diff options
155 files changed, 2322 insertions, 1659 deletions
diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl index 5bcbb6e..f869b03 100644 --- a/Documentation/DocBook/libata.tmpl +++ b/Documentation/DocBook/libata.tmpl @@ -705,7 +705,7 @@ and other resources, etc. <sect1><title>ata_scsi_error()</title> <para> - ata_scsi_error() is the current hostt->eh_strategy_handler() + ata_scsi_error() is the current transportt->eh_strategy_handler() for libata. As discussed above, this will be entered in two cases - timeout and ATAPI error completion. This function calls low level libata driver's eng_timeout() callback, the diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt index 331afd7..ce767b9 100644 --- a/Documentation/scsi/scsi_eh.txt +++ b/Documentation/scsi/scsi_eh.txt @@ -19,9 +19,9 @@ TABLE OF CONTENTS [2-1-1] Overview [2-1-2] Flow of scmds through EH [2-1-3] Flow of control - [2-2] EH through hostt->eh_strategy_handler() - [2-2-1] Pre hostt->eh_strategy_handler() SCSI midlayer conditions - [2-2-2] Post hostt->eh_strategy_handler() SCSI midlayer conditions + [2-2] EH through transportt->eh_strategy_handler() + [2-2-1] Pre transportt->eh_strategy_handler() SCSI midlayer conditions + [2-2-2] Post transportt->eh_strategy_handler() SCSI midlayer conditions [2-2-3] Things to consider @@ -413,9 +413,9 @@ scmd->allowed. layer of failure of the scmds. -[2-2] EH through hostt->eh_strategy_handler() +[2-2] EH through transportt->eh_strategy_handler() - hostt->eh_strategy_handler() is invoked in the place of + transportt->eh_strategy_handler() is invoked in the place of scsi_unjam_host() and it is responsible for whole recovery process. On completion, the handler should have made lower layers forget about all failed scmds and either ready for new commands or offline. Also, @@ -424,7 +424,7 @@ SCSI midlayer. IOW, of the steps described in [2-1-2], all steps except for #1 must be implemented by eh_strategy_handler(). -[2-2-1] Pre hostt->eh_strategy_handler() SCSI midlayer conditions +[2-2-1] Pre transportt->eh_strategy_handler() SCSI midlayer conditions The following conditions are true on entry to the handler. @@ -437,7 +437,7 @@ except for #1 must be implemented by eh_strategy_handler(). - shost->host_failed == shost->host_busy -[2-2-2] Post hostt->eh_strategy_handler() SCSI midlayer conditions +[2-2-2] Post transportt->eh_strategy_handler() SCSI midlayer conditions The following conditions must be true on exit from the handler. diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt index 8bbae3e..75a535a 100644 --- a/Documentation/scsi/scsi_mid_low_api.txt +++ b/Documentation/scsi/scsi_mid_low_api.txt @@ -804,7 +804,6 @@ Summary: eh_bus_reset_handler - issue SCSI bus reset eh_device_reset_handler - issue SCSI device reset eh_host_reset_handler - reset host (host bus adapter) - eh_strategy_handler - driver supplied alternate to scsi_unjam_host() info - supply information about given host ioctl - driver can respond to ioctls proc_info - supports /proc/scsi/{driver_name}/{host_no} @@ -970,24 +969,6 @@ Details: /** - * eh_strategy_handler - driver supplied alternate to scsi_unjam_host() - * @shp: host on which error has occurred - * - * Returns TRUE if host unjammed, else FALSE. - * - * Locks: none - * - * Calling context: kernel thread - * - * Notes: Invoked from scsi_eh thread. LLD supplied alternate to - * scsi_unjam_host() found in scsi_error.c - * - * Optionally defined in: LLD - **/ - int eh_strategy_handler(struct Scsi_Host * shp) - - -/** * info - supply information about given host: driver name plus data * to distinguish given host * @shp: host to supply information about diff --git a/Documentation/x86_64/boot-options.txt b/Documentation/x86_64/boot-options.txt index 1921353..f2cd6ef 100644 --- a/Documentation/x86_64/boot-options.txt +++ b/Documentation/x86_64/boot-options.txt @@ -151,6 +151,11 @@ NUMA numa=fake=X Fake X nodes and ignore NUMA setup of the actual machine. + numa=hotadd=percent + Only allow hotadd memory to preallocate page structures upto + percent of already available memory. + numa=hotadd=0 will disable hotadd memory. + ACPI acpi=off Don't enable ACPI diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 0330661..8dab352 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -215,7 +215,7 @@ static int __init acpi_parse_madt(unsigned long phys_addr, unsigned long size) { struct acpi_table_madt *madt = NULL; - if (!phys_addr || !size) + if (!phys_addr || !size || !cpu_has_apic) return -EINVAL; madt = (struct acpi_table_madt *)__acpi_map_table(phys_addr, size); @@ -751,6 +751,9 @@ static int __init acpi_parse_madt_ioapic_entries(void) return -ENODEV; } + if (!cpu_has_apic) + return -ENODEV; + /* * if "noapic" boot option, don't look for IO-APICs */ diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c index 6273bf7..254cee9 100644 --- a/arch/i386/kernel/apic.c +++ b/arch/i386/kernel/apic.c @@ -62,6 +62,18 @@ int apic_verbosity; static void apic_pm_activate(void); +int modern_apic(void) +{ + unsigned int lvr, version; + /* AMD systems use old APIC versions, so check the CPU */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + boot_cpu_data.x86 >= 0xf) + return 1; + lvr = apic_read(APIC_LVR); + version = GET_APIC_VERSION(lvr); + return version >= 0x14; +} + /* * 'what should we do if we get a hw irq event on an illegal vector'. * each architecture has to answer this themselves. @@ -119,10 +131,7 @@ void enable_NMI_through_LVT0 (void * dummy) int get_physical_broadcast(void) { - unsigned int lvr, version; - lvr = apic_read(APIC_LVR); - version = GET_APIC_VERSION(lvr); - if (!APIC_INTEGRATED(version) || version >= 0x14) + if (modern_apic()) return 0xff; else return 0xf; @@ -349,9 +358,9 @@ int __init verify_local_APIC(void) void __init sync_Arb_IDs(void) { - /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */ - unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); - if (ver >= 0x14) /* P4 or higher */ + /* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 + And not needed on AMD */ + if (modern_apic()) return; /* * Wait for idle. diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index 712a26b..7c0e160 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -46,7 +46,7 @@ #define PFX "powernow-k8: " #define BFX PFX "BIOS error: " -#define VERSION "version 1.60.1" +#define VERSION "version 1.60.2" #include "powernow-k8.h" /* serialize freq changes */ @@ -55,7 +55,7 @@ static DEFINE_MUTEX(fidvid_mutex); static struct powernow_k8_data *powernow_data[NR_CPUS]; #ifndef CONFIG_SMP -static cpumask_t cpu_core_map[1] = { CPU_MASK_ALL }; +static cpumask_t cpu_core_map[1]; #endif /* Return a frequency in MHz, given an input fid */ @@ -910,6 +910,9 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi unsigned int newstate; int ret = -EIO; + if (!data) + return -EINVAL; + /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; set_cpus_allowed(current, cpumask_of_cpu(pol->cpu)); @@ -969,6 +972,9 @@ static int powernowk8_verify(struct cpufreq_policy *pol) { struct powernow_k8_data *data = powernow_data[pol->cpu]; + if (!data) + return -EINVAL; + return cpufreq_frequency_table_verify(pol, data->powernow_table); } @@ -977,7 +983,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; cpumask_t oldmask = CPU_MASK_ALL; - int rc, i; + int rc; if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1063,8 +1069,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) printk("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); - for_each_cpu_mask(i, cpu_core_map[pol->cpu]) - powernow_data[i] = data; + powernow_data[pol->cpu] = data; return 0; @@ -1104,6 +1109,9 @@ static unsigned int powernowk8_get (unsigned int cpu) if (!data) return -EINVAL; + if (!data) + return -EINVAL; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) { printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu); diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c index 8d8aa9d..db12017 100644 --- a/arch/i386/kernel/mpparse.c +++ b/arch/i386/kernel/mpparse.c @@ -110,21 +110,6 @@ static int __init mpf_checksum(unsigned char *mp, int len) static int mpc_record; static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] __initdata; -#ifdef CONFIG_X86_NUMAQ -static int MP_valid_apicid(int apicid, int version) -{ - return hweight_long(apicid & 0xf) == 1 && (apicid >> 4) != 0xf; -} -#else -static int MP_valid_apicid(int apicid, int version) -{ - if (version >= 0x14) - return apicid < 0xff; - else - return apicid < 0xf; -} -#endif - static void __devinit MP_processor_info (struct mpc_config_processor *m) { int ver, apicid; @@ -190,12 +175,6 @@ static void __devinit MP_processor_info (struct mpc_config_processor *m) ver = m->mpc_apicver; - if (!MP_valid_apicid(apicid, ver)) { - printk(KERN_WARNING "Processor #%d INVALID. (Max ID: %d).\n", - m->mpc_apicid, MAX_APICS); - return; - } - /* * Validate version */ diff --git a/arch/i386/kernel/reboot_fixups.c b/arch/i386/kernel/reboot_fixups.c index 10e21a4..99aab41 100644 --- a/arch/i386/kernel/reboot_fixups.c +++ b/arch/i386/kernel/reboot_fixups.c @@ -51,7 +51,5 @@ void mach_reboot_fixups(void) cur->reboot_fixup(dev); } - - printk(KERN_WARNING "No reboot fixup found for your hardware\n"); } diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index eacc3f0..80cb3b2 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -963,6 +963,36 @@ efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg) return 0; } + /* + * This function checks if the entire range <start,end> is mapped with type. + * + * Note: this function only works correct if the e820 table is sorted and + * not-overlapping, which is the case + */ +int __init +e820_all_mapped(unsigned long start, unsigned long end, unsigned type) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + if (type && ei->type != type) + continue; + /* is the region (part) in overlap with the current region ?*/ + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + /* if the region is at the beginning of <start,end> we move + * start to the end of the region since it's ok until there + */ + if (ei->addr <= start) + start = ei->addr + ei->size; + /* if start is now at or beyond end, we're done, full + * coverage */ + if (start >= end) + return 1; /* we're done */ + } + return 0; +} + /* * Find the highest page frame number we have available */ @@ -1317,8 +1347,8 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat /* * Request address space for all standard resources * - * This is called just before pcibios_assign_resources(), which is also - * an fs_initcall, but is linked in later (in arch/i386/pci/i386.c). + * This is called just before pcibios_init(), which is also a + * subsys_initcall, but is linked in later (in arch/i386/pci/common.c). */ static int __init request_standard_resources(void) { @@ -1339,7 +1369,7 @@ static int __init request_standard_resources(void) return 0; } -fs_initcall(request_standard_resources); +subsys_initcall(request_standard_resources); static void __init register_memory(void) { diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c index 9f66ac5..ae6534a 100644 --- a/arch/i386/mm/init.c +++ b/arch/i386/mm/init.c @@ -651,6 +651,7 @@ void __init mem_init(void) * Specifically, in the case of x86, we will always add * memory to the highmem for now. */ +#ifdef CONFIG_HOTPLUG_MEMORY #ifndef CONFIG_NEED_MULTIPLE_NODES int add_memory(u64 start, u64 size) { @@ -667,6 +668,7 @@ int remove_memory(u64 start, u64 size) return -EINVAL; } #endif +#endif kmem_cache_t *pgd_cache; kmem_cache_t *pmd_cache; diff --git a/arch/i386/pci/direct.c b/arch/i386/pci/direct.c index 99012b9..0659ced 100644 --- a/arch/i386/pci/direct.c +++ b/arch/i386/pci/direct.c @@ -4,6 +4,7 @@ #include <linux/pci.h> #include <linux/init.h> +#include <linux/dmi.h> #include "pci.h" /* @@ -18,8 +19,10 @@ int pci_conf1_read(unsigned int seg, unsigned int bus, { unsigned long flags; - if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) + if (!value || (bus > 255) || (devfn > 255) || (reg > 255)) { + *value = -1; return -EINVAL; + } spin_lock_irqsave(&pci_config_lock, flags); @@ -188,6 +191,10 @@ static int __init pci_sanity_check(struct pci_raw_ops *o) if (pci_probe & PCI_NO_CHECKS) return 1; + /* Assume Type 1 works for newer systems. + This handles machines that don't have anything on PCI Bus 0. */ + if (dmi_get_year(DMI_BIOS_DATE) >= 2001) + return 1; for (devfn = 0; devfn < 0x100; devfn++) { if (o->read(0, 0, devfn, PCI_CLASS_DEVICE, 2, &x)) diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index 6137890..f77d7f8 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -12,14 +12,20 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/acpi.h> +#include <asm/e820.h> #include "pci.h" +#define MMCONFIG_APER_SIZE (256*1024*1024) + +/* Assume systems with more busses have correct MCFG */ +#define MAX_CHECK_BUS 16 + #define mmcfg_virt_addr ((void __iomem *) fix_to_virt(FIX_PCIE_MCFG)) /* The base address of the last MMCONFIG device accessed */ static u32 mmcfg_last_accessed_device; -static DECLARE_BITMAP(fallback_slots, 32); +static DECLARE_BITMAP(fallback_slots, MAX_CHECK_BUS*32); /* * Functions for accessing PCI configuration space with MMCONFIG accesses @@ -29,8 +35,8 @@ static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn) int cfg_num = -1; struct acpi_table_mcfg_config *cfg; - if (seg == 0 && bus == 0 && - test_bit(PCI_SLOT(devfn), fallback_slots)) + if (seg == 0 && bus < MAX_CHECK_BUS && + test_bit(PCI_SLOT(devfn) + 32*bus, fallback_slots)) return 0; while (1) { @@ -74,8 +80,10 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus, unsigned long flags; u32 base; - if (!value || (bus > 255) || (devfn > 255) || (reg > 4095)) + if (!value || (bus > 255) || (devfn > 255) || (reg > 4095)) { + *value = -1; return -EINVAL; + } base = get_base_addr(seg, bus, devfn); if (!base) @@ -146,29 +154,34 @@ static struct pci_raw_ops pci_mmcfg = { Normally this can be expressed in the MCFG by not listing them and assigning suitable _SEGs, but this isn't implemented in some BIOS. Instead try to discover all devices on bus 0 that are unreachable using MM - and fallback for them. - We only do this for bus 0/seg 0 */ + and fallback for them. */ static __init void unreachable_devices(void) { - int i; + int i, k; unsigned long flags; - for (i = 0; i < 32; i++) { - u32 val1; - u32 addr; - - pci_conf1_read(0, 0, PCI_DEVFN(i, 0), 0, 4, &val1); - if (val1 == 0xffffffff) - continue; - - /* Locking probably not needed, but safer */ - spin_lock_irqsave(&pci_config_lock, flags); - addr = get_base_addr(0, 0, PCI_DEVFN(i, 0)); - if (addr != 0) - pci_exp_set_dev_base(addr, 0, PCI_DEVFN(i, 0)); - if (addr == 0 || readl((u32 __iomem *)mmcfg_virt_addr) != val1) - set_bit(i, fallback_slots); - spin_unlock_irqrestore(&pci_config_lock, flags); + for (k = 0; k < MAX_CHECK_BUS; k++) { + for (i = 0; i < 32; i++) { + u32 val1; + u32 addr; + + pci_conf1_read(0, k, PCI_DEVFN(i, 0), 0, 4, &val1); + if (val1 == 0xffffffff) + continue; + + /* Locking probably not needed, but safer */ + spin_lock_irqsave(&pci_config_lock, flags); + addr = get_base_addr(0, k, PCI_DEVFN(i, 0)); + if (addr != 0) + pci_exp_set_dev_base(addr, k, PCI_DEVFN(i, 0)); + if (addr == 0 || + readl((u32 __iomem *)mmcfg_virt_addr) != val1) { + set_bit(i, fallback_slots); + printk(KERN_NOTICE + "PCI: No mmconfig possible on %x:%x\n", k, i); + } + spin_unlock_irqrestore(&pci_config_lock, flags); + } } } @@ -183,6 +196,14 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; + if (!e820_all_mapped(pci_mmcfg_config[0].base_address, + pci_mmcfg_config[0].base_address + MMCONFIG_APER_SIZE, + E820_RESERVED)) { + printk(KERN_ERR "PCI: BIOS Bug: MCFG area is not E820-reserved\n"); + printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); + return; + } + printk(KERN_INFO "PCI: Using MMCONFIG\n"); raw_pci_ops = &pci_mmcfg; pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig index d1e2fc5..648047a 100644 --- a/arch/sparc64/Kconfig +++ b/arch/sparc64/Kconfig @@ -194,6 +194,9 @@ endchoice endmenu +config ARCH_SELECT_MEMORY_MODEL + def_bool y + config ARCH_SPARSEMEM_ENABLE def_bool y diff --git a/arch/sparc64/defconfig b/arch/sparc64/defconfig index 3038908..1317380 100644 --- a/arch/sparc64/defconfig +++ b/arch/sparc64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit # Linux kernel version: 2.6.16 -# Fri Mar 31 01:40:57 2006 +# Sun Apr 2 19:31:04 2006 # CONFIG_SPARC=y CONFIG_SPARC64=y @@ -838,7 +838,6 @@ CONFIG_FB_TILEBLITTING=y # CONFIG_FB_NVIDIA is not set # CONFIG_FB_RIVA is not set # CONFIG_FB_MATROX is not set -# CONFIG_FB_RADEON_OLD is not set CONFIG_FB_RADEON=y CONFIG_FB_RADEON_I2C=y # CONFIG_FB_RADEON_DEBUG is not set @@ -924,6 +923,7 @@ CONFIG_SND_MTPAV=m # PCI devices # # CONFIG_SND_AD1889 is not set +# CONFIG_SND_ALS300 is not set CONFIG_SND_ALI5451=m # CONFIG_SND_ATIIXP is not set # CONFIG_SND_ATIIXP_MODEM is not set @@ -955,6 +955,7 @@ CONFIG_SND_ALI5451=m # CONFIG_SND_MIXART is not set # CONFIG_SND_NM256 is not set # CONFIG_SND_PCXHR is not set +# CONFIG_SND_RIPTIDE is not set # CONFIG_SND_RME32 is not set # CONFIG_SND_RME96 is not set # CONFIG_SND_RME9652 is not set @@ -1109,6 +1110,11 @@ CONFIG_USB_HIDDEV=y # CONFIG_MMC is not set # +# LED devices +# +# CONFIG_NEW_LEDS is not set + +# # InfiniBand support # # CONFIG_INFINIBAND is not set diff --git a/arch/sparc64/kernel/ptrace.c b/arch/sparc64/kernel/ptrace.c index eb93e9c..49e6ded 100644 --- a/arch/sparc64/kernel/ptrace.c +++ b/arch/sparc64/kernel/ptrace.c @@ -244,6 +244,13 @@ asmlinkage void do_ptrace(struct pt_regs *regs) } switch(request) { + case PTRACE_PEEKUSR: + if (addr != 0) + pt_error_return(regs, EIO); + else + pt_succ_return(regs, 0); + goto out_tsk; + case PTRACE_PEEKTEXT: /* read word at location addr. */ case PTRACE_PEEKDATA: { unsigned long tmp64; @@ -602,6 +609,22 @@ asmlinkage void do_ptrace(struct pt_regs *regs) /* PTRACE_DUMPCORE unsupported... */ + case PTRACE_GETEVENTMSG: { + int err; + + if (test_thread_flag(TIF_32BIT)) + err = put_user(child->ptrace_message, + (unsigned int __user *) data); + else + err = put_user(child->ptrace_message, + (unsigned long __user *) data); + if (err) + pt_error_return(regs, -err); + else + pt_succ_return(regs, 0); + break; + } + default: { int err = ptrace_request(child, request, addr, data); if (err) diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c index 8175a69..eb36f79 100644 --- a/arch/sparc64/kernel/smp.c +++ b/arch/sparc64/kernel/smp.c @@ -745,12 +745,21 @@ struct call_data_struct { int wait; }; -static DEFINE_SPINLOCK(call_lock); +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(call_lock); static struct call_data_struct *call_data; extern unsigned long xcall_call_function; -/* +/** + * smp_call_function(): Run a function on all other CPUs. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @nonatomic: currently unused. + * @wait: If true, wait (atomically) until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. Does not return until + * remote CPUs are nearly ready to execute <<func>> or are or have executed. + * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ @@ -759,7 +768,6 @@ static int smp_call_function_mask(void (*func)(void *info), void *info, { struct call_data_struct data; int cpus; - long timeout; /* Can deadlock when called with interrupts disabled */ WARN_ON(irqs_disabled()); @@ -777,31 +785,18 @@ static int smp_call_function_mask(void (*func)(void *info), void *info, goto out_unlock; call_data = &data; + mb(); smp_cross_call_masked(&xcall_call_function, 0, 0, 0, mask); - /* - * Wait for other cpus to complete function or at - * least snap the call data. - */ - timeout = 1000000; - while (atomic_read(&data.finished) != cpus) { - if (--timeout <= 0) - goto out_timeout; - barrier(); - udelay(1); - } + /* Wait for response */ + while (atomic_read(&data.finished) != cpus) + cpu_relax(); out_unlock: spin_unlock(&call_lock); return 0; - -out_timeout: - spin_unlock(&call_lock); - printk("XCALL: Remote cpus not responding, ncpus=%d finished=%d\n", - cpus, atomic_read(&data.finished)); - return 0; } int smp_call_function(void (*func)(void *info), void *info, diff --git a/arch/sparc64/kernel/traps.c b/arch/sparc64/kernel/traps.c index ff090bb..2793a5d 100644 --- a/arch/sparc64/kernel/traps.c +++ b/arch/sparc64/kernel/traps.c @@ -1130,9 +1130,9 @@ static void cheetah_log_errors(struct pt_regs *regs, struct cheetah_err_info *in (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(), afsr, afar, (afsr & CHAFSR_TL1) ? 1 : 0); - printk("%s" "ERROR(%d): TPC[%016lx] TNPC[%016lx] TSTATE[%016lx]\n", + printk("%s" "ERROR(%d): TPC[%lx] TNPC[%lx] O7[%lx] TSTATE[%lx]\n", (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(), - regs->tpc, regs->tnpc, regs->tstate); + regs->tpc, regs->tnpc, regs->u_regs[UREG_I7], regs->tstate); printk("%s" "ERROR(%d): M_SYND(%lx), E_SYND(%lx)%s%s\n", (recoverable ? KERN_WARNING : KERN_CRIT), smp_processor_id(), (afsr & CHAFSR_M_SYNDROME) >> CHAFSR_M_SYNDROME_SHIFT, diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 4310b4a..7df2fe1 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -136,6 +136,11 @@ config X86_L1_CACHE_SHIFT default "7" if GENERIC_CPU || MPSC default "6" if MK8 +config X86_INTERNODE_CACHE_BYTES + int + default "4096" if X86_VSMP + default X86_L1_CACHE_BYTES if !X86_VSMP + config X86_TSC bool default y diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile index 585fd4a..e573e2a 100644 --- a/arch/x86_64/Makefile +++ b/arch/x86_64/Makefile @@ -24,37 +24,37 @@ LDFLAGS := -m elf_x86_64 OBJCOPYFLAGS := -O binary -R .note -R .comment -S LDFLAGS_vmlinux := - CHECKFLAGS += -D__x86_64__ -m64 +cflags-y := cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) -CFLAGS += $(cflags-y) -CFLAGS += -m64 -CFLAGS += -mno-red-zone -CFLAGS += -mcmodel=kernel -CFLAGS += -pipe +cflags-y += -m64 +cflags-y += -mno-red-zone +cflags-y += -mcmodel=kernel +cflags-y += -pipe cflags-$(CONFIG_REORDER) += -ffunction-sections # this makes reading assembly source easier, but produces worse code # actually it makes the kernel smaller too. -CFLAGS += -fno-reorder-blocks -CFLAGS += -Wno-sign-compare +cflags-y += -fno-reorder-blocks +cflags-y += -Wno-sign-compare ifneq ($(CONFIG_UNWIND_INFO),y) -CFLAGS += -fno-asynchronous-unwind-tables +cflags-y += -fno-asynchronous-unwind-tables endif ifneq ($(CONFIG_DEBUG_INFO),y) # -fweb shrinks the kernel a bit, but the difference is very small # it also messes up debugging, so don't use it for now. -#CFLAGS += $(call cc-option,-fweb) +#cflags-y += $(call cc-option,-fweb) endif # -funit-at-a-time shrinks the kernel .text considerably # unfortunately it makes reading oopses harder. -CFLAGS += $(call cc-option,-funit-at-a-time) +cflags-y += $(call cc-option,-funit-at-a-time) # prevent gcc from generating any FP code by mistake -CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +cflags-y += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) +CFLAGS += $(cflags-y) AFLAGS += -m64 head-y := arch/x86_64/kernel/head.o arch/x86_64/kernel/head64.o arch/x86_64/kernel/init_task.o diff --git a/arch/x86_64/defconfig b/arch/x86_64/defconfig index 566ecc9..3c45ec2 100644 --- a/arch/x86_64/defconfig +++ b/arch/x86_64/defconfig @@ -1,7 +1,7 @@ # # Automatically generated make config: don't edit -# Linux kernel version: 2.6.16-git9 -# Sat Mar 25 15:18:40 2006 +# Linux kernel version: 2.6.17-rc1 +# Mon Apr 3 16:11:14 2006 # CONFIG_X86_64=y CONFIG_64BIT=y @@ -9,6 +9,7 @@ CONFIG_X86=y CONFIG_SEMAPHORE_SLEEPERS=y CONFIG_MMU=y CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_HWEIGHT=y CONFIG_GENERIC_CALIBRATE_DELAY=y CONFIG_X86_CMPXCHG=y CONFIG_EARLY_PRINTK=y @@ -55,10 +56,6 @@ CONFIG_BASE_FULL=y CONFIG_FUTEX=y CONFIG_EPOLL=y CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 CONFIG_SLAB=y # CONFIG_TINY_SHMEM is not set CONFIG_BASE_SMALL=0 @@ -70,7 +67,6 @@ CONFIG_BASE_SMALL=0 CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_OBSOLETE_MODPARM=y # CONFIG_MODVERSIONS is not set # CONFIG_MODULE_SRCVERSION_ALL is not set # CONFIG_KMOD is not set @@ -81,6 +77,7 @@ CONFIG_STOP_MACHINE=y # CONFIG_LBD=y # CONFIG_BLK_DEV_IO_TRACE is not set +# CONFIG_LSF is not set # # IO Schedulers @@ -105,6 +102,7 @@ CONFIG_X86_PC=y CONFIG_GENERIC_CPU=y CONFIG_X86_L1_CACHE_BYTES=128 CONFIG_X86_L1_CACHE_SHIFT=7 +CONFIG_X86_INTERNODE_CACHE_BYTES=128 CONFIG_X86_TSC=y CONFIG_X86_GOOD_APIC=y # CONFIG_MICROCODE is not set @@ -116,6 +114,7 @@ CONFIG_X86_LOCAL_APIC=y CONFIG_MTRR=y CONFIG_SMP=y CONFIG_SCHED_SMT=y +CONFIG_SCHED_MC=y # CONFIG_PREEMPT_NONE is not set CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_PREEMPT is not set @@ -138,6 +137,7 @@ CONFIG_NEED_MULTIPLE_NODES=y CONFIG_SPLIT_PTLOCK_CPUS=4 CONFIG_MIGRATION=y CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y +CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y CONFIG_NR_CPUS=32 CONFIG_HOTPLUG_CPU=y CONFIG_HPET_TIMER=y @@ -289,6 +289,7 @@ CONFIG_IP_PNP_DHCP=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set +# CONFIG_INET_XFRM_TUNNEL is not set # CONFIG_INET_TUNNEL is not set CONFIG_INET_DIAG=y CONFIG_INET_TCP_DIAG=y @@ -300,6 +301,7 @@ CONFIG_IPV6=y # CONFIG_INET6_AH is not set # CONFIG_INET6_ESP is not set # CONFIG_INET6_IPCOMP is not set +# CONFIG_INET6_XFRM_TUNNEL is not set # CONFIG_INET6_TUNNEL is not set # CONFIG_IPV6_TUNNEL is not set # CONFIG_NETFILTER is not set @@ -704,7 +706,6 @@ CONFIG_S2IO=m # Wireless LAN (non-hamradio) # # CONFIG_NET_RADIO is not set -# CONFIG_NET_WIRELESS_RTNETLINK is not set # # Wan interfaces @@ -791,7 +792,7 @@ CONFIG_HW_CONSOLE=y # CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -# CONFIG_SERIAL_8250_ACPI is not set +CONFIG_SERIAL_8250_PCI=y CONFIG_SERIAL_8250_NR_UARTS=4 CONFIG_SERIAL_8250_RUNTIME_UARTS=4 # CONFIG_SERIAL_8250_EXTENDED is not set @@ -921,6 +922,7 @@ CONFIG_HWMON=y # Digital Video Broadcasting Devices # # CONFIG_DVB is not set +# CONFIG_USB_DABUSB is not set # # Graphics support @@ -932,6 +934,8 @@ CONFIG_VIDEO_SELECT=y # Console display driver support # CONFIG_VGA_CONSOLE=y +CONFIG_VGACON_SOFT_SCROLLBACK=y +CONFIG_VGACON_SOFT_SCROLLBACK_SIZE=256 CONFIG_DUMMY_CONSOLE=y # @@ -1058,15 +1062,6 @@ CONFIG_USB_HIDINPUT=y # CONFIG_USB_MICROTEK is not set # -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set - -# -# Video4Linux support is needed for USB Multimedia device support -# - -# # USB Network Adapters # # CONFIG_USB_CATC is not set @@ -1118,9 +1113,15 @@ CONFIG_USB_MON=y # CONFIG_MMC is not set # +# LED devices +# +# CONFIG_NEW_LEDS is not set + +# # InfiniBand support # # CONFIG_INFINIBAND is not set +# CONFIG_IPATH_CORE is not set # # EDAC - error detection and reporting (RAS) (EXPERIMENTAL) @@ -1128,6 +1129,11 @@ CONFIG_USB_MON=y # CONFIG_EDAC is not set # +# Real Time Clock +# +# CONFIG_RTC_CLASS is not set + +# # Firmware Drivers # # CONFIG_EDD is not set diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 35b2fac..5a98026 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -15,6 +15,8 @@ #include <asm/vsyscall32.h> #include <linux/linkage.h> +#define IA32_NR_syscalls ((ia32_syscall_end - ia32_sys_call_table)/8) + .macro IA32_ARG_FIXUP noebp=0 movl %edi,%r8d .if \noebp @@ -109,8 +111,8 @@ ENTRY(ia32_sysenter_target) CFI_REMEMBER_STATE jnz sysenter_tracesys sysenter_do_call: - cmpl $(IA32_NR_syscalls),%eax - jae ia32_badsys + cmpl $(IA32_NR_syscalls-1),%eax + ja ia32_badsys IA32_ARG_FIXUP 1 call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) @@ -210,8 +212,8 @@ ENTRY(ia32_cstar_target) CFI_REMEMBER_STATE jnz cstar_tracesys cstar_do_call: - cmpl $IA32_NR_syscalls,%eax - jae ia32_badsys + cmpl $IA32_NR_syscalls-1,%eax + ja ia32_badsys IA32_ARG_FIXUP 1 call *ia32_sys_call_table(,%rax,8) movq %rax,RAX-ARGOFFSET(%rsp) @@ -296,8 +298,8 @@ ENTRY(ia32_syscall) testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) jnz ia32_tracesys ia32_do_syscall: - cmpl $(IA32_NR_syscalls),%eax - jae ia32_badsys + cmpl $(IA32_NR_syscalls-1),%eax + ja ia32_badsys IA32_ARG_FIXUP call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: @@ -685,12 +687,11 @@ ia32_sys_call_table: .quad sys_readlinkat /* 305 */ .quad sys_fchmodat .quad sys_faccessat - .quad sys_ni_syscall /* pselect6 for now */ - .quad sys_ni_syscall /* ppoll for now */ + .quad quiet_ni_syscall /* pselect6 for now */ + .quad quiet_ni_syscall /* ppoll for now */ .quad sys_unshare /* 310 */ .quad compat_sys_set_robust_list .quad compat_sys_get_robust_list + .quad sys_splice + .quad sys_sync_file_range ia32_syscall_end: - .rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8 - .quad ni_syscall - .endr diff --git a/arch/x86_64/kernel/aperture.c b/arch/x86_64/kernel/aperture.c index fffd6b0..70b9d21 100644 --- a/arch/x86_64/kernel/aperture.c +++ b/arch/x86_64/kernel/aperture.c @@ -80,7 +80,7 @@ static int __init aperture_valid(char *name, u64 aper_base, u32 aper_size) printk("Aperture from %s beyond 4GB. Ignoring.\n",name); return 0; } - if (e820_mapped(aper_base, aper_base + aper_size, E820_RAM)) { + if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { printk("Aperture from %s pointing to e820 RAM. Ignoring.\n",name); return 0; } diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c index 293cd71..62776c0 100644 --- a/arch/x86_64/kernel/e820.c +++ b/arch/x86_64/kernel/e820.c @@ -80,7 +80,12 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size) return 0; } -int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) +/* + * This function checks if any part of the range <start,end> is mapped + * with type. + */ +int __meminit +e820_any_mapped(unsigned long start, unsigned long end, unsigned type) { int i; for (i = 0; i < e820.nr_map; i++) { @@ -94,6 +99,35 @@ int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) return 0; } +/* + * This function checks if the entire range <start,end> is mapped with type. + * + * Note: this function only works correct if the e820 table is sorted and + * not-overlapping, which is the case + */ +int __init e820_all_mapped(unsigned long start, unsigned long end, unsigned type) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + if (type && ei->type != type) + continue; + /* is the region (part) in overlap with the current region ?*/ + if (ei->addr >= end || ei->addr + ei->size <= start) + continue; + + /* if the region is at the beginning of <start,end> we move + * start to the end of the region since it's ok until there + */ + if (ei->addr <= start) + start = ei->addr + ei->size; + /* if start is now at or beyond end, we're done, full coverage */ + if (start >= end) + return 1; /* we're done */ + } + return 0; +} + /* * Find a free area in a specific range. */ diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S index 8538bfe..c946e4f 100644 --- a/arch/x86_64/kernel/entry.S +++ b/arch/x86_64/kernel/entry.S @@ -180,6 +180,10 @@ rff_trace: * * XXX if we had a free scratch register we could save the RSP into the stack frame * and report it properly in ps. Unfortunately we haven't. + * + * When user can change the frames always force IRET. That is because + * it deals with uncanonical addresses better. SYSRET has trouble + * with them due to bugs in both AMD and Intel CPUs. */ ENTRY(system_call) @@ -254,7 +258,10 @@ sysret_signal: xorl %esi,%esi # oldset -> arg2 call ptregscall_common 1: movl $_TIF_NEED_RESCHED,%edi - jmp sysret_check + /* Use IRET because user could have changed frame. This + works because ptregscall_common has called FIXUP_TOP_OF_STACK. */ + cli + jmp int_with_check badsys: movq $-ENOSYS,RAX-ARGOFFSET(%rsp) @@ -280,7 +287,8 @@ tracesys: call syscall_trace_leave RESTORE_TOP_OF_STACK %rbx RESTORE_REST - jmp ret_from_sys_call + /* Use IRET because user could have changed frame */ + jmp int_ret_from_sys_call CFI_ENDPROC /* @@ -408,25 +416,9 @@ ENTRY(stub_execve) CFI_ADJUST_CFA_OFFSET -8 CFI_REGISTER rip, r11 SAVE_REST - movq %r11, %r15 - CFI_REGISTER rip, r15 FIXUP_TOP_OF_STACK %r11 call sys_execve - GET_THREAD_INFO(%rcx) - bt $TIF_IA32,threadinfo_flags(%rcx) - CFI_REMEMBER_STATE - jc exec_32bit RESTORE_TOP_OF_STACK %r11 - movq %r15, %r11 - CFI_REGISTER rip, r11 - RESTORE_REST - pushq %r11 - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET rip, 0 - ret - -exec_32bit: - CFI_RESTORE_STATE movq %rax,RAX(%rsp) RESTORE_REST jmp int_ret_from_sys_call diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c index 10b3e34..6f0790e 100644 --- a/arch/x86_64/kernel/mce.c +++ b/arch/x86_64/kernel/mce.c @@ -29,6 +29,8 @@ #define MISC_MCELOG_MINOR 227 #define NR_BANKS 6 +atomic_t mce_entry; + static int mce_dont_init; /* 0: always panic, 1: panic if deadlock possible, 2: try to avoid panic, @@ -172,10 +174,12 @@ void do_machine_check(struct pt_regs * regs, long error_code) int i; int panicm_found = 0; + atomic_inc(&mce_entry); + if (regs) notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL); if (!banks) - return; + goto out2; memset(&m, 0, sizeof(struct mce)); m.cpu = safe_smp_processor_id(); @@ -266,6 +270,8 @@ void do_machine_check(struct pt_regs * regs, long error_code) out: /* Last thing done in the machine check exception to clear state. */ wrmsrl(MSR_IA32_MCG_STATUS, 0); + out2: + atomic_dec(&mce_entry); } /* diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c index d9e4067..4e6357f 100644 --- a/arch/x86_64/kernel/nmi.c +++ b/arch/x86_64/kernel/nmi.c @@ -34,6 +34,7 @@ #include <asm/proto.h> #include <asm/kdebug.h> #include <asm/local.h> +#include <asm/mce.h> /* * lapic_nmi_owner tracks the ownership of the lapic NMI hardware: @@ -480,6 +481,12 @@ void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason) __get_cpu_var(nmi_touch) = 0; touched = 1; } +#ifdef CONFIG_X86_MCE + /* Could check oops_in_progress here too, but it's safer + not too */ + if (atomic_read(&mce_entry) > 0) + touched = 1; +#endif if (!touched && __get_cpu_var(last_irq_sum) == sum) { /* * Ayiee, looks like this CPU is stuck ... diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c index 03c9eee..af035ed 100644 --- a/arch/x86_64/kernel/pci-dma.c +++ b/arch/x86_64/kernel/pci-dma.c @@ -48,9 +48,11 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) { struct page *page; int node; +#ifdef CONFIG_PCI if (dev->bus == &pci_bus_type) node = pcibus_to_node(to_pci_dev(dev)->bus); else +#endif node = numa_node_id(); page = alloc_pages_node(node, gfp, order); return page ? page_address(page) : NULL; diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c index 70dd8e5..1c44b53 100644 --- a/arch/x86_64/kernel/process.c +++ b/arch/x86_64/kernel/process.c @@ -781,10 +781,16 @@ long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) } case ARCH_GET_GS: { unsigned long base; + unsigned gsindex; if (task->thread.gsindex == GS_TLS_SEL) base = read_32bit_tls(task, GS_TLS); - else if (doit) - rdmsrl(MSR_KERNEL_GS_BASE, base); + else if (doit) { + asm("movl %%gs,%0" : "=r" (gsindex)); + if (gsindex) + rdmsrl(MSR_KERNEL_GS_BASE, base); + else + base = task->thread.gs; + } else base = task->thread.gs; ret = put_user(base, (unsigned long __user *)addr); diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index 0856ad4..c50b067 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -353,8 +353,10 @@ static __init void parse_cmdline_early (char ** cmdline_p) if (fullarg(from, "enable_timer_pin_1")) disable_timer_pin_1 = -1; - if (fullarg(from, "nolapic") || fullarg(from, "disableapic")) + if (fullarg(from, "nolapic") || fullarg(from, "disableapic")) { + clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability); disable_apic = 1; + } if (fullarg(from, "noapic")) skip_ioapic_setup = 1; diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c index ef8bc46..7392570 100644 --- a/arch/x86_64/kernel/time.c +++ b/arch/x86_64/kernel/time.c @@ -726,7 +726,7 @@ static __init int late_hpet_init(void) unsigned int ntimer; if (!vxtime.hpet_address) - return -1; + return 0; memset(&hd, 0, sizeof (hd)); @@ -917,6 +917,8 @@ void __init time_init(void) vxtime.hpet_address = 0; if (hpet_use_timer) { + /* set tick_nsec to use the proper rate for HPET */ + tick_nsec = TICK_NSEC_HPET; cpu_khz = hpet_calibrate_tsc(); timename = "HPET"; #ifdef CONFIG_X86_PM_TIMER diff --git a/arch/x86_64/kernel/vmlinux.lds.S b/arch/x86_64/kernel/vmlinux.lds.S index 39ff070..b81f473 100644 --- a/arch/x86_64/kernel/vmlinux.lds.S +++ b/arch/x86_64/kernel/vmlinux.lds.S @@ -65,7 +65,7 @@ SECTIONS .data.cacheline_aligned : AT(ADDR(.data.cacheline_aligned) - LOAD_OFFSET) { *(.data.cacheline_aligned) } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(CONFIG_X86_INTERNODE_CACHE_BYTES); .data.read_mostly : AT(ADDR(.data.read_mostly) - LOAD_OFFSET) { *(.data.read_mostly) } diff --git a/arch/x86_64/kernel/x8664_ksyms.c b/arch/x86_64/kernel/x8664_ksyms.c index d78f460..fec4e52 100644 --- a/arch/x86_64/kernel/x8664_ksyms.c +++ b/arch/x86_64/kernel/x8664_ksyms.c @@ -112,7 +112,6 @@ EXPORT_SYMBOL_GPL(unset_nmi_callback); #undef memcpy #undef memset #undef memmove -#undef strlen extern void * memset(void *,int,__kernel_size_t); extern size_t strlen(const char *); @@ -121,7 +120,6 @@ extern void * memcpy(void *,const void *,__kernel_size_t); extern void * __memcpy(void *,const void *,__kernel_size_t); EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(strlen); EXPORT_SYMBOL(strpbrk); EXPORT_SYMBOL(memmove); EXPORT_SYMBOL(memcpy); diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index e5f7f1c..4ba34e9 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -305,7 +305,7 @@ static void __meminit phys_pud_init(pud_t *pud, unsigned long address, unsigned if (paddr >= end) break; - if (!after_bootmem && !e820_mapped(paddr, paddr+PUD_SIZE, 0)) { + if (!after_bootmem && !e820_any_mapped(paddr, paddr+PUD_SIZE, 0)) { set_pud(pud, __pud(0)); continue; } @@ -507,9 +507,8 @@ void __init clear_kernel_mapping(unsigned long address, unsigned long size) /* * Memory hotplug specific functions - * These are only for non-NUMA machines right now. */ -#ifdef CONFIG_MEMORY_HOTPLUG +#if defined(CONFIG_ACPI_HOTPLUG_MEMORY) || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE) void online_page(struct page *page) { @@ -520,6 +519,38 @@ void online_page(struct page *page) num_physpages++; } +#ifndef CONFIG_MEMORY_HOTPLUG +/* + * Memory Hotadd without sparsemem. The mem_maps have been allocated in advance, + * just online the pages. + */ +int __add_pages(struct zone *z, unsigned long start_pfn, unsigned long nr_pages) +{ + int err = -EIO; + unsigned long pfn; + unsigned long total = 0, mem = 0; + for (pfn = start_pfn; pfn < start_pfn + nr_pages; pfn++) { + if (pfn_valid(pfn)) { + online_page(pfn_to_page(pfn)); + err = 0; + mem++; + } + total++; + } + if (!err) { + z->spanned_pages += total; + z->present_pages += mem; + z->zone_pgdat->node_spanned_pages += total; + z->zone_pgdat->node_present_pages += mem; + } + return err; +} +#endif + +/* + * Memory is added always to NORMAL zone. This means you will never get + * additional DMA/DMA32 memory. + */ int add_memory(u64 start, u64 size) { struct pglist_data *pgdat = NODE_DATA(0); diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index 4be82d6..cc02573 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -100,11 +100,30 @@ int early_pfn_to_nid(unsigned long pfn) } #endif +static void * __init +early_node_mem(int nodeid, unsigned long start, unsigned long end, + unsigned long size) +{ + unsigned long mem = find_e820_area(start, end, size); + void *ptr; + if (mem != -1L) + return __va(mem); + ptr = __alloc_bootmem_nopanic(size, + SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS)); + if (ptr == 0) { + printk(KERN_ERR "Cannot find %lu bytes in node %d\n", + size, nodeid); + return NULL; + } + return ptr; +} + /* Initialize bootmem allocator for a node */ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) { unsigned long start_pfn, end_pfn, bootmap_pages, bootmap_size, bootmap_start; unsigned long nodedata_phys; + void *bootmap; const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE); start = round_up(start, ZONE_ALIGN); @@ -114,13 +133,11 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en start_pfn = start >> PAGE_SHIFT; end_pfn = end >> PAGE_SHIFT; - nodedata_phys = find_e820_area(start, end, pgdat_size); - if (nodedata_phys == -1L) - panic("Cannot find memory pgdat in node %d\n", nodeid); - - Dprintk("nodedata_phys %lx\n", nodedata_phys); + node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size); + if (node_data[nodeid] == NULL) + return; + nodedata_phys = __pa(node_data[nodeid]); - node_data[nodeid] = phys_to_virt(nodedata_phys); memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid]; NODE_DATA(nodeid)->node_start_pfn = start_pfn; @@ -129,9 +146,15 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en /* Find a place for the bootmem map */ bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE); - bootmap_start = find_e820_area(bootmap_start, end, bootmap_pages<<PAGE_SHIFT); - if (bootmap_start == -1L) - panic("Not enough continuous space for bootmap on node %d", nodeid); + bootmap = early_node_mem(nodeid, bootmap_start, end, + bootmap_pages<<PAGE_SHIFT); + if (bootmap == NULL) { + if (nodedata_phys < start || nodedata_phys >= end) + free_bootmem((unsigned long)node_data[nodeid],pgdat_size); + node_data[nodeid] = NULL; + return; + } + bootmap_start = __pa(bootmap); Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages); bootmap_size = init_bootmem_node(NODE_DATA(nodeid), @@ -142,6 +165,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size); reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<<PAGE_SHIFT); +#ifdef CONFIG_ACPI_NUMA + srat_reserve_add_area(nodeid); +#endif node_set_online(nodeid); } @@ -335,6 +361,8 @@ __init int numa_setup(char *opt) #ifdef CONFIG_ACPI_NUMA if (!strncmp(opt,"noacpi",6)) acpi_numa = -1; + if (!strncmp(opt,"hotadd=", 7)) + hotadd_percent = simple_strtoul(opt+7, NULL, 10); #endif return 1; } diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index 2eb8795..15ae9fc 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -15,15 +15,26 @@ #include <linux/bitmap.h> #include <linux/module.h> #include <linux/topology.h> +#include <linux/bootmem.h> +#include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> #include <asm/e820.h> +#if (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \ + defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) \ + && !defined(CONFIG_MEMORY_HOTPLUG) +#define RESERVE_HOTADD 1 +#endif + static struct acpi_table_slit *acpi_slit; static nodemask_t nodes_parsed __initdata; static nodemask_t nodes_found __initdata; static struct bootnode nodes[MAX_NUMNODES] __initdata; +static struct bootnode nodes_add[MAX_NUMNODES] __initdata; +static int found_add_area __initdata; +int hotadd_percent __initdata = 10; static u8 pxm2node[256] = { [0 ... 255] = 0xff }; /* Too small nodes confuse the VM badly. Usually they result @@ -71,6 +82,10 @@ static __init int conflicting_nodes(unsigned long start, unsigned long end) static __init void cutoff_node(int i, unsigned long start, unsigned long end) { struct bootnode *nd = &nodes[i]; + + if (found_add_area) + return; + if (nd->start < start) { nd->start = start; if (nd->end < nd->start) @@ -90,6 +105,8 @@ static __init void bad_srat(void) acpi_numa = -1; for (i = 0; i < MAX_LOCAL_APIC; i++) apicid_to_node[i] = NUMA_NO_NODE; + for (i = 0; i < MAX_NUMNODES; i++) + nodes_add[i].start = nodes[i].end = 0; } static __init inline int srat_disabled(void) @@ -155,11 +172,114 @@ acpi_numa_processor_affinity_init(struct acpi_table_processor_affinity *pa) pxm, pa->apic_id, node); } +#ifdef RESERVE_HOTADD +/* + * Protect against too large hotadd areas that would fill up memory. + */ +static int hotadd_enough_memory(struct bootnode *nd) +{ + static unsigned long allocated; + static unsigned long last_area_end; + unsigned long pages = (nd->end - nd->start) >> PAGE_SHIFT; + long mem = pages * sizeof(struct page); + unsigned long addr; + unsigned long allowed; + unsigned long oldpages = pages; + + if (mem < 0) + return 0; + allowed = (end_pfn - e820_hole_size(0, end_pfn)) * PAGE_SIZE; + allowed = (allowed / 100) * hotadd_percent; + if (allocated + mem > allowed) { + /* Give them at least part of their hotadd memory upto hotadd_percent + It would be better to spread the limit out + over multiple hotplug areas, but that is too complicated + right now */ + if (allocated >= allowed) + return 0; + pages = (allowed - allocated + mem) / sizeof(struct page); + mem = pages * sizeof(struct page); + nd->end = nd->start + pages*PAGE_SIZE; + } + /* Not completely fool proof, but a good sanity check */ + addr = find_e820_area(last_area_end, end_pfn<<PAGE_SHIFT, mem); + if (addr == -1UL) + return 0; + if (pages != oldpages) + printk(KERN_NOTICE "SRAT: Hotadd area limited to %lu bytes\n", + pages << PAGE_SHIFT); + last_area_end = addr + mem; + allocated += mem; + return 1; +} + +/* + * It is fine to add this area to the nodes data it will be used later + * This code supports one contigious hot add area per node. + */ +static int reserve_hotadd(int node, unsigned long start, unsigned long end) +{ + unsigned long s_pfn = start >> PAGE_SHIFT; + unsigned long e_pfn = end >> PAGE_SHIFT; + int changed = 0; + struct bootnode *nd = &nodes_add[node]; + + /* I had some trouble with strange memory hotadd regions breaking + the boot. Be very strict here and reject anything unexpected. + If you want working memory hotadd write correct SRATs. + + The node size check is a basic sanity check to guard against + mistakes */ + if ((signed long)(end - start) < NODE_MIN_SIZE) { + printk(KERN_ERR "SRAT: Hotplug area too small\n"); + return -1; + } + + /* This check might be a bit too strict, but I'm keeping it for now. */ + if (e820_hole_size(s_pfn, e_pfn) != e_pfn - s_pfn) { + printk(KERN_ERR "SRAT: Hotplug area has existing memory\n"); + return -1; + } + + if (!hotadd_enough_memory(&nodes_add[node])) { + printk(KERN_ERR "SRAT: Hotplug area too large\n"); + return -1; + } + + /* Looks good */ + + found_add_area = 1; + if (nd->start == nd->end) { + nd->start = start; + nd->end = end; + changed = 1; + } else { + if (nd->start == end) { + nd->start = start; + changed = 1; + } + if (nd->end == start) { + nd->end = end; + changed = 1; + } + if (!changed) + printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); + } + + if ((nd->end >> PAGE_SHIFT) > end_pfn) + end_pfn = nd->end >> PAGE_SHIFT; + + if (changed) + printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", nd->start, nd->end); + return 0; +} +#endif + /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ void __init acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) { - struct bootnode *nd; + struct bootnode *nd, oldnode; unsigned long start, end; int node, pxm; int i; @@ -172,6 +292,8 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) } if (ma->flags.enabled == 0) return; + if (ma->flags.hot_pluggable && hotadd_percent == 0) + return; start = ma->base_addr_lo | ((u64)ma->base_addr_hi << 32); end = start + (ma->length_lo | ((u64)ma->length_hi << 32)); pxm = ma->proximity_domain; @@ -181,10 +303,6 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) bad_srat(); return; } - /* It is fine to add this area to the nodes data it will be used later*/ - if (ma->flags.hot_pluggable == 1) - printk(KERN_INFO "SRAT: hot plug zone found %lx - %lx \n", - start, end); i = conflicting_nodes(start, end); if (i == node) { printk(KERN_WARNING @@ -199,6 +317,7 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) return; } nd = &nodes[node]; + oldnode = *nd; if (!node_test_and_set(node, nodes_parsed)) { nd->start = start; nd->end = end; @@ -208,8 +327,19 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) if (nd->end < end) nd->end = end; } + printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm, nd->start, nd->end); + +#ifdef RESERVE_HOTADD + if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) { + /* Ignore hotadd region. Undo damage */ + printk(KERN_NOTICE "SRAT: Hotplug region ignored\n"); + *nd = oldnode; + if ((nd->start | nd->end) == 0) + node_clear(node, nodes_parsed); + } +#endif } /* Sanity check to catch more bad SRATs (they are amazingly common). @@ -225,6 +355,9 @@ static int nodes_cover_memory(void) unsigned long e = nodes[i].end >> PAGE_SHIFT; pxmram += e - s; pxmram -= e820_hole_size(s, e); + pxmram -= nodes_add[i].end - nodes_add[i].start; + if ((long)pxmram < 0) + pxmram = 0; } e820ram = end_pfn - e820_hole_size(0, end_pfn); @@ -258,7 +391,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) /* First clean up the node list */ for (i = 0; i < MAX_NUMNODES; i++) { - cutoff_node(i, start, end); + cutoff_node(i, start, end); if ((nodes[i].end - nodes[i].start) < NODE_MIN_SIZE) unparse_node(i); } @@ -282,6 +415,12 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) /* Finally register nodes */ for_each_node_mask(i, nodes_parsed) setup_node_bootmem(i, nodes[i].start, nodes[i].end); + /* Try again in case setup_node_bootmem missed one due + to missing bootmem */ + for_each_node_mask(i, nodes_parsed) + if (!node_online(i)) + setup_node_bootmem(i, nodes[i].start, nodes[i].end); + for (i = 0; i < NR_CPUS; i++) { if (cpu_to_node[i] == NUMA_NO_NODE) continue; @@ -303,6 +442,25 @@ static int node_to_pxm(int n) return 0; } +void __init srat_reserve_add_area(int nodeid) +{ + if (found_add_area && nodes_add[nodeid].end) { + u64 total_mb; + + printk(KERN_INFO "SRAT: Reserving hot-add memory space " + "for node %d at %Lx-%Lx\n", + nodeid, nodes_add[nodeid].start, nodes_add[nodeid].end); + total_mb = (nodes_add[nodeid].end - nodes_add[nodeid].start) + >> PAGE_SHIFT; + total_mb *= sizeof(struct page); + total_mb >>= 20; + printk(KERN_INFO "SRAT: This will cost you %Lu MB of " + "pre-allocated memory.\n", (unsigned long long)total_mb); + reserve_bootmem_node(NODE_DATA(nodeid), nodes_add[nodeid].start, + nodes_add[nodeid].end - nodes_add[nodeid].start); + } +} + int __node_distance(int a, int b) { int index; diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c index e6165002..b493ed9 100644 --- a/arch/x86_64/pci/mmconfig.c +++ b/arch/x86_64/pci/mmconfig.c @@ -9,11 +9,16 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/bitmap.h> +#include <asm/e820.h> + #include "pci.h" #define MMCONFIG_APER_SIZE (256*1024*1024) +/* Verify the first 16 busses. We assume that systems with more busses + get MCFG right. */ +#define MAX_CHECK_BUS 16 -static DECLARE_BITMAP(fallback_slots, 32); +static DECLARE_BITMAP(fallback_slots, 32*MAX_CHECK_BUS); /* Static virtual mapping of the MMCONFIG aperture */ struct mmcfg_virt { @@ -55,7 +60,8 @@ static char __iomem *get_virt(unsigned int seg, unsigned bus) static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn) { char __iomem *addr; - if (seg == 0 && bus == 0 && test_bit(PCI_SLOT(devfn), fallback_slots)) + if (seg == 0 && bus < MAX_CHECK_BUS && + test_bit(32*bus + PCI_SLOT(devfn), fallback_slots)) return NULL; addr = get_virt(seg, bus); if (!addr) @@ -69,8 +75,10 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus, char __iomem *addr; /* Why do we have this when nobody checks it. How about a BUG()!? -AK */ - if (unlikely(!value || (bus > 255) || (devfn > 255) || (reg > 4095))) + if (unlikely(!value || (bus > 255) || (devfn > 255) || (reg > 4095))) { + *value = -1; return -EINVAL; + } addr = pci_dev_base(seg, bus, devfn); if (!addr) @@ -129,21 +137,26 @@ static struct pci_raw_ops pci_mmcfg = { Normally this can be expressed in the MCFG by not listing them and assigning suitable _SEGs, but this isn't implemented in some BIOS. Instead try to discover all devices on bus 0 that are unreachable using MM - and fallback for them. - We only do this for bus 0/seg 0 */ + and fallback for them. */ static __init void unreachable_devices(void) { - int i; - for (i = 0; i < 32; i++) { - u32 val1; - char __iomem *addr; - - pci_conf1_read(0, 0, PCI_DEVFN(i,0), 0, 4, &val1); - if (val1 == 0xffffffff) - continue; - addr = pci_dev_base(0, 0, PCI_DEVFN(i, 0)); - if (addr == NULL|| readl(addr) != val1) { - set_bit(i, fallback_slots); + int i, k; + /* Use the max bus number from ACPI here? */ + for (k = 0; i < MAX_CHECK_BUS; k++) { + for (i = 0; i < 32; i++) { + u32 val1; + char __iomem *addr; + + pci_conf1_read(0, k, PCI_DEVFN(i,0), 0, 4, &val1); + if (val1 == 0xffffffff) + continue; + addr = pci_dev_base(0, k, PCI_DEVFN(i, 0)); + if (addr == NULL|| readl(addr) != val1) { + set_bit(i + 32*k, fallback_slots); + printk(KERN_NOTICE + "PCI: No mmconfig possible on device %x:%x\n", + k, i); + } } } } @@ -161,6 +174,14 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; + if (!e820_all_mapped(pci_mmcfg_config[0].base_address, + pci_mmcfg_config[0].base_address + MMCONFIG_APER_SIZE, + E820_RESERVED)) { + printk(KERN_ERR "PCI: BIOS Bug: MCFG area is not E820-reserved\n"); + printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); + return; + } + /* RED-PEN i386 doesn't do _nocache right now */ pci_mmcfg_virt = kmalloc(sizeof(*pci_mmcfg_virt) * pci_mmcfg_config_num, GFP_KERNEL); if (pci_mmcfg_virt == NULL) { diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 5cb9630..c24652d 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -329,7 +329,7 @@ config ACPI_CONTAINER config ACPI_HOTPLUG_MEMORY tristate "Memory Hotplug" depends on ACPI - depends on MEMORY_HOTPLUG + depends on MEMORY_HOTPLUG || X86_64 default n help This driver adds supports for ACPI Memory Hotplug. This driver diff --git a/drivers/char/random.c b/drivers/char/random.c index 86be04b..58f3512 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1584,7 +1584,6 @@ u32 secure_ipv6_port_ephemeral(const __u32 *saddr, const __u32 *daddr, __u16 dpo return twothirdsMD4Transform(daddr, hash); } -EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) diff --git a/drivers/net/irda/irda-usb.c b/drivers/net/irda/irda-usb.c index 6e2ec56..606243d 100644 --- a/drivers/net/irda/irda-usb.c +++ b/drivers/net/irda/irda-usb.c @@ -1,7 +1,7 @@ /***************************************************************************** * * Filename: irda-usb.c - * Version: 0.9b + * Version: 0.10 * Description: IrDA-USB Driver * Status: Experimental * Author: Dag Brattli <dag@brattli.net> @@ -9,6 +9,9 @@ * Copyright (C) 2000, Roman Weissgaerber <weissg@vienna.at> * Copyright (C) 2001, Dag Brattli <dag@brattli.net> * Copyright (C) 2001, Jean Tourrilhes <jt@hpl.hp.com> + * Copyright (C) 2004, SigmaTel, Inc. <irquality@sigmatel.com> + * Copyright (C) 2005, Milan Beno <beno@pobox.sk> + * Copyright (C) 2006, Nick Fedchik <nick@fedchik.org.ua> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -61,6 +64,7 @@ #include <linux/slab.h> #include <linux/rtnetlink.h> #include <linux/usb.h> +#include <linux/firmware.h> #include "irda-usb.h" @@ -78,8 +82,12 @@ static struct usb_device_id dongles[] = { { USB_DEVICE(0x50f, 0x180), .driver_info = IUC_SPEED_BUG | IUC_NO_WINDOW }, /* Extended Systems, Inc., XTNDAccess IrDA USB (ESI-9685) */ { USB_DEVICE(0x8e9, 0x100), .driver_info = IUC_SPEED_BUG | IUC_NO_WINDOW }, + /* SigmaTel STIR4210/4220/4116 USB IrDA (VFIR) Bridge */ + { USB_DEVICE(0x66f, 0x4210), .driver_info = IUC_STIR_4210 | IUC_SPEED_BUG }, + { USB_DEVICE(0x66f, 0x4220), .driver_info = IUC_STIR_4210 | IUC_SPEED_BUG }, + { USB_DEVICE(0x66f, 0x4116), .driver_info = IUC_STIR_4210 | IUC_SPEED_BUG }, { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS | - USB_DEVICE_ID_MATCH_INT_SUBCLASS, + USB_DEVICE_ID_MATCH_INT_SUBCLASS, .bInterfaceClass = USB_CLASS_APP_SPEC, .bInterfaceSubClass = USB_CLASS_IRDA, .driver_info = IUC_DEFAULT, }, @@ -99,6 +107,7 @@ MODULE_DEVICE_TABLE(usb, dongles); /*------------------------------------------------------------------*/ +static void irda_usb_init_qos(struct irda_usb_cb *self) ; static struct irda_class_desc *irda_usb_find_class_desc(struct usb_interface *intf); static void irda_usb_disconnect(struct usb_interface *intf); static void irda_usb_change_speed_xbofs(struct irda_usb_cb *self); @@ -141,7 +150,24 @@ static void irda_usb_build_header(struct irda_usb_cb *self, __u8 *header, int force) { - /* Set the negotiated link speed */ + /* Here we check if we have an STIR421x chip, + * and if either speed or xbofs (or both) needs + * to be changed. + */ + if (self->capability & IUC_STIR_4210 && + ((self->new_speed != -1) || (self->new_xbofs != -1))) { + + /* With STIR421x, speed and xBOFs must be set at the same + * time, even if only one of them changes. + */ + if (self->new_speed == -1) + self->new_speed = self->speed ; + + if (self->new_xbofs == -1) + self->new_xbofs = self->xbofs ; + } + + /* Set the link speed */ if (self->new_speed != -1) { /* Hum... Ugly hack :-( * Some device are not compliant with the spec and change @@ -191,7 +217,11 @@ static void irda_usb_build_header(struct irda_usb_cb *self, *header = SPEED_4000000; self->new_xbofs = 0; break; - } + case 16000000: + *header = SPEED_16000000; + self->new_xbofs = 0; + break; + } } else /* No change */ *header = 0; @@ -235,6 +265,32 @@ static void irda_usb_build_header(struct irda_usb_cb *self, } } +/* +* calculate turnaround time for SigmaTel header +*/ +static __u8 get_turnaround_time(struct sk_buff *skb) +{ + int turnaround_time = irda_get_mtt(skb); + + if ( turnaround_time == 0 ) + return 0; + else if ( turnaround_time <= 10 ) + return 1; + else if ( turnaround_time <= 50 ) + return 2; + else if ( turnaround_time <= 100 ) + return 3; + else if ( turnaround_time <= 500 ) + return 4; + else if ( turnaround_time <= 1000 ) + return 5; + else if ( turnaround_time <= 5000 ) + return 6; + else + return 7; +} + + /*------------------------------------------------------------------*/ /* * Send a command to change the speed of the dongle @@ -262,12 +318,18 @@ static void irda_usb_change_speed_xbofs(struct irda_usb_cb *self) /* Set the new speed and xbofs in this fake frame */ irda_usb_build_header(self, frame, 1); + if ( self->capability & IUC_STIR_4210 ) { + if (frame[0] == 0) return ; // do nothing if no change + frame[1] = 0; // other parameters don't change here + frame[2] = 0; + } + /* Submit the 0 length IrDA frame to trigger new speed settings */ usb_fill_bulk_urb(urb, self->usbdev, usb_sndbulkpipe(self->usbdev, self->bulk_out_ep), frame, IRDA_USB_SPEED_MTU, speed_bulk_callback, self); - urb->transfer_buffer_length = USB_IRDA_HEADER; + urb->transfer_buffer_length = self->header_length; urb->transfer_flags = 0; /* Irq disabled -> GFP_ATOMIC */ @@ -383,16 +445,35 @@ static int irda_usb_hard_xmit(struct sk_buff *skb, struct net_device *netdev) * allocation will be done lower in skb_push(). * Also, we don't use directly skb_cow(), because it require * headroom >= 16, which force unnecessary copies - Jean II */ - if (skb_headroom(skb) < USB_IRDA_HEADER) { + if (skb_headroom(skb) < self->header_length) { IRDA_DEBUG(0, "%s(), Insuficient skb headroom.\n", __FUNCTION__); - if (skb_cow(skb, USB_IRDA_HEADER)) { + if (skb_cow(skb, self->header_length)) { IRDA_WARNING("%s(), failed skb_cow() !!!\n", __FUNCTION__); goto drop; } } /* Change setting for next frame */ - irda_usb_build_header(self, skb_push(skb, USB_IRDA_HEADER), 0); + + if ( self->capability & IUC_STIR_4210 ) { + __u8 turnaround_time; + __u8* frame; + turnaround_time = get_turnaround_time( skb ); + frame= skb_push(skb, self->header_length); + irda_usb_build_header(self, frame, 0); + frame[2] = turnaround_time; + if ((skb->len != 0) && + ((skb->len % 128) == 0) && + ((skb->len % 512) != 0)) { + /* add extra byte for special SigmaTel feature */ + frame[1] = 1; + skb_put(skb, 1); + } else { + frame[1] = 0; + } + } else { + irda_usb_build_header(self, skb_push(skb, self->header_length), 0); + } /* FIXME: Make macro out of this one */ ((struct irda_skb_cb *)skb->cb)->context = self; @@ -795,7 +876,7 @@ static void irda_usb_receive(struct urb *urb, struct pt_regs *regs) } /* Check for empty frames */ - if (urb->actual_length <= USB_IRDA_HEADER) { + if (urb->actual_length <= self->header_length) { IRDA_WARNING("%s(), empty frame!\n", __FUNCTION__); goto done; } @@ -816,7 +897,11 @@ static void irda_usb_receive(struct urb *urb, struct pt_regs *regs) docopy = (urb->actual_length < IRDA_RX_COPY_THRESHOLD); /* Allocate a new skb */ - newskb = dev_alloc_skb(docopy ? urb->actual_length : IRDA_SKB_MAX_MTU); + if ( self->capability & IUC_STIR_4210 ) + newskb = dev_alloc_skb(docopy ? urb->actual_length : IRDA_SKB_MAX_MTU + USB_IRDA_SIGMATEL_HEADER); + else + newskb = dev_alloc_skb(docopy ? urb->actual_length : IRDA_SKB_MAX_MTU); + if (!newskb) { self->stats.rx_dropped++; /* We could deliver the current skb, but this would stall @@ -845,7 +930,7 @@ static void irda_usb_receive(struct urb *urb, struct pt_regs *regs) /* Set proper length on skb & remove USB-IrDA header */ skb_put(dataskb, urb->actual_length); - skb_pull(dataskb, USB_IRDA_HEADER); + skb_pull(dataskb, self->header_length); /* Ask the networking layer to queue the packet for the IrDA stack */ dataskb->dev = self->netdev; @@ -937,6 +1022,191 @@ static int irda_usb_is_receiving(struct irda_usb_cb *self) return 0; /* For now */ } + +#define STIR421X_PATCH_PRODUCT_VERSION_STR "Product Version: " +#define STIR421X_PATCH_COMPONENT_VERSION_STR "Component Version: " +#define STIR421X_PATCH_DATA_TAG_STR "STMP" +#define STIR421X_PATCH_FILE_VERSION_MAX_OFFSET 512 /* version info is before here */ +#define STIR421X_PATCH_FILE_IMAGE_MAX_OFFSET 512 /* patch image starts before here */ +#define STIR421X_PATCH_FILE_END_OF_HEADER_TAG 0x1A /* marks end of patch file header (PC DOS text file EOF character) */ + +/* + * Known firmware patches for STIR421x dongles + */ +static char * stir421x_patches[] = { + "42101001.sb", + "42101002.sb", +}; + +static int stir421x_get_patch_version(unsigned char * patch, const unsigned long patch_len) +{ + unsigned int version_offset; + unsigned long version_major, version_minor, version_build; + unsigned char * version_start; + int version_found = 0; + + for (version_offset = 0; + version_offset < STIR421X_PATCH_FILE_END_OF_HEADER_TAG; + version_offset++) { + if (!memcmp(patch + version_offset, + STIR421X_PATCH_PRODUCT_VERSION_STR, + sizeof(STIR421X_PATCH_PRODUCT_VERSION_STR) - 1)) { + version_found = 1; + version_start = patch + + version_offset + + sizeof(STIR421X_PATCH_PRODUCT_VERSION_STR) - 1; + break; + } + } + + /* We couldn't find a product version on this patch */ + if (!version_found) + return -EINVAL; + + /* Let's check if the product version is dotted */ + if (version_start[3] != '.' || + version_start[7] != '.') + return -EINVAL; + + version_major = simple_strtoul(version_start, NULL, 10); + version_minor = simple_strtoul(version_start + 4, NULL, 10); + version_build = simple_strtoul(version_start + 8, NULL, 10); + + IRDA_DEBUG(2, "%s(), Major: %ld Minor: %ld Build: %ld\n", + __FUNCTION__, + version_major, version_minor, version_build); + + return (((version_major) << 12) + + ((version_minor) << 8) + + ((version_build / 10) << 4) + + (version_build % 10)); + +} + + +static int stir421x_upload_patch (struct irda_usb_cb *self, + unsigned char * patch, + const unsigned int patch_len) +{ + int retval = 0; + int actual_len; + unsigned int i = 0, download_amount = 0; + unsigned char * patch_chunk; + + IRDA_DEBUG (2, "%s(), Uploading STIR421x Patch\n", __FUNCTION__); + + patch_chunk = kzalloc(STIR421X_MAX_PATCH_DOWNLOAD_SIZE, GFP_KERNEL); + if (patch_chunk == NULL) + return -ENOMEM; + + /* break up patch into 1023-byte sections */ + for (i = 0; retval >= 0 && i < patch_len; i += download_amount) { + download_amount = patch_len - i; + if (download_amount > STIR421X_MAX_PATCH_DOWNLOAD_SIZE) + download_amount = STIR421X_MAX_PATCH_DOWNLOAD_SIZE; + + /* download the patch section */ + memcpy(patch_chunk, patch + i, download_amount); + + retval = usb_bulk_msg (self->usbdev, + usb_sndbulkpipe (self->usbdev, + self->bulk_out_ep), + patch_chunk, download_amount, + &actual_len, msecs_to_jiffies (500)); + IRDA_DEBUG (2, "%s(), Sent %u bytes\n", __FUNCTION__, + actual_len); + if (retval == 0) + mdelay(10); + } + + kfree(patch_chunk); + + if (i != patch_len) { + IRDA_ERROR ("%s(), Pushed %d bytes (!= patch_len (%d))\n", + __FUNCTION__, i, patch_len); + retval = -EIO; + } + + if (retval < 0) + /* todo - mark device as not ready */ + IRDA_ERROR ("%s(), STIR421x patch upload failed (%d)\n", + __FUNCTION__, retval); + + return retval; +} + + +static int stir421x_patch_device(struct irda_usb_cb *self) +{ + unsigned int i, patch_found = 0, data_found = 0, data_offset; + int patch_version, ret = 0; + const struct firmware *fw_entry; + + for (i = 0; i < ARRAY_SIZE(stir421x_patches); i++) { + if(request_firmware(&fw_entry, stir421x_patches[i], &self->usbdev->dev) != 0) { + IRDA_ERROR( "%s(), Patch %s is not available\n", __FUNCTION__, stir421x_patches[i]); + continue; + } + + /* We found a patch from userspace */ + patch_version = stir421x_get_patch_version (fw_entry->data, fw_entry->size); + + if (patch_version < 0) { + /* Couldn't fetch a version, let's move on to the next file */ + IRDA_ERROR("%s(), version parsing failed\n", __FUNCTION__); + ret = patch_version; + release_firmware(fw_entry); + continue; + } + + if (patch_version != self->usbdev->descriptor.bcdDevice) { + /* Patch version and device don't match */ + IRDA_ERROR ("%s(), wrong patch version (%d <-> %d)\n", + __FUNCTION__, + patch_version, self->usbdev->descriptor.bcdDevice); + ret = -EINVAL; + release_firmware(fw_entry); + continue; + } + + /* If we're here, we've found a correct patch */ + patch_found = 1; + break; + + } + + /* We couldn't find a valid firmware, let's leave */ + if (!patch_found) + return ret; + + /* The actual image starts after the "STMP" keyword */ + for (data_offset = 0; data_offset < STIR421X_PATCH_FILE_IMAGE_MAX_OFFSET; data_offset++) { + if (!memcmp(fw_entry->data + data_offset, + STIR421X_PATCH_DATA_TAG_STR, + sizeof(STIR421X_PATCH_FILE_IMAGE_MAX_OFFSET))) { + IRDA_DEBUG(2, "%s(), found patch data for STIR421x at offset %d\n", + __FUNCTION__, data_offset); + data_found = 1; + break; + } + } + + /* We couldn't find "STMP" from the header */ + if (!data_found) + return -EINVAL; + + /* Let's upload the patch to the target */ + ret = stir421x_upload_patch(self, + &fw_entry->data[data_offset + sizeof(STIR421X_PATCH_FILE_IMAGE_MAX_OFFSET)], + fw_entry->size - (data_offset + sizeof(STIR421X_PATCH_FILE_IMAGE_MAX_OFFSET))); + + release_firmware(fw_entry); + + return ret; + +} + + /********************** IRDA DEVICE CALLBACKS **********************/ /* * Main calls from the IrDA/Network subsystem. @@ -972,6 +1242,11 @@ static int irda_usb_net_open(struct net_device *netdev) return -1; } + if(self->needspatch) { + IRDA_WARNING("%s(), device needs patch\n", __FUNCTION__) ; + return -EIO ; + } + /* Initialise default speed and xbofs value * (IrLAP will change that soon) */ self->speed = -1; @@ -1050,7 +1325,7 @@ static int irda_usb_net_close(struct net_device *netdev) del_timer(&self->rx_defer_timer); /* Deallocate all the Rx path buffers (URBs and skb) */ - for (i = 0; i < IU_MAX_RX_URBS; i++) { + for (i = 0; i < self->max_rx_urb; i++) { struct urb *urb = self->rx_urb[i]; struct sk_buff *skb = (struct sk_buff *) urb->context; /* Cancel the receive command */ @@ -1426,8 +1701,22 @@ static int irda_usb_probe(struct usb_interface *intf, spin_lock_init(&self->lock); init_timer(&self->rx_defer_timer); + self->capability = id->driver_info; + self->needspatch = ((self->capability & IUC_STIR_4210) != 0) ; + /* Create all of the needed urbs */ - for (i = 0; i < IU_MAX_RX_URBS; i++) { + if (self->capability & IUC_STIR_4210) { + self->max_rx_urb = IU_SIGMATEL_MAX_RX_URBS; + self->header_length = USB_IRDA_SIGMATEL_HEADER; + } else { + self->max_rx_urb = IU_MAX_RX_URBS; + self->header_length = USB_IRDA_HEADER; + } + + self->rx_urb = kzalloc(self->max_rx_urb * sizeof(struct urb *), + GFP_KERNEL); + + for (i = 0; i < self->max_rx_urb; i++) { self->rx_urb[i] = usb_alloc_urb(0, GFP_KERNEL); if (!self->rx_urb[i]) { goto err_out_1; @@ -1479,17 +1768,28 @@ static int irda_usb_probe(struct usb_interface *intf, goto err_out_3; } + self->usbdev = dev; + /* Find IrDA class descriptor */ irda_desc = irda_usb_find_class_desc(intf); ret = -ENODEV; if (irda_desc == NULL) goto err_out_3; + if (self->needspatch) { + ret = usb_control_msg (self->usbdev, usb_sndctrlpipe (self->usbdev, 0), + 0x02, 0x40, 0, 0, 0, 0, msecs_to_jiffies(500)); + if (ret < 0) { + IRDA_DEBUG (0, "usb_control_msg failed %d\n", ret); + goto err_out_3; + } else { + mdelay(10); + } + } + self->irda_desc = irda_desc; self->present = 1; self->netopen = 0; - self->capability = id->driver_info; - self->usbdev = dev; self->usbintf = intf; /* Allocate the buffer for speed changes */ @@ -1508,6 +1808,28 @@ static int irda_usb_probe(struct usb_interface *intf, IRDA_MESSAGE("IrDA: Registered device %s\n", net->name); usb_set_intfdata(intf, self); + + if (self->needspatch) { + /* Now we fetch and upload the firmware patch */ + ret = stir421x_patch_device(self); + self->needspatch = (ret < 0); + if (ret < 0) { + printk("patch_device failed\n"); + goto err_out_4; + } + + /* replace IrDA class descriptor with what patched device is now reporting */ + irda_desc = irda_usb_find_class_desc (self->usbintf); + if (irda_desc == NULL) { + ret = -ENODEV; + goto err_out_4; + } + if (self->irda_desc) + kfree (self->irda_desc); + self->irda_desc = irda_desc; + irda_usb_init_qos(self); + } + return 0; err_out_4: @@ -1518,7 +1840,7 @@ err_out_3: err_out_2: usb_free_urb(self->tx_urb); err_out_1: - for (i = 0; i < IU_MAX_RX_URBS; i++) { + for (i = 0; i < self->max_rx_urb; i++) { if (self->rx_urb[i]) usb_free_urb(self->rx_urb[i]); } @@ -1571,7 +1893,7 @@ static void irda_usb_disconnect(struct usb_interface *intf) /*netif_device_detach(self->netdev);*/ netif_stop_queue(self->netdev); /* Stop all the receive URBs. Must be synchronous. */ - for (i = 0; i < IU_MAX_RX_URBS; i++) + for (i = 0; i < self->max_rx_urb; i++) usb_kill_urb(self->rx_urb[i]); /* Cancel Tx and speed URB. * Make sure it's synchronous to avoid races. */ @@ -1586,8 +1908,9 @@ static void irda_usb_disconnect(struct usb_interface *intf) self->usbintf = NULL; /* Clean up our urbs */ - for (i = 0; i < IU_MAX_RX_URBS; i++) + for (i = 0; i < self->max_rx_urb; i++) usb_free_urb(self->rx_urb[i]); + kfree(self->rx_urb); /* Clean up Tx and speed URB */ usb_free_urb(self->tx_urb); usb_free_urb(self->speed_urb); @@ -1648,6 +1971,6 @@ module_exit(usb_irda_cleanup); */ module_param(qos_mtt_bits, int, 0); MODULE_PARM_DESC(qos_mtt_bits, "Minimum Turn Time"); -MODULE_AUTHOR("Roman Weissgaerber <weissg@vienna.at>, Dag Brattli <dag@brattli.net> and Jean Tourrilhes <jt@hpl.hp.com>"); -MODULE_DESCRIPTION("IrDA-USB Dongle Driver"); +MODULE_AUTHOR("Roman Weissgaerber <weissg@vienna.at>, Dag Brattli <dag@brattli.net>, Jean Tourrilhes <jt@hpl.hp.com> and Nick Fedchik <nick@fedchik.org.ua>"); +MODULE_DESCRIPTION("IrDA-USB Dongle Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/net/irda/irda-usb.h b/drivers/net/irda/irda-usb.h index 4026af4..d833db5 100644 --- a/drivers/net/irda/irda-usb.h +++ b/drivers/net/irda/irda-usb.h @@ -1,7 +1,7 @@ /***************************************************************************** * * Filename: irda-usb.h - * Version: 0.9b + * Version: 0.10 * Description: IrDA-USB Driver * Status: Experimental * Author: Dag Brattli <dag@brattli.net> @@ -9,6 +9,9 @@ * Copyright (C) 2001, Roman Weissgaerber <weissg@vienna.at> * Copyright (C) 2000, Dag Brattli <dag@brattli.net> * Copyright (C) 2001, Jean Tourrilhes <jt@hpl.hp.com> + * Copyright (C) 2004, SigmaTel, Inc. <irquality@sigmatel.com> + * Copyright (C) 2005, Milan Beno <beno@pobox.sk> + * Copyright (C) 2006, Nick FEdchik <nick@fedchik.org.ua> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -31,6 +34,9 @@ #include <net/irda/irda.h> #include <net/irda/irda_device.h> /* struct irlap_cb */ +#define PATCH_FILE_SIZE_MAX 65536 +#define PATCH_FILE_SIZE_MIN 80 + #define RX_COPY_THRESHOLD 200 #define IRDA_USB_MAX_MTU 2051 #define IRDA_USB_SPEED_MTU 64 /* Weird, but work like this */ @@ -79,15 +85,16 @@ /* Inbound header */ #define MEDIA_BUSY 0x80 -#define SPEED_2400 0x01 -#define SPEED_9600 0x02 -#define SPEED_19200 0x03 -#define SPEED_38400 0x04 -#define SPEED_57600 0x05 -#define SPEED_115200 0x06 -#define SPEED_576000 0x07 -#define SPEED_1152000 0x08 -#define SPEED_4000000 0x09 +#define SPEED_2400 0x01 +#define SPEED_9600 0x02 +#define SPEED_19200 0x03 +#define SPEED_38400 0x04 +#define SPEED_57600 0x05 +#define SPEED_115200 0x06 +#define SPEED_576000 0x07 +#define SPEED_1152000 0x08 +#define SPEED_4000000 0x09 +#define SPEED_16000000 0x0a /* Basic capabilities */ #define IUC_DEFAULT 0x00 /* Basic device compliant with 1.0 spec */ @@ -100,11 +107,14 @@ #define IUC_SMALL_PKT 0x10 /* Device doesn't behave with big Rx packets */ #define IUC_MAX_WINDOW 0x20 /* Device underestimate the Rx window */ #define IUC_MAX_XBOFS 0x40 /* Device need more xbofs than advertised */ +#define IUC_STIR_4210 0x80 /* SigmaTel 4210/4220/4116 VFIR */ /* USB class definitions */ -#define USB_IRDA_HEADER 0x01 -#define USB_CLASS_IRDA 0x02 /* USB_CLASS_APP_SPEC subclass */ -#define USB_DT_IRDA 0x21 +#define USB_IRDA_HEADER 0x01 +#define USB_CLASS_IRDA 0x02 /* USB_CLASS_APP_SPEC subclass */ +#define USB_DT_IRDA 0x21 +#define USB_IRDA_SIGMATEL_HEADER 0x03 +#define IU_SIGMATEL_MAX_RX_URBS (IU_MAX_ACTIVE_RX_URBS + USB_IRDA_SIGMATEL_HEADER) struct irda_class_desc { __u8 bLength; @@ -123,6 +133,7 @@ struct irda_class_desc { * (6.2.5, USB-IrDA class spec 1.0) */ #define IU_REQ_GET_CLASS_DESC 0x06 +#define STIR421X_MAX_PATCH_DOWNLOAD_SIZE 1023 struct irda_usb_cb { struct irda_class_desc *irda_desc; @@ -136,7 +147,8 @@ struct irda_usb_cb { __u16 bulk_out_mtu; /* Max Tx packet size in bytes */ __u8 bulk_int_ep; /* Interrupt Endpoint assignments */ - struct urb *rx_urb[IU_MAX_RX_URBS]; /* URBs used to receive data frames */ + __u8 max_rx_urb; + struct urb **rx_urb; /* URBs used to receive data frames */ struct urb *idle_rx_urb; /* Pointer to idle URB in Rx path */ struct urb *tx_urb; /* URB used to send data frames */ struct urb *speed_urb; /* URB used to send speed commands */ @@ -157,6 +169,9 @@ struct irda_usb_cb { __u32 speed; /* Current speed */ __s32 new_speed; /* speed we need to set */ + __u8 header_length; /* USB-IrDA frame header size */ + int needspatch; /* device needs firmware patch */ + struct timer_list rx_defer_timer; /* Wait for Rx error to clear */ }; diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c index ec94ecd..bbcfc8e 100644 --- a/drivers/net/irda/smsc-ircc2.c +++ b/drivers/net/irda/smsc-ircc2.c @@ -11,6 +11,7 @@ * Copyright (c) 2002 Daniele Peri * All Rights Reserved. * Copyright (c) 2002 Jean Tourrilhes + * Copyright (c) 2006 Linus Walleij * * * Based on smc-ircc.c: @@ -61,6 +62,9 @@ #include <linux/spinlock.h> #include <linux/pm.h> +#ifdef CONFIG_PCI +#include <linux/pci.h> +#endif #include <net/irda/wrapper.h> #include <net/irda/irda.h> @@ -100,6 +104,22 @@ MODULE_PARM_DESC(ircc_transceiver, "Transceiver type"); /* Types */ +#ifdef CONFIG_PCI +struct smsc_ircc_subsystem_configuration { + unsigned short vendor; /* PCI vendor ID */ + unsigned short device; /* PCI vendor ID */ + unsigned short subvendor; /* PCI subsystem vendor ID */ + unsigned short subdevice; /* PCI sybsystem device ID */ + unsigned short sir_io; /* I/O port for SIR */ + unsigned short fir_io; /* I/O port for FIR */ + unsigned char fir_irq; /* FIR IRQ */ + unsigned char fir_dma; /* FIR DMA */ + unsigned short cfg_base; /* I/O port for chip configuration */ + int (*preconfigure)(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf); /* Preconfig function */ + const char *name; /* name shown as info */ +}; +#endif + struct smsc_transceiver { char *name; void (*set_for_speed)(int fir_base, u32 speed); @@ -202,6 +222,16 @@ static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned shor static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type); static int __init smsc_superio_fdc(unsigned short cfg_base); static int __init smsc_superio_lpc(unsigned short cfg_base); +#ifdef CONFIG_PCI +static int __init preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf); +static int __init preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf); +static int __init preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf); +static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg, + unsigned short ircc_fir, + unsigned short ircc_sir, + unsigned char ircc_dma, + unsigned char ircc_irq); +#endif /* Transceivers specific functions */ @@ -353,6 +383,13 @@ static int __init smsc_ircc_init(void) return ret; } +#ifdef CONFIG_PCI + if (smsc_ircc_preconfigure_subsystems(ircc_cfg, ircc_fir, ircc_sir, ircc_dma, ircc_irq) < 0) { + /* Ignore errors from preconfiguration */ + IRDA_ERROR("%s, Preconfiguration failed !\n", driver_name); + } +#endif + dev_count = 0; if (ircc_fir > 0 && ircc_sir > 0) { @@ -2285,6 +2322,280 @@ static int __init smsc_superio_lpc(unsigned short cfg_base) return ret; } +/* + * Look for some specific subsystem setups that need + * pre-configuration not properly done by the BIOS (especially laptops) + * This code is based in part on smcinit.c, tosh1800-smcinit.c + * and tosh2450-smcinit.c. The table lists the device entries + * for ISA bridges with an LPC (Local Peripheral Configurator) + * that are in turn used to configure the SMSC device with default + * SIR and FIR I/O ports, DMA and IRQ. + */ +#ifdef CONFIG_PCI +#define PCIID_VENDOR_INTEL 0x8086 +#define PCIID_VENDOR_ALI 0x10b9 +static struct smsc_ircc_subsystem_configuration subsystem_configurations[] __devinitdata = { + { + .vendor = PCIID_VENDOR_INTEL, /* Intel 82801DBM LPC bridge */ + .device = 0x24cc, + .subvendor = 0x103c, + .subdevice = 0x088c, + .sir_io = 0x02f8, /* Quite certain these are the same for nc8000 as for nc6000 */ + .fir_io = 0x0130, + .fir_irq = 0x09, + .fir_dma = 0x03, + .cfg_base = 0x004e, + .preconfigure = preconfigure_through_82801, + .name = "HP nc8000", + }, + { + .vendor = PCIID_VENDOR_INTEL, /* Intel 82801DBM LPC bridge */ + .device = 0x24cc, + .subvendor = 0x103c, + .subdevice = 0x0890, + .sir_io = 0x02f8, + .fir_io = 0x0130, + .fir_irq = 0x09, + .fir_dma = 0x03, + .cfg_base = 0x004e, + .preconfigure = preconfigure_through_82801, + .name = "HP nc6000", + }, + { + .vendor = PCIID_VENDOR_INTEL, /* Intel 82801DB/DBL (ICH4/ICH4-L) LPC Interface Bridge */ + .device = 0x24c0, + .subvendor = 0x1179, + .subdevice = 0xffff, /* 0xffff is "any", Not sure, 0x0001 or 0x0002 */ + .sir_io = 0x03f8, + .fir_io = 0x0130, + .fir_irq = 0x07, + .fir_dma = 0x01, + .cfg_base = 0x002e, + .preconfigure = preconfigure_through_82801, + .name = "Toshiba Satellite 2450", + }, + { + .vendor = PCIID_VENDOR_INTEL, /* Intel 82801CAM ISA bridge */ + .device = 0x248c, /* Some use 24cc? */ + .subvendor = 0x1179, + .subdevice = 0xffff, /* 0xffff is "any", Not sure, 0x0001 or 0x0002 */ + .sir_io = 0x03f8, + .fir_io = 0x0130, + .fir_irq = 0x03, + .fir_dma = 0x03, + .cfg_base = 0x002e, + .preconfigure = preconfigure_through_82801, + .name = "Toshiba Satellite 5100/5200, Tecra 9100", + }, + { + .vendor = PCIID_VENDOR_ALI, /* ALi M1533/M1535 PCI to ISA Bridge [Aladdin IV/V/V+] */ + .device = 0x1533, + .subvendor = 0x1179, + .subdevice = 0xffff, /* 0xffff is "any", Not sure, 0x0001 or 0x0002 */ + .sir_io = 0x02e8, + .fir_io = 0x02f8, + .fir_irq = 0x07, + .fir_dma = 0x03, + .cfg_base = 0x002e, + .preconfigure = preconfigure_through_ali, + .name = "Toshiba Satellite 1800", + }, + { } // Terminator +}; + + +/* + * This sets up the basic SMSC parameters (FIR port, SIR port, FIR DMA, FIR IRQ) + * through the chip configuration port. + */ +static int __init preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf) +{ + unsigned short iobase = conf->cfg_base; + unsigned char tmpbyte; + + outb(LPC47N227_CFGACCESSKEY, iobase); // enter configuration state + outb(SMSCSIOFLAT_DEVICEID_REG, iobase); // set for device ID + tmpbyte = inb(iobase +1); // Read device ID + IRDA_DEBUG(0, "Detected Chip id: 0x%02x, setting up registers...\n",tmpbyte); + + /* Disable UART1 and set up SIR I/O port */ + outb(0x24, iobase); // select CR24 - UART1 base addr + outb(0x00, iobase + 1); // disable UART1 + outb(SMSCSIOFLAT_UART2BASEADDR_REG, iobase); // select CR25 - UART2 base addr + outb( (conf->sir_io >> 2), iobase + 1); // bits 2-9 of 0x3f8 + tmpbyte = inb(iobase + 1); + if (tmpbyte != (conf->sir_io >> 2) ) { + IRDA_WARNING("ERROR: could not configure SIR ioport.\n"); + return -ENXIO; + } + + /* Set up FIR IRQ channel for UART2 */ + outb(SMSCSIOFLAT_UARTIRQSELECT_REG, iobase); // select CR28 - UART1,2 IRQ select + tmpbyte = inb(iobase + 1); + tmpbyte &= SMSCSIOFLAT_UART1IRQSELECT_MASK; // Do not touch the UART1 portion + tmpbyte |= (conf->fir_irq & SMSCSIOFLAT_UART2IRQSELECT_MASK); + outb(tmpbyte, iobase + 1); + tmpbyte = inb(iobase + 1) & SMSCSIOFLAT_UART2IRQSELECT_MASK; + if (tmpbyte != conf->fir_irq) { + IRDA_WARNING("ERROR: could not configure FIR IRQ channel.\n"); + return -ENXIO; + } + + /* Set up FIR I/O port */ + outb(SMSCSIOFLAT_FIRBASEADDR_REG, iobase); // CR2B - SCE (FIR) base addr + outb((conf->fir_io >> 3), iobase + 1); + tmpbyte = inb(iobase + 1); + if (tmpbyte != (conf->fir_io >> 3) ) { + IRDA_WARNING("ERROR: could not configure FIR I/O port.\n"); + return -ENXIO; + } + + /* Set up FIR DMA channel */ + outb(SMSCSIOFLAT_FIRDMASELECT_REG, iobase); // CR2C - SCE (FIR) DMA select + outb((conf->fir_dma & LPC47N227_FIRDMASELECT_MASK), iobase + 1); // DMA + tmpbyte = inb(iobase + 1) & LPC47N227_FIRDMASELECT_MASK; + if (tmpbyte != (conf->fir_dma & LPC47N227_FIRDMASELECT_MASK)) { + IRDA_WARNING("ERROR: could not configure FIR DMA channel.\n"); + return -ENXIO; + } + + outb(SMSCSIOFLAT_UARTMODE0C_REG, iobase); // CR0C - UART mode + tmpbyte = inb(iobase + 1); + tmpbyte &= ~SMSCSIOFLAT_UART2MODE_MASK | SMSCSIOFLAT_UART2MODE_VAL_IRDA; + outb(tmpbyte, iobase + 1); // enable IrDA (HPSIR) mode, high speed + + outb(LPC47N227_APMBOOTDRIVE_REG, iobase); // CR07 - Auto Pwr Mgt/boot drive sel + tmpbyte = inb(iobase + 1); + outb(tmpbyte | LPC47N227_UART2AUTOPWRDOWN_MASK, iobase + 1); // enable UART2 autopower down + + /* This one was not part of tosh1800 */ + outb(0x0a, iobase); // CR0a - ecp fifo / ir mux + tmpbyte = inb(iobase + 1); + outb(tmpbyte | 0x40, iobase + 1); // send active device to ir port + + outb(LPC47N227_UART12POWER_REG, iobase); // CR02 - UART 1,2 power + tmpbyte = inb(iobase + 1); + outb(tmpbyte | LPC47N227_UART2POWERDOWN_MASK, iobase + 1); // UART2 power up mode, UART1 power down + + outb(LPC47N227_FDCPOWERVALIDCONF_REG, iobase); // CR00 - FDC Power/valid config cycle + tmpbyte = inb(iobase + 1); + outb(tmpbyte | LPC47N227_VALID_MASK, iobase + 1); // valid config cycle done + + outb(LPC47N227_CFGEXITKEY, iobase); // Exit configuration + + return 0; +} + +/* 82801CAM registers */ +#define VID 0x00 +#define DID 0x02 +#define PIRQA_ROUT 0x60 +#define PCI_DMA_C 0x90 +#define COM_DEC 0xe0 +#define LPC_EN 0xe6 +#define GEN2_DEC 0xec +/* + * Sets up the I/O range using the 82801CAM ISA bridge, 82801DBM LPC bridge or + * Intel 82801DB/DBL (ICH4/ICH4-L) LPC Interface Bridge. They all work the same way! + */ +static int __init preconfigure_through_82801(struct pci_dev *dev, + struct smsc_ircc_subsystem_configuration *conf) +{ + unsigned short tmpword; + int ret; + + IRDA_MESSAGE("Setting up the SMSC device via the 82801 controller.\n"); + pci_write_config_byte(dev, COM_DEC, 0x10); + + /* Enable LPC */ + pci_read_config_word(dev, LPC_EN, &tmpword); /* LPC_EN register */ + tmpword &= 0xfffd; /* mask bit 1 */ + tmpword |= 0x0001; /* set bit 0 : COMA addr range enable */ + pci_write_config_word(dev, LPC_EN, tmpword); + + /* Setup DMA */ + pci_write_config_word(dev, PCI_DMA_C, 0xc0c0); /* LPC I/F DMA on, channel 3 -- rtm (?? PCI DMA ?) */ + pci_write_config_word(dev, GEN2_DEC, 0x131); /* LPC I/F 2nd decode range */ + + /* Pre-configure chip */ + ret = preconfigure_smsc_chip(conf); + + /* Disable LPC */ + pci_read_config_word(dev, LPC_EN, &tmpword); /* LPC_EN register */ + tmpword &= 0xfffc; /* mask bit 1 and bit 0, COMA addr range disable */ + pci_write_config_word(dev, LPC_EN, tmpword); + return ret; +} + +static int __init preconfigure_through_ali(struct pci_dev *dev, + struct smsc_ircc_subsystem_configuration *conf) +{ + /* TODO: put in ALi 1533 configuration here. */ + IRDA_MESSAGE("SORRY: %s has an unsupported bridge controller (ALi): not pre-configured.\n", conf->name); + return -ENODEV; +} + +static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg, + unsigned short ircc_fir, + unsigned short ircc_sir, + unsigned char ircc_dma, + unsigned char ircc_irq) +{ + struct pci_dev *dev = NULL; + unsigned short ss_vendor = 0x0000; + unsigned short ss_device = 0x0000; + int ret = 0; + + dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); + + while (dev != NULL) { + struct smsc_ircc_subsystem_configuration *conf; + + /* + * Cache the subsystem vendor/device: some manufacturers fail to set + * this for all components, so we save it in case there is just + * 0x0000 0x0000 on the device we want to check. + */ + if (dev->subsystem_vendor != 0x0000U) { + ss_vendor = dev->subsystem_vendor; + ss_device = dev->subsystem_device; + } + conf = subsystem_configurations; + for( ; conf->subvendor; conf++) { + if(conf->vendor == dev->vendor && + conf->device == dev->device && + conf->subvendor == ss_vendor && /* Sometimes these are cached values */ + (conf->subdevice == ss_device || conf->subdevice == 0xffff)) { + struct smsc_ircc_subsystem_configuration tmpconf; + + memcpy(&tmpconf, conf, sizeof(struct smsc_ircc_subsystem_configuration)); + + /* Override the default values with anything passed in as parameter */ + if (ircc_cfg != 0) + tmpconf.cfg_base = ircc_cfg; + if (ircc_fir != 0) + tmpconf.fir_io = ircc_fir; + if (ircc_sir != 0) + tmpconf.sir_io = ircc_sir; + if (ircc_dma != 0xff) + tmpconf.fir_dma = ircc_dma; + if (ircc_irq != 0xff) + tmpconf.fir_irq = ircc_irq; + + IRDA_MESSAGE("Detected unconfigured %s SMSC IrDA chip, pre-configuring device.\n", conf->name); + if (conf->preconfigure) + ret = conf->preconfigure(dev, &tmpconf); + else + ret = -ENODEV; + } + } + dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); + } + + return ret; +} +#endif // CONFIG_PCI + /************************************************ * * Transceivers specific functions diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 75b35ad..66e74f7 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -87,6 +87,7 @@ static void write_msg(struct console *con, const char *msg, unsigned int len) } static struct console netconsole = { + .name = "netcon", .flags = CON_ENABLED | CON_PRINTBUFFER, .write = write_msg }; diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 0b53580..73e271e 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -497,21 +497,20 @@ static void tg3_write_mem(struct tg3 *tp, u32 off, u32 val) unsigned long flags; spin_lock_irqsave(&tp->indirect_lock, flags); - pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, off); - pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_DATA, val); + if (tp->tg3_flags & TG3_FLAG_SRAM_USE_CONFIG) { + pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, off); + pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_DATA, val); - /* Always leave this as zero. */ - pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, 0); - spin_unlock_irqrestore(&tp->indirect_lock, flags); -} + /* Always leave this as zero. */ + pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, 0); + } else { + tw32_f(TG3PCI_MEM_WIN_BASE_ADDR, off); + tw32_f(TG3PCI_MEM_WIN_DATA, val); -static void tg3_write_mem_fast(struct tg3 *tp, u32 off, u32 val) -{ - /* If no workaround is needed, write to mem space directly */ - if (tp->write32 != tg3_write_indirect_reg32) - tw32(NIC_SRAM_WIN_BASE + off, val); - else - tg3_write_mem(tp, off, val); + /* Always leave this as zero. */ + tw32_f(TG3PCI_MEM_WIN_BASE_ADDR, 0); + } + spin_unlock_irqrestore(&tp->indirect_lock, flags); } static void tg3_read_mem(struct tg3 *tp, u32 off, u32 *val) @@ -519,11 +518,19 @@ static void tg3_read_mem(struct tg3 *tp, u32 off, u32 *val) unsigned long flags; spin_lock_irqsave(&tp->indirect_lock, flags); - pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, off); - pci_read_config_dword(tp->pdev, TG3PCI_MEM_WIN_DATA, val); + if (tp->tg3_flags & TG3_FLAG_SRAM_USE_CONFIG) { + pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, off); + pci_read_config_dword(tp->pdev, TG3PCI_MEM_WIN_DATA, val); - /* Always leave this as zero. */ - pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, 0); + /* Always leave this as zero. */ + pci_write_config_dword(tp->pdev, TG3PCI_MEM_WIN_BASE_ADDR, 0); + } else { + tw32_f(TG3PCI_MEM_WIN_BASE_ADDR, off); + *val = tr32(TG3PCI_MEM_WIN_DATA); + + /* Always leave this as zero. */ + tw32_f(TG3PCI_MEM_WIN_BASE_ADDR, 0); + } spin_unlock_irqrestore(&tp->indirect_lock, flags); } @@ -1367,12 +1374,12 @@ static int tg3_set_power_state(struct tg3 *tp, pci_power_t state) } } + tg3_write_sig_post_reset(tp, RESET_KIND_SHUTDOWN); + /* Finally, set the new power state. */ pci_write_config_word(tp->pdev, pm + PCI_PM_CTRL, power_control); udelay(100); /* Delay after power state change */ - tg3_write_sig_post_reset(tp, RESET_KIND_SHUTDOWN); - return 0; } @@ -5828,10 +5835,14 @@ static int tg3_reset_hw(struct tg3 *tp) GRC_MODE_NO_TX_PHDR_CSUM | GRC_MODE_NO_RX_PHDR_CSUM); tp->grc_mode |= GRC_MODE_HOST_SENDBDS; - if (tp->tg3_flags & TG3_FLAG_NO_TX_PSEUDO_CSUM) - tp->grc_mode |= GRC_MODE_NO_TX_PHDR_CSUM; - if (tp->tg3_flags & TG3_FLAG_NO_RX_PSEUDO_CSUM) - tp->grc_mode |= GRC_MODE_NO_RX_PHDR_CSUM; + + /* Pseudo-header checksum is done by hardware logic and not + * the offload processers, so make the chip do the pseudo- + * header checksums on receive. For transmit it is more + * convenient to do the pseudo-header checksum in software + * as Linux does that on transmit for us in all cases. + */ + tp->grc_mode |= GRC_MODE_NO_TX_PHDR_CSUM; tw32(GRC_MODE, tp->grc_mode | @@ -6535,11 +6546,11 @@ static void tg3_timer(unsigned long __opaque) if (tp->tg3_flags & TG3_FLAG_ENABLE_ASF) { u32 val; - tg3_write_mem_fast(tp, NIC_SRAM_FW_CMD_MBOX, - FWCMD_NICDRV_ALIVE2); - tg3_write_mem_fast(tp, NIC_SRAM_FW_CMD_LEN_MBOX, 4); + tg3_write_mem(tp, NIC_SRAM_FW_CMD_MBOX, + FWCMD_NICDRV_ALIVE2); + tg3_write_mem(tp, NIC_SRAM_FW_CMD_LEN_MBOX, 4); /* 5 seconds timeout */ - tg3_write_mem_fast(tp, NIC_SRAM_FW_CMD_DATA_MBOX, 5); + tg3_write_mem(tp, NIC_SRAM_FW_CMD_DATA_MBOX, 5); val = tr32(GRC_RX_CPU_EVENT); val |= (1 << 14); tw32(GRC_RX_CPU_EVENT, val); @@ -8034,9 +8045,13 @@ static int tg3_test_nvram(struct tg3 *tp) for (i = 0; i < size; i++) csum8 += buf8[i]; - if (csum8 == 0) - return 0; - return -EIO; + if (csum8 == 0) { + err = 0; + goto out; + } + + err = -EIO; + goto out; } /* Bootstrap checksum at offset 0x10 */ @@ -9531,8 +9546,11 @@ static void __devinit tg3_get_eeprom_hw_cfg(struct tg3 *tp) tp->led_ctrl = LED_CTRL_MODE_PHY_1; /* Do not even try poking around in here on Sun parts. */ - if (tp->tg3_flags2 & TG3_FLG2_SUN_570X) + if (tp->tg3_flags2 & TG3_FLG2_SUN_570X) { + /* All SUN chips are built-in LOMs. */ + tp->tg3_flags |= TG3_FLAG_EEPROM_WRITE_PROT; return; + } tg3_read_mem(tp, NIC_SRAM_DATA_SIG, &val); if (val == NIC_SRAM_DATA_SIG_MAGIC) { @@ -9630,9 +9648,7 @@ static void __devinit tg3_get_eeprom_hw_cfg(struct tg3 *tp) tp->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL) tp->led_ctrl = LED_CTRL_MODE_PHY_2; - if ((GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5700) && - (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5701) && - (nic_cfg & NIC_SRAM_DATA_CFG_EEPROM_WP)) + if (nic_cfg & NIC_SRAM_DATA_CFG_EEPROM_WP) tp->tg3_flags |= TG3_FLAG_EEPROM_WRITE_PROT; if (nic_cfg & NIC_SRAM_DATA_CFG_ASF_ENABLE) { @@ -10257,6 +10273,13 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) pci_write_config_word(tp->pdev, PCI_COMMAND, pci_cmd); } + if (tp->write32 == tg3_write_indirect_reg32 || + ((tp->tg3_flags & TG3_FLAG_PCIX_MODE) && + (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5700 || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5701)) || + (tp->tg3_flags2 & TG3_FLG2_SUN_570X)) + tp->tg3_flags |= TG3_FLAG_SRAM_USE_CONFIG; + /* Get eeprom hw config before calling tg3_set_power_state(). * In particular, the TG3_FLAG_EEPROM_WRITE_PROT flag must be * determined before calling tg3_set_power_state() so that @@ -10299,15 +10322,6 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) if (tp->pci_chip_rev_id == CHIPREV_ID_5700_B0) tp->tg3_flags |= TG3_FLAG_BROKEN_CHECKSUMS; - /* Pseudo-header checksum is done by hardware logic and not - * the offload processers, so make the chip do the pseudo- - * header checksums on receive. For transmit it is more - * convenient to do the pseudo-header checksum in software - * as Linux does that on transmit for us in all cases. - */ - tp->tg3_flags |= TG3_FLAG_NO_TX_PSEUDO_CSUM; - tp->tg3_flags &= ~TG3_FLAG_NO_RX_PSEUDO_CSUM; - /* Derive initial jumbo mode from MTU assigned in * ether_setup() via the alloc_etherdev() call */ diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index c43cc32..8c8b987 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -2171,8 +2171,7 @@ struct tg3 { #define TG3_FLAG_PCIX_MODE 0x00020000 #define TG3_FLAG_PCI_HIGH_SPEED 0x00040000 #define TG3_FLAG_PCI_32BIT 0x00080000 -#define TG3_FLAG_NO_TX_PSEUDO_CSUM 0x00100000 -#define TG3_FLAG_NO_RX_PSEUDO_CSUM 0x00200000 +#define TG3_FLAG_SRAM_USE_CONFIG 0x00100000 #define TG3_FLAG_SERDES_WOL_CAP 0x00400000 #define TG3_FLAG_JUMBO_RING_ENABLE 0x00800000 #define TG3_FLAG_10_100_ONLY 0x01000000 diff --git a/drivers/scsi/ahci.c b/drivers/scsi/ahci.c index 1bd82c4..b4f8fb1 100644 --- a/drivers/scsi/ahci.c +++ b/drivers/scsi/ahci.c @@ -207,7 +207,6 @@ static struct scsi_host_template ahci_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = AHCI_MAX_SG, diff --git a/drivers/scsi/ata_piix.c b/drivers/scsi/ata_piix.c index 24e71b5..6dc8814 100644 --- a/drivers/scsi/ata_piix.c +++ b/drivers/scsi/ata_piix.c @@ -209,7 +209,6 @@ static struct scsi_host_template piix_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index ef57f25..dfcb96f 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -294,18 +294,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) if (sht->unchecked_isa_dma && privsize) gfp_mask |= __GFP_DMA; - /* Check to see if this host has any error handling facilities */ - if (!sht->eh_strategy_handler && !sht->eh_abort_handler && - !sht->eh_device_reset_handler && !sht->eh_bus_reset_handler && - !sht->eh_host_reset_handler) { - printk(KERN_ERR "ERROR: SCSI host `%s' has no error handling\n" - "ERROR: This is not a safe way to run your " - "SCSI host\n" - "ERROR: The error handling must be added to " - "this driver\n", sht->proc_name); - dump_stack(); - } - shost = kzalloc(sizeof(struct Scsi_Host) + privsize, gfp_mask); if (!shost) return NULL; diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c index e63c1ff..bd14720 100644 --- a/drivers/scsi/libata-core.c +++ b/drivers/scsi/libata-core.c @@ -4938,7 +4938,6 @@ EXPORT_SYMBOL_GPL(ata_busy_sleep); EXPORT_SYMBOL_GPL(ata_port_queue_task); EXPORT_SYMBOL_GPL(ata_scsi_ioctl); EXPORT_SYMBOL_GPL(ata_scsi_queuecmd); -EXPORT_SYMBOL_GPL(ata_scsi_error); EXPORT_SYMBOL_GPL(ata_scsi_slave_config); EXPORT_SYMBOL_GPL(ata_scsi_release); EXPORT_SYMBOL_GPL(ata_host_intr); diff --git a/drivers/scsi/libata-scsi.c b/drivers/scsi/libata-scsi.c index 53f5b0d..a0289ec 100644 --- a/drivers/scsi/libata-scsi.c +++ b/drivers/scsi/libata-scsi.c @@ -53,6 +53,7 @@ typedef unsigned int (*ata_xlat_func_t)(struct ata_queued_cmd *qc, const u8 *scsicmd); static struct ata_device * ata_scsi_find_dev(struct ata_port *ap, const struct scsi_device *scsidev); +static void ata_scsi_error(struct Scsi_Host *host); enum scsi_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd); #define RW_RECOVERY_MPAGE 0x1 @@ -99,6 +100,7 @@ static const u8 def_control_mpage[CONTROL_MPAGE_LEN] = { * It just needs the eh_timed_out hook. */ struct scsi_transport_template ata_scsi_transport_template = { + .eh_strategy_handler = ata_scsi_error, .eh_timed_out = ata_scsi_timed_out, }; @@ -772,12 +774,9 @@ enum scsi_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd) * * LOCKING: * Inherited from SCSI layer (none, can sleep) - * - * RETURNS: - * Zero. */ -int ata_scsi_error(struct Scsi_Host *host) +static void ata_scsi_error(struct Scsi_Host *host) { struct ata_port *ap; unsigned long flags; @@ -805,7 +804,6 @@ int ata_scsi_error(struct Scsi_Host *host) spin_unlock_irqrestore(&ap->host_set->lock, flags); DPRINTK("EXIT\n"); - return 0; } static void ata_eh_scsidone(struct scsi_cmnd *scmd) diff --git a/drivers/scsi/libata.h b/drivers/scsi/libata.h index 1c755b1..bac8cba 100644 --- a/drivers/scsi/libata.h +++ b/drivers/scsi/libata.h @@ -60,7 +60,6 @@ extern int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg); extern struct scsi_transport_template ata_scsi_transport_template; extern void ata_scsi_scan_host(struct ata_port *ap); -extern int ata_scsi_error(struct Scsi_Host *host); extern unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf, unsigned int buflen); diff --git a/drivers/scsi/pdc_adma.c b/drivers/scsi/pdc_adma.c index 3c85c4b..5cda16c 100644 --- a/drivers/scsi/pdc_adma.c +++ b/drivers/scsi/pdc_adma.c @@ -143,7 +143,6 @@ static struct scsi_host_template adma_ata_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_mv.c b/drivers/scsi/sata_mv.c index fa901fd..b64b077 100644 --- a/drivers/scsi/sata_mv.c +++ b/drivers/scsi/sata_mv.c @@ -378,7 +378,6 @@ static struct scsi_host_template mv_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = MV_USE_Q_DEPTH, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = MV_MAX_SG_CT / 2, diff --git a/drivers/scsi/sata_nv.c b/drivers/scsi/sata_nv.c index f77bf18..9f55308 100644 --- a/drivers/scsi/sata_nv.c +++ b/drivers/scsi/sata_nv.c @@ -201,7 +201,6 @@ static struct scsi_host_template nv_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_promise.c b/drivers/scsi/sata_promise.c index cc928c6..7eb67a6 100644 --- a/drivers/scsi/sata_promise.c +++ b/drivers/scsi/sata_promise.c @@ -111,7 +111,6 @@ static struct scsi_host_template pdc_ata_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_qstor.c b/drivers/scsi/sata_qstor.c index 9ffe1ef..886f344 100644 --- a/drivers/scsi/sata_qstor.c +++ b/drivers/scsi/sata_qstor.c @@ -132,7 +132,6 @@ static struct scsi_host_template qs_ata_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = QS_MAX_PRD, diff --git a/drivers/scsi/sata_sil.c b/drivers/scsi/sata_sil.c index 18c296c..1066272 100644 --- a/drivers/scsi/sata_sil.c +++ b/drivers/scsi/sata_sil.c @@ -146,7 +146,6 @@ static struct scsi_host_template sil_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_sil24.c b/drivers/scsi/sata_sil24.c index 068c98a..f7264fd 100644 --- a/drivers/scsi/sata_sil24.c +++ b/drivers/scsi/sata_sil24.c @@ -281,7 +281,6 @@ static struct scsi_host_template sil24_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_sis.c b/drivers/scsi/sata_sis.c index acc8439..728530d 100644 --- a/drivers/scsi/sata_sis.c +++ b/drivers/scsi/sata_sis.c @@ -87,7 +87,6 @@ static struct scsi_host_template sis_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = ATA_MAX_PRD, diff --git a/drivers/scsi/sata_svw.c b/drivers/scsi/sata_svw.c index 724f0ed..53b0d5c 100644 --- a/drivers/scsi/sata_svw.c +++ b/drivers/scsi/sata_svw.c @@ -290,7 +290,6 @@ static struct scsi_host_template k2_sata_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_sx4.c b/drivers/scsi/sata_sx4.c index ae70f60..4139ad4 100644 --- a/drivers/scsi/sata_sx4.c +++ b/drivers/scsi/sata_sx4.c @@ -182,7 +182,6 @@ static struct scsi_host_template pdc_sata_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_uli.c b/drivers/scsi/sata_uli.c index 7ac5a5f..38b52bd 100644 --- a/drivers/scsi/sata_uli.c +++ b/drivers/scsi/sata_uli.c @@ -81,7 +81,6 @@ static struct scsi_host_template uli_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_via.c b/drivers/scsi/sata_via.c index 791bf65..9e7ae4e 100644 --- a/drivers/scsi/sata_via.c +++ b/drivers/scsi/sata_via.c @@ -94,7 +94,6 @@ static struct scsi_host_template svia_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/sata_vsc.c b/drivers/scsi/sata_vsc.c index 836bbbb..8a29ce3 100644 --- a/drivers/scsi/sata_vsc.c +++ b/drivers/scsi/sata_vsc.c @@ -263,7 +263,6 @@ static struct scsi_host_template vsc_sata_sht = { .name = DRV_NAME, .ioctl = ata_scsi_ioctl, .queuecommand = ata_scsi_queuecmd, - .eh_strategy_handler = ata_scsi_error, .can_queue = ATA_DEF_QUEUE, .this_id = ATA_SHT_THIS_ID, .sg_tablesize = LIBATA_MAX_PRD, diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 5f0fdfb..1c75646 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1537,8 +1537,8 @@ int scsi_error_handler(void *data) * what we need to do to get it up and online again (if we can). * If we fail, we end up taking the thing offline. */ - if (shost->hostt->eh_strategy_handler) - shost->hostt->eh_strategy_handler(shost); + if (shost->transportt->eh_strategy_handler) + shost->transportt->eh_strategy_handler(shost); else scsi_unjam_host(shost); @@ -723,7 +723,12 @@ static int de_thread(struct task_struct *tsk) current->parent = current->real_parent = leader->real_parent; leader->parent = leader->real_parent = child_reaper; current->group_leader = current; - leader->group_leader = leader; + leader->group_leader = current; + + /* Reduce leader to a thread */ + detach_pid(leader, PIDTYPE_PGID); + detach_pid(leader, PIDTYPE_SID); + list_del_init(&leader->tasks); add_parent(current); add_parent(leader); diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h index ff9ac8d..288233f 100644 --- a/include/asm-i386/apic.h +++ b/include/asm-i386/apic.h @@ -139,6 +139,8 @@ void switch_ipi_to_APIC_timer(void *cpumask); extern int timer_over_8254; +extern int modern_apic(void); + #else /* !CONFIG_X86_LOCAL_APIC */ static inline void lapic_shutdown(void) { } diff --git a/include/asm-i386/e820.h b/include/asm-i386/e820.h index edf65be..ca82acb 100644 --- a/include/asm-i386/e820.h +++ b/include/asm-i386/e820.h @@ -35,6 +35,10 @@ struct e820map { }; extern struct e820map e820; + +extern int e820_all_mapped(unsigned long start, unsigned long end, + unsigned type); + #endif/*!__ASSEMBLY__*/ #endif/*__E820_HEADER*/ diff --git a/include/asm-i386/hpet.h b/include/asm-i386/hpet.h index 16ef9f9..7f1a8a6 100644 --- a/include/asm-i386/hpet.h +++ b/include/asm-i386/hpet.h @@ -89,6 +89,7 @@ * then 32 bit HPET counter wrapsaround in less than 0.5 sec. */ #define HPET_MIN_PERIOD (100000UL) +#define HPET_TICK_RATE (HZ * 100000UL) extern unsigned long hpet_tick; /* hpet clks count per tick */ extern unsigned long hpet_address; /* hpet memory map physical address */ diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h index 8dcc326..93b51df 100644 --- a/include/asm-x86_64/e820.h +++ b/include/asm-x86_64/e820.h @@ -47,7 +47,8 @@ extern void contig_e820_setup(void); extern unsigned long e820_end_of_ram(void); extern void e820_reserve_resources(void); extern void e820_print_map(char *who); -extern int e820_mapped(unsigned long start, unsigned long end, unsigned type); +extern int e820_any_mapped(unsigned long start, unsigned long end, unsigned type); +extern int e820_all_mapped(unsigned long start, unsigned long end, unsigned type); extern void e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end); extern void e820_setup_gap(void); diff --git a/include/asm-x86_64/hpet.h b/include/asm-x86_64/hpet.h index 08b75c1..18ff7ee 100644 --- a/include/asm-x86_64/hpet.h +++ b/include/asm-x86_64/hpet.h @@ -51,6 +51,8 @@ #define HPET_TN_ROUTE_SHIFT 9 +#define HPET_TICK_RATE (HZ * 100000UL) + extern int is_hpet_enabled(void); extern int hpet_rtc_timer_init(void); extern int oem_force_hpet_timer(void); diff --git a/include/asm-x86_64/ia32_unistd.h b/include/asm-x86_64/ia32_unistd.h index eeb2bcd..b4f4b17 100644 --- a/include/asm-x86_64/ia32_unistd.h +++ b/include/asm-x86_64/ia32_unistd.h @@ -317,6 +317,4 @@ #define __NR_ia32_ppoll 309 #define __NR_ia32_unshare 310 -#define IA32_NR_syscalls 315 /* must be > than biggest syscall! */ - #endif /* _ASM_X86_64_IA32_UNISTD_H_ */ diff --git a/include/asm-x86_64/mce.h b/include/asm-x86_64/mce.h index 5d298b7..7229785 100644 --- a/include/asm-x86_64/mce.h +++ b/include/asm-x86_64/mce.h @@ -70,6 +70,9 @@ struct mce_log { #define MCE_THRESHOLD_BASE MCE_EXTENDED_BANK + 1 /* MCE_AMD */ #define MCE_THRESHOLD_DRAM_ECC MCE_THRESHOLD_BASE + 4 +#ifdef __KERNEL__ +#include <asm/atomic.h> + void mce_log(struct mce *m); #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); @@ -87,4 +90,8 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) } #endif +extern atomic_t mce_entry; + +#endif + #endif diff --git a/include/asm-x86_64/numa.h b/include/asm-x86_64/numa.h index f6cbb4c..f0ba4d9 100644 --- a/include/asm-x86_64/numa.h +++ b/include/asm-x86_64/numa.h @@ -18,6 +18,8 @@ extern void numa_init_array(void); extern int numa_off; extern void numa_set_node(int cpu, int node); +extern void srat_reserve_add_area(int nodeid); +extern int hotadd_percent; extern unsigned char apicid_to_node[256]; #ifdef CONFIG_NUMA diff --git a/include/asm-x86_64/numnodes.h b/include/asm-x86_64/numnodes.h index 32be16b..5a1d506 100644 --- a/include/asm-x86_64/numnodes.h +++ b/include/asm-x86_64/numnodes.h @@ -5,8 +5,6 @@ #ifdef CONFIG_NUMA #define NODES_SHIFT 6 -#else -#define NODES_SHIFT 0 #endif #endif diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index de3eb8d..da2d107 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -45,6 +45,7 @@ extern unsigned long __init bootmem_bootmap_pages (unsigned long); extern unsigned long __init init_bootmem (unsigned long addr, unsigned long memend); extern void __init free_bootmem (unsigned long addr, unsigned long size); extern void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal); +extern void * __init __alloc_bootmem_nopanic (unsigned long size, unsigned long align, unsigned long goal); extern void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal); diff --git a/include/linux/init.h b/include/linux/init.h index ed0ac7c..93dcbe1 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -245,7 +245,8 @@ void __init parse_early_param(void); #define __cpuexitdata __exitdata #endif -#ifdef CONFIG_MEMORY_HOTPLUG +#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_ACPI_HOTPLUG_MEMORY) \ + || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE) #define __meminit #define __meminitdata #define __memexit diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 99905e1..0433769 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -36,6 +36,8 @@ /* LATCH is used in the interval timer and ftape setup. */ #define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ +#define LATCH_HPET ((HPET_TICK_RATE + HZ/2) / HZ) + /* Suppose we want to devide two numbers NOM and DEN: NOM/DEN, the we can * improve accuracy by shifting LSH bits, hence calculating: * (NOM << LSH) / DEN @@ -51,9 +53,13 @@ /* HZ is the requested value. ACTHZ is actual HZ ("<< 8" is for accuracy) */ #define ACTHZ (SH_DIV (CLOCK_TICK_RATE, LATCH, 8)) +#define ACTHZ_HPET (SH_DIV (HPET_TICK_RATE, LATCH_HPET, 8)) + /* TICK_NSEC is the time between ticks in nsec assuming real ACTHZ */ #define TICK_NSEC (SH_DIV (1000000UL * 1000, ACTHZ, 8)) +#define TICK_NSEC_HPET (SH_DIV(1000000UL * 1000, ACTHZ_HPET, 8)) + /* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ #define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) diff --git a/include/linux/libata.h b/include/linux/libata.h index 0d61357..b80d2e7 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -523,7 +523,6 @@ extern void ata_host_set_remove(struct ata_host_set *host_set); extern int ata_scsi_detect(struct scsi_host_template *sht); extern int ata_scsi_ioctl(struct scsi_device *dev, int cmd, void __user *arg); extern int ata_scsi_queuecmd(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd *)); -extern int ata_scsi_error(struct Scsi_Host *host); extern void ata_eh_qc_complete(struct ata_queued_cmd *qc); extern void ata_eh_qc_retry(struct ata_queued_cmd *qc); extern int ata_scsi_release(struct Scsi_Host *host); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 968b1aa..4ca3e6a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -58,8 +58,6 @@ extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* need some defines for these for archs that don't support it */ extern void online_page(struct page *page); /* VM interface that may be used by firmware interface */ -extern int add_memory(u64 start, u64 size); -extern int remove_memory(u64 start, u64 size); extern int online_pages(unsigned long, unsigned long); /* reasonably generic interface to expand the physical pages in a zone */ @@ -92,11 +90,6 @@ static inline int mhp_notimplemented(const char *func) return -ENOSYS; } -static inline int __add_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages) -{ - return mhp_notimplemented(__FUNCTION__); -} #endif /* ! CONFIG_MEMORY_HOTPLUG */ static inline int __remove_pages(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) @@ -105,4 +98,11 @@ static inline int __remove_pages(struct zone *zone, unsigned long start_pfn, dump_stack(); return -ENOSYS; } + +#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_ACPI_HOTPLUG_MEMORY) \ + || defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE) +extern int add_memory(u64 start, u64 size); +extern int remove_memory(u64 start, u64 size); +#endif + #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 6aa016f..1154684 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -229,10 +229,9 @@ struct page { unsigned long private; /* Mapping-private opaque data: * usually used for buffer_heads * if PagePrivate set; used for - * swp_entry_t if PageSwapCache. - * When page is free, this + * swp_entry_t if PageSwapCache; * indicates order in the buddy - * system. + * system if PG_buddy is set. */ struct address_space *mapping; /* If low bit clear, points to * inode address_space, or NULL. diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 412e52c..b31a9bc 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -110,6 +110,8 @@ struct nf_info /* Function to register/unregister hook points. */ int nf_register_hook(struct nf_hook_ops *reg); void nf_unregister_hook(struct nf_hook_ops *reg); +int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n); +void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n); /* Functions to register get/setsockopt ranges (non-inclusive). You need to check permissions yourself! */ @@ -281,16 +283,42 @@ extern void nf_invalidate_cache(int pf); Returns true or false. */ extern int skb_make_writable(struct sk_buff **pskb, unsigned int writable_len); -struct nf_queue_rerouter { - void (*save)(const struct sk_buff *skb, struct nf_info *info); - int (*reroute)(struct sk_buff **skb, const struct nf_info *info); - int rer_size; +struct nf_afinfo { + unsigned short family; + unsigned int (*checksum)(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); + void (*saveroute)(const struct sk_buff *skb, + struct nf_info *info); + int (*reroute)(struct sk_buff **skb, + const struct nf_info *info); + int route_key_size; }; -#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info)) +extern struct nf_afinfo *nf_afinfo[]; +static inline struct nf_afinfo *nf_get_afinfo(unsigned short family) +{ + return rcu_dereference(nf_afinfo[family]); +} + +static inline unsigned int +nf_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, + u_int8_t protocol, unsigned short family) +{ + struct nf_afinfo *afinfo; + unsigned int csum = 0; + + rcu_read_lock(); + afinfo = nf_get_afinfo(family); + if (afinfo) + csum = afinfo->checksum(skb, hook, dataoff, protocol); + rcu_read_unlock(); + return csum; +} -extern int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer); -extern int nf_unregister_queue_rerouter(int pf); +extern int nf_register_afinfo(struct nf_afinfo *afinfo); +extern void nf_unregister_afinfo(struct nf_afinfo *afinfo); + +#define nf_info_reroute(x) ((void *)x + sizeof(struct nf_info)) #include <net/flow.h> extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 43c09d7..85301c5 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -80,6 +80,8 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff **pskb); extern int ip_xfrm_me_harder(struct sk_buff **pskb); +extern unsigned int nf_ip_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); #endif /*__KERNEL__*/ #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/include/linux/netfilter_ipv4/ip_conntrack_h323.h b/include/linux/netfilter_ipv4/ip_conntrack_h323.h index 0987cea..eace86b 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack_h323.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_h323.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include <linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h> + #define RAS_PORT 1719 #define Q931_PORT 1720 #define H323_RTP_CHANNEL_MAX 4 /* Audio, video, FAX and other */ @@ -25,6 +27,56 @@ struct ip_ct_h323_master { }; }; +struct ip_conntrack_expect; + +extern int get_h225_addr(unsigned char *data, TransportAddress * addr, + u_int32_t * ip, u_int16_t * port); +extern void ip_conntrack_h245_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this); +extern void ip_conntrack_q931_expect(struct ip_conntrack *new, + struct ip_conntrack_expect *this); +extern int (*set_h245_addr_hook) (struct sk_buff ** pskb, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int32_t ip, u_int16_t port); +extern int (*set_h225_addr_hook) (struct sk_buff ** pskb, + unsigned char **data, int dataoff, + TransportAddress * addr, + u_int32_t ip, u_int16_t port); +extern int (*set_sig_addr_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count); +extern int (*set_ras_addr_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, + TransportAddress * addr, int count); +extern int (*nat_rtp_rtcp_hook) (struct sk_buff ** pskb, + struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, + u_int16_t port, u_int16_t rtp_port, + struct ip_conntrack_expect * rtp_exp, + struct ip_conntrack_expect * rtcp_exp); +extern int (*nat_t120_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + H245_TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); +extern int (*nat_h245_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, int dataoff, + TransportAddress * addr, u_int16_t port, + struct ip_conntrack_expect * exp); +extern int (*nat_q931_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, + enum ip_conntrack_info ctinfo, + unsigned char **data, TransportAddress * addr, + int idx, u_int16_t port, + struct ip_conntrack_expect * exp); + #endif #endif diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.h b/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h index 0bd8280..0bd8280 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_types.h b/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_types.h index cc98f7a..cc98f7a 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323_types.h +++ b/include/linux/netfilter_ipv4/ip_conntrack_helper_h323_types.h diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 14f2bd0..52a7b9e 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -73,6 +73,9 @@ enum nf_ip6_hook_priorities { }; #ifdef CONFIG_NETFILTER +extern unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol); + extern int ipv6_netfilter_init(void); extern void ipv6_netfilter_fini(void); #else /* CONFIG_NETFILTER */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 9ea629c..547aac7 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -74,7 +74,9 @@ #define PG_mappedtodisk 16 /* Has blocks allocated on-disk */ #define PG_reclaim 17 /* To be reclaimed asap */ #define PG_nosave_free 18 /* Free, should not be written */ -#define PG_uncached 19 /* Page has been mapped as uncached */ +#define PG_buddy 19 /* Page is free, on buddy lists */ + +#define PG_uncached 20 /* Page has been mapped as uncached */ /* * Global page accounting. One instance per CPU. Only unsigned longs are @@ -317,6 +319,10 @@ extern void __mod_page_state_offset(unsigned long offset, unsigned long delta); #define SetPageNosaveFree(page) set_bit(PG_nosave_free, &(page)->flags) #define ClearPageNosaveFree(page) clear_bit(PG_nosave_free, &(page)->flags) +#define PageBuddy(page) test_bit(PG_buddy, &(page)->flags) +#define __SetPageBuddy(page) __set_bit(PG_buddy, &(page)->flags) +#define __ClearPageBuddy(page) __clear_bit(PG_buddy, &(page)->flags) + #define PageMappedToDisk(page) test_bit(PG_mappedtodisk, &(page)->flags) #define SetPageMappedToDisk(page) set_bit(PG_mappedtodisk, &(page)->flags) #define ClearPageMappedToDisk(page) clear_bit(PG_mappedtodisk, &(page)->flags) diff --git a/include/linux/sched.h b/include/linux/sched.h index 541f482..a3e4f6b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1203,7 +1203,8 @@ extern void wait_task_inactive(task_t * p); #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) -#define thread_group_leader(p) (p->pid == p->tgid) +/* de_thread depends on thread_group_leader not being a pid based check */ +#define thread_group_leader(p) (p == p->group_leader) static inline task_t *next_thread(task_t *p) { diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 25f708f..59f0c83 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -48,31 +48,7 @@ static inline int inet6_sk_ehashfn(const struct sock *sk) return inet6_ehashfn(laddr, lport, faddr, fport); } -static inline void __inet6_hash(struct inet_hashinfo *hashinfo, - struct sock *sk) -{ - struct hlist_head *list; - rwlock_t *lock; - - BUG_TRAP(sk_unhashed(sk)); - - if (sk->sk_state == TCP_LISTEN) { - list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &hashinfo->lhash_lock; - inet_listen_wlock(hashinfo); - } else { - unsigned int hash; - sk->sk_hash = hash = inet6_sk_ehashfn(sk); - hash &= (hashinfo->ehash_size - 1); - list = &hashinfo->ehash[hash].chain; - lock = &hashinfo->ehash[hash].lock; - write_lock(lock); - } - - __sk_add_node(sk, list); - sock_prot_inc_use(sk->sk_prot); - write_unlock(lock); -} +extern void __inet6_hash(struct inet_hashinfo *hashinfo, struct sock *sk); /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so @@ -80,52 +56,12 @@ static inline void __inet6_hash(struct inet_hashinfo *hashinfo, * * The sockhash lock must be held as a reader here. */ -static inline struct sock * - __inet6_lookup_established(struct inet_hashinfo *hashinfo, +extern struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const u16 sport, const struct in6_addr *daddr, const u16 hnum, - const int dif) -{ - struct sock *sk; - const struct hlist_node *node; - const __u32 ports = INET_COMBINED_PORTS(sport, hnum); - /* Optimize here for direct hit, only listening connections can - * have wildcards anyways. - */ - unsigned int hash = inet6_ehashfn(daddr, hnum, saddr, sport); - struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); - - prefetch(head->chain.first); - read_lock(&head->lock); - sk_for_each(sk, node, &head->chain) { - /* For IPV6 do the cheaper port and family tests first. */ - if (INET6_MATCH(sk, hash, saddr, daddr, ports, dif)) - goto hit; /* You sunk my battleship! */ - } - /* Must check for a TIME_WAIT'er before going to listener hash. */ - sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) { - const struct inet_timewait_sock *tw = inet_twsk(sk); - - if(*((__u32 *)&(tw->tw_dport)) == ports && - sk->sk_family == PF_INET6) { - const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); - - if (ipv6_addr_equal(&tw6->tw_v6_daddr, saddr) && - ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr) && - (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif)) - goto hit; - } - } - read_unlock(&head->lock); - return NULL; - -hit: - sock_hold(sk); - read_unlock(&head->lock); - return sk; -} + const int dif); extern struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, diff --git a/include/net/ip.h b/include/net/ip.h index 8fe6156..3d2e5ca 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -95,6 +95,7 @@ extern int ip_local_deliver(struct sk_buff *skb); extern int ip_mr_input(struct sk_buff *skb); extern int ip_output(struct sk_buff *skb); extern int ip_mc_output(struct sk_buff *skb); +extern int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); extern int ip_do_nat(struct sk_buff *skb); extern void ip_send_check(struct iphdr *ip); extern int ip_queue_xmit(struct sk_buff *skb, int ipfragok); diff --git a/include/net/x25device.h b/include/net/x25device.h index 1a31837..1d10c87 100644 --- a/include/net/x25device.h +++ b/include/net/x25device.h @@ -8,6 +8,7 @@ static inline __be16 x25_type_trans(struct sk_buff *skb, struct net_device *dev) { skb->mac.raw = skb->data; + skb->dev = dev; skb->pkt_type = PACKET_HOST; return htons(ETH_P_X25); diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h index dc6862d..de6ce54 100644 --- a/include/scsi/scsi_host.h +++ b/include/scsi/scsi_host.h @@ -140,7 +140,6 @@ struct scsi_host_template { * * Status: REQUIRED (at least one of them) */ - int (* eh_strategy_handler)(struct Scsi_Host *); int (* eh_abort_handler)(struct scsi_cmnd *); int (* eh_device_reset_handler)(struct scsi_cmnd *); int (* eh_bus_reset_handler)(struct scsi_cmnd *); diff --git a/include/scsi/scsi_transport.h b/include/scsi/scsi_transport.h index b3657f1..cca1d49 100644 --- a/include/scsi/scsi_transport.h +++ b/include/scsi/scsi_transport.h @@ -50,6 +50,11 @@ struct scsi_transport_template { unsigned int create_work_queue : 1; /* + * Allows a transport to override the default error handler. + */ + void (* eh_strategy_handler)(struct Scsi_Host *); + + /* * This is an optional routine that allows the transport to become * involved when a scsi io timer fires. The return value tells the * timer routine how to finish the io timeout handling: diff --git a/kernel/timer.c b/kernel/timer.c index c3a874f..471ab87 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1455,7 +1455,7 @@ static void time_interpolator_update(long delta_nsec) */ if (jiffies % INTERPOLATOR_ADJUST == 0) { - if (time_interpolator->skips == 0 && time_interpolator->offset > TICK_NSEC) + if (time_interpolator->skips == 0 && time_interpolator->offset > tick_nsec) time_interpolator->nsec_per_cyc--; if (time_interpolator->ns_skipped > INTERPOLATOR_MAX_SKIP && time_interpolator->offset == 0) time_interpolator->nsec_per_cyc++; diff --git a/mm/bootmem.c b/mm/bootmem.c index d3e3bd2..d213fed 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -401,7 +401,7 @@ unsigned long __init free_all_bootmem (void) return(free_all_bootmem_core(NODE_DATA(0))); } -void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal) +void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, unsigned long goal) { bootmem_data_t *bdata; void *ptr; @@ -409,7 +409,14 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned list_for_each_entry(bdata, &bdata_list, list) if ((ptr = __alloc_bootmem_core(bdata, size, align, goal, 0))) return(ptr); + return NULL; +} +void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal) +{ + void *mem = __alloc_bootmem_nopanic(size,align,goal); + if (mem) + return mem; /* * Whoops, we cannot satisfy the allocation request. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index dc523a1..b8165e0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -151,7 +151,8 @@ static void bad_page(struct page *page) 1 << PG_reclaim | 1 << PG_slab | 1 << PG_swapcache | - 1 << PG_writeback ); + 1 << PG_writeback | + 1 << PG_buddy ); set_page_count(page, 0); reset_page_mapcount(page); page->mapping = NULL; @@ -236,12 +237,12 @@ static inline unsigned long page_order(struct page *page) { static inline void set_page_order(struct page *page, int order) { set_page_private(page, order); - __SetPagePrivate(page); + __SetPageBuddy(page); } static inline void rmv_page_order(struct page *page) { - __ClearPagePrivate(page); + __ClearPageBuddy(page); set_page_private(page, 0); } @@ -280,11 +281,13 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * This function checks whether a page is free && is the buddy * we can do coalesce a page and its buddy if * (a) the buddy is not in a hole && - * (b) the buddy is free && - * (c) the buddy is on the buddy system && - * (d) a page and its buddy have the same order. - * for recording page's order, we use page_private(page) and PG_private. + * (b) the buddy is in the buddy system && + * (c) a page and its buddy have the same order. + * + * For recording whether a page is in the buddy system, we use PG_buddy. + * Setting, clearing, and testing PG_buddy is serialized by zone->lock. * + * For recording page's order, we use page_private(page). */ static inline int page_is_buddy(struct page *page, int order) { @@ -293,10 +296,10 @@ static inline int page_is_buddy(struct page *page, int order) return 0; #endif - if (PagePrivate(page) && - (page_order(page) == order) && - page_count(page) == 0) + if (PageBuddy(page) && page_order(page) == order) { + BUG_ON(page_count(page) != 0); return 1; + } return 0; } @@ -313,7 +316,7 @@ static inline int page_is_buddy(struct page *page, int order) * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * At each level, we keep a list of pages, which are heads of continuous - * free pages of length of (1 << order) and marked with PG_Private.Page's + * free pages of length of (1 << order) and marked with PG_buddy. Page's * order is recorded in page_private(page) field. * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were @@ -376,7 +379,8 @@ static inline int free_pages_check(struct page *page) 1 << PG_slab | 1 << PG_swapcache | 1 << PG_writeback | - 1 << PG_reserved )))) + 1 << PG_reserved | + 1 << PG_buddy )))) bad_page(page); if (PageDirty(page)) __ClearPageDirty(page); @@ -524,7 +528,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) 1 << PG_slab | 1 << PG_swapcache | 1 << PG_writeback | - 1 << PG_reserved )))) + 1 << PG_reserved | + 1 << PG_buddy )))) bad_page(page); /* diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 6b61323..0c2d13a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -255,7 +255,7 @@ static inline int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) } if ((err = hci_send_sco(conn->hcon, skb)) < 0) - goto fail; + return err; return count; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index f29450b..3da9264 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -765,6 +765,15 @@ out: return NF_STOLEN; } +static int br_nf_dev_queue_xmit(struct sk_buff *skb) +{ + if (skb->protocol == htons(ETH_P_IP) && + skb->len > skb->dev->mtu && + !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size)) + return ip_fragment(skb, br_dev_queue_push_xmit); + else + return br_dev_queue_push_xmit(skb); +} /* PF_BRIDGE/POST_ROUTING ********************************************/ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, @@ -824,7 +833,7 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff **pskb, realoutdev = nf_bridge->netoutdev; #endif NF_HOOK(pf, NF_IP_POST_ROUTING, skb, NULL, realoutdev, - br_dev_queue_push_xmit); + br_nf_dev_queue_xmit); return NF_STOLEN; @@ -869,7 +878,7 @@ static unsigned int ip_sabotage_out(unsigned int hook, struct sk_buff **pskb, if ((out->hard_start_xmit == br_dev_xmit && okfn != br_nf_forward_finish && - okfn != br_nf_local_out_finish && okfn != br_dev_queue_push_xmit) + okfn != br_nf_local_out_finish && okfn != br_nf_dev_queue_xmit) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) || ((out->priv_flags & IFF_802_1Q_VLAN) && VLAN_DEV_INFO(out)->real_dev->hard_start_xmit == br_dev_xmit) diff --git a/net/core/dev.c b/net/core/dev.c index 434220d..2731570 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3042,11 +3042,11 @@ void netdev_run_todo(void) switch(dev->reg_state) { case NETREG_REGISTERING: + dev->reg_state = NETREG_REGISTERED; err = netdev_register_sysfs(dev); if (err) printk(KERN_ERR "%s: failed sysfs registration (%d)\n", dev->name, err); - dev->reg_state = NETREG_REGISTERED; break; case NETREG_UNREGISTERING: @@ -3100,12 +3100,11 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name, alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; alloc_size += sizeof_priv + NETDEV_ALIGN_CONST; - p = kmalloc(alloc_size, GFP_KERNEL); + p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { printk(KERN_ERR "alloc_dev: Unable to allocate device.\n"); return NULL; } - memset(p, 0, alloc_size); dev = (struct net_device *) (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); diff --git a/net/core/dv.c b/net/core/dv.c index cf58140..29ee77f1 100644 --- a/net/core/dv.c +++ b/net/core/dv.c @@ -55,15 +55,12 @@ int alloc_divert_blk(struct net_device *dev) dev->divert = NULL; if (dev->type == ARPHRD_ETHER) { - dev->divert = (struct divert_blk *) - kmalloc(alloc_size, GFP_KERNEL); + dev->divert = kzalloc(alloc_size, GFP_KERNEL); if (dev->divert == NULL) { printk(KERN_INFO "divert: unable to allocate divert_blk for %s\n", dev->name); return -ENOMEM; } - - memset(dev->divert, 0, sizeof(struct divert_blk)); dev_hold(dev); } diff --git a/net/core/flow.c b/net/core/flow.c index 55789f8..885a2f6 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -318,12 +318,10 @@ static void __devinit flow_cache_cpu_prepare(int cpu) /* NOTHING */; flow_table(cpu) = (struct flow_cache_entry **) - __get_free_pages(GFP_KERNEL, order); + __get_free_pages(GFP_KERNEL|__GFP_ZERO, order); if (!flow_table(cpu)) panic("NET: failed to allocate flow cache order %lu\n", order); - memset(flow_table(cpu), 0, PAGE_SIZE << order); - flow_hash_rnd_recalc(cpu) = 1; flow_count(cpu) = 0; diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index b07c029..3cad026 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -159,11 +159,10 @@ int gen_new_estimator(struct gnet_stats_basic *bstats, if (parm->interval < -2 || parm->interval > 3) return -EINVAL; - est = kmalloc(sizeof(*est), GFP_KERNEL); + est = kzalloc(sizeof(*est), GFP_KERNEL); if (est == NULL) return -ENOBUFS; - memset(est, 0, sizeof(*est)); est->interval = parm->interval + 2; est->bstats = bstats; est->rate_est = rate_est; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 0c86668..2ec8693 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -284,14 +284,11 @@ static struct neighbour **neigh_hash_alloc(unsigned int entries) struct neighbour **ret; if (size <= PAGE_SIZE) { - ret = kmalloc(size, GFP_ATOMIC); + ret = kzalloc(size, GFP_ATOMIC); } else { ret = (struct neighbour **) - __get_free_pages(GFP_ATOMIC, get_order(size)); + __get_free_pages(GFP_ATOMIC|__GFP_ZERO, get_order(size)); } - if (ret) - memset(ret, 0, size); - return ret; } @@ -1089,8 +1086,7 @@ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, if (hh->hh_type == protocol) break; - if (!hh && (hh = kmalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) { - memset(hh, 0, sizeof(struct hh_cache)); + if (!hh && (hh = kzalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) { rwlock_init(&hh->hh_lock); hh->hh_type = protocol; atomic_set(&hh->hh_refcnt, 0); @@ -1366,13 +1362,11 @@ void neigh_table_init(struct neigh_table *tbl) tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); - tbl->phash_buckets = kmalloc(phsize, GFP_KERNEL); + tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); if (!tbl->hash_buckets || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); - memset(tbl->phash_buckets, 0, phsize); - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); rwlock_init(&tbl->lock); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 21b6846..c12990c9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -165,7 +165,7 @@ static ssize_t show_operstate(struct class_device *dev, char *buf) operstate = IF_OPER_DOWN; read_unlock(&dev_base_lock); - if (operstate >= sizeof(operstates)) + if (operstate >= ARRAY_SIZE(operstates)) return -EINVAL; /* should not happen */ return sprintf(buf, "%s\n", operstates[operstate]); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 1e44eda..79ebd75 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -38,13 +38,11 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, { const int lopt_size = sizeof(struct listen_sock) + nr_table_entries * sizeof(struct request_sock *); - struct listen_sock *lopt = kmalloc(lopt_size, GFP_KERNEL); + struct listen_sock *lopt = kzalloc(lopt_size, GFP_KERNEL); if (lopt == NULL) return -ENOMEM; - memset(lopt, 0, lopt_size); - for (lopt->max_qlen_log = 6; (1 << lopt->max_qlen_log) < sysctl_max_syn_backlog; lopt->max_qlen_log++); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index ccd3efc..95a639f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -50,7 +50,7 @@ * Patrick McHardy <kaber@trash.net> */ -#define VERSION "0.406" +#define VERSION "0.407" #include <linux/config.h> #include <asm/uaccess.h> @@ -314,11 +314,6 @@ static void __leaf_free_rcu(struct rcu_head *head) kfree(container_of(head, struct leaf, rcu)); } -static inline void free_leaf(struct leaf *leaf) -{ - call_rcu(&leaf->rcu, __leaf_free_rcu); -} - static void __leaf_info_free_rcu(struct rcu_head *head) { kfree(container_of(head, struct leaf_info, rcu)); @@ -357,7 +352,12 @@ static void __tnode_free_rcu(struct rcu_head *head) static inline void tnode_free(struct tnode *tn) { - call_rcu(&tn->rcu, __tnode_free_rcu); + if(IS_LEAF(tn)) { + struct leaf *l = (struct leaf *) tn; + call_rcu_bh(&l->rcu, __leaf_free_rcu); + } + else + call_rcu(&tn->rcu, __tnode_free_rcu); } static struct leaf *leaf_new(void) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 2a8adda..da734c4 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -304,13 +304,17 @@ out: /* Creation primitives. */ -static struct ipq *ip_frag_intern(unsigned int hash, struct ipq *qp_in) +static struct ipq *ip_frag_intern(struct ipq *qp_in) { struct ipq *qp; #ifdef CONFIG_SMP struct hlist_node *n; #endif + unsigned int hash; + write_lock(&ipfrag_lock); + hash = ipqhashfn(qp_in->id, qp_in->saddr, qp_in->daddr, + qp_in->protocol); #ifdef CONFIG_SMP /* With SMP race we have to recheck hash table, because * such entry could be created on other cpu, while we @@ -345,7 +349,7 @@ static struct ipq *ip_frag_intern(unsigned int hash, struct ipq *qp_in) } /* Add an entry to the 'ipq' queue for a newly received IP datagram. */ -static struct ipq *ip_frag_create(unsigned hash, struct iphdr *iph, u32 user) +static struct ipq *ip_frag_create(struct iphdr *iph, u32 user) { struct ipq *qp; @@ -371,7 +375,7 @@ static struct ipq *ip_frag_create(unsigned hash, struct iphdr *iph, u32 user) spin_lock_init(&qp->lock); atomic_set(&qp->refcnt, 1); - return ip_frag_intern(hash, qp); + return ip_frag_intern(qp); out_nomem: LIMIT_NETDEBUG(KERN_ERR "ip_frag_create: no memory left !\n"); @@ -387,11 +391,12 @@ static inline struct ipq *ip_find(struct iphdr *iph, u32 user) __u32 saddr = iph->saddr; __u32 daddr = iph->daddr; __u8 protocol = iph->protocol; - unsigned int hash = ipqhashfn(id, saddr, daddr, protocol); + unsigned int hash; struct ipq *qp; struct hlist_node *n; read_lock(&ipfrag_lock); + hash = ipqhashfn(id, saddr, daddr, protocol); hlist_for_each_entry(qp, n, &ipq_hash[hash], list) { if(qp->id == id && qp->saddr == saddr && @@ -405,7 +410,7 @@ static inline struct ipq *ip_find(struct iphdr *iph, u32 user) } read_unlock(&ipfrag_lock); - return ip_frag_create(hash, iph, user); + return ip_frag_create(iph, user); } /* Is the fragment too far ahead to be part of ipq? */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9981dcd..ab99beb 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -656,7 +656,7 @@ static int ipgre_rcv(struct sk_buff *skb) read_unlock(&ipgre_lock); return(0); } - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: read_unlock(&ipgre_lock); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f75ff1d..8dcba38 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -86,8 +86,6 @@ int sysctl_ip_default_ttl = IPDEFTTL; -static int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)); - /* Generate a checksum for an outgoing IP datagram. */ __inline__ void ip_send_check(struct iphdr *iph) { @@ -421,7 +419,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) * single device frame, and queue such a frame for sending. */ -static int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) +int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) { struct iphdr *iph; int raw = 0; @@ -673,6 +671,8 @@ fail: return err; } +EXPORT_SYMBOL(ip_fragment); + int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index eef07b0..ea398ee 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -474,9 +474,6 @@ static int ipip_rcv(struct sk_buff *skb) struct iphdr *iph; struct ip_tunnel *tunnel; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - iph = skb->nh.iph; read_lock(&ipip_lock); @@ -508,7 +505,6 @@ static int ipip_rcv(struct sk_buff *skb) } read_unlock(&ipip_lock); -out: return -1; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index b5ad9ac..6a9e34b 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -133,7 +133,7 @@ struct ip_rt_info { u_int8_t tos; }; -static void queue_save(const struct sk_buff *skb, struct nf_info *info) +static void nf_ip_saveroute(const struct sk_buff *skb, struct nf_info *info) { struct ip_rt_info *rt_info = nf_info_reroute(info); @@ -146,7 +146,7 @@ static void queue_save(const struct sk_buff *skb, struct nf_info *info) } } -static int queue_reroute(struct sk_buff **pskb, const struct nf_info *info) +static int nf_ip_reroute(struct sk_buff **pskb, const struct nf_info *info) { const struct ip_rt_info *rt_info = nf_info_reroute(info); @@ -161,20 +161,54 @@ static int queue_reroute(struct sk_buff **pskb, const struct nf_info *info) return 0; } -static struct nf_queue_rerouter ip_reroute = { - .rer_size = sizeof(struct ip_rt_info), - .save = queue_save, - .reroute = queue_reroute, +unsigned int nf_ip_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol) +{ + struct iphdr *iph = skb->nh.iph; + unsigned int csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_HW: + if (hook != NF_IP_PRE_ROUTING && hook != NF_IP_LOCAL_IN) + break; + if ((protocol == 0 && !(u16)csum_fold(skb->csum)) || + !csum_tcpudp_magic(iph->saddr, iph->daddr, + skb->len - dataoff, protocol, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + /* fall through */ + case CHECKSUM_NONE: + if (protocol == 0) + skb->csum = 0; + else + skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb->len - dataoff, + protocol, 0); + csum = __skb_checksum_complete(skb); + } + return csum; +} + +EXPORT_SYMBOL(nf_ip_checksum); + +static struct nf_afinfo nf_ip_afinfo = { + .family = AF_INET, + .checksum = nf_ip_checksum, + .saveroute = nf_ip_saveroute, + .reroute = nf_ip_reroute, + .route_key_size = sizeof(struct ip_rt_info), }; static int ipv4_netfilter_init(void) { - return nf_register_queue_rerouter(PF_INET, &ip_reroute); + return nf_register_afinfo(&nf_ip_afinfo); } static void ipv4_netfilter_fini(void) { - nf_unregister_queue_rerouter(PF_INET); + nf_unregister_afinfo(&nf_ip_afinfo); } module_init(ipv4_netfilter_init); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 77855cc..c60fd5c 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -69,6 +69,7 @@ config IP_NF_CONNTRACK_NETLINK tristate 'Connection tracking netlink interface (EXPERIMENTAL)' depends on EXPERIMENTAL && IP_NF_CONNTRACK && NETFILTER_NETLINK depends on IP_NF_CONNTRACK!=y || NETFILTER_NETLINK!=m + depends on IP_NF_NAT=n || IP_NF_NAT help This option enables support for a netlink-based userspace interface diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index d0d379c..d7c472f 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -181,33 +181,26 @@ static struct nf_hook_ops arpt_ops[] = { static int __init arptable_filter_init(void) { - int ret, i; + int ret; /* Register table */ ret = arpt_register_table(&packet_filter, &initial_table.repl); if (ret < 0) return ret; - for (i = 0; i < ARRAY_SIZE(arpt_ops); i++) - if ((ret = nf_register_hook(&arpt_ops[i])) < 0) - goto cleanup_hooks; + ret = nf_register_hooks(arpt_ops, ARRAY_SIZE(arpt_ops)); + if (ret < 0) + goto cleanup_table; return ret; -cleanup_hooks: - while (--i >= 0) - nf_unregister_hook(&arpt_ops[i]); - +cleanup_table: arpt_unregister_table(&packet_filter); return ret; } static void __exit arptable_filter_fini(void) { - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(arpt_ops); i++) - nf_unregister_hook(&arpt_ops[i]); - + nf_unregister_hooks(arpt_ops, ARRAY_SIZE(arpt_ops)); arpt_unregister_table(&packet_filter); } diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323.c b/net/ipv4/netfilter/ip_conntrack_helper_h323.c index daeb139..2c2fb70 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323.c @@ -9,37 +9,6 @@ * Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> * * For more information, please see http://nath323.sourceforge.net/ - * - * Changes: - * 2006-02-01 - initial version 0.1 - * - * 2006-02-20 - version 0.2 - * 1. Changed source format to follow kernel conventions - * 2. Deleted some unnecessary structures - * 3. Minor fixes - * - * 2006-03-10 - version 0.3 - * 1. Added support for multiple TPKTs in one packet (suggested by - * Patrick McHardy) - * 2. Avoid excessive stack usage (based on Patrick McHardy's patch) - * 3. Added support for non-linear skb (based on Patrick McHardy's patch) - * 4. Fixed missing H.245 module owner (Patrick McHardy) - * 5. Avoid long RAS expectation chains (Patrick McHardy) - * 6. Fixed incorrect __exit attribute (Patrick McHardy) - * 7. Eliminated unnecessary return code - * 8. Fixed incorrect use of NAT data from conntrack code (suggested by - * Patrick McHardy) - * 9. Fixed TTL calculation error in RCF - * 10. Added TTL support in RRQ - * 11. Better support for separate TPKT header and data - * - * 2006-03-15 - version 0.4 - * 1. Added support for T.120 channels - * 2. Added parameter gkrouted_only (suggested by Patrick McHardy) - * 3. Splitted ASN.1 code and data (suggested by Patrick McHardy) - * 4. Sort ASN.1 data to avoid forwarding declarations (suggested by - * Patrick McHardy) - * 5. Reset next TPKT data length in get_tpkt_data() */ #include <linux/config.h> @@ -54,8 +23,6 @@ #include <linux/netfilter_ipv4/ip_conntrack_h323.h> #include <linux/moduleparam.h> -#include "ip_conntrack_helper_h323_asn1.h" - #if 0 #define DEBUGP printk #else @@ -63,6 +30,10 @@ #endif /* Parameters */ +static unsigned int default_rrq_ttl = 300; +module_param(default_rrq_ttl, uint, 0600); +MODULE_PARM_DESC(default_rrq_ttl, "use this TTL if it's missing in RRQ"); + static int gkrouted_only = 1; module_param(gkrouted_only, int, 0600); MODULE_PARM_DESC(gkrouted_only, "only accept calls from gatekeeper"); @@ -222,8 +193,8 @@ static int get_tpkt_data(struct sk_buff **pskb, struct ip_conntrack *ct, } /****************************************************************************/ -int get_h245_addr(unsigned char *data, H245_TransportAddress * addr, - u_int32_t * ip, u_int16_t * port) +static int get_h245_addr(unsigned char *data, H245_TransportAddress * addr, + u_int32_t * ip, u_int16_t * port) { unsigned char *p; @@ -1302,7 +1273,7 @@ static int process_rrq(struct sk_buff **pskb, struct ip_conntrack *ct, DEBUGP("ip_ct_ras: RRQ TTL = %u seconds\n", rrq->timeToLive); info->timeout = rrq->timeToLive; } else - info->timeout = 0; + info->timeout = default_rrq_ttl; return 0; } @@ -1713,18 +1684,17 @@ static int __init init(void) module_init(init); module_exit(fini); -EXPORT_SYMBOL(get_h245_addr); -EXPORT_SYMBOL(get_h225_addr); -EXPORT_SYMBOL(ip_conntrack_h245_expect); -EXPORT_SYMBOL(ip_conntrack_q931_expect); -EXPORT_SYMBOL(set_h245_addr_hook); -EXPORT_SYMBOL(set_h225_addr_hook); -EXPORT_SYMBOL(set_sig_addr_hook); -EXPORT_SYMBOL(set_ras_addr_hook); -EXPORT_SYMBOL(nat_rtp_rtcp_hook); -EXPORT_SYMBOL(nat_t120_hook); -EXPORT_SYMBOL(nat_h245_hook); -EXPORT_SYMBOL(nat_q931_hook); +EXPORT_SYMBOL_GPL(get_h225_addr); +EXPORT_SYMBOL_GPL(ip_conntrack_h245_expect); +EXPORT_SYMBOL_GPL(ip_conntrack_q931_expect); +EXPORT_SYMBOL_GPL(set_h245_addr_hook); +EXPORT_SYMBOL_GPL(set_h225_addr_hook); +EXPORT_SYMBOL_GPL(set_sig_addr_hook); +EXPORT_SYMBOL_GPL(set_ras_addr_hook); +EXPORT_SYMBOL_GPL(nat_rtp_rtcp_hook); +EXPORT_SYMBOL_GPL(nat_t120_hook); +EXPORT_SYMBOL_GPL(nat_h245_hook); +EXPORT_SYMBOL_GPL(nat_q931_hook); MODULE_AUTHOR("Jing Min Zhao <zhaojingmin@users.sourceforge.net>"); MODULE_DESCRIPTION("H.323 connection tracking helper"); diff --git a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c index afa5251..4807800 100644 --- a/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c +++ b/net/ipv4/netfilter/ip_conntrack_helper_h323_asn1.c @@ -15,7 +15,7 @@ #else #include <stdio.h> #endif -#include "ip_conntrack_helper_h323_asn1.h" +#include <linux/netfilter_ipv4/ip_conntrack_helper_h323_asn1.h> /* Trace Flag */ #ifndef H323_TRACE diff --git a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c index 3021af0..d8b14a9 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_icmp.c @@ -224,25 +224,14 @@ icmp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, } /* See ip_conntrack_proto_tcp.c */ - if (hooknum != NF_IP_PRE_ROUTING) - goto checksum_skipped; - - switch (skb->ip_summed) { - case CHECKSUM_HW: - if (!(u16)csum_fold(skb->csum)) - break; - /* fall through */ - case CHECKSUM_NONE: - skb->csum = 0; - if (__skb_checksum_complete(skb)) { - if (LOG_INVALID(IPPROTO_ICMP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, - "ip_ct_icmp: bad ICMP checksum "); - return -NF_ACCEPT; - } + if (hooknum == NF_IP_PRE_ROUTING && + nf_ip_checksum(skb, hooknum, skb->nh.iph->ihl * 4, 0)) { + if (LOG_INVALID(IPPROTO_ICMP)) + nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, + "ip_ct_icmp: bad ICMP checksum "); + return -NF_ACCEPT; } -checksum_skipped: /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c index e0dc370..062b252 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c @@ -870,11 +870,8 @@ static int tcp_error(struct sk_buff *skb, * and moreover root might send raw packets. */ /* FIXME: Source route IP option packets --RR */ - if (hooknum == NF_IP_PRE_ROUTING - && skb->ip_summed != CHECKSUM_UNNECESSARY - && csum_tcpudp_magic(iph->saddr, iph->daddr, tcplen, IPPROTO_TCP, - skb->ip_summed == CHECKSUM_HW ? skb->csum - : skb_checksum(skb, iph->ihl*4, tcplen, 0))) { + if (hooknum == NF_IP_PRE_ROUTING && + nf_ip_checksum(skb, hooknum, iph->ihl * 4, IPPROTO_TCP)) { if (LOG_INVALID(IPPROTO_TCP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_tcp: bad TCP checksum "); diff --git a/net/ipv4/netfilter/ip_conntrack_proto_udp.c b/net/ipv4/netfilter/ip_conntrack_proto_udp.c index 55b7d32..7089986 100644 --- a/net/ipv4/netfilter/ip_conntrack_proto_udp.c +++ b/net/ipv4/netfilter/ip_conntrack_proto_udp.c @@ -120,11 +120,8 @@ static int udp_error(struct sk_buff *skb, enum ip_conntrack_info *ctinfo, * because the semantic of CHECKSUM_HW is different there * and moreover root might send raw packets. * FIXME: Source route IP option packets --RR */ - if (hooknum == NF_IP_PRE_ROUTING - && skb->ip_summed != CHECKSUM_UNNECESSARY - && csum_tcpudp_magic(iph->saddr, iph->daddr, udplen, IPPROTO_UDP, - skb->ip_summed == CHECKSUM_HW ? skb->csum - : skb_checksum(skb, iph->ihl*4, udplen, 0))) { + if (hooknum == NF_IP_PRE_ROUTING && + nf_ip_checksum(skb, hooknum, iph->ihl * 4, IPPROTO_UDP)) { if (LOG_INVALID(IPPROTO_UDP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "ip_ct_udp: bad UDP checksum "); diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 5207602..929d61f 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -469,70 +469,63 @@ static unsigned int ip_conntrack_local(unsigned int hooknum, /* Connection tracking may drop packets, but never alters them, so make it the first hook. */ -static struct nf_hook_ops ip_conntrack_defrag_ops = { - .hook = ip_conntrack_defrag, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_DEFRAG, -}; - -static struct nf_hook_ops ip_conntrack_in_ops = { - .hook = ip_conntrack_in, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_CONNTRACK, -}; - -static struct nf_hook_ops ip_conntrack_defrag_local_out_ops = { - .hook = ip_conntrack_defrag, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_CONNTRACK_DEFRAG, -}; - -static struct nf_hook_ops ip_conntrack_local_out_ops = { - .hook = ip_conntrack_local, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_CONNTRACK, -}; - -/* helpers */ -static struct nf_hook_ops ip_conntrack_helper_out_ops = { - .hook = ip_conntrack_help, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_HELPER, -}; - -static struct nf_hook_ops ip_conntrack_helper_in_ops = { - .hook = ip_conntrack_help, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_HELPER, -}; - -/* Refragmenter; last chance. */ -static struct nf_hook_ops ip_conntrack_out_ops = { - .hook = ip_confirm, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_CONFIRM, -}; - -static struct nf_hook_ops ip_conntrack_local_in_ops = { - .hook = ip_confirm, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_CONFIRM, +static struct nf_hook_ops ip_conntrack_ops[] = { + { + .hook = ip_conntrack_defrag, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ip_conntrack_in, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ip_conntrack_defrag, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ip_conntrack_local, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ip_conntrack_help, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ip_conntrack_help, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ip_confirm, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, + { + .hook = ip_confirm, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, }; /* Sysctl support */ @@ -783,18 +776,46 @@ static ctl_table ip_ct_net_table[] = { EXPORT_SYMBOL(ip_ct_log_invalid); #endif /* CONFIG_SYSCTL */ -static int init_or_cleanup(int init) +/* FIXME: Allow NULL functions and sub in pointers to generic for + them. --RR */ +int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto) +{ + int ret = 0; + + write_lock_bh(&ip_conntrack_lock); + if (ip_ct_protos[proto->proto] != &ip_conntrack_generic_protocol) { + ret = -EBUSY; + goto out; + } + ip_ct_protos[proto->proto] = proto; + out: + write_unlock_bh(&ip_conntrack_lock); + return ret; +} + +void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto) +{ + write_lock_bh(&ip_conntrack_lock); + ip_ct_protos[proto->proto] = &ip_conntrack_generic_protocol; + write_unlock_bh(&ip_conntrack_lock); + + /* Somebody could be still looking at the proto in bh. */ + synchronize_net(); + + /* Remove all contrack entries for this protocol */ + ip_ct_iterate_cleanup(kill_proto, &proto->proto); +} + +static int __init ip_conntrack_standalone_init(void) { #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc, *proc_exp, *proc_stat; #endif int ret = 0; - if (!init) goto cleanup; - ret = ip_conntrack_init(); if (ret < 0) - goto cleanup_nothing; + return ret; #ifdef CONFIG_PROC_FS ret = -ENOMEM; @@ -813,78 +834,25 @@ static int init_or_cleanup(int init) proc_stat->owner = THIS_MODULE; #endif - ret = nf_register_hook(&ip_conntrack_defrag_ops); + ret = nf_register_hooks(ip_conntrack_ops, ARRAY_SIZE(ip_conntrack_ops)); if (ret < 0) { - printk("ip_conntrack: can't register pre-routing defrag hook.\n"); + printk("ip_conntrack: can't register hooks.\n"); goto cleanup_proc_stat; } - ret = nf_register_hook(&ip_conntrack_defrag_local_out_ops); - if (ret < 0) { - printk("ip_conntrack: can't register local_out defrag hook.\n"); - goto cleanup_defragops; - } - ret = nf_register_hook(&ip_conntrack_in_ops); - if (ret < 0) { - printk("ip_conntrack: can't register pre-routing hook.\n"); - goto cleanup_defraglocalops; - } - ret = nf_register_hook(&ip_conntrack_local_out_ops); - if (ret < 0) { - printk("ip_conntrack: can't register local out hook.\n"); - goto cleanup_inops; - } - ret = nf_register_hook(&ip_conntrack_helper_in_ops); - if (ret < 0) { - printk("ip_conntrack: can't register local in helper hook.\n"); - goto cleanup_inandlocalops; - } - ret = nf_register_hook(&ip_conntrack_helper_out_ops); - if (ret < 0) { - printk("ip_conntrack: can't register postrouting helper hook.\n"); - goto cleanup_helperinops; - } - ret = nf_register_hook(&ip_conntrack_out_ops); - if (ret < 0) { - printk("ip_conntrack: can't register post-routing hook.\n"); - goto cleanup_helperoutops; - } - ret = nf_register_hook(&ip_conntrack_local_in_ops); - if (ret < 0) { - printk("ip_conntrack: can't register local in hook.\n"); - goto cleanup_inoutandlocalops; - } #ifdef CONFIG_SYSCTL ip_ct_sysctl_header = register_sysctl_table(ip_ct_net_table, 0); if (ip_ct_sysctl_header == NULL) { printk("ip_conntrack: can't register to sysctl.\n"); ret = -ENOMEM; - goto cleanup_localinops; + goto cleanup_hooks; } #endif - return ret; - cleanup: - synchronize_net(); #ifdef CONFIG_SYSCTL - unregister_sysctl_table(ip_ct_sysctl_header); - cleanup_localinops: + cleanup_hooks: + nf_unregister_hooks(ip_conntrack_ops, ARRAY_SIZE(ip_conntrack_ops)); #endif - nf_unregister_hook(&ip_conntrack_local_in_ops); - cleanup_inoutandlocalops: - nf_unregister_hook(&ip_conntrack_out_ops); - cleanup_helperoutops: - nf_unregister_hook(&ip_conntrack_helper_out_ops); - cleanup_helperinops: - nf_unregister_hook(&ip_conntrack_helper_in_ops); - cleanup_inandlocalops: - nf_unregister_hook(&ip_conntrack_local_out_ops); - cleanup_inops: - nf_unregister_hook(&ip_conntrack_in_ops); - cleanup_defraglocalops: - nf_unregister_hook(&ip_conntrack_defrag_local_out_ops); - cleanup_defragops: - nf_unregister_hook(&ip_conntrack_defrag_ops); cleanup_proc_stat: #ifdef CONFIG_PROC_FS remove_proc_entry("ip_conntrack", proc_net_stat); @@ -895,48 +863,22 @@ static int init_or_cleanup(int init) cleanup_init: #endif /* CONFIG_PROC_FS */ ip_conntrack_cleanup(); - cleanup_nothing: - return ret; -} - -/* FIXME: Allow NULL functions and sub in pointers to generic for - them. --RR */ -int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto) -{ - int ret = 0; - - write_lock_bh(&ip_conntrack_lock); - if (ip_ct_protos[proto->proto] != &ip_conntrack_generic_protocol) { - ret = -EBUSY; - goto out; - } - ip_ct_protos[proto->proto] = proto; - out: - write_unlock_bh(&ip_conntrack_lock); return ret; } -void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto) -{ - write_lock_bh(&ip_conntrack_lock); - ip_ct_protos[proto->proto] = &ip_conntrack_generic_protocol; - write_unlock_bh(&ip_conntrack_lock); - - /* Somebody could be still looking at the proto in bh. */ - synchronize_net(); - - /* Remove all contrack entries for this protocol */ - ip_ct_iterate_cleanup(kill_proto, &proto->proto); -} - -static int __init ip_conntrack_standalone_init(void) -{ - return init_or_cleanup(1); -} - static void __exit ip_conntrack_standalone_fini(void) { - init_or_cleanup(0); + synchronize_net(); +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(ip_ct_sysctl_header); +#endif + nf_unregister_hooks(ip_conntrack_ops, ARRAY_SIZE(ip_conntrack_ops)); +#ifdef CONFIG_PROC_FS + remove_proc_entry("ip_conntrack", proc_net_stat); + proc_net_remove("ip_conntrack_expect"); + proc_net_remove("ip_conntrack"); +#endif /* CONFIG_PROC_FS */ + ip_conntrack_cleanup(); } module_init(ip_conntrack_standalone_init); diff --git a/net/ipv4/netfilter/ip_nat_helper_h323.c b/net/ipv4/netfilter/ip_nat_helper_h323.c index a0bc883..d45663d 100644 --- a/net/ipv4/netfilter/ip_nat_helper_h323.c +++ b/net/ipv4/netfilter/ip_nat_helper_h323.c @@ -7,24 +7,6 @@ * * Based on the 'brute force' H.323 NAT module by * Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> - * - * Changes: - * 2006-02-01 - initial version 0.1 - * - * 2006-02-20 - version 0.2 - * 1. Changed source format to follow kernel conventions - * 2. Deleted some unnecessary structures - * 3. Minor fixes - * - * 2006-03-10 - version 0.3 - * 1. Added support for multiple TPKTs in one packet (suggested by - * Patrick McHardy) - * 2. Added support for non-linear skb (based on Patrick McHardy's patch) - * 3. Eliminated unnecessary return code - * - * 2006-03-15 - version 0.4 - * 1. Added support for T.120 channels - * 2. Added parameter gkrouted_only (suggested by Patrick McHardy) */ #include <linux/module.h> @@ -41,65 +23,12 @@ #include <linux/netfilter_ipv4/ip_conntrack_h323.h> #include <linux/netfilter_ipv4/ip_conntrack_helper.h> -#include "ip_conntrack_helper_h323_asn1.h" - #if 0 #define DEBUGP printk #else #define DEBUGP(format, args...) #endif -extern int get_h245_addr(unsigned char *data, H245_TransportAddress * addr, - u_int32_t * ip, u_int16_t * port); -extern int get_h225_addr(unsigned char *data, TransportAddress * addr, - u_int32_t * ip, u_int16_t * port); -extern void ip_conntrack_h245_expect(struct ip_conntrack *new, - struct ip_conntrack_expect *this); -extern void ip_conntrack_q931_expect(struct ip_conntrack *new, - struct ip_conntrack_expect *this); -extern int (*set_h245_addr_hook) (struct sk_buff ** pskb, - unsigned char **data, int dataoff, - H245_TransportAddress * addr, - u_int32_t ip, u_int16_t port); -extern int (*set_h225_addr_hook) (struct sk_buff ** pskb, - unsigned char **data, int dataoff, - TransportAddress * addr, - u_int32_t ip, u_int16_t port); -extern int (*set_sig_addr_hook) (struct sk_buff ** pskb, - struct ip_conntrack * ct, - enum ip_conntrack_info ctinfo, - unsigned char **data, - TransportAddress * addr, int count); -extern int (*set_ras_addr_hook) (struct sk_buff ** pskb, - struct ip_conntrack * ct, - enum ip_conntrack_info ctinfo, - unsigned char **data, - TransportAddress * addr, int count); -extern int (*nat_rtp_rtcp_hook) (struct sk_buff ** pskb, - struct ip_conntrack * ct, - enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, - H245_TransportAddress * addr, - u_int16_t port, u_int16_t rtp_port, - struct ip_conntrack_expect * rtp_exp, - struct ip_conntrack_expect * rtcp_exp); -extern int (*nat_t120_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, - enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, - H245_TransportAddress * addr, u_int16_t port, - struct ip_conntrack_expect * exp); -extern int (*nat_h245_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, - enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, - TransportAddress * addr, u_int16_t port, - struct ip_conntrack_expect * exp); -extern int (*nat_q931_hook) (struct sk_buff ** pskb, struct ip_conntrack * ct, - enum ip_conntrack_info ctinfo, - unsigned char **data, TransportAddress * addr, - int idx, u_int16_t port, - struct ip_conntrack_expect * exp); - - /****************************************************************************/ static int set_addr(struct sk_buff **pskb, unsigned char **data, int dataoff, diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index efba8c4..1aba926 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -279,7 +279,7 @@ static struct ipt_target ipt_dnat_reg = { .target = ipt_dnat_target, .targetsize = sizeof(struct ip_nat_multi_range_compat), .table = "nat", - .hooks = 1 << NF_IP_PRE_ROUTING, + .hooks = (1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_OUT), .checkentry = ipt_dnat_checkentry, }; diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 3505b0d..8f760b2 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -299,69 +299,63 @@ ip_nat_adjust(unsigned int hooknum, /* We must be after connection tracking and before packet filtering. */ -/* Before packet filtering, change destination */ -static struct nf_hook_ops ip_nat_in_ops = { - .hook = ip_nat_in, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_NAT_DST, +static struct nf_hook_ops ip_nat_ops[] = { + /* Before packet filtering, change destination */ + { + .hook = ip_nat_in, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = ip_nat_out, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* After conntrack, adjust sequence number */ + { + .hook = ip_nat_adjust, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SEQ_ADJUST, + }, + /* Before packet filtering, change destination */ + { + .hook = ip_nat_local_fn, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = ip_nat_fn, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* After conntrack, adjust sequence number */ + { + .hook = ip_nat_adjust, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SEQ_ADJUST, + }, }; -/* After packet filtering, change source */ -static struct nf_hook_ops ip_nat_out_ops = { - .hook = ip_nat_out, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_NAT_SRC, -}; - -/* After conntrack, adjust sequence number */ -static struct nf_hook_ops ip_nat_adjust_out_ops = { - .hook = ip_nat_adjust, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_NAT_SEQ_ADJUST, -}; - -/* Before packet filtering, change destination */ -static struct nf_hook_ops ip_nat_local_out_ops = { - .hook = ip_nat_local_fn, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_NAT_DST, -}; - -/* After packet filtering, change source for reply packets of LOCAL_OUT DNAT */ -static struct nf_hook_ops ip_nat_local_in_ops = { - .hook = ip_nat_fn, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_IN, - .priority = NF_IP_PRI_NAT_SRC, -}; - -/* After conntrack, adjust sequence number */ -static struct nf_hook_ops ip_nat_adjust_in_ops = { - .hook = ip_nat_adjust, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_IN, - .priority = NF_IP_PRI_NAT_SEQ_ADJUST, -}; - - -static int init_or_cleanup(int init) +static int __init ip_nat_standalone_init(void) { int ret = 0; need_conntrack(); - if (!init) goto cleanup; - #ifdef CONFIG_XFRM BUG_ON(ip_nat_decode_session != NULL); ip_nat_decode_session = nat_decode_session; @@ -371,50 +365,13 @@ static int init_or_cleanup(int init) printk("ip_nat_init: can't setup rules.\n"); goto cleanup_decode_session; } - ret = nf_register_hook(&ip_nat_in_ops); + ret = nf_register_hooks(ip_nat_ops, ARRAY_SIZE(ip_nat_ops)); if (ret < 0) { - printk("ip_nat_init: can't register in hook.\n"); + printk("ip_nat_init: can't register hooks.\n"); goto cleanup_rule_init; } - ret = nf_register_hook(&ip_nat_out_ops); - if (ret < 0) { - printk("ip_nat_init: can't register out hook.\n"); - goto cleanup_inops; - } - ret = nf_register_hook(&ip_nat_adjust_in_ops); - if (ret < 0) { - printk("ip_nat_init: can't register adjust in hook.\n"); - goto cleanup_outops; - } - ret = nf_register_hook(&ip_nat_adjust_out_ops); - if (ret < 0) { - printk("ip_nat_init: can't register adjust out hook.\n"); - goto cleanup_adjustin_ops; - } - ret = nf_register_hook(&ip_nat_local_out_ops); - if (ret < 0) { - printk("ip_nat_init: can't register local out hook.\n"); - goto cleanup_adjustout_ops; - } - ret = nf_register_hook(&ip_nat_local_in_ops); - if (ret < 0) { - printk("ip_nat_init: can't register local in hook.\n"); - goto cleanup_localoutops; - } return ret; - cleanup: - nf_unregister_hook(&ip_nat_local_in_ops); - cleanup_localoutops: - nf_unregister_hook(&ip_nat_local_out_ops); - cleanup_adjustout_ops: - nf_unregister_hook(&ip_nat_adjust_out_ops); - cleanup_adjustin_ops: - nf_unregister_hook(&ip_nat_adjust_in_ops); - cleanup_outops: - nf_unregister_hook(&ip_nat_out_ops); - cleanup_inops: - nf_unregister_hook(&ip_nat_in_ops); cleanup_rule_init: ip_nat_rule_cleanup(); cleanup_decode_session: @@ -425,14 +382,14 @@ static int init_or_cleanup(int init) return ret; } -static int __init ip_nat_standalone_init(void) -{ - return init_or_cleanup(1); -} - static void __exit ip_nat_standalone_fini(void) { - init_or_cleanup(0); + nf_unregister_hooks(ip_nat_ops, ARRAY_SIZE(ip_nat_ops)); + ip_nat_rule_cleanup(); +#ifdef CONFIG_XFRM + ip_nat_decode_session = NULL; + synchronize_net(); +#endif } module_init(ip_nat_standalone_init); diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index 896a244..b93f049 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -662,15 +662,11 @@ static struct nf_queue_handler nfqh = { .outfn = &ipq_enqueue_packet, }; -static int -init_or_cleanup(int init) +static int __init ip_queue_init(void) { int status = -ENOMEM; struct proc_dir_entry *proc; - if (!init) - goto cleanup; - netlink_register_notifier(&ipq_nl_notifier); ipqnl = netlink_kernel_create(NETLINK_FIREWALL, 0, ipq_rcv_sk, THIS_MODULE); @@ -697,11 +693,6 @@ init_or_cleanup(int init) } return status; -cleanup: - nf_unregister_queue_handlers(&nfqh); - synchronize_net(); - ipq_flush(NF_DROP); - cleanup_sysctl: unregister_sysctl_table(ipq_sysctl_header); unregister_netdevice_notifier(&ipq_dev_notifier); @@ -717,15 +708,21 @@ cleanup_netlink_notifier: return status; } -static int __init ip_queue_init(void) -{ - - return init_or_cleanup(1); -} - static void __exit ip_queue_fini(void) { - init_or_cleanup(0); + nf_unregister_queue_handlers(&nfqh); + synchronize_net(); + ipq_flush(NF_DROP); + + unregister_sysctl_table(ipq_sysctl_header); + unregister_netdevice_notifier(&ipq_dev_notifier); + proc_net_remove(IPQ_PROC_FS_NAME); + + sock_release(ipqnl->sk_socket); + mutex_lock(&ipqnl_mutex); + mutex_unlock(&ipqnl_mutex); + + netlink_unregister_notifier(&ipq_nl_notifier); } MODULE_DESCRIPTION("IPv4 packet queue handler"); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index e4768a3..aad9d28 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -725,22 +725,17 @@ static struct file_operations clusterip_proc_fops = { #endif /* CONFIG_PROC_FS */ -static int init_or_cleanup(int fini) +static int __init ipt_clusterip_init(void) { int ret; - if (fini) - goto cleanup; - - if (ipt_register_target(&clusterip_tgt)) { - ret = -EINVAL; - goto cleanup_none; - } + ret = ipt_register_target(&clusterip_tgt); + if (ret < 0) + return ret; - if (nf_register_hook(&cip_arp_ops) < 0) { - ret = -EINVAL; + ret = nf_register_hook(&cip_arp_ops); + if (ret < 0) goto cleanup_target; - } #ifdef CONFIG_PROC_FS clusterip_procdir = proc_mkdir("ipt_CLUSTERIP", proc_net); @@ -753,31 +748,24 @@ static int init_or_cleanup(int fini) printk(KERN_NOTICE "ClusterIP Version %s loaded successfully\n", CLUSTERIP_VERSION); - return 0; -cleanup: - printk(KERN_NOTICE "ClusterIP Version %s unloading\n", - CLUSTERIP_VERSION); -#ifdef CONFIG_PROC_FS - remove_proc_entry(clusterip_procdir->name, clusterip_procdir->parent); -#endif cleanup_hook: nf_unregister_hook(&cip_arp_ops); cleanup_target: ipt_unregister_target(&clusterip_tgt); -cleanup_none: - return -EINVAL; -} - -static int __init ipt_clusterip_init(void) -{ - return init_or_cleanup(0); + return ret; } static void __exit ipt_clusterip_fini(void) { - init_or_cleanup(1); + printk(KERN_NOTICE "ClusterIP Version %s unloading\n", + CLUSTERIP_VERSION); +#ifdef CONFIG_PROC_FS + remove_proc_entry(clusterip_procdir->name, clusterip_procdir->parent); +#endif + nf_unregister_hook(&cip_arp_ops); + ipt_unregister_target(&clusterip_tgt); } module_init(ipt_clusterip_init); diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 4269a54..0bba3c2 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -106,7 +106,6 @@ static void send_reset(struct sk_buff *oldskb, int hook) struct rtable *rt; u_int16_t tmp_port; u_int32_t tmp_addr; - unsigned int tcplen; int needs_ack; int hh_len; @@ -124,13 +123,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) return; /* Check checksum */ - tcplen = oldskb->len - iph->ihl * 4; - if (((hook != NF_IP_LOCAL_IN && oldskb->ip_summed != CHECKSUM_HW) || - (hook == NF_IP_LOCAL_IN && - oldskb->ip_summed != CHECKSUM_UNNECESSARY)) && - csum_tcpudp_magic(iph->saddr, iph->daddr, tcplen, IPPROTO_TCP, - oldskb->ip_summed == CHECKSUM_HW ? oldskb->csum : - skb_checksum(oldskb, iph->ihl * 4, tcplen, 0))) + if (nf_ip_checksum(oldskb, hook, iph->ihl * 4, IPPROTO_TCP)) return; if ((rt = route_reverse(oldskb, oth, hook)) == NULL) diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 3d80aefe..7f41748 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -157,37 +157,20 @@ static int __init iptable_filter_init(void) return ret; /* Register hooks */ - ret = nf_register_hook(&ipt_ops[0]); + ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); if (ret < 0) goto cleanup_table; - ret = nf_register_hook(&ipt_ops[1]); - if (ret < 0) - goto cleanup_hook0; - - ret = nf_register_hook(&ipt_ops[2]); - if (ret < 0) - goto cleanup_hook1; - return ret; - cleanup_hook1: - nf_unregister_hook(&ipt_ops[1]); - cleanup_hook0: - nf_unregister_hook(&ipt_ops[0]); cleanup_table: ipt_unregister_table(&packet_filter); - return ret; } static void __exit iptable_filter_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ipt_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ipt_ops[i]); - + nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); ipt_unregister_table(&packet_filter); } diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 412fc96..397b95c 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -211,49 +211,20 @@ static int __init iptable_mangle_init(void) return ret; /* Register hooks */ - ret = nf_register_hook(&ipt_ops[0]); + ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); if (ret < 0) goto cleanup_table; - ret = nf_register_hook(&ipt_ops[1]); - if (ret < 0) - goto cleanup_hook0; - - ret = nf_register_hook(&ipt_ops[2]); - if (ret < 0) - goto cleanup_hook1; - - ret = nf_register_hook(&ipt_ops[3]); - if (ret < 0) - goto cleanup_hook2; - - ret = nf_register_hook(&ipt_ops[4]); - if (ret < 0) - goto cleanup_hook3; - return ret; - cleanup_hook3: - nf_unregister_hook(&ipt_ops[3]); - cleanup_hook2: - nf_unregister_hook(&ipt_ops[2]); - cleanup_hook1: - nf_unregister_hook(&ipt_ops[1]); - cleanup_hook0: - nf_unregister_hook(&ipt_ops[0]); cleanup_table: ipt_unregister_table(&packet_mangler); - return ret; } static void __exit iptable_mangle_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ipt_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ipt_ops[i]); - + nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); ipt_unregister_table(&packet_mangler); } diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 03cc79a..7912cce 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -101,18 +101,18 @@ ipt_hook(unsigned int hook, /* 'raw' is the very first table. */ static struct nf_hook_ops ipt_ops[] = { { - .hook = ipt_hook, - .pf = PF_INET, - .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_RAW, - .owner = THIS_MODULE, + .hook = ipt_hook, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_RAW, + .owner = THIS_MODULE, }, { - .hook = ipt_hook, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_RAW, - .owner = THIS_MODULE, + .hook = ipt_hook, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_RAW, + .owner = THIS_MODULE, }, }; @@ -126,31 +126,20 @@ static int __init iptable_raw_init(void) return ret; /* Register hooks */ - ret = nf_register_hook(&ipt_ops[0]); + ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); if (ret < 0) goto cleanup_table; - ret = nf_register_hook(&ipt_ops[1]); - if (ret < 0) - goto cleanup_hook0; - return ret; - cleanup_hook0: - nf_unregister_hook(&ipt_ops[0]); cleanup_table: ipt_unregister_table(&packet_raw); - return ret; } static void __exit iptable_raw_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ipt_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ipt_ops[i]); - + nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops)); ipt_unregister_table(&packet_raw); } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 4afbc69..5bc9f64 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -210,71 +210,63 @@ static unsigned int ipv4_conntrack_local(unsigned int hooknum, /* Connection tracking may drop packets, but never alters them, so make it the first hook. */ -static struct nf_hook_ops ipv4_conntrack_defrag_ops = { - .hook = ipv4_conntrack_defrag, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_DEFRAG, -}; - -static struct nf_hook_ops ipv4_conntrack_in_ops = { - .hook = ipv4_conntrack_in, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_PRE_ROUTING, - .priority = NF_IP_PRI_CONNTRACK, -}; - -static struct nf_hook_ops ipv4_conntrack_defrag_local_out_ops = { - .hook = ipv4_conntrack_defrag, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_CONNTRACK_DEFRAG, -}; - -static struct nf_hook_ops ipv4_conntrack_local_out_ops = { - .hook = ipv4_conntrack_local, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_OUT, - .priority = NF_IP_PRI_CONNTRACK, -}; - -/* helpers */ -static struct nf_hook_ops ipv4_conntrack_helper_out_ops = { - .hook = ipv4_conntrack_help, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_HELPER, -}; - -static struct nf_hook_ops ipv4_conntrack_helper_in_ops = { - .hook = ipv4_conntrack_help, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_HELPER, -}; - - -/* Refragmenter; last chance. */ -static struct nf_hook_ops ipv4_conntrack_out_ops = { - .hook = ipv4_confirm, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_CONFIRM, -}; - -static struct nf_hook_ops ipv4_conntrack_local_in_ops = { - .hook = ipv4_confirm, - .owner = THIS_MODULE, - .pf = PF_INET, - .hooknum = NF_IP_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_CONFIRM, +static struct nf_hook_ops ipv4_conntrack_ops[] = { + { + .hook = ipv4_conntrack_defrag, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv4_conntrack_in, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_PRE_ROUTING, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ipv4_conntrack_defrag, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv4_conntrack_local, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_OUT, + .priority = NF_IP_PRI_CONNTRACK, + }, + { + .hook = ipv4_conntrack_help, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv4_conntrack_help, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_HELPER, + }, + { + .hook = ipv4_confirm, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_POST_ROUTING, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, + { + .hook = ipv4_confirm, + .owner = THIS_MODULE, + .pf = PF_INET, + .hooknum = NF_IP_LOCAL_IN, + .priority = NF_IP_PRI_CONNTRACK_CONFIRM, + }, }; #ifdef CONFIG_SYSCTL @@ -440,16 +432,20 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { extern struct nf_conntrack_protocol nf_conntrack_protocol_tcp4; extern struct nf_conntrack_protocol nf_conntrack_protocol_udp4; extern struct nf_conntrack_protocol nf_conntrack_protocol_icmp; -static int init_or_cleanup(int init) + +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); +MODULE_LICENSE("GPL"); + +static int __init nf_conntrack_l3proto_ipv4_init(void) { int ret = 0; - if (!init) goto cleanup; + need_conntrack(); ret = nf_register_sockopt(&so_getorigdst); if (ret < 0) { printk(KERN_ERR "Unable to register netfilter socket option\n"); - goto cleanup_nothing; + return ret; } ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_tcp4); @@ -476,84 +472,26 @@ static int init_or_cleanup(int init) goto cleanup_icmp; } - ret = nf_register_hook(&ipv4_conntrack_defrag_ops); + ret = nf_register_hooks(ipv4_conntrack_ops, + ARRAY_SIZE(ipv4_conntrack_ops)); if (ret < 0) { - printk("nf_conntrack_ipv4: can't register pre-routing defrag hook.\n"); + printk("nf_conntrack_ipv4: can't register hooks.\n"); goto cleanup_ipv4; } - ret = nf_register_hook(&ipv4_conntrack_defrag_local_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register local_out defrag hook.\n"); - goto cleanup_defragops; - } - - ret = nf_register_hook(&ipv4_conntrack_in_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register pre-routing hook.\n"); - goto cleanup_defraglocalops; - } - - ret = nf_register_hook(&ipv4_conntrack_local_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register local out hook.\n"); - goto cleanup_inops; - } - - ret = nf_register_hook(&ipv4_conntrack_helper_in_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register local helper hook.\n"); - goto cleanup_inandlocalops; - } - - ret = nf_register_hook(&ipv4_conntrack_helper_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register postrouting helper hook.\n"); - goto cleanup_helperinops; - } - - ret = nf_register_hook(&ipv4_conntrack_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register post-routing hook.\n"); - goto cleanup_helperoutops; - } - - ret = nf_register_hook(&ipv4_conntrack_local_in_ops); - if (ret < 0) { - printk("nf_conntrack_ipv4: can't register local in hook.\n"); - goto cleanup_inoutandlocalops; - } - #ifdef CONFIG_SYSCTL nf_ct_ipv4_sysctl_header = register_sysctl_table(nf_ct_net_table, 0); if (nf_ct_ipv4_sysctl_header == NULL) { printk("nf_conntrack: can't register to sysctl.\n"); ret = -ENOMEM; - goto cleanup_localinops; + goto cleanup_hooks; } #endif return ret; - cleanup: - synchronize_net(); #ifdef CONFIG_SYSCTL - unregister_sysctl_table(nf_ct_ipv4_sysctl_header); - cleanup_localinops: + cleanup_hooks: + nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); #endif - nf_unregister_hook(&ipv4_conntrack_local_in_ops); - cleanup_inoutandlocalops: - nf_unregister_hook(&ipv4_conntrack_out_ops); - cleanup_helperoutops: - nf_unregister_hook(&ipv4_conntrack_helper_out_ops); - cleanup_helperinops: - nf_unregister_hook(&ipv4_conntrack_helper_in_ops); - cleanup_inandlocalops: - nf_unregister_hook(&ipv4_conntrack_local_out_ops); - cleanup_inops: - nf_unregister_hook(&ipv4_conntrack_in_ops); - cleanup_defraglocalops: - nf_unregister_hook(&ipv4_conntrack_defrag_local_out_ops); - cleanup_defragops: - nf_unregister_hook(&ipv4_conntrack_defrag_ops); cleanup_ipv4: nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv4); cleanup_icmp: @@ -564,22 +502,21 @@ static int init_or_cleanup(int init) nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp4); cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst); - cleanup_nothing: return ret; } -MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET)); -MODULE_LICENSE("GPL"); - -static int __init nf_conntrack_l3proto_ipv4_init(void) -{ - need_conntrack(); - return init_or_cleanup(1); -} - static void __exit nf_conntrack_l3proto_ipv4_fini(void) { - init_or_cleanup(0); + synchronize_net(); +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(nf_ct_ipv4_sysctl_header); +#endif + nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); + nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv4); + nf_conntrack_protocol_unregister(&nf_conntrack_protocol_icmp); + nf_conntrack_protocol_unregister(&nf_conntrack_protocol_udp4); + nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp4); + nf_unregister_sockopt(&so_getorigdst); } module_init(nf_conntrack_l3proto_ipv4_init); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 52dc175..4b0d361 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -235,30 +235,14 @@ icmp_error(struct sk_buff *skb, unsigned int dataoff, } /* See ip_conntrack_proto_tcp.c */ - if (hooknum != NF_IP_PRE_ROUTING) - goto checksum_skipped; - - switch (skb->ip_summed) { - case CHECKSUM_HW: - if (!(u16)csum_fold(skb->csum)) - break; + if (hooknum == NF_IP_PRE_ROUTING && + nf_ip_checksum(skb, hooknum, dataoff, 0)) { if (LOG_INVALID(IPPROTO_ICMP)) nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL, "nf_ct_icmp: bad HW ICMP checksum "); return -NF_ACCEPT; - case CHECKSUM_NONE: - if ((u16)csum_fold(skb_checksum(skb, 0, skb->len, 0))) { - if (LOG_INVALID(IPPROTO_ICMP)) - nf_log_packet(PF_INET, 0, skb, NULL, NULL, - NULL, - "nf_ct_icmp: bad ICMP checksum "); - return -NF_ACCEPT; - } - default: - break; } -checksum_skipped: /* * 18 is the highest 'known' ICMP type. Anything else is a mystery * diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 0d7d386..8d30c48 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -8,6 +8,8 @@ #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/icmp.h> +#include <net/ip.h> #include <net/protocol.h> #include <net/xfrm.h> @@ -70,10 +72,16 @@ static int tunnel4_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto drop; + for (handler = tunnel4_handlers; handler; handler = handler->next) if (!handler->handler(skb)) return 0; + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + +drop: kfree_skb(skb); return 0; } diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index e1b8f4b..3e174c8 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -37,8 +37,6 @@ static int xfrm4_parse_spi(struct sk_buff *skb, u8 nexthdr, u32 *spi, u32 *seq) { switch (nexthdr) { case IPPROTO_IPIP: - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return -EINVAL; *spi = skb->nh.iph->saddr; *seq = 0; return 0; @@ -90,7 +88,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, __u16 encap_type) if (unlikely(x->km.state != XFRM_STATE_VALID)) goto drop_unlock; - if (x->encap->encap_type != encap_type) + if ((x->encap ? x->encap->encap_type : 0) != encap_type) goto drop_unlock; if (x->props.replay_window && xfrm_replay_check(x, seq)) diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index bb8ffb8..2ae84c9 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -23,6 +23,86 @@ #include <net/inet6_hashtables.h> #include <net/ip.h> +void __inet6_hash(struct inet_hashinfo *hashinfo, + struct sock *sk) +{ + struct hlist_head *list; + rwlock_t *lock; + + BUG_TRAP(sk_unhashed(sk)); + + if (sk->sk_state == TCP_LISTEN) { + list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; + lock = &hashinfo->lhash_lock; + inet_listen_wlock(hashinfo); + } else { + unsigned int hash; + sk->sk_hash = hash = inet6_sk_ehashfn(sk); + hash &= (hashinfo->ehash_size - 1); + list = &hashinfo->ehash[hash].chain; + lock = &hashinfo->ehash[hash].lock; + write_lock(lock); + } + + __sk_add_node(sk, list); + sock_prot_inc_use(sk->sk_prot); + write_unlock(lock); +} +EXPORT_SYMBOL(__inet6_hash); + +/* + * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so + * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM + * + * The sockhash lock must be held as a reader here. + */ +struct sock *__inet6_lookup_established(struct inet_hashinfo *hashinfo, + const struct in6_addr *saddr, + const u16 sport, + const struct in6_addr *daddr, + const u16 hnum, + const int dif) +{ + struct sock *sk; + const struct hlist_node *node; + const __u32 ports = INET_COMBINED_PORTS(sport, hnum); + /* Optimize here for direct hit, only listening connections can + * have wildcards anyways. + */ + unsigned int hash = inet6_ehashfn(daddr, hnum, saddr, sport); + struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); + + prefetch(head->chain.first); + read_lock(&head->lock); + sk_for_each(sk, node, &head->chain) { + /* For IPV6 do the cheaper port and family tests first. */ + if (INET6_MATCH(sk, hash, saddr, daddr, ports, dif)) + goto hit; /* You sunk my battleship! */ + } + /* Must check for a TIME_WAIT'er before going to listener hash. */ + sk_for_each(sk, node, &(head + hashinfo->ehash_size)->chain) { + const struct inet_timewait_sock *tw = inet_twsk(sk); + + if(*((__u32 *)&(tw->tw_dport)) == ports && + sk->sk_family == PF_INET6) { + const struct inet6_timewait_sock *tw6 = inet6_twsk(sk); + + if (ipv6_addr_equal(&tw6->tw_v6_daddr, saddr) && + ipv6_addr_equal(&tw6->tw_v6_rcv_saddr, daddr) && + (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif)) + goto hit; + } + } + read_unlock(&head->lock); + return NULL; + +hit: + sock_hold(sk); + read_unlock(&head->lock); + return sk; +} +EXPORT_SYMBOL(__inet6_lookup_established); + struct sock *inet6_lookup_listener(struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, const unsigned short hnum, const int dif) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index ff9040c..a995796 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -519,9 +519,6 @@ ip6ip6_rcv(struct sk_buff *skb) struct ipv6hdr *ipv6h; struct ip6_tnl *t; - if (!pskb_may_pull(skb, sizeof (*ipv6h))) - goto discard; - ipv6h = skb->nh.ipv6h; read_lock(&ip6ip6_lock); @@ -529,8 +526,7 @@ ip6ip6_rcv(struct sk_buff *skb) if ((t = ip6ip6_tnl_lookup(&ipv6h->saddr, &ipv6h->daddr)) != NULL) { if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { read_unlock(&ip6ip6_lock); - kfree_skb(skb); - return 0; + goto discard; } if (!(t->parms.flags & IP6_TNL_F_CAP_RCV)) { @@ -557,9 +553,11 @@ ip6ip6_rcv(struct sk_buff *skb) return 0; } read_unlock(&ip6ip6_lock); - icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev); -discard: return 1; + +discard: + kfree_skb(skb); + return 0; } static inline struct ipv6_txoptions *create_tel(__u8 encap_limit) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index d750cfc..395a417 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -7,6 +7,7 @@ #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/xfrm.h> +#include <net/ip6_checksum.h> int ip6_route_me_harder(struct sk_buff *skb) { @@ -54,7 +55,7 @@ struct ip6_rt_info { struct in6_addr saddr; }; -static void save(const struct sk_buff *skb, struct nf_info *info) +static void nf_ip6_saveroute(const struct sk_buff *skb, struct nf_info *info) { struct ip6_rt_info *rt_info = nf_info_reroute(info); @@ -66,7 +67,7 @@ static void save(const struct sk_buff *skb, struct nf_info *info) } } -static int reroute(struct sk_buff **pskb, const struct nf_info *info) +static int nf_ip6_reroute(struct sk_buff **pskb, const struct nf_info *info) { struct ip6_rt_info *rt_info = nf_info_reroute(info); @@ -79,15 +80,50 @@ static int reroute(struct sk_buff **pskb, const struct nf_info *info) return 0; } -static struct nf_queue_rerouter ip6_reroute = { - .rer_size = sizeof(struct ip6_rt_info), - .save = &save, - .reroute = &reroute, +unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, + unsigned int dataoff, u_int8_t protocol) +{ + struct ipv6hdr *ip6h = skb->nh.ipv6h; + unsigned int csum = 0; + + switch (skb->ip_summed) { + case CHECKSUM_HW: + if (hook != NF_IP6_PRE_ROUTING && hook != NF_IP6_LOCAL_IN) + break; + if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - dataoff, protocol, + csum_sub(skb->csum, + skb_checksum(skb, 0, + dataoff, 0)))) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + /* fall through */ + case CHECKSUM_NONE: + skb->csum = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - dataoff, + protocol, + csum_sub(0, + skb_checksum(skb, 0, + dataoff, 0))); + csum = __skb_checksum_complete(skb); + } + return csum; +} + +EXPORT_SYMBOL(nf_ip6_checksum); + +static struct nf_afinfo nf_ip6_afinfo = { + .family = AF_INET6, + .checksum = nf_ip6_checksum, + .saveroute = nf_ip6_saveroute, + .reroute = nf_ip6_reroute, + .route_key_size = sizeof(struct ip6_rt_info), }; int __init ipv6_netfilter_init(void) { - return nf_register_queue_rerouter(PF_INET6, &ip6_reroute); + return nf_register_afinfo(&nf_ip6_afinfo); } /* This can be called from inet6_init() on errors, so it cannot @@ -95,5 +131,5 @@ int __init ipv6_netfilter_init(void) */ void ipv6_netfilter_fini(void) { - nf_unregister_queue_rerouter(PF_INET6); + nf_unregister_afinfo(&nf_ip6_afinfo); } diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index e81c6a9..b4b7d44 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -658,15 +658,11 @@ static struct nf_queue_handler nfqh = { .outfn = &ipq_enqueue_packet, }; -static int -init_or_cleanup(int init) +static int __init ip6_queue_init(void) { int status = -ENOMEM; struct proc_dir_entry *proc; - if (!init) - goto cleanup; - netlink_register_notifier(&ipq_nl_notifier); ipqnl = netlink_kernel_create(NETLINK_IP6_FW, 0, ipq_rcv_sk, THIS_MODULE); @@ -693,11 +689,6 @@ init_or_cleanup(int init) } return status; -cleanup: - nf_unregister_queue_handlers(&nfqh); - synchronize_net(); - ipq_flush(NF_DROP); - cleanup_sysctl: unregister_sysctl_table(ipq_sysctl_header); unregister_netdevice_notifier(&ipq_dev_notifier); @@ -713,15 +704,21 @@ cleanup_netlink_notifier: return status; } -static int __init ip6_queue_init(void) -{ - - return init_or_cleanup(1); -} - static void __exit ip6_queue_fini(void) { - init_or_cleanup(0); + nf_unregister_queue_handlers(&nfqh); + synchronize_net(); + ipq_flush(NF_DROP); + + unregister_sysctl_table(ipq_sysctl_header); + unregister_netdevice_notifier(&ipq_dev_notifier); + proc_net_remove(IPQ_PROC_FS_NAME); + + sock_release(ipqnl->sk_socket); + mutex_lock(&ipqnl_mutex); + mutex_unlock(&ipqnl_mutex); + + netlink_unregister_notifier(&ipq_nl_notifier); } MODULE_DESCRIPTION("IPv6 packet queue handler"); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index e5e724d..60976c0 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -177,37 +177,20 @@ static int __init ip6table_filter_init(void) return ret; /* Register hooks */ - ret = nf_register_hook(&ip6t_ops[0]); + ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); if (ret < 0) goto cleanup_table; - ret = nf_register_hook(&ip6t_ops[1]); - if (ret < 0) - goto cleanup_hook0; - - ret = nf_register_hook(&ip6t_ops[2]); - if (ret < 0) - goto cleanup_hook1; - return ret; - cleanup_hook1: - nf_unregister_hook(&ip6t_ops[1]); - cleanup_hook0: - nf_unregister_hook(&ip6t_ops[0]); cleanup_table: ip6t_unregister_table(&packet_filter); - return ret; } static void __exit ip6table_filter_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ip6t_ops[i]); - + nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); ip6t_unregister_table(&packet_filter); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index e1f0f6a..03a13ea 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -238,49 +238,20 @@ static int __init ip6table_mangle_init(void) return ret; /* Register hooks */ - ret = nf_register_hook(&ip6t_ops[0]); + ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); if (ret < 0) goto cleanup_table; - ret = nf_register_hook(&ip6t_ops[1]); - if (ret < 0) - goto cleanup_hook0; - - ret = nf_register_hook(&ip6t_ops[2]); - if (ret < 0) - goto cleanup_hook1; - - ret = nf_register_hook(&ip6t_ops[3]); - if (ret < 0) - goto cleanup_hook2; - - ret = nf_register_hook(&ip6t_ops[4]); - if (ret < 0) - goto cleanup_hook3; - return ret; - cleanup_hook3: - nf_unregister_hook(&ip6t_ops[3]); - cleanup_hook2: - nf_unregister_hook(&ip6t_ops[2]); - cleanup_hook1: - nf_unregister_hook(&ip6t_ops[1]); - cleanup_hook0: - nf_unregister_hook(&ip6t_ops[0]); cleanup_table: ip6t_unregister_table(&packet_mangler); - return ret; } static void __exit ip6table_mangle_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ip6t_ops[i]); - + nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); ip6t_unregister_table(&packet_mangler); } diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 54d1fff..61a7c58 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -152,31 +152,20 @@ static int __init ip6table_raw_init(void) return ret; /* Register hooks */ - ret = nf_register_hook(&ip6t_ops[0]); + ret = nf_register_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); if (ret < 0) goto cleanup_table; - ret = nf_register_hook(&ip6t_ops[1]); - if (ret < 0) - goto cleanup_hook0; - return ret; - cleanup_hook0: - nf_unregister_hook(&ip6t_ops[0]); cleanup_table: ip6t_unregister_table(&packet_raw); - return ret; } static void __exit ip6table_raw_fini(void) { - unsigned int i; - - for (i = 0; i < sizeof(ip6t_ops)/sizeof(struct nf_hook_ops); i++) - nf_unregister_hook(&ip6t_ops[i]); - + nf_unregister_hooks(ip6t_ops, ARRAY_SIZE(ip6t_ops)); ip6t_unregister_table(&packet_raw); } diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c8b5a96..93bae36 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -286,55 +286,49 @@ static unsigned int ipv6_conntrack_local(unsigned int hooknum, return ipv6_conntrack_in(hooknum, pskb, in, out, okfn); } -/* Connection tracking may drop packets, but never alters them, so - make it the first hook. */ -static struct nf_hook_ops ipv6_conntrack_defrag_ops = { - .hook = ipv6_defrag, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_PRE_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, -}; - -static struct nf_hook_ops ipv6_conntrack_in_ops = { - .hook = ipv6_conntrack_in, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_PRE_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK, -}; - -static struct nf_hook_ops ipv6_conntrack_local_out_ops = { - .hook = ipv6_conntrack_local, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_OUT, - .priority = NF_IP6_PRI_CONNTRACK, -}; - -static struct nf_hook_ops ipv6_conntrack_defrag_local_out_ops = { - .hook = ipv6_defrag, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_OUT, - .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, -}; - -/* Refragmenter; last chance. */ -static struct nf_hook_ops ipv6_conntrack_out_ops = { - .hook = ipv6_confirm, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_POST_ROUTING, - .priority = NF_IP6_PRI_LAST, -}; - -static struct nf_hook_ops ipv6_conntrack_local_in_ops = { - .hook = ipv6_confirm, - .owner = THIS_MODULE, - .pf = PF_INET6, - .hooknum = NF_IP6_LOCAL_IN, - .priority = NF_IP6_PRI_LAST-1, +static struct nf_hook_ops ipv6_conntrack_ops[] = { + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_IP6_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv6_conntrack_in, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_IP6_PRE_ROUTING, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_conntrack_local, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_IP6_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK, + }, + { + .hook = ipv6_defrag, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_IP6_LOCAL_OUT, + .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, + }, + { + .hook = ipv6_confirm, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_IP6_POST_ROUTING, + .priority = NF_IP6_PRI_LAST, + }, + { + .hook = ipv6_confirm, + .owner = THIS_MODULE, + .pf = PF_INET6, + .hooknum = NF_IP6_LOCAL_IN, + .priority = NF_IP6_PRI_LAST-1, + }, }; #ifdef CONFIG_SYSCTL @@ -470,16 +464,21 @@ extern struct nf_conntrack_protocol nf_conntrack_protocol_udp6; extern struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6; extern int nf_ct_frag6_init(void); extern void nf_ct_frag6_cleanup(void); -static int init_or_cleanup(int init) + +MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); + +static int __init nf_conntrack_l3proto_ipv6_init(void) { int ret = 0; - if (!init) goto cleanup; + need_conntrack(); ret = nf_ct_frag6_init(); if (ret < 0) { printk("nf_conntrack_ipv6: can't initialize frag6.\n"); - goto cleanup_nothing; + return ret; } ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_tcp6); if (ret < 0) { @@ -505,71 +504,27 @@ static int init_or_cleanup(int init) goto cleanup_icmpv6; } - ret = nf_register_hook(&ipv6_conntrack_defrag_ops); + ret = nf_register_hooks(ipv6_conntrack_ops, + ARRAY_SIZE(ipv6_conntrack_ops)); if (ret < 0) { printk("nf_conntrack_ipv6: can't register pre-routing defrag " "hook.\n"); goto cleanup_ipv6; } - - ret = nf_register_hook(&ipv6_conntrack_defrag_local_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv6: can't register local_out defrag " - "hook.\n"); - goto cleanup_defragops; - } - - ret = nf_register_hook(&ipv6_conntrack_in_ops); - if (ret < 0) { - printk("nf_conntrack_ipv6: can't register pre-routing hook.\n"); - goto cleanup_defraglocalops; - } - - ret = nf_register_hook(&ipv6_conntrack_local_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv6: can't register local out hook.\n"); - goto cleanup_inops; - } - - ret = nf_register_hook(&ipv6_conntrack_out_ops); - if (ret < 0) { - printk("nf_conntrack_ipv6: can't register post-routing hook.\n"); - goto cleanup_inandlocalops; - } - - ret = nf_register_hook(&ipv6_conntrack_local_in_ops); - if (ret < 0) { - printk("nf_conntrack_ipv6: can't register local in hook.\n"); - goto cleanup_inoutandlocalops; - } - #ifdef CONFIG_SYSCTL nf_ct_ipv6_sysctl_header = register_sysctl_table(nf_ct_net_table, 0); if (nf_ct_ipv6_sysctl_header == NULL) { printk("nf_conntrack: can't register to sysctl.\n"); ret = -ENOMEM; - goto cleanup_localinops; + goto cleanup_hooks; } #endif return ret; - cleanup: - synchronize_net(); #ifdef CONFIG_SYSCTL - unregister_sysctl_table(nf_ct_ipv6_sysctl_header); - cleanup_localinops: + cleanup_hooks: + nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); #endif - nf_unregister_hook(&ipv6_conntrack_local_in_ops); - cleanup_inoutandlocalops: - nf_unregister_hook(&ipv6_conntrack_out_ops); - cleanup_inandlocalops: - nf_unregister_hook(&ipv6_conntrack_local_out_ops); - cleanup_inops: - nf_unregister_hook(&ipv6_conntrack_in_ops); - cleanup_defraglocalops: - nf_unregister_hook(&ipv6_conntrack_defrag_local_out_ops); - cleanup_defragops: - nf_unregister_hook(&ipv6_conntrack_defrag_ops); cleanup_ipv6: nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); cleanup_icmpv6: @@ -580,23 +535,21 @@ static int init_or_cleanup(int init) nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp6); cleanup_frag6: nf_ct_frag6_cleanup(); - cleanup_nothing: return ret; } -MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6)); -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); - -static int __init nf_conntrack_l3proto_ipv6_init(void) -{ - need_conntrack(); - return init_or_cleanup(1); -} - static void __exit nf_conntrack_l3proto_ipv6_fini(void) { - init_or_cleanup(0); + synchronize_net(); +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(nf_ct_ipv6_sysctl_header); +#endif + nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); + nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6); + nf_conntrack_protocol_unregister(&nf_conntrack_protocol_icmpv6); + nf_conntrack_protocol_unregister(&nf_conntrack_protocol_udp6); + nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp6); + nf_ct_frag6_cleanup(); } module_init(nf_conntrack_l3proto_ipv6_init); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 09945c3..86c6703 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -233,21 +233,13 @@ icmpv6_error(struct sk_buff *skb, unsigned int dataoff, return -NF_ACCEPT; } - if (hooknum != NF_IP6_PRE_ROUTING) - goto skipped; - - /* Ignore it if the checksum's bogus. */ - if (csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, - skb->len - dataoff, IPPROTO_ICMPV6, - skb_checksum(skb, dataoff, - skb->len - dataoff, 0))) { + if (hooknum == NF_IP6_PRE_ROUTING && + nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) { nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL, "nf_ct_icmpv6: ICMPv6 checksum failed\n"); return -NF_ACCEPT; } -skipped: - /* is not error message ? */ if (icmp6h->icmp6_type >= 128) return NF_ACCEPT; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c2d3e17..6578c30 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -397,7 +397,7 @@ static int ipip6_rcv(struct sk_buff *skb) return 0; } - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0); + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); kfree_skb(skb); read_unlock(&ipip6_lock); out: diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 5659b52..0ef9a35 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -19,11 +19,13 @@ * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ +#include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> @@ -87,10 +89,16 @@ static int tunnel6_rcv(struct sk_buff **pskb) struct sk_buff *skb = *pskb; struct xfrm6_tunnel *handler; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto drop; + for (handler = tunnel6_handlers; handler; handler = handler->next) if (!handler->handler(skb)) return 0; + icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, skb->dev); + +drop: kfree_skb(skb); return 0; } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 1ceb1a6..8455a32 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -27,6 +27,29 @@ #include "nf_internals.h" +static DEFINE_SPINLOCK(afinfo_lock); + +struct nf_afinfo *nf_afinfo[NPROTO]; +EXPORT_SYMBOL(nf_afinfo); + +int nf_register_afinfo(struct nf_afinfo *afinfo) +{ + spin_lock(&afinfo_lock); + rcu_assign_pointer(nf_afinfo[afinfo->family], afinfo); + spin_unlock(&afinfo_lock); + return 0; +} +EXPORT_SYMBOL_GPL(nf_register_afinfo); + +void nf_unregister_afinfo(struct nf_afinfo *afinfo) +{ + spin_lock(&afinfo_lock); + rcu_assign_pointer(nf_afinfo[afinfo->family], NULL); + spin_unlock(&afinfo_lock); + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(nf_unregister_afinfo); + /* In this code, we can be waiting indefinitely for userspace to * service a packet if a hook returns NF_QUEUE. We could keep a count * of skbuffs queued for userspace, and not deregister a hook unless @@ -63,6 +86,34 @@ void nf_unregister_hook(struct nf_hook_ops *reg) } EXPORT_SYMBOL(nf_unregister_hook); +int nf_register_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + unsigned int i; + int err = 0; + + for (i = 0; i < n; i++) { + err = nf_register_hook(®[i]); + if (err) + goto err; + } + return err; + +err: + if (i > 0) + nf_unregister_hooks(reg, i); + return err; +} +EXPORT_SYMBOL(nf_register_hooks); + +void nf_unregister_hooks(struct nf_hook_ops *reg, unsigned int n) +{ + unsigned int i; + + for (i = 0; i < n; i++) + nf_unregister_hook(®[i]); +} +EXPORT_SYMBOL(nf_unregister_hooks); + unsigned int nf_iterate(struct list_head *head, struct sk_buff **skb, int hook, diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 6492ed6..69899f2 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -799,8 +799,7 @@ static int tcp_error(struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, int pf, - unsigned int hooknum, - int(*csum)(const struct sk_buff *,unsigned int)) + unsigned int hooknum) { struct tcphdr _tcph, *th; unsigned int tcplen = skb->len - dataoff; @@ -830,9 +829,8 @@ static int tcp_error(struct sk_buff *skb, */ /* FIXME: Source route IP option packets --RR */ if (((pf == PF_INET && hooknum == NF_IP_PRE_ROUTING) || - (pf == PF_INET6 && hooknum == NF_IP6_PRE_ROUTING)) - && skb->ip_summed != CHECKSUM_UNNECESSARY - && csum(skb, dataoff)) { + (pf == PF_INET6 && hooknum == NF_IP6_PRE_ROUTING)) && + nf_checksum(skb, hooknum, dataoff, IPPROTO_TCP, pf)) { if (LOG_INVALID(IPPROTO_TCP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: bad TCP checksum "); @@ -851,44 +849,6 @@ static int tcp_error(struct sk_buff *skb, return NF_ACCEPT; } -static int csum4(const struct sk_buff *skb, unsigned int dataoff) -{ - return csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr, - skb->len - dataoff, IPPROTO_TCP, - skb->ip_summed == CHECKSUM_HW ? skb->csum - : skb_checksum(skb, dataoff, - skb->len - dataoff, 0)); -} - -static int csum6(const struct sk_buff *skb, unsigned int dataoff) -{ - return csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, - skb->len - dataoff, IPPROTO_TCP, - skb->ip_summed == CHECKSUM_HW - ? csum_sub(skb->csum, - skb_checksum(skb, 0, dataoff, 0)) - : skb_checksum(skb, dataoff, skb->len - dataoff, - 0)); -} - -static int tcp_error4(struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info *ctinfo, - int pf, - unsigned int hooknum) -{ - return tcp_error(skb, dataoff, ctinfo, pf, hooknum, csum4); -} - -static int tcp_error6(struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info *ctinfo, - int pf, - unsigned int hooknum) -{ - return tcp_error(skb, dataoff, ctinfo, pf, hooknum, csum6); -} - /* Returns verdict for packet, or -1 for invalid. */ static int tcp_packet(struct nf_conn *conntrack, const struct sk_buff *skb, @@ -1218,7 +1178,7 @@ struct nf_conntrack_protocol nf_conntrack_protocol_tcp4 = .print_conntrack = tcp_print_conntrack, .packet = tcp_packet, .new = tcp_new, - .error = tcp_error4, + .error = tcp_error, #if defined(CONFIG_NF_CT_NETLINK) || \ defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nfattr = tcp_to_nfattr, @@ -1239,7 +1199,7 @@ struct nf_conntrack_protocol nf_conntrack_protocol_tcp6 = .print_conntrack = tcp_print_conntrack, .packet = tcp_packet, .new = tcp_new, - .error = tcp_error6, + .error = tcp_error, #if defined(CONFIG_NF_CT_NETLINK) || \ defined(CONFIG_NF_CT_NETLINK_MODULE) .to_nfattr = tcp_to_nfattr, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 831d206..d93edbf 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -103,8 +103,7 @@ static int udp_new(struct nf_conn *conntrack, const struct sk_buff *skb, static int udp_error(struct sk_buff *skb, unsigned int dataoff, enum ip_conntrack_info *ctinfo, int pf, - unsigned int hooknum, - int (*csum)(const struct sk_buff *, unsigned int)) + unsigned int hooknum) { unsigned int udplen = skb->len - dataoff; struct udphdr _hdr, *hdr; @@ -136,9 +135,8 @@ static int udp_error(struct sk_buff *skb, unsigned int dataoff, * and moreover root might send raw packets. * FIXME: Source route IP option packets --RR */ if (((pf == PF_INET && hooknum == NF_IP_PRE_ROUTING) || - (pf == PF_INET6 && hooknum == NF_IP6_PRE_ROUTING)) - && skb->ip_summed != CHECKSUM_UNNECESSARY - && csum(skb, dataoff)) { + (pf == PF_INET6 && hooknum == NF_IP6_PRE_ROUTING)) && + nf_checksum(skb, hooknum, dataoff, IPPROTO_UDP, pf)) { if (LOG_INVALID(IPPROTO_UDP)) nf_log_packet(pf, 0, skb, NULL, NULL, NULL, "nf_ct_udp: bad UDP checksum "); @@ -148,44 +146,6 @@ static int udp_error(struct sk_buff *skb, unsigned int dataoff, return NF_ACCEPT; } -static int csum4(const struct sk_buff *skb, unsigned int dataoff) -{ - return csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr, - skb->len - dataoff, IPPROTO_UDP, - skb->ip_summed == CHECKSUM_HW ? skb->csum - : skb_checksum(skb, dataoff, - skb->len - dataoff, 0)); -} - -static int csum6(const struct sk_buff *skb, unsigned int dataoff) -{ - return csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, - skb->len - dataoff, IPPROTO_UDP, - skb->ip_summed == CHECKSUM_HW - ? csum_sub(skb->csum, - skb_checksum(skb, 0, dataoff, 0)) - : skb_checksum(skb, dataoff, skb->len - dataoff, - 0)); -} - -static int udp_error4(struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info *ctinfo, - int pf, - unsigned int hooknum) -{ - return udp_error(skb, dataoff, ctinfo, pf, hooknum, csum4); -} - -static int udp_error6(struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info *ctinfo, - int pf, - unsigned int hooknum) -{ - return udp_error(skb, dataoff, ctinfo, pf, hooknum, csum6); -} - struct nf_conntrack_protocol nf_conntrack_protocol_udp4 = { .l3proto = PF_INET, @@ -197,7 +157,7 @@ struct nf_conntrack_protocol nf_conntrack_protocol_udp4 = .print_conntrack = udp_print_conntrack, .packet = udp_packet, .new = udp_new, - .error = udp_error4, + .error = udp_error, #if defined(CONFIG_NF_CT_NETLINK) || \ defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, @@ -216,7 +176,7 @@ struct nf_conntrack_protocol nf_conntrack_protocol_udp6 = .print_conntrack = udp_print_conntrack, .packet = udp_packet, .new = udp_new, - .error = udp_error6, + .error = udp_error, #if defined(CONFIG_NF_CT_NETLINK) || \ defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index c72aa3c..408960c 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -649,63 +649,6 @@ static ctl_table nf_ct_net_table[] = { EXPORT_SYMBOL(nf_ct_log_invalid); #endif /* CONFIG_SYSCTL */ -static int init_or_cleanup(int init) -{ -#ifdef CONFIG_PROC_FS - struct proc_dir_entry *proc, *proc_exp, *proc_stat; -#endif - int ret = 0; - - if (!init) goto cleanup; - - ret = nf_conntrack_init(); - if (ret < 0) - goto cleanup_nothing; - -#ifdef CONFIG_PROC_FS - proc = proc_net_fops_create("nf_conntrack", 0440, &ct_file_ops); - if (!proc) goto cleanup_init; - - proc_exp = proc_net_fops_create("nf_conntrack_expect", 0440, - &exp_file_ops); - if (!proc_exp) goto cleanup_proc; - - proc_stat = create_proc_entry("nf_conntrack", S_IRUGO, proc_net_stat); - if (!proc_stat) - goto cleanup_proc_exp; - - proc_stat->proc_fops = &ct_cpu_seq_fops; - proc_stat->owner = THIS_MODULE; -#endif -#ifdef CONFIG_SYSCTL - nf_ct_sysctl_header = register_sysctl_table(nf_ct_net_table, 0); - if (nf_ct_sysctl_header == NULL) { - printk("nf_conntrack: can't register to sysctl.\n"); - ret = -ENOMEM; - goto cleanup_proc_stat; - } -#endif - - return ret; - - cleanup: -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(nf_ct_sysctl_header); - cleanup_proc_stat: -#endif -#ifdef CONFIG_PROC_FS - remove_proc_entry("nf_conntrack", proc_net_stat); - cleanup_proc_exp: - proc_net_remove("nf_conntrack_expect"); - cleanup_proc: - proc_net_remove("nf_conntrack"); - cleanup_init: -#endif /* CNFIG_PROC_FS */ - nf_conntrack_cleanup(); - cleanup_nothing: - return ret; -} - int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; @@ -808,12 +751,66 @@ void nf_conntrack_protocol_unregister(struct nf_conntrack_protocol *proto) static int __init nf_conntrack_standalone_init(void) { - return init_or_cleanup(1); +#ifdef CONFIG_PROC_FS + struct proc_dir_entry *proc, *proc_exp, *proc_stat; +#endif + int ret = 0; + + ret = nf_conntrack_init(); + if (ret < 0) + return ret; + +#ifdef CONFIG_PROC_FS + proc = proc_net_fops_create("nf_conntrack", 0440, &ct_file_ops); + if (!proc) goto cleanup_init; + + proc_exp = proc_net_fops_create("nf_conntrack_expect", 0440, + &exp_file_ops); + if (!proc_exp) goto cleanup_proc; + + proc_stat = create_proc_entry("nf_conntrack", S_IRUGO, proc_net_stat); + if (!proc_stat) + goto cleanup_proc_exp; + + proc_stat->proc_fops = &ct_cpu_seq_fops; + proc_stat->owner = THIS_MODULE; +#endif +#ifdef CONFIG_SYSCTL + nf_ct_sysctl_header = register_sysctl_table(nf_ct_net_table, 0); + if (nf_ct_sysctl_header == NULL) { + printk("nf_conntrack: can't register to sysctl.\n"); + ret = -ENOMEM; + goto cleanup_proc_stat; + } +#endif + return ret; + +#ifdef CONFIG_SYSCTL + cleanup_proc_stat: +#endif +#ifdef CONFIG_PROC_FS + remove_proc_entry("nf_conntrack", proc_net_stat); + cleanup_proc_exp: + proc_net_remove("nf_conntrack_expect"); + cleanup_proc: + proc_net_remove("nf_conntrack"); + cleanup_init: +#endif /* CNFIG_PROC_FS */ + nf_conntrack_cleanup(); + return ret; } static void __exit nf_conntrack_standalone_fini(void) { - init_or_cleanup(0); +#ifdef CONFIG_SYSCTL + unregister_sysctl_table(nf_ct_sysctl_header); +#endif +#ifdef CONFIG_PROC_FS + remove_proc_entry("nf_conntrack", proc_net_stat); + proc_net_remove("nf_conntrack_expect"); + proc_net_remove("nf_conntrack"); +#endif /* CNFIG_PROC_FS */ + nf_conntrack_cleanup(); } module_init(nf_conntrack_standalone_init); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index d9f0d7e..ee8f708 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -17,7 +17,6 @@ * for queueing and must reinject all packets it receives, no matter what. */ static struct nf_queue_handler *queue_handler[NPROTO]; -static struct nf_queue_rerouter *queue_rerouter[NPROTO]; static DEFINE_RWLOCK(queue_handler_lock); @@ -59,32 +58,6 @@ int nf_unregister_queue_handler(int pf) } EXPORT_SYMBOL(nf_unregister_queue_handler); -int nf_register_queue_rerouter(int pf, struct nf_queue_rerouter *rer) -{ - if (pf >= NPROTO) - return -EINVAL; - - write_lock_bh(&queue_handler_lock); - rcu_assign_pointer(queue_rerouter[pf], rer); - write_unlock_bh(&queue_handler_lock); - - return 0; -} -EXPORT_SYMBOL_GPL(nf_register_queue_rerouter); - -int nf_unregister_queue_rerouter(int pf) -{ - if (pf >= NPROTO) - return -EINVAL; - - write_lock_bh(&queue_handler_lock); - rcu_assign_pointer(queue_rerouter[pf], NULL); - write_unlock_bh(&queue_handler_lock); - synchronize_rcu(); - return 0; -} -EXPORT_SYMBOL_GPL(nf_unregister_queue_rerouter); - void nf_unregister_queue_handlers(struct nf_queue_handler *qh) { int pf; @@ -116,7 +89,7 @@ int nf_queue(struct sk_buff **skb, struct net_device *physindev = NULL; struct net_device *physoutdev = NULL; #endif - struct nf_queue_rerouter *rerouter; + struct nf_afinfo *afinfo; /* QUEUE == DROP if noone is waiting, to be safe. */ read_lock(&queue_handler_lock); @@ -126,7 +99,14 @@ int nf_queue(struct sk_buff **skb, return 1; } - info = kmalloc(sizeof(*info)+queue_rerouter[pf]->rer_size, GFP_ATOMIC); + afinfo = nf_get_afinfo(pf); + if (!afinfo) { + read_unlock(&queue_handler_lock); + kfree_skb(*skb); + return 1; + } + + info = kmalloc(sizeof(*info) + afinfo->route_key_size, GFP_ATOMIC); if (!info) { if (net_ratelimit()) printk(KERN_ERR "OOM queueing packet %p\n", @@ -158,10 +138,7 @@ int nf_queue(struct sk_buff **skb, if (physoutdev) dev_hold(physoutdev); } #endif - rerouter = rcu_dereference(queue_rerouter[pf]); - if (rerouter) - rerouter->save(*skb, info); - + afinfo->saveroute(*skb, info); status = queue_handler[pf]->outfn(*skb, info, queuenum, queue_handler[pf]->data); @@ -190,7 +167,7 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info, { struct list_head *elem = &info->elem->list; struct list_head *i; - struct nf_queue_rerouter *rerouter; + struct nf_afinfo *afinfo; rcu_read_lock(); @@ -228,8 +205,8 @@ void nf_reinject(struct sk_buff *skb, struct nf_info *info, } if (verdict == NF_ACCEPT) { - rerouter = rcu_dereference(queue_rerouter[info->pf]); - if (rerouter && rerouter->reroute(&skb, info) < 0) + afinfo = nf_get_afinfo(info->pf); + if (!afinfo || afinfo->reroute(&skb, info) < 0) verdict = NF_DROP; } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3e3f544..c60273c 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1033,17 +1033,13 @@ static struct file_operations nful_file_ops = { #endif /* PROC_FS */ -static int -init_or_cleanup(int init) +static int __init nfnetlink_log_init(void) { int i, status = -ENOMEM; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_nful; #endif - if (!init) - goto cleanup; - for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&instance_table[i]); @@ -1066,30 +1062,25 @@ init_or_cleanup(int init) goto cleanup_subsys; proc_nful->proc_fops = &nful_file_ops; #endif - return status; -cleanup: - nf_log_unregister_logger(&nfulnl_logger); #ifdef CONFIG_PROC_FS - remove_proc_entry("nfnetlink_log", proc_net_netfilter); cleanup_subsys: -#endif nfnetlink_subsys_unregister(&nfulnl_subsys); +#endif cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); return status; } -static int __init nfnetlink_log_init(void) -{ - - return init_or_cleanup(1); -} - static void __exit nfnetlink_log_fini(void) { - init_or_cleanup(0); + nf_log_unregister_logger(&nfulnl_logger); +#ifdef CONFIG_PROC_FS + remove_proc_entry("nfnetlink_log", proc_net_netfilter); +#endif + nfnetlink_subsys_unregister(&nfulnl_subsys); + netlink_unregister_notifier(&nfulnl_rtnl_notifier); } MODULE_DESCRIPTION("netfilter userspace logging"); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index d0e62f6..86a4ac3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1071,17 +1071,13 @@ static struct file_operations nfqnl_file_ops = { #endif /* PROC_FS */ -static int -init_or_cleanup(int init) +static int __init nfnetlink_queue_init(void) { int i, status = -ENOMEM; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_nfqueue; #endif - if (!init) - goto cleanup; - for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&instance_table[i]); @@ -1101,31 +1097,26 @@ init_or_cleanup(int init) #endif register_netdevice_notifier(&nfqnl_dev_notifier); - return status; -cleanup: - nf_unregister_queue_handlers(&nfqh); - unregister_netdevice_notifier(&nfqnl_dev_notifier); #ifdef CONFIG_PROC_FS - remove_proc_entry("nfnetlink_queue", proc_net_netfilter); cleanup_subsys: -#endif nfnetlink_subsys_unregister(&nfqnl_subsys); +#endif cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); return status; } -static int __init nfnetlink_queue_init(void) -{ - - return init_or_cleanup(1); -} - static void __exit nfnetlink_queue_fini(void) { - init_or_cleanup(0); + nf_unregister_queue_handlers(&nfqh); + unregister_netdevice_notifier(&nfqnl_dev_notifier); +#ifdef CONFIG_PROC_FS + remove_proc_entry("nfnetlink_queue", proc_net_netfilter); +#endif + nfnetlink_subsys_unregister(&nfqnl_subsys); + netlink_unregister_notifier(&nfqnl_rtnl_notifier); } MODULE_DESCRIPTION("netfilter packet queue handler"); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index fa877f8..24c348f 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -66,7 +66,7 @@ static __inline__ struct tcf_police * tcf_police_lookup(u32 index) } #ifdef CONFIG_NET_CLS_ACT -static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, +static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb, int type, struct tc_action *a) { struct tcf_police *p; @@ -113,7 +113,7 @@ rtattr_failure: } static inline int -tcf_hash_search(struct tc_action *a, u32 index) +tcf_act_police_hash_search(struct tc_action *a, u32 index) { struct tcf_police *p = tcf_police_lookup(index); @@ -387,9 +387,9 @@ static struct tc_action_ops act_police_ops = { .act = tcf_act_police, .dump = tcf_act_police_dump, .cleanup = tcf_act_police_cleanup, - .lookup = tcf_hash_search, + .lookup = tcf_act_police_hash_search, .init = tcf_act_police_locate, - .walk = tcf_generic_walker + .walk = tcf_act_police_walker }; static int __init diff --git a/security/keys/key.c b/security/keys/key.c index a057e33..b6061fa 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -785,6 +785,10 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref, key_check(keyring); + key_ref = ERR_PTR(-ENOTDIR); + if (keyring->type != &key_type_keyring) + goto error_2; + down_write(&keyring->sem); /* if we're going to allocate a new key, we're going to have diff --git a/security/keys/keyring.c b/security/keys/keyring.c index d65a180..bffa924 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -437,6 +437,7 @@ EXPORT_SYMBOL(keyring_search); /* * search the given keyring only (no recursion) * - keyring must be locked by caller + * - caller must guarantee that the keyring is a keyring */ key_ref_t __keyring_search_one(key_ref_t keyring_ref, const struct key_type *ktype, diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index dfab6c8..abe99d8 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -281,7 +281,7 @@ u32 selinux_socket_getpeer_dgram(struct sk_buff *skb) int i; for (i = sp->len-1; i >= 0; i--) { - struct xfrm_state *x = sp->x[i].xvec; + struct xfrm_state *x = sp->xvec[i]; if (selinux_authorizable_xfrm(x)) { struct xfrm_sec_ctx *ctx = x->security; return ctx->ctx_sid; @@ -314,7 +314,7 @@ int selinux_xfrm_sock_rcv_skb(u32 isec_sid, struct sk_buff *skb) * Only need to verify the existence of an authorizable sp. */ for (i = 0; i < sp->len; i++) { - struct xfrm_state *x = sp->x[i].xvec; + struct xfrm_state *x = sp->xvec[i]; if (x && selinux_authorizable_xfrm(x)) goto accept; |
