From: Linus Torvalds Date: Fri, 26 Jan 2007 22:47:05 +0000 (-0800) Subject: Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 X-Git-Tag: v2.6.20-rc7~56 X-Git-Url: http://git.samba.org/samba.git/?p=sfrench%2Fcifs-2.6.git;a=commitdiff_plain;h=d312c8f81c9810d669cdf13b28f1a5d474738eaf;hp=7399072a7348d025e7bcb5eb5d5e9be941d490b7 Merge /pub/scm/linux/kernel/git/davem/net-2.6 * master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: [NETFILTER]: nf_conntrack_pptp: fix NAT setup of expected GRE connections [NETFILTER]: nf_nat_pptp: fix expectation removal [NETFILTER]: nf_nat: fix ICMP translation with statically linked conntrack [TCP]: Restore SKB socket owner setting in tcp_transmit_skb(). [AF_PACKET]: Check device down state before hard header callbacks. [DECNET]: Handle a failure in neigh_parms_alloc (take 2) [BNX2]: Fix 2nd port's MAC address. [TCP]: Fix sorting of SACK blocks. [AF_PACKET]: Fix BPF handling. [IPV4]: Fix the fib trie iterator to work with a single entry routing tables --- diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt index 43b89c214d20..4d075a4558f9 100644 --- a/Documentation/filesystems/9p.txt +++ b/Documentation/filesystems/9p.txt @@ -73,8 +73,22 @@ OPTIONS RESOURCES ========= -The Linux version of the 9p server is now maintained under the npfs project -on sourceforge (http://sourceforge.net/projects/npfs). +Our current recommendation is to use Inferno (http://www.vitanuova.com/inferno) +as the 9p server. You can start a 9p server under Inferno by issuing the +following command: + ; styxlisten -A tcp!*!564 export '#U*' + +The -A specifies an unauthenticated export. The 564 is the port # (you may +have to choose a higher port number if running as a normal user). The '#U*' +specifies exporting the root of the Linux name space. You may specify a +subset of the namespace by extending the path: '#U*'/tmp would just export +/tmp. For more information, see the Inferno manual pages covering styxlisten +and export. + +A Linux version of the 9p server is now maintained under the npfs project +on sourceforge (http://sourceforge.net/projects/npfs). There is also a +more stable single-threaded version of the server (named spfs) available from +the same CVS repository. There are user and developer mailing lists available through the v9fs project on sourceforge (http://sourceforge.net/projects/v9fs). @@ -96,5 +110,5 @@ STATUS The 2.6 kernel support is working on PPC and x86. -PLEASE USE THE SOURCEFORGE BUG-TRACKER TO REPORT PROBLEMS. +PLEASE USE THE KERNEL BUGZILLA TO REPORT PROBLEMS. (http://bugzilla.kernel.org) diff --git a/MAINTAINERS b/MAINTAINERS index d6f04a81f761..f0596e452c5c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1137,9 +1137,9 @@ T: git kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git S: Maintained DSCC4 DRIVER -P: François Romieu -M: romieu@cogenit.fr -M: romieu@ensta.fr +P: Francois Romieu +M: romieu@fr.zoreil.com +L: netdev@vger.kernel.org S: Maintained DVB SUBSYSTEM AND DRIVERS @@ -1928,11 +1928,10 @@ S: Maintained KERNEL NFSD P: Neil Brown -M: neilb@cse.unsw.edu.au +M: neilb@suse.de L: nfs@lists.sourceforge.net W: http://nfs.sourceforge.net/ -W: http://www.cse.unsw.edu.au/~neilb/patches/linux-devel/ -S: Maintained +S: Supported KERNEL VIRTUAL MACHINE (KVM) P: Avi Kivity @@ -2993,9 +2992,9 @@ SOFTWARE RAID (Multiple Disks) SUPPORT P: Ingo Molnar M: mingo@redhat.com P: Neil Brown -M: neilb@cse.unsw.edu.au +M: neilb@suse.de L: linux-raid@vger.kernel.org -S: Maintained +S: Supported SOFTWARE SUSPEND: P: Pavel Machek @@ -3575,6 +3574,12 @@ M: khali@linux-fr.org L: i2c@lm-sensors.org S: Maintained +VIA VELOCITY NETWORK DRIVER +P: Francois Romieu +M: romieu@fr.zoreil.com +L: netdev@vger.kernel.org +S: Maintained + UCLINUX (AND M68KNOMMU) P: Greg Ungerer M: gerg@uclinux.org diff --git a/Makefile b/Makefile index 477f52e3c7f6..9e1adac8aa28 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 2 PATCHLEVEL = 6 SUBLEVEL = 20 -EXTRAVERSION =-rc5 +EXTRAVERSION =-rc6 NAME = Homicidal Dwarf Hamster # *DOCUMENTATION* diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index 06461b8b715d..5e47683fc63a 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -302,12 +302,16 @@ sysenter_past_esp: pushl $(__USER_CS) CFI_ADJUST_CFA_OFFSET 4 /*CFI_REL_OFFSET cs, 0*/ +#ifndef CONFIG_COMPAT_VDSO /* * Push current_thread_info()->sysenter_return to the stack. * A tiny bit of offset fixup is necessary - 4*4 means the 4 words * pushed above; +8 corresponds to copy_thread's esp0 setting. */ pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp) +#else + pushl $SYSENTER_RETURN +#endif CFI_ADJUST_CFA_OFFSET 4 CFI_REL_OFFSET eip, 0 diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c index 7de9117b5a3a..5da744204d10 100644 --- a/arch/i386/kernel/sysenter.c +++ b/arch/i386/kernel/sysenter.c @@ -79,11 +79,6 @@ int __init sysenter_setup(void) #ifdef CONFIG_COMPAT_VDSO __set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY); printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO)); -#else - /* - * In the non-compat case the ELF coredumping code needs the fixmap: - */ - __set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_KERNEL_RO); #endif if (!boot_cpu_has(X86_FEATURE_SEP)) { @@ -100,6 +95,7 @@ int __init sysenter_setup(void) return 0; } +#ifndef CONFIG_COMPAT_VDSO static struct page *syscall_nopage(struct vm_area_struct *vma, unsigned long adr, int *type) { @@ -146,6 +142,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack) vma->vm_end = addr + PAGE_SIZE; /* MAYWRITE to allow gdb to COW and set breakpoints */ vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYWRITE; + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + vma->vm_flags |= VM_ALWAYSDUMP; vma->vm_flags |= mm->def_flags; vma->vm_page_prot = protection_map[vma->vm_flags & 7]; vma->vm_ops = &syscall_vm_ops; @@ -187,3 +190,4 @@ int in_gate_area_no_task(unsigned long addr) { return 0; } +#endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 0855d55c194d..b268c417c0bf 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -484,6 +484,7 @@ config PPC_MAPLE select PPC_970_NAP select PPC_NATIVE select PPC_RTAS + select ATA_NONSTANDARD if ATA default n help This option enables support for the Maple 970FX Evaluation Board. diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index a4b28c73bba0..ae0ede19879d 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -284,6 +284,13 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, * pages though */ vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC; + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + vma->vm_flags |= VM_ALWAYSDUMP; vma->vm_flags |= mm->def_flags; vma->vm_page_prot = protection_map[vma->vm_flags & 0x7]; vma->vm_ops = &vdso_vmops; diff --git a/arch/um/Kconfig.i386 b/arch/um/Kconfig.i386 index f191a550a079..77558a88a2fe 100644 --- a/arch/um/Kconfig.i386 +++ b/arch/um/Kconfig.i386 @@ -19,22 +19,22 @@ config SEMAPHORE_SLEEPERS choice prompt "Host memory split" default HOST_VMSPLIT_3G - ---help--- - This is needed when the host kernel on which you run has a non-default - (like 2G/2G) memory split, instead of the customary 3G/1G. If you did - not recompile your own kernel but use the default distro's one, you can - safely accept the "Default split" option. + help + This is needed when the host kernel on which you run has a non-default + (like 2G/2G) memory split, instead of the customary 3G/1G. If you did + not recompile your own kernel but use the default distro's one, you can + safely accept the "Default split" option. - It can be enabled on recent (>=2.6.16-rc2) vanilla kernels via - CONFIG_VM_SPLIT_*, or on previous kernels with special patches (-ck - patchset by Con Kolivas, or other ones) - option names match closely the - host CONFIG_VM_SPLIT_* ones. + It can be enabled on recent (>=2.6.16-rc2) vanilla kernels via + CONFIG_VM_SPLIT_*, or on previous kernels with special patches (-ck + patchset by Con Kolivas, or other ones) - option names match closely the + host CONFIG_VM_SPLIT_* ones. - A lower setting (where 1G/3G is lowest and 3G/1G is higher) will - tolerate even more "normal" host kernels, but an higher setting will be - stricter. + A lower setting (where 1G/3G is lowest and 3G/1G is higher) will + tolerate even more "normal" host kernels, but an higher setting will be + stricter. - So, if you do not know what to do here, say 'Default split'. + So, if you do not know what to do here, say 'Default split'. config HOST_VMSPLIT_3G bool "Default split (3G/1G user/kernel host split)" @@ -67,13 +67,13 @@ config 3_LEVEL_PGTABLES config STUB_CODE hex - default 0xbfffe000 if !HOST_2G_2G - default 0x7fffe000 if HOST_2G_2G + default 0xbfffe000 if !HOST_VMSPLIT_2G + default 0x7fffe000 if HOST_VMSPLIT_2G config STUB_DATA hex - default 0xbffff000 if !HOST_2G_2G - default 0x7ffff000 if HOST_2G_2G + default 0xbffff000 if !HOST_VMSPLIT_2G + default 0x7ffff000 if HOST_VMSPLIT_2G config STUB_START hex diff --git a/arch/x86_64/ia32/ia32_binfmt.c b/arch/x86_64/ia32/ia32_binfmt.c index 543ef4f405e9..5ce0bd486bbf 100644 --- a/arch/x86_64/ia32/ia32_binfmt.c +++ b/arch/x86_64/ia32/ia32_binfmt.c @@ -64,55 +64,6 @@ typedef unsigned int elf_greg_t; #define ELF_NGREG (sizeof (struct user_regs_struct32) / sizeof(elf_greg_t)) typedef elf_greg_t elf_gregset_t[ELF_NGREG]; -/* - * These macros parameterize elf_core_dump in fs/binfmt_elf.c to write out - * extra segments containing the vsyscall DSO contents. Dumping its - * contents makes post-mortem fully interpretable later without matching up - * the same kernel and hardware config to see what PC values meant. - * Dumping its extra ELF program headers includes all the other information - * a debugger needs to easily find how the vsyscall DSO was being used. - */ -#define ELF_CORE_EXTRA_PHDRS (find_vma(current->mm, VSYSCALL32_BASE) ? \ - (VSYSCALL32_EHDR->e_phnum) : 0) -#define ELF_CORE_WRITE_EXTRA_PHDRS \ -do { \ - if (find_vma(current->mm, VSYSCALL32_BASE)) { \ - const struct elf32_phdr *const vsyscall_phdrs = \ - (const struct elf32_phdr *) (VSYSCALL32_BASE \ - + VSYSCALL32_EHDR->e_phoff);\ - int i; \ - Elf32_Off ofs = 0; \ - for (i = 0; i < VSYSCALL32_EHDR->e_phnum; ++i) { \ - struct elf32_phdr phdr = vsyscall_phdrs[i]; \ - if (phdr.p_type == PT_LOAD) { \ - BUG_ON(ofs != 0); \ - ofs = phdr.p_offset = offset; \ - phdr.p_memsz = PAGE_ALIGN(phdr.p_memsz); \ - phdr.p_filesz = phdr.p_memsz; \ - offset += phdr.p_filesz; \ - } \ - else \ - phdr.p_offset += ofs; \ - phdr.p_paddr = 0; /* match other core phdrs */ \ - DUMP_WRITE(&phdr, sizeof(phdr)); \ - } \ - } \ -} while (0) -#define ELF_CORE_WRITE_EXTRA_DATA \ -do { \ - if (find_vma(current->mm, VSYSCALL32_BASE)) { \ - const struct elf32_phdr *const vsyscall_phdrs = \ - (const struct elf32_phdr *) (VSYSCALL32_BASE \ - + VSYSCALL32_EHDR->e_phoff); \ - int i; \ - for (i = 0; i < VSYSCALL32_EHDR->e_phnum; ++i) { \ - if (vsyscall_phdrs[i].p_type == PT_LOAD) \ - DUMP_WRITE((void *) (u64) vsyscall_phdrs[i].p_vaddr,\ - PAGE_ALIGN(vsyscall_phdrs[i].p_memsz)); \ - } \ - } \ -} while (0) - struct elf_siginfo { int si_signo; /* signal number */ diff --git a/arch/x86_64/ia32/syscall32.c b/arch/x86_64/ia32/syscall32.c index 3e5ed20cba45..59f1fa155915 100644 --- a/arch/x86_64/ia32/syscall32.c +++ b/arch/x86_64/ia32/syscall32.c @@ -59,6 +59,13 @@ int syscall32_setup_pages(struct linux_binprm *bprm, int exstack) vma->vm_end = VSYSCALL32_END; /* MAYWRITE to allow gdb to COW and set breakpoints */ vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYWRITE; + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + vma->vm_flags |= VM_ALWAYSDUMP; vma->vm_flags |= mm->def_flags; vma->vm_page_prot = protection_map[vma->vm_flags & 7]; vma->vm_ops = &syscall32_vm_ops; @@ -75,6 +82,14 @@ int syscall32_setup_pages(struct linux_binprm *bprm, int exstack) return 0; } +const char *arch_vma_name(struct vm_area_struct *vma) +{ + if (vma->vm_start == VSYSCALL32_BASE && + vma->vm_mm && vma->vm_mm->task_size == IA32_PAGE_OFFSET) + return "[vdso]"; + return NULL; +} + static int __init init_syscall32(void) { syscall32_page = (void *)get_zeroed_page(GFP_KERNEL); diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 5207f9e4b443..cbb6f0814ce2 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -322,10 +322,6 @@ static int acpi_processor_get_performance_info(struct acpi_processor *pr) if (result) return result; - result = acpi_processor_get_platform_limit(pr); - if (result) - return result; - return 0; } diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index da21552d2b1c..1c94b43d2c9b 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -19,6 +19,10 @@ config ATA if ATA +config ATA_NONSTANDARD + bool + default n + config SATA_AHCI tristate "AHCI SATA support" depends on PCI diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index e3c7b312287a..28a82e3403f1 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -75,6 +75,7 @@ enum { AHCI_CMD_CLR_BUSY = (1 << 10), RX_FIS_D2H_REG = 0x40, /* offset of D2H Register FIS data */ + RX_FIS_SDB = 0x58, /* offset of SDB FIS data */ RX_FIS_UNK = 0x60, /* offset of Unknown FIS data */ board_ahci = 0, @@ -202,6 +203,10 @@ struct ahci_port_priv { dma_addr_t cmd_tbl_dma; void *rx_fis; dma_addr_t rx_fis_dma; + /* for NCQ spurious interrupt analysis */ + int ncq_saw_spurious_sdb_cnt; + unsigned int ncq_saw_d2h:1; + unsigned int ncq_saw_dmas:1; }; static u32 ahci_scr_read (struct ata_port *ap, unsigned int sc_reg); @@ -898,7 +903,7 @@ static int ahci_hardreset(struct ata_port *ap, unsigned int *class) /* clear D2H reception area to properly wait for D2H FIS */ ata_tf_init(ap->device, &tf); - tf.command = 0xff; + tf.command = 0x80; ata_tf_to_fis(&tf, d2h_fis, 0); rc = sata_std_hardreset(ap, class); @@ -1109,8 +1114,9 @@ static void ahci_host_intr(struct ata_port *ap) void __iomem *mmio = ap->host->mmio_base; void __iomem *port_mmio = ahci_port_base(mmio, ap->port_no); struct ata_eh_info *ehi = &ap->eh_info; + struct ahci_port_priv *pp = ap->private_data; u32 status, qc_active; - int rc; + int rc, known_irq = 0; status = readl(port_mmio + PORT_IRQ_STAT); writel(status, port_mmio + PORT_IRQ_STAT); @@ -1137,17 +1143,53 @@ static void ahci_host_intr(struct ata_port *ap) /* hmmm... a spurious interupt */ - /* some devices send D2H reg with I bit set during NCQ command phase */ - if (ap->sactive && (status & PORT_IRQ_D2H_REG_FIS)) + /* if !NCQ, ignore. No modern ATA device has broken HSM + * implementation for non-NCQ commands. + */ + if (!ap->sactive) return; - /* ignore interim PIO setup fis interrupts */ - if (ata_tag_valid(ap->active_tag) && (status & PORT_IRQ_PIOS_FIS)) - return; + if (status & PORT_IRQ_D2H_REG_FIS) { + if (!pp->ncq_saw_d2h) + ata_port_printk(ap, KERN_INFO, + "D2H reg with I during NCQ, " + "this message won't be printed again\n"); + pp->ncq_saw_d2h = 1; + known_irq = 1; + } + + if (status & PORT_IRQ_DMAS_FIS) { + if (!pp->ncq_saw_dmas) + ata_port_printk(ap, KERN_INFO, + "DMAS FIS during NCQ, " + "this message won't be printed again\n"); + pp->ncq_saw_dmas = 1; + known_irq = 1; + } + + if (status & PORT_IRQ_SDB_FIS && + pp->ncq_saw_spurious_sdb_cnt < 10) { + /* SDB FIS containing spurious completions might be + * dangerous, we need to know more about them. Print + * more of it. + */ + const u32 *f = pp->rx_fis + RX_FIS_SDB; + + ata_port_printk(ap, KERN_INFO, "Spurious SDB FIS during NCQ " + "issue=0x%x SAct=0x%x FIS=%08x:%08x%s\n", + readl(port_mmio + PORT_CMD_ISSUE), + readl(port_mmio + PORT_SCR_ACT), + le32_to_cpu(f[0]), le32_to_cpu(f[1]), + pp->ncq_saw_spurious_sdb_cnt < 10 ? + "" : ", shutting up"); + + pp->ncq_saw_spurious_sdb_cnt++; + known_irq = 1; + } - if (ata_ratelimit()) + if (!known_irq) ata_port_printk(ap, KERN_INFO, "spurious interrupt " - "(irq_stat 0x%x active_tag %d sactive 0x%x)\n", + "(irq_stat 0x%x active_tag 0x%x sactive 0x%x)\n", status, ap->active_tag, ap->sactive); } diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c index 908751d27e76..24af56081b5d 100644 --- a/drivers/ata/ata_generic.c +++ b/drivers/ata/ata_generic.c @@ -64,6 +64,7 @@ static void generic_error_handler(struct ata_port *ap) /** * generic_set_mode - mode setting * @ap: interface to set up + * @unused: returned device on error * * Use a non standard set_mode function. We don't want to be tuned. * The BIOS configured everything. Our job is not to fiddle. We @@ -71,7 +72,7 @@ static void generic_error_handler(struct ata_port *ap) * and respect them. */ -static void generic_set_mode(struct ata_port *ap) +static int generic_set_mode(struct ata_port *ap, struct ata_device **unused) { int dma_enabled = 0; int i; @@ -82,7 +83,7 @@ static void generic_set_mode(struct ata_port *ap) for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &ap->device[i]; - if (ata_dev_enabled(dev)) { + if (ata_dev_ready(dev)) { /* We don't really care */ dev->pio_mode = XFER_PIO_0; dev->dma_mode = XFER_MW_DMA_0; @@ -99,6 +100,7 @@ static void generic_set_mode(struct ata_port *ap) } } } + return 0; } static struct scsi_host_template generic_sht = { diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 0d51d13b16bf..a388a8df0043 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2431,18 +2431,8 @@ int ata_set_mode(struct ata_port *ap, struct ata_device **r_failed_dev) int i, rc = 0, used_dma = 0, found = 0; /* has private set_mode? */ - if (ap->ops->set_mode) { - /* FIXME: make ->set_mode handle no device case and - * return error code and failing device on failure. - */ - for (i = 0; i < ATA_MAX_DEVICES; i++) { - if (ata_dev_ready(&ap->device[i])) { - ap->ops->set_mode(ap); - break; - } - } - return 0; - } + if (ap->ops->set_mode) + return ap->ops->set_mode(ap, r_failed_dev); /* step 1: calculate xfer_mask */ for (i = 0; i < ATA_MAX_DEVICES; i++) { diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 623cec914c9b..12c88c588039 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -827,7 +827,8 @@ void ata_bmdma_error_handler(struct ata_port *ap) */ void ata_bmdma_post_internal_cmd(struct ata_queued_cmd *qc) { - ata_bmdma_stop(qc); + if (qc->ap->ioaddr.bmdma_addr) + ata_bmdma_stop(qc); } #ifdef CONFIG_PCI @@ -870,7 +871,8 @@ ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port, int pci_resource_start(pdev, 1) | ATA_PCI_CTL_OFS; bmdma = pci_resource_start(pdev, 4); if (bmdma) { - if (inb(bmdma + 2) & 0x80) + if ((!(port[p]->flags & ATA_FLAG_IGN_SIMPLEX)) && + (inb(bmdma + 2) & 0x80)) probe_ent->_host_flags |= ATA_HOST_SIMPLEX; probe_ent->port[p].bmdma_addr = bmdma; } @@ -886,7 +888,8 @@ ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port, int bmdma = pci_resource_start(pdev, 4); if (bmdma) { bmdma += 8; - if(inb(bmdma + 2) & 0x80) + if ((!(port[p]->flags & ATA_FLAG_IGN_SIMPLEX)) && + (inb(bmdma + 2) & 0x80)) probe_ent->_host_flags |= ATA_HOST_SIMPLEX; probe_ent->port[p].bmdma_addr = bmdma; } @@ -914,13 +917,14 @@ static struct ata_probe_ent *ata_pci_init_legacy_port(struct pci_dev *pdev, probe_ent->irq_flags = IRQF_SHARED; if (port_mask & ATA_PORT_PRIMARY) { - probe_ent->irq = ATA_PRIMARY_IRQ; + probe_ent->irq = ATA_PRIMARY_IRQ(pdev); probe_ent->port[0].cmd_addr = ATA_PRIMARY_CMD; probe_ent->port[0].altstatus_addr = probe_ent->port[0].ctl_addr = ATA_PRIMARY_CTL; if (bmdma) { probe_ent->port[0].bmdma_addr = bmdma; - if (inb(bmdma + 2) & 0x80) + if ((!(port[0]->flags & ATA_FLAG_IGN_SIMPLEX)) && + (inb(bmdma + 2) & 0x80)) probe_ent->_host_flags |= ATA_HOST_SIMPLEX; } ata_std_ports(&probe_ent->port[0]); @@ -929,15 +933,16 @@ static struct ata_probe_ent *ata_pci_init_legacy_port(struct pci_dev *pdev, if (port_mask & ATA_PORT_SECONDARY) { if (probe_ent->irq) - probe_ent->irq2 = ATA_SECONDARY_IRQ; + probe_ent->irq2 = ATA_SECONDARY_IRQ(pdev); else - probe_ent->irq = ATA_SECONDARY_IRQ; + probe_ent->irq = ATA_SECONDARY_IRQ(pdev); probe_ent->port[1].cmd_addr = ATA_SECONDARY_CMD; probe_ent->port[1].altstatus_addr = probe_ent->port[1].ctl_addr = ATA_SECONDARY_CTL; if (bmdma) { probe_ent->port[1].bmdma_addr = bmdma + 8; - if (inb(bmdma + 10) & 0x80) + if ((!(port[1]->flags & ATA_FLAG_IGN_SIMPLEX)) && + (inb(bmdma + 10) & 0x80)) probe_ent->_host_flags |= ATA_HOST_SIMPLEX; } ata_std_ports(&probe_ent->port[1]); diff --git a/drivers/ata/pata_cmd64x.c b/drivers/ata/pata_cmd64x.c index 15841a563694..449162cbf93e 100644 --- a/drivers/ata/pata_cmd64x.c +++ b/drivers/ata/pata_cmd64x.c @@ -197,7 +197,7 @@ static void cmd64x_set_piomode(struct ata_port *ap, struct ata_device *adev) static void cmd64x_set_dmamode(struct ata_port *ap, struct ata_device *adev) { static const u8 udma_data[] = { - 0x31, 0x21, 0x11, 0x25, 0x15, 0x05 + 0x30, 0x20, 0x10, 0x20, 0x10, 0x00 }; static const u8 mwdma_data[] = { 0x30, 0x20, 0x10 @@ -213,12 +213,21 @@ static void cmd64x_set_dmamode(struct ata_port *ap, struct ata_device *adev) pci_read_config_byte(pdev, pciD, ®D); pci_read_config_byte(pdev, pciU, ®U); - regD &= ~(0x20 << shift); - regU &= ~(0x35 << shift); + /* DMA bits off */ + regD &= ~(0x20 << adev->devno); + /* DMA control bits */ + regU &= ~(0x30 << shift); + /* DMA timing bits */ + regU &= ~(0x05 << adev->devno); - if (adev->dma_mode >= XFER_UDMA_0) + if (adev->dma_mode >= XFER_UDMA_0) { + /* Merge thge timing value */ regU |= udma_data[adev->dma_mode - XFER_UDMA_0] << shift; - else + /* Merge the control bits */ + regU |= 1 << adev->devno; /* UDMA on */ + if (adev->dma_mode > 2) /* 15nS timing */ + regU |= 4 << adev->devno; + } else regD |= mwdma_data[adev->dma_mode - XFER_MW_DMA_0] << shift; regD |= 0x20 << adev->devno; @@ -239,8 +248,8 @@ static void cmd648_bmdma_stop(struct ata_queued_cmd *qc) struct ata_port *ap = qc->ap; struct pci_dev *pdev = to_pci_dev(ap->host->dev); u8 dma_intr; - int dma_reg = ap->port_no ? ARTTIM23_INTR_CH1 : CFR_INTR_CH0; - int dma_mask = ap->port_no ? ARTTIM2 : CFR; + int dma_mask = ap->port_no ? ARTTIM23_INTR_CH1 : CFR_INTR_CH0; + int dma_reg = ap->port_no ? ARTTIM2 : CFR; ata_bmdma_stop(qc); diff --git a/drivers/ata/pata_hpt3x2n.c b/drivers/ata/pata_hpt3x2n.c index f6817b4093a4..886fab9aa62c 100644 --- a/drivers/ata/pata_hpt3x2n.c +++ b/drivers/ata/pata_hpt3x2n.c @@ -25,7 +25,7 @@ #include #define DRV_NAME "pata_hpt3x2n" -#define DRV_VERSION "0.3" +#define DRV_VERSION "0.3.2" enum { HPT_PCI_FAST = (1 << 31), @@ -297,11 +297,11 @@ static int hpt3x2n_pair_idle(struct ata_port *ap) return 0; } -static int hpt3x2n_use_dpll(struct ata_port *ap, int reading) +static int hpt3x2n_use_dpll(struct ata_port *ap, int writing) { long flags = (long)ap->host->private_data; /* See if we should use the DPLL */ - if (reading == 0) + if (writing) return USE_DPLL; /* Needed for write */ if (flags & PCI66) return USE_DPLL; /* Needed at 66Mhz */ diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c index 0b56ff3d1cfe..e8afd486434a 100644 --- a/drivers/ata/pata_it821x.c +++ b/drivers/ata/pata_it821x.c @@ -476,6 +476,7 @@ static unsigned int it821x_passthru_qc_issue_prot(struct ata_queued_cmd *qc) /** * it821x_smart_set_mode - mode setting * @ap: interface to set up + * @unused: device that failed (error only) * * Use a non standard set_mode function. We don't want to be tuned. * The BIOS configured everything. Our job is not to fiddle. We @@ -483,7 +484,7 @@ static unsigned int it821x_passthru_qc_issue_prot(struct ata_queued_cmd *qc) * and respect them. */ -static void it821x_smart_set_mode(struct ata_port *ap) +static int it821x_smart_set_mode(struct ata_port *ap, struct ata_device **unused) { int dma_enabled = 0; int i; @@ -512,6 +513,7 @@ static void it821x_smart_set_mode(struct ata_port *ap) } } } + return 0; } /** diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index cb8924109f59..23b8aab3ebd8 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -23,9 +23,9 @@ #include #define DRV_NAME "pata_ixp4xx_cf" -#define DRV_VERSION "0.1.1" +#define DRV_VERSION "0.1.1ac1" -static void ixp4xx_set_mode(struct ata_port *ap) +static int ixp4xx_set_mode(struct ata_port *ap, struct ata_device *adev) { int i; @@ -38,6 +38,7 @@ static void ixp4xx_set_mode(struct ata_port *ap) dev->flags |= ATA_DFLAG_PIO; } } + return 0; } static void ixp4xx_phy_reset(struct ata_port *ap) diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index e7bf9d89c8ee..581cb33c6f45 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -96,6 +96,7 @@ static int pio_mask = 0x1F; /* PIO range for autospeed devices */ /** * legacy_set_mode - mode setting * @ap: IDE interface + * @unused: Device that failed when error is returned * * Use a non standard set_mode function. We don't want to be tuned. * @@ -105,7 +106,7 @@ static int pio_mask = 0x1F; /* PIO range for autospeed devices */ * expand on this as per hdparm in the base kernel. */ -static void legacy_set_mode(struct ata_port *ap) +static int legacy_set_mode(struct ata_port *ap, struct ata_device **unused) { int i; @@ -118,6 +119,7 @@ static void legacy_set_mode(struct ata_port *ap) dev->flags |= ATA_DFLAG_PIO; } } + return 0; } static struct scsi_host_template legacy_sht = { diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c index adf4cc134f25..cec0729225e1 100644 --- a/drivers/ata/pata_rz1000.c +++ b/drivers/ata/pata_rz1000.c @@ -52,19 +52,20 @@ static void rz1000_error_handler(struct ata_port *ap) /** * rz1000_set_mode - mode setting function * @ap: ATA interface + * @unused: returned device on set_mode failure * * Use a non standard set_mode function. We don't want to be tuned. We * would prefer to be BIOS generic but for the fact our hardware is * whacked out. */ -static void rz1000_set_mode(struct ata_port *ap) +static int rz1000_set_mode(struct ata_port *ap, struct ata_device **unused) { int i; for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &ap->device[i]; - if (ata_dev_enabled(dev)) { + if (ata_dev_ready(dev)) { /* We don't really care */ dev->pio_mode = XFER_PIO_0; dev->xfer_mode = XFER_PIO_0; @@ -72,6 +73,7 @@ static void rz1000_set_mode(struct ata_port *ap) dev->flags |= ATA_DFLAG_PIO; } } + return 0; } diff --git a/drivers/ata/sata_uli.c b/drivers/ata/sata_uli.c index 5c603ca3a50a..a43aec62d505 100644 --- a/drivers/ata/sata_uli.c +++ b/drivers/ata/sata_uli.c @@ -128,7 +128,8 @@ static const struct ata_port_operations uli_ops = { static struct ata_port_info uli_port_info = { .sht = &uli_sht, - .flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY, + .flags = ATA_FLAG_SATA | ATA_FLAG_NO_LEGACY | + ATA_FLAG_IGN_SIMPLEX, .pio_mask = 0x1f, /* pio0-4 */ .udma_mask = 0x7f, /* udma0-6 */ .port_ops = &uli_ops, diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c index 88f0565c8883..d3d5c0d57032 100644 --- a/drivers/ata/sata_via.c +++ b/drivers/ata/sata_via.c @@ -74,6 +74,7 @@ enum { static int svia_init_one (struct pci_dev *pdev, const struct pci_device_id *ent); static u32 svia_scr_read (struct ata_port *ap, unsigned int sc_reg); static void svia_scr_write (struct ata_port *ap, unsigned int sc_reg, u32 val); +static void svia_noop_freeze(struct ata_port *ap); static void vt6420_error_handler(struct ata_port *ap); static const struct pci_device_id svia_pci_tbl[] = { @@ -128,7 +129,7 @@ static const struct ata_port_operations vt6420_sata_ops = { .qc_issue = ata_qc_issue_prot, .data_xfer = ata_pio_data_xfer, - .freeze = ata_bmdma_freeze, + .freeze = svia_noop_freeze, .thaw = ata_bmdma_thaw, .error_handler = vt6420_error_handler, .post_internal_cmd = ata_bmdma_post_internal_cmd, @@ -204,6 +205,15 @@ static void svia_scr_write (struct ata_port *ap, unsigned int sc_reg, u32 val) outl(val, ap->ioaddr.scr_addr + (4 * sc_reg)); } +static void svia_noop_freeze(struct ata_port *ap) +{ + /* Some VIA controllers choke if ATA_NIEN is manipulated in + * certain way. Leave it alone and just clear pending IRQ. + */ + ata_chk_status(ap); + ata_bmdma_irq_clear(ap); +} + /** * vt6420_prereset - prereset for vt6420 * @ap: target ATA port diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 5ab5e393b882..c6281ccd4fe7 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -122,8 +122,6 @@ struct efivar_entry { struct kobject kobj; }; -#define get_efivar_entry(n) list_entry(n, struct efivar_entry, list) - struct efivar_attribute { struct attribute attr; ssize_t (*show) (struct efivar_entry *entry, char *buf); @@ -386,9 +384,6 @@ static struct sysfs_ops efivar_attr_ops = { static void efivar_release(struct kobject *kobj) { struct efivar_entry *var = container_of(kobj, struct efivar_entry, kobj); - spin_lock(&efivars_lock); - list_del(&var->list); - spin_unlock(&efivars_lock); kfree(var); } @@ -430,9 +425,8 @@ static ssize_t efivar_create(struct subsystem *sub, const char *buf, size_t count) { struct efi_variable *new_var = (struct efi_variable *)buf; - struct efivar_entry *search_efivar = NULL; + struct efivar_entry *search_efivar, *n; unsigned long strsize1, strsize2; - struct list_head *pos, *n; efi_status_t status = EFI_NOT_FOUND; int found = 0; @@ -444,8 +438,7 @@ efivar_create(struct subsystem *sub, const char *buf, size_t count) /* * Does this variable already exist? */ - list_for_each_safe(pos, n, &efivar_list) { - search_efivar = get_efivar_entry(pos); + list_for_each_entry_safe(search_efivar, n, &efivar_list, list) { strsize1 = utf8_strsize(search_efivar->var.VariableName, 1024); strsize2 = utf8_strsize(new_var->VariableName, 1024); if (strsize1 == strsize2 && @@ -490,9 +483,8 @@ static ssize_t efivar_delete(struct subsystem *sub, const char *buf, size_t count) { struct efi_variable *del_var = (struct efi_variable *)buf; - struct efivar_entry *search_efivar = NULL; + struct efivar_entry *search_efivar, *n; unsigned long strsize1, strsize2; - struct list_head *pos, *n; efi_status_t status = EFI_NOT_FOUND; int found = 0; @@ -504,8 +496,7 @@ efivar_delete(struct subsystem *sub, const char *buf, size_t count) /* * Does this variable already exist? */ - list_for_each_safe(pos, n, &efivar_list) { - search_efivar = get_efivar_entry(pos); + list_for_each_entry_safe(search_efivar, n, &efivar_list, list) { strsize1 = utf8_strsize(search_efivar->var.VariableName, 1024); strsize2 = utf8_strsize(del_var->VariableName, 1024); if (strsize1 == strsize2 && @@ -537,9 +528,9 @@ efivar_delete(struct subsystem *sub, const char *buf, size_t count) spin_unlock(&efivars_lock); return -EIO; } + list_del(&search_efivar->list); /* We need to release this lock before unregistering. */ spin_unlock(&efivars_lock); - efivar_unregister(search_efivar); /* It's dead Jim.... */ @@ -768,10 +759,14 @@ out_free: static void __exit efivars_exit(void) { - struct list_head *pos, *n; + struct efivar_entry *entry, *n; - list_for_each_safe(pos, n, &efivar_list) - efivar_unregister(get_efivar_entry(pos)); + list_for_each_entry_safe(entry, n, &efivar_list, list) { + spin_lock(&efivars_lock); + list_del(&entry->list); + spin_unlock(&efivars_lock); + efivar_unregister(entry); + } subsystem_unregister(&vars_subsys); firmware_unregister(&efi_subsys); diff --git a/drivers/isdn/gigaset/common.c b/drivers/isdn/gigaset/common.c index 95eff3b2917a..4f75cce6fdff 100644 --- a/drivers/isdn/gigaset/common.c +++ b/drivers/isdn/gigaset/common.c @@ -356,16 +356,17 @@ static struct cardstate *alloc_cs(struct gigaset_driver *drv) { unsigned long flags; unsigned i; - static struct cardstate *ret = NULL; + struct cardstate *ret = NULL; spin_lock_irqsave(&drv->lock, flags); for (i = 0; i < drv->minors; ++i) { if (!(drv->flags[i] & VALID_MINOR)) { - drv->flags[i] = VALID_MINOR; - ret = drv->cs + i; - } - if (ret) + if (try_module_get(drv->owner)) { + drv->flags[i] = VALID_MINOR; + ret = drv->cs + i; + } break; + } } spin_unlock_irqrestore(&drv->lock, flags); return ret; @@ -376,6 +377,8 @@ static void free_cs(struct cardstate *cs) unsigned long flags; struct gigaset_driver *drv = cs->driver; spin_lock_irqsave(&drv->lock, flags); + if (drv->flags[cs->minor_index] & VALID_MINOR) + module_put(drv->owner); drv->flags[cs->minor_index] = 0; spin_unlock_irqrestore(&drv->lock, flags); } @@ -579,7 +582,7 @@ static struct bc_state *gigaset_initbcs(struct bc_state *bcs, } else if ((bcs->skb = dev_alloc_skb(SBUFSIZE + HW_HDR_LEN)) != NULL) skb_reserve(bcs->skb, HW_HDR_LEN); else { - warn("could not allocate skb\n"); + warn("could not allocate skb"); bcs->inputstate |= INS_skip_frame; } @@ -632,17 +635,25 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, int i; gig_dbg(DEBUG_INIT, "allocating cs"); - cs = alloc_cs(drv); - if (!cs) - goto error; + if (!(cs = alloc_cs(drv))) { + err("maximum number of devices exceeded"); + return NULL; + } + mutex_init(&cs->mutex); + mutex_lock(&cs->mutex); + gig_dbg(DEBUG_INIT, "allocating bcs[0..%d]", channels - 1); cs->bcs = kmalloc(channels * sizeof(struct bc_state), GFP_KERNEL); - if (!cs->bcs) + if (!cs->bcs) { + err("out of memory"); goto error; + } gig_dbg(DEBUG_INIT, "allocating inbuf"); cs->inbuf = kmalloc(sizeof(struct inbuf_t), GFP_KERNEL); - if (!cs->inbuf) + if (!cs->inbuf) { + err("out of memory"); goto error; + } cs->cs_init = 0; cs->channels = channels; @@ -654,8 +665,6 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, spin_lock_init(&cs->ev_lock); cs->ev_tail = 0; cs->ev_head = 0; - mutex_init(&cs->mutex); - mutex_lock(&cs->mutex); tasklet_init(&cs->event_tasklet, &gigaset_handle_event, (unsigned long) cs); @@ -684,8 +693,10 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, for (i = 0; i < channels; ++i) { gig_dbg(DEBUG_INIT, "setting up bcs[%d].read", i); - if (!gigaset_initbcs(cs->bcs + i, cs, i)) + if (!gigaset_initbcs(cs->bcs + i, cs, i)) { + err("could not allocate channel %d data", i); goto error; + } } ++cs->cs_init; @@ -720,8 +731,10 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, make_valid(cs, VALID_ID); ++cs->cs_init; gig_dbg(DEBUG_INIT, "setting up hw"); - if (!cs->ops->initcshw(cs)) + if (!cs->ops->initcshw(cs)) { + err("could not allocate device specific data"); goto error; + } ++cs->cs_init; @@ -743,8 +756,8 @@ struct cardstate *gigaset_initcs(struct gigaset_driver *drv, int channels, mutex_unlock(&cs->mutex); return cs; -error: if (cs) - mutex_unlock(&cs->mutex); +error: + mutex_unlock(&cs->mutex); gig_dbg(DEBUG_INIT, "failed"); gigaset_freecs(cs); return NULL; @@ -1040,7 +1053,6 @@ void gigaset_freedriver(struct gigaset_driver *drv) spin_unlock_irqrestore(&driver_lock, flags); gigaset_if_freedriver(drv); - module_put(drv->owner); kfree(drv->cs); kfree(drv->flags); @@ -1072,10 +1084,6 @@ struct gigaset_driver *gigaset_initdriver(unsigned minor, unsigned minors, if (!drv) return NULL; - if (!try_module_get(owner)) - goto out1; - - drv->cs = NULL; drv->have_tty = 0; drv->minor = minor; drv->minors = minors; @@ -1087,11 +1095,11 @@ struct gigaset_driver *gigaset_initdriver(unsigned minor, unsigned minors, drv->cs = kmalloc(minors * sizeof *drv->cs, GFP_KERNEL); if (!drv->cs) - goto out2; + goto error; drv->flags = kmalloc(minors * sizeof *drv->flags, GFP_KERNEL); if (!drv->flags) - goto out3; + goto error; for (i = 0; i < minors; ++i) { drv->flags[i] = 0; @@ -1108,11 +1116,8 @@ struct gigaset_driver *gigaset_initdriver(unsigned minor, unsigned minors, return drv; -out3: +error: kfree(drv->cs); -out2: - module_put(owner); -out1: kfree(drv); return NULL; } diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h index 91e0c75aca8f..2db1ca4c6800 100644 --- a/drivers/kvm/kvm.h +++ b/drivers/kvm/kvm.h @@ -242,6 +242,7 @@ struct kvm_vcpu { u64 pdptrs[4]; /* pae */ u64 shadow_efer; u64 apic_base; + u64 ia32_misc_enable_msr; int nmsrs; struct vmx_msr_entry *guest_msrs; struct vmx_msr_entry *host_msrs; diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c index be4651abe72c..b10972ed0c9f 100644 --- a/drivers/kvm/kvm_main.c +++ b/drivers/kvm/kvm_main.c @@ -1226,6 +1226,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_APICBASE: data = vcpu->apic_base; break; + case MSR_IA32_MISC_ENABLE: + data = vcpu->ia32_misc_enable_msr; + break; #ifdef CONFIG_X86_64 case MSR_EFER: data = vcpu->shadow_efer; @@ -1297,6 +1300,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_IA32_APICBASE: vcpu->apic_base = data; break; + case MSR_IA32_MISC_ENABLE: + vcpu->ia32_misc_enable_msr = data; + break; default: printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr); return 1; @@ -1600,6 +1606,10 @@ static u32 msrs_to_save[] = { static unsigned num_msrs_to_save; +static u32 emulated_msrs[] = { + MSR_IA32_MISC_ENABLE, +}; + static __init void kvm_init_msr_list(void) { u32 dummy[2]; @@ -1925,7 +1935,7 @@ static long kvm_dev_ioctl(struct file *filp, if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) goto out; n = msr_list.nmsrs; - msr_list.nmsrs = num_msrs_to_save; + msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) goto out; r = -E2BIG; @@ -1935,6 +1945,11 @@ static long kvm_dev_ioctl(struct file *filp, if (copy_to_user(user_msr_list->indices, &msrs_to_save, num_msrs_to_save * sizeof(u32))) goto out; + if (copy_to_user(user_msr_list->indices + + num_msrs_to_save * sizeof(u32), + &emulated_msrs, + ARRAY_SIZE(emulated_msrs) * sizeof(u32))) + goto out; r = 0; break; } diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c index c6f972914f08..22c426cd8cb2 100644 --- a/drivers/kvm/mmu.c +++ b/drivers/kvm/mmu.c @@ -143,6 +143,7 @@ static int dbg = 1; #define PFERR_PRESENT_MASK (1U << 0) #define PFERR_WRITE_MASK (1U << 1) #define PFERR_USER_MASK (1U << 2) +#define PFERR_FETCH_MASK (1U << 4) #define PT64_ROOT_LEVEL 4 #define PT32_ROOT_LEVEL 2 @@ -168,6 +169,11 @@ static int is_cpuid_PSE36(void) return 1; } +static int is_nx(struct kvm_vcpu *vcpu) +{ + return vcpu->shadow_efer & EFER_NX; +} + static int is_present_pte(unsigned long pte) { return pte & PT_PRESENT_MASK; @@ -992,16 +998,6 @@ static inline int fix_read_pf(u64 *shadow_ent) return 0; } -static int may_access(u64 pte, int write, int user) -{ - - if (user && !(pte & PT_USER_MASK)) - return 0; - if (write && !(pte & PT_WRITABLE_MASK)) - return 0; - return 1; -} - static void paging_free(struct kvm_vcpu *vcpu) { nonpaging_free(vcpu); diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h index 6bc41950fbb3..149fa45fd9a5 100644 --- a/drivers/kvm/paging_tmpl.h +++ b/drivers/kvm/paging_tmpl.h @@ -63,13 +63,15 @@ struct guest_walker { pt_element_t *ptep; pt_element_t inherited_ar; gfn_t gfn; + u32 error_code; }; /* * Fetch a guest pte for a guest virtual address */ -static void FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr) +static int FNAME(walk_addr)(struct guest_walker *walker, + struct kvm_vcpu *vcpu, gva_t addr, + int write_fault, int user_fault, int fetch_fault) { hpa_t hpa; struct kvm_memory_slot *slot; @@ -86,7 +88,7 @@ static void FNAME(walk_addr)(struct guest_walker *walker, walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3]; root = *walker->ptep; if (!(root & PT_PRESENT_MASK)) - return; + goto not_present; --walker->level; } #endif @@ -111,11 +113,23 @@ static void FNAME(walk_addr)(struct guest_walker *walker, ASSERT(((unsigned long)walker->table & PAGE_MASK) == ((unsigned long)ptep & PAGE_MASK)); - if (is_present_pte(*ptep) && !(*ptep & PT_ACCESSED_MASK)) - *ptep |= PT_ACCESSED_MASK; - if (!is_present_pte(*ptep)) - break; + goto not_present; + + if (write_fault && !is_writeble_pte(*ptep)) + if (user_fault || is_write_protection(vcpu)) + goto access_error; + + if (user_fault && !(*ptep & PT_USER_MASK)) + goto access_error; + +#if PTTYPE == 64 + if (fetch_fault && is_nx(vcpu) && (*ptep & PT64_NX_MASK)) + goto access_error; +#endif + + if (!(*ptep & PT_ACCESSED_MASK)) + *ptep |= PT_ACCESSED_MASK; /* avoid rmw */ if (walker->level == PT_PAGE_TABLE_LEVEL) { walker->gfn = (*ptep & PT_BASE_ADDR_MASK) @@ -146,6 +160,23 @@ static void FNAME(walk_addr)(struct guest_walker *walker, } walker->ptep = ptep; pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep); + return 1; + +not_present: + walker->error_code = 0; + goto err; + +access_error: + walker->error_code = PFERR_PRESENT_MASK; + +err: + if (write_fault) + walker->error_code |= PFERR_WRITE_MASK; + if (user_fault) + walker->error_code |= PFERR_USER_MASK; + if (fetch_fault) + walker->error_code |= PFERR_FETCH_MASK; + return 0; } static void FNAME(release_walker)(struct guest_walker *walker) @@ -347,8 +378,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code) { int write_fault = error_code & PFERR_WRITE_MASK; - int pte_present = error_code & PFERR_PRESENT_MASK; int user_fault = error_code & PFERR_USER_MASK; + int fetch_fault = error_code & PFERR_FETCH_MASK; struct guest_walker walker; u64 *shadow_pte; int fixed; @@ -365,19 +396,20 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, /* * Look up the shadow pte for the faulting address. */ - FNAME(walk_addr)(&walker, vcpu, addr); - shadow_pte = FNAME(fetch)(vcpu, addr, &walker); + r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault, + fetch_fault); /* * The page is not mapped by the guest. Let the guest handle it. */ - if (!shadow_pte) { - pgprintk("%s: not mapped\n", __FUNCTION__); - inject_page_fault(vcpu, addr, error_code); + if (!r) { + pgprintk("%s: guest page fault\n", __FUNCTION__); + inject_page_fault(vcpu, addr, walker.error_code); FNAME(release_walker)(&walker); return 0; } + shadow_pte = FNAME(fetch)(vcpu, addr, &walker); pgprintk("%s: shadow pte %p %llx\n", __FUNCTION__, shadow_pte, *shadow_pte); @@ -399,22 +431,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, * mmio: emulate if accessible, otherwise its a guest fault. */ if (is_io_pte(*shadow_pte)) { - if (may_access(*shadow_pte, write_fault, user_fault)) - return 1; - pgprintk("%s: io work, no access\n", __FUNCTION__); - inject_page_fault(vcpu, addr, - error_code | PFERR_PRESENT_MASK); - kvm_mmu_audit(vcpu, "post page fault (io)"); - return 0; - } - - /* - * pte not present, guest page fault. - */ - if (pte_present && !fixed && !write_pt) { - inject_page_fault(vcpu, addr, error_code); - kvm_mmu_audit(vcpu, "post page fault (guest)"); - return 0; + return 1; } ++kvm_stat.pf_fixed; @@ -429,7 +446,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr) pt_element_t guest_pte; gpa_t gpa; - FNAME(walk_addr)(&walker, vcpu, vaddr); + FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0); guest_pte = *walker.ptep; FNAME(release_walker)(&walker); diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c index 7397bfbbcb1c..9c70ff65e6b7 100644 --- a/drivers/kvm/svm.c +++ b/drivers/kvm/svm.c @@ -502,6 +502,7 @@ static void init_vmcb(struct vmcb *vmcb) (1ULL << INTERCEPT_IOIO_PROT) | (1ULL << INTERCEPT_MSR_PROT) | (1ULL << INTERCEPT_TASK_SWITCH) | + (1ULL << INTERCEPT_SHUTDOWN) | (1ULL << INTERCEPT_VMRUN) | (1ULL << INTERCEPT_VMMCALL) | (1ULL << INTERCEPT_VMLOAD) | @@ -680,14 +681,14 @@ static void svm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { - dt->limit = vcpu->svm->vmcb->save.ldtr.limit; - dt->base = vcpu->svm->vmcb->save.ldtr.base; + dt->limit = vcpu->svm->vmcb->save.idtr.limit; + dt->base = vcpu->svm->vmcb->save.idtr.base; } static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) { - vcpu->svm->vmcb->save.ldtr.limit = dt->limit; - vcpu->svm->vmcb->save.ldtr.base = dt->base ; + vcpu->svm->vmcb->save.idtr.limit = dt->limit; + vcpu->svm->vmcb->save.idtr.base = dt->base ; } static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) @@ -892,6 +893,19 @@ static int pf_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; } +static int shutdown_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +{ + /* + * VMCB is undefined after a SHUTDOWN intercept + * so reinitialize it. + */ + memset(vcpu->svm->vmcb, 0, PAGE_SIZE); + init_vmcb(vcpu->svm->vmcb); + + kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + return 0; +} + static int io_get_override(struct kvm_vcpu *vcpu, struct vmcb_seg **seg, int *addr_override) @@ -1249,6 +1263,7 @@ static int (*svm_exit_handlers[])(struct kvm_vcpu *vcpu, [SVM_EXIT_IOIO] = io_interception, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, + [SVM_EXIT_SHUTDOWN] = shutdown_interception, [SVM_EXIT_VMRUN] = invalid_op_interception, [SVM_EXIT_VMMCALL] = invalid_op_interception, [SVM_EXIT_VMLOAD] = invalid_op_interception, diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 5432d07c074d..11108165e264 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -479,9 +479,12 @@ static int bitmap_read_sb(struct bitmap *bitmap) int err = -EINVAL; /* page 0 is the superblock, read it... */ - if (bitmap->file) - bitmap->sb_page = read_page(bitmap->file, 0, bitmap, PAGE_SIZE); - else { + if (bitmap->file) { + loff_t isize = i_size_read(bitmap->file->f_mapping->host); + int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize; + + bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes); + } else { bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset, 0); } if (IS_ERR(bitmap->sb_page)) { @@ -877,7 +880,8 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) int count; /* unmap the old page, we're done with it */ if (index == num_pages-1) - count = bytes - index * PAGE_SIZE; + count = bytes + sizeof(bitmap_super_t) + - index * PAGE_SIZE; else count = PAGE_SIZE; if (index == 0) { diff --git a/drivers/md/dm.c b/drivers/md/dm.c index fe7c56e10435..3668b170ea68 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1116,7 +1116,8 @@ static int __bind(struct mapped_device *md, struct dm_table *t) if (size != get_capacity(md->disk)) memset(&md->geometry, 0, sizeof(md->geometry)); - __set_size(md, size); + if (md->suspended_bdev) + __set_size(md, size); if (size == 0) return 0; @@ -1264,6 +1265,11 @@ int dm_swap_table(struct mapped_device *md, struct dm_table *table) if (!dm_suspended(md)) goto out; + /* without bdev, the device size cannot be changed */ + if (!md->suspended_bdev) + if (get_capacity(md->disk) != dm_table_get_size(table)) + goto out; + __unbind(md); r = __bind(md, table); @@ -1341,11 +1347,14 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags) /* This does not get reverted if there's an error later. */ dm_table_presuspend_targets(map); - md->suspended_bdev = bdget_disk(md->disk, 0); - if (!md->suspended_bdev) { - DMWARN("bdget failed in dm_suspend"); - r = -ENOMEM; - goto flush_and_out; + /* bdget() can stall if the pending I/Os are not flushed */ + if (!noflush) { + md->suspended_bdev = bdget_disk(md->disk, 0); + if (!md->suspended_bdev) { + DMWARN("bdget failed in dm_suspend"); + r = -ENOMEM; + goto flush_and_out; + } } /* @@ -1473,8 +1482,10 @@ int dm_resume(struct mapped_device *md) unlock_fs(md); - bdput(md->suspended_bdev); - md->suspended_bdev = NULL; + if (md->suspended_bdev) { + bdput(md->suspended_bdev); + md->suspended_bdev = NULL; + } clear_bit(DMF_SUSPENDED, &md->flags); diff --git a/drivers/md/md.c b/drivers/md/md.c index d1cb45f6d6a9..e8807ea5377d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1633,7 +1633,8 @@ repeat: * and 'events' is odd, we can roll back to the previous clean state */ if (nospares && (mddev->in_sync && mddev->recovery_cp == MaxSector) - && (mddev->events & 1)) + && (mddev->events & 1) + && mddev->events != 1) mddev->events--; else { /* otherwise we have to go forward and ... */ @@ -3563,6 +3564,8 @@ static int get_bitmap_file(mddev_t * mddev, void __user * arg) char *ptr, *buf = NULL; int err = -ENOMEM; + md_allow_write(mddev); + file = kmalloc(sizeof(*file), GFP_KERNEL); if (!file) goto out; @@ -5031,6 +5034,33 @@ void md_write_end(mddev_t *mddev) } } +/* md_allow_write(mddev) + * Calling this ensures that the array is marked 'active' so that writes + * may proceed without blocking. It is important to call this before + * attempting a GFP_KERNEL allocation while holding the mddev lock. + * Must be called with mddev_lock held. + */ +void md_allow_write(mddev_t *mddev) +{ + if (!mddev->pers) + return; + if (mddev->ro) + return; + + spin_lock_irq(&mddev->write_lock); + if (mddev->in_sync) { + mddev->in_sync = 0; + set_bit(MD_CHANGE_CLEAN, &mddev->flags); + if (mddev->safemode_delay && + mddev->safemode == 0) + mddev->safemode = 1; + spin_unlock_irq(&mddev->write_lock); + md_update_sb(mddev, 0); + } else + spin_unlock_irq(&mddev->write_lock); +} +EXPORT_SYMBOL_GPL(md_allow_write); + static DECLARE_WAIT_QUEUE_HEAD(resync_wait); #define SYNC_MARKS 10 diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 164b25dca101..97ee870b265d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1266,6 +1266,11 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio) sbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset; sbio->bi_bdev = conf->mirrors[i].rdev->bdev; + for (j = 0; j < vcnt ; j++) + memcpy(page_address(sbio->bi_io_vec[j].bv_page), + page_address(pbio->bi_io_vec[j].bv_page), + PAGE_SIZE); + } } } @@ -2099,6 +2104,8 @@ static int raid1_reshape(mddev_t *mddev) return -EINVAL; } + md_allow_write(mddev); + raid_disks = mddev->raid_disks + mddev->delta_disks; if (raid_disks < conf->raid_disks) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index be008f034ada..467c16982d02 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -405,6 +405,8 @@ static int resize_stripes(raid5_conf_t *conf, int newsize) if (newsize <= conf->pool_size) return 0; /* never bother to shrink */ + md_allow_write(conf->mddev); + /* Step 1 */ sc = kmem_cache_create(conf->cache_name[1-conf->active_name], sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev), @@ -2678,7 +2680,7 @@ static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio) mdk_rdev_t *rdev; if (!in_chunk_boundary(mddev, raid_bio)) { - printk("chunk_aligned_read : non aligned\n"); + PRINTK("chunk_aligned_read : non aligned\n"); return 0; } /* @@ -3250,6 +3252,7 @@ raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len) else break; } + md_allow_write(mddev); while (new > conf->max_nr_stripes) { if (grow_one_stripe(conf)) conf->max_nr_stripes++; diff --git a/drivers/rtc/rtc-sysfs.c b/drivers/rtc/rtc-sysfs.c index 9418a59fb368..2ddd0cf07140 100644 --- a/drivers/rtc/rtc-sysfs.c +++ b/drivers/rtc/rtc-sysfs.c @@ -78,7 +78,7 @@ static struct attribute_group rtc_attr_group = { .attrs = rtc_attrs, }; -static int __devinit rtc_sysfs_add_device(struct class_device *class_dev, +static int rtc_sysfs_add_device(struct class_device *class_dev, struct class_interface *class_intf) { int err; diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c index 6ed3f1da9296..8b41f9cc2560 100644 --- a/drivers/spi/pxa2xx_spi.c +++ b/drivers/spi/pxa2xx_spi.c @@ -1169,8 +1169,9 @@ static int setup(struct spi_device *spi) spi->bits_per_word - 16 : spi->bits_per_word) | SSCR0_SSE | (spi->bits_per_word > 16 ? SSCR0_EDSS : 0); - chip->cr1 |= (((spi->mode & SPI_CPHA) != 0) << 4) - | (((spi->mode & SPI_CPOL) != 0) << 3); + chip->cr1 &= ~(SSCR1_SPO | SSCR1_SPH); + chip->cr1 |= (((spi->mode & SPI_CPHA) != 0) ? SSCR1_SPH : 0) + | (((spi->mode & SPI_CPOL) != 0) ? SSCR1_SPO : 0); /* NOTE: PXA25x_SSP _could_ use external clocking ... */ if (drv_data->ssp_type != PXA25x_SSP) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 270e6211c2e3..6307428d2c94 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -366,7 +366,6 @@ spi_alloc_master(struct device *dev, unsigned size) class_device_initialize(&master->cdev); master->cdev.class = &spi_master_class; - kobj_set_kset_s(&master->cdev, spi_master_class.subsys); master->cdev.dev = get_device(dev); spi_master_set_devdata(master, &master[1]); @@ -466,14 +465,20 @@ EXPORT_SYMBOL_GPL(spi_unregister_master); */ struct spi_master *spi_busnum_to_master(u16 bus_num) { - char name[9]; - struct kobject *bus; - - snprintf(name, sizeof name, "spi%u", bus_num); - bus = kset_find_obj(&spi_master_class.subsys.kset, name); - if (bus) - return container_of(bus, struct spi_master, cdev.kobj); - return NULL; + struct class_device *cdev; + struct spi_master *master = NULL; + struct spi_master *m; + + down(&spi_master_class.sem); + list_for_each_entry(cdev, &spi_master_class.children, node) { + m = container_of(cdev, struct spi_master, cdev); + if (m->bus_num == bus_num) { + master = spi_master_get(m); + break; + } + } + up(&spi_master_class.sem); + return master; } EXPORT_SYMBOL_GPL(spi_busnum_to_master); diff --git a/drivers/spi/spi_s3c24xx.c b/drivers/spi/spi_s3c24xx.c index 8ca08713528e..651379c51ae6 100644 --- a/drivers/spi/spi_s3c24xx.c +++ b/drivers/spi/spi_s3c24xx.c @@ -10,9 +10,6 @@ * */ - -//#define DEBUG - #include #include #include @@ -44,6 +41,9 @@ struct s3c24xx_spi { int len; int count; + int (*set_cs)(struct s3c2410_spi_info *spi, + int cs, int pol); + /* data buffers */ const unsigned char *tx; unsigned char *rx; @@ -64,6 +64,11 @@ static inline struct s3c24xx_spi *to_hw(struct spi_device *sdev) return spi_master_get_devdata(sdev->master); } +static void s3c24xx_spi_gpiocs(struct s3c2410_spi_info *spi, int cs, int pol) +{ + s3c2410_gpio_setpin(spi->pin_cs, pol); +} + static void s3c24xx_spi_chipsel(struct spi_device *spi, int value) { struct s3c24xx_spi *hw = to_hw(spi); @@ -72,10 +77,7 @@ static void s3c24xx_spi_chipsel(struct spi_device *spi, int value) switch (value) { case BITBANG_CS_INACTIVE: - if (hw->pdata->set_cs) - hw->pdata->set_cs(hw->pdata, value, cspol); - else - s3c2410_gpio_setpin(hw->pdata->pin_cs, cspol ^ 1); + hw->pdata->set_cs(hw->pdata, spi->chip_select, cspol^1); break; case BITBANG_CS_ACTIVE: @@ -96,14 +98,9 @@ static void s3c24xx_spi_chipsel(struct spi_device *spi, int value) /* write new configration */ writeb(spcon, hw->regs + S3C2410_SPCON); - - if (hw->pdata->set_cs) - hw->pdata->set_cs(hw->pdata, value, cspol); - else - s3c2410_gpio_setpin(hw->pdata->pin_cs, cspol); + hw->pdata->set_cs(hw->pdata, spi->chip_select, cspol); break; - } } @@ -330,9 +327,12 @@ static int s3c24xx_spi_probe(struct platform_device *pdev) /* setup any gpio we can */ if (!hw->pdata->set_cs) { + hw->set_cs = s3c24xx_spi_gpiocs; + s3c2410_gpio_setpin(hw->pdata->pin_cs, 1); s3c2410_gpio_cfgpin(hw->pdata->pin_cs, S3C2410_GPIO_OUTPUT); - } + } else + hw->set_cs = hw->pdata->set_cs; /* register our spi controller */ diff --git a/fs/9p/error.c b/fs/9p/error.c index ae91555c1558..0d7fa4e08812 100644 --- a/fs/9p/error.c +++ b/fs/9p/error.c @@ -83,6 +83,7 @@ int v9fs_errstr2errno(char *errstr, int len) if (errno == 0) { /* TODO: if error isn't found, add it dynamically */ + errstr[len] = 0; printk(KERN_ERR "%s: errstr :%s: not found\n", __FUNCTION__, errstr); errno = 1; diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 27507201f9e7..a9b6301a04fc 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "debug.h" #include "v9fs.h" @@ -84,6 +85,7 @@ struct v9fs_fid *v9fs_fid_create(struct v9fs_session_info *v9ses, int fid) new->iounit = 0; new->rdir_pos = 0; new->rdir_fcall = NULL; + init_MUTEX(&new->lock); INIT_LIST_HEAD(&new->list); return new; @@ -102,11 +104,11 @@ void v9fs_fid_destroy(struct v9fs_fid *fid) } /** - * v9fs_fid_lookup - retrieve the right fid from a particular dentry + * v9fs_fid_lookup - return a locked fid from a dentry * @dentry: dentry to look for fid in - * @type: intent of lookup (operation or traversal) * - * find a fid in the dentry + * find a fid in the dentry, obtain its semaphore and return a reference to it. + * code calling lookup is responsible for releasing lock * * TODO: only match fids that have the same uid as current user * @@ -124,7 +126,68 @@ struct v9fs_fid *v9fs_fid_lookup(struct dentry *dentry) if (!return_fid) { dprintk(DEBUG_ERROR, "Couldn't find a fid in dentry\n"); + return_fid = ERR_PTR(-EBADF); } + if(down_interruptible(&return_fid->lock)) + return ERR_PTR(-EINTR); + return return_fid; } + +/** + * v9fs_fid_clone - lookup the fid for a dentry, clone a private copy and release it + * @dentry: dentry to look for fid in + * + * find a fid in the dentry and then clone to a new private fid + * + * TODO: only match fids that have the same uid as current user + * + */ + +struct v9fs_fid *v9fs_fid_clone(struct dentry *dentry) +{ + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); + struct v9fs_fid *base_fid, *new_fid = ERR_PTR(-EBADF); + struct v9fs_fcall *fcall = NULL; + int fid, err; + + base_fid = v9fs_fid_lookup(dentry); + + if(IS_ERR(base_fid)) + return base_fid; + + if(base_fid) { /* clone fid */ + fid = v9fs_get_idpool(&v9ses->fidpool); + if (fid < 0) { + eprintk(KERN_WARNING, "newfid fails!\n"); + new_fid = ERR_PTR(-ENOSPC); + goto Release_Fid; + } + + err = v9fs_t_walk(v9ses, base_fid->fid, fid, NULL, &fcall); + if (err < 0) { + dprintk(DEBUG_ERROR, "clone walk didn't work\n"); + v9fs_put_idpool(fid, &v9ses->fidpool); + new_fid = ERR_PTR(err); + goto Free_Fcall; + } + new_fid = v9fs_fid_create(v9ses, fid); + if (new_fid == NULL) { + dprintk(DEBUG_ERROR, "out of memory\n"); + new_fid = ERR_PTR(-ENOMEM); + } +Free_Fcall: + kfree(fcall); + } + +Release_Fid: + up(&base_fid->lock); + return new_fid; +} + +void v9fs_fid_clunk(struct v9fs_session_info *v9ses, struct v9fs_fid *fid) +{ + v9fs_t_clunk(v9ses, fid->fid); + v9fs_fid_destroy(fid); +} diff --git a/fs/9p/fid.h b/fs/9p/fid.h index aa974d6875c3..48fc170c26c8 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -30,6 +30,8 @@ struct v9fs_fid { struct list_head list; /* list of fids associated with a dentry */ struct list_head active; /* XXX - debug */ + struct semaphore lock; + u32 fid; unsigned char fidopen; /* set when fid is opened */ unsigned char fidclunked; /* set when fid has already been clunked */ @@ -55,3 +57,6 @@ struct v9fs_fid *v9fs_fid_get_created(struct dentry *); void v9fs_fid_destroy(struct v9fs_fid *fid); struct v9fs_fid *v9fs_fid_create(struct v9fs_session_info *, int fid); int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry); +struct v9fs_fid *v9fs_fid_clone(struct dentry *dentry); +void v9fs_fid_clunk(struct v9fs_session_info *v9ses, struct v9fs_fid *fid); + diff --git a/fs/9p/mux.c b/fs/9p/mux.c index 944273c3dbff..147ceef8e537 100644 --- a/fs/9p/mux.c +++ b/fs/9p/mux.c @@ -132,8 +132,10 @@ int v9fs_mux_global_init(void) v9fs_mux_poll_tasks[i].task = NULL; v9fs_mux_wq = create_workqueue("v9fs"); - if (!v9fs_mux_wq) + if (!v9fs_mux_wq) { + printk(KERN_WARNING "v9fs: mux: creating workqueue failed\n"); return -ENOMEM; + } return 0; } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 0b96fae8b479..d9b561ba5e58 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -457,14 +457,19 @@ static int __init init_v9fs(void) v9fs_error_init(); - printk(KERN_INFO "Installing v9fs 9P2000 file system support\n"); + printk(KERN_INFO "Installing v9fs 9p2000 file system support\n"); ret = v9fs_mux_global_init(); - if (!ret) + if (ret) { + printk(KERN_WARNING "v9fs: starting mux failed\n"); return ret; + } ret = register_filesystem(&v9fs_fs_type); - if (!ret) + if (ret) { + printk(KERN_WARNING "v9fs: registering file system failed\n"); v9fs_mux_global_exit(); + } + return ret; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index e86a07151280..9f17b0cacdd0 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -55,53 +55,22 @@ int v9fs_file_open(struct inode *inode, struct file *file) struct v9fs_fid *vfid; struct v9fs_fcall *fcall = NULL; int omode; - int fid = V9FS_NOFID; int err; dprintk(DEBUG_VFS, "inode: %p file: %p \n", inode, file); - vfid = v9fs_fid_lookup(file->f_path.dentry); - if (!vfid) { - dprintk(DEBUG_ERROR, "Couldn't resolve fid from dentry\n"); - return -EBADF; - } - - fid = v9fs_get_idpool(&v9ses->fidpool); - if (fid < 0) { - eprintk(KERN_WARNING, "newfid fails!\n"); - return -ENOSPC; - } + vfid = v9fs_fid_clone(file->f_path.dentry); + if (IS_ERR(vfid)) + return PTR_ERR(vfid); - err = v9fs_t_walk(v9ses, vfid->fid, fid, NULL, &fcall); - if (err < 0) { - dprintk(DEBUG_ERROR, "rewalk didn't work\n"); - if (fcall && fcall->id == RWALK) - goto clunk_fid; - else { - v9fs_put_idpool(fid, &v9ses->fidpool); - goto free_fcall; - } - } - kfree(fcall); - - /* TODO: do special things for O_EXCL, O_NOFOLLOW, O_SYNC */ - /* translate open mode appropriately */ omode = v9fs_uflags2omode(file->f_flags); - err = v9fs_t_open(v9ses, fid, omode, &fcall); + err = v9fs_t_open(v9ses, vfid->fid, omode, &fcall); if (err < 0) { PRINT_FCALL_ERROR("open failed", fcall); - goto clunk_fid; - } - - vfid = kmalloc(sizeof(struct v9fs_fid), GFP_KERNEL); - if (vfid == NULL) { - dprintk(DEBUG_ERROR, "out of memory\n"); - err = -ENOMEM; - goto clunk_fid; + goto Clunk_Fid; } file->private_data = vfid; - vfid->fid = fid; vfid->fidopen = 1; vfid->fidclunked = 0; vfid->iounit = fcall->params.ropen.iounit; @@ -112,10 +81,8 @@ int v9fs_file_open(struct inode *inode, struct file *file) return 0; -clunk_fid: - v9fs_t_clunk(v9ses, fid); - -free_fcall: +Clunk_Fid: + v9fs_fid_clunk(v9ses, vfid); kfree(fcall); return err; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 18f26cdfd882..9109ba1d6969 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -416,12 +416,8 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir) sb = file_inode->i_sb; v9ses = v9fs_inode2v9ses(file_inode); v9fid = v9fs_fid_lookup(file); - - if (!v9fid) { - dprintk(DEBUG_ERROR, - "no v9fs_fid\n"); - return -EBADF; - } + if(IS_ERR(v9fid)) + return PTR_ERR(v9fid); fid = v9fid->fid; if (fid < 0) { @@ -433,11 +429,13 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir) result = v9fs_t_remove(v9ses, fid, &fcall); if (result < 0) { PRINT_FCALL_ERROR("remove fails", fcall); + goto Error; } v9fs_put_idpool(fid, &v9ses->fidpool); v9fs_fid_destroy(v9fid); +Error: kfree(fcall); return result; } @@ -473,9 +471,13 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, inode = NULL; vfid = NULL; v9ses = v9fs_inode2v9ses(dir); - dfid = v9fs_fid_lookup(dentry->d_parent); - perm = unixmode2p9mode(v9ses, mode); + dfid = v9fs_fid_clone(dentry->d_parent); + if(IS_ERR(dfid)) { + err = PTR_ERR(dfid); + goto error; + } + perm = unixmode2p9mode(v9ses, mode); if (nd && nd->flags & LOOKUP_OPEN) flags = nd->intent.open.flags - 1; else @@ -485,9 +487,10 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, perm, v9fs_uflags2omode(flags), NULL, &fid, &qid, &iounit); if (err) - goto error; + goto clunk_dfid; vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry); + v9fs_fid_clunk(v9ses, dfid); if (IS_ERR(vfid)) { err = PTR_ERR(vfid); vfid = NULL; @@ -525,6 +528,9 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, return 0; +clunk_dfid: + v9fs_fid_clunk(v9ses, dfid); + error: if (vfid) v9fs_fid_destroy(vfid); @@ -551,7 +557,12 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) inode = NULL; vfid = NULL; v9ses = v9fs_inode2v9ses(dir); - dfid = v9fs_fid_lookup(dentry->d_parent); + dfid = v9fs_fid_clone(dentry->d_parent); + if(IS_ERR(dfid)) { + err = PTR_ERR(dfid); + goto error; + } + perm = unixmode2p9mode(v9ses, mode | S_IFDIR); err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name, @@ -559,37 +570,36 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (err) { dprintk(DEBUG_ERROR, "create error %d\n", err); - goto error; - } - - err = v9fs_t_clunk(v9ses, fid); - if (err) { - dprintk(DEBUG_ERROR, "clunk error %d\n", err); - goto error; + goto clean_up_dfid; } vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry); if (IS_ERR(vfid)) { err = PTR_ERR(vfid); vfid = NULL; - goto error; + goto clean_up_dfid; } + v9fs_fid_clunk(v9ses, dfid); inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); inode = NULL; - goto error; + goto clean_up_fids; } dentry->d_op = &v9fs_dentry_operations; d_instantiate(dentry, inode); return 0; -error: +clean_up_fids: if (vfid) v9fs_fid_destroy(vfid); +clean_up_dfid: + v9fs_fid_clunk(v9ses, dfid); + +error: return err; } @@ -622,28 +632,23 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_op = &v9fs_dentry_operations; dirfid = v9fs_fid_lookup(dentry->d_parent); - if (!dirfid) { - dprintk(DEBUG_ERROR, "no dirfid\n"); - return ERR_PTR(-EINVAL); - } + if(IS_ERR(dirfid)) + return ERR_PTR(PTR_ERR(dirfid)); dirfidnum = dirfid->fid; - if (dirfidnum < 0) { - dprintk(DEBUG_ERROR, "no dirfid for inode %p, #%lu\n", - dir, dir->i_ino); - return ERR_PTR(-EBADF); - } - newfid = v9fs_get_idpool(&v9ses->fidpool); if (newfid < 0) { eprintk(KERN_WARNING, "newfid fails!\n"); - return ERR_PTR(-ENOSPC); + result = -ENOSPC; + goto Release_Dirfid; } result = v9fs_t_walk(v9ses, dirfidnum, newfid, (char *)dentry->d_name.name, &fcall); + up(&dirfid->lock); + if (result < 0) { if (fcall && fcall->id == RWALK) v9fs_t_clunk(v9ses, newfid); @@ -701,8 +706,12 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, return NULL; - FreeFcall: +Release_Dirfid: + up(&dirfid->lock); + +FreeFcall: kfree(fcall); + return ERR_PTR(result); } @@ -746,10 +755,8 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *old_inode = old_dentry->d_inode; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(old_inode); struct v9fs_fid *oldfid = v9fs_fid_lookup(old_dentry); - struct v9fs_fid *olddirfid = - v9fs_fid_lookup(old_dentry->d_parent); - struct v9fs_fid *newdirfid = - v9fs_fid_lookup(new_dentry->d_parent); + struct v9fs_fid *olddirfid; + struct v9fs_fid *newdirfid; struct v9fs_wstat wstat; struct v9fs_fcall *fcall = NULL; int fid = -1; @@ -759,16 +766,26 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, dprintk(DEBUG_VFS, "\n"); - if ((!oldfid) || (!olddirfid) || (!newdirfid)) { - dprintk(DEBUG_ERROR, "problem with arguments\n"); - return -EBADF; + if(IS_ERR(oldfid)) + return PTR_ERR(oldfid); + + olddirfid = v9fs_fid_clone(old_dentry->d_parent); + if(IS_ERR(olddirfid)) { + retval = PTR_ERR(olddirfid); + goto Release_lock; + } + + newdirfid = v9fs_fid_clone(new_dentry->d_parent); + if(IS_ERR(newdirfid)) { + retval = PTR_ERR(newdirfid); + goto Clunk_olddir; } /* 9P can only handle file rename in the same directory */ if (memcmp(&olddirfid->qid, &newdirfid->qid, sizeof(newdirfid->qid))) { dprintk(DEBUG_ERROR, "old dir and new dir are different\n"); - retval = -EPERM; - goto FreeFcallnBail; + retval = -EXDEV; + goto Clunk_newdir; } fid = oldfid->fid; @@ -779,7 +796,7 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, dprintk(DEBUG_ERROR, "no fid for old file #%lu\n", old_inode->i_ino); retval = -EBADF; - goto FreeFcallnBail; + goto Clunk_newdir; } v9fs_blank_wstat(&wstat); @@ -788,11 +805,20 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, retval = v9fs_t_wstat(v9ses, fid, &wstat, &fcall); - FreeFcallnBail: if (retval < 0) PRINT_FCALL_ERROR("wstat error", fcall); kfree(fcall); + +Clunk_newdir: + v9fs_fid_clunk(v9ses, newdirfid); + +Clunk_olddir: + v9fs_fid_clunk(v9ses, olddirfid); + +Release_lock: + up(&oldfid->lock); + return retval; } @@ -810,15 +836,12 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, { struct v9fs_fcall *fcall = NULL; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); - struct v9fs_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_fid *fid = v9fs_fid_clone(dentry); int err = -EPERM; dprintk(DEBUG_VFS, "dentry: %p\n", dentry); - if (!fid) { - dprintk(DEBUG_ERROR, - "couldn't find fid associated with dentry\n"); - return -EBADF; - } + if(IS_ERR(fid)) + return PTR_ERR(fid); err = v9fs_t_stat(v9ses, fid->fid, &fcall); @@ -831,6 +854,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, } kfree(fcall); + v9fs_fid_clunk(v9ses, fid); return err; } @@ -844,18 +868,14 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); - struct v9fs_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_fid *fid = v9fs_fid_clone(dentry); struct v9fs_fcall *fcall = NULL; struct v9fs_wstat wstat; int res = -EPERM; dprintk(DEBUG_VFS, "\n"); - - if (!fid) { - dprintk(DEBUG_ERROR, - "Couldn't find fid associated with dentry\n"); - return -EBADF; - } + if(IS_ERR(fid)) + return PTR_ERR(fid); v9fs_blank_wstat(&wstat); if (iattr->ia_valid & ATTR_MODE) @@ -887,6 +907,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) if (res >= 0) res = inode_setattr(dentry->d_inode, iattr); + v9fs_fid_clunk(v9ses, fid); return res; } @@ -987,18 +1008,15 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) struct v9fs_fcall *fcall = NULL; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); - struct v9fs_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_fid *fid = v9fs_fid_clone(dentry); - if (!fid) { - dprintk(DEBUG_ERROR, "could not resolve fid from dentry\n"); - retval = -EBADF; - goto FreeFcall; - } + if(IS_ERR(fid)) + return PTR_ERR(fid); if (!v9ses->extended) { retval = -EBADF; dprintk(DEBUG_ERROR, "not extended\n"); - goto FreeFcall; + goto ClunkFid; } dprintk(DEBUG_VFS, " %s\n", dentry->d_name.name); @@ -1009,8 +1027,10 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) goto FreeFcall; } - if (!fcall) - return -EIO; + if (!fcall) { + retval = -EIO; + goto ClunkFid; + } if (!(fcall->params.rstat.stat.mode & V9FS_DMSYMLINK)) { retval = -EINVAL; @@ -1028,9 +1048,12 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) fcall->params.rstat.stat.extension.str, buffer); retval = buflen; - FreeFcall: +FreeFcall: kfree(fcall); +ClunkFid: + v9fs_fid_clunk(v9ses, fid); + return retval; } @@ -1123,52 +1146,58 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, int err; u32 fid, perm; struct v9fs_session_info *v9ses; - struct v9fs_fid *dfid, *vfid; - struct inode *inode; + struct v9fs_fid *dfid, *vfid = NULL; + struct inode *inode = NULL; - inode = NULL; - vfid = NULL; v9ses = v9fs_inode2v9ses(dir); - dfid = v9fs_fid_lookup(dentry->d_parent); - perm = unixmode2p9mode(v9ses, mode); - if (!v9ses->extended) { dprintk(DEBUG_ERROR, "not extended\n"); return -EPERM; } + dfid = v9fs_fid_clone(dentry->d_parent); + if(IS_ERR(dfid)) { + err = PTR_ERR(dfid); + goto error; + } + + perm = unixmode2p9mode(v9ses, mode); + err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name, perm, V9FS_OREAD, (char *) extension, &fid, NULL, NULL); if (err) - goto error; + goto clunk_dfid; err = v9fs_t_clunk(v9ses, fid); if (err) - goto error; + goto clunk_dfid; vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry); if (IS_ERR(vfid)) { err = PTR_ERR(vfid); vfid = NULL; - goto error; + goto clunk_dfid; } inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); inode = NULL; - goto error; + goto free_vfid; } dentry->d_op = &v9fs_dentry_operations; d_instantiate(dentry, inode); return 0; -error: - if (vfid) - v9fs_fid_destroy(vfid); +free_vfid: + v9fs_fid_destroy(vfid); + +clunk_dfid: + v9fs_fid_clunk(v9ses, dfid); +error: return err; } @@ -1209,26 +1238,29 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { int retval; + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); struct v9fs_fid *oldfid; char *name; dprintk(DEBUG_VFS, " %lu,%s,%s\n", dir->i_ino, dentry->d_name.name, old_dentry->d_name.name); - oldfid = v9fs_fid_lookup(old_dentry); - if (!oldfid) { - dprintk(DEBUG_ERROR, "can't find oldfid\n"); - return -EPERM; - } + oldfid = v9fs_fid_clone(old_dentry); + if(IS_ERR(oldfid)) + return PTR_ERR(oldfid); name = __getname(); - if (unlikely(!name)) - return -ENOMEM; + if (unlikely(!name)) { + retval = -ENOMEM; + goto clunk_fid; + } sprintf(name, "%d\n", oldfid->fid); retval = v9fs_vfs_mkspecial(dir, dentry, V9FS_DMLINK, name); __putname(name); +clunk_fid: + v9fs_fid_clunk(v9ses, oldfid); return retval; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7cb28720f90e..669dbe5b0317 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -682,6 +682,15 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) retval = PTR_ERR(interpreter); if (IS_ERR(interpreter)) goto out_free_interp; + + /* + * If the binary is not readable then enforce + * mm->dumpable = 0 regardless of the interpreter's + * permissions. + */ + if (file_permission(interpreter, MAY_READ) < 0) + bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; + retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE); if (retval != BINPRM_BUF_SIZE) { @@ -1178,6 +1187,10 @@ static int dump_seek(struct file *file, loff_t off) */ static int maydump(struct vm_area_struct *vma) { + /* The vma can be set up to tell us the answer directly. */ + if (vma->vm_flags & VM_ALWAYSDUMP) + return 1; + /* Do not dump I/O mapped devices or special mappings */ if (vma->vm_flags & (VM_IO | VM_RESERVED)) return 0; @@ -1424,6 +1437,32 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) return sz; } +static struct vm_area_struct *first_vma(struct task_struct *tsk, + struct vm_area_struct *gate_vma) +{ + struct vm_area_struct *ret = tsk->mm->mmap; + + if (ret) + return ret; + return gate_vma; +} +/* + * Helper function for iterating across a vma list. It ensures that the caller + * will visit `gate_vma' prior to terminating the search. + */ +static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma, + struct vm_area_struct *gate_vma) +{ + struct vm_area_struct *ret; + + ret = this_vma->vm_next; + if (ret) + return ret; + if (this_vma == gate_vma) + return NULL; + return gate_vma; +} + /* * Actual dumper * @@ -1439,7 +1478,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) int segs; size_t size = 0; int i; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *gate_vma; struct elfhdr *elf = NULL; loff_t offset = 0, dataoff, foffset; unsigned long limit = current->signal->rlim[RLIMIT_CORE].rlim_cur; @@ -1525,6 +1564,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) segs += ELF_CORE_EXTRA_PHDRS; #endif + gate_vma = get_gate_vma(current); + if (gate_vma != NULL) + segs++; + /* Set up header */ fill_elf_header(elf, segs + 1); /* including notes section */ @@ -1592,7 +1635,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE); /* Write program headers for segments dump */ - for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) { + for (vma = first_vma(current, gate_vma); vma != NULL; + vma = next_vma(vma, gate_vma)) { struct elf_phdr phdr; size_t sz; @@ -1641,7 +1685,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) /* Align to page */ DUMP_SEEK(dataoff - foffset); - for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) { + for (vma = first_vma(current, gate_vma); vma != NULL; + vma = next_vma(vma, gate_vma)) { unsigned long addr; if (!maydump(vma)) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 6e6d4568d548..a4d933a51208 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -234,6 +234,14 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, goto error; } + /* + * If the binary is not readable then enforce + * mm->dumpable = 0 regardless of the interpreter's + * permissions. + */ + if (file_permission(interpreter, MAY_READ) < 0) + bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; + retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE); if (retval < 0) diff --git a/fs/buffer.c b/fs/buffer.c index 3b116078b4c3..460f1c43238e 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2834,7 +2834,7 @@ int try_to_free_buffers(struct page *page) int ret = 0; BUG_ON(!PageLocked(page)); - if (PageDirty(page) || PageWriteback(page)) + if (PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ @@ -2845,6 +2845,19 @@ int try_to_free_buffers(struct page *page) spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); spin_unlock(&mapping->private_lock); + + /* + * If the filesystem writes its buffers by hand (eg ext3) + * then we can have clean buffers against a dirty page. We + * clean the page here; otherwise the VM will never notice + * that the filesystem did any IO at all. + * + * Also, during truncate, discard_buffer will have marked all + * the page's buffers clean. We discover that here and clean + * the page also. + */ + if (ret) + cancel_dirty_page(page, PAGE_CACHE_SIZE); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c403b66ec83c..a4b142a6a2c7 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -251,8 +251,19 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) WARN_ON(inode->i_state & I_WILL_FREE); if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_LOCK)) { + struct address_space *mapping = inode->i_mapping; + int ret; + list_move(&inode->i_list, &inode->i_sb->s_dirty); - return 0; + + /* + * Even if we don't actually write the inode itself here, + * we can at least start some of the data writeout.. + */ + spin_unlock(&inode_lock); + ret = do_writepages(mapping, wbc); + spin_lock(&inode_lock); + return ret; } /* diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 277df40f098d..e695660921ec 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -990,15 +990,16 @@ encode_entry(struct readdir_cd *ccd, const char *name, } int -nfs3svc_encode_entry(struct readdir_cd *cd, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int d_type) +nfs3svc_encode_entry(void *cd, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int d_type) { return encode_entry(cd, name, namlen, offset, ino, d_type, 0); } int -nfs3svc_encode_entry_plus(struct readdir_cd *cd, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int d_type) +nfs3svc_encode_entry_plus(void *cd, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { return encode_entry(cd, name, namlen, offset, ino, d_type, 1); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fea46368afb2..18aa9440df14 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1880,9 +1880,10 @@ nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr) } static int -nfsd4_encode_dirent(struct readdir_cd *ccd, const char *name, int namlen, - loff_t offset, ino_t ino, unsigned int d_type) +nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { + struct readdir_cd *ccd = ccdv; struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common); int buflen; __be32 *p = cd->buffer; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 0aaccb03bf76..fbf5d51947ea 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -72,7 +72,7 @@ static struct svc_program nfsd_acl_program = { .pg_prog = NFS_ACL_PROGRAM, .pg_nvers = NFSD_ACL_NRVERS, .pg_vers = nfsd_acl_versions, - .pg_name = "nfsd", + .pg_name = "nfsacl", .pg_class = "nfsd", .pg_stats = &nfsd_acl_svcstats, .pg_authenticate = &svc_set_client, @@ -118,16 +118,16 @@ int nfsd_vers(int vers, enum vers_op change) switch(change) { case NFSD_SET: nfsd_versions[vers] = nfsd_version[vers]; - break; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) if (vers < NFSD_ACL_NRVERS) - nfsd_acl_version[vers] = nfsd_acl_version[vers]; + nfsd_acl_versions[vers] = nfsd_acl_version[vers]; #endif + break; case NFSD_CLEAR: nfsd_versions[vers] = NULL; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) if (vers < NFSD_ACL_NRVERS) - nfsd_acl_version[vers] = NULL; + nfsd_acl_versions[vers] = NULL; #endif break; case NFSD_TEST: diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index f5243f943996..6555c50d9006 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -462,9 +462,10 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_entry(struct readdir_cd *ccd, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int d_type) +nfssvc_encode_entry(void *ccdv, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int d_type) { + struct readdir_cd *ccd = ccdv; struct nfsd_readdirres *cd = container_of(ccd, struct nfsd_readdirres, common); __be32 *p = cd->buffer; int buflen, slen; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7a79c23aa6d4..5d32e5fa697e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -822,7 +822,8 @@ nfsd_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset rqstp->rq_res.page_len = size; } else if (page != pp[-1]) { get_page(page); - put_page(*pp); + if (*pp) + put_page(*pp); *pp = page; rqstp->rq_resused++; rqstp->rq_res.page_len += size; @@ -1244,7 +1245,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 err; int host_err; __u32 v_mtime=0, v_atime=0; - int v_mode=0; err = nfserr_perm; if (!flen) @@ -1281,16 +1281,11 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; if (createmode == NFS3_CREATE_EXCLUSIVE) { - /* while the verifier would fit in mtime+atime, - * solaris7 gets confused (bugid 4218508) if these have - * the high bit set, so we use the mode as well + /* solaris7 gets confused (bugid 4218508) if these have + * the high bit set, so just clear the high bits. */ v_mtime = verifier[0]&0x7fffffff; v_atime = verifier[1]&0x7fffffff; - v_mode = S_IFREG - | ((verifier[0]&0x80000000) >> (32-7)) /* u+x */ - | ((verifier[1]&0x80000000) >> (32-9)) /* u+r */ - ; } if (dchild->d_inode) { @@ -1318,7 +1313,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, case NFS3_CREATE_EXCLUSIVE: if ( dchild->d_inode->i_mtime.tv_sec == v_mtime && dchild->d_inode->i_atime.tv_sec == v_atime - && dchild->d_inode->i_mode == v_mode && dchild->d_inode->i_size == 0 ) break; /* fallthru */ @@ -1340,26 +1334,22 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, } if (createmode == NFS3_CREATE_EXCLUSIVE) { - /* Cram the verifier into atime/mtime/mode */ + /* Cram the verifier into atime/mtime */ iap->ia_valid = ATTR_MTIME|ATTR_ATIME - | ATTR_MTIME_SET|ATTR_ATIME_SET - | ATTR_MODE; + | ATTR_MTIME_SET|ATTR_ATIME_SET; /* XXX someone who knows this better please fix it for nsec */ iap->ia_mtime.tv_sec = v_mtime; iap->ia_atime.tv_sec = v_atime; iap->ia_mtime.tv_nsec = 0; iap->ia_atime.tv_nsec = 0; - iap->ia_mode = v_mode; } /* Set file attributes. - * Mode has already been set but we might need to reset it - * for CREATE_EXCLUSIVE * Irix appears to send along the gid when it tries to * implement setgid directories via NFS. Clear out all that cruft. */ set_attr: - if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID)) != 0) { + if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) { __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); if (err2) err = err2; @@ -1726,7 +1716,7 @@ out: */ __be32 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, - struct readdir_cd *cdp, encode_dent_fn func) + struct readdir_cd *cdp, filldir_t func) { __be32 err; int host_err; @@ -1751,7 +1741,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, do { cdp->err = nfserr_eof; /* will be cleared on successful read */ - host_err = vfs_readdir(file, (filldir_t) func, cdp); + host_err = vfs_readdir(file, func, cdp); } while (host_err >=0 && cdp->err == nfs_ok); if (host_err) err = nfserrno(host_err); diff --git a/fs/proc/base.c b/fs/proc/base.c index 77a57b5799c4..ff7a66850602 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -371,9 +371,11 @@ static int mounts_open(struct inode *inode, struct file *file) if (task) { task_lock(task); - ns = task->nsproxy->mnt_ns; - if (ns) - get_mnt_ns(ns); + if (task->nsproxy) { + ns = task->nsproxy->mnt_ns; + if (ns) + get_mnt_ns(ns); + } task_unlock(task); put_task_struct(task); } diff --git a/include/asm-generic/libata-portmap.h b/include/asm-generic/libata-portmap.h index 9202fd02d5be..62fb3618293d 100644 --- a/include/asm-generic/libata-portmap.h +++ b/include/asm-generic/libata-portmap.h @@ -3,10 +3,10 @@ #define ATA_PRIMARY_CMD 0x1F0 #define ATA_PRIMARY_CTL 0x3F6 -#define ATA_PRIMARY_IRQ 14 +#define ATA_PRIMARY_IRQ(dev) 14 #define ATA_SECONDARY_CMD 0x170 #define ATA_SECONDARY_CTL 0x376 -#define ATA_SECONDARY_IRQ 15 +#define ATA_SECONDARY_IRQ(dev) 15 #endif diff --git a/include/asm-i386/elf.h b/include/asm-i386/elf.h index 45d21a0c95bf..369035dfe4b6 100644 --- a/include/asm-i386/elf.h +++ b/include/asm-i386/elf.h @@ -143,11 +143,8 @@ extern int dump_task_extended_fpu (struct task_struct *, struct user_fxsr_struct # define VDSO_PRELINK 0 #endif -#define VDSO_COMPAT_SYM(x) \ - (VDSO_COMPAT_BASE + (unsigned long)(x) - VDSO_PRELINK) - #define VDSO_SYM(x) \ - (VDSO_BASE + (unsigned long)(x) - VDSO_PRELINK) + (VDSO_COMPAT_BASE + (unsigned long)(x) - VDSO_PRELINK) #define VDSO_HIGH_EHDR ((const struct elfhdr *) VDSO_HIGH_BASE) #define VDSO_EHDR ((const struct elfhdr *) VDSO_COMPAT_BASE) @@ -156,10 +153,12 @@ extern void __kernel_vsyscall; #define VDSO_ENTRY VDSO_SYM(&__kernel_vsyscall) +#ifndef CONFIG_COMPAT_VDSO #define ARCH_HAS_SETUP_ADDITIONAL_PAGES struct linux_binprm; extern int arch_setup_additional_pages(struct linux_binprm *bprm, int executable_stack); +#endif extern unsigned int vdso_enabled; @@ -169,50 +168,6 @@ do if (vdso_enabled) { \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_COMPAT_BASE); \ } while (0) -/* - * These macros parameterize elf_core_dump in fs/binfmt_elf.c to write out - * extra segments containing the vsyscall DSO contents. Dumping its - * contents makes post-mortem fully interpretable later without matching up - * the same kernel and hardware config to see what PC values meant. - * Dumping its extra ELF program headers includes all the other information - * a debugger needs to easily find how the vsyscall DSO was being used. - */ -#define ELF_CORE_EXTRA_PHDRS (VDSO_HIGH_EHDR->e_phnum) -#define ELF_CORE_WRITE_EXTRA_PHDRS \ -do { \ - const struct elf_phdr *const vsyscall_phdrs = \ - (const struct elf_phdr *) (VDSO_HIGH_BASE \ - + VDSO_HIGH_EHDR->e_phoff); \ - int i; \ - Elf32_Off ofs = 0; \ - for (i = 0; i < VDSO_HIGH_EHDR->e_phnum; ++i) { \ - struct elf_phdr phdr = vsyscall_phdrs[i]; \ - if (phdr.p_type == PT_LOAD) { \ - BUG_ON(ofs != 0); \ - ofs = phdr.p_offset = offset; \ - phdr.p_memsz = PAGE_ALIGN(phdr.p_memsz); \ - phdr.p_filesz = phdr.p_memsz; \ - offset += phdr.p_filesz; \ - } \ - else \ - phdr.p_offset += ofs; \ - phdr.p_paddr = 0; /* match other core phdrs */ \ - DUMP_WRITE(&phdr, sizeof(phdr)); \ - } \ -} while (0) -#define ELF_CORE_WRITE_EXTRA_DATA \ -do { \ - const struct elf_phdr *const vsyscall_phdrs = \ - (const struct elf_phdr *) (VDSO_HIGH_BASE \ - + VDSO_HIGH_EHDR->e_phoff); \ - int i; \ - for (i = 0; i < VDSO_HIGH_EHDR->e_phnum; ++i) { \ - if (vsyscall_phdrs[i].p_type == PT_LOAD) \ - DUMP_WRITE((void *) vsyscall_phdrs[i].p_vaddr, \ - PAGE_ALIGN(vsyscall_phdrs[i].p_memsz)); \ - } \ -} while (0) - #endif #endif diff --git a/include/asm-i386/fixmap.h b/include/asm-i386/fixmap.h index 02428cb36621..3e9f610c35df 100644 --- a/include/asm-i386/fixmap.h +++ b/include/asm-i386/fixmap.h @@ -23,6 +23,8 @@ extern unsigned long __FIXADDR_TOP; #else #define __FIXADDR_TOP 0xfffff000 +#define FIXADDR_USER_START __fix_to_virt(FIX_VDSO) +#define FIXADDR_USER_END __fix_to_virt(FIX_VDSO - 1) #endif #ifndef __ASSEMBLY__ diff --git a/include/asm-i386/page.h b/include/asm-i386/page.h index fd3f64ace248..7b19f454761d 100644 --- a/include/asm-i386/page.h +++ b/include/asm-i386/page.h @@ -143,7 +143,9 @@ extern int page_is_ram(unsigned long pagenr); #include #include +#ifndef CONFIG_COMPAT_VDSO #define __HAVE_ARCH_GATE_AREA 1 +#endif #endif /* __KERNEL__ */ #endif /* _I386_PAGE_H */ diff --git a/include/asm-powerpc/libata-portmap.h b/include/asm-powerpc/libata-portmap.h new file mode 100644 index 000000000000..4d8518049f4d --- /dev/null +++ b/include/asm-powerpc/libata-portmap.h @@ -0,0 +1,12 @@ +#ifndef __ASM_POWERPC_LIBATA_PORTMAP_H +#define __ASM_POWERPC_LIBATA_PORTMAP_H + +#define ATA_PRIMARY_CMD 0x1F0 +#define ATA_PRIMARY_CTL 0x3F6 +#define ATA_PRIMARY_IRQ(dev) pci_get_legacy_ide_irq(dev, 0) + +#define ATA_SECONDARY_CMD 0x170 +#define ATA_SECONDARY_CTL 0x376 +#define ATA_SECONDARY_IRQ(dev) pci_get_legacy_ide_irq(dev, 1) + +#endif diff --git a/include/asm-x86_64/uaccess.h b/include/asm-x86_64/uaccess.h index d5dbc87274f8..c0eac519840b 100644 --- a/include/asm-x86_64/uaccess.h +++ b/include/asm-x86_64/uaccess.h @@ -157,7 +157,7 @@ do { \ case 1: __put_user_asm(x,ptr,retval,"b","b","iq",-EFAULT); break;\ case 2: __put_user_asm(x,ptr,retval,"w","w","ir",-EFAULT); break;\ case 4: __put_user_asm(x,ptr,retval,"l","k","ir",-EFAULT); break;\ - case 8: __put_user_asm(x,ptr,retval,"q","","ir",-EFAULT); break;\ + case 8: __put_user_asm(x,ptr,retval,"q","","Zr",-EFAULT); break;\ default: __put_user_bad(); \ } \ } while (0) diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 5d1eabcde5d5..638165f571da 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -31,9 +31,8 @@ static inline unsigned long hweight_long(unsigned long w) return sizeof(w) == 4 ? hweight32(w) : hweight64(w); } -/* +/** * rol32 - rotate a 32-bit value left - * * @word: value to rotate * @shift: bits to roll */ @@ -42,9 +41,8 @@ static inline __u32 rol32(__u32 word, unsigned int shift) return (word << shift) | (word >> (32 - shift)); } -/* +/** * ror32 - rotate a 32-bit value right - * * @word: value to rotate * @shift: bits to roll */ diff --git a/include/linux/kvm.h b/include/linux/kvm.h index bc8b4616bad7..1be148f0fce4 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -46,6 +46,7 @@ enum kvm_exit_reason { KVM_EXIT_HLT = 5, KVM_EXIT_MMIO = 6, KVM_EXIT_IRQ_WINDOW_OPEN = 7, + KVM_EXIT_SHUTDOWN = 8, }; /* for KVM_RUN */ diff --git a/include/linux/libata.h b/include/linux/libata.h index f7f268e38749..22aa69e20905 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -177,6 +177,7 @@ enum { * Register FIS clearing BSY */ ATA_FLAG_DEBUGMSG = (1 << 13), ATA_FLAG_SETXFER_POLLING= (1 << 14), /* use polling for SETXFER */ + ATA_FLAG_IGN_SIMPLEX = (1 << 15), /* ignore SIMPLEX */ /* The following flag belongs to ap->pflags but is kept in * ap->flags because it's referenced in many LLDs and will be @@ -612,11 +613,11 @@ struct ata_port_operations { void (*dev_select)(struct ata_port *ap, unsigned int device); void (*phy_reset) (struct ata_port *ap); /* obsolete */ - void (*set_mode) (struct ata_port *ap); + int (*set_mode) (struct ata_port *ap, struct ata_device **r_failed_dev); void (*post_set_mode) (struct ata_port *ap); - int (*check_atapi_dma) (struct ata_queued_cmd *qc); + int (*check_atapi_dma) (struct ata_queued_cmd *qc); void (*bmdma_setup) (struct ata_queued_cmd *qc); void (*bmdma_start) (struct ata_queued_cmd *qc); diff --git a/include/linux/list.h b/include/linux/list.h index a9c90287c0ff..611059d633f4 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -227,13 +227,13 @@ static inline void list_replace_init(struct list_head *old, INIT_LIST_HEAD(old); } -/* +/** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * - * The old entry will be replaced with the new entry atomically. - * Note: 'old' should not be empty. + * The @old entry will be replaced with the @new entry atomically. + * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) @@ -680,12 +680,12 @@ static inline void hlist_del_init(struct hlist_node *n) } } -/* +/** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * - * The old entry will be replaced with the new entry atomically. + * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) diff --git a/include/linux/mm.h b/include/linux/mm.h index 76912231af41..2d2c08d5f473 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -168,6 +168,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ +#define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS diff --git a/include/linux/mutex.h b/include/linux/mutex.h index a7544afd7582..b81bc2adaeff 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -105,7 +105,7 @@ do { \ extern void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); -/*** +/** * mutex_is_locked - is the mutex locked * @lock: the mutex to be queried * diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h index 0727774772ba..4b7c4b568f6d 100644 --- a/include/linux/nfsd/nfsd.h +++ b/include/linux/nfsd/nfsd.h @@ -52,8 +52,6 @@ struct readdir_cd { __be32 err; /* 0, nfserr, or nfserr_eof */ }; -typedef int (*encode_dent_fn)(struct readdir_cd *, const char *, - int, loff_t, ino_t, unsigned int); typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int); extern struct svc_program nfsd_program; @@ -117,7 +115,7 @@ __be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type, int nfsd_truncate(struct svc_rqst *, struct svc_fh *, unsigned long size); __be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *, - loff_t *, struct readdir_cd *, encode_dent_fn); + loff_t *, struct readdir_cd *, filldir_t); __be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *, struct kstatfs *); diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index f3b51d62ec7d..d9c6c382165d 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -217,11 +217,7 @@ void fh_put(struct svc_fh *); static __inline__ struct svc_fh * fh_copy(struct svc_fh *dst, struct svc_fh *src) { - if (src->fh_dentry || src->fh_locked) { - struct dentry *dentry = src->fh_dentry; - printk(KERN_ERR "fh_copy: copying %s/%s, already verified!\n", - dentry->d_parent->d_name.name, dentry->d_name.name); - } + WARN_ON(src->fh_dentry || src->fh_locked); *dst = *src; return dst; @@ -300,10 +296,8 @@ fh_lock_nested(struct svc_fh *fhp, unsigned int subclass) dfprintk(FILEOP, "nfsd: fh_lock(%s) locked = %d\n", SVCFH_fmt(fhp), fhp->fh_locked); - if (!fhp->fh_dentry) { - printk(KERN_ERR "fh_lock: fh not verified!\n"); - return; - } + BUG_ON(!dentry); + if (fhp->fh_locked) { printk(KERN_WARNING "fh_lock: %s/%s already locked!\n", dentry->d_parent->d_name.name, dentry->d_name.name); @@ -328,8 +322,7 @@ fh_lock(struct svc_fh *fhp) static inline void fh_unlock(struct svc_fh *fhp) { - if (!fhp->fh_dentry) - printk(KERN_ERR "fh_unlock: fh not verified!\n"); + BUG_ON(!fhp->fh_dentry); if (fhp->fh_locked) { fill_post_wcc(fhp); diff --git a/include/linux/nfsd/xdr.h b/include/linux/nfsd/xdr.h index 877192d3ae79..67885d5e6e50 100644 --- a/include/linux/nfsd/xdr.h +++ b/include/linux/nfsd/xdr.h @@ -165,8 +165,8 @@ int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); -int nfssvc_encode_entry(struct readdir_cd *, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int); +int nfssvc_encode_entry(void *, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int); int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); diff --git a/include/linux/nfsd/xdr3.h b/include/linux/nfsd/xdr3.h index 79963867b0d7..89d9d6061a62 100644 --- a/include/linux/nfsd/xdr3.h +++ b/include/linux/nfsd/xdr3.h @@ -331,11 +331,11 @@ int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd3_attrstat *); int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, struct nfsd3_fhandle_pair *); -int nfs3svc_encode_entry(struct readdir_cd *, const char *name, - int namlen, loff_t offset, ino_t ino, +int nfs3svc_encode_entry(void *, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int); -int nfs3svc_encode_entry_plus(struct readdir_cd *, const char *name, - int namlen, loff_t offset, ino_t ino, +int nfs3svc_encode_entry_plus(void *, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int); /* Helper functions for NFSv3 ACL code */ __be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h index 866a1e2b0ce0..fbaeda79b2e9 100644 --- a/include/linux/raid/md.h +++ b/include/linux/raid/md.h @@ -94,7 +94,7 @@ extern int sync_page_io(struct block_device *bdev, sector_t sector, int size, struct page *page, int rw); extern void md_do_sync(mddev_t *mddev); extern void md_new_event(mddev_t *mddev); - +extern void md_allow_write(mddev_t *mddev); #endif /* CONFIG_MD */ #endif diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index b0090e9f7884..382bb7951166 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -16,7 +16,7 @@ #include #include -/* +/** * The rt_mutex structure * * @wait_lock: spinlock to protect the structure @@ -71,7 +71,7 @@ struct hrtimer_sleeper; #define DEFINE_RT_MUTEX(mutexname) \ struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) -/*** +/** * rt_mutex_is_locked - is the mutex locked * @lock: the mutex to be queried * diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 965d6c20086e..64f3d60c72af 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -144,8 +144,11 @@ extern u32 svc_max_payload(const struct svc_rqst *rqstp); * * Each request/reply pair can have at most one "payload", plus two pages, * one for the request, and one for the reply. + * We using ->sendfile to return read data, we might need one extra page + * if the request is not page-aligned. So add another '1'. */ -#define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE + 2) +#define RPCSVC_MAXPAGES ((RPCSVC_MAXPAYLOAD+PAGE_SIZE-1)/PAGE_SIZE \ + + 2 + 1) static inline u32 svc_getnl(struct kvec *iov) { diff --git a/include/linux/timer.h b/include/linux/timer.h index eeef6643d4c6..fb5edaaf0ebd 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -41,7 +41,7 @@ static inline void setup_timer(struct timer_list * timer, init_timer(timer); } -/*** +/** * timer_pending - is a timer pending? * @timer: the timer in question * @@ -63,7 +63,7 @@ extern int mod_timer(struct timer_list *timer, unsigned long expires); extern unsigned long next_timer_interrupt(void); -/*** +/** * add_timer - start a timer * @timer: the timer to be added * diff --git a/mm/memory.c b/mm/memory.c index af227d26e104..ef09f0acb1d8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2606,8 +2606,15 @@ static int __init gate_vma_init(void) gate_vma.vm_mm = NULL; gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; - gate_vma.vm_page_prot = PAGE_READONLY; - gate_vma.vm_flags = 0; + gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + gate_vma.vm_page_prot = __P101; + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + gate_vma.vm_flags |= VM_ALWAYSDUMP; return 0; } __initcall(gate_vma_init); diff --git a/mm/truncate.c b/mm/truncate.c index 6c79ca4a1ca7..5df947de7654 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -51,15 +51,22 @@ static inline void truncate_partial_page(struct page *page, unsigned partial) do_invalidatepage(page, partial); } +/* + * This cancels just the dirty bit on the kernel page itself, it + * does NOT actually remove dirty bits on any mmap's that may be + * around. It also leaves the page tagged dirty, so any sync + * activity will still find it on the dirty lists, and in particular, + * clear_page_dirty_for_io() will still look at the dirty bits in + * the VM. + * + * Doing this should *normally* only ever be done when a page + * is truncated, and is not actually mapped anywhere at all. However, + * fs/buffer.c does this when it notices that somebody has cleaned + * out all the buffers on a page without actually doing it through + * the VM. Can you say "ext3 is horribly ugly"? Tought you could. + */ void cancel_dirty_page(struct page *page, unsigned int account_size) { - /* If we're cancelling the page, it had better not be mapped any more */ - if (page_mapped(page)) { - static unsigned int warncount; - - WARN_ON(++warncount < 5); - } - if (TestClearPageDirty(page)) { struct address_space *mapping = page->mapping; if (mapping && mapping_cap_account_dirty(mapping)) { @@ -422,7 +429,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_release(&pvec); cond_resched(); } - WARN_ON_ONCE(ret); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index f3001f3626f6..bf21a2047010 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -910,7 +910,8 @@ err_bad_prog: err_bad_vers: #ifdef RPC_PARANOIA - printk("svc: unknown version (%d)\n", vers); + printk("svc: unknown version (%d for prog %d, %s)\n", + vers, prog, progp->pg_name); #endif serv->sv_stats->rpcbadfmt++; svc_putnl(resv, RPC_PROG_MISMATCH); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 99f54fb6d669..45120f268d03 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1278,6 +1278,8 @@ svc_recv(struct svc_rqst *rqstp, long timeout) schedule_timeout_uninterruptible(msecs_to_jiffies(500)); rqstp->rq_pages[i] = p; } + rqstp->rq_pages[i++] = NULL; /* this might be seen in nfs_read_actor */ + BUG_ON(pages >= RPCSVC_MAXPAGES); /* Make arg->head point to first page and arg->pages point to rest */ arg = &rqstp->rq_arg;