -623,6 +647,8 @@ static long lineevent_ioctl(struct file *filep, unsigned int cmd, if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) { int val; + memset(&ghd, 0, sizeof(ghd)); + val = gpiod_get_value_cansleep(le->desc); if (val < 0) return val; @@ -726,6 +752,18 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) lflags = eventreq.handleflags; eflags = eventreq.eventflags; + if (offset >= gdev->ngpio) { + ret = -EINVAL; + goto out_free_label; + } + + /* Return an error if a unknown flag is set */ + if ((lflags & ~GPIOHANDLE_REQUEST_VALID_FLAGS) || + (eflags & ~GPIOEVENT_REQUEST_VALID_FLAGS)) { + ret = -EINVAL; + goto out_free_label; + } + /* This is just wrong: we don't look for events on output lines */ if (lflags & GPIOHANDLE_REQUEST_OUTPUT) { ret = -EINVAL; @@ -823,6 +861,8 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (cmd == GPIO_GET_CHIPINFO_IOCTL) { struct gpiochip_info chipinfo; + memset(&chipinfo, 0, sizeof(chipinfo)); + strncpy(chipinfo.name, dev_name(&gdev->dev), sizeof(chipinfo.name)); chipinfo.name[sizeof(chipinfo.name)-1] = '\0'; @@ -839,7 +879,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (copy_from_user(&lineinfo, ip, sizeof(lineinfo))) return -EFAULT; - if (lineinfo.line_offset > gdev->ngpio) + if (lineinfo.line_offset >= gdev->ngpio) return -EINVAL; desc = &gdev->descs[lineinfo.line_offset]; diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 831935a..a7a8847 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -1205,7 +1205,7 @@ static int verify_fcx_max_data(struct dasd_device *device, __u8 lpm) mdc, lpm); return mdc; } - fcx_max_data = mdc * FCX_MAX_DATA_FACTOR; + fcx_max_data = (u32)mdc * FCX_MAX_DATA_FACTOR; if (fcx_max_data < private->fcx_max_data) { dev_warn(&device->cdev->dev, "The maximum data size for zHPF requests %u " @@ -1675,7 +1675,7 @@ static u32 get_fcx_max_data(struct dasd_device *device) " data size for zHPF requests failed\n"); return 0; } else - return mdc * FCX_MAX_DATA_FACTOR; + return (u32)mdc * FCX_MAX_DATA_FACTOR; } /* diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 46be25c..876c7e6 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -780,7 +780,7 @@ static int cfg_wait_idle(void) static int __init chp_init(void) { struct chp_id chpid; - int ret; + int state, ret; ret = crw_register_handler(CRW_RSC_CPATH, chp_process_crw); if (ret) @@ -791,7 +791,9 @@ static int __init chp_init(void) return 0; /* Register available channel-paths. */ chp_id_for_each(&chpid) { - if (chp_info_get_status(chpid) != CHP_STATUS_NOT_RECOGNIZED) + state = chp_info_get_status(chpid); + if (state == CHP_STATUS_CONFIGURED || + state == CHP_STATUS_STANDBY) chp_new(chpid); } diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c index db27390..790babc 100644 --- a/drivers/scsi/NCR5380.c +++ b/drivers/scsi/NCR5380.c @@ -353,7 +353,7 @@ static void NCR5380_print_phase(struct Scsi_Host *instance) #endif -static int probe_irq __initdata; +static int probe_irq; /** * probe_intr - helper for IRQ autoprobe @@ -365,7 +365,7 @@ static int probe_irq __initdata; * used by the IRQ probe code. */ -static irqreturn_t __init probe_intr(int irq, void *dev_id) +static irqreturn_t probe_intr(int irq, void *dev_id) { probe_irq = irq; return IRQ_HANDLED; @@ -380,7 +380,7 @@ static irqreturn_t __init probe_intr(int irq, void *dev_id) * and then looking to see what interrupt actually turned up. */ -static int __init __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance, +static int __maybe_unused NCR5380_probe_irq(struct Scsi_Host *instance, int possible) { struct NCR5380_hostdata *hostdata = shost_priv(instance); diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 68138a6..d9239c2 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -900,8 +900,9 @@ void hwi_ring_cq_db(struct beiscsi_hba *phba, static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba) { struct sgl_handle *psgl_handle; + unsigned long flags; - spin_lock_bh(&phba->io_sgl_lock); + spin_lock_irqsave(&phba->io_sgl_lock, flags); if (phba->io_sgl_hndl_avbl) { beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO, "BM_%d : In alloc_io_sgl_handle," @@ -919,14 +920,16 @@ static struct sgl_handle *alloc_io_sgl_handle(struct beiscsi_hba *phba) phba->io_sgl_alloc_index++; } else psgl_handle = NULL; - spin_unlock_bh(&phba->io_sgl_lock); + spin_unlock_irqrestore(&phba->io_sgl_lock, flags); return psgl_handle; } static void free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle) { - spin_lock_bh(&phba->io_sgl_lock); + unsigned long flags; + + spin_lock_irqsave(&phba->io_sgl_lock, flags); beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_IO, "BM_%d : In free_,io_sgl_free_index=%d\n", phba->io_sgl_free_index); @@ -941,7 +944,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle) "value there=%p\n", phba->io_sgl_free_index, phba->io_sgl_hndl_base [phba->io_sgl_free_index]); - spin_unlock_bh(&phba->io_sgl_lock); + spin_unlock_irqrestore(&phba->io_sgl_lock, flags); return; } phba->io_sgl_hndl_base[phba->io_sgl_free_index] = psgl_handle; @@ -950,7 +953,7 @@ free_io_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle) phba->io_sgl_free_index = 0; else phba->io_sgl_free_index++; - spin_unlock_bh(&phba->io_sgl_lock); + spin_unlock_irqrestore(&phba->io_sgl_lock, flags); } static inline struct wrb_handle * @@ -958,15 +961,16 @@ beiscsi_get_wrb_handle(struct hwi_wrb_context *pwrb_context, unsigned int wrbs_per_cxn) { struct wrb_handle *pwrb_handle; + unsigned long flags; - spin_lock_bh(&pwrb_context->wrb_lock); + spin_lock_irqsave(&pwrb_context->wrb_lock, flags); pwrb_handle = pwrb_context->pwrb_handle_base[pwrb_context->alloc_index]; pwrb_context->wrb_handles_available--; if (pwrb_context->alloc_index == (wrbs_per_cxn - 1)) pwrb_context->alloc_index = 0; else pwrb_context->alloc_index++; - spin_unlock_bh(&pwrb_context->wrb_lock); + spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags); if (pwrb_handle) memset(pwrb_handle->pwrb, 0, sizeof(*pwrb_handle->pwrb)); @@ -1001,14 +1005,16 @@ beiscsi_put_wrb_handle(struct hwi_wrb_context *pwrb_context, struct wrb_handle *pwrb_handle, unsigned int wrbs_per_cxn) { - spin_lock_bh(&pwrb_context->wrb_lock); + unsigned long flags; + + spin_lock_irqsave(&pwrb_context->wrb_lock, flags); pwrb_context->pwrb_handle_base[pwrb_context->free_index] = pwrb_handle; pwrb_context->wrb_handles_available++; if (pwrb_context->free_index == (wrbs_per_cxn - 1)) pwrb_context->free_index = 0; else pwrb_context->free_index++; - spin_unlock_bh(&pwrb_context->wrb_lock); + spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags); } /** @@ -1037,8 +1043,9 @@ free_wrb_handle(struct beiscsi_hba *phba, struct hwi_wrb_context *pwrb_context, static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba) { struct sgl_handle *psgl_handle; + unsigned long flags; - spin_lock_bh(&phba->mgmt_sgl_lock); + spin_lock_irqsave(&phba->mgmt_sgl_lock, flags); if (phba->eh_sgl_hndl_avbl) { psgl_handle = phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index]; phba->eh_sgl_hndl_base[phba->eh_sgl_alloc_index] = NULL; @@ -1056,14 +1063,16 @@ static struct sgl_handle *alloc_mgmt_sgl_handle(struct beiscsi_hba *phba) phba->eh_sgl_alloc_index++; } else psgl_handle = NULL; - spin_unlock_bh(&phba->mgmt_sgl_lock); + spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags); return psgl_handle; } void free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle) { - spin_lock_bh(&phba->mgmt_sgl_lock); + unsigned long flags; + + spin_lock_irqsave(&phba->mgmt_sgl_lock, flags); beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG, "BM_%d : In free_mgmt_sgl_handle," "eh_sgl_free_index=%d\n", @@ -1078,7 +1087,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle) "BM_%d : Double Free in eh SGL ," "eh_sgl_free_index=%d\n", phba->eh_sgl_free_index); - spin_unlock_bh(&phba->mgmt_sgl_lock); + spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags); return; } phba->eh_sgl_hndl_base[phba->eh_sgl_free_index] = psgl_handle; @@ -1088,7 +1097,7 @@ free_mgmt_sgl_handle(struct beiscsi_hba *phba, struct sgl_handle *psgl_handle) phba->eh_sgl_free_index = 0; else phba->eh_sgl_free_index++; - spin_unlock_bh(&phba->mgmt_sgl_lock); + spin_unlock_irqrestore(&phba->mgmt_sgl_lock, flags); } static void diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index c051694..f9b6fba 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -791,9 +791,9 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr, free_task: /* regular RX path uses back_lock */ - spin_lock_bh(&session->back_lock); + spin_lock(&session->back_lock); __iscsi_put_task(task); - spin_unlock_bh(&session->back_lock); + spin_unlock(&session->back_lock); return NULL; } diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c index 9b4815e..19bf202 100644 --- a/drivers/thermal/intel_pch_thermal.c +++ b/drivers/thermal/intel_pch_thermal.c @@ -20,10 +20,13 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/pci.h> +#include <linux/acpi.h> #include <linux/thermal.h> #include <linux/pm.h> /* Intel PCH thermal Device IDs */ +#define PCH_THERMAL_DID_HSW_1 0x9C24 /* Haswell PCH */ +#define PCH_THERMAL_DID_HSW_2 0x8C24 /* Haswell PCH */ #define PCH_THERMAL_DID_WPT 0x9CA4 /* Wildcat Point */ #define PCH_THERMAL_DID_SKL 0x9D31 /* Skylake PCH */ @@ -66,9 +69,53 @@ struct pch_thermal_device { unsigned long crt_temp; int hot_trip_id; unsigned long hot_temp; + int psv_trip_id; + unsigned long psv_temp; bool bios_enabled; }; +#ifdef CONFIG_ACPI + +/* + * On some platforms, there is a companion ACPI device, which adds + * passive trip temperature using _PSV method. There is no specific + * passive temperature setting in MMIO interface of this PCI device. + */ +static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, + int *nr_trips) +{ + struct acpi_device *adev; + + ptd->psv_trip_id = -1; + + adev = ACPI_COMPANION(&ptd->pdev->dev); + if (adev) { + unsigned long long r; + acpi_status status; + + status = acpi_evaluate_integer(adev->handle, "_PSV", NULL, + &r); + if (ACPI_SUCCESS(status)) { + unsigned long trip_temp; + + trip_temp = DECI_KELVIN_TO_MILLICELSIUS(r); + if (trip_temp) { + ptd->psv_temp = trip_temp; + ptd->psv_trip_id = *nr_trips; + ++(*nr_trips); + } + } + } +} +#else +static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd, + int *nr_trips) +{ + ptd->psv_trip_id = -1; + +} +#endif + static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) { u8 tsel; @@ -119,6 +166,8 @@ read_trips: ++(*nr_trips); } + pch_wpt_add_acpi_psv_trip(ptd, nr_trips); + return 0; } @@ -194,6 +243,8 @@ static int pch_get_trip_type(struct thermal_zone_device *tzd, int trip, *type = THERMAL_TRIP_CRITICAL; else if (ptd->hot_trip_id == trip) *type = THERMAL_TRIP_HOT; + else if (ptd->psv_trip_id == trip) + *type = THERMAL_TRIP_PASSIVE; else return -EINVAL; @@ -208,6 +259,8 @@ static int pch_get_trip_temp(struct thermal_zone_device *tzd, int trip, int *tem *temp = ptd->crt_temp; else if (ptd->hot_trip_id == trip) *temp = ptd->hot_temp; + else if (ptd->psv_trip_id == trip) + *temp = ptd->psv_temp; else return -EINVAL; @@ -242,6 +295,11 @@ static int intel_pch_thermal_probe(struct pci_dev *pdev, ptd->ops = &pch_dev_ops_wpt; dev_name = "pch_skylake"; break; + case PCH_THERMAL_DID_HSW_1: + case PCH_THERMAL_DID_HSW_2: + ptd->ops = &pch_dev_ops_wpt; + dev_name = "pch_haswell"; + break; default: dev_err(&pdev->dev, "unknown pch thermal device\n"); return -ENODEV; @@ -324,6 +382,8 @@ static int intel_pch_thermal_resume(struct device *device) static struct pci_device_id intel_pch_thermal_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_1) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_2) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id); diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index 0e4dc0a..7a22307 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -669,20 +669,10 @@ static struct thermal_cooling_device_ops powerclamp_cooling_ops = { .set_cur_state = powerclamp_set_cur_state, }; -static const struct x86_cpu_id intel_powerclamp_ids[] __initconst = { - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT }, - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_ARAT }, - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_NONSTOP_TSC }, - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_CONSTANT_TSC}, - {} -}; -MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids); - static int __init powerclamp_probe(void) { - if (!x86_match_cpu(intel_powerclamp_ids)) { - pr_err("Intel powerclamp does not run on family %d model %d\n", - boot_cpu_data.x86, boot_cpu_data.x86_model); + if (!boot_cpu_has(X86_FEATURE_MWAIT)) { + pr_err("CPU does not support MWAIT"); return -ENODEV; } diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index e12bd36..26e5e85 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -168,7 +168,9 @@ out: #endif /* CONFIG_HIBERNATE_CALLBACKS */ struct shutdown_handler { - const char *command; +#define SHUTDOWN_CMD_SIZE 11 + const char command[SHUTDOWN_CMD_SIZE]; + bool flag; void (*cb)(void); }; @@ -206,22 +208,22 @@ static void do_reboot(void) ctrl_alt_del(); } +static struct shutdown_handler shutdown_handlers[] = { + { "poweroff", true, do_poweroff }, + { "halt", false, do_poweroff }, + { "reboot", true, do_reboot }, +#ifdef CONFIG_HIBERNATE_CALLBACKS + { "suspend", true, do_suspend }, +#endif +}; + static void shutdown_handler(struct xenbus_watch *watch, const char **vec, unsigned int len) { char *str; struct xenbus_transaction xbt; int err; - static struct shutdown_handler handlers[] = { - { "poweroff", do_poweroff }, - { "halt", do_poweroff }, - { "reboot", do_reboot }, -#ifdef CONFIG_HIBERNATE_CALLBACKS - { "suspend", do_suspend }, -#endif - {NULL, NULL}, - }; - static struct shutdown_handler *handler; + int idx; if (shutting_down != SHUTDOWN_INVALID) return; @@ -238,13 +240,13 @@ static void shutdown_handler(struct xenbus_watch *watch, return; } - for (handler = &handlers[0]; handler->command; handler++) { - if (strcmp(str, handler->command) == 0) + for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) { + if (strcmp(str, shutdown_handlers[idx].command) == 0) break; } /* Only acknowledge commands which we are prepared to handle. */ - if (handler->cb) + if (idx < ARRAY_SIZE(shutdown_handlers)) xenbus_write(xbt, "control", "shutdown", ""); err = xenbus_transaction_end(xbt, 0); @@ -253,8 +255,8 @@ static void shutdown_handler(struct xenbus_watch *watch, goto again; } - if (handler->cb) { - handler->cb(); + if (idx < ARRAY_SIZE(shutdown_handlers)) { + shutdown_handlers[idx].cb(); } else { pr_info("Ignoring shutdown request: %s\n", str); shutting_down = SHUTDOWN_INVALID; @@ -310,6 +312,9 @@ static struct notifier_block xen_reboot_nb = { static int setup_shutdown_watcher(void) { int err; + int idx; +#define FEATURE_PATH_SIZE (SHUTDOWN_CMD_SIZE + sizeof("feature-")) + char node[FEATURE_PATH_SIZE]; err = register_xenbus_watch(&shutdown_watch); if (err) { @@ -326,6 +331,14 @@ static int setup_shutdown_watcher(void) } #endif + for (idx = 0; idx < ARRAY_SIZE(shutdown_handlers); idx++) { + if (!shutdown_handlers[idx].flag) + continue; + snprintf(node, FEATURE_PATH_SIZE, "feature-%s", + shutdown_handlers[idx].command); + xenbus_printf(XBT_NIL, "control", node, "%u", 1); + } + return 0; } diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index c1010f01..1e8be12 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -364,7 +364,7 @@ out: static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u) { - struct watch_adapter *watch, *tmp_watch; + struct watch_adapter *watch; char *path, *token; int err, rc; LIST_HEAD(staging_q); @@ -399,7 +399,7 @@ static int xenbus_write_watch(unsigned msg_type, struct xenbus_file_priv *u) } list_add(&watch->list, &u->watches); } else { - list_for_each_entry_safe(watch, tmp_watch, &u->watches, list) { + list_for_each_entry(watch, &u->watches, list) { if (!strcmp(watch->token, token) && !strcmp(watch->watch.node, path)) { unregister_xenbus_watch(&watch->watch); diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index 611a231..6d40a97 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -335,7 +335,9 @@ static int backend_state; static void xenbus_reset_backend_state_changed(struct xenbus_watch *w, const char **v, unsigned int l) { - xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", &backend_state); + if (xenbus_scanf(XBT_NIL, v[XS_WATCH_PATH], "", "%i", + &backend_state) != 1) + backend_state = XenbusStateUnknown; printk(KERN_DEBUG "XENBUS: backend %s %s\n", v[XS_WATCH_PATH], xenbus_strstate(backend_state)); wake_up(&backend_state_wq); @@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, struct page *page = data; int ret; - ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length, - NULL, iomap); + ret = __block_write_begin_int(page, pos, length, NULL, iomap); if (ret) return ret; @@ -561,7 +560,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, } while (len > 0) { - ret = iomap_apply(inode, start, len, 0, ops, &ctx, + ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx, iomap_fiemap_actor); /* inode with no (attribute) mapping will give ENOENT */ if (ret == -ENOENT) diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c index 1e8fe84..5355efb 100644 --- a/fs/orangefs/dcache.c +++ b/fs/orangefs/dcache.c @@ -73,7 +73,7 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) } } - dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; + orangefs_set_timeout(dentry); ret = 1; out_release_op: op_release(new_op); @@ -94,8 +94,9 @@ out_drop: static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) { int ret; + unsigned long time = (unsigned long) dentry->d_fsdata; - if (time_before(jiffies, dentry->d_time)) + if (time_before(jiffies, time)) return 1; if (flags & LOOKUP_RCU) diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index 66ea0cc..02cc613 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -621,9 +621,9 @@ static int orangefs_file_release(struct inode *inode, struct file *file) * readahead cache (if any); this forces an expensive refresh of * data for the next caller of mmap (or 'get_block' accesses) */ - if (file->f_path.dentry->d_inode && - file->f_path.dentry->d_inode->i_mapping && - mapping_nrpages(&file->f_path.dentry->d_inode->i_data)) { + if (file_inode(file) && + file_inode(file)->i_mapping && + mapping_nrpages(&file_inode(file)->i_data)) { if (orangefs_features & ORANGEFS_FEATURE_READAHEAD) { gossip_debug(GOSSIP_INODE_DEBUG, "calling flush_racache on %pU\n", @@ -632,7 +632,7 @@ static int orangefs_file_release(struct inode *inode, struct file *file) gossip_debug(GOSSIP_INODE_DEBUG, "flush_racache finished\n"); } - truncate_inode_pages(file->f_path.dentry->d_inode->i_mapping, + truncate_inode_pages(file_inode(file)->i_mapping, 0); } return 0; @@ -648,7 +648,7 @@ static int orangefs_fsync(struct file *file, { int ret = -EINVAL; struct orangefs_inode_s *orangefs_inode = - ORANGEFS_I(file->f_path.dentry->d_inode); + ORANGEFS_I(file_inode(file)); struct orangefs_kernel_op_s *new_op = NULL; /* required call */ @@ -661,7 +661,7 @@ static int orangefs_fsync(struct file *file, ret = service_operation(new_op, "orangefs_fsync", - get_interruptible_flag(file->f_path.dentry->d_inode)); + get_interruptible_flag(file_inode(file))); gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_fsync got return value of %d\n", @@ -669,7 +669,7 @@ static int orangefs_fsync(struct file *file, op_release(new_op); - orangefs_flush_inode(file->f_path.dentry->d_inode); + orangefs_flush_inode(file_inode(file)); return ret; } diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index d15d3d2..a290ff6 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -72,7 +72,7 @@ static int orangefs_create(struct inode *dir, d_instantiate(dentry, inode); unlock_new_inode(inode); - dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; + orangefs_set_timeout(dentry); ORANGEFS_I(inode)->getattr_time = jiffies - 1; gossip_debug(GOSSIP_NAME_DEBUG, @@ -183,7 +183,7 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry, goto out; } - dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; + orangefs_set_timeout(dentry); inode = orangefs_iget(dir->i_sb, &new_op->downcall.resp.lookup.refn); if (IS_ERR(inode)) { @@ -322,7 +322,7 @@ static int orangefs_symlink(struct inode *dir, d_instantiate(dentry, inode); unlock_new_inode(inode); - dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; + orangefs_set_timeout(dentry); ORANGEFS_I(inode)->getattr_time = jiffies - 1; gossip_debug(GOSSIP_NAME_DEBUG, @@ -386,7 +386,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode d_instantiate(dentry, inode); unlock_new_inode(inode); - dentry->d_time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; + orangefs_set_timeout(dentry); ORANGEFS_I(inode)->getattr_time = jiffies - 1; gossip_debug(GOSSIP_NAME_DEBUG, diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index 0a82048..3bf803d 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -580,4 +580,11 @@ static inline void orangefs_i_size_write(struct inode *inode, loff_t i_size) #endif } +static inline void orangefs_set_timeout(struct dentry *dentry) +{ + unsigned long time = jiffies + orangefs_dcache_timeout_msecs*HZ/1000; + + dentry->d_fsdata = (void *) time; +} + #endif /* __ORANGEFSKERNEL_H */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 8e65446..adfc5b4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -252,7 +252,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, * Inherently racy -- command line shares address space * with code and data. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_FORCE); + rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); if (rv <= 0) goto out_free_page; @@ -270,8 +270,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, int nr_read; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, - FOLL_FORCE); + nr_read = access_remote_vm(mm, p, page, _count, 0); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -306,8 +305,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, bool final; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, - FOLL_FORCE); + nr_read = access_remote_vm(mm, p, page, _count, 0); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -356,8 +354,7 @@ skip_argv: bool final; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, - FOLL_FORCE); + nr_read = access_remote_vm(mm, p, page, _count, 0); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -835,7 +832,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, unsigned long addr = *ppos; ssize_t copied; char *page; - unsigned int flags = FOLL_FORCE; + unsigned int flags; if (!mm) return 0; @@ -848,6 +845,8 @@ static ssize_t mem_rw(struct file *file, char __user *buf, if (!atomic_inc_not_zero(&mm->mm_users)) goto free; + /* Maybe we should limit FOLL_FORCE to actual ptrace users? */ + flags = FOLL_FORCE; if (write) flags |= FOLL_WRITE; @@ -971,8 +970,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); - retval = access_remote_vm(mm, (env_start + src), - page, this_len, FOLL_FORCE); + retval = access_remote_vm(mm, (env_start + src), page, this_len, 0); if (retval <= 0) { ret = retval; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index c27344c..c6eb219 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3974,9 +3974,6 @@ xfs_bmap_remap_alloc( * allocating, so skip that check by pretending to be freeing. */ error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING); - if (error) - goto error0; -error0: xfs_perag_put(args.pag); if (error) trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_); @@ -3999,6 +3996,39 @@ xfs_bmap_alloc( return xfs_bmap_btalloc(ap); } +/* Trim extent to fit a logical block range. */ +void +xfs_trim_extent( + struct xfs_bmbt_irec *irec, + xfs_fileoff_t bno, + xfs_filblks_t len) +{ + xfs_fileoff_t distance; + xfs_fileoff_t end = bno + len; + + if (irec->br_startoff + irec->br_blockcount <= bno || + irec->br_startoff >= end) { + irec->br_blockcount = 0; + return; + } + + if (irec->br_startoff < bno) { + distance = bno - irec->br_startoff; + if (isnullstartblock(irec->br_startblock)) + irec->br_startblock = DELAYSTARTBLOCK; + if (irec->br_startblock != DELAYSTARTBLOCK && + irec->br_startblock != HOLESTARTBLOCK) + irec->br_startblock += distance; + irec->br_startoff += distance; + irec->br_blockcount -= distance; + } + + if (end < irec->br_startoff + irec->br_blockcount) { + distance = irec->br_startoff + irec->br_blockcount - end; + irec->br_blockcount -= distance; + } +} + /* * Trim the returned map to the required bounds */ @@ -4829,6 +4859,219 @@ xfs_bmap_split_indlen( return stolen; } +int +xfs_bmap_del_extent_delay( + struct xfs_inode *ip, + int whichfork, + xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_bmbt_irec new; + int64_t da_old, da_new, da_diff = 0; + xfs_fileoff_t del_endoff, got_endoff; + xfs_filblks_t got_indlen, new_indlen, stolen; + int error = 0, state = 0; + bool isrt; + + XFS_STATS_INC(mp, xs_del_exlist); + + isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); + del_endoff = del->br_startoff + del->br_blockcount; + got_endoff = got->br_startoff + got->br_blockcount; + da_old = startblockval(got->br_startblock); + da_new = 0; + + ASSERT(*idx >= 0); + ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(del->br_blockcount > 0); + ASSERT(got->br_startoff <= del->br_startoff); + ASSERT(got_endoff >= del_endoff); + + if (isrt) { + int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount); + + do_div(rtexts, mp->m_sb.sb_rextsize); + xfs_mod_frextents(mp, rtexts); + } + + /* + * Update the inode delalloc counter now and wait to update the + * sb counters as we might have to borrow some blocks for the + * indirect block accounting. + */ + xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0, + isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); + ip->i_delayed_blks -= del->br_blockcount; + + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; + + if (got->br_startoff == del->br_startoff) + state |= BMAP_LEFT_CONTIG; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_CONTIG; + + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * Matches the whole extent. Delete the entry. + */ + xfs_iext_remove(ip, *idx, 1, state); + --*idx; + break; + case BMAP_LEFT_CONTIG: + /* + * Deleting the first part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_startoff = del_endoff; + got->br_blockcount -= del->br_blockcount; + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, + got->br_blockcount), da_old); + got->br_startblock = nullstartblock((int)da_new); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case BMAP_RIGHT_CONTIG: + /* + * Deleting the last part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount = got->br_blockcount - del->br_blockcount; + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, + got->br_blockcount), da_old); + got->br_startblock = nullstartblock((int)da_new); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case 0: + /* + * Deleting the middle of the extent. + * + * Distribute the original indlen reservation across the two new + * extents. Steal blocks from the deleted extent if necessary. + * Stealing blocks simply fudges the fdblocks accounting below. + * Warn if either of the new indlen reservations is zero as this + * can lead to delalloc problems. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + + got->br_blockcount = del->br_startoff - got->br_startoff; + got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount); + + new.br_blockcount = got_endoff - del_endoff; + new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount); + + WARN_ON_ONCE(!got_indlen || !new_indlen); + stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen, + del->br_blockcount); + + got->br_startblock = nullstartblock((int)got_indlen); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_); + + new.br_startoff = del_endoff; + new.br_state = got->br_state; + new.br_startblock = nullstartblock((int)new_indlen); + + ++*idx; + xfs_iext_insert(ip, *idx, 1, &new, state); + + da_new = got_indlen + new_indlen - stolen; + del->br_blockcount -= stolen; + break; + } + + ASSERT(da_old >= da_new); + da_diff = da_old - da_new; + if (!isrt) + da_diff += del->br_blockcount; + if (da_diff) + xfs_mod_fdblocks(mp, da_diff, false); + return error; +} + +void +xfs_bmap_del_extent_cow( + struct xfs_inode *ip, + xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec new; + xfs_fileoff_t del_endoff, got_endoff; + int state = BMAP_COWFORK; + + XFS_STATS_INC(mp, xs_del_exlist); + + del_endoff = del->br_startoff + del->br_blockcount; + got_endoff = got->br_startoff + got->br_blockcount; + + ASSERT(*idx >= 0); + ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(del->br_blockcount > 0); + ASSERT(got->br_startoff <= del->br_startoff); + ASSERT(got_endoff >= del_endoff); + ASSERT(!isnullstartblock(got->br_startblock)); + + if (got->br_startoff == del->br_startoff) + state |= BMAP_LEFT_CONTIG; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_CONTIG; + + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * Matches the whole extent. Delete the entry. + */ + xfs_iext_remove(ip, *idx, 1, state); + --*idx; + break; + case BMAP_LEFT_CONTIG: + /* + * Deleting the first part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_startoff = del_endoff; + got->br_blockcount -= del->br_blockcount; + got->br_startblock = del->br_startblock + del->br_blockcount; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case BMAP_RIGHT_CONTIG: + /* + * Deleting the last part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount -= del->br_blockcount; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case 0: + /* + * Deleting the middle of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount = del->br_startoff - got->br_startoff; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + + new.br_startoff = del_endoff; + new.br_blockcount = got_endoff - del_endoff; + new.br_state = got->br_state; + new.br_startblock = del->br_startblock + del->br_blockcount; + + ++*idx; + xfs_iext_insert(ip, *idx, 1, &new, state); + break; + } +} + /* * Called by xfs_bmapi to update file extent records and the btree * after removing space (or undoing a delayed allocation). @@ -5171,175 +5414,6 @@ done: return error; } -/* Remove an extent from the CoW fork. Similar to xfs_bmap_del_extent. */ -int -xfs_bunmapi_cow( - struct xfs_inode *ip, - struct xfs_bmbt_irec *del) -{ - xfs_filblks_t da_new; - xfs_filblks_t da_old; - xfs_fsblock_t del_endblock = 0; - xfs_fileoff_t del_endoff; - int delay; - struct xfs_bmbt_rec_host *ep; - int error; - struct xfs_bmbt_irec got; - xfs_fileoff_t got_endoff; - struct xfs_ifork *ifp; - struct xfs_mount *mp; - xfs_filblks_t nblks; - struct xfs_bmbt_irec new; - /* REFERENCED */ - uint qfield; - xfs_filblks_t temp; - xfs_filblks_t temp2; - int state = BMAP_COWFORK; - int eof; - xfs_extnum_t eidx; - - mp = ip->i_mount; - XFS_STATS_INC(mp, xs_del_exlist); - - ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof, - &eidx, &got, &new); - - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp; - ASSERT((eidx >= 0) && (eidx < ifp->if_bytes / - (uint)sizeof(xfs_bmbt_rec_t))); - ASSERT(del->br_blockcount > 0); - ASSERT(got.br_startoff <= del->br_startoff); - del_endoff = del->br_startoff + del->br_blockcount; - got_endoff = got.br_startoff + got.br_blockcount; - ASSERT(got_endoff >= del_endoff); - delay = isnullstartblock(got.br_startblock); - ASSERT(isnullstartblock(del->br_startblock) == delay); - qfield = 0; - error = 0; - /* - * If deleting a real allocation, must free up the disk space. - */ - if (!delay) { - nblks = del->br_blockcount; - qfield = XFS_TRANS_DQ_BCOUNT; - /* - * Set up del_endblock and cur for later. - */ - del_endblock = del->br_startblock + del->br_blockcount; - da_old = da_new = 0; - } else { - da_old = startblockval(got.br_startblock); - da_new = 0; - nblks = 0; - } - qfield = qfield; - nblks = nblks; - - /* - * Set flag value to use in switch statement. - * Left-contig is 2, right-contig is 1. - */ - switch (((got.br_startoff == del->br_startoff) << 1) | - (got_endoff == del_endoff)) { - case 3: - /* - * Matches the whole extent. Delete the entry. - */ - xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK); - --eidx; - break; - - case 2: - /* - * Deleting the first part of the extent. - */ - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_startoff(ep, del_endoff); - temp = got.br_blockcount - del->br_blockcount; - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - da_new = temp; - break; - } - xfs_bmbt_set_startblock(ep, del_endblock); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - break; - - case 1: - /* - * Deleting the last part of the extent. - */ - temp = got.br_blockcount - del->br_blockcount; - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - da_new = temp; - break; - } - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - break; - - case 0: - /* - * Deleting the middle of the extent. - */ - temp = del->br_startoff - got.br_startoff; - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - new.br_startoff = del_endoff; - temp2 = got_endoff - del_endoff; - new.br_blockcount = temp2; - new.br_state = got.br_state; - if (!delay) { - new.br_startblock = del_endblock; - } else { - temp = xfs_bmap_worst_indlen(ip, temp); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - temp2 = xfs_bmap_worst_indlen(ip, temp2); - new.br_startblock = nullstartblock((int)temp2); - da_new = temp + temp2; - while (da_new > da_old) { - if (temp) { - temp--; - da_new--; - xfs_bmbt_set_startblock(ep, - nullstartblock((int)temp)); - } - if (da_new == da_old) - break; - if (temp2) { - temp2--; - da_new--; - new.br_startblock = - nullstartblock((int)temp2); - } - } - } - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - xfs_iext_insert(ip, eidx + 1, 1, &new, state); - ++eidx; - break; - } - - /* - * Account for change in delayed indirect blocks. - * Nothing to do for disk quota accounting here. - */ - ASSERT(da_old >= da_new); - if (da_old > da_new) - xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false); - - return error; -} - /* * Unmap (remove) blocks from a file. * If nexts is nonzero then the number of extents to remove is limited to diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index f97db71..7cae6ec 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -190,6 +190,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, #define XFS_BMAP_TRACE_EXLIST(ip,c,w) #endif +void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, + xfs_filblks_t len); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, @@ -221,7 +223,11 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, int flags, xfs_extnum_t nexts, xfs_fsblock_t *firstblock, struct xfs_defer_ops *dfops, int *done); -int xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del); +int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, + xfs_extnum_t *idx, struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del); +void xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del); int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx, xfs_extnum_t num); uint xfs_default_attroffset(struct xfs_inode *ip); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5c8e6f2..0e80993 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4826,7 +4826,7 @@ xfs_btree_calc_size( return rval; } -int +static int xfs_btree_count_blocks_helper( struct xfs_btree_cur *cur, int level, diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 3cc3cf7..ac9a003 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc( if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else - ndquots = xfs_calc_dquots_per_chunk( - XFS_BB_TO_FSB(mp, bp->b_length)); + ndquots = xfs_calc_dquots_per_chunk(bp->b_length); for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index f6547fc..6b7579e 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -865,7 +865,6 @@ typedef struct xfs_timestamp { * padding field for v3 inodes. */ #define XFS_DINODE_MAGIC 0x494e /* 'IN' */ -#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3) typedef struct xfs_dinode { __be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */ __be16 di_mode; /* mode and type of file */ diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 8de9a3a..134424f 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -57,6 +57,17 @@ xfs_inobp_check( } #endif +bool +xfs_dinode_good_version( + struct xfs_mount *mp, + __u8 version) +{ + if (xfs_sb_version_hascrc(&mp->m_sb)) + return version == 3; + + return version == 1 || version == 2; +} + /* * If we are doing readahead on an inode buffer, we might be in log recovery * reading an inode allocation buffer that hasn't yet been replayed, and hence @@ -91,7 +102,7 @@ xfs_inode_buf_verify( dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog)); di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) && - XFS_DINODE_GOOD_VERSION(dip->di_version); + xfs_dinode_good_version(mp, dip->di_version); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP, XFS_RANDOM_ITOBP_INOTOBP))) { diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 62d9d46..3cfe12a 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -74,6 +74,8 @@ void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); void xfs_log_dinode_to_disk(struct xfs_log_dinode *from, struct xfs_dinode *to); +bool xfs_dinode_good_version(struct xfs_mount *mp, __u8 version); + #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); #else diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a314fc7..6e4f7f9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -249,6 +249,7 @@ xfs_file_dio_aio_read( struct xfs_inode *ip = XFS_I(inode); loff_t isize = i_size_read(inode); size_t count = iov_iter_count(to); + loff_t end = iocb->ki_pos + count - 1; struct iov_iter data; struct xfs_buftarg *target; ssize_t ret = 0; @@ -272,49 +273,21 @@ xfs_file_dio_aio_read( file_accessed(iocb->ki_filp); - /* - * Locking is a bit tricky here. If we take an exclusive lock for direct - * IO, we effectively serialise all new concurrent read IO to this file - * and block it behind IO that is currently in progress because IO in - * progress holds the IO lock shared. We only need to hold the lock - * exclusive to blow away the page cache, so only take lock exclusively - * if the page cache needs invalidation. This allows the normal direct - * IO case of no page cache pages to proceeed concurrently without - * serialisation. - */ xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); if (mapping->nrpages) { - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); - xfs_rw_ilock(ip, XFS_IOLOCK_EXCL); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); + if (ret) + goto out_unlock; /* - * The generic dio code only flushes the range of the particular - * I/O. Because we take an exclusive lock here, this whole - * sequence is considerably more expensive for us. This has a - * noticeable performance impact for any file with cached pages, - * even when outside of the range of the particular I/O. - * - * Hence, amortize the cost of the lock against a full file - * flush and reduce the chances of repeated iolock cycles going - * forward. + * Invalidate whole pages. This can return an error if we fail + * to invalidate a page, but this should never happen on XFS. + * Warn if it does fail. */ - if (mapping->nrpages) { - ret = filemap_write_and_wait(mapping); - if (ret) { - xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); - return ret; - } - - /* - * Invalidate whole pages. This can return an error if - * we fail to invalidate a page, but this should never - * happen on XFS. Warn if it does fail. - */ - ret = invalidate_inode_pages2(mapping); - WARN_ON_ONCE(ret); - ret = 0; - } - xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; } data = *to; @@ -324,8 +297,9 @@ xfs_file_dio_aio_read( iocb->ki_pos += ret; iov_iter_advance(to, ret); } - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); +out_unlock: + xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } @@ -570,61 +544,49 @@ xfs_file_dio_aio_write( if ((iocb->ki_pos | count) & target->bt_logical_sectormask) return -EINVAL; - /* "unaligned" here means not aligned to a filesystem block */ - if ((iocb->ki_pos & mp->m_blockmask) || - ((iocb->ki_pos + count) & mp->m_blockmask)) - unaligned_io = 1; - /* - * We don't need to take an exclusive lock unless there page cache needs - * to be invalidated or unaligned IO is being executed. We don't need to - * consider the EOF extension case here because - * xfs_file_aio_write_checks() will relock the inode as necessary for - * EOF zeroing cases and fill out the new inode size as appropriate. + * Don't take the exclusive iolock here unless the I/O is unaligned to + * the file system block size. We don't need to consider the EOF + * extension case here because xfs_file_aio_write_checks() will relock + * the inode as necessary for EOF zeroing cases and fill out the new + * inode size as appropriate. */ - if (unaligned_io || mapping->nrpages) + if ((iocb->ki_pos & mp->m_blockmask) || + ((iocb->ki_pos + count) & mp->m_blockmask)) { + unaligned_io = 1; iolock = XFS_IOLOCK_EXCL; - else + } else { iolock = XFS_IOLOCK_SHARED; - xfs_rw_ilock(ip, iolock); - - /* - * Recheck if there are cached pages that need invalidate after we got - * the iolock to protect against other threads adding new pages while - * we were waiting for the iolock. - */ - if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) { - xfs_rw_iunlock(ip, iolock); - iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, iolock); } + xfs_rw_ilock(ip, iolock); + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; count = iov_iter_count(from); end = iocb->ki_pos + count - 1; - /* - * See xfs_file_dio_aio_read() for why we do a full-file flush here. - */ if (mapping->nrpages) { - ret = filemap_write_and_wait(VFS_I(ip)->i_mapping); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); if (ret) goto out; + /* * Invalidate whole pages. This can return an error if we fail * to invalidate a page, but this should never happen on XFS. * Warn if it does fail. */ - ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping); + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } /* * If we are doing unaligned IO, wait for all other IO to drain, - * otherwise demote the lock if we had to flush cached pages + * otherwise demote the lock if we had to take the exclusive lock + * for other reasons in xfs_file_aio_write_checks. */ if (unaligned_io) inode_dio_wait(inode); @@ -947,134 +909,6 @@ out_unlock: return error; } -/* - * Flush all file writes out to disk. - */ -static int -xfs_file_wait_for_io( - struct inode *inode, - loff_t offset, - size_t len) -{ - loff_t rounding; - loff_t ioffset; - loff_t iendoffset; - loff_t bs; - int ret; - - bs = inode->i_sb->s_blocksize; - inode_dio_wait(inode); - - rounding = max_t(xfs_off_t, bs, PAGE_SIZE); - ioffset = round_down(offset, rounding); - iendoffset = round_up(offset + len, rounding) - 1; - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - iendoffset); - return ret; -} - -/* Hook up to the VFS reflink function */ -STATIC int -xfs_file_share_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - bool is_dedupe) -{ - struct inode *inode_in; - struct inode *inode_out; - ssize_t ret; - loff_t bs; - loff_t isize; - int same_inode; - loff_t blen; - unsigned int flags = 0; - - inode_in = file_inode(file_in); - inode_out = file_inode(file_out); - bs = inode_out->i_sb->s_blocksize; - - /* Don't touch certain kinds of inodes */ - if (IS_IMMUTABLE(inode_out)) - return -EPERM; - if (IS_SWAPFILE(inode_in) || - IS_SWAPFILE(inode_out)) - return -ETXTBSY; - - /* Reflink only works within this filesystem. */ - if (inode_in->i_sb != inode_out->i_sb) - return -EXDEV; - same_inode = (inode_in->i_ino == inode_out->i_ino); - - /* Don't reflink dirs, pipes, sockets... */ - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - return -EISDIR; - if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) - return -EINVAL; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - return -EINVAL; - - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) - return -EINVAL; - - /* Are we going all the way to the end? */ - isize = i_size_read(inode_in); - if (isize == 0) - return 0; - if (len == 0) - len = isize - pos_in; - - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + len < pos_in || pos_out + len < pos_out || - pos_in + len > isize) - return -EINVAL; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + len > disize) - return -EINVAL; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; - - /* Wait for the completion of any pending IOs on srcfile */ - ret = xfs_file_wait_for_io(inode_in, pos_in, len); - if (ret) - goto out; - ret = xfs_file_wait_for_io(inode_out, pos_out, len); - if (ret) - goto out; - - if (is_dedupe) - flags |= XFS_REFLINK_DEDUPE; - ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out), - pos_out, len, flags); - if (ret < 0) - goto out; - -out: - return ret; -} - STATIC ssize_t xfs_file_copy_range( struct file *file_in, @@ -1086,7 +920,7 @@ xfs_file_copy_range( { int error; - error = xfs_file_share_range(file_in, pos_in, file_out, pos_out, + error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, false); if (error) return error; @@ -1101,7 +935,7 @@ xfs_file_clone_range( loff_t pos_out, u64 len) { - return xfs_file_share_range(file_in, pos_in, file_out, pos_out, + return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, false); } @@ -1124,7 +958,7 @@ xfs_file_dedupe_range( if (len > XFS_MAX_DEDUPE_LEN) len = XFS_MAX_DEDUPE_LEN; - error = xfs_file_share_range(src_file, loff, dst_file, dst_loff, + error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff, len, true); if (error) return error; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 14796b7..f295049 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1656,9 +1656,9 @@ void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { - trace_xfs_inode_set_eofblocks_tag(ip); + trace_xfs_inode_set_cowblocks_tag(ip); return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks, - trace_xfs_perag_set_eofblocks, + trace_xfs_perag_set_cowblocks, XFS_ICI_COWBLOCKS_TAG); } @@ -1666,7 +1666,7 @@ void xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { - trace_xfs_inode_clear_eofblocks_tag(ip); + trace_xfs_inode_clear_cowblocks_tag(ip); return __xfs_inode_clear_eofblocks_tag(ip, - trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG); + trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d907eb9..436e109 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay( xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx, &got, &prev); if (!eof && got.br_startoff <= offset_fsb) { + if (xfs_is_reflink_inode(ip)) { + bool shared; + + end_fsb = min(XFS_B_TO_FSB(mp, offset + count), + maxbytes_fsb); + xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb); + error = xfs_reflink_reserve_cow(ip, &got, &shared); + if (error) + goto out_unlock; + } + trace_xfs_iomap_found(ip, offset, count, 0, &got); goto done; } @@ -961,19 +972,13 @@ xfs_file_iomap_begin( struct xfs_mount *mp = ip->i_mount; struct xfs_bmbt_irec imap; xfs_fileoff_t offset_fsb, end_fsb; - bool shared, trimmed; int nimaps = 1, error = 0; + bool shared = false, trimmed = false; unsigned lockmode; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { - error = xfs_reflink_reserve_cow_range(ip, offset, length); - if (error < 0) - return error; - } - if ((flags & IOMAP_WRITE) && !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ @@ -981,7 +986,16 @@ xfs_file_iomap_begin( iomap); } - lockmode = xfs_ilock_data_map_shared(ip); + /* + * COW writes will allocate delalloc space, so we need to make sure + * to take the lock exclusively here. + */ + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, XFS_ILOCK_EXCL); + } else { + lockmode = xfs_ilock_data_map_shared(ip); + } ASSERT(offset <= mp->m_super->s_maxbytes); if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes) @@ -991,16 +1005,24 @@ xfs_file_iomap_begin( error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); - if (error) { - xfs_iunlock(ip, lockmode); - return error; + if (error) + goto out_unlock; + + if (flags & IOMAP_REPORT) { + /* Trim the mapping to the nearest shared extent boundary. */ + error = xfs_reflink_trim_around_shared(ip, &imap, &shared, + &trimmed); + if (error) + goto out_unlock; } - /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); - if (error) { - xfs_iunlock(ip, lockmode); - return error; + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + error = xfs_reflink_reserve_cow(ip, &imap, &shared); + if (error) + goto out_unlock; + + end_fsb = imap.br_startoff + imap.br_blockcount; + length = XFS_FSB_TO_B(mp, end_fsb) - offset; } if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) { @@ -1039,6 +1061,9 @@ xfs_file_iomap_begin( if (shared) iomap->flags |= IOMAP_F_SHARED; return 0; +out_unlock: + xfs_iunlock(ip, lockmode); + return error; } static int diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index fc78739..b341f10 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1009,6 +1009,7 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: + mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 5965e94..a279b4e 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared( if (!xfs_is_reflink_inode(ip) || ISUNWRITTEN(irec) || irec->br_startblock == HOLESTARTBLOCK || - irec->br_startblock == DELAYSTARTBLOCK) { + irec->br_startblock == DELAYSTARTBLOCK || + isnullstartblock(irec->br_startblock)) { *shared = false; return 0; } @@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared( } } -/* Create a CoW reservation for a range of blocks within a file. */ -static int -__xfs_reflink_reserve_cow( +/* + * Trim the passed in imap to the next shared/unshared extent boundary, and + * if imap->br_startoff points to a shared extent reserve space for it in the + * COW fork. In this case *shared is set to true, else to false. + * + * Note that imap will always contain the block numbers for the existing blocks + * in the data fork, as the upper layers need them for read-modify-write + * operations. + */ +int +xfs_reflink_reserve_cow( struct xfs_inode *ip, - xfs_fileoff_t *offset_fsb, - xfs_fileoff_t end_fsb, - bool *skipped) + struct xfs_bmbt_irec *imap, + bool *shared) { - struct xfs_bmbt_irec got, prev, imap; - xfs_fileoff_t orig_end_fsb; - int nimaps, eof = 0, error = 0; - bool shared = false, trimmed = false; + struct xfs_bmbt_irec got, prev; + xfs_fileoff_t end_fsb, orig_end_fsb; + int eof = 0, error = 0; + bool trimmed; xfs_extnum_t idx; xfs_extlen_t align; - /* Already reserved? Skip the refcount btree access. */ - xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx, + /* + * Search the COW fork extent list first. This serves two purposes: + * first this implement the speculative preallocation using cowextisze, + * so that we also unshared block adjacent to shared blocks instead + * of just the shared blocks themselves. Second the lookup in the + * extent list is generally faster than going out to the shared extent + * tree. + */ + xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx, &got, &prev); - if (!eof && got.br_startoff <= *offset_fsb) { - end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount; - trace_xfs_reflink_cow_found(ip, &got); - goto done; - } + if (!eof && got.br_startoff <= imap->br_startoff) { + trace_xfs_reflink_cow_found(ip, imap); + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); - /* Read extent from the source file. */ - nimaps = 1; - error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, - &imap, &nimaps, 0); - if (error) - goto out_unlock; - ASSERT(nimaps == 1); + *shared = true; + return 0; + } /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); + error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); if (error) - goto out_unlock; - - end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount; + return error; /* Not shared? Just report the (potentially capped) extent. */ - if (!shared) { - *skipped = true; - goto done; - } + if (!*shared) + return 0; /* * Fork all the shared blocks from our write offset until the end of @@ -278,72 +283,38 @@ __xfs_reflink_reserve_cow( */ error = xfs_qm_dqattach_locked(ip, 0); if (error) - goto out_unlock; + return error; + + end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount; align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip)); if (align) end_fsb = roundup_64(end_fsb, align); retry: - error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb, - end_fsb - *offset_fsb, &got, - &prev, &idx, eof); + error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff, + end_fsb - imap->br_startoff, &got, &prev, &idx, eof); switch (error) { case 0: break; case -ENOSPC: case -EDQUOT: /* retry without any preallocation */ - trace_xfs_reflink_cow_enospc(ip, &imap); + trace_xfs_reflink_cow_enospc(ip, imap); if (end_fsb != orig_end_fsb) { end_fsb = orig_end_fsb; goto retry; } /*FALLTHRU*/ default: - goto out_unlock; + return error; } if (end_fsb != orig_end_fsb) xfs_inode_set_cowblocks_tag(ip); trace_xfs_reflink_cow_alloc(ip, &got); -done: - *offset_fsb = end_fsb; -out_unlock: - return error; -} - -/* Create a CoW reservation for part of a file. */ -int -xfs_reflink_reserve_cow_range( - struct xfs_inode *ip, - xfs_off_t offset, - xfs_off_t count) -{ - struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb, end_fsb; - bool skipped = false; - int error; - - trace_xfs_reflink_reserve_cow_range(ip, offset, count); - - offset_fsb = XFS_B_TO_FSBT(mp, offset); - end_fsb = XFS_B_TO_FSB(mp, offset + count); - - xfs_ilock(ip, XFS_ILOCK_EXCL); - while (offset_fsb < end_fsb) { - error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb, - &skipped); - if (error) { - trace_xfs_reflink_reserve_cow_range_error(ip, error, - _RET_IP_); - break; - } - } - xfs_iunlock(ip, XFS_ILOCK_EXCL); - - return error; + return 0; } /* Allocate all CoW reservations covering a range of blocks in a file. */ @@ -358,9 +329,8 @@ __xfs_reflink_allocate_cow( struct xfs_defer_ops dfops; struct xfs_trans *tp; xfs_fsblock_t first_block; - xfs_fileoff_t next_fsb; int nimaps = 1, error; - bool skipped = false; + bool shared; xfs_defer_init(&dfops, &first_block); @@ -371,33 +341,38 @@ __xfs_reflink_allocate_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); - next_fsb = *offset_fsb; - error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped); + /* Read extent from the source file. */ + nimaps = 1; + error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, + &imap, &nimaps, 0); + if (error) + goto out_unlock; + ASSERT(nimaps == 1); + + error = xfs_reflink_reserve_cow(ip, &imap, &shared); if (error) goto out_trans_cancel; - if (skipped) { - *offset_fsb = next_fsb; + if (!shared) { + *offset_fsb = imap.br_startoff + imap.br_blockcount; goto out_trans_cancel; } xfs_trans_ijoin(tp, ip, 0); - error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb, + error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount, XFS_BMAPI_COWFORK, &first_block, XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), &imap, &nimaps, &dfops); if (error) goto out_trans_cancel; - /* We might not have been able to map the whole delalloc extent */ - *offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb); - error = xfs_defer_finish(&tp, &dfops, NULL); if (error) goto out_trans_cancel; error = xfs_trans_commit(tp); + *offset_fsb = imap.br_startoff + imap.br_blockcount; out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; @@ -536,58 +511,49 @@ xfs_reflink_cancel_cow_blocks( xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb) { - struct xfs_bmbt_irec irec; - xfs_filblks_t count_fsb; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got, prev, del; + xfs_extnum_t idx; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error = 0; - int nimaps; + int error = 0, eof = 0; if (!xfs_is_reflink_inode(ip)) return 0; - /* Go find the old extent in the CoW fork. */ - while (offset_fsb < end_fsb) { - nimaps = 1; - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); - error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec, - &nimaps, XFS_BMAPI_COWFORK); - if (error) - break; - ASSERT(nimaps == 1); - - trace_xfs_reflink_cancel_cow(ip, &irec); + xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx, + &got, &prev); + if (eof) + return 0; - if (irec.br_startblock == DELAYSTARTBLOCK) { - /* Free a delayed allocation. */ - xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount, - false); - ip->i_delayed_blks -= irec.br_blockcount; + while (got.br_startoff < end_fsb) { + del = got; + xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb); + trace_xfs_reflink_cancel_cow(ip, &del); - /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &irec); + if (isnullstartblock(del.br_startblock)) { + error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, + &idx, &got, &del); if (error) break; - } else if (irec.br_startblock == HOLESTARTBLOCK) { - /* empty */ } else { xfs_trans_ijoin(*tpp, ip, 0); xfs_defer_init(&dfops, &firstfsb); /* Free the CoW orphan record. */ error = xfs_refcount_free_cow_extent(ip->i_mount, - &dfops, irec.br_startblock, - irec.br_blockcount); + &dfops, del.br_startblock, + del.br_blockcount); if (error) break; xfs_bmap_add_free(ip->i_mount, &dfops, - irec.br_startblock, irec.br_blockcount, + del.br_startblock, del.br_blockcount, NULL); /* Update quota accounting */ xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT, - -(long)irec.br_blockcount); + -(long)del.br_blockcount); /* Roll the transaction */ error = xfs_defer_finish(tpp, &dfops, ip); @@ -597,15 +563,18 @@ xfs_reflink_cancel_cow_blocks( } /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &irec); - if (error) - break; + xfs_bmap_del_extent_cow(ip, &idx, &got, &del); } - /* Roll on... */ - offset_fsb = irec.br_startoff + irec.br_blockcount; + if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)) + break; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } + /* clear tag if cow fork is emptied */ + if (!ifp->if_bytes) + xfs_inode_clear_cowblocks_tag(ip); + return error; } @@ -668,25 +637,26 @@ xfs_reflink_end_cow( xfs_off_t offset, xfs_off_t count) { - struct xfs_bmbt_irec irec; - struct xfs_bmbt_irec uirec; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got, prev, del; struct xfs_trans *tp; xfs_fileoff_t offset_fsb; xfs_fileoff_t end_fsb; - xfs_filblks_t count_fsb; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error; + int error, eof = 0; unsigned int resblks; - xfs_filblks_t ilen; xfs_filblks_t rlen; - int nimaps; + xfs_extnum_t idx; trace_xfs_reflink_end_cow(ip, offset, count); + /* No COW extents? That's easy! */ + if (ifp->if_bytes == 0) + return 0; + offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count); - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); /* Start a rolling transaction to switch the mappings */ resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK); @@ -698,72 +668,65 @@ xfs_reflink_end_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - /* Go find the old extent in the CoW fork. */ - while (offset_fsb < end_fsb) { - /* Read extent from the source file */ - nimaps = 1; - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); - error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec, - &nimaps, XFS_BMAPI_COWFORK); - if (error) - goto out_cancel; - ASSERT(nimaps == 1); + xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx, + &got, &prev); - ASSERT(irec.br_startblock != DELAYSTARTBLOCK); - trace_xfs_reflink_cow_remap(ip, &irec); + /* If there is a hole at end_fsb - 1 go to the previous extent */ + if (eof || got.br_startoff > end_fsb) { + ASSERT(idx > 0); + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got); + } - /* - * We can have a hole in the CoW fork if part of a directio - * write is CoW but part of it isn't. - */ - rlen = ilen = irec.br_blockcount; - if (irec.br_startblock == HOLESTARTBLOCK) + /* Walk backwards until we're out of the I/O range... */ + while (got.br_startoff + got.br_blockcount > offset_fsb) { + del = got; + xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb); + + /* Extent delete may have bumped idx forward */ + if (!del.br_blockcount) { + idx--; goto next_extent; + } + + ASSERT(!isnullstartblock(got.br_startblock)); /* Unmap the old blocks in the data fork. */ - while (rlen) { - xfs_defer_init(&dfops, &firstfsb); - error = __xfs_bunmapi(tp, ip, irec.br_startoff, - &rlen, 0, 1, &firstfsb, &dfops); - if (error) - goto out_defer; - - /* - * Trim the extent to whatever got unmapped. - * Remember, bunmapi works backwards. - */ - uirec.br_startblock = irec.br_startblock + rlen; - uirec.br_startoff = irec.br_startoff + rlen; - uirec.br_blockcount = irec.br_blockcount - rlen; - irec.br_blockcount = rlen; - trace_xfs_reflink_cow_remap_piece(ip, &uirec); + xfs_defer_init(&dfops, &firstfsb); + rlen = del.br_blockcount; + error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1, + &firstfsb, &dfops); + if (error) + goto out_defer; - /* Free the CoW orphan record. */ - error = xfs_refcount_free_cow_extent(tp->t_mountp, - &dfops, uirec.br_startblock, - uirec.br_blockcount); - if (error) - goto out_defer; + /* Trim the extent to whatever got unmapped. */ + if (rlen) { + xfs_trim_extent(&del, del.br_startoff + rlen, + del.br_blockcount - rlen); + } + trace_xfs_reflink_cow_remap(ip, &del); - /* Map the new blocks into the data fork. */ - error = xfs_bmap_map_extent(tp->t_mountp, &dfops, - ip, &uirec); - if (error) - goto out_defer; + /* Free the CoW orphan record. */ + error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops, + del.br_startblock, del.br_blockcount); + if (error) + goto out_defer; - /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &uirec); - if (error) - goto out_defer; + /* Map the new blocks into the data fork. */ + error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del); + if (error) + goto out_defer; - error = xfs_defer_finish(&tp, &dfops, ip); - if (error) - goto out_defer; - } + /* Remove the mapping from the CoW fork. */ + xfs_bmap_del_extent_cow(ip, &idx, &got, &del); + + error = xfs_defer_finish(&tp, &dfops, ip); + if (error) + goto out_defer; next_extent: - /* Roll on... */ - offset_fsb = irec.br_startoff + ilen; + if (idx < 0) + break; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } error = xfs_trans_commit(tp); @@ -774,7 +737,6 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); -out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: @@ -1312,19 +1274,26 @@ out_error: */ int xfs_reflink_remap_range( - struct xfs_inode *src, - xfs_off_t srcoff, - struct xfs_inode *dest, - xfs_off_t destoff, - xfs_off_t len, - unsigned int flags) + struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len, + bool is_dedupe) { + struct inode *inode_in = file_inode(file_in); + struct xfs_inode *src = XFS_I(inode_in); + struct inode *inode_out = file_inode(file_out); + struct xfs_inode *dest = XFS_I(inode_out); struct xfs_mount *mp = src->i_mount; + loff_t bs = inode_out->i_sb->s_blocksize; + bool same_inode = (inode_in == inode_out); xfs_fileoff_t sfsbno, dfsbno; xfs_filblks_t fsblen; - int error; xfs_extlen_t cowextsize; - bool is_same; + loff_t isize; + ssize_t ret; + loff_t blen; if (!xfs_sb_version_hasreflink(&mp->m_sb)) return -EOPNOTSUPP; @@ -1332,17 +1301,8 @@ xfs_reflink_remap_range( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - /* Don't reflink realtime inodes */ - if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) - return -EINVAL; - - if (flags & ~XFS_REFLINK_ALL) - return -EINVAL; - - trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff); - /* Lock both files against IO */ - if (src->i_ino == dest->i_ino) { + if (same_inode) { xfs_ilock(src, XFS_IOLOCK_EXCL); xfs_ilock(src, XFS_MMAPLOCK_EXCL); } else { @@ -1350,39 +1310,126 @@ xfs_reflink_remap_range( xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL); } + /* Don't touch certain kinds of inodes */ + ret = -EPERM; + if (IS_IMMUTABLE(inode_out)) + goto out_unlock; + + ret = -ETXTBSY; + if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) + goto out_unlock; + + + /* Don't reflink dirs, pipes, sockets... */ + ret = -EISDIR; + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + goto out_unlock; + ret = -EINVAL; + if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) + goto out_unlock; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + goto out_unlock; + + /* Don't reflink realtime inodes */ + if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) + goto out_unlock; + + /* Don't share DAX file data for now. */ + if (IS_DAX(inode_in) || IS_DAX(inode_out)) + goto out_unlock; + + /* Are we going all the way to the end? */ + isize = i_size_read(inode_in); + if (isize == 0) { + ret = 0; + goto out_unlock; + } + + if (len == 0) + len = isize - pos_in; + + /* Ensure offsets don't wrap and the input is inside i_size */ + if (pos_in + len < pos_in || pos_out + len < pos_out || + pos_in + len > isize) + goto out_unlock; + + /* Don't allow dedupe past EOF in the dest file */ + if (is_dedupe) { + loff_t disize; + + disize = i_size_read(inode_out); + if (pos_out >= disize || pos_out + len > disize) + goto out_unlock; + } + + /* If we're linking to EOF, continue to the block boundary. */ + if (pos_in + len == isize) + blen = ALIGN(isize, bs) - pos_in; + else + blen = len; + + /* Only reflink if we're aligned to block boundaries */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || + !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) + goto out_unlock; + + /* Don't allow overlapped reflink within the same file */ + if (same_inode) { + if (pos_out + blen > pos_in && pos_out < pos_in + blen) + goto out_unlock; + } + + /* Wait for the completion of any pending IOs on both files */ + inode_dio_wait(inode_in); + if (!same_inode) + inode_dio_wait(inode_out); + + ret = filemap_write_and_wait_range(inode_in->i_mapping, + pos_in, pos_in + len - 1); + if (ret) + goto out_unlock; + + ret = filemap_write_and_wait_range(inode_out->i_mapping, + pos_out, pos_out + len - 1); + if (ret) + goto out_unlock; + + trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + /* * Check that the extents are the same. */ - if (flags & XFS_REFLINK_DEDUPE) { - is_same = false; - error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest), - destoff, len, &is_same); - if (error) - goto out_error; + if (is_dedupe) { + bool is_same = false; + + ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out, + len, &is_same); + if (ret) + goto out_unlock; if (!is_same) { - error = -EBADE; - goto out_error; + ret = -EBADE; + goto out_unlock; } } - error = xfs_reflink_set_inode_flag(src, dest); - if (error) - goto out_error; + ret = xfs_reflink_set_inode_flag(src, dest); + if (ret) + goto out_unlock; /* * Invalidate the page cache so that we can clear any CoW mappings * in the destination file. */ - truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff, - PAGE_ALIGN(destoff + len) - 1); + truncate_inode_pages_range(&inode_out->i_data, pos_out, + PAGE_ALIGN(pos_out + len) - 1); - dfsbno = XFS_B_TO_FSBT(mp, destoff); - sfsbno = XFS_B_TO_FSBT(mp, srcoff); + dfsbno = XFS_B_TO_FSBT(mp, pos_out); + sfsbno = XFS_B_TO_FSBT(mp, pos_in); fsblen = XFS_B_TO_FSB(mp, len); - error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, - destoff + len); - if (error) - goto out_error; + ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, + pos_out + len); + if (ret) + goto out_unlock; /* * Carry the cowextsize hint from src to dest if we're sharing the @@ -1390,26 +1437,24 @@ xfs_reflink_remap_range( * has a cowextsize hint, and the destination file does not. */ cowextsize = 0; - if (srcoff == 0 && len == i_size_read(VFS_I(src)) && + if (pos_in == 0 && len == i_size_read(inode_in) && (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) && - destoff == 0 && len >= i_size_read(VFS_I(dest)) && + pos_out == 0 && len >= i_size_read(inode_out) && !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) cowextsize = src->i_d.di_cowextsize; - error = xfs_reflink_update_dest(dest, destoff + len, cowextsize); - if (error) - goto out_error; + ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize); -out_error: +out_unlock: xfs_iunlock(src, XFS_MMAPLOCK_EXCL); xfs_iunlock(src, XFS_IOLOCK_EXCL); if (src->i_ino != dest->i_ino) { xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); xfs_iunlock(dest, XFS_IOLOCK_EXCL); } - if (error) - trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_); - return error; + if (ret) + trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + return ret; } /* diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 5dc3c8a..fad1160 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno, extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed); -extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip, - xfs_off_t offset, xfs_off_t count); +extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, bool *shared); extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, @@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset, extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); -#define XFS_REFLINK_DEDUPE 1 /* only reflink if contents match */ -#define XFS_REFLINK_ALL (XFS_REFLINK_DEDUPE) -extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff, - struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len, - unsigned int flags); +extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe); extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, struct xfs_trans **tpp); extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset, diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 5f8d55d..276d302 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = { }; -struct kobj_type xfs_error_cfg_ktype = { +static struct kobj_type xfs_error_cfg_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, .default_attrs = xfs_error_attrs, }; -struct kobj_type xfs_error_ktype = { +static struct kobj_type xfs_error_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, }; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ad188d3..0907752 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); -DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range); +DEFINE_RW_EVENT(xfs_reflink_reserve_cow); DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range); DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write); @@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap); -DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece); -DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index af59638..a428aec 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -785,7 +785,7 @@ extern struct of_device_id __clk_of_table; * routines, one at of_clk_init(), and one at platform device probe */ #define CLK_OF_DECLARE_DRIVER(name, compat, fn) \ - static void name##_of_clk_init_driver(struct device_node *np) \ + static void __init name##_of_clk_init_driver(struct device_node *np) \ { \ of_node_clear_flag(np, OF_POPULATED); \ fn(np); \ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index e63e288..7892f55 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -19,11 +19,15 @@ struct vm_fault; #define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ /* - * Flags for iomap mappings: + * Flags for all iomap mappings: */ -#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */ -#define IOMAP_F_SHARED 0x02 /* block shared with another file */ -#define IOMAP_F_NEW 0x04 /* blocks have been newly allocated */ +#define IOMAP_F_NEW 0x01 /* blocks have been newly allocated */ + +/* + * Flags that only need to be reported for IOMAP_REPORT requests: + */ +#define IOMAP_F_MERGED 0x10 /* contains multiple blocks/extents */ +#define IOMAP_F_SHARED 0x20 /* block shared with another file */ /* * Magic value for blkno: @@ -42,8 +46,9 @@ struct iomap { /* * Flags for iomap_begin / iomap_end. No flag implies a read. */ -#define IOMAP_WRITE (1 << 0) -#define IOMAP_ZERO (1 << 1) +#define IOMAP_WRITE (1 << 0) /* writing, must allocate blocks */ +#define IOMAP_ZERO (1 << 1) /* zeroing operation, may skip holes */ +#define IOMAP_REPORT (1 << 2) /* report extent status, e.g. FIEMAP */ struct iomap_ops { /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 3a19185..a92c8d7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1271,10 +1271,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, int len, unsigned int gup_flags); -long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int foll_flags, struct page **pages, - struct vm_area_struct **vmas, int *nonblocking); long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7f2ae99..0f088f3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -440,33 +440,7 @@ struct zone { seqlock_t span_seqlock; #endif - /* - * wait_table -- the array holding the hash table - * wait_table_hash_nr_entries -- the size of the hash table array - * wait_table_bits -- wait_table_size == (1 << wait_table_bits) - * - * The purpose of all these is to keep track of the people - * waiting for a page to become available and make them - * runnable again when possible. The trouble is that this - * consumes a lot of space, especially when so few things - * wait on pages at a given time. So instead of using - * per-page waitqueues, we use a waitqueue hash table. - * - * The bucket discipline is to sleep on the same queue when - * colliding and wake all in that wait queue when removing. - * When something wakes, it must check to be sure its page is - * truly available, a la thundering herd. The cost of a - * collision is great, but given the expected load of the - * table, they should be so rare as to be outweighed by the - * benefits from the saved space. - * - * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the - * primary users of these fields, and in mm/page_alloc.c - * free_area_init_core() performs the initialization of them. - */ - wait_queue_head_t *wait_table; - unsigned long wait_table_hash_nr_entries; - unsigned long wait_table_bits; + int initialized; /* Write-intensive fields used from the page allocator */ ZONE_PADDING(_pad1_) @@ -546,7 +520,7 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn) static inline bool zone_is_initialized(struct zone *zone) { - return !!zone->wait_table; + return zone->initialized; } static inline bool zone_is_empty(struct zone *zone) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 94732d1..42d4027 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7515,11 +7515,27 @@ static struct kmem_cache *task_group_cache __read_mostly; DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); +#define WAIT_TABLE_BITS 8 +#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS) +static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned; + +wait_queue_head_t *bit_waitqueue(void *word, int bit) +{ + const int shift = BITS_PER_LONG == 32 ? 5 : 6; + unsigned long val = (unsigned long)word << shift | bit; + + return bit_wait_table + hash_long(val, WAIT_TABLE_BITS); +} +EXPORT_SYMBOL(bit_waitqueue); + void __init sched_init(void) { int i, j; unsigned long alloc_size = 0, ptr; + for (i = 0; i < WAIT_TABLE_SIZE; i++) + init_waitqueue_head(bit_wait_table + i); + #ifdef CONFIG_FAIR_GROUP_SCHED alloc_size += 2 * nr_cpu_ids * sizeof(void **); #endif diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 4f70535..9453efe 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -480,16 +480,6 @@ void wake_up_bit(void *word, int bit) } EXPORT_SYMBOL(wake_up_bit); -wait_queue_head_t *bit_waitqueue(void *word, int bit) -{ - const int shift = BITS_PER_LONG == 32 ? 5 : 6; - const struct zone *zone = page_zone(virt_to_page(word)); - unsigned long val = (unsigned long)word << shift | bit; - - return &zone->wait_table[hash_long(val, zone->wait_table_bits)]; -} -EXPORT_SYMBOL(bit_waitqueue); - /* * Manipulate the atomic_t address to produce a better bit waitqueue table hash * index (we're keying off bit -1, but that would produce a horrible hash diff --git a/kernel/softirq.c b/kernel/softirq.c index 1bf81ef..744fa61 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -58,7 +58,7 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp DEFINE_PER_CPU(struct task_struct *, ksoftirqd); const char * const softirq_to_name[NR_SOFTIRQS] = { - "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "BLOCK_IOPOLL", + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL", "TASKLET", "SCHED", "HRTIMER", "RCU" }; diff --git a/mm/filemap.c b/mm/filemap.c index 849f459..c7fe2f1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -790,9 +790,7 @@ EXPORT_SYMBOL(__page_cache_alloc); */ wait_queue_head_t *page_waitqueue(struct page *page) { - const struct zone *zone = page_zone(page); - - return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)]; + return bit_waitqueue(page, 0); } EXPORT_SYMBOL(page_waitqueue); @@ -526,7 +526,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ -long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, +static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *nonblocking) @@ -631,7 +631,6 @@ next_page: } while (nr_pages); return i; } -EXPORT_SYMBOL(__get_user_pages); bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9629273..b18dab40 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -268,7 +268,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat) unsigned long i, pfn, end_pfn, nr_pages; int node = pgdat->node_id; struct page *page; - struct zone *zone; nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; page = virt_to_page(pgdat); @@ -276,19 +275,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat) for (i = 0; i < nr_pages; i++, page++) get_page_bootmem(node, page, NODE_INFO); - zone = &pgdat->node_zones[0]; - for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) { - if (zone_is_initialized(zone)) { - nr_pages = zone->wait_table_hash_nr_entries - * sizeof(wait_queue_head_t); - nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT; - page = virt_to_page(zone->wait_table); - - for (i = 0; i < nr_pages; i++, page++) - get_page_bootmem(node, page, NODE_INFO); - } - } - pfn = pgdat->node_start_pfn; end_pfn = pgdat_end_pfn(pgdat); @@ -2158,20 +2144,6 @@ void try_offline_node(int nid) */ node_set_offline(nid); unregister_one_node(nid); - - /* free waittable in each zone */ - for (i = 0; i < MAX_NR_ZONES; i++) { - struct zone *zone = pgdat->node_zones + i; - - /* - * wait_table may be allocated from boot memory, - * here only free if it's allocated by vmalloc. - */ - if (is_vmalloc_addr(zone->wait_table)) { - vfree(zone->wait_table); - zone->wait_table = NULL; - } - } } EXPORT_SYMBOL(try_offline_node); @@ -109,7 +109,7 @@ unsigned int kobjsize(const void *objp) return PAGE_SIZE << compound_order(page); } -long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, +static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int foll_flags, struct page **pages, struct vm_area_struct **vmas, int *nonblocking) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2b3bf67..de7c6e4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4977,72 +4977,6 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) } /* - * Helper functions to size the waitqueue hash table. - * Essentially these want to choose hash table sizes sufficiently - * large so that collisions trying to wait on pages are rare. - * But in fact, the number of active page waitqueues on typical - * systems is ridiculously low, less than 200. So this is even - * conservative, even though it seems large. - * - * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to - * waitqueues, i.e. the size of the waitq table given the number of pages. - */ -#define PAGES_PER_WAITQUEUE 256 - -#ifndef CONFIG_MEMORY_HOTPLUG -static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) -{ - unsigned long size = 1; - - pages /= PAGES_PER_WAITQUEUE; - - while (size < pages) - size <<= 1; - - /* - * Once we have dozens or even hundreds of threads sleeping - * on IO we've got bigger problems than wait queue collision. - * Limit the size of the wait table to a reasonable size. - */ - size = min(size, 4096UL); - - return max(size, 4UL); -} -#else -/* - * A zone's size might be changed by hot-add, so it is not possible to determine - * a suitable size for its wait_table. So we use the maximum size now. - * - * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie: - * - * i386 (preemption config) : 4096 x 16 = 64Kbyte. - * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte. - * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte. - * - * The maximum entries are prepared when a zone's memory is (512K + 256) pages - * or more by the traditional way. (See above). It equals: - * - * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte. - * ia64(16K page size) : = ( 8G + 4M)byte. - * powerpc (64K page size) : = (32G +16M)byte. - */ -static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) -{ - return 4096UL; -} -#endif - -/* - * This is an integer logarithm so that shifts can be used later - * to extract the more random high bits from the multiplicative - * hash function before the remainder is taken. - */ -static inline unsigned long wait_table_bits(unsigned long size) -{ - return ffz(~size); -} - -/* * Initially all pages are reserved - free ones are freed * up by free_all_bootmem() once the early boot process is * done. Non-atomic initialization, single-pass. @@ -5304,49 +5238,6 @@ void __init setup_per_cpu_pageset(void) alloc_percpu(struct per_cpu_nodestat); } -static noinline __ref -int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) -{ - int i; - size_t alloc_size; - - /* - * The per-page waitqueue mechanism uses hashed waitqueues - * per zone. - */ - zone->wait_table_hash_nr_entries = - wait_table_hash_nr_entries(zone_size_pages); - zone->wait_table_bits = - wait_table_bits(zone->wait_table_hash_nr_entries); - alloc_size = zone->wait_table_hash_nr_entries - * sizeof(wait_queue_head_t); - - if (!slab_is_available()) { - zone->wait_table = (wait_queue_head_t *) - memblock_virt_alloc_node_nopanic( - alloc_size, zone->zone_pgdat->node_id); - } else { - /* - * This case means that a zone whose size was 0 gets new memory - * via memory hot-add. - * But it may be the case that a new node was hot-added. In - * this case vmalloc() will not be able to use this new node's - * memory - this wait_table must be initialized to use this new - * node itself as well. - * To use this new node's memory, further consideration will be - * necessary. - */ - zone->wait_table = vmalloc(alloc_size); - } - if (!zone->wait_table) - return -ENOMEM; - - for (i = 0; i < zone->wait_table_hash_nr_entries; ++i) - init_waitqueue_head(zone->wait_table + i); - - return 0; -} - static __meminit void zone_pcp_init(struct zone *zone) { /* @@ -5367,10 +5258,7 @@ int __meminit init_currently_empty_zone(struct zone *zone, unsigned long size) { struct pglist_data *pgdat = zone->zone_pgdat; - int ret; - ret = zone_wait_table_init(zone, size); - if (ret) - return ret; + pgdat->nr_zones = zone_idx(zone) + 1; zone->zone_start_pfn = zone_start_pfn; @@ -5382,6 +5270,7 @@ int __meminit init_currently_empty_zone(struct zone *zone, zone_start_pfn, (zone_start_pfn + size)); zone_init_free_lists(zone); + zone->initialized = 1; return 0; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 28510e7..2907b7b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1346,21 +1346,19 @@ unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *w static int get_user_page_nowait(unsigned long start, int write, struct page **page) { - int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET; + int flags = FOLL_NOWAIT | FOLL_HWPOISON; if (write) flags |= FOLL_WRITE; - return __get_user_pages(current, current->mm, start, 1, flags, page, - NULL, NULL); + return get_user_pages(start, 1, flags, page, NULL); } static inline int check_user_page_hwpoison(unsigned long addr) { - int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE; + int rc, flags = FOLL_HWPOISON | FOLL_WRITE; - rc = __get_user_pages(current, current->mm, addr, 1, - flags, NULL, NULL, NULL); + rc = get_user_pages(addr, 1, flags, NULL, NULL); return rc == -EHWPOISON; } |